1
0
mirror of synced 2026-04-10 23:29:36 +00:00

initial checkin for misc files

unicode tables
This commit is contained in:
Larry Masinter
2020-08-29 18:26:03 -07:00
parent 758c289cef
commit feaf0a556f
117 changed files with 568137 additions and 0 deletions

20
unicode/README.txt Normal file
View File

@@ -0,0 +1,20 @@
This Unicode directory contains mapping files extracted from the CDROM that came with the Unicode 3.0 book (2000).
The Xerox subdirectory contains mappings from the Xerox character encoding (version XC1-3-3-0, 1887) into Unicode 3.0. standard into Unicode. That is the version of XCCS corresponding to the fonts in the Medley system. The Xerox mappings did not come from the Unicode CDROM, they were constructed by combining and constrasting information from a binary file (xerox>XCCStoUni) of unknown provenance with code mappings scraped from the Wikipedia page https://en.wikipedia.org/wiki/Xerox_Character_Code_Standard in July 2020. Both sources were errorful and incomplete, so many of the mappings were hand corrected. There are still missing mappings, and there still may be errors.
EASTASIA:
CJK cross reference mappings for standards such as KSC5601,
GB2312, JIS0208, etc. to Unicode 2.0.
ISO8859:
These are the mapping tables of the ISO 8859 series (1 through 9)
VENDORS:
Miscellaneous mapping tables for small codesets, typically provided
by vendors.
TCVN:
Chu Nom mapping & database.
Always consult www.unicode.org for updates and changes to these files.

277
unicode/WINLATIN2-UNICODE Normal file
View File

@@ -0,0 +1,277 @@
#
# Name: cp1250_WinLatin2 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1250_WinLatin2 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1250_WinLatin2 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 #UNDEFINED
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 #UNDEFINED
0x89 0x2030 #PER MILLE SIGN
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON
0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON
0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADE MARK SIGN
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE
0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON
0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON
0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x02C7 #CARON
0xA2 0x02D8 #BREVE
0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC #UNDEFINED
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x02DB #OGONEK
0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE
0xB4 0x00B4 #ACUTE ACCENT
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #CEDILLA
0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK
0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON
0xBD 0x02DD #DOUBLE ACUTE ACCENT
0xBE 0x013E #LATIN SMALL LETTER L WITH CARON
0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON
0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON
0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE
0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x011B #LATIN SMALL LETTER E WITH CARON
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x010F #LATIN SMALL LETTER D WITH CARON
0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON
0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
0xFF 0x02D9 #DOT ABOVE


21318
unicode/eastasia/cjkxref.txt Normal file

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,202 @@
#
# Name: JIS X 0201 (1976) to Unicode 1.1 Table
# Unicode version: 1.1
# Table version: 0.9
# Table format: Format A
# Date: 8 March 1994
# Authors: Glenn Adams <glenn@metis.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1994 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# single-byte JIS X 0201 characters map into Unicode 1.1
# (ISO/IEC 10646:1-1993 UCS-2).
#
# Format: Three tab-separated columns
# Column #1 is the shift JIS code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode (ISO 10646) name (follows a comment sign)
#
# The entries are in JIS order
#
# These mappings are provisional, pending definition of
# official mappings by Japanese standards bodies.
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x00A5 # YEN SIGN
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x203E # OVERLINE
0xA1 0xFF61 # HALFWIDTH IDEOGRAPHIC FULL STOP
0xA2 0xFF62 # HALFWIDTH LEFT CORNER BRACKET
0xA3 0xFF63 # HALFWIDTH RIGHT CORNER BRACKET
0xA4 0xFF64 # HALFWIDTH IDEOGRAPHIC COMMA
0xA5 0xFF65 # HALFWIDTH KATAKANA MIDDLE DOT
0xA6 0xFF66 # HALFWIDTH KATAKANA LETTER WO
0xA7 0xFF67 # HALFWIDTH KATAKANA LETTER SMALL A
0xA8 0xFF68 # HALFWIDTH KATAKANA LETTER SMALL I
0xA9 0xFF69 # HALFWIDTH KATAKANA LETTER SMALL U
0xAA 0xFF6A # HALFWIDTH KATAKANA LETTER SMALL E
0xAB 0xFF6B # HALFWIDTH KATAKANA LETTER SMALL O
0xAC 0xFF6C # HALFWIDTH KATAKANA LETTER SMALL YA
0xAD 0xFF6D # HALFWIDTH KATAKANA LETTER SMALL YU
0xAE 0xFF6E # HALFWIDTH KATAKANA LETTER SMALL YO
0xAF 0xFF6F # HALFWIDTH KATAKANA LETTER SMALL TU
0xB0 0xFF70 # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
0xB1 0xFF71 # HALFWIDTH KATAKANA LETTER A
0xB2 0xFF72 # HALFWIDTH KATAKANA LETTER I
0xB3 0xFF73 # HALFWIDTH KATAKANA LETTER U
0xB4 0xFF74 # HALFWIDTH KATAKANA LETTER E
0xB5 0xFF75 # HALFWIDTH KATAKANA LETTER O
0xB6 0xFF76 # HALFWIDTH KATAKANA LETTER KA
0xB7 0xFF77 # HALFWIDTH KATAKANA LETTER KI
0xB8 0xFF78 # HALFWIDTH KATAKANA LETTER KU
0xB9 0xFF79 # HALFWIDTH KATAKANA LETTER KE
0xBA 0xFF7A # HALFWIDTH KATAKANA LETTER KO
0xBB 0xFF7B # HALFWIDTH KATAKANA LETTER SA
0xBC 0xFF7C # HALFWIDTH KATAKANA LETTER SI
0xBD 0xFF7D # HALFWIDTH KATAKANA LETTER SU
0xBE 0xFF7E # HALFWIDTH KATAKANA LETTER SE
0xBF 0xFF7F # HALFWIDTH KATAKANA LETTER SO
0xC0 0xFF80 # HALFWIDTH KATAKANA LETTER TA
0xC1 0xFF81 # HALFWIDTH KATAKANA LETTER TI
0xC2 0xFF82 # HALFWIDTH KATAKANA LETTER TU
0xC3 0xFF83 # HALFWIDTH KATAKANA LETTER TE
0xC4 0xFF84 # HALFWIDTH KATAKANA LETTER TO
0xC5 0xFF85 # HALFWIDTH KATAKANA LETTER NA
0xC6 0xFF86 # HALFWIDTH KATAKANA LETTER NI
0xC7 0xFF87 # HALFWIDTH KATAKANA LETTER NU
0xC8 0xFF88 # HALFWIDTH KATAKANA LETTER NE
0xC9 0xFF89 # HALFWIDTH KATAKANA LETTER NO
0xCA 0xFF8A # HALFWIDTH KATAKANA LETTER HA
0xCB 0xFF8B # HALFWIDTH KATAKANA LETTER HI
0xCC 0xFF8C # HALFWIDTH KATAKANA LETTER HU
0xCD 0xFF8D # HALFWIDTH KATAKANA LETTER HE
0xCE 0xFF8E # HALFWIDTH KATAKANA LETTER HO
0xCF 0xFF8F # HALFWIDTH KATAKANA LETTER MA
0xD0 0xFF90 # HALFWIDTH KATAKANA LETTER MI
0xD1 0xFF91 # HALFWIDTH KATAKANA LETTER MU
0xD2 0xFF92 # HALFWIDTH KATAKANA LETTER ME
0xD3 0xFF93 # HALFWIDTH KATAKANA LETTER MO
0xD4 0xFF94 # HALFWIDTH KATAKANA LETTER YA
0xD5 0xFF95 # HALFWIDTH KATAKANA LETTER YU
0xD6 0xFF96 # HALFWIDTH KATAKANA LETTER YO
0xD7 0xFF97 # HALFWIDTH KATAKANA LETTER RA
0xD8 0xFF98 # HALFWIDTH KATAKANA LETTER RI
0xD9 0xFF99 # HALFWIDTH KATAKANA LETTER RU
0xDA 0xFF9A # HALFWIDTH KATAKANA LETTER RE
0xDB 0xFF9B # HALFWIDTH KATAKANA LETTER RO
0xDC 0xFF9C # HALFWIDTH KATAKANA LETTER WA
0xDD 0xFF9D # HALFWIDTH KATAKANA LETTER N
0xDE 0xFF9E # HALFWIDTH KATAKANA VOICED SOUND MARK
0xDF 0xFF9F # HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,31 @@
"TCVN-NSCII Stack 1.0" README
--------------------
The accompanying file TCV-SEA.HQX is a BinHex'd
self-extracting archive of a Macintosh HyperCard 2.1 stack. After
retrieving the file, convert it from BinHex with any of the popular Mac
archiving utilities (such as CompactPro or Stuffit), and execute the
resulting application to extract the stack.
The stack consists of 2357 cards (about 1.2Meg), which correspond to
the Nom proper characters documented in the new 16-bit Vietnamese
national character standard TCVN-5773:1993 (NSCII - Nom Standard Code
for Information Interchange) for the Vietnamese Han-based Nom script.
TCVN-5773 adopts the ISO 10646-1:1993 (UCS) BMP as its base, and
defines 1775 additional Nom characters extracted from "Tu dien chu Nom"
["Nom Dictionary"] by Nguyen Quang Xy and Vu Van Kinh (Saigon, 1971).
Each card in the stack shows the Nom glyph, the corresponding Quoc ngu
(Latin) spelling, and character codes. The code value of any Nom proper
character already defined in ISO 10646/Unicode is prefixed with "U+",
otherwise "V+" is used; further cross-references to other CJKV code
standards are displayed where available. The Latin spelling is encoded
in 8-bit TCVN-5712:1993 (VSCII).
------------------------------------------------------------------------
* This file is provided as-is by Unicode, Inc (The Unicode Consortium).
No claims are made as to fitness for any particular purpose. No
warranties of any kind are expressed or implied. The recipient agrees
to determine applicability of information provided.

File diff suppressed because it is too large Load Diff

330353
unicode/eastasia/unihan.txt Normal file

File diff suppressed because it is too large Load Diff

230
unicode/iso8859/8859-1.txt Normal file
View File

@@ -0,0 +1,230 @@
#
# Name: ISO 8859-1 (1987) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-1 (1987) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-1 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-1 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x00A1 # INVERTED EXCLAMATION MARK
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x00A5 # YEN SIGN
0xA6 0x00A6 # BROKEN BAR
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x00AA # FEMININE ORDINAL INDICATOR
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC # NOT SIGN
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x00AE # REGISTERED SIGN
0xAF 0x00AF # MACRON
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x00B2 # SUPERSCRIPT TWO
0xB3 0x00B3 # SUPERSCRIPT THREE
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x00B5 # MICRO SIGN
0xB6 0x00B6 # PILCROW SIGN
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x00B8 # CEDILLA
0xB9 0x00B9 # SUPERSCRIPT ONE
0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
0xBD 0x00BD # VULGAR FRACTION ONE HALF
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
0xBF 0x00BF # INVERTED QUESTION MARK
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 # MULTIPLICATION SIGN
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 # LATIN SMALL LETTER AE
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 # DIVISION SIGN
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS

230
unicode/iso8859/8859-2.txt Normal file
View File

@@ -0,0 +1,230 @@
#
# Name: ISO 8859-2 (1987) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-2 (1987) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-2 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-2 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
0xA2 0x02D8 # BREVE
0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON
0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON
0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
0xB2 0x02DB # OGONEK
0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x013E # LATIN SMALL LETTER L WITH CARON
0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE
0xB7 0x02C7 # CARON
0xB8 0x00B8 # CEDILLA
0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON
0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE
0xBD 0x02DD # DOUBLE ACUTE ACCENT
0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE
0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 # MULTIPLICATION SIGN
0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON
0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x013A # LATIN SMALL LETTER L WITH ACUTE
0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x011B # LATIN SMALL LETTER E WITH CARON
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x010F # LATIN SMALL LETTER D WITH CARON
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 # DIVISION SIGN
0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON
0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x0163 # LATIN SMALL LETTER T WITH CEDILLA
0xFF 0x02D9 # DOT ABOVE

223
unicode/iso8859/8859-3.txt Normal file
View File

@@ -0,0 +1,223 @@
#
# Name: ISO 8859-3 (1988) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-3 (1988) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-3 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-3 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE
0xA2 0x02D8 # BREVE
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A4 # CURRENCY SIGN
0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE
0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
0xAD 0x00AD # SOFT HYPHEN
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE
0xB2 0x00B2 # SUPERSCRIPT TWO
0xB3 0x00B3 # SUPERSCRIPT THREE
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x00B5 # MICRO SIGN
0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x00B8 # CEDILLA
0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I
0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE
0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX
0xBD 0x00BD # VULGAR FRACTION ONE HALF
0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 # MULTIPLICATION SIGN
0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE
0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 # DIVISION SIGN
0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE
0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX
0xFF 0x02D9 # DOT ABOVE

230
unicode/iso8859/8859-4.txt Normal file
View File

@@ -0,0 +1,230 @@
#
# Name: ISO 8859-4 (1988) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-4 (1988) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-4 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-4 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
0xA2 0x0138 # LATIN SMALL LETTER KRA
0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xAF 0x00AF # MACRON
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
0xB2 0x02DB # OGONEK
0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA
0xB7 0x02C7 # CARON
0xB8 0x00B8 # CEDILLA
0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON
0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE
0xBD 0x014A # LATIN CAPITAL LETTER ENG
0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
0xBF 0x014B # LATIN SMALL LETTER ENG
0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 # MULTIPLICATION SIGN
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 # LATIN SMALL LETTER AE
0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 # DIVISION SIGN
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x0169 # LATIN SMALL LETTER U WITH TILDE
0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON
0xFF 0x02D9 # DOT ABOVE

230
unicode/iso8859/8859-5.txt Normal file
View File

@@ -0,0 +1,230 @@
#
# Name: ISO 8859-5 (1988) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-5 (1988) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-5 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-5 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO
0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE
0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE
0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE
0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI
0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE
0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE
0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE
0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE
0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U
0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE
0xB0 0x0410 # CYRILLIC CAPITAL LETTER A
0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE
0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE
0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE
0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE
0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE
0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE
0xB8 0x0418 # CYRILLIC CAPITAL LETTER I
0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
0xBA 0x041A # CYRILLIC CAPITAL LETTER KA
0xBB 0x041B # CYRILLIC CAPITAL LETTER EL
0xBC 0x041C # CYRILLIC CAPITAL LETTER EM
0xBD 0x041D # CYRILLIC CAPITAL LETTER EN
0xBE 0x041E # CYRILLIC CAPITAL LETTER O
0xBF 0x041F # CYRILLIC CAPITAL LETTER PE
0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER
0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES
0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE
0xC3 0x0423 # CYRILLIC CAPITAL LETTER U
0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF
0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA
0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE
0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE
0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA
0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU
0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
0xCD 0x042D # CYRILLIC CAPITAL LETTER E
0xCE 0x042E # CYRILLIC CAPITAL LETTER YU
0xCF 0x042F # CYRILLIC CAPITAL LETTER YA
0xD0 0x0430 # CYRILLIC SMALL LETTER A
0xD1 0x0431 # CYRILLIC SMALL LETTER BE
0xD2 0x0432 # CYRILLIC SMALL LETTER VE
0xD3 0x0433 # CYRILLIC SMALL LETTER GHE
0xD4 0x0434 # CYRILLIC SMALL LETTER DE
0xD5 0x0435 # CYRILLIC SMALL LETTER IE
0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
0xD7 0x0437 # CYRILLIC SMALL LETTER ZE
0xD8 0x0438 # CYRILLIC SMALL LETTER I
0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I
0xDA 0x043A # CYRILLIC SMALL LETTER KA
0xDB 0x043B # CYRILLIC SMALL LETTER EL
0xDC 0x043C # CYRILLIC SMALL LETTER EM
0xDD 0x043D # CYRILLIC SMALL LETTER EN
0xDE 0x043E # CYRILLIC SMALL LETTER O
0xDF 0x043F # CYRILLIC SMALL LETTER PE
0xE0 0x0440 # CYRILLIC SMALL LETTER ER
0xE1 0x0441 # CYRILLIC SMALL LETTER ES
0xE2 0x0442 # CYRILLIC SMALL LETTER TE
0xE3 0x0443 # CYRILLIC SMALL LETTER U
0xE4 0x0444 # CYRILLIC SMALL LETTER EF
0xE5 0x0445 # CYRILLIC SMALL LETTER HA
0xE6 0x0446 # CYRILLIC SMALL LETTER TSE
0xE7 0x0447 # CYRILLIC SMALL LETTER CHE
0xE8 0x0448 # CYRILLIC SMALL LETTER SHA
0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA
0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN
0xEB 0x044B # CYRILLIC SMALL LETTER YERU
0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
0xED 0x044D # CYRILLIC SMALL LETTER E
0xEE 0x044E # CYRILLIC SMALL LETTER YU
0xEF 0x044F # CYRILLIC SMALL LETTER YA
0xF0 0x2116 # NUMERO SIGN
0xF1 0x0451 # CYRILLIC SMALL LETTER IO
0xF2 0x0452 # CYRILLIC SMALL LETTER DJE
0xF3 0x0453 # CYRILLIC SMALL LETTER GJE
0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
0xF5 0x0455 # CYRILLIC SMALL LETTER DZE
0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0xF7 0x0457 # CYRILLIC SMALL LETTER YI
0xF8 0x0458 # CYRILLIC SMALL LETTER JE
0xF9 0x0459 # CYRILLIC SMALL LETTER LJE
0xFA 0x045A # CYRILLIC SMALL LETTER NJE
0xFB 0x045B # CYRILLIC SMALL LETTER TSHE
0xFC 0x045C # CYRILLIC SMALL LETTER KJE
0xFD 0x00A7 # SECTION SIGN
0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U
0xFF 0x045F # CYRILLIC SMALL LETTER DZHE

185
unicode/iso8859/8859-6.txt Normal file
View File

@@ -0,0 +1,185 @@
#
# Name: ISO 8859-6 (1987) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-6 (1987) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-6 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-6 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0660 # ARABIC-INDIC DIGIT ZERO
0x31 0x0661 # ARABIC-INDIC DIGIT ONE
0x32 0x0662 # ARABIC-INDIC DIGIT TWO
0x33 0x0663 # ARABIC-INDIC DIGIT THREE
0x34 0x0664 # ARABIC-INDIC DIGIT FOUR
0x35 0x0665 # ARABIC-INDIC DIGIT FIVE
0x36 0x0666 # ARABIC-INDIC DIGIT SIX
0x37 0x0667 # ARABIC-INDIC DIGIT SEVEN
0x38 0x0668 # ARABIC-INDIC DIGIT EIGHT
0x39 0x0669 # ARABIC-INDIC DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA4 0x00A4 # CURRENCY SIGN
0xAC 0x060C # ARABIC COMMA
0xAD 0x00AD # SOFT HYPHEN
0xBB 0x061B # ARABIC SEMICOLON
0xBF 0x061F # ARABIC QUESTION MARK
0xC1 0x0621 # ARABIC LETTER HAMZA
0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE
0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE
0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE
0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW
0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE
0xC7 0x0627 # ARABIC LETTER ALEF
0xC8 0x0628 # ARABIC LETTER BEH
0xC9 0x0629 # ARABIC LETTER TEH MARBUTA
0xCA 0x062A # ARABIC LETTER TEH
0xCB 0x062B # ARABIC LETTER THEH
0xCC 0x062C # ARABIC LETTER JEEM
0xCD 0x062D # ARABIC LETTER HAH
0xCE 0x062E # ARABIC LETTER KHAH
0xCF 0x062F # ARABIC LETTER DAL
0xD0 0x0630 # ARABIC LETTER THAL
0xD1 0x0631 # ARABIC LETTER REH
0xD2 0x0632 # ARABIC LETTER ZAIN
0xD3 0x0633 # ARABIC LETTER SEEN
0xD4 0x0634 # ARABIC LETTER SHEEN
0xD5 0x0635 # ARABIC LETTER SAD
0xD6 0x0636 # ARABIC LETTER DAD
0xD7 0x0637 # ARABIC LETTER TAH
0xD8 0x0638 # ARABIC LETTER ZAH
0xD9 0x0639 # ARABIC LETTER AIN
0xDA 0x063A # ARABIC LETTER GHAIN
0xE0 0x0640 # ARABIC TATWEEL
0xE1 0x0641 # ARABIC LETTER FEH
0xE2 0x0642 # ARABIC LETTER QAF
0xE3 0x0643 # ARABIC LETTER KAF
0xE4 0x0644 # ARABIC LETTER LAM
0xE5 0x0645 # ARABIC LETTER MEEM
0xE6 0x0646 # ARABIC LETTER NOON
0xE7 0x0647 # ARABIC LETTER HEH
0xE8 0x0648 # ARABIC LETTER WAW
0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA
0xEA 0x064A # ARABIC LETTER YEH
0xEB 0x064B # ARABIC FATHATAN
0xEC 0x064C # ARABIC DAMMATAN
0xED 0x064D # ARABIC KASRATAN
0xEE 0x064E # ARABIC FATHA
0xEF 0x064F # ARABIC DAMMA
0xF0 0x0650 # ARABIC KASRA
0xF1 0x0651 # ARABIC SHADDA
0xF2 0x0652 # ARABIC SUKUN

224
unicode/iso8859/8859-7.txt Normal file
View File

@@ -0,0 +1,224 @@
#
# Name: ISO 8859-7 (1987) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-7 (1987) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-7 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-7 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x02BD # MODIFIER LETTER REVERSED COMMA
0xA2 0x02BC # MODIFIER LETTER APOSTROPHE
0xA3 0x00A3 # POUND SIGN
0xA6 0x00A6 # BROKEN BAR
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x00A9 # COPYRIGHT SIGN
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC # NOT SIGN
0xAD 0x00AD # SOFT HYPHEN
0xAF 0x2015 # HORIZONTAL BAR
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x00B2 # SUPERSCRIPT TWO
0xB3 0x00B3 # SUPERSCRIPT THREE
0xB4 0x0384 # GREEK TONOS
0xB5 0x0385 # GREEK DIALYTIKA TONOS
0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS
0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS
0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS
0xBD 0x00BD # VULGAR FRACTION ONE HALF
0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS
0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS
0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA
0xC2 0x0392 # GREEK CAPITAL LETTER BETA
0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA
0xC4 0x0394 # GREEK CAPITAL LETTER DELTA
0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON
0xC6 0x0396 # GREEK CAPITAL LETTER ZETA
0xC7 0x0397 # GREEK CAPITAL LETTER ETA
0xC8 0x0398 # GREEK CAPITAL LETTER THETA
0xC9 0x0399 # GREEK CAPITAL LETTER IOTA
0xCA 0x039A # GREEK CAPITAL LETTER KAPPA
0xCB 0x039B # GREEK CAPITAL LETTER LAMDA
0xCC 0x039C # GREEK CAPITAL LETTER MU
0xCD 0x039D # GREEK CAPITAL LETTER NU
0xCE 0x039E # GREEK CAPITAL LETTER XI
0xCF 0x039F # GREEK CAPITAL LETTER OMICRON
0xD0 0x03A0 # GREEK CAPITAL LETTER PI
0xD1 0x03A1 # GREEK CAPITAL LETTER RHO
0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA
0xD4 0x03A4 # GREEK CAPITAL LETTER TAU
0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON
0xD6 0x03A6 # GREEK CAPITAL LETTER PHI
0xD7 0x03A7 # GREEK CAPITAL LETTER CHI
0xD8 0x03A8 # GREEK CAPITAL LETTER PSI
0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA
0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS
0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS
0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS
0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS
0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xE1 0x03B1 # GREEK SMALL LETTER ALPHA
0xE2 0x03B2 # GREEK SMALL LETTER BETA
0xE3 0x03B3 # GREEK SMALL LETTER GAMMA
0xE4 0x03B4 # GREEK SMALL LETTER DELTA
0xE5 0x03B5 # GREEK SMALL LETTER EPSILON
0xE6 0x03B6 # GREEK SMALL LETTER ZETA
0xE7 0x03B7 # GREEK SMALL LETTER ETA
0xE8 0x03B8 # GREEK SMALL LETTER THETA
0xE9 0x03B9 # GREEK SMALL LETTER IOTA
0xEA 0x03BA # GREEK SMALL LETTER KAPPA
0xEB 0x03BB # GREEK SMALL LETTER LAMDA
0xEC 0x03BC # GREEK SMALL LETTER MU
0xED 0x03BD # GREEK SMALL LETTER NU
0xEE 0x03BE # GREEK SMALL LETTER XI
0xEF 0x03BF # GREEK SMALL LETTER OMICRON
0xF0 0x03C0 # GREEK SMALL LETTER PI
0xF1 0x03C1 # GREEK SMALL LETTER RHO
0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA
0xF3 0x03C3 # GREEK SMALL LETTER SIGMA
0xF4 0x03C4 # GREEK SMALL LETTER TAU
0xF5 0x03C5 # GREEK SMALL LETTER UPSILON
0xF6 0x03C6 # GREEK SMALL LETTER PHI
0xF7 0x03C7 # GREEK SMALL LETTER CHI
0xF8 0x03C8 # GREEK SMALL LETTER PSI
0xF9 0x03C9 # GREEK SMALL LETTER OMEGA
0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS
0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS
0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS

192
unicode/iso8859/8859-8.txt Normal file
View File

@@ -0,0 +1,192 @@
#
# Name: ISO 8859-8 (1988) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-8 (1988) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-8 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-8 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x00A5 # YEN SIGN
0xA6 0x00A6 # BROKEN BAR
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x00D7 # MULTIPLICATION SIGN
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC # NOT SIGN
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x00AE # REGISTERED SIGN
0xAF 0x203E # OVERLINE
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x00B2 # SUPERSCRIPT TWO
0xB3 0x00B3 # SUPERSCRIPT THREE
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x00B5 # MICRO SIGN
0xB6 0x00B6 # PILCROW SIGN
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x00B8 # CEDILLA
0xB9 0x00B9 # SUPERSCRIPT ONE
0xBA 0x00F7 # DIVISION SIGN
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
0xBD 0x00BD # VULGAR FRACTION ONE HALF
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
0xDF 0x2017 # DOUBLE LOW LINE
0xE0 0x05D0 # HEBREW LETTER ALEF
0xE1 0x05D1 # HEBREW LETTER BET
0xE2 0x05D2 # HEBREW LETTER GIMEL
0xE3 0x05D3 # HEBREW LETTER DALET
0xE4 0x05D4 # HEBREW LETTER HE
0xE5 0x05D5 # HEBREW LETTER VAV
0xE6 0x05D6 # HEBREW LETTER ZAYIN
0xE7 0x05D7 # HEBREW LETTER HET
0xE8 0x05D8 # HEBREW LETTER TET
0xE9 0x05D9 # HEBREW LETTER YOD
0xEA 0x05DA # HEBREW LETTER FINAL KAF
0xEB 0x05DB # HEBREW LETTER KAF
0xEC 0x05DC # HEBREW LETTER LAMED
0xED 0x05DD # HEBREW LETTER FINAL MEM
0xEE 0x05DE # HEBREW LETTER MEM
0xEF 0x05DF # HEBREW LETTER FINAL NUN
0xF0 0x05E0 # HEBREW LETTER NUN
0xF1 0x05E1 # HEBREW LETTER SAMEKH
0xF2 0x05E2 # HEBREW LETTER AYIN
0xF3 0x05E3 # HEBREW LETTER FINAL PE
0xF4 0x05E4 # HEBREW LETTER PE
0xF5 0x05E5 # HEBREW LETTER FINAL TSADI
0xF6 0x05E6 # HEBREW LETTER TSADI
0xF7 0x05E7 # HEBREW LETTER QOF
0xF8 0x05E8 # HEBREW LETTER RESH
0xF9 0x05E9 # HEBREW LETTER SHIN
0xFA 0x05EA # HEBREW LETTER TAV

232
unicode/iso8859/8859-9.txt Normal file
View File

@@ -0,0 +1,232 @@
#
# Name: ISO 8859-9 (1989) to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 16 January 1995
# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO 8859-9 (1989) characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO 8859-9 code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
#
# The entries are in ISO 8859-9 order
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x00A1 # INVERTED EXCLAMATION MARK
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x00A5 # YEN SIGN
0xA6 0x00A6 # BROKEN BAR
0xA7 0x00A7 # SECTION SIGN
0xA8 0x00A8 # DIAERESIS
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x00AA # FEMININE ORDINAL INDICATOR
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC # NOT SIGN
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x00AE # REGISTERED SIGN
0xAF 0x00AF # MACRON
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x00B2 # SUPERSCRIPT TWO
0xB3 0x00B3 # SUPERSCRIPT THREE
0xB4 0x00B4 # ACUTE ACCENT
0xB5 0x00B5 # MICRO SIGN
0xB6 0x00B6 # PILCROW SIGN
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x00B8 # CEDILLA
0xB9 0x00B9 # SUPERSCRIPT ONE
0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
0xBD 0x00BD # VULGAR FRACTION ONE HALF
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
0xBF 0x00BF # INVERTED QUESTION MARK
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 # MULTIPLICATION SIGN
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 # LATIN SMALL LETTER AE
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 # DIVISION SIGN
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x0131 # LATIN SMALL LETTER DOTLESS I
0xFE 0x015F # LATIN SMALL LETTER S WITH CEDILLA
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS

View File

@@ -0,0 +1,6 @@
8859 to Unicode mapping tables.
These tables are believed to be substantially correct in their
mappings. However, the names in the comment fields (after "#"
on each line of the file) have not been updated since Unicode
Version 1.0.
May 2, 1996.

View File

@@ -0,0 +1,980 @@
DISCLAIMER, May 1, 1996: This file is obsolete. It was made
for Unicode Version 1.0, and has neither been updated nor
verified for use with any subsequent version of the standard.
Use this data entirely at your own risk.
== == == == == == == == == == == == == == == == == == == == ==
Copyright 1991-1992 Unicode, Inc.
All Rights reserved.
This file is provided as-is by Unicode, Inc. (The Unicode Consortium). No
claims are made as to fitness for any particular purpose. No warranties of
any kind are expressed or implied. The recipient agrees to determine
applicability of information provided. If this file has been provided on
magnetic media by Unicode, Inc., the sole remedy for any claim will be
exchange of defective media within 90 days of receipt.
Unicode Encoding, Version 1.0 to ISO 8879 (SGML) & ISO DIS 6862.2 Mappings
ISO 8879-1986 contains an ASCII-alphabetic encoding of a large number
of "character entities" used as identifiers in SGML (Standard Graphic
Markup Language). The following table maps Unicode character encodings
to the entity reference names of those character entities which clearly
constitute characters in the sense used by the Unicode standard.
However, SGML also contains many identifiers for character entities
which are glyph variants or stylistic variants which do not have
one-to-one mappings with Unicode characters.
ISO/DIS 6862.2 contains two 7-bit character encodings of mathematical
symbols of various types. The first encoding (set G0) is identified by
numbers beginning with a digit 0 in the table below, for example, 07.13,
while the second encoding (set G1) is identified by numbers beginning
with a digit 1 in the table below, for example, 17.13. The other digits
are to be interpreted as decimal values corresponding to regular ISO
conventions for citing the position of characters in code tables; 17.13
can thus be interpreted as position 7/13 in the code table for set G1.
UNIC 6862.2 SGML Unicode character name
0021 excl EXCLAMATION MARK
0023 num NUMBER SIGN
0024 dollar DOLLAR SIGN
0025 percnt PERCENT SIGN
0026 amp AMPERSAND
0027 quot APOSTROPHE-QUOTE
0028 lpar OPENING PARENTHESIS
0029 rpar CLOSING PARENTHESIS
002A ast ASTERISK
002B 05.00 plus PLUS SIGN
002C comma COMMA
002D hyphen HYPHEN-MINUS
002E period PERIOD
002F sol SLASH
003A colon COLON
003B semi SEMICOLON
003C lt LESS-THAN SIGN
003D equals EQUALS SIGN
003E gt GREATER-THAN SIGN
003F quest QUESTION MARK
0040 commat COMMERCIAL AT
005B lsqb OPENING SQUARE BRACKET
005C bsol BACKSLASH
005D rsqb CLOSING SQUARE BRACKET
005E circ SPACING CIRCUMFLEX
005F lowbar SPACING UNDERSCORE
0060 grave SPACING GRAVE
007B lcub OPENING CURLY BRACKET
007C verbar VERTICAL BAR
007D rcub CLOSING CURLY BRACKET
007E tilde TILDE
00A0 nbsp NON-BREAKING SPACE
00A1 iexcl INVERTED EXCLAMATION MARK
00A2 cent CENT SIGN
00A3 pound POUND SIGN
00A4 curren CURRENCY SIGN
00A5 yen YEN SIGN
00A6 brvbar BROKEN VERTICAL BAR
00A7 sect SECTION SIGN
00A8 die,Dot SPACING DIAERESIS
00A8 uml SPACING DIAERESIS
00A9 copy COPYRIGHT SIGN
00AA ordf FEMININE ORDINAL INDICATOR
00AB laquo LEFT POINTING GUILLEMET
00AC 07.05 not NOT SIGN
00AD shy SOFT HYPHEN
00AE reg REGISTERED TRADE MARK SIGN
00AF macr SPACING MACRON
00B0 03.12 deg DEGREE SIGN
00B1 03.01 plusmn PLUS-OR-MINUS SIGN
00B2 sup2 SUPERSCRIPT DIGIT TWO
00B3 sup3 SUPERSCRIPT DIGIT THREE
00B4 acute SPACING ACUTE
00B5 micro MICRO SIGN
00B6 para PARAGRAPH SIGN
00B7 middot MIDDLE DOT
00B8 cedil SPACING CEDILLA
00B9 sup1 SUPERSCRIPT DIGIT ONE
00BA ordm MASCULINE ORDINAL INDICATOR
00BB raquo RIGHT POINTING GUILLEMET
00BC frac14 FRACTION ONE QUARTER
00BD frac12 FRACTION ONE HALF
00BE frac34 FRACTION THREE QUARTERS
00BF iquest INVERTED QUESTION MARK
00C0 Agrave LATIN CAPITAL LETTER A GRAVE
00C1 Aacute LATIN CAPITAL LETTER A ACUTE
00C2 Acirc LATIN CAPITAL LETTER A CIRCUMFLEX
00C3 Atilde LATIN CAPITAL LETTER A TILDE
00C4 Auml LATIN CAPITAL LETTER A DIAERESIS
00C5 Aring LATIN CAPITAL LETTER A RING
00C6 AElig LATIN CAPITAL LETTER A E
00C7 Ccedil LATIN CAPITAL LETTER C CEDILLA
00C8 Egrave LATIN CAPITAL LETTER E GRAVE
00C9 Eacute LATIN CAPITAL LETTER E ACUTE
00CA Ecirc LATIN CAPITAL LETTER E CIRCUMFLEX
00CB Euml LATIN CAPITAL LETTER E DIAERESIS
00CC Igrave LATIN CAPITAL LETTER I GRAVE
00CD Iacute LATIN CAPITAL LETTER I ACUTE
00CE Icirc LATIN CAPITAL LETTER I CIRCUMFLEX
00CF Iuml LATIN CAPITAL LETTER I DIAERESIS
00D0 ETH LATIN CAPITAL LETTER ETH
00D1 Ntilde LATIN CAPITAL LETTER N TILDE
00D2 Ograve LATIN CAPITAL LETTER O GRAVE
00D3 Oacute LATIN CAPITAL LETTER O ACUTE
00D4 Ocirc LATIN CAPITAL LETTER O CIRCUMFLEX
00D5 Otilde LATIN CAPITAL LETTER O TILDE
00D6 Ouml LATIN CAPITAL LETTER O DIAERESIS
00D7 03.00 times MULTIPLICATION SIGN
00D8 Oslash LATIN CAPITAL LETTER O SLASH
00D9 Ugrave LATIN CAPITAL LETTER U GRAVE
00DA Uacute LATIN CAPITAL LETTER U ACUTE
00DB Ucirc LATIN CAPITAL LETTER U CIRCUMFLEX
00DC Uuml LATIN CAPITAL LETTER U DIAERESIS
00DD Yacute LATIN CAPITAL LETTER Y ACUTE
00DE THORN LATIN CAPITAL LETTER THORN
00DF szlig LATIN SMALL LETTER SHARP S
00E0 agrave LATIN SMALL LETTER A GRAVE
00E1 aacute LATIN SMALL LETTER A ACUTE
00E2 acirc LATIN SMALL LETTER A CIRCUMFLEX
00E3 atilde LATIN SMALL LETTER A TILDE
00E4 auml LATIN SMALL LETTER A DIAERESIS
00E5 aring LATIN SMALL LETTER A RING
00E6 aelig LATIN SMALL LETTER A E
00E7 ccedil LATIN SMALL LETTER C CEDILLA
00E8 egrave LATIN SMALL LETTER E GRAVE
00E9 eacute LATIN SMALL LETTER E ACUTE
00EA ecirc LATIN SMALL LETTER E CIRCUMFLEX
00EB euml LATIN SMALL LETTER E DIAERESIS
00EC igrave LATIN SMALL LETTER I GRAVE
00ED iacute LATIN SMALL LETTER I ACUTE
00EE icirc LATIN SMALL LETTER I CIRCUMFLEX
00EF iuml LATIN SMALL LETTER I DIAERESIS
00F0 eth LATIN SMALL LETTER ETH
00F1 ntilde LATIN SMALL LETTER N TILDE
00F2 ograve LATIN SMALL LETTER O GRAVE
00F3 oacute LATIN SMALL LETTER O ACUTE
00F4 ocirc LATIN SMALL LETTER O CIRCUMFLEX
00F5 otilde LATIN SMALL LETTER O TILDE
00F6 ouml LATIN SMALL LETTER O DIAERESIS
00F7 04.00 divide DIVISION SIGN
00F8 oslash LATIN SMALL LETTER O SLASH
00F9 ugrave LATIN SMALL LETTER U GRAVE
00FA uacute LATIN SMALL LETTER U ACUTE
00FB ucirc LATIN SMALL LETTER U CIRCUMFLEX
00FC uuml LATIN SMALL LETTER U DIAERESIS
00FD yacute LATIN SMALL LETTER Y ACUTE
00FE thorn LATIN SMALL LETTER THORN
00FF yuml LATIN SMALL LETTER Y DIAERESIS
0100 Amacr LATIN CAPITAL LETTER A MACRON
0101 amacr LATIN SMALL LETTER A MACRON
0102 Abreve LATIN CAPITAL LETTER A BREVE
0103 abreve LATIN SMALL LETTER A BREVE
0104 Aogon LATIN CAPITAL LETTER A OGONEK
0105 aogon LATIN SMALL LETTER A OGONEK
0106 Cacute LATIN CAPITAL LETTER C ACUTE
0107 cacute LATIN SMALL LETTER C ACUTE
0108 Ccirc LATIN CAPITAL LETTER C CIRCUMFLEX
0109 ccirc LATIN SMALL LETTER C CIRCUMFLEX
010A Cdot LATIN CAPITAL LETTER C DOT
010B cdot LATIN SMALL LETTER C DOT
010C Ccaron LATIN CAPITAL LETTER C HACEK
010D ccaron LATIN SMALL LETTER C HACEK
010E Dcaron LATIN CAPITAL LETTER D HACEK
010F dcaron LATIN SMALL LETTER D HACEK
0110 Dstrok LATIN CAPITAL LETTER D BAR
0111 dstrok LATIN SMALL LETTER D BAR
0112 Emacr LATIN CAPITAL LETTER E MACRON
0113 emacr LATIN SMALL LETTER E MACRON
0116 Edot LATIN CAPITAL LETTER E DOT
0117 edot LATIN SMALL LETTER E DOT
0118 Eogon LATIN CAPITAL LETTER E OGONEK
0119 eogon LATIN SMALL LETTER E OGONEK
011A Ecaron LATIN CAPITAL LETTER E HACEK
011B ecaron LATIN SMALL LETTER E HACEK
011C Gcirc LATIN CAPITAL LETTER G CIRCUMFLEX
011D gcirc LATIN SMALL LETTER G CIRCUMFLEX
011E Gbreve LATIN CAPITAL LETTER G BREVE
011F gbreve LATIN SMALL LETTER G BREVE
0120 Gdot LATIN CAPITAL LETTER G DOT
0121 gdot LATIN SMALL LETTER G DOT
0122 Gcedil LATIN CAPITAL LETTER G CEDILLA
0123 gcedil LATIN SMALL LETTER G CEDILLA
0124 Hcirc LATIN CAPITAL LETTER H CIRCUMFLEX
0125 hcirc LATIN SMALL LETTER H CIRCUMFLEX
0126 Hstrok LATIN CAPITAL LETTER H BAR
0127 hstrok LATIN SMALL LETTER H BAR
0128 Itilde LATIN CAPITAL LETTER I TILDE
0129 itilde LATIN SMALL LETTER I TILDE
012A Imacr LATIN CAPITAL LETTER I MACRON
012B imacr LATIN SMALL LETTER I MACRON
012E Iogon LATIN CAPITAL LETTER I OGONEK
012F iogon LATIN SMALL LETTER I OGONEK
0130 Idot LATIN CAPITAL LETTER I DOT
0131 inodot LATIN SMALL LETTER DOTLESS I
0132 IJlig LATIN CAPITAL LETTER I J
0133 ijlig LATIN SMALL LETTER I J
0134 Jcirc LATIN CAPITAL LETTER J CIRCUMFLEX
0135 jcirc LATIN SMALL LETTER J CIRCUMFLEX
0136 Kcedil LATIN CAPITAL LETTER K CEDILLA
0137 kcedil LATIN SMALL LETTER K CEDILLA
0138 kgreen LATIN SMALL LETTER KRA
0139 Lacute LATIN CAPITAL LETTER L ACUTE
013A lacute LATIN SMALL LETTER L ACUTE
013B Lcedil LATIN CAPITAL LETTER L CEDILLA
013C lcedil LATIN SMALL LETTER L CEDILLA
013D Lcaron LATIN CAPITAL LETTER L HACEK
013E lcaron LATIN SMALL LETTER L HACEK
013F Lmidot LATIN CAPITAL LETTER L WITH MIDDLE DOT
0140 lmidot LATIN SMALL LETTER L WITH MIDDLE DOT
0141 Lstrok LATIN CAPITAL LETTER L SLASH
0142 lstrok LATIN SMALL LETTER L SLASH
0143 Nacute LATIN CAPITAL LETTER N ACUTE
0144 nacute LATIN SMALL LETTER N ACUTE
0145 Ncedil LATIN CAPITAL LETTER N CEDILLA
0146 ncedil LATIN SMALL LETTER N CEDILLA
0147 Ncaron LATIN CAPITAL LETTER N HACEK
0148 ncaron LATIN SMALL LETTER N HACEK
0149 napos LATIN SMALL LETTER APOSTROPHE N
014A ENG LATIN CAPITAL LETTER ENG
014B eng LATIN SMALL LETTER ENG
014C Omacr LATIN CAPITAL LETTER O MACRON
014D omacr LATIN SMALL LETTER O MACRON
0150 Odblac LATIN CAPITAL LETTER O DOUBLE ACUTE
0151 odblac LATIN SMALL LETTER O DOUBLE ACUTE
0152 OElig LATIN CAPITAL LETTER O E
0153 oelig LATIN SMALL LETTER O E
0154 Racute LATIN CAPITAL LETTER R ACUTE
0155 racute LATIN SMALL LETTER R ACUTE
0156 Rcedil LATIN CAPITAL LETTER R CEDILLA
0157 rcedil LATIN SMALL LETTER R CEDILLA
0158 Rcaron LATIN CAPITAL LETTER R HACEK
0159 rcaron LATIN SMALL LETTER R HACEK
015A Sacute LATIN CAPITAL LETTER S ACUTE
015B sacute LATIN SMALL LETTER S ACUTE
015C Scirc LATIN CAPITAL LETTER S CIRCUMFLEX
015D scirc LATIN SMALL LETTER S CIRCUMFLEX
015E Scedil LATIN CAPITAL LETTER S CEDILLA
015F scedil LATIN SMALL LETTER S CEDILLA
0160 Scaron LATIN CAPITAL LETTER S HACEK
0161 scaron LATIN SMALL LETTER S HACEK
0162 Tcedil LATIN CAPITAL LETTER T CEDILLA
0163 tcedil LATIN SMALL LETTER T CEDILLA
0164 Tcaron LATIN CAPITAL LETTER T HACEK
0165 tcaron LATIN SMALL LETTER T HACEK
0166 Tstrok LATIN CAPITAL LETTER T BAR
0167 tstrok LATIN SMALL LETTER T BAR
0168 Utilde LATIN CAPITAL LETTER U TILDE
0169 utilde LATIN SMALL LETTER U TILDE
016A Umacr LATIN CAPITAL LETTER U MACRON
016B umacr LATIN SMALL LETTER U MACRON
016C Ubreve LATIN CAPITAL LETTER U BREVE
016D ubreve LATIN SMALL LETTER U BREVE
016E Uring LATIN CAPITAL LETTER U RING
016F uring LATIN SMALL LETTER U RING
0170 Udblac LATIN CAPITAL LETTER U DOUBLE ACUTE
0171 udblac LATIN SMALL LETTER U DOUBLE ACUTE
0172 Uogon LATIN CAPITAL LETTER U OGONEK
0173 uogon LATIN SMALL LETTER U OGONEK
0174 Wcirc LATIN CAPITAL LETTER W CIRCUMFLEX
0175 wcirc LATIN SMALL LETTER W CIRCUMFLEX
0176 Ycirc LATIN CAPITAL LETTER Y CIRCUMFLEX
0177 ycirc LATIN SMALL LETTER Y CIRCUMFLEX
0178 Yuml LATIN CAPITAL LETTER Y DIAERESIS
0179 Zacute LATIN CAPITAL LETTER Z ACUTE
017A zacute LATIN SMALL LETTER Z ACUTE
017B Zdot LATIN CAPITAL LETTER Z DOT
017C zdot LATIN SMALL LETTER Z DOT
017D Zcaron LATIN CAPITAL LETTER Z HACEK
017E zcaron LATIN SMALL LETTER Z HACEK
0192 fnof LATIN SMALL LETTER SCRIPT F
02BC apos MODIFIER LETTER APOSTROPHE
02C7 caron MODIFIER LETTER HACEK
02D8 breve SPACING BREVE
02D9 dot SPACING DOT ABOVE
02DA ring SPACING RING ABOVE
02DB ogon SPACING OGONEK
02DC tilde SPACING TILDE
02DD dblac SPACING DOUBLE ACUTE
0302 02.12 NON-SPACING CIRCUMFLEX
0307 02.09 NON-SPACING DOT ABOVE
0308 02.10 NON-SPACING DIAERESIS
030C 02.13 NON-SPACING HACEK
0336 02.04 NON-SPACING LONG BAR OVERLAY
0338 02.01 NON-SPACING LONG SLASH OVERLAY
0386 Aacgr GREEK CAPITAL LETTER ALPHA TONOS
0388 Eacgr GREEK CAPITAL LETTER EPSILON TONOS
0389 EEacgr GREEK CAPITAL LETTER ETA TONOS
038A Iacgr GREEK CAPITAL LETTER IOTA TONOS
038C Oacgr GREEK CAPITAL LETTER OMICRON TONOS
038E Uacgr GREEK CAPITAL LETTER UPSILON TONOS
038F OHacgr GREEK CAPITAL LETTER OMEGA TONOS
0390 idiagr GREEK SMALL LETTER IOTA DIAERESIS TONOS
0391 Agr GREEK CAPITAL LETTER ALPHA
0392 Bgr GREEK CAPITAL LETTER BETA
0393 Ggr,Gamma GREEK CAPITAL LETTER GAMMA
0394 Dgr,Delta GREEK CAPITAL LETTER DELTA
0395 Egr GREEK CAPITAL LETTER EPSILON
0396 Zgr GREEK CAPITAL LETTER ZETA
0397 EEgr GREEK CAPITAL LETTER ETA
0398 THgr,Theta GREEK CAPITAL LETTER THETA
0399 Igr GREEK CAPITAL LETTER IOTA
039A Kgr GREEK CAPITAL LETTER KAPPA
039B Lgr,Lambda GREEK CAPITAL LETTER LAMBDA
039C Mgr GREEK CAPITAL LETTER MU
039D Ngr GREEK CAPITAL LETTER NU
039E Xgr,Xi GREEK CAPITAL LETTER XI
039F Ogr GREEK CAPITAL LETTER OMICRON
03A0 Pgr,Pi GREEK CAPITAL LETTER PI
03A1 Rgr GREEK CAPITAL LETTER RHO
03A3 Sgr,Sigma GREEK CAPITAL LETTER SIGMA
03A4 Tgr GREEK CAPITAL LETTER TAU
03A5 Ugr,Upsi GREEK CAPITAL LETTER UPSILON
03A6 PHgr,Phi GREEK CAPITAL LETTER PHI
03A7 KHgr GREEK CAPITAL LETTER CHI
03A8 PSgr,Psi GREEK CAPITAL LETTER PSI
03A9 OHgr,Omega GREEK CAPITAL LETTER OMEGA
03AA Idigr GREEK CAPITAL LETTER IOTA DIAERESIS
03AB Udigr GREEK CAPITAL LETTER UPSILON DIAERESIS
03AC aacgr GREEK SMALL LETTER ALPHA TONOS
03AD eacgr GREEK SMALL LETTER EPSILON TONOS
03AE eeacgr GREEK SMALL LETTER ETA TONOS
03AF iacgr GREEK SMALL LETTER IOTA TONOS
03B0 udiagr GREEK SMALL LETTER UPSILON DIAERESIS TONOS
03B1 agr,alpha GREEK SMALL LETTER ALPHA
03B2 bgr,beta GREEK SMALL LETTER BETA
03B3 ggr,gamma GREEK SMALL LETTER GAMMA
03B4 dgr,delta GREEK SMALL LETTER DELTA
03B5 egr,epsi GREEK SMALL LETTER EPSILON
03B6 zgr,zeta GREEK SMALL LETTER ZETA
03B7 eegr,eta GREEK SMALL LETTER ETA
03B8 thetas GREEK SMALL LETTER THETA
03B8 thgr GREEK SMALL LETTER THETA
03B9 igr,iota GREEK SMALL LETTER IOTA
03BA kgr,kappa GREEK SMALL LETTER KAPPA
03BB lgr,lambda GREEK SMALL LETTER LAMBDA
03BC mgr,mu GREEK SMALL LETTER MU
03BD ngr,nu GREEK SMALL LETTER NU
03BE xgr,xi GREEK SMALL LETTER XI
03BF ogr GREEK SMALL LETTER OMICRON
03C0 pgr,pi GREEK SMALL LETTER PI
03C1 rgr,rho GREEK SMALL LETTER RHO
03C2 sfgr,sigmav GREEK SMALL LETTER FINAL SIGMA
03C3 sgr,sigma GREEK SMALL LETTER SIGMA
03C4 tgr,tau GREEK SMALL LETTER TAU
03C5 ugr,upsi GREEK SMALL LETTER UPSILON
03C6 phgr,phis GREEK SMALL LETTER PHI
03C7 khgr,chi GREEK SMALL LETTER CHI
03C8 psgr,psi GREEK SMALL LETTER PSI
03C9 ohgr,omega GREEK SMALL LETTER OMEGA
03CA idigr GREEK SMALL LETTER IOTA DIAERESIS
03CB udigr GREEK SMALL LETTER UPSILON DIAERESIS
03CC oacgr GREEK SMALL LETTER OMICRON TONOS
03CD uacgr GREEK SMALL LETTER UPSILON TONOS
03CE ohacgr GREEK SMALL LETTER OMEGA TONOS
03D1 thetav GREEK SMALL LETTER SCRIPT THETA
03D5 phiv GREEK SMALL LETTER SCRIPT PHI
03D6 piv GREEK SMALL LETTER OMEGA PI
03DD gammad GREEK SMALL LETTER DIGAMMA
03F0 kappav GREEK SMALL LETTER SCRIPT KAPPA
03F1 rhov GREEK SMALL LETTER TAILED RHO
0401 IOcy CYRILLIC CAPITAL LETTER IO
0402 DJcy CYRILLIC CAPITAL LETTER DJE
0403 GJcy CYRILLIC CAPITAL LETTER GJE
0404 Jukcy CYRILLIC CAPITAL LETTER E
0405 DScy CYRILLIC CAPITAL LETTER DZE
0406 Iukcy CYRILLIC CAPITAL LETTER I
0407 YIcy CYRILLIC CAPITAL LETTER YI
0408 Jsercy CYRILLIC CAPITAL LETTER JE
0409 LJcy CYRILLIC CAPITAL LETTER LJE
040A NJcy CYRILLIC CAPITAL LETTER NJE
040B TSHcy CYRILLIC CAPITAL LETTER TSHE
040C KJcy CYRILLIC CAPITAL LETTER KJE
040E Ubrcy CYRILLIC CAPITAL LETTER SHORT U
040F DZcy CYRILLIC CAPITAL LETTER DZHE
0410 Acy CYRILLIC CAPITAL LETTER A
0411 Bcy CYRILLIC CAPITAL LETTER BE
0412 Vcy CYRILLIC CAPITAL LETTER VE
0413 Gcy CYRILLIC CAPITAL LETTER GE
0414 dcy CYRILLIC CAPITAL LETTER DE
0415 IEcy CYRILLIC CAPITAL LETTER IE
0416 ZHcy CYRILLIC CAPITAL LETTER ZHE
0417 Zcy CYRILLIC CAPITAL LETTER ZE
0418 Icy CYRILLIC CAPITAL LETTER II
0419 Jcy CYRILLIC CAPITAL LETTER SHORT II
041A Kcy CYRILLIC CAPITAL LETTER KA
041B Lcy CYRILLIC CAPITAL LETTER EL
041C Mcy CYRILLIC CAPITAL LETTER EM
041D Ncy CYRILLIC CAPITAL LETTER EN
041E Ocy CYRILLIC CAPITAL LETTER O
041F Pcy CYRILLIC CAPITAL LETTER PE
0420 Rcy CYRILLIC CAPITAL LETTER ER
0421 Scy CYRILLIC CAPITAL LETTER ES
0422 Tcy CYRILLIC CAPITAL LETTER TE
0423 Ucy CYRILLIC CAPITAL LETTER U
0424 Fcy CYRILLIC CAPITAL LETTER EF
0425 KHcy CYRILLIC CAPITAL LETTER KHA
0426 TScy CYRILLIC CAPITAL LETTER TSE
0427 CHcy CYRILLIC CAPITAL LETTER CHE
0428 SHcy CYRILLIC CAPITAL LETTER SHA
0429 SHCHcy CYRILLIC CAPITAL LETTER SHCHA
042A HARDcy CYRILLIC CAPITAL LETTER HARD SIGN
042B Ycy CYRILLIC CAPITAL LETTER YERI
042C SOFTcy CYRILLIC CAPITAL LETTER SOFT SIGN
042D Ecy CYRILLIC CAPITAL LETTER REVERSED E
042E YUcy CYRILLIC CAPITAL LETTER IU
042F YAcy CYRILLIC CAPITAL LETTER IA
0430 acy CYRILLIC SMALL LETTER A
0431 bcy CYRILLIC SMALL LETTER BE
0432 vcy CYRILLIC SMALL LETTER VE
0433 gcy CYRILLIC SMALL LETTER GE
0434 dcy CYRILLIC SMALL LETTER DE
0435 iecy CYRILLIC SMALL LETTER IE
0436 zhcy CYRILLIC SMALL LETTER ZHE
0437 zcy CYRILLIC SMALL LETTER ZE
0438 icy CYRILLIC SMALL LETTER II
0439 jcy CYRILLIC SMALL LETTER SHORT II
043A kcy CYRILLIC SMALL LETTER KA
043B lcy CYRILLIC SMALL LETTER EL
043C mcy CYRILLIC SMALL LETTER EM
043D ncy CYRILLIC SMALL LETTER EN
043E ocy CYRILLIC SMALL LETTER O
043F pcy CYRILLIC SMALL LETTER PE
0440 rcy CYRILLIC SMALL LETTER ER
0441 scy CYRILLIC SMALL LETTER ES
0442 tcy CYRILLIC SMALL LETTER TE
0443 ucy CYRILLIC SMALL LETTER U
0444 fcy CYRILLIC SMALL LETTER EF
0445 khcy CYRILLIC SMALL LETTER KHA
0446 tscy CYRILLIC SMALL LETTER TSE
0447 chcy CYRILLIC SMALL LETTER CHE
0448 shcy CYRILLIC SMALL LETTER SHA
0449 shchcy CYRILLIC SMALL LETTER SHCHA
044A hardcy CYRILLIC SMALL LETTER HARD SIGN
044B ycy CYRILLIC SMALL LETTER YERI
044C softcy CYRILLIC SMALL LETTER SOFT SIGN
044D ecy CYRILLIC SMALL LETTER REVERSED E
044E yucy CYRILLIC SMALL LETTER IU
044F yacy CYRILLIC SMALL LETTER IA
0451 iocy CYRILLIC SMALL LETTER IO
0452 djcy CYRILLIC SMALL LETTER DJE
0453 gjcy CYRILLIC SMALL LETTER GJE
0454 jukcy CYRILLIC SMALL LETTER E
0455 dscy CYRILLIC SMALL LETTER DZE
0456 iukcy CYRILLIC SMALL LETTER I
0457 yicy CYRILLIC SMALL LETTER YI
0458 jsercy CYRILLIC SMALL LETTER JE
0459 ljcy CYRILLIC SMALL LETTER LJE
045A njcy CYRILLIC SMALL LETTER NJE
045B tshcy CYRILLIC SMALL LETTER TSHE
045C kjcy CYRILLIC SMALL LETTER KJE
045E ubrcy CYRILLIC SMALL LETTER SHORT U
045F dzcy CYRILLIC SMALL LETTER DZHE
2002 ensp EN SPACE
2003 emsp EM SPACE
2004 emsp13 THREE-PER-EM SPACE
2005 emsp14 FOUR-PER-EM SPACE
2007 numsp FIGURE SPACE
2008 puncsp PUNCTUATION SPACE
2009 thinsp THIN SPACE
200A hairsp HAIR SPACE
2010 dash HYPHEN
2013 ndash EN DASH
2014 mdash EM DASH
2015 horbar QUOTATION DASH
2016 15.00 Verbar DOUBLE VERTICAL BAR
2018 lsquo SINGLE TURNED COMMA QUOTATION MARK
2018 rsquor SINGLE TURNED COMMA QUOTATION MARK
2019 rsquo SINGLE COMMA QUOTATION MARK
201A lsquor LOW SINGLE COMMA QUOTATION MARK
201C ldquo DOUBLE TURNED COMMA QUOTATION MARK
201C rdquor DOUBLE TURNED COMMA QUOTATION MARK
201D rdquo DOUBLE COMMA QUOTATION MARK
201E ldquor LOW DOUBLE COMMA QUOTATION MARK
2020 dagger DAGGER
2021 Dagger DOUBLE DAGGER
2022 bull BULLET
2025 nldr TWO DOT LEADER
2026 hellip HORIZONTAL ELLIPSIS
2026 mldr HORIZONTAL ELLIPSIS
2030 04.12 permil PER MILLE SIGN
2032 07.00 prime PRIME
2032 vprime PRIME
2033 07.01 Prime DOUBLE PRIME
2034 07.02 tprime TRIPLE PRIME
2035 bprime REVERSED PRIME
2041 caret CARET INSERTION POINT
2043 hybull HYPHEN BULLET
20D2 02.02 NON-SPACING LONG VERTICAL BAR OVERLAY
20D3 02.03 NON-SPACING SHORT VERTICAL BAR OVERLAY
20D4 02.08 NON-SPACING ANTICLOCKWISE ARROW ABOVE
20D5 02.15 NON-SPACING CLOCKWISE ARROW ABOVE
20D6 02.11 NON-SPACING LEFT ARROW ABOVE
20D7 02.14 NON-SPACING RIGHT ARROW ABOVE
20D8 02.05 NON-SPACING RING OVERLAY
20D9 02.07 NON-SPACING CLOCKWISE RING OVERLAY
20DA 02.06 NON-SPACING ANTICLOCKWISE RING OVERLAY
20DB tdot NON-SPACING THREE DOTS ABOVE
20DC DotDot NON-SPACING FOUR DOTS ABOVE
2105 incare CARE OF
210B hamilt SCRIPT H
210E 07.06 PLANCK CONSTANT
210F 07.12 planck PLANCK CONSTANT OVER 2 PI
2111 image BLACK-LETTER I
2112 lagran SCRIPT L
2113 ell SCRIPT SMALL L
2116 numero NUMERO
2117 copysr SOUND RECORDING COPYRIGHT
2118 17.13 weierp SCRIPT P
211C real BLACK-LETTER R
211E 17.14 rx PRESCRIPTION TAKE
2122 trade TRADEMARK
2126 ohm OHM
2129 17.12 TURNED GREEK SMALL LETTER IOTA
212B angst ANGSTROM UNIT
212C bernou SCRIPT B
2133 phmmat SCRIPT M
2134 order SCRIPT SMALL O
2135 07.13 aleph FIRST TRANSFINITE CARDINAL
2136 beth SECOND TRANSFINITE CARDINAL
2137 gimel THIRD TRANSFINITE CARDINAL
2138 daleth FOURTH TRANSFINITE CARDINAL
2153 frac13 FRACTION ONE THIRD
2154 frac23 FRACTION TWO THIRDS
2155 frac15 FRACTION ONE FIFTH
2156 frac25 FRACTION TWO FIFTHS
2157 frac35 FRACTION THREE FIFTHS
2158 frac45 FRACTION FOUR FIFTHS
2159 frac16 FRACTION ONE SIXTH
215A frac56 FRACTION FIVE SIXTHS
215B frac18 FRACTION ONE EIGHTH
215C frac38 FRACTION THREE EIGHTHS
215D frac58 FRACTION FIVE EIGHTHS
215E frac78 FRACTION SEVEN EIGHTHS
2190 larr LEFT ARROW
2191 uarr UP ARROW
2192 rarr RIGHT ARROW
2193 darr DOWN ARROW
2194 05.10 harr LEFT RIGHT ARROW
2195 06.10 varr UP DOWN ARROW
2196 15.07 nwarr UPPER LEFT ARROW
2197 16.07 nearr UPPER RIGHT ARROW
2198 16.08 drarr LOWER RIGHT ARROW
2199 15.08 dlarr LOWER LEFT ARROW
219A 17.08 nlarr LEFT ARROW WITH STROKE
219B 15.10 nrarr RIGHT ARROW WITH STROKE
219D rarrw RIGHT WAVE ARROW
219E Larr LEFT TWO HEADED ARROW
21A0 16.10 Rarr RIGHT TWO HEADED ARROW
21A2 larrtl LEFT ARROW WITH TAIL
21A3 rarrtl RIGHT ARROW WITH TAIL
21A6 05.12 map RIGHT ARROW FROM BAR
21A9 16.11 larrhk LEFT ARROW WITH HOOK
21AA 15.11 rarrhk RIGHT ARROW WITH HOOK
21AB larrlp LEFT ARROW WITH LOOP
21AC rarrlp RIGHT ARROW WITH LOOP
21AD harrw LEFT RIGHT WAVE ARROW
21AE nharr LEFT RIGHT ARROW WITH STROKE
21B0 lsh UP ARROW WITH TIP LEFT
21B1 rsh UP ARROW WITH TIP RIGHT
21B6 05.09 cularr ANTICLOCKWISE TOP SEMICIRCLE ARROW
21B7 06.09 curarr CLOCKWISE TOP SEMICIRCLE ARROW
21BA olarr ANTICLOCKWISE OPEN CIRCLE ARROW
21BB orarr CLOCKWISE OPEN CIRCLE ARROW
21BC lharu LEFT HARPOON WITH BARB UP
21BD lhard LEFT HARPOON WITH BARB DOWN
21BE 15.09 uharr UP HARPOON WITH BARB RIGHT
21BF uharl UP HARPOON WITH BARB LEFT
21C0 rharu RIGHT HARPOON WITH BARB UP
21C1 rhard RIGHT HARPOON WITH BARB DOWN
21C2 dharr DOWN HARPOON WITH BARB RIGHT
21C3 dharl DOWN HARPOON WITH BARB LEFT
21C4 06.11 rlarr2 RIGHT ARROW OVER LEFT ARROW
21C5 06.12 UP ARROW LEFT OF DOWN ARROW
21C6 05.11 lrarr2 LEFT ARROW OVER RIGHT ARROW
21C7 larr2 LEFT PAIRED ARROWS
21C8 uarr2 UP PAIRED ARROWS
21C9 rarr2 RIGHT PAIRED ARROWS
21CA darr2 DOWN PAIRED ARROWS
21CB lrhar2 LEFT HARPOON OVER RIGHT HARPOON
21CC rlhar2 RIGHT HARPOON OVER LEFT HARPOON
21CD nlArr LEFT DOUBLE ARROW WITH STROKE
21CE nhArr LEFT RIGHT DOUBLE ARROW WITH STROKE
21CF nrArr RIGHT DOUBLE ARROW WITH STROKE
21D0 05.14 lArr LEFT DOUBLE ARROW
21D1 05.13 uArr UP DOUBLE ARROW
21D2 06.14 rArr RIGHT DOUBLE ARROW
21D3 06.13 dArr DOWN DOUBLE ARROW
21D4 17.10 hArr,iff LEFT RIGHT DOUBLE ARROW
21D5 17.11 vArr UP DOWN DOUBLE ARROW
21DA lAarr LEFT TRIPLE ARROW
21DB rAarr RIGHT TRIPLE ARROW
21DC 17.09 LEFT SQUIGGLE ARROW
21DD 16.09 rarrw RIGHT SQUIGGLE ARROW
2200 05.05 forall FOR ALL
2201 05.06 comp COMPLEMENT
2202 07.11 part PARTIAL DIFFERENTIAL
2203 06.05 exist THERE EXISTS
2204 nexist THERE DOES NOT EXIST
2205 06.06 empty EMPTY SET
2206 03.11 INCREMENT
2207 04.11 nabla NABLA
2208 05.03 isin ELEMENT OF
2209 notin NOT AN ELEMENT OF
220A 15.06 epsis SMALL ELEMENT OF
220B 06.03 ni CONTAINS AS MEMBER
220D 16.06 bepsi SMALL CONTAINS AS MEMBER
220E 16.13 END OF PROOF
220F 04.15 prod N-ARY PRODUCT
2210 coprod N-ARY COPRODUCT
2210 amalg N-ARY COPRODUCT
2210 samalg N-ARY COPRODUCT
2211 03.15 sum N-ARY SUMMATION
2212 06.00 minus MINUS SIGN
2213 04.01 mnplus MINUS-OR-PLUS SIGN
2214 12.12 plusdo DOT PLUS
2216 16.02 setmn SET MINUS
2218 07.14 compfn RING OPERATOR
221A 06.15 radic SQUARE ROOT
221D vprop PROPORTIONAL TO
221D 17.02 prop PROPORTIONAL TO
221E 05.15 infin INFINITY
221F 03.10 ang90 RIGHT ANGLE
2220 04.10 ang ANGLE
2221 angmsd MEASURED ANGLE
2222 16.15 angsph SPHERICAL ANGLE
2223 mid DIVIDES
2224 17.07 nmid DOES NOT DIVIDE
2225 03.09 par PARALLEL TO
2226 17.06 npar NOT PARALLEL TO
2227 07.04 and LOGICAL AND
2228 07.03 or LOGICAL OR
2229 16.04 cap INTERSECTION
222A 15.04 cup UNION
222B 07.08 int INTEGRAL
222C 07.09 DOUBLE INTEGRAL
222D 07.10 TRIPLE INTEGRAL
222E conint CONTOUR INTEGRAL
2234 12.05 there4 THEREFORE
2235 12.06 becaus BECAUSE
2237 14.01 PROPORTION
2238 13.12 DOT MINUS
223A 17.01 GEOMETRIC PROPORTION
223B 12.14 HOMOTHETIC
223C thksim TILDE OPERATOR
223C 03.02 sim TILDE OPERATOR
223D bsim REVERSED TILDE
223E 12.13 INVERTED LAZY S
2240 wreath WREATH PRODUCT
2241 nsim NOT TILDE
2243 04.02 sime ASYMPTOTICALLY EQUAL TO
2244 nsime NOT ASYMPTOTICALLY EQUAL TO
2245 04.03 cong APPROXIMATELY EQUAL TO
2247 ncong NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO
2248 thkap ALMOST EQUAL TO
2248 03.03 ap ALMOST EQUAL TO
2249 nap NOT ALMOST EQUAL TO
224A 14.00 ape ALMOST EQUAL OR EQUAL TO
224C bcong ALL EQUAL TO
224D asymp EQUIVALENT TO
224E 14.04 bump GEOMETRICALLY EQUIVALENT TO
224F 04.04 bumpe DIFFERENCE BETWEEN
2250 14.12 esdot APPROACHES THE LIMIT
2251 eDot GEOMETRICALLY EQUAL TO
2252 17.00 efDot APPROXIMATELY EQUAL TO OR THE IMAGE OF
2253 13.01 erDot IMAGE OF OR APPROXIMATELY EQUAL TO
2254 colone COLON EQUAL
2255 ecolon EQUAL COLON
2256 ecir RING IN EQUAL TO
2257 cire RING EQUAL TO
2259 13.13 wedgeq ESTIMATES
225A 14.13 EQUIANGULAR TO
225C trie DELTA EQUAL TO
2260 13.00 ne NOT EQUAL TO
2261 03.04 equiv IDENTICAL TO
2262 nequiv NOT IDENTICAL TO
2264 03.05 le LESS THAN OR EQUAL TO
2264 les LESS THAN OR EQUAL TO
2265 04.05 ge GREATER THAN OR EQUAL TO
2265 ges GREATER THAN OR EQUAL TO
2266 lE LESS THAN OVER EQUAL TO
2267 gE GREATER THAN OVER EQUAL TO
2268 lnE LESS THAN BUT NOT EQUAL TO
2268 lvnE LESS THAN BUT NOT EQUAL TO
2269 gnE GREATER THAN BUT NOT EQUAL TO
2269 gvnE GREATER THAN BUT NOT EQUAL TO
226A Lt MUCH LESS THAN
226A 03.08 MUCH LESS THAN
226B Gt MUCH GREATER THAN
226B 04.08 MUCH GREATER THAN
226C twixt BETWEEN
226E nlt NOT LESS THAN
226F ngt NOT GREATER THAN
2270 nles NEITHER LESS THAN NOR EQUAL TO
2270 nle NEITHER LESS THAN NOR EQUAL TO
2271 nges NEITHER GREATER THAN NOR EQUAL TO
2271 nge NEITHER GREATER THAN NOR EQUAL TO
2272 03.07 lsim LESS THAN OR EQUIVALENT TO
2273 04.07 gsim GREATER THAN OR EQUIVALENT TO
2276 03.06 lg LESS THAN OR GREATER THAN
2277 04.06 gl GREATER THAN OR LESS THAN
227A 13.10 pr PRECEDES
227B 14.10 sc SUCCEEDS
227C 13.11 cupre PRECEDES OR EQUAL TO
227D 14.11 sccue SUCCEEDS OR EQUAL TO
227E 14.09 prsim PRECEDES OR EQUIVALENT TO
227F 13.09 scsim SUCCEEDS OR EQUIVALENT TO
2280 npr DOES NOT PRECEDE
2281 nsc DOES NOT SUCCEED
2282 05.01 sub SUBSET OF
2282 15.05 SUBSET OF
2283 06.01 sup SUPERSET OF
2283 16.05 SUPERSET OF
2284 nsub NOT A SUBSET OF
2285 nsup NOT A SUPERSET OF
2286 05.02 sube SUBSET OF OR EQUAL TO
2287 06.02 supe SUPERSET OF OR EQUAL TO
2288 nsube NEITHER A SUBSET OF NOR EQUAL TO
2289 nsupe NEITHER A SUPERSET OF NOR EQUAL TO
228A subnE SUBSET OF OR NOT EQUAL TO
228B supnE SUPERSET OF OR NOT EQUAL TO
228E uplus MULTISET UNION
228F 12.07 sqsub SQUARE IMAGE OF
2290 12.08 sqsup SQUARE ORIGINAL OF
2291 sqsube SQUARE IMAGE OF OR EQUAL TO
2292 sqsupe SQUARE ORIGINAL OF OR EQUAL TO
2293 sqcap SQUARE CAP
2294 sqcup SQUARE CUP
2295 12.01 oplus CIRCLED PLUS
2296 12.02 ominus CIRCLED MINUS
2297 12.03 otimes CIRCLED TIMES
2298 osol CIRCLED DIVISION SLASH
2299 12.04 odot CIRCLED DOT OPERATOR
229A ocir CIRCLED RING OPERATOR
229B oast CIRCLED ASTERISK OPERATOR
229D odash CIRCLED DASH
229E plusb SQUARED PLUS
229F minusb SQUARED MINUS
22A0 timesb SQUARED TIMES
22A1 sdotb SQUARED DOT OPERATOR
22A2 07.07 vdash RIGHT TACK
22A3 dashv LEFT TACK
22A4 top DOWN TACK
22A5 bottom UP TACK
22A5 04.09 perp UP TACK
22A6 17.05 ASSERTION
22A7 17.04 models MODELS
22A8 vDash TRUE
22A9 Vdash FORCES
22AA Vvdash TRIPLE VERTICAL BAR RIGHT TURNSTILE
22AC nvdash DOES NOT PROVE
22AD nvDash NOT TRUE
22AE nVdash DOES NOT FORCE
22AF nVDash NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE
22B0 12.15 PRECEDES UNDER RELATION
22B2 13.08 vltri NORMAL SUBGROUP OF
22B3 vrtri CONTAINS AS NORMAL SUBGROUP
22B4 14.08 ltrie NORMAL SUBGROUP OF OR EQUAL TO
22B5 rtrie CONTAINS AS NORMAL SUBGROUP OR EQUAL TO
22B6 12.10 ORIGINAL OF
22B7 12.09 IMAGE OF
22B8 mumap MULTIMAP
22B9 12.11 HERMITIAN CONJUGATE MATRIX
22BA intcal INTERCALATE
22BB veebar XOR
22BC barwed NAND
22C0 16.03 N-ARY LOGICAL AND
22C1 15.03 N-ARY LOGICAL OR
22C2 06.04 N-ARY INTERSECTION
22C3 05.04 N-ARY UNION
22C4 diam DIAMOND OPERATOR
22C5 sdot DOT OPERATOR
22C6 sstarf STAR OPERATOR
22C7 divonx DIVISION TIMES
22C8 bowtie BOWTIE
22C9 ltimes LEFT NORMAL FACTOR SEMIDIRECT PRODUCT
22CA rtimes RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT
22CB lthree LEFT SEMIDIRECT PRODUCT
22CC rthree RIGHT SEMIDIRECT PRODUCT
22CD bsime REVERSED TILDE EQUALS
22CE cuvee CURLY LOGICAL OR
22CF cuwed CURLY LOGICAL AND
22D0 Sub DOUBLE SUBSET
22D1 Sup DOUBLE SUPERSET
22D2 Cap DOUBLE INTERSECTION
22D3 Cup DOUBLE UNION
22D4 fork PITCHFORK
22D6 ldot LESS THAN WITH DOT
22D7 gsdot GREATER THAN WITH DOT
22D8 Ll VERY MUCH LESS THAN
22D9 Gg VERY MUCH GREATER THAN
22DA leg LESS THAN EQUAL TO OR GREATER THAN
22DB gel GREATER THAN EQUAL TO OR LESS THAN
22DC els EQUAL TO OR LESS THAN
22DD egs EQUAL TO OR GREATER THAN
22DE cuepr EQUAL TO OR PRECEDES
22DF cuesc EQUAL TO OR SUCCEEDS
22E0 npre DOES NOT PRECEDE OR EQUAL
22E1 nsce DOES NOT SUCCEED OR EQUAL
22E6 lnsim LESS THAN BUT NOT EQUIVALENT TO
22E7 gnsim GREATER THAN BUT NOT EQUIVALENT TO
22E8 prnsim PRECEDES BUT NOT EQUIVALENT TO
22E9 scnsim SUCCEEDS BUT NOT EQUIVALENT TO
22EA nltri NOT NORMAL SUBGROUP OF
22EB nrtri DOES NOT CONTAIN AS NORMAL SUBGROUP
22EC nltrie NOT NORMAL SUBGROUP OF OR EQUAL TO
22ED nrtrie DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL
22EE 13.04 vellip VERTICAL ELLIPSIS
2306 Barwed PERSPECTIVE
2307 17.03 WAVY LINE
2308 lceil LEFT CEILING
2309 rceil RIGHT CEILING
230A lfloor LEFT FLOOR
230B rfloor RIGHT FLOOR
230C drcrop BOTTOM RIGHT CROP
230D dlcrop BOTTOM LEFT CROP
230E urcrop TOP RIGHT CROP
230F ulcrop TOP LEFT CROP
2315 telrec TELEPHONE RECORDER
2316 target POSITION INDICATOR
231C ulcorn TOP LEFT CORNER
231D urcorn TOP RIGHT CORNER
231E dlcorn BOTTOM LEFT CORNER
231F drcorn BOTTOM RIGHT CORNER
2322 frown FROWN
2323 smile SMILE
2329 03.13 lang BRA
232A 04.13 rang KET
2423 blank OPEN BOX
24C8 oS CIRCLED LATIN CAPITAL LETTER S
2500 boxh FORMS LIGHT HORIZONTAL
2502 boxv FORMS LIGHT VERTICAL
250C boxdr FORMS LIGHT DOWN AND RIGHT
2510 boxdl FORMS LIGHT DOWN AND LEFT
2514 boxur FORMS LIGHT UP AND RIGHT
2518 boxul FORMS LIGHT UP AND LEFT
251C boxvr FORMS LIGHT VERTICAL AND RIGHT
2524 boxvl FORMS LIGHT VERTICAL AND LEFT
252C boxhd FORMS LIGHT DOWN AND HORIZONTAL
2534 boxhu FORMS LIGHT UP AND HORIZONTAL
253C boxvh FORMS LIGHT VERTICAL AND HORIZONTAL
2550 boxH FORMS DOUBLE HORIZONTAL
2551 boxV FORMS DOUBLE VERTICAL
2552 boxdR FORMS DOWN SINGLE AND RIGHT DOUBLE
2553 boxDr FORMS DOWN DOUBLE AND RIGHT SINGLE
2554 boxDR FORMS DOUBLE DOWN AND RIGHT
2555 boxdL FORMS DOWN SINGLE AND LEFT DOUBLE
2556 boxDl FORMS DOWN DOUBLE AND LEFT SINGLE
2557 boxDL FORMS DOUBLE DOWN AND LEFT
2558 boxuR FORMS UP SINGLE AND RIGHT DOUBLE
2559 boxUr FORMS UP DOUBLE AND RIGHT SINGLE
255A boxUR FORMS DOUBLE UP AND RIGHT
255B boxuL FORMS UP SINGLE AND LEFT DOUBLE
255C boxUl FORMS UP DOUBLE AND LEFT SINGLE
255D boxUL FORMS DOUBLE UP AND LEFT
255E boxvR FORMS VERTICAL SINGLE AND RIGHT DOUBLE
255F boxVr FORMS VERTICAL DOUBLE AND RIGHT SINGLE
2560 boxVR FORMS DOUBLE VERTICAL AND RIGHT
2561 boxvL FORMS VERTICAL SINGLE AND LEFT DOUBLE
2562 boxVl FORMS VERTICAL DOUBLE AND LEFT SINGLE
2563 boxVL FORMS DOUBLE VERTICAL AND LEFT
2564 boxHd FORMS DOWN SINGLE AND HORIZONTAL DOUBLE
2565 boxhD FORMS DOWN DOUBLE AND HORIZONTAL SINGLE
2566 boxHD FORMS DOUBLE DOWN AND HORIZONTAL
2567 boxHu FORMS UP SINGLE AND HORIZONTAL DOUBLE
2568 boxhU FORMS UP DOUBLE AND HORIZONTAL SINGLE
2569 boxHU FORMS DOUBLE UP AND HORIZONTAL
256A boxvH FORMS VERTICAL SINGLE AND HORIZONTAL DOUBLE
256B boxVh FORMS VERTICAL DOUBLE AND HORIZONTAL SINGLE
256C boxVH FORMS DOUBLE VERTICAL AND HORIZONTAL
2571 15.01 FORMS LIGHT DIAGONAL UPPER RIGHT TO LOWER LEFT
2572 16.01 FORMS LIGHT DIAGONAL UPPER LEFT TO LOWER RIGHT
2580 uhblk UPPER HALF BLOCK
2584 lhblk LOWER HALF BLOCK
2588 block FULL BLOCK
2591 blk14 LIGHT SHADE
2592 blk12 MEDIUM SHADE
2593 blk34 DARK SHADE
25A1 15.13 squ,square WHITE SQUARE
25AA squf BLACK SMALL SQUARE
25AD 15.14 rect WHITE RECTANGLE
25AE marker BLACK VERTICAL RECTANGLE
25B1 16.14 WHITE PARALLELOGRAM
25B3 13.15 xutri WHITE UP POINTING TRIANGLE
25B4 utrif BLACK UP POINTING SMALL TRIANGLE
25B5 utri WHITE UP POINTING SMALL TRIANGLE
25B7 14.14 WHITE RIGHT POINTING TRIANGLE
25B8 rtrif BLACK RIGHT POINTING SMALL TRIANGLE
25B9 rtri WHITE RIGHT POINTING SMALL TRIANGLE
25BD 14.15 xdtri WHITE DOWN POINTING TRIANGLE
25BE dtrif BLACK DOWN POINTING SMALL TRIANGLE
25BF dtri WHITE DOWN POINTING SMALL TRIANGLE
25C1 13.14 WHITE LEFT POINTING TRIANGLE
25C2 ltrif BLACK LEFT POINTING SMALL TRIANGLE
25C3 ltri WHITE LEFT POINTING SMALL TRIANGLE
25CA 15.15 LOZENGE
25CB 15.12 cir WHITE CIRCLE
25CB xcirc WHITE CIRCLE
25CF 16.12 BLACK CIRCLE
2605 starf BLACK STAR
2606 star WHITE STAR
260E phone BLACK TELEPHONE
2640 female FEMALE SIGN
2642 male MALE SIGN
2660 spades BLACK SPADE SUIT
2661 hearts WHITE HEART SUIT
2662 diams WHITE DIAMOND SUIT
2663 clubs BLACK CLUB SUIT
266A sung EIGHTH NOTE
266D flat FLAT
266E natur NATURAL
266F sharp SHARP
2713 check CHECK MARK
2717 cross BALLOT X
2720 malt MALTESE CROSS
2726 lozf BLACK FOUR POINTED STAR
2727 loz WHITE FOUR POINTED STAR
2736 sextile SIX POINTED BLACK STAR
3018 13.02 OPENING WHITE TORTOISE SHELL BRACKET
3019 14.02 CLOSING WHITE TORTOISE SHELL BRACKET
301A 03.14 OPENING WHITE SQUARE BRACKET
301B 04.14 CLOSING WHITE SQUARE BRACKET
SGML and ISO 6862.2 ligatures, glyphs, and glyph variants which
are not encoded in Unicode:
fflig
ffilig
ffllig
filig
fllig
fjlig
jnodot
spar
16.00 smid
nsmid
nspar
ssmile
sfrown
lap
gap
lnap
gnap
lEg
gEl
vsupne
vsubne
vsubnE
vsupnE
subne
supne
pre
sce
prnE
scnE
prap
scap
prnap
scnap
xlArr
xrArr
xharr

4
unicode/vendors/adobe/readme.txt vendored Normal file
View File

@@ -0,0 +1,4 @@
The files in this directory are not official. They were created
from the original Unicode Version 1.0 mapping tables for
convenience only.
Contact rick@unicode.org with any problems.

181
unicode/vendors/adobe/stdenc.txt vendored Normal file
View File

@@ -0,0 +1,181 @@
#
# Name: Adobe Standard Encoding to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 05 May 1995
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# Format: Three tab-separated columns
# Column #1 is the Unicode code (in hex)
# Column #2 is the Adobe code (in hex)
# Column #3 # Unicode name <tab> # Adobe name
#
# Any comments or questions contact: unicode-inc@unicode.org
#
0020 20 # SPACE # space
0021 21 # EXCLAMATION MARK # exclam
0022 22 # QUOTATION MARK # quotedbl
0023 23 # NUMBER SIGN # numbersign
0024 24 # DOLLAR SIGN # dollar
0025 25 # PERCENT SIGN # percent
0026 26 # AMPERSAND # ampersand
0027 A9 # APOSTROPHE-QUOTE # quotesingle
0028 28 # OPENING PARENTHESIS # parenleft
0029 29 # CLOSING PARENTHESIS # parenright
002A 2A # ASTERISK # asterisk
002B 2B # PLUS SIGN # plus
002C 2C # COMMA # comma
002D 2D # HYPHEN-MINUS # hyphen
002E 2E # PERIOD # period
002F 2F # SLASH # slash
0030 30 # DIGIT ZERO # zero
0031 31 # DIGIT ONE # one
0032 32 # DIGIT TWO # two
0033 33 # DIGIT THREE # three
0034 34 # DIGIT FOUR # four
0035 35 # DIGIT FIVE # five
0036 36 # DIGIT SIX # six
0037 37 # DIGIT SEVEN # seven
0038 38 # DIGIT EIGHT # eight
0039 39 # DIGIT NINE # nine
003A 3A # COLON # colon
003B 3B # SEMICOLON # semicolon
003C 3C # LESS-THAN SIGN # less
003D 3D # EQUALS SIGN # equal
003E 3E # GREATER-THAN SIGN # greater
003F 3F # QUESTION MARK # question
0040 40 # COMMERCIAL AT # at
0041 41 # LATIN CAPITAL LETTER A # A
0042 42 # LATIN CAPITAL LETTER B # B
0043 43 # LATIN CAPITAL LETTER C # C
0044 44 # LATIN CAPITAL LETTER D # D
0045 45 # LATIN CAPITAL LETTER E # E
0046 46 # LATIN CAPITAL LETTER F # F
0047 47 # LATIN CAPITAL LETTER G # G
0048 48 # LATIN CAPITAL LETTER H # H
0049 49 # LATIN CAPITAL LETTER I # I
004A 4A # LATIN CAPITAL LETTER J # J
004B 4B # LATIN CAPITAL LETTER K # K
004C 4C # LATIN CAPITAL LETTER L # L
004D 4D # LATIN CAPITAL LETTER M # M
004E 4E # LATIN CAPITAL LETTER N # N
004F 4F # LATIN CAPITAL LETTER O # O
0050 50 # LATIN CAPITAL LETTER P # P
0051 51 # LATIN CAPITAL LETTER Q # Q
0052 52 # LATIN CAPITAL LETTER R # R
0053 53 # LATIN CAPITAL LETTER S # S
0054 54 # LATIN CAPITAL LETTER T # T
0055 55 # LATIN CAPITAL LETTER U # U
0056 56 # LATIN CAPITAL LETTER V # V
0057 57 # LATIN CAPITAL LETTER W # W
0058 58 # LATIN CAPITAL LETTER X # X
0059 59 # LATIN CAPITAL LETTER Y # Y
005A 5A # LATIN CAPITAL LETTER Z # Z
005B 5B # OPENING SQUARE BRACKET # bracketleft
005C 5C # BACKSLASH # backslash
005D 5D # CLOSING SQUARE BRACKET # bracketright
005E 5E # SPACING CIRCUMFLEX # asciicircum
005F 5F # SPACING UNDERSCORE # underscore
0060 C1 # SPACING GRAVE # grave
0061 61 # LATIN SMALL LETTER A # a
0062 62 # LATIN SMALL LETTER B # b
0063 63 # LATIN SMALL LETTER C # c
0064 64 # LATIN SMALL LETTER D # d
0065 65 # LATIN SMALL LETTER E # e
0066 66 # LATIN SMALL LETTER F # f
0067 67 # LATIN SMALL LETTER G # g
0068 68 # LATIN SMALL LETTER H # h
0069 69 # LATIN SMALL LETTER I # i
006A 6A # LATIN SMALL LETTER J # j
006B 6B # LATIN SMALL LETTER K # k
006C 6C # LATIN SMALL LETTER L # l
006D 6D # LATIN SMALL LETTER M # m
006E 6E # LATIN SMALL LETTER N # n
006F 6F # LATIN SMALL LETTER O # o
0070 70 # LATIN SMALL LETTER P # p
0071 71 # LATIN SMALL LETTER Q # q
0072 72 # LATIN SMALL LETTER R # r
0073 73 # LATIN SMALL LETTER S # s
0074 74 # LATIN SMALL LETTER T # t
0075 75 # LATIN SMALL LETTER U # u
0076 76 # LATIN SMALL LETTER V # v
0077 77 # LATIN SMALL LETTER W # w
0078 78 # LATIN SMALL LETTER X # x
0079 79 # LATIN SMALL LETTER Y # y
007A 7A # LATIN SMALL LETTER Z # z
007B 7B # OPENING CURLY BRACKET # braceleft
007C 7C # VERTICAL BAR # bar
007D 7D # CLOSING CURLY BRACKET # braceright
007E 7E # TILDE # asciitilde
00A1 A1 # INVERTED EXCLAMATION MARK # exclamdown
00A2 A2 # CENT SIGN # cent
00A3 A3 # POUND SIGN # sterling
00A4 A8 # CURRENCY SIGN # currency
00A5 A5 # YEN SIGN # yen
00A7 A7 # SECTION SIGN # section
00A8 C8 # SPACING DIAERESIS # dieresis
00AA E3 # FEMININE ORDINAL INDICATOR # ordfeminine
00AB AB # LEFT POINTING GUILLEMET # guillemotleft
00AF C5 # SPACING MACRON # macron
00B4 C2 # SPACING ACUTE # acute
00B6 B6 # PARAGRAPH SIGN # paragraph
00B7 B4 # MIDDLE DOT # periodcentered
00B8 CB # SPACING CEDILLA # cedilla
00BA EB # MASCULINE ORDINAL INDICATOR # ordmasculine
00BB BB # RIGHT POINTING GUILLEMET # guillemotright
00BF BF # INVERTED QUESTION MARK # questiondown
00C6 E1 # LATIN CAPITAL LETTER A E # AE
00D8 E9 # LATIN CAPITAL LETTER O SLASH # Oslash
00DF FB # LATIN SMALL LETTER SHARP S # germandbls
00E6 F1 # LATIN SMALL LETTER A E # ae
00F8 F9 # LATIN SMALL LETTER O SLASH # oslash
0131 F5 # LATIN SMALL LETTER DOTLESS I # dotlessi
0141 E8 # LATIN CAPITAL LETTER L SLASH # Lslash
0142 F8 # LATIN SMALL LETTER L SLASH # lslash
0152 EA # LATIN CAPITAL LETTER O E # OE
0153 FA # LATIN SMALL LETTER O E # oe
0192 A6 # LATIN SMALL LETTER SCRIPT F # florin
02C6 C3 # MODIFIER LETTER CIRCUMFLEX # circumflex
02C7 CF # MODIFIER LETTER HACEK # caron
02D8 C6 # SPACING BREVE # breve
02D9 C7 # SPACING DOT ABOVE # dotaccent
02DA CA # SPACING RING ABOVE # ring
02DB CE # SPACING OGONEK # ogonek
02DC C4 # SPACING TILDE # tilde
02DD CD # SPACING DOUBLE ACUTE # hungarumlaut
2013 B1 # EN DASH # endash
2014 D0 # EM DASH # emdash
2018 60 # SINGLE TURNED COMMA QUOTATION MARK # quoteleft
2019 27 # SINGLE COMMA QUOTATION MARK # quoteright
201A B8 # LOW SINGLE COMMA QUOTATION MARK # quotesinglbase
201C AA # DOUBLE TURNED COMMA QUOTATION MARK # quotedblleft
201D BA # DOUBLE COMMA QUOTATION MARK # quotedblright
201E B9 # LOW DOUBLE COMMA QUOTATION MARK # quotedblbase
2020 B2 # DAGGER # dagger
2021 B3 # DOUBLE DAGGER # daggerdbl
2022 B7 # BULLET # bullet
2026 BC # HORIZONTAL ELLIPSIS # ellipsis
2030 BD # PER MILLE SIGN # perthousand
2039 AC # LEFT POINTING SINGLE GUILLEMET # guilsinglleft
203A AD # RIGHT POINTING SINGLE GUILLEMET # guilsinglright
2044 A4 # FRACTION SLASH # fraction
FB01 AE # LATIN SMALL LIGATURE FI # fi
FB02 AF # LATIN SMALL LIGATURE FL # fl

226
unicode/vendors/adobe/symbol.txt vendored Normal file
View File

@@ -0,0 +1,226 @@
#
# Name: Adobe Symbol Encoding to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 05 May 1995
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# Format: Three tab-separated columns
# Column #1 is the Unicode code (in hex)
# Column #2 is the Adobe code (in hex)
# Column #3 # Unicode name <tab> # Adobe name
#
# General notes: There are a number of glyph parts in the Adobe Symbol
# Encoding which are not in the Unicode set. They are as follows:
#
# BD arrowvertex
# BE arrowhorizex
# E6 parenlefttp
# E7 parenleftex
# E8 parenleftbt
# E9 bracketlefttp
# EA bracketleftex
# EB bracketleftbt
# EC bracelefttp
# ED braceleftmid
# EE braceleftbt
# EF braceex
# F4 integralex
# F6 parenrighttp
# F7 parenrightex
# F8 parenrightbt
# F9 bracketrighttp
# FA bracketrightex
# FB bracketrightbt
# FC bracerighttp
# FD bracerightmid
# FE bracerightbt
#
# Any comments or questions contact: unicode-inc@unicode.org
#
#
0020 20 # SPACE # space
0021 21 # EXCLAMATION MARK # exclam
0023 23 # NUMBER SIGN # numbersign
0025 25 # PERCENT SIGN # percent
0026 26 # AMPERSAND # ampersand
0028 28 # OPENING PARENTHESIS # parenleft
0029 29 # CLOSING PARENTHESIS # parenright
002B 2B # PLUS SIGN # plus
002C 2C # COMMA # comma
002E 2E # PERIOD # period
002F 2F # SLASH # slash
0030 30 # DIGIT ZERO # zero
0031 31 # DIGIT ONE # one
0032 32 # DIGIT TWO # two
0033 33 # DIGIT THREE # three
0034 34 # DIGIT FOUR # four
0035 35 # DIGIT FIVE # five
0036 36 # DIGIT SIX # six
0037 37 # DIGIT SEVEN # seven
0038 38 # DIGIT EIGHT # eight
0039 39 # DIGIT NINE # nine
003A 3A # COLON # colon
003B 3B # SEMICOLON # semicolon
003C 3C # LESS-THAN SIGN # less
003D 3D # EQUALS SIGN # equal
003E 3E # GREATER-THAN SIGN # greater
003F 3F # QUESTION MARK # question
005B 5B # OPENING SQUARE BRACKET # bracketleft
005D 5D # CLOSING SQUARE BRACKET # bracketright
005F 5F # SPACING UNDERSCORE # underscore
007B 7B # OPENING CURLY BRACKET # braceleft
007C 7C # VERTICAL BAR # bar
007D 7D # CLOSING CURLY BRACKET # braceright
00A9 D3 # COPYRIGHT SIGN # copyrightserif
00A9 E3 # COPYRIGHT SIGN # copyrightsans
00AC D8 # NOT SIGN # logicalnot
00AE D2 # REGISTERED TRADE MARK SIGN # registeredserif
00AE E2 # REGISTERED TRADE MARK SIGN # registeredsans
00B0 B0 # DEGREE SIGN # degree
00B1 B1 # PLUS-OR-MINUS SIGN # plusminus
00D7 B4 # MULTIPLICATION SIGN # multiply
00F7 B8 # DIVISION SIGN # divide
0192 A6 # LATIN SMALL LETTER SCRIPT F # florin
0391 41 # GREEK CAPITAL LETTER ALPHA # Alpha
0392 42 # GREEK CAPITAL LETTER BETA # Beta
0393 47 # GREEK CAPITAL LETTER GAMMA # Gamma
0394 44 # GREEK CAPITAL LETTER DELTA # Delta
0395 45 # GREEK CAPITAL LETTER EPSILON # Epsilon
0396 5A # GREEK CAPITAL LETTER ZETA # Zeta
0397 48 # GREEK CAPITAL LETTER ETA # Eta
0398 51 # GREEK CAPITAL LETTER THETA # Theta
0399 49 # GREEK CAPITAL LETTER IOTA # Iota
039A 4B # GREEK CAPITAL LETTER KAPPA # Kappa
039B 4C # GREEK CAPITAL LETTER LAMBDA # Lambda
039C 4D # GREEK CAPITAL LETTER MU # Mu
039D 4E # GREEK CAPITAL LETTER NU # Nu
039E 58 # GREEK CAPITAL LETTER XI # Xi
039F 4F # GREEK CAPITAL LETTER OMICRON # Omicron
03A0 50 # GREEK CAPITAL LETTER PI # Pi
03A1 52 # GREEK CAPITAL LETTER RHO # Rho
03A3 53 # GREEK CAPITAL LETTER SIGMA # Sigma
03A4 54 # GREEK CAPITAL LETTER TAU # Tau
03A5 55 # GREEK CAPITAL LETTER UPSILON # Upsilon
03A6 46 # GREEK CAPITAL LETTER PHI # Phi
03A7 43 # GREEK CAPITAL LETTER CHI # Chi
03A8 59 # GREEK CAPITAL LETTER PSI # Psi
03A9 57 # GREEK CAPITAL LETTER OMEGA # Omega
03B1 61 # GREEK SMALL LETTER ALPHA # alpha
03B2 62 # GREEK SMALL LETTER BETA # beta
03B3 67 # GREEK SMALL LETTER GAMMA # gamma
03B4 64 # GREEK SMALL LETTER DELTA # delta
03B5 65 # GREEK SMALL LETTER EPSILON # epsilon
03B6 7A # GREEK SMALL LETTER ZETA # zeta
03B7 68 # GREEK SMALL LETTER ETA # eta
03B8 71 # GREEK SMALL LETTER THETA # theta
03B9 69 # GREEK SMALL LETTER IOTA # iota
03BA 6B # GREEK SMALL LETTER KAPPA # kappa
03BB 6C # GREEK SMALL LETTER LAMBDA # lambda
03BC 6D # GREEK SMALL LETTER MU # mu
03BD 6E # GREEK SMALL LETTER NU # nu
03BE 78 # GREEK SMALL LETTER XI # xi
03BF 6F # GREEK SMALL LETTER OMICRON # omicron
03C0 70 # GREEK SMALL LETTER PI # pi
03C1 72 # GREEK SMALL LETTER RHO # rho
03C2 56 # GREEK SMALL LETTER FINAL SIGMA # sigma1
03C3 73 # GREEK SMALL LETTER SIGMA # sigma
03C4 74 # GREEK SMALL LETTER TAU # tau
03C5 75 # GREEK SMALL LETTER UPSILON # upsilon
03C6 66 # GREEK SMALL LETTER PHI # phi
03C7 63 # GREEK SMALL LETTER CHI # chi
03C8 79 # GREEK SMALL LETTER PSI # psi
03C9 77 # GREEK SMALL LETTER OMEGA # omega
03D1 4A # GREEK SMALL LETTER SCRIPT THETA # theta1
03D2 A1 # GREEK CAPITAL LETTER UPSILON HOOK # Upsilon1
03D5 6A # GREEK SMALL LETTER SCRIPT PHI # phi1
03D6 76 # GREEK SMALL LETTER OMEGA PI # omega1
2022 B7 # BULLET # bullet
2026 BC # HORIZONTAL ELLIPSIS # ellipsis
2032 A2 # PRIME # minute
2033 B2 # DOUBLE PRIME # second
203E 60 # SPACING OVERSCORE # radicalex
2044 A4 # FRACTION SLASH # fraction
2111 C1 # BLACK-LETTER I # Ifraktur
2118 C3 # SCRIPT P # weierstrass
211C C2 # BLACK-LETTER R # Rfraktur
2122 D4 # TRADEMARK # trademarkserif
2122 E4 # TRADEMARK # trademarksans
2126 57 # OHM # Omega
2135 C0 # FIRST TRANSFINITE CARDINAL # aleph
2190 AC # LEFT ARROW # arrowleft
2191 AD # UP ARROW # arrowup
2192 AE # RIGHT ARROW # arrowright
2193 AF # DOWN ARROW # arrowdown
2194 AB # LEFT RIGHT ARROW # arrowboth
21B5 BF # DOWN ARROW WITH CORNER LEFT # carriagereturn
21D0 DC # LEFT DOUBLE ARROW # arrowdblleft
21D1 DD # UP DOUBLE ARROW # arrowdblup
21D2 DE # RIGHT DOUBLE ARROW # arrowdblright
21D3 DF # DOWN DOUBLE ARROW # arrowdbldown
21D4 DB # LEFT RIGHT DOUBLE ARROW # arrowdblboth
2200 22 # FOR ALL # universal
2202 B6 # PARTIAL DIFFERENTIAL # partialdiff
2203 24 # THERE EXISTS # existential
2205 C6 # EMPTY SET # emptyset
2206 44 # INCREMENT # Delta
2207 D1 # NABLA # gradient
2208 CE # ELEMENT OF # element
2209 CF # NOT AN ELEMENT OF # notelement
220B 27 # CONTAINS AS MEMBER # suchthat
220F D5 # N-ARY PRODUCT # product
2211 E5 # N-ARY SUMMATION # summation
2212 2D # MINUS SIGN # minus
2215 A4 # DIVISION SLASH # fraction
2217 2A # ASTERISK OPERATOR # asteriskmath
221A D6 # SQUARE ROOT # radical
221D B5 # PROPORTIONAL TO # proportional
221E A5 # INFINITY # infinity
2220 D0 # ANGLE # angle
2227 D9 # LOGICAL AND # logicaland
2228 DA # LOGICAL OR # logicalor
2229 C7 # INTERSECTION # intersection
222A C8 # UNION # union
222B F2 # INTEGRAL # integral
2234 5C # THEREFORE # therefore
223C 7E # TILDE OPERATOR # similar
2245 40 # APPROXIMATELY EQUAL TO # congruent
2248 BB # ALMOST EQUAL TO # approxequal
2260 B9 # NOT EQUAL TO # notequal
2261 BA # IDENTICAL TO # equivalence
2264 A3 # LESS THAN OR EQUAL TO # lessequal
2265 B3 # GREATER THAN OR EQUAL TO # greaterequal
2282 CC # SUBSET OF # propersubset
2283 C9 # SUPERSET OF # propersuperset
2284 CB # NOT A SUBSET OF # notsubset
2286 CD # SUBSET OF OR EQUAL TO # reflexsubset
2287 CA # SUPERSET OF OR EQUAL TO # reflexsuperset
2295 C5 # CIRCLED PLUS # circleplus
2297 C4 # CIRCLED TIMES # circlemultiply
22A5 5E # UP TACK # perpendicular
22C5 D7 # DOT OPERATOR # dotmath
2320 F3 # TOP HALF INTEGRAL # integraltp
2321 F5 # BOTTOM HALF INTEGRAL # integralbt
2329 E1 # BRA # angleleft
232A F1 # KET # angleright
25CA E0 # LOZENGE # lozenge
2660 AA # BLACK SPADE SUIT # spade
2663 A7 # BLACK CLUB SUIT # club
2665 A9 # BLACK HEART SUIT # heart
2666 A8 # BLACK DIAMOND SUIT # diamond

217
unicode/vendors/adobe/zdingbat.txt vendored Normal file
View File

@@ -0,0 +1,217 @@
#
# Name: Adobe Zapf Dingbats Encoding to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 05 May 1995
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# Format: Three tab-separated columns
# Column #1 is the Unicode code (in hex)
# Column #2 is the Adobe code (in hex)
# Column #3 # Unicode name <tab> # Adobe name
#
# Any comments or questions contact: unicode-inc@unicode.org
#
2192 D5 # RIGHT ARROW # a161
2194 D6 # LEFT RIGHT ARROW # a163
2195 D7 # UP DOWN ARROW # a164
2460 AC # CIRCLED DIGIT ONE # a120
2461 AD # CIRCLED DIGIT TWO # a121
2462 AE # CIRCLED DIGIT THREE # a122
2463 AF # CIRCLED DIGIT FOUR # a123
2464 B0 # CIRCLED DIGIT FIVE # a124
2465 B1 # CIRCLED DIGIT SIX # a125
2466 B2 # CIRCLED DIGIT SEVEN # a126
2467 B3 # CIRCLED DIGIT EIGHT # a127
2468 B4 # CIRCLED DIGIT NINE # a128
2469 B5 # CIRCLED NUMBER TEN # a129
25A0 6E # BLACK SQUARE # a73
25B2 73 # BLACK UP POINTING TRIANGLE # a76
25BC 74 # BLACK DOWN POINTING TRIANGLE # a77
25C6 75 # BLACK DIAMOND # a78
2605 48 # BLACK STAR # a35
260E 25 # BLACK TELEPHONE # a4
261B 2A # BLACK RIGHT POINTING INDEX # a11
261E 2B # WHITE RIGHT POINTING INDEX # a12
2660 AB # BLACK SPADE SUIT # a109
2663 A8 # BLACK CLUB SUIT # a112
2665 AA # BLACK HEART SUIT # a110
2666 A9 # BLACK DIAMOND SUIT # a111
2701 21 # UPPER BLADE SCISSORS # a1
2702 22 # BLACK SCISSORS # a2
2703 23 # LOWER BLADE SCISSORS # a202
2704 24 # WHITE SCISSORS # a3
2706 26 # TELEPHONE LOCATION SIGN # a5
2707 27 # TAPE DRIVE # a119
2708 28 # AIRPLANE # a118
2709 29 # ENVELOPE # a117
270C 2C # VICTORY HAND # a13
270D 2D # WRITING HAND # a14
270E 2E # LOWER RIGHT PENCIL # a15
270F 2F # PENCIL # a16
2710 30 # UPPER RIGHT PENCIL # a105
2711 31 # WHITE NIB # a17
2712 32 # BLACK NIB # a18
2713 33 # CHECK MARK # a19
2714 34 # HEAVY CHECK MARK # a20
2715 35 # MULTIPLICATION X # a21
2716 36 # HEAVY MULTIPLICATION X # a22
2717 37 # BALLOT X # a23
2718 38 # HEAVY BALLOT X # a24
2719 39 # OUTLINED GREEK CROSS # a25
271A 3A # HEAVY GREEK CROSS # a26
271B 3B # OPEN CENTER CROSS # a27
271C 3C # HEAVY OPEN CENTER CROSS # a28
271D 3D # LATIN CROSS # a6
271E 3E # SHADOWED WHITE LATIN CROSS # a7
271F 3F # OUTLINED LATIN CROSS # a8
2720 40 # MALTESE CROSS # a9
2721 41 # STAR OF DAVID # a10
2722 42 # FOUR TEARDROP-SPOKED ASTERISK # a29
2723 43 # FOUR BALLOON-SPOKED ASTERISK # a30
2724 44 # HEAVY FOUR BALLOON-SPOKED ASTERISK # a31
2725 45 # FOUR CLUB-SPOKED ASTERISK # a32
2726 46 # BLACK FOUR POINTED STAR # a33
2727 47 # WHITE FOUR POINTED STAR # a34
2729 49 # STRESS OUTLINED WHITE STAR # a36
272A 4A # CIRCLED WHITE STAR # a37
272B 4B # OPEN CENTER BLACK STAR # a38
272C 4C # BLACK CENTER WHITE STAR # a39
272D 4D # OUTLINED BLACK STAR # a40
272E 4E # HEAVY OUTLINED BLACK STAR # a41
272F 4F # PINWHEEL STAR # a42
2730 50 # SHADOWED WHITE STAR # a43
2731 51 # HEAVY ASTERISK # a44
2732 52 # OPEN CENTER ASTERISK # a45
2733 53 # EIGHT SPOKED ASTERISK # a46
2734 54 # EIGHT POINTED BLACK STAR # a47
2735 55 # EIGHT POINTED PINWHEEL STAR # a48
2736 56 # SIX POINTED BLACK STAR # a49
2737 57 # EIGHT POINTED RECTILINEAR BLACK STAR # a50
2738 58 # HEAVY EIGHT POINTED RECTILINEAR BLACK STAR # a51
2739 59 # TWELVE POINTED BLACK STAR # a52
273A 5A # SIXTEEN POINTED ASTERISK # a53
273B 5B # TEARDROP-SPOKED ASTERISK # a54
273C 5C # OPEN CENTER TEARDROP-SPOKED ASTERISK # a55
273D 5D # HEAVY TEARDROP-SPOKED ASTERISK # a56
273E 5E # SIX PETALLED BLACK AND WHITE FLORETTE # a57
273F 5F # BLACK FLORETTE # a58
2740 60 # WHITE FLORETTE # a59
2741 61 # EIGHT PETALLED OUTLINED BLACK FLORETTE # a60
2742 62 # CIRCLED OPEN CENTER EIGHT POINTED STAR # a61
2743 63 # HEAVY TEARDROP-SPOKED PINWHEEL ASTERISK # a62
2744 64 # SNOWFLAKE # a63
2745 65 # TIGHT TRIFOLIATE SNOWFLAKE # a64
2746 66 # HEAVY CHEVRON SNOWFLAKE # a65
2747 67 # SPARKLE # a66
2748 68 # HEAVY SPARKLE # a67
2749 69 # BALLOON-SPOKED ASTERISK # a68
274A 6A # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK # a69
274B 6B # HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK # a70
274D 6D # SHADOWED WHITE CIRCLE # a72
274F 6F # LOWER RIGHT DROP-SHADOWED WHITE SQUARE # a74
2750 70 # UPPER RIGHT DROP-SHADOWED WHITE SQUARE # a203
2751 71 # LOWER RIGHT SHADOWED WHITE SQUARE # a75
2752 72 # UPPER RIGHT SHADOWED WHITE SQUARE # a204
2756 76 # BLACK DIAMOND MINUS WHITE X # a79
2758 78 # LIGHT VERTICAL BAR # a82
2759 79 # MEDIUM VERTICAL BAR # a83
275A 7A # HEAVY VERTICAL BAR # a84
275B 7B # HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT # a97
275C 7C # HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT # a98
275D 7D # HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT # a99
275E 7E # HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT # a100
2761 A1 # CURVED STEM PARAGRAPH SIGN ORNAMENT # a101
2762 A2 # HEAVY EXCLAMATION MARK ORNAMENT # a102
2763 A3 # HEAVY HEART EXCLAMATION MARK ORNAMENT # a103
2764 A4 # HEAVY BLACK HEART # a104
2765 A5 # ROTATED HEAVY BLACK HEART BULLET # a105
2766 A6 # FLORAL HEART # a106
2767 A7 # ROTATED FLORAL HEART BULLET # a107
2776 B6 # INVERSE CIRCLED DIGIT ONE # a130
2777 B7 # INVERSE CIRCLED DIGIT TWO # a131
2778 B8 # INVERSE CIRCLED DIGIT THREE # a132
2779 B9 # INVERSE CIRCLED DIGIT FOUR # a133
277A BA # INVERSE CIRCLED DIGIT FIVE # a134
277B BB # INVERSE CIRCLED DIGIT SIX # a135
277C BC # INVERSE CIRCLED DIGIT SEVEN # a136
277D BD # INVERSE CIRCLED DIGIT EIGHT # a137
277E BE # INVERSE CIRCLED DIGIT NINE # a138
277F BF # INVERSE CIRCLED NUMBER TEN # a139
2780 C0 # CIRCLED SANS-SERIF DIGIT ONE # a140
2781 C1 # CIRCLED SANS-SERIF DIGIT TWO # a141
2782 C2 # CIRCLED SANS-SERIF DIGIT THREE # a142
2783 C3 # CIRCLED SANS-SERIF DIGIT FOUR # a143
2784 C4 # CIRCLED SANS-SERIF DIGIT FIVE # a144
2785 C5 # CIRCLED SANS-SERIF DIGIT SIX # a145
2786 C6 # CIRCLED SANS-SERIF DIGIT SEVEN # a146
2787 C7 # CIRCLED SANS-SERIF DIGIT EIGHT # a147
2788 C8 # CIRCLED SANS-SERIF DIGIT NINE # a148
2789 C9 # CIRCLED SANS-SERIF NUMBER TEN # a149
278A CA # INVERSE CIRCLED SANS-SERIF DIGIT ONE # a150
278B CB # INVERSE CIRCLED SANS-SERIF DIGIT TWO # a151
278C CC # INVERSE CIRCLED SANS-SERIF DIGIT THREE # a152
278D CD # INVERSE CIRCLED SANS-SERIF DIGIT FOUR # a153
278E CE # INVERSE CIRCLED SANS-SERIF DIGIT FIVE # a154
278F CF # INVERSE CIRCLED SANS-SERIF DIGIT SIX # a155
2790 D0 # INVERSE CIRCLED SANS-SERIF DIGIT SEVEN # a156
2791 D1 # INVERSE CIRCLED SANS-SERIF DIGIT EIGHT # a157
2792 D2 # INVERSE CIRCLED SANS-SERIF DIGIT NINE # a158
2793 D3 # INVERSE CIRCLED SANS-SERIF NUMBER TEN # a159
2794 D4 # HEAVY WIDE-HEADED RIGHT ARROW # a160
2798 D8 # HEAVY LOWER RIGHT ARROW # a196
2799 D9 # HEAVY RIGHT ARROW # a165
279A DA # HEAVY UPPER RIGHT ARROW # a192
279B DB # DRAFTING POINT RIGHT ARROW # a166
279C DC # HEAVY ROUND-TIPPED RIGHT ARROW # a167
279D DD # TRIANGLE-HEADED RIGHT ARROW # a168
279E DE # HEAVY TRIANGLE-HEADED RIGHT ARROW # a169
279F DF # DASHED TRIANGLE-HEADED RIGHT ARROW # a170
27A0 E0 # HEAVY DASHED TRIANGLE-HEADED RIGHT ARROW # a171
27A1 E1 # BLACK RIGHT ARROW # a172
27A2 E2 # THREE-D TOP-LIGHTED RIGHT ARROWHEAD # a173
27A3 E3 # THREE-D BOTTOM-LIGHTED RIGHT ARROWHEAD # a162
27A4 E4 # BLACK RIGHT ARROWHEAD # a174
27A5 E5 # HEAVY BLACK CURVED DOWN AND RIGHT ARROW # a175
27A6 E6 # HEAVY BLACK CURVED UP AND RIGHT ARROW # a176
27A7 E7 # SQUAT BLACK RIGHT ARROW # a177
27A8 E8 # HEAVY CONCAVE-POINTED BLACK RIGHT ARROW # a178
27A9 E9 # RIGHT-SHADED WHITE RIGHT ARROW # a179
27AA EA # LEFT-SHADED WHITE RIGHT ARROW # a193
27AB EB # BACK-TILTED SHADOWED WHITE RIGHT ARROW # a180
27AC EC # FRONT-TILTED SHADOWED WHITE RIGHT ARROW # a199
27AD ED # HEAVY LOWER RIGHT-SHADOWED WHITE RIGHT ARROW # a181
27AE EE # HEAVY UPPER RIGHT-SHADOWED WHITE RIGHT ARROW # a200
27AF EF # NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHT ARROW # a182
27B1 F1 # NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHT ARROW # a201
27B2 F2 # CIRCLED HEAVY WHITE RIGHT ARROW # a183
27B3 F3 # WHITE-FEATHERED RIGHT ARROW # a184
27B4 F4 # BLACK-FEATHERED LOWER RIGHT ARROW # a197
27B5 F5 # BLACK-FEATHERED RIGHT ARROW # a185
27B6 F6 # BLACK-FEATHERED UPPER RIGHT ARROW # a194
27B7 F7 # HEAVY BLACK-FEATHERED LOWER RIGHT ARROW # a198
27B8 F8 # HEAVY BLACK-FEATHERED RIGHT ARROW # a186
27B9 F9 # HEAVY BLACK-FEATHERED UPPER RIGHT ARROW # a195
27BA FA # TEARDROP-BARBED RIGHT ARROW # a187
27BB FB # HEAVY TEARDROP-SHANKED RIGHT ARROW # a188
27BC FC # WEDGE-TAILED RIGHT ARROW # a189
27BD FD # HEAVY WEDGE-TAILED RIGHT ARROW # a190
27BE FE # OPEN-OUTLINED RIGHT ARROW # a191

393
unicode/vendors/apple/arabic.txt vendored Normal file
View File

@@ -0,0 +1,393 @@
#
# Name: MacOS_Arabic [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <11>)
# Date: 15 April 1995
# Authors: Peter Edberg <edberg1@applelink.apple.com>
# Frank Tang
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Arabic code (in hex as 0xNN)
# Column #2 is the Unicode or Unicode sequence (in hex as 0xNNNN
# or 0xNNNN+0xNNNN+0xNNNN).
# Column #3 is the Unicode name (follows a comment sign, '#')
# Note: The abbreviations LRO, RLO, and PDF are used for
# LEFT-TO-RIGHT OVERRIDE, RIGHT-TO-LEFT OVERRIDE, and
# POP DIRECTIONAL FORMATTING, respectively.
#
# The entries are in MacOS Arabic code order.
#
# Note that in many cases, a single MacOS Arabic character maps
# to a sequence of Unicode characters: LRO or RLO plus some Unicode
# character + PDF. This is indicated by joining the Unicode
# characters with '+'. This happens when the direction class of
# the MacOS Arabic character is different than the direction class
# of the Unicode character (usually the MacOS Arabic character has
# a strong direction class and the corresponding Unicode character
# is neutral or has a wek direction class).
#
# Notes on MacOS Arabic:
# ----------------------
#
# 1. General
#
# The MacOS Arabic character set is used for the Arabic and Persian
# (Farsi) localizations.
#
# The MacOS Arabic character set is essentially a superset of ISO
# 8859-6. The 8859-6 code points that are interpreted differently
# in the MacOS Arabic set are as follows:
# 0xA0 is no-break space in 8859-6 and right-left space in MacOS
# Arabic; NBSP is 0x81 in MacOS Arabic.
# 0xA4 is currency sign in 8859-6 and right-left dollar sign in
# MacOS Arabic.
# 0xAD is soft hyphen in 8859-6 and right-left hyphen in MacOS
# Arabic.
# ISO 8859-6 specifies that codes 0x30-0x39 can be rendered either
# with European digit shapes or Arabic digit shapes. This is also
# true MacOS Arabic, which determines from context which digit shapes
# to use.
#
# The MacOS Arabic character set uses the C1 controls area and other
# code points which are undefined in ISO 8859-6 for additional
# graphic characters: additional Arabic letters for Persian and Urdu,
# some accented Roman letters for European languages (such as French),
# and duplicates of some of the punctuation, symbols, and digits in
# the ASCII block. The duplicate punctuation, symbol, and digit
# characters have right-left directionality, while the ASCII versions
# have left-right directionality. See the next section for more
# information on this.
#
# MacOS Arabic characters 0xEB-0xF2 are non-spacing/combining marks.
#
# 2. Directional characters and roundtrip fidelity
#
# The MacOS Arabic character set was developed in 1986-1987. At that
# time the bidirectional line line layout algorithm used in the MacOS
# Arabic system was fairly simple; it used only a few direction
# classes (instead of the 13 or so now used in the Unicode
# bidirectional algorithm). In order to permit users to handle some
# tricky layout problems, certain punctuation and symbol characters
# have duplicate code points, one with a left-right direction
# attribute and the other with a right-left direction attribute.
#
# For example, ampersand is encoded at 0x26 with a left-right
# attribute, and at 0xA6 with a right-left attribute. However, there
# is only one ampersand character in Unicode. We need to have a way
# to map both MacOS Arabic ampersand characters to Unicode and back
# again without loss of information. Mapping one of the MacOS Arabic
# ampersand characters to a code in the Unicode corporate use zone is
# undesirable, since both of the ampersand characters are likely to
# be used in text that is interchanged.
#
# The problem is solved with the use of direction override characters
# and direction-dependent mappings. When mapping from MacOS Arabic to
# Unicode, such problem characters are surrounded with an appropriate
# direction override:
# MacOS Arabic 0x26 ampersand (left) ->
# Unicode 0x202D (LRO) + 0x0026 (AMPERSAND) + 0x202C (PDF)
# MacOS Arabic 0xA6 ampersand (right) ->
# Unicode 0x202E (RLO) + 0x0026 (AMPERSAND) + 0x202C (PDF)
# When mapping from Unicode to MacOS Arabic, the MacOS Unicode
# converter uses the Unicode bidirectional algorithm to determine
# resolved directions. The mapping from Unicode to MacOS Arabic can
# then be disambiguated by the use of the resolved direction:
# Unicode 0x0026 -> MacOS Arabic 0x26 (if L) or 0xA6 (if R)
#
# However, note that this means we also need to discard the direction
# override characters when mapping from Unicode to MacOS Arabic.
#
# Even when direction overrides are not needed for roundtrip
# fidelity, they are sometimes used when mapping MacOS Arabic
# characters to Unicode in order to achieve similar text layout with
# the resulting Unicode text. For example, the single MacOS Arabic
# ellipsis character has direction class right-left,and there is no
# left-right version. However, the Unicode HORIZONTAL ELLIPSIS
# character has direction class neutral (which means it may end up
# with a resolved direction of left-right if surrounded by left-right
# characters). When mapping the MacOS Arabic ellipsis to Unicode, it
# is surrounded with a direction override to help preserve proper
# text layout. The resolved direction is not needed or used when
# mapping the Unicode HORIZONTAL ELLIPSIS back to MacOS Arabic.
#
# MacOS Arabic also has duplicate digit codes at 0xB0-0xB9. These
# have right-left direction and are always displayed with Arabic
# digit glyphs (unlike the 0x30-0x39 digits, which have left-right
# direction). The MacOS Arabic 0xB0-0xB9 digits are mapped to the
# Unicode Arabic digits U+0660-U+0669 and surrounded with direction
# overrides, since the Unicode Arabic digits have a weak left-right
# direction.
#
# 3. Problematic character assignments
#
# In the Cairo font, the characters at 0x2A and 0xAA are rendered as
# an asterisk (which normally has 6 points) and the character at 0xC0
# is rendered as something that looks like a large 8-pointed asterisk.
# This handling of 0x2A and 0xAA is consistent with (1) the general
# principle that in MacOS character sets, the ASCII part should be
# identical to ASCII (0x2A is asterisk in ASCII), and (2) in MacOS
# Arabic, the right-left duplicates have codes that are equal to the
# ASCII code of the left-right version plus 0x80. However, in all of
# the other MacOS Arabic fonts, 0x2A and 0xAA are rendered as
# multiply sign (U+00D7), and 0xC0 is rendered as asterisk (with 6
# points). Also note that Unicode has a character ARABIC FIVE POINTED
# STAR (U+066D), which is similar to an asterisk but has five points.
#
# For now the strict mappings treat 0x2A and 0xAA as asterisk; the
# loose mappings also map U+00D7 to 0xAA; and 0xC0 is treated as
# ARABIC FIVE POINTED STAR (until we find a better mapping).
#
##################
0x20 0x202D+0x0020+0x202C # LRO + SPACE + PDF
0x21 0x202D+0x0021+0x202C # LRO + EXCLAMATION MARK + PDF
0x22 0x202D+0x0022+0x202C # LRO + QUOTATION MARK + PDF
0x23 0x202D+0x0023+0x202C # LRO + NUMBER SIGN + PDF
0x24 0x202D+0x0024+0x202C # LRO + DOLLAR SIGN + PDF
0x25 0x0025 # PERCENT SIGN
0x26 0x202D+0x0026+0x202C # LRO + AMPERSAND + PDF
0x27 0x202D+0x0027+0x202C # LRO + APOSTROPHE + PDF
0x28 0x202D+0x0028+0x202C # LRO + LEFT PARENTHESIS + PDF
0x29 0x202D+0x0029+0x202C # LRO + RIGHT PARENTHESIS + PDF
0x2A 0x202D+0x002A+0x202C # LRO + ASTERISK + PDF
0x2B 0x202D+0x002B+0x202C # LRO + PLUS SIGN + PDF
0x2C 0x002C # COMMA
0x2D 0x202D+0x002D+0x202C # LRO + HYPHEN-MINUS + PDF
0x2E 0x202D+0x002E+0x202C # LRO + FULL STOP + PDF
0x2F 0x202D+0x002F+0x202C # LRO + SOLIDUS + PDF
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x202D+0x003A+0x202C # LRO + COLON + PDF
0x3B 0x003B # SEMICOLON
0x3C 0x202D+0x003C+0x202C # LRO + LESS-THAN SIGN + PDF
0x3D 0x202D+0x003D+0x202C # LRO + EQUALS SIGN + PDF
0x3E 0x202D+0x003E+0x202C # LRO + GREATER-THAN SIGN + PDF
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x202D+0x005B+0x202C # LRO + LEFT SQUARE BRACKET + PDF
0x5C 0x202D+0x005C+0x202C # LRO + REVERSE SOLIDUS + PDF
0x5D 0x202D+0x005D+0x202C # LRO + RIGHT SQUARE BRACKET + PDF
0x5E 0x202D+0x005E+0x202C # LRO + CIRCUMFLEX ACCENT + PDF
0x5F 0x202D+0x005F+0x202C # LRO + LOW LINE + PDF
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x202D+0x007B+0x202C # LRO + LEFT CURLY BRACKET + PDF
0x7C 0x202D+0x007C+0x202C # LRO + VERTICAL LINE + PDF
0x7D 0x202D+0x007D+0x202C # LRO + RIGHT CURLY BRACKET + PDF
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x202E+0x00A0+0x202C # RLO + NO-BREAK SPACE + PDF
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x06BA # ARABIC LETTER NOON GHUNNA
0x8C 0x202E+0x00AB+0x202C # RLO + LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + PDF
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x202E+0x2026+0x202C # RLO + HORIZONTAL ELLIPSIS + PDF
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x202E+0x00BB+0x202C # RLO + RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + PDF
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x202E+0x00F7+0x202C # RLO + DIVISION SIGN + PDF
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x202E+0x0020+0x202C # RLO + SPACE + PDF
0xA1 0x202E+0x0021+0x202C # RLO + EXCLAMATION MARK + PDF
0xA2 0x202E+0x0022+0x202C # RLO + QUOTATION MARK + PDF
0xA3 0x202E+0x0023+0x202C # RLO + NUMBER SIGN + PDF
0xA4 0x202E+0x0024+0x202C # RLO + DOLLAR SIGN + PDF
0xA5 0x066A # ARABIC PERCENT SIGN
0xA6 0x202E+0x0026+0x202C # RLO + AMPERSAND + PDF
0xA7 0x202E+0x0027+0x202C # RLO + APOSTROPHE + PDF
0xA8 0x202E+0x0028+0x202C # RLO + LEFT PARENTHESIS + PDF
0xA9 0x202E+0x0029+0x202C # RLO + RIGHT PARENTHESIS + PDF
0xAA 0x202E+0x002A+0x202C # RLO + ASTERISK + PDF
0xAB 0x202E+0x002B+0x202C # RLO + PLUS SIGN + PDF
0xAC 0x060C # ARABIC COMMA
0xAD 0x202E+0x002D+0x202C # RLO + HYPHEN-MINUS + PDF
0xAE 0x202E+0x002E+0x202C # RLO + FULL STOP + PDF
0xAF 0x202E+0x002F+0x202C # RLO + SOLIDUS + PDF
0xB0 0x202E+0x0660+0x202C # RLO + ARABIC-INDIC DIGIT ZERO + PDF
0xB1 0x202E+0x0661+0x202C # RLO + ARABIC-INDIC DIGIT ONE + PDF
0xB2 0x202E+0x0662+0x202C # RLO + ARABIC-INDIC DIGIT TWO + PDF
0xB3 0x202E+0x0663+0x202C # RLO + ARABIC-INDIC DIGIT THREE + PDF
0xB4 0x202E+0x0664+0x202C # RLO + ARABIC-INDIC DIGIT FOUR + PDF
0xB5 0x202E+0x0665+0x202C # RLO + ARABIC-INDIC DIGIT FIVE + PDF
0xB6 0x202E+0x0666+0x202C # RLO + ARABIC-INDIC DIGIT SIX + PDF
0xB7 0x202E+0x0667+0x202C # RLO + ARABIC-INDIC DIGIT SEVEN + PDF
0xB8 0x202E+0x0668+0x202C # RLO + ARABIC-INDIC DIGIT EIGHT + PDF
0xB9 0x202E+0x0669+0x202C # RLO + ARABIC-INDIC DIGIT NINE + PDF
0xBA 0x202E+0x003A+0x202C # RLO + COLON + PDF
0xBB 0x061B # ARABIC SEMICOLON
0xBC 0x202E+0x003C+0x202C # RLO + LESS-THAN SIGN + PDF
0xBD 0x202E+0x003D+0x202C # RLO + EQUALS SIGN + PDF
0xBE 0x202E+0x003E+0x202C # RLO + GREATER-THAN SIGN + PDF
0xBF 0x061F # ARABIC QUESTION MARK
0xC0 0x066D # ARABIC FIVE POINTED STAR
0xC1 0x0621 # ARABIC LETTER HAMZA
0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE
0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE
0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE
0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW
0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE
0xC7 0x0627 # ARABIC LETTER ALEF
0xC8 0x0628 # ARABIC LETTER BEH
0xC9 0x0629 # ARABIC LETTER TEH MARBUTA
0xCA 0x062A # ARABIC LETTER TEH
0xCB 0x062B # ARABIC LETTER THEH
0xCC 0x062C # ARABIC LETTER JEEM
0xCD 0x062D # ARABIC LETTER HAH
0xCE 0x062E # ARABIC LETTER KHAH
0xCF 0x062F # ARABIC LETTER DAL
0xD0 0x0630 # ARABIC LETTER THAL
0xD1 0x0631 # ARABIC LETTER REH
0xD2 0x0632 # ARABIC LETTER ZAIN
0xD3 0x0633 # ARABIC LETTER SEEN
0xD4 0x0634 # ARABIC LETTER SHEEN
0xD5 0x0635 # ARABIC LETTER SAD
0xD6 0x0636 # ARABIC LETTER DAD
0xD7 0x0637 # ARABIC LETTER TAH
0xD8 0x0638 # ARABIC LETTER ZAH
0xD9 0x0639 # ARABIC LETTER AIN
0xDA 0x063A # ARABIC LETTER GHAIN
0xDB 0x202E+0x005B+0x202C # RLO + LEFT SQUARE BRACKET + PDF
0xDC 0x202E+0x005C+0x202C # RLO + REVERSE SOLIDUS + PDF
0xDD 0x202E+0x005D+0x202C # RLO + RIGHT SQUARE BRACKET + PDF
0xDE 0x202E+0x005E+0x202C # RLO + CIRCUMFLEX ACCENT + PDF
0xDF 0x202E+0x005F+0x202C # RLO + LOW LINE + PDF
0xE0 0x0640 # ARABIC TATWEEL
0xE1 0x0641 # ARABIC LETTER FEH
0xE2 0x0642 # ARABIC LETTER QAF
0xE3 0x0643 # ARABIC LETTER KAF
0xE4 0x0644 # ARABIC LETTER LAM
0xE5 0x0645 # ARABIC LETTER MEEM
0xE6 0x0646 # ARABIC LETTER NOON
0xE7 0x0647 # ARABIC LETTER HEH
0xE8 0x0648 # ARABIC LETTER WAW
0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA
0xEA 0x064A # ARABIC LETTER YEH
0xEB 0x064B # ARABIC FATHATAN
0xEC 0x064C # ARABIC DAMMATAN
0xED 0x064D # ARABIC KASRATAN
0xEE 0x064E # ARABIC FATHA
0xEF 0x064F # ARABIC DAMMA
0xF0 0x0650 # ARABIC KASRA
0xF1 0x0651 # ARABIC SHADDA
0xF2 0x0652 # ARABIC SUKUN
0xF3 0x067E # ARABIC LETTER PEH
0xF4 0x0679 # ARABIC LETTER TTEH
0xF5 0x0686 # ARABIC LETTER TCHEH
0xF6 0x06D5 # ARABIC LETTER AE
0xF7 0x06A4 # ARABIC LETTER VEH
0xF8 0x06AF # ARABIC LETTER GAF
0xF9 0x0688 # ARABIC LETTER DDAL
0xFA 0x0691 # ARABIC LETTER RREH
0xFB 0x202E+0x007B+0x202C # RLO + LEFT CURLY BRACKET + PDF
0xFC 0x202E+0x007C+0x202C # RLO + VERTICAL LINE + PDF
0xFD 0x202E+0x007D+0x202C # RLO + RIGHT CURLY BRACKET + PDF
0xFE 0x0698 # ARABIC LETTER JEH
0xFF 0x06D2 # ARABIC LETTER YEH BARREE

293
unicode/vendors/apple/cnteuro.txt vendored Normal file
View File

@@ -0,0 +1,293 @@
#
# Name: MacOS_CentralEurope [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <5>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS CentralEurope code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS CentralEurope code order.
#
# Notes on MacOS CentralEurope:
# -----------------------------
#
# This character set is intended to cover the following languages,
# which are written in Roman script but using a different set of
# accented characters which are not in the standard MacOS Roman
# set (MacOS CentralEurope also contains fewer punctuation and
# math characters than standard MacOS Roman):
# - several Slavic languages (Czech, Polish, Slovak, Slovenian)
# - Hungarian
# - the languages of the Baltic republics (Estonian, Latvian,
# Lithuanian)
#
# The MacOS CentralEurope encoding also includes a number of
# characters needed for the Mac OS user interface (e.g. ellipsis),
# Mac OS localization (bullet for echoing passwords, copyright
# sign, etc.), several typographic punctuation symbols, math
# symbols, etc. All of the characters in MacOS CentralEurope that
# are also in the MacOS Roman encoding are at the same code point
# as in MacOS Roman. This improves application compatibility (since
# some naughty applications hard-code the MacOS Roman code points
# of certain characters).
#
# The MacOS CentralEurope encoding is currently used for the
# following MacOS localizations: Czech, Polish, and Hungarian.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
0x82 0x0101 # LATIN SMALL LETTER A WITH MACRON
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x0105 # LATIN SMALL LETTER A WITH OGONEK
0x89 0x010C # LATIN CAPITAL LETTER C WITH CARON
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x010D # LATIN SMALL LETTER C WITH CARON
0x8C 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
0x8D 0x0107 # LATIN SMALL LETTER C WITH ACUTE
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
0x90 0x017A # LATIN SMALL LETTER Z WITH ACUTE
0x91 0x010E # LATIN CAPITAL LETTER D WITH CARON
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x010F # LATIN SMALL LETTER D WITH CARON
0x94 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
0x95 0x0113 # LATIN SMALL LETTER E WITH MACRON
0x96 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x011A # LATIN CAPITAL LETTER E WITH CARON
0x9E 0x011B # LATIN SMALL LETTER E WITH CARON
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x0119 # LATIN SMALL LETTER E WITH OGONEK
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
0xAF 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
0xB0 0x012F # LATIN SMALL LETTER I WITH OGONEK
0xB1 0x012A # LATIN CAPITAL LETTER I WITH MACRON
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x012B # LATIN SMALL LETTER I WITH MACRON
0xB5 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x0142 # LATIN SMALL LETTER L WITH STROKE
0xB9 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
0xBA 0x013C # LATIN SMALL LETTER L WITH CEDILLA
0xBB 0x013D # LATIN CAPITAL LETTER L WITH CARON
0xBC 0x013E # LATIN SMALL LETTER L WITH CARON
0xBD 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE
0xBE 0x013A # LATIN SMALL LETTER L WITH ACUTE
0xBF 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
0xC0 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
0xC1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0144 # LATIN SMALL LETTER N WITH ACUTE
0xC5 0x0147 # LATIN CAPITAL LETTER N WITH CARON
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x0148 # LATIN SMALL LETTER N WITH CARON
0xCC 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xCF 0x014C # LATIN CAPITAL LETTER O WITH MACRON
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0x014D # LATIN SMALL LETTER O WITH MACRON
0xD9 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE
0xDA 0x0155 # LATIN SMALL LETTER R WITH ACUTE
0xDB 0x0158 # LATIN CAPITAL LETTER R WITH CARON
0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0x0159 # LATIN SMALL LETTER R WITH CARON
0xDF 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
0xE0 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
0xE1 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x0161 # LATIN SMALL LETTER S WITH CARON
0xE5 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
0xE6 0x015B # LATIN SMALL LETTER S WITH ACUTE
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x0164 # LATIN CAPITAL LETTER T WITH CARON
0xE9 0x0165 # LATIN SMALL LETTER T WITH CARON
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xEC 0x017E # LATIN SMALL LETTER Z WITH CARON
0xED 0x016A # LATIN CAPITAL LETTER U WITH MACRON
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0x016B # LATIN SMALL LETTER U WITH MACRON
0xF1 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x016F # LATIN SMALL LETTER U WITH RING ABOVE
0xF4 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xF5 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xF6 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
0xF7 0x0173 # LATIN SMALL LETTER U WITH OGONEK
0xF8 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
0xF9 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
0xFA 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
0xFB 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xFC 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
0xFD 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
0xFE 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
0xFF 0x02C7 # CARON

205
unicode/vendors/apple/corpchr.txt vendored Normal file
View File

@@ -0,0 +1,205 @@
#
# Name: MacOS_CorpChars
# Unicode versions: 1.1, 2.0
# Table version/date:
# Current - 0.4, 15 Nov 1995 (from internal version <8>)
# Add chars for Hebrew and Thai
# Previous - 0.3, 15 Apr 1995 (from internal version <5>)
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the Unicode corporate character code point
# (in hex as 0xNNNN)
# Column #2 is a comment containing:
# 1) an informal name describing the MacOS usage of the character
# ("presentation" is abbreviated as "pres.")
# 2) another '#'
# 3) a list of the corresponding code points in MacOS encodings
# (Japanese is abbreviated as just J)
#
# The entries are in Unicode order.
#_______________________________________________________________________
*/
# The following (22) are added for MacOS Thai encoding.
# In this encoding, positional variants of upper vowels, tone marks,
# and other marks are normally handled automatically by Worldscript I.
# However, the Thai-DTP keyboard allows the codes for the positional
# variants to be entered directly, so they must be treated as
# characters. When the abstract character is treated as a positional
# variant, it has the right (and high, if relevant) position.
0xF884 # form for THAI CHARACTER MAI HAN-AKAT, left position # Thai-x92
0xF885 # form for THAI CHARACTER SARA I, left position # Thai-x94
0xF886 # form for THAI CHARACTER SARA II, left position # Thai-x95
0xF887 # form for THAI CHARACTER SARA UE, left position # Thai-x96
0xF888 # form for THAI CHARACTER SARA UEE, left position # Thai-x97
0xF889 # form for THAI CHARACTER MAITAIKHU, left position # Thai-x93
0xF88A # form for THAI CHARACTER MAI EK, left position # Thai-x98
0xF88B # form for THAI CHARACTER MAI EK, low position # Thai-x88
0xF88C # form for THAI CHARACTER MAI EK, low left position # Thai-x83
0xF88D # form for THAI CHARACTER MAI THO, left position # Thai-x99
0xF88E # form for THAI CHARACTER MAI THO, low position # Thai-x89
0xF88F # form for THAI CHARACTER MAI THO, low left position # Thai-x84
0xF890 # form for THAI CHARACTER MAI TRI, left position # Thai-x9A
0xF891 # form for THAI CHARACTER MAI TRI, low position # Thai-x8A
0xF892 # form for THAI CHARACTER MAI TRI, low left position # Thai-x85
0xF893 # form for THAI CHARACTER MAI CHATTAWA, left position # Thai-x9B
0xF894 # form for THAI CHARACTER MAI CHATTAWA, low position # Thai-x8B
0xF895 # form for THAI CHARACTER MAI CHATTAWA, low left position # Thai-x86
0xF896 # form for THAI CHARACTER THANTHAKHAT, left position # Thai-x9C
0xF897 # form for THAI CHARACTER THANTHAKHAT, low position # Thai-x8C
0xF898 # form for THAI CHARACTER THANTHAKHAT, low left position # Thai-x87
0xF899 # form for THAI CHARACTER NIKHAHIT, left position # Thai-x8F
# The following (6) are added for MacOS Hebrew encoding. Four of
# these are for the obsolete "canoral" codes that were used before
# System7.1/Worldscript to control positioning of nikud marks (points).
# In the future these 4 code points may be redefined.
0xF89A # Hebrew ligature lamed holam # Hebrew-xC0
0xF89B # Hebrew canoral 1 # Hebrew-xC2
0xF89C # Hebrew canoral 2 # Hebrew-xC3
0xF89D # Hebrew canoral 3 # Hebrew-xC4
0xF89E # Hebrew canoral 4 # Hebrew-xC5
0xF89F # Hebrew point qamats qatan # Hebrew-xDE
# The following (1) is added to handle mapping of the single undefined
# code point in MacOS Greek and Turkish encodings, thus permitting full
# round-trip fidelity.
0xF8A0 # undefined1 # Greek-0xFF, Turkish-0xF5
# The following (54) were added for MacOS Japanese encoding
# part 1 - Apple corporate Unicode chars for MacOS Japanese extended
# characters not in Unicode.
0xF8A1 # digit zero full stop # J-0x8591
0xF8A2 # roman numeral thirteen # J-0x85AB
0xF8A3 # roman numeral fourteen # J-0x85AC
0xF8A4 # roman numeral fifteen # J-0x85AD
0xF8A5 # small roman numeral thirteen # J-0x85BF
0xF8A6 # small roman numeral fourteen # J-0x85C0
0xF8A7 # small roman numeral fifteen # J-0x85C1
0xF8A8 # square m (meter?) # J-0x8645
0xF8A9 # square g (gram?) # J-0x864B
0xF8AA # square l (liter?) # J-0x8650
0xF8AB # square TB # J-0x865D
0xF8AC # FAX sign # J-0x869E
0xF8AD # downwards arrow leftwards of upwards arrow # J-0x86CE
0xF8AE # rightwards black arrow # J-0x86D3
0xF8AF # leftwards black arrow # J-0x86D4
0xF8B0 # upwards black arrow # J-0x86D5
0xF8B1 # downwards black arrow # J-0x86D6
0xF8B2 # square "limited company, ltd. [yuugen gaisha]" # J-0x87FB
0xF8B3 # square "foundation [zaidan houjin]" # J-0x87FC
0xF8B4 # inverted double prime quotation mark # J-0x8855
# part 2 - Apple corporate Unicode chars for MacOS Japanese vertical
# forms not in Unicode.
0xF8B5 # pres. form for vertical IDEOGRAPHIC COMMA # J-0xEB41
0xF8B6 # pres. form for vertical IDEOGRAPHIC FULL STOP # J-0xEB42
0xF8B7 # pres. form for vertical OVERLINE # J-0xEB50
0xF8B8 # pres. form for vertical KATAKANA-HIRAGANA PROLONGED SOUND MARK # J-0xEB5B
0xF8B9 # pres. form for vertical HYPHEN # J-0xEB5D
0xF8BA # pres. form for vertical WAVE DASH # J-0xEB60
0xF8BB # pres. form for vertical DOUBLE VERTICAL LINE # J-0xEB61
0xF8BC # pres. form for vertical FULLWIDTH VERTICAL LINE # J-0xEB62
0xF8BD # pres. form for vertical MIDLINE HORIZONTAL ELLIPSIS # J-0xEB63
0xF8BE # pres. form for vertical FULLWIDTH LEFT SQUARE BRACKET # J-0xEB6D
0xF8BF # pres. form for vertical FULLWIDTH RIGHT SQUARE BRACKET # J-0xEB6E
0xF8C0 # pres. form for vertical FULLWIDTH EQUALS SIGN # J-0xEB81
0xF8C1 # pres. form for vertical HIRAGANA LETTER SMALL A # J-0xEC9F
0xF8C2 # pres. form for vertical HIRAGANA LETTER SMALL I # J-0xECA1
0xF8C3 # pres. form for vertical HIRAGANA LETTER SMALL U # J-0xECA3
0xF8C4 # pres. form for vertical HIRAGANA LETTER SMALL E # J-0xECA5
0xF8C5 # pres. form for vertical HIRAGANA LETTER SMALL O # J-0xECA7
0xF8C6 # pres. form for vertical HIRAGANA LETTER SMALL TU # J-0xECC1
0xF8C7 # pres. form for vertical HIRAGANA LETTER SMALL YA # J-0xECE1
0xF8C8 # pres. form for vertical HIRAGANA LETTER SMALL YU # J-0xECE3
0xF8C9 # pres. form for vertical HIRAGANA LETTER SMALL YO # J-0xECE5
0xF8CA # pres. form for vertical HIRAGANA LETTER SMALL WA # J-0xECEC
0xF8CB # pres. form for vertical KATAKANA LETTER SMALL A # J-0xED40
0xF8CC # pres. form for vertical KATAKANA LETTER SMALL I # J-0xED42
0xF8CD # pres. form for vertical KATAKANA LETTER SMALL U # J-0xED44
0xF8CE # pres. form for vertical KATAKANA LETTER SMALL E # J-0xED46
0xF8CF # pres. form for vertical KATAKANA LETTER SMALL O # J-0xED48
0xF8D0 # pres. form for vertical KATAKANA LETTER SMALL TU # J-0xED62
0xF8D1 # pres. form for vertical KATAKANA LETTER SMALL YA # J-0xED83
0xF8D2 # pres. form for vertical KATAKANA LETTER SMALL YU # J-0xED85
0xF8D3 # pres. form for vertical KATAKANA LETTER SMALL YO # J-0xED87
0xF8D4 # pres. form for vertical KATAKANA LETTER SMALL WA # J-0xED8E
0xF8D5 # pres. form for vertical KATAKANA LETTER SMALL KA # J-0xED95
0xF8D6 # pres. form for vertical KATAKANA LETTER SMALL KE # J-0xED96
# The following (14) were added for MacOS Dingbats encoding
0xF8D7 # medium left parenthesis ornament # Dingbats-0x80
0xF8D8 # medium right parenthesis ornament # Dingbats-0x81
0xF8D9 # medium flattened left parenthesis ornament # Dingbats-0x82
0xF8DA # medium flattened right parenthesis ornament # Dingbats-0x83
0xF8DB # medium left-pointing angle bracket ornament # Dingbats-0x84
0xF8DC # medium right-pointing angle bracket ornament # Dingbats-0x85
0xF8DD # heavy left-pointing angle quotation mark ornament # Dingbats-0x86
0xF8DE # heavy right-pointing angle quotation mark ornament # Dingbats-0x87
0xF8DF # heavy left-pointing angle bracket ornament # Dingbats-0x88
0xF8E0 # heavy right-pointing angle bracket ornament # Dingbats-0x89
0xF8E1 # light left tortoise shell bracket ornament # Dingbats-0x8A
0xF8E2 # light right tortoise shell bracket ornament # Dingbats-0x8B
0xF8E3 # medium left curly bracket ornament # Dingbats-0x8C
0xF8E4 # medium right curly bracket ornament # Dingbats-0x8D
# The following (26) were added for MacOS Symbol encoding
0xF8E5 # radical extender # Symbol-0x60
0xF8E6 # vertical arrow extender # Symbol-0xBD
0xF8E7 # horizontal arrow extender # Symbol-0xBE
0xF8E8 # registered sign sans serif # Symbol-0xE2
0xF8E9 # copyright sign sans serif # Symbol-0xE3
0xF8EA # trade mark sign sans serif # Symbol-0xE4
0xF8EB # left parenthesis top # Symbol-0xE6
0xF8EC # left parenthesis extender # Symbol-0xE7
0xF8ED # left parenthesis bottom # Symbol-0xE8
0xF8EE # left square bracket top # Symbol-0xE9
0xF8EF # left square bracket extender # Symbol-0xEA
0xF8F0 # left square bracket bottom # Symbol-0xEB
0xF8F1 # left curly bracket top # Symbol-0xEC
0xF8F2 # left curly bracket center # Symbol-0xED
0xF8F3 # left curly bracket bottom # Symbol-0xEE
0xF8F4 # curly bracket extender # Symbol-0xEF
0xF8F5 # integral extender # Symbol-0xF4
0xF8F6 # right parenthesis top # Symbol-0xF6
0xF8F7 # right parenthesis extender # Symbol-0xF7
0xF8F8 # right parenthesis bottom # Symbol-0xF8
0xF8F9 # right square bracket top # Symbol-0xF9
0xF8FA # right square bracket extender # Symbol-0xFA
0xF8FB # right square bracket bottom # Symbol-0xFB
0xF8FC # right curly bracket top # Symbol-0xFC
0xF8FD # right curly bracket center # Symbol-0xFD
0xF8FE # right curly bracket bottom # Symbol-0xFE
# The following (1) was added for MacOS Roman encoding
0xF8FF # Apple logo # Roman-0xF0, Symbol-0xF0, Croatian-0xD8
# NOTE: The graphic image associated with the Apple logo character is
# not authorized for use without permission of Apple, and unauthorized
# use might constitute trademark infringement.

287
unicode/vendors/apple/croatian.txt vendored Normal file
View File

@@ -0,0 +1,287 @@
#
# Name: MacOS_Croatian [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <6>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Croatian code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Croatian code order.
#
# One of these mappings requires the use of a corporate character
# (for the Apple logo character). See the file "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Croatian:
# ------------------------
#
# The MacOS Croatian encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Croatian encoding is being used, you must check if the
# system region code is 68, verCroatia (or 25, verYugoCroatian,
# only used in older systems).
#
# This character set is a variant of standard MacOS Roman
# encoding, adding five accented letter case pairs to handle
# Croatian. It has 20 code point differences from standard
# MacOS Roman, but only 10 differences in repertoire.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x2206 # INCREMENT
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x220F # N-ARY PRODUCT
0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
0xBD 0x2126 # OHM SIGN
0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0xF8FF # Apple logo
0xD9 0x00A9 # COPYRIGHT SIGN
0xDA 0x2044 # FRACTION SLASH
0xDB 0x00A4 # CURRENCY SIGN
0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0x00C6 # LATIN CAPITAL LIGATURE AE
0xDF 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xE0 0x2013 # EN DASH
0xE1 0x00B7 # MIDDLE DOT
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 # PER MILLE SIGN
0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 # LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC # SMALL TILDE
0xF8 0x00AF # MACRON
0xF9 0x03C0 # GREEK SMALL LETTER PI
0xFA 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xFB 0x02DA # RING ABOVE
0xFC 0x00B8 # CEDILLA
0xFD 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xFE 0x00E6 # LATIN SMALL LIGATURE AE
0xFF 0x02C7 # CARON

287
unicode/vendors/apple/cyrillic.txt vendored Normal file
View File

@@ -0,0 +1,287 @@
#
# Name: MacOS_Cyrillic [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <5>)
# Date: 15 April 1995
# Authors: Peter Edberg <edberg1@applelink.apple.com>
# Judy Kettenhofen
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Cyrillic code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Cyrillic code order.
#
# Notes on MacOS Cyrillic:
# ------------------------
#
# The MacOS Cyrillic encoding includes the full Cyrillic letter
# repertoire of ISO 8859-5 (although not at the same code points).
# This covers most of the Slavic languages written in Cyrillic
# script.
#
# The MacOS Cyrillic encoding also includes a number of characters
# needed for the MacOS user interface (e.g. ellipsis), MacOS
# localization (bullet for echoing passwords, copyright sign, etc.
# All of the characters in MacOS Cyrillic that are also in the MacOS
# Roman encoding are at the same code point as MacOS Roman. This
# improves application compatibility (since some naughty applications
# hard-code the MacOS Roman code points of certain characters).
#
# A variant of MacOS Cyrillic is used for Ukrainian. A separate
# mapping table is available for Ukrainian.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x0410 # CYRILLIC CAPITAL LETTER A
0x81 0x0411 # CYRILLIC CAPITAL LETTER BE
0x82 0x0412 # CYRILLIC CAPITAL LETTER VE
0x83 0x0413 # CYRILLIC CAPITAL LETTER GHE
0x84 0x0414 # CYRILLIC CAPITAL LETTER DE
0x85 0x0415 # CYRILLIC CAPITAL LETTER IE
0x86 0x0416 # CYRILLIC CAPITAL LETTER ZHE
0x87 0x0417 # CYRILLIC CAPITAL LETTER ZE
0x88 0x0418 # CYRILLIC CAPITAL LETTER I
0x89 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
0x8A 0x041A # CYRILLIC CAPITAL LETTER KA
0x8B 0x041B # CYRILLIC CAPITAL LETTER EL
0x8C 0x041C # CYRILLIC CAPITAL LETTER EM
0x8D 0x041D # CYRILLIC CAPITAL LETTER EN
0x8E 0x041E # CYRILLIC CAPITAL LETTER O
0x8F 0x041F # CYRILLIC CAPITAL LETTER PE
0x90 0x0420 # CYRILLIC CAPITAL LETTER ER
0x91 0x0421 # CYRILLIC CAPITAL LETTER ES
0x92 0x0422 # CYRILLIC CAPITAL LETTER TE
0x93 0x0423 # CYRILLIC CAPITAL LETTER U
0x94 0x0424 # CYRILLIC CAPITAL LETTER EF
0x95 0x0425 # CYRILLIC CAPITAL LETTER HA
0x96 0x0426 # CYRILLIC CAPITAL LETTER TSE
0x97 0x0427 # CYRILLIC CAPITAL LETTER CHE
0x98 0x0428 # CYRILLIC CAPITAL LETTER SHA
0x99 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
0x9A 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
0x9B 0x042B # CYRILLIC CAPITAL LETTER YERU
0x9C 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
0x9D 0x042D # CYRILLIC CAPITAL LETTER E
0x9E 0x042E # CYRILLIC CAPITAL LETTER YU
0x9F 0x042F # CYRILLIC CAPITAL LETTER YA
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x0402 # CYRILLIC CAPITAL LETTER DJE
0xAC 0x0452 # CYRILLIC SMALL LETTER DJE
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x0403 # CYRILLIC CAPITAL LETTER GJE
0xAF 0x0453 # CYRILLIC SMALL LETTER GJE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x0408 # CYRILLIC CAPITAL LETTER JE
0xB8 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xB9 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
0xBA 0x0407 # CYRILLIC CAPITAL LETTER YI
0xBB 0x0457 # CYRILLIC SMALL LETTER YI
0xBC 0x0409 # CYRILLIC CAPITAL LETTER LJE
0xBD 0x0459 # CYRILLIC SMALL LETTER LJE
0xBE 0x040A # CYRILLIC CAPITAL LETTER NJE
0xBF 0x045A # CYRILLIC SMALL LETTER NJE
0xC0 0x0458 # CYRILLIC SMALL LETTER JE
0xC1 0x0405 # CYRILLIC CAPITAL LETTER DZE
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x040B # CYRILLIC CAPITAL LETTER TSHE
0xCC 0x045B # CYRILLIC SMALL LETTER TSHE
0xCD 0x040C # CYRILLIC CAPITAL LETTER KJE
0xCE 0x045C # CYRILLIC SMALL LETTER KJE
0xCF 0x0455 # CYRILLIC SMALL LETTER DZE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xD8 0x040E # CYRILLIC CAPITAL LETTER SHORT U
0xD9 0x045E # CYRILLIC SMALL LETTER SHORT U
0xDA 0x040F # CYRILLIC CAPITAL LETTER DZHE
0xDB 0x045F # CYRILLIC SMALL LETTER DZHE
0xDC 0x2116 # NUMERO SIGN
0xDD 0x0401 # CYRILLIC CAPITAL LETTER IO
0xDE 0x0451 # CYRILLIC SMALL LETTER IO
0xDF 0x044F # CYRILLIC SMALL LETTER YA
0xE0 0x0430 # CYRILLIC SMALL LETTER A
0xE1 0x0431 # CYRILLIC SMALL LETTER BE
0xE2 0x0432 # CYRILLIC SMALL LETTER VE
0xE3 0x0433 # CYRILLIC SMALL LETTER GHE
0xE4 0x0434 # CYRILLIC SMALL LETTER DE
0xE5 0x0435 # CYRILLIC SMALL LETTER IE
0xE6 0x0436 # CYRILLIC SMALL LETTER ZHE
0xE7 0x0437 # CYRILLIC SMALL LETTER ZE
0xE8 0x0438 # CYRILLIC SMALL LETTER I
0xE9 0x0439 # CYRILLIC SMALL LETTER SHORT I
0xEA 0x043A # CYRILLIC SMALL LETTER KA
0xEB 0x043B # CYRILLIC SMALL LETTER EL
0xEC 0x043C # CYRILLIC SMALL LETTER EM
0xED 0x043D # CYRILLIC SMALL LETTER EN
0xEE 0x043E # CYRILLIC SMALL LETTER O
0xEF 0x043F # CYRILLIC SMALL LETTER PE
0xF0 0x0440 # CYRILLIC SMALL LETTER ER
0xF1 0x0441 # CYRILLIC SMALL LETTER ES
0xF2 0x0442 # CYRILLIC SMALL LETTER TE
0xF3 0x0443 # CYRILLIC SMALL LETTER U
0xF4 0x0444 # CYRILLIC SMALL LETTER EF
0xF5 0x0445 # CYRILLIC SMALL LETTER HA
0xF6 0x0446 # CYRILLIC SMALL LETTER TSE
0xF7 0x0447 # CYRILLIC SMALL LETTER CHE
0xF8 0x0448 # CYRILLIC SMALL LETTER SHA
0xF9 0x0449 # CYRILLIC SMALL LETTER SHCHA
0xFA 0x044A # CYRILLIC SMALL LETTER HARD SIGN
0xFB 0x044B # CYRILLIC SMALL LETTER YERU
0xFC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
0xFD 0x044D # CYRILLIC SMALL LETTER E
0xFE 0x044E # CYRILLIC SMALL LETTER YU
0xFF 0x00A4 # CURRENCY SIGN

260
unicode/vendors/apple/dingbat.txt vendored Normal file
View File

@@ -0,0 +1,260 @@
#
# Name: MacOS_Dingbats [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <4>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Dingbats code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Dingbats code order.
#
# Several of these mappings require the use of corporate
# characters. See the file "MacOS-CorpCharList".
#
# Notes on MacOS Dingbats:
# ------------------------
#
# The MacOS Dingbats encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Dingbats encoding is being used, you must check if the
# font name is "Zapf Dingbats".
#
# The layout of the Dingbats character set is identical to or
# a superset of the layout of the Adobe Zapf Dingbats encoding
# vector.
#
##################
0x20 0x0020 # SPACE
0x21 0x2701 # UPPER BLADE SCISSORS
0x22 0x2702 # BLACK SCISSORS
0x23 0x2703 # LOWER BLADE SCISSORS
0x24 0x2704 # WHITE SCISSORS
0x25 0x260E # BLACK TELEPHONE
0x26 0x2706 # TELEPHONE LOCATION SIGN
0x27 0x2707 # TAPE DRIVE
0x28 0x2708 # AIRPLANE
0x29 0x2709 # ENVELOPE
0x2A 0x261B # BLACK RIGHT POINTING INDEX
0x2B 0x261E # WHITE RIGHT POINTING INDEX
0x2C 0x270C # VICTORY HAND
0x2D 0x270D # WRITING HAND
0x2E 0x270E # LOWER RIGHT PENCIL
0x2F 0x270F # PENCIL
0x30 0x2710 # UPPER RIGHT PENCIL
0x31 0x2711 # WHITE NIB
0x32 0x2712 # BLACK NIB
0x33 0x2713 # CHECK MARK
0x34 0x2714 # HEAVY CHECK MARK
0x35 0x2715 # MULTIPLICATION X
0x36 0x2716 # HEAVY MULTIPLICATION X
0x37 0x2717 # BALLOT X
0x38 0x2718 # HEAVY BALLOT X
0x39 0x2719 # OUTLINED GREEK CROSS
0x3A 0x271A # HEAVY GREEK CROSS
0x3B 0x271B # OPEN CENTRE CROSS
0x3C 0x271C # HEAVY OPEN CENTRE CROSS
0x3D 0x271D # LATIN CROSS
0x3E 0x271E # SHADOWED WHITE LATIN CROSS
0x3F 0x271F # OUTLINED LATIN CROSS
0x40 0x2720 # MALTESE CROSS
0x41 0x2721 # STAR OF DAVID
0x42 0x2722 # FOUR TEARDROP-SPOKED ASTERISK
0x43 0x2723 # FOUR BALLOON-SPOKED ASTERISK
0x44 0x2724 # HEAVY FOUR BALLOON-SPOKED ASTERISK
0x45 0x2725 # FOUR CLUB-SPOKED ASTERISK
0x46 0x2726 # BLACK FOUR POINTED STAR
0x47 0x2727 # WHITE FOUR POINTED STAR
0x48 0x2605 # BLACK STAR
0x49 0x2729 # STRESS OUTLINED WHITE STAR
0x4A 0x272A # CIRCLED WHITE STAR
0x4B 0x272B # OPEN CENTRE BLACK STAR
0x4C 0x272C # BLACK CENTRE WHITE STAR
0x4D 0x272D # OUTLINED BLACK STAR
0x4E 0x272E # HEAVY OUTLINED BLACK STAR
0x4F 0x272F # PINWHEEL STAR
0x50 0x2730 # SHADOWED WHITE STAR
0x51 0x2731 # HEAVY ASTERISK
0x52 0x2732 # OPEN CENTRE ASTERISK
0x53 0x2733 # EIGHT SPOKED ASTERISK
0x54 0x2734 # EIGHT POINTED BLACK STAR
0x55 0x2735 # EIGHT POINTED PINWHEEL STAR
0x56 0x2736 # SIX POINTED BLACK STAR
0x57 0x2737 # EIGHT POINTED RECTILINEAR BLACK STAR
0x58 0x2738 # HEAVY EIGHT POINTED RECTILINEAR BLACK STAR
0x59 0x2739 # TWELVE POINTED BLACK STAR
0x5A 0x273A # SIXTEEN POINTED ASTERISK
0x5B 0x273B # TEARDROP-SPOKED ASTERISK
0x5C 0x273C # OPEN CENTRE TEARDROP-SPOKED ASTERISK
0x5D 0x273D # HEAVY TEARDROP-SPOKED ASTERISK
0x5E 0x273E # SIX PETALLED BLACK AND WHITE FLORETTE
0x5F 0x273F # BLACK FLORETTE
0x60 0x2740 # WHITE FLORETTE
0x61 0x2741 # EIGHT PETALLED OUTLINED BLACK FLORETTE
0x62 0x2742 # CIRCLED OPEN CENTRE EIGHT POINTED STAR
0x63 0x2743 # HEAVY TEARDROP-SPOKED PINWHEEL ASTERISK
0x64 0x2744 # SNOWFLAKE
0x65 0x2745 # TIGHT TRIFOLIATE SNOWFLAKE
0x66 0x2746 # HEAVY CHEVRON SNOWFLAKE
0x67 0x2747 # SPARKLE
0x68 0x2748 # HEAVY SPARKLE
0x69 0x2749 # BALLOON-SPOKED ASTERISK
0x6A 0x274A # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK
0x6B 0x274B # HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK
0x6C 0x25CF # BLACK CIRCLE
0x6D 0x274D # SHADOWED WHITE CIRCLE
0x6E 0x25A0 # BLACK SQUARE
0x6F 0x274F # LOWER RIGHT DROP-SHADOWED WHITE SQUARE
0x70 0x2750 # UPPER RIGHT DROP-SHADOWED WHITE SQUARE
0x71 0x2751 # LOWER RIGHT SHADOWED WHITE SQUARE
0x72 0x2752 # UPPER RIGHT SHADOWED WHITE SQUARE
0x73 0x25B2 # BLACK UP-POINTING TRIANGLE
0x74 0x25BC # BLACK DOWN-POINTING TRIANGLE
0x75 0x25C6 # BLACK DIAMOND
0x76 0x2756 # BLACK DIAMOND MINUS WHITE X
0x77 0x25D7 # RIGHT HALF BLACK CIRCLE
0x78 0x2758 # LIGHT VERTICAL BAR
0x79 0x2759 # MEDIUM VERTICAL BAR
0x7A 0x275A # HEAVY VERTICAL BAR
0x7B 0x275B # HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT
0x7C 0x275C # HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT
0x7D 0x275D # HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT
0x7E 0x275E # HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
0x80 0xF8D7 # medium left parenthesis ornament
0x81 0xF8D8 # medium right parenthesis ornament
0x82 0xF8D9 # medium flattened left parenthesis ornament
0x83 0xF8DA # medium flattened right parenthesis ornament
0x84 0xF8DB # medium left-pointing angle bracket ornament
0x85 0xF8DC # medium right-pointing angle bracket ornament
0x86 0xF8DD # heavy left-pointing angle quotation mark ornament
0x87 0xF8DE # heavy right-pointing angle quotation mark ornament
0x88 0xF8DF # heavy left-pointing angle bracket ornament
0x89 0xF8E0 # heavy right-pointing angle bracket ornament
0x8A 0xF8E1 # light left tortoise shell bracket ornament
0x8B 0xF8E2 # light right tortoise shell bracket ornament
0x8C 0xF8E3 # medium left curly bracket ornament
0x8D 0xF8E4 # medium right curly bracket ornament
0xA1 0x2761 # CURVED STEM PARAGRAPH SIGN ORNAMENT
0xA2 0x2762 # HEAVY EXCLAMATION MARK ORNAMENT
0xA3 0x2763 # HEAVY HEART EXCLAMATION MARK ORNAMENT
0xA4 0x2764 # HEAVY BLACK HEART
0xA5 0x2765 # ROTATED HEAVY BLACK HEART BULLET
0xA6 0x2766 # FLORAL HEART
0xA7 0x2767 # ROTATED FLORAL HEART BULLET
0xA8 0x2663 # BLACK CLUB SUIT
0xA9 0x2666 # BLACK DIAMOND SUIT
0xAA 0x2665 # BLACK HEART SUIT
0xAB 0x2660 # BLACK SPADE SUIT
0xAC 0x2460 # CIRCLED DIGIT ONE
0xAD 0x2461 # CIRCLED DIGIT TWO
0xAE 0x2462 # CIRCLED DIGIT THREE
0xAF 0x2463 # CIRCLED DIGIT FOUR
0xB0 0x2464 # CIRCLED DIGIT FIVE
0xB1 0x2465 # CIRCLED DIGIT SIX
0xB2 0x2466 # CIRCLED DIGIT SEVEN
0xB3 0x2467 # CIRCLED DIGIT EIGHT
0xB4 0x2468 # CIRCLED DIGIT NINE
0xB5 0x2469 # CIRCLED NUMBER TEN
0xB6 0x2776 # DINGBAT NEGATIVE CIRCLED DIGIT ONE
0xB7 0x2777 # DINGBAT NEGATIVE CIRCLED DIGIT TWO
0xB8 0x2778 # DINGBAT NEGATIVE CIRCLED DIGIT THREE
0xB9 0x2779 # DINGBAT NEGATIVE CIRCLED DIGIT FOUR
0xBA 0x277A # DINGBAT NEGATIVE CIRCLED DIGIT FIVE
0xBB 0x277B # DINGBAT NEGATIVE CIRCLED DIGIT SIX
0xBC 0x277C # DINGBAT NEGATIVE CIRCLED DIGIT SEVEN
0xBD 0x277D # DINGBAT NEGATIVE CIRCLED DIGIT EIGHT
0xBE 0x277E # DINGBAT NEGATIVE CIRCLED DIGIT NINE
0xBF 0x277F # DINGBAT NEGATIVE CIRCLED NUMBER TEN
0xC0 0x2780 # DINGBAT CIRCLED SANS-SERIF DIGIT ONE
0xC1 0x2781 # DINGBAT CIRCLED SANS-SERIF DIGIT TWO
0xC2 0x2782 # DINGBAT CIRCLED SANS-SERIF DIGIT THREE
0xC3 0x2783 # DINGBAT CIRCLED SANS-SERIF DIGIT FOUR
0xC4 0x2784 # DINGBAT CIRCLED SANS-SERIF DIGIT FIVE
0xC5 0x2785 # DINGBAT CIRCLED SANS-SERIF DIGIT SIX
0xC6 0x2786 # DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN
0xC7 0x2787 # DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT
0xC8 0x2788 # DINGBAT CIRCLED SANS-SERIF DIGIT NINE
0xC9 0x2789 # DINGBAT CIRCLED SANS-SERIF NUMBER TEN
0xCA 0x278A # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE
0xCB 0x278B # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO
0xCC 0x278C # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE
0xCD 0x278D # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR
0xCE 0x278E # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE
0xCF 0x278F # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX
0xD0 0x2790 # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN
0xD1 0x2791 # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT
0xD2 0x2792 # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE
0xD3 0x2793 # DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN
0xD4 0x2794 # HEAVY WIDE-HEADED RIGHTWARDS ARROW
0xD5 0x2192 # RIGHTWARDS ARROW
0xD6 0x2194 # LEFT RIGHT ARROW
0xD7 0x2195 # UP DOWN ARROW
0xD8 0x2798 # HEAVY SOUTH EAST ARROW
0xD9 0x2799 # HEAVY RIGHTWARDS ARROW
0xDA 0x279A # HEAVY NORTH EAST ARROW
0xDB 0x279B # DRAFTING POINT RIGHTWARDS ARROW
0xDC 0x279C # HEAVY ROUND-TIPPED RIGHTWARDS ARROW
0xDD 0x279D # TRIANGLE-HEADED RIGHTWARDS ARROW
0xDE 0x279E # HEAVY TRIANGLE-HEADED RIGHTWARDS ARROW
0xDF 0x279F # DASHED TRIANGLE-HEADED RIGHTWARDS ARROW
0xE0 0x27A0 # HEAVY DASHED TRIANGLE-HEADED RIGHTWARDS ARROW
0xE1 0x27A1 # BLACK RIGHTWARDS ARROW
0xE2 0x27A2 # THREE-D TOP-LIGHTED RIGHTWARDS ARROWHEAD
0xE3 0x27A3 # THREE-D BOTTOM-LIGHTED RIGHTWARDS ARROWHEAD
0xE4 0x27A4 # BLACK RIGHTWARDS ARROWHEAD
0xE5 0x27A5 # HEAVY BLACK CURVED DOWNWARDS AND RIGHTWARDS ARROW
0xE6 0x27A6 # HEAVY BLACK CURVED UPWARDS AND RIGHTWARDS ARROW
0xE7 0x27A7 # SQUAT BLACK RIGHTWARDS ARROW
0xE8 0x27A8 # HEAVY CONCAVE-POINTED BLACK RIGHTWARDS ARROW
0xE9 0x27A9 # RIGHT-SHADED WHITE RIGHTWARDS ARROW
0xEA 0x27AA # LEFT-SHADED WHITE RIGHTWARDS ARROW
0xEB 0x27AB # BACK-TILTED SHADOWED WHITE RIGHTWARDS ARROW
0xEC 0x27AC # FRONT-TILTED SHADOWED WHITE RIGHTWARDS ARROW
0xED 0x27AD # HEAVY LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
0xEE 0x27AE # HEAVY UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
0xEF 0x27AF # NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
0xF1 0x27B1 # NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
0xF2 0x27B2 # CIRCLED HEAVY WHITE RIGHTWARDS ARROW
0xF3 0x27B3 # WHITE-FEATHERED RIGHTWARDS ARROW
0xF4 0x27B4 # BLACK-FEATHERED SOUTH EAST ARROW
0xF5 0x27B5 # BLACK-FEATHERED RIGHTWARDS ARROW
0xF6 0x27B6 # BLACK-FEATHERED NORTH EAST ARROW
0xF7 0x27B7 # HEAVY BLACK-FEATHERED SOUTH EAST ARROW
0xF8 0x27B8 # HEAVY BLACK-FEATHERED RIGHTWARDS ARROW
0xF9 0x27B9 # HEAVY BLACK-FEATHERED NORTH EAST ARROW
0xFA 0x27BA # TEARDROP-BARBED RIGHTWARDS ARROW
0xFB 0x27BB # HEAVY TEARDROP-SHANKED RIGHTWARDS ARROW
0xFC 0x27BC # WEDGE-TAILED RIGHTWARDS ARROW
0xFD 0x27BD # HEAVY WEDGE-TAILED RIGHTWARDS ARROW
0xFE 0x27BE # OPEN OUTLINED RIGHTWARDS ARROW

290
unicode/vendors/apple/greek.txt vendored Normal file
View File

@@ -0,0 +1,290 @@
#
# Name: MacOS_Greek [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <7>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Greek code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Greek code order.
#
# One of these mappings requires the use of a corporate character
# (for an undefined code point). See the file "MacOS-CorpCharList".
#
# Notes on MacOS Greek:
# ---------------------
#
# Although a MacOS script code is defined for Greek (smGreek = 6),
# the Greek localized system does not currently use it (the font
# family IDs are in the MacOS Roman range). To determine if the
# Greek encoding is being used when the script code is smRoman (0),
# you must check if the system region code is 20, verGreece.
#
# The MacOS Greek encoding is a superset of the repertoire of
# ISO 8859-5 (although characters are not at the same code points).
#
# This character set was used by all MacOS Greek systems 6.x and
# 7.x except for system 6.0.7, which used a variant character set
# but was quickly replaced with Greek system 6.0.7.1 using the
# standard character set documented here. Greek system 4.1 used a
# variant Greek set that had ISO 8859-7 in 0xA0-0xFF (with some
# holes filled in with DTP characters), and MacOS Roman accented
# Roman letters in 0x80-0x9F.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00B9 # SUPERSCRIPT ONE
0x82 0x00B2 # SUPERSCRIPT TWO
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00B3 # SUPERSCRIPT THREE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x0385 # GREEK DIALYTIKA TONOS
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x0384 # GREEK TONOS
0x8C 0x00A8 # DIAERESIS
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00A3 # POUND SIGN
0x93 0x2122 # TRADE MARK SIGN
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x2022 # BULLET
0x97 0x00BD # VULGAR FRACTION ONE HALF
0x98 0x2030 # PER MILLE SIGN
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00A6 # BROKEN BAR
0x9C 0x00AD # SOFT HYPHEN
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x0393 # GREEK CAPITAL LETTER GAMMA
0xA2 0x0394 # GREEK CAPITAL LETTER DELTA
0xA3 0x0398 # GREEK CAPITAL LETTER THETA
0xA4 0x039B # GREEK CAPITAL LETTER LAMBDA
0xA5 0x039E # GREEK CAPITAL LETTER XI
0xA6 0x03A0 # GREEK CAPITAL LETTER PI
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x03A3 # GREEK CAPITAL LETTER SIGMA
0xAB 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0xAC 0x00A7 # SECTION SIGN
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x00B0 # DEGREE SIGN
0xAF 0x0387 # GREEK ANO TELEIA
0xB0 0x0391 # GREEK CAPITAL LETTER ALPHA
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00A5 # YEN SIGN
0xB5 0x0392 # GREEK CAPITAL LETTER BETA
0xB6 0x0395 # GREEK CAPITAL LETTER EPSILON
0xB7 0x0396 # GREEK CAPITAL LETTER ZETA
0xB8 0x0397 # GREEK CAPITAL LETTER ETA
0xB9 0x0399 # GREEK CAPITAL LETTER IOTA
0xBA 0x039A # GREEK CAPITAL LETTER KAPPA
0xBB 0x039C # GREEK CAPITAL LETTER MU
0xBC 0x03A6 # GREEK CAPITAL LETTER PHI
0xBD 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0xBE 0x03A8 # GREEK CAPITAL LETTER PSI
0xBF 0x03A9 # GREEK CAPITAL LETTER OMEGA
0xC0 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS
0xC1 0x039D # GREEK CAPITAL LETTER NU
0xC2 0x00AC # NOT SIGN
0xC3 0x039F # GREEK CAPITAL LETTER OMICRON
0xC4 0x03A1 # GREEK CAPITAL LETTER RHO
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x03A4 # GREEK CAPITAL LETTER TAU
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x03A5 # GREEK CAPITAL LETTER UPSILON
0xCC 0x03A7 # GREEK CAPITAL LETTER CHI
0xCD 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS
0xCE 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x2013 # EN DASH
0xD1 0x2015 # HORIZONTAL BAR
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS
0xD8 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS
0xD9 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS
0xDA 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS
0xDB 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS
0xDC 0x03AE # GREEK SMALL LETTER ETA WITH TONOS
0xDD 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS
0xDE 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS
0xDF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS
0xE0 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS
0xE1 0x03B1 # GREEK SMALL LETTER ALPHA
0xE2 0x03B2 # GREEK SMALL LETTER BETA
0xE3 0x03C8 # GREEK SMALL LETTER PSI
0xE4 0x03B4 # GREEK SMALL LETTER DELTA
0xE5 0x03B5 # GREEK SMALL LETTER EPSILON
0xE6 0x03C6 # GREEK SMALL LETTER PHI
0xE7 0x03B3 # GREEK SMALL LETTER GAMMA
0xE8 0x03B7 # GREEK SMALL LETTER ETA
0xE9 0x03B9 # GREEK SMALL LETTER IOTA
0xEA 0x03BE # GREEK SMALL LETTER XI
0xEB 0x03BA # GREEK SMALL LETTER KAPPA
0xEC 0x03BB # GREEK SMALL LETTER LAMBDA
0xED 0x03BC # GREEK SMALL LETTER MU
0xEE 0x03BD # GREEK SMALL LETTER NU
0xEF 0x03BF # GREEK SMALL LETTER OMICRON
0xF0 0x03C0 # GREEK SMALL LETTER PI
0xF1 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS
0xF2 0x03C1 # GREEK SMALL LETTER RHO
0xF3 0x03C3 # GREEK SMALL LETTER SIGMA
0xF4 0x03C4 # GREEK SMALL LETTER TAU
0xF5 0x03B8 # GREEK SMALL LETTER THETA
0xF6 0x03C9 # GREEK SMALL LETTER OMEGA
0xF7 0x03C2 # GREEK SMALL LETTER FINAL SIGMA
0xF8 0x03C7 # GREEK SMALL LETTER CHI
0xF9 0x03C5 # GREEK SMALL LETTER UPSILON
0xFA 0x03B6 # GREEK SMALL LETTER ZETA
0xFB 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xFC 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xFD 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xFE 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xFF 0xF8A0 # undefined1

388
unicode/vendors/apple/hebrew.txt vendored Normal file
View File

@@ -0,0 +1,388 @@
#
# Name: MacOS_Hebrew [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.1 (from internal ufrm version <8>)
# Date: 15 November 1995
# Authors: Peter Edberg <edberg1@applelink.apple.com>
# Judy Kettenhofen
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Hebrew code (in hex as 0xNN)
# Column #2 is the Unicode or Unicode sequence (in hex as 0xNNNN
# or 0xNNNN+0xNNNN+0xNNNN).
# Column #3 is the Unicode name (follows a comment sign, '#')
# Note: The abbreviations LRO, RLO, and PDF are used for
# LEFT-TO-RIGHT OVERRIDE, RIGHT-TO-LEFT OVERRIDE, and
# POP DIRECTIONAL FORMATTING, respectively.
#
# The entries are in MacOS Hebrew code order.
#
# Note that in many cases, a single MacOS Hebrew character maps
# to a sequence of Unicode characters: LRO or RLO plus some Unicode
# character + PDF. This is indicated by joining the Unicode
# characters with '+'. This happens when the direction class of
# the MacOS Hebrew character is different than the direction class
# of the Unicode character (usually the MacOS Hebrew character has
# a strong direction class and the corresponding Unicode character
# is neutral or has a wek direction class).
#
# Notes on MacOS Hebrew:
# ----------------------
#
# 1. General
#
# The MacOS Hebrew character set incorporates the Hebrew letter
# repertoire of ISO 8859-8, and uses the same code points, 0xE0-0xFA.
# It also incorporates the ASCII character set. In addition, the
# MacOS Hebrew character set includes the following:
#
# - Hebrew points (nikud marks) at xC6, xCB-xCF and xD8-xDF. These are
# non-spacing combining marks. Note that the RAFE point at 0xD8 is
# not displayed correctly in some fonts, and cannot be typed using
# the keyboard layouts in the current Hebrew localized systems. Also
# note: The character given in Unicode as QAMATS (U+05B8) actually
# refers to two different sounds, depending on context. For example,
# when ALEF is followed by QAMATS, the QAMATS can actually refer to
# two different sounds depending on the following letters. The MacOS
# Hebrew character set separately encodes these two sounds for the
# same graphic shape, as "qamats" (0xCB) and "qamats qatan" (0xDE).
# The "qamats" character is more common, so it is mapped to the
# Unicode QAMATS; "qamats qatan" can only be used with a limited
# number of characters, and it is mapped (for roundtrip fidelity) to
# a character in the corporate use zone.
#
# - Various Hebrew ligatures at 0x81, 0xC0, 0xC7, 0xC8, 0xD6, and
# 0xD7. One of these must be mapped to a corporate zone character
# for roundtrip fidelity. Also note that the Yiddish YOD YOD PATAH
# ligature at 0x81 is missing in some fonts.
#
# - The NEW SHEQEL SIGN at 0xA6.
#
# - Latin characters with diacritics at 0x80 and 0x82-0x9F. However,
# most of these cannot be typed using the keyboard layouts in the
# Hebrew localized systems.
#
# - Right-left versions of certain ASCII punctuation, symbols and
# digits: 0xA0-0xA5, 0xA7-0xBF, 0xFB-0xFF. See section 2 (below)
# on directional characters.
#
# - Miscellaneous additional punctuation at 0xC1, 0xC9, 0xCA, and
# 0xD0-0xD5. There is a variant of the Hebrew encoding in which
# the LEFT SINGLE QUOTATION MARK at 0xD4 is replaced by FIGURE
# SPACE. The glyphs for some of the other punctuation characters
# are missing in some fonts.
#
# - Four obsolete characters at 0xC2-0xC5 known as canorals (not to
# be confused with cantillation marks!). These were used for
# manual positioning of nikud marks before System 7.1 (at which
# point nikud positioning became automatic with WorldScript.).
# However, they may have been incorporated in stored text, so they
# must be mapped to corporate zone characters for roundtrip
# fidelity.
#
# The MacOS Hebrew character set supports the Hebrew and Yiddish
# languages.
#
# 2. Directional characters and roundtrip fidelity
#
# The MacOS Hebrew character set was developed around 1987. At that
# time the bidirectional line line layout algorithm used in the MacOS
# Hebrew system was fairly simple; it used only a few direction
# classes (instead of the 12 or so now used in the Unicode
# bidirectional algorithm). In order to permit users to handle some
# tricky layout problems, certain punctuation, symbol, and digit
# characters have duplicate code points, one with a left-right
# direction attribute and the other with a right-left direction attribute.
#
# For example, percent is encoded at 0x25 with a left-right
# attribute, and at 0xA5 with a right-left attribute. However, there
# is only one percent character in Unicode. We need to have a way
# to map both MacOS Hebrew percent characters to Unicode and back
# again without loss of information. Mapping one of the MacOS Hebrew
# percent characters to a code in the Unicode corporate use zone is
# undesirable, since both of the percent characters are likely to
# be used in text that is interchanged.
#
# The problem is solved with the use of direction override characters
# and direction-dependent mappings. When mapping from MacOS Hebrew to
# Unicode, such problem characters are surrounded with an appropriate
# direction override:
# MacOS Hebrew 0x25 percent (left) ->
# Unicode 0x202D (LRO) + 0x0025 (PERCENT SIGN) + 0x202C (PDF)
# MacOS Hebrew 0xA5 percent (right) ->
# Unicode 0x202E (RLO) + 0x0025 (PERCENT SIGN) + 0x202C (PDF)
# When mapping from Unicode to MacOS Hebrew, the MacOS Unicode
# converter uses the Unicode bidirectional algorithm to determine
# resolved directions. The mapping from Unicode to MacOS Hebrew can
# then be disambiguated by the use of the resolved direction:
# Unicode 0x0025 -> MacOS Hebrew 0x25 (if L) or 0xA5 (if R)
#
# However, note that this means we also need to discard the direction
# override characters when mapping from Unicode to MacOS Hebrew.
#
# Even when direction overrides are not needed for roundtrip
# fidelity, they are sometimes used when mapping MacOS Hebrew
# characters to Unicode in order to achieve similar text layout with
# the resulting Unicode text. For example, the single MacOS Hebrew
# ellipsis character has direction class right-left,and there is no
# left-right version. However, the Unicode HORIZONTAL ELLIPSIS
# character has direction class neutral (which means it may end up
# with a resolved direction of left-right if surrounded by left-right
# characters). When mapping the MacOS Hebrew ellipsis to Unicode, it
# is surrounded with a direction override to help preserve proper
# text layout. The resolved direction is not needed or used when
# mapping the Unicode HORIZONTAL ELLIPSIS back to MacOS Hebrew.
#
##################
0x20 0x202D+0x0020+0x202C # LRO + SPACE + PDF
0x21 0x202D+0x0021+0x202C # LRO + EXCLAMATION MARK + PDF
0x22 0x202D+0x0022+0x202C # LRO + QUOTATION MARK + PDF
0x23 0x202D+0x0023+0x202C # LRO + NUMBER SIGN + PDF
0x24 0x202D+0x0024+0x202C # LRO + DOLLAR SIGN + PDF
0x25 0x202D+0x0025+0x202C # LRO + PERCENT SIGN + PDF
0x26 0x0026 # AMPERSAND
0x27 0x202D+0x0027+0x202C # LRO + APOSTROPHE + PDF
0x28 0x202D+0x0028+0x202C # LRO + LEFT PARENTHESIS + PDF
0x29 0x202D+0x0029+0x202C # LRO + RIGHT PARENTHESIS + PDF
0x2A 0x202D+0x002A+0x202C # LRO + ASTERISK + PDF
0x2B 0x202D+0x002B+0x202C # LRO + PLUS SIGN + PDF
0x2C 0x202D+0x002C+0x202C # LRO + COMMA + PDF
0x2D 0x202D+0x002D+0x202C # LRO + HYPHEN-MINUS + PDF
0x2E 0x202D+0x002E+0x202C # LRO + FULL STOP + PDF
0x2F 0x202D+0x002F+0x202C # LRO + SOLIDUS + PDF
0x30 0x202D+0x0030+0x202C # LRO + DIGIT ZERO + PDF
0x31 0x202D+0x0031+0x202C # LRO + DIGIT ONE + PDF
0x32 0x202D+0x0032+0x202C # LRO + DIGIT TWO + PDF
0x33 0x202D+0x0033+0x202C # LRO + DIGIT THREE + PDF
0x34 0x202D+0x0034+0x202C # LRO + DIGIT FOUR + PDF
0x35 0x202D+0x0035+0x202C # LRO + DIGIT FIVE + PDF
0x36 0x202D+0x0036+0x202C # LRO + DIGIT SIX + PDF
0x37 0x202D+0x0037+0x202C # LRO + DIGIT SEVEN + PDF
0x38 0x202D+0x0038+0x202C # LRO + DIGIT EIGHT + PDF
0x39 0x202D+0x0039+0x202C # LRO + DIGIT NINE + PDF
0x3A 0x202D+0x003A+0x202C # LRO + COLON + PDF
0x3B 0x202D+0x003B+0x202C # LRO + SEMICOLON + PDF
0x3C 0x202D+0x003C+0x202C # LRO + LESS-THAN SIGN + PDF
0x3D 0x202D+0x003D+0x202C # LRO + EQUALS SIGN + PDF
0x3E 0x202D+0x003E+0x202C # LRO + GREATER-THAN SIGN + PDF
0x3F 0x202D+0x003F+0x202C # LRO + QUESTION MARK + PDF
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x202D+0x005B+0x202C # LRO + LEFT SQUARE BRACKET + PDF
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x202D+0x005D+0x202C # LRO + RIGHT SQUARE BRACKET + PDF
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x202D+0x007B+0x202C # LRO + LEFT CURLY BRACKET + PDF
0x7C 0x202D+0x007C+0x202C # LRO + VERTICAL LINE + PDF
0x7D 0x202D+0x007D+0x202C # LRO + RIGHT CURLY BRACKET + PDF
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0xFB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x202E+0x0020+0x202C # RLO + SPACE + PDF
0xA1 0x202E+0x0021+0x202C # RLO + EXCLAMATION MARK + PDF
0xA2 0x202E+0x0022+0x202C # RLO + QUOTATION MARK + PDF
0xA3 0x202E+0x0023+0x202C # RLO + NUMBER SIGN + PDF
0xA4 0x202E+0x0024+0x202C # RLO + DOLLAR SIGN + PDF
0xA5 0x202E+0x0025+0x202C # RLO + PERCENT SIGN + PDF
0xA6 0x20AA # NEW SHEQEL SIGN
0xA7 0x202E+0x0027+0x202C # RLO + APOSTROPHE + PDF
0xA8 0x202E+0x0028+0x202C # RLO + LEFT PARENTHESIS + PDF
0xA9 0x202E+0x0029+0x202C # RLO + RIGHT PARENTHESIS + PDF
0xAA 0x202E+0x002A+0x202C # RLO + ASTERISK + PDF
0xAB 0x202E+0x002B+0x202C # RLO + PLUS SIGN + PDF
0xAC 0x202E+0x002C+0x202C # RLO + COMMA + PDF
0xAD 0x202E+0x002D+0x202C # RLO + HYPHEN-MINUS + PDF
0xAE 0x202E+0x002E+0x202C # RLO + FULL STOP + PDF
0xAF 0x202E+0x002F+0x202C # RLO + SOLIDUS + PDF
0xB0 0x202E+0x0030+0x202C # RLO + DIGIT ZERO + PDF
0xB1 0x202E+0x0031+0x202C # RLO + DIGIT ONE + PDF
0xB2 0x202E+0x0032+0x202C # RLO + DIGIT TWO + PDF
0xB3 0x202E+0x0033+0x202C # RLO + DIGIT THREE + PDF
0xB4 0x202E+0x0034+0x202C # RLO + DIGIT FOUR + PDF
0xB5 0x202E+0x0035+0x202C # RLO + DIGIT FIVE + PDF
0xB6 0x202E+0x0036+0x202C # RLO + DIGIT SIX + PDF
0xB7 0x202E+0x0037+0x202C # RLO + DIGIT SEVEN + PDF
0xB8 0x202E+0x0038+0x202C # RLO + DIGIT EIGHT + PDF
0xB9 0x202E+0x0039+0x202C # RLO + DIGIT NINE + PDF
0xBA 0x202E+0x003A+0x202C # RLO + COLON + PDF
0xBB 0x202E+0x003B+0x202C # RLO + SEMICOLON + PDF
0xBC 0x202E+0x003C+0x202C # RLO + LESS-THAN SIGN + PDF
0xBD 0x202E+0x003D+0x202C # RLO + EQUALS SIGN + PDF
0xBE 0x202E+0x003E+0x202C # RLO + GREATER-THAN SIGN + PDF
0xBF 0x202E+0x003F+0x202C # RLO + QUESTION MARK + PDF
0xC0 0xF89A # Hebrew ligature lamed holam
0xC1 0x202E+0x201E+0x202C # RLO + DOUBLE LOW-9 QUOTATION MARK + PDF
0xC2 0xF89B # Hebrew canoral 1
0xC3 0xF89C # Hebrew canoral 2
0xC4 0xF89D # Hebrew canoral 3
0xC5 0xF89E # Hebrew canoral 4
0xC6 0x05BC # HEBREW POINT DAGESH OR MAPIQ
0xC7 0xFB4B # HEBREW LETTER VAV WITH HOLAM
0xC8 0xFB35 # HEBREW LETTER VAV WITH DAGESH
0xC9 0x202E+0x2026+0x202C # RLO + HORIZONTAL ELLIPSIS
0xCA 0x202E+0x00A0+0x202C # RLO + NO-BREAK SPACE
0xCB 0x05B8 # HEBREW POINT QAMATS
0xCC 0x05B7 # HEBREW POINT PATAH
0xCD 0x05B5 # HEBREW POINT TSERE
0xCE 0x05B6 # HEBREW POINT SEGOL
0xCF 0x05B4 # HEBREW POINT HIRIQ
0xD0 0x202E+0x2013+0x202C # RLO + EN DASH + PDF
0xD1 0x202E+0x2014+0x202C # RLO + EM DASH + PDF
0xD2 0x202E+0x201C+0x202C # RLO + LEFT DOUBLE QUOTATION MARK + PDF
0xD3 0x202E+0x201D+0x202C # RLO + RIGHT DOUBLE QUOTATION MARK + PDF
0xD4 0x202E+0x2018+0x202C # RLO + LEFT SINGLE QUOTATION MARK + PDF
0xD5 0x202E+0x2019+0x202C # RLO + RIGHT SINGLE QUOTATION MARK + PDF
0xD6 0xFB2A # HEBREW LETTER SHIN WITH SHIN DOT
0xD7 0xFB2B # HEBREW LETTER SHIN WITH SIN DOT
0xD8 0x05BF # HEBREW POINT RAFE
0xD9 0x05B0 # HEBREW POINT SHEVA
0xDA 0x05B2 # HEBREW POINT HATAF PATAH
0xDB 0x05B1 # HEBREW POINT HATAF SEGOL
0xDC 0x05BB # HEBREW POINT QUBUTS
0xDD 0x05B9 # HEBREW POINT HOLAM
0xDE 0xF89F # Hebrew point qamats qatan
0xDF 0x05B3 # HEBREW POINT HATAF QAMATS
0xE0 0x05D0 # HEBREW LETTER ALEF
0xE1 0x05D1 # HEBREW LETTER BET
0xE2 0x05D2 # HEBREW LETTER GIMEL
0xE3 0x05D3 # HEBREW LETTER DALET
0xE4 0x05D4 # HEBREW LETTER HE
0xE5 0x05D5 # HEBREW LETTER VAV
0xE6 0x05D6 # HEBREW LETTER ZAYIN
0xE7 0x05D7 # HEBREW LETTER HET
0xE8 0x05D8 # HEBREW LETTER TET
0xE9 0x05D9 # HEBREW LETTER YOD
0xEA 0x05DA # HEBREW LETTER FINAL KAF
0xEB 0x05DB # HEBREW LETTER KAF
0xEC 0x05DC # HEBREW LETTER LAMED
0xED 0x05DD # HEBREW LETTER FINAL MEM
0xEE 0x05DE # HEBREW LETTER MEM
0xEF 0x05DF # HEBREW LETTER FINAL NUN
0xF0 0x05E0 # HEBREW LETTER NUN
0xF1 0x05E1 # HEBREW LETTER SAMEKH
0xF2 0x05E2 # HEBREW LETTER AYIN
0xF3 0x05E3 # HEBREW LETTER FINAL PE
0xF4 0x05E4 # HEBREW LETTER PE
0xF5 0x05E5 # HEBREW LETTER FINAL TSADI
0xF6 0x05E6 # HEBREW LETTER TSADI
0xF7 0x05E7 # HEBREW LETTER QOF
0xF8 0x05E8 # HEBREW LETTER RESH
0xF9 0x05E9 # HEBREW LETTER SHIN
0xFA 0x05EA # HEBREW LETTER TAV
0xFB 0x202E+0x007D+0x202C # RLO + RIGHT CURLY BRACKET + PDF
0xFC 0x202E+0x005D+0x202C # RLO + RIGHT SQUARE BRACKET + PDF
0xFD 0x202E+0x007B+0x202C # RLO + LEFT CURLY BRACKET + PDF
0xFE 0x202E+0x005B+0x202C # RLO + LEFT SQUARE BRACKET + PDF
0xFF 0x202E+0x007C+0x202C # RLO + VERTICAL LINE + PDF

285
unicode/vendors/apple/iceland.txt vendored Normal file
View File

@@ -0,0 +1,285 @@
#
# Name: MacOS_Icelandic [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <5>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Icelandic code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Icelandic code order.
#
# One of these mappings requires the use of a corporate character
# (for the Apple logo character). See the file "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Icelandic:
# -------------------------
#
# The MacOS Icelandic encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Icelandic encoding is being used, you must also check if
# the system region code is 21, verIceland.
#
# This character set is a variant of standard MacOS Roman,
# adding upper and lower eth, thorn, and Y acute. It has 6 code
# point differences from standard MacOS Roman.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x00C6 # LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00A5 # YEN SIGN
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x220F # N-ARY PRODUCT
0xB9 0x03C0 # GREEK SMALL LETTER PI
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
0xBD 0x2126 # OHM SIGN
0xBE 0x00E6 # LATIN SMALL LIGATURE AE
0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 # FRACTION SLASH
0xDB 0x00A4 # CURRENCY SIGN
0xDC 0x00D0 # LATIN CAPITAL LETTER ETH
0xDD 0x00F0 # LATIN SMALL LETTER ETH
0xDE 0x00DE # LATIN CAPITAL LETTER THORN
0xDF 0x00FE # LATIN SMALL LETTER THORN
0xE0 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
0xE1 0x00B7 # MIDDLE DOT
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 # PER MILLE SIGN
0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0xF8FF # Apple logo
0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 # LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC # SMALL TILDE
0xF8 0x00AF # MACRON
0xF9 0x02D8 # BREVE
0xFA 0x02D9 # DOT ABOVE
0xFB 0x02DA # RING ABOVE
0xFC 0x00B8 # CEDILLA
0xFD 0x02DD # DOUBLE ACUTE ACCENT
0xFE 0x02DB # OGONEK
0xFF 0x02C7 # CARON

7599
unicode/vendors/apple/japan.txt vendored Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,338 @@
/*
This file was automatically converted using the program convertMappingToC.py.
Original File: /home1/__/user/pas/unicode/mappings/vendors/apple/cyrillic.txt
Converted On: Sun May 18 15:01:34 1997.
The set of files for which this converter was created are the files
in /unix/mappings/ on the CD-ROM which comes with the Unicode 2.0
standard. Any comments in the original files are preserved in the
output.
You should probably not edit this file.
To use this file, you must define the following macros and then
include this file. For example, to create a simple list of these
values indexed by windows code page value:
#define WCP_UNICODE_STR_TYPE unsigned int
#define WCP_UNICODE_STR_VALUES(_v,_u,_s) _u
#include "thisfile.c"
See the NOTES section at the end of this file for VERY IMPORTANT
information that arose during the creating of this file.
*/
/* Any header comments from original file follow: */
/* Name: MacOS_Cyrillic [to Unicode] */
/* Unicode versions: 1.1, 2.0 */
/* Table version: 0.2 (from internal ufrm version <5>) */
/* Date: 15 April 1995 */
/* Authors: Peter Edberg <edberg1@applelink.apple.com> */
/* Judy Kettenhofen */
/* Copyright (c) 1995 Apple Computer, Inc. All Rights reserved. */
/* Apple, the Apple logo, and Macintosh are trademarks of Apple */
/* Computer, Inc., registered in the United States and other countries. */
/* Unicode is a trademark of Unicode Inc. For the sake of brevity, */
/* throughout this document, "Macintosh" can be used to refer to */
/* Macintosh computers and "Unicode" can be used to refer to the */
/* Unicode standard. */
/* Apple makes no warranty or representation, either express or */
/* implied, with respect to these tables, their quality, accuracy, or */
/* fitness for a particular purpose. In no event will Apple be liable */
/* for direct, indirect, special, incidental, or consequential damages */
/* resulting from any defect or inaccuracy in this document or the */
/* accompanying tables. */
/* These mapping tables and character lists are preliminary and */
/* subject to change. Updated tables will be available from the */
/* Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site */
/* (ftp.info.apple.com), the Apple Computer World-Wide Web pages */
/* (http://www.info.apple.com), and possibly on diskette from APDA */
/* (Apple's mail-order distribution service for developers). */
/* Format: */
/* ------- */
/* Three tab-separated columns; */
/* '#' begins a comment which continues to the end of the line. */
/* Column #1 is the MacOS Cyrillic code (in hex as 0xNN) */
/* Column #2 is the Unicode (in hex as 0xNNNN) */
/* Column #3 is the Unicode name (follows a comment sign, '#') */
/* The entries are in MacOS Cyrillic code order. */
/* Notes on MacOS Cyrillic: */
/* ------------------------ */
/* The MacOS Cyrillic encoding includes the full Cyrillic letter */
/* repertoire of ISO 8859-5 (although not at the same code points). */
/* This covers most of the Slavic languages written in Cyrillic */
/* script. */
/* The MacOS Cyrillic encoding also includes a number of characters */
/* needed for the MacOS user interface (e.g. ellipsis), MacOS */
/* localization (bullet for echoing passwords, copyright sign, etc. */
/* All of the characters in MacOS Cyrillic that are also in the MacOS */
/* Roman encoding are at the same code point as MacOS Roman. This */
/* improves application compatibility (since some naughty applications */
/* hard-code the MacOS Roman code points of certain characters). */
/* A variant of MacOS Cyrillic is used for Ukrainian. A separate */
/* mapping table is available for Ukrainian. */
/* ################# */
WCP_UNICODE_STR_TYPE cyrillic[] = {
WCP_UNICODE_STR_VALUES(0x00, 0x0000, "NULL"),
WCP_UNICODE_STR_VALUES(0x01, 0x0001, "START OF HEADING"),
WCP_UNICODE_STR_VALUES(0x02, 0x0002, "START OF TEXT"),
WCP_UNICODE_STR_VALUES(0x03, 0x0003, "END OF TEXT"),
WCP_UNICODE_STR_VALUES(0x04, 0x0004, "END OF TRANSMISSION"),
WCP_UNICODE_STR_VALUES(0x05, 0x0005, "ENQUIRY"),
WCP_UNICODE_STR_VALUES(0x06, 0x0006, "ACKNOWLEDGE"),
WCP_UNICODE_STR_VALUES(0x07, 0x0007, "BELL"),
WCP_UNICODE_STR_VALUES(0x08, 0x0008, "BACKSPACE"),
WCP_UNICODE_STR_VALUES(0x09, 0x0009, "HORIZONTAL TABULATION"),
WCP_UNICODE_STR_VALUES(0x0A, 0x000A, "LINE FEED"),
WCP_UNICODE_STR_VALUES(0x0B, 0x000B, "VERTICAL TABULATION"),
WCP_UNICODE_STR_VALUES(0x0C, 0x000C, "FORM FEED"),
WCP_UNICODE_STR_VALUES(0x0D, 0x000D, "CARRIAGE RETURN"),
WCP_UNICODE_STR_VALUES(0x0E, 0x000E, "SHIFT OUT"),
WCP_UNICODE_STR_VALUES(0x0F, 0x000F, "SHIFT IN"),
WCP_UNICODE_STR_VALUES(0x10, 0x0010, "DATA LINK ESCAPE"),
WCP_UNICODE_STR_VALUES(0x11, 0x0011, "DEVICE CONTROL ONE"),
WCP_UNICODE_STR_VALUES(0x12, 0x0012, "DEVICE CONTROL TWO"),
WCP_UNICODE_STR_VALUES(0x13, 0x0013, "DEVICE CONTROL THREE"),
WCP_UNICODE_STR_VALUES(0x14, 0x0014, "DEVICE CONTROL FOUR"),
WCP_UNICODE_STR_VALUES(0x15, 0x0015, "NEGATIVE ACKNOWLEDGE"),
WCP_UNICODE_STR_VALUES(0x16, 0x0016, "SYNCHRONOUS IDLE"),
WCP_UNICODE_STR_VALUES(0x17, 0x0017, "END OF TRANSMISSION BLOCK"),
WCP_UNICODE_STR_VALUES(0x18, 0x0018, "CANCEL"),
WCP_UNICODE_STR_VALUES(0x19, 0x0019, "END OF MEDIUM"),
WCP_UNICODE_STR_VALUES(0x1A, 0x001A, "SUBSTITUTE"),
WCP_UNICODE_STR_VALUES(0x1B, 0x001B, "ESCAPE"),
WCP_UNICODE_STR_VALUES(0x1C, 0x001C, "FILE SEPARATOR"),
WCP_UNICODE_STR_VALUES(0x1D, 0x001D, "GROUP SEPARATOR"),
WCP_UNICODE_STR_VALUES(0x1E, 0x001E, "RECORD SEPARATOR"),
WCP_UNICODE_STR_VALUES(0x1F, 0x001F, "UNIT SEPARATOR"),
WCP_UNICODE_STR_VALUES(0x20, 0x0020, "SPACE"),
WCP_UNICODE_STR_VALUES(0x21, 0x0021, "EXCLAMATION MARK"),
WCP_UNICODE_STR_VALUES(0x22, 0x0022, "QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0x23, 0x0023, "NUMBER SIGN"),
WCP_UNICODE_STR_VALUES(0x24, 0x0024, "DOLLAR SIGN"),
WCP_UNICODE_STR_VALUES(0x25, 0x0025, "PERCENT SIGN"),
WCP_UNICODE_STR_VALUES(0x26, 0x0026, "AMPERSAND"),
WCP_UNICODE_STR_VALUES(0x27, 0x0027, "APOSTROPHE"),
WCP_UNICODE_STR_VALUES(0x28, 0x0028, "LEFT PARENTHESIS"),
WCP_UNICODE_STR_VALUES(0x29, 0x0029, "RIGHT PARENTHESIS"),
WCP_UNICODE_STR_VALUES(0x2A, 0x002A, "ASTERISK"),
WCP_UNICODE_STR_VALUES(0x2B, 0x002B, "PLUS SIGN"),
WCP_UNICODE_STR_VALUES(0x2C, 0x002C, "COMMA"),
WCP_UNICODE_STR_VALUES(0x2D, 0x002D, "HYPHEN-MINUS"),
WCP_UNICODE_STR_VALUES(0x2E, 0x002E, "FULL STOP"),
WCP_UNICODE_STR_VALUES(0x2F, 0x002F, "SOLIDUS"),
WCP_UNICODE_STR_VALUES(0x30, 0x0030, "DIGIT ZERO"),
WCP_UNICODE_STR_VALUES(0x31, 0x0031, "DIGIT ONE"),
WCP_UNICODE_STR_VALUES(0x32, 0x0032, "DIGIT TWO"),
WCP_UNICODE_STR_VALUES(0x33, 0x0033, "DIGIT THREE"),
WCP_UNICODE_STR_VALUES(0x34, 0x0034, "DIGIT FOUR"),
WCP_UNICODE_STR_VALUES(0x35, 0x0035, "DIGIT FIVE"),
WCP_UNICODE_STR_VALUES(0x36, 0x0036, "DIGIT SIX"),
WCP_UNICODE_STR_VALUES(0x37, 0x0037, "DIGIT SEVEN"),
WCP_UNICODE_STR_VALUES(0x38, 0x0038, "DIGIT EIGHT"),
WCP_UNICODE_STR_VALUES(0x39, 0x0039, "DIGIT NINE"),
WCP_UNICODE_STR_VALUES(0x3A, 0x003A, "COLON"),
WCP_UNICODE_STR_VALUES(0x3B, 0x003B, "SEMICOLON"),
WCP_UNICODE_STR_VALUES(0x3C, 0x003C, "LESS-THAN SIGN"),
WCP_UNICODE_STR_VALUES(0x3D, 0x003D, "EQUALS SIGN"),
WCP_UNICODE_STR_VALUES(0x3E, 0x003E, "GREATER-THAN SIGN"),
WCP_UNICODE_STR_VALUES(0x3F, 0x003F, "QUESTION MARK"),
WCP_UNICODE_STR_VALUES(0x40, 0x0040, "COMMERCIAL AT"),
WCP_UNICODE_STR_VALUES(0x41, 0x0041, "LATIN CAPITAL LETTER A"),
WCP_UNICODE_STR_VALUES(0x42, 0x0042, "LATIN CAPITAL LETTER B"),
WCP_UNICODE_STR_VALUES(0x43, 0x0043, "LATIN CAPITAL LETTER C"),
WCP_UNICODE_STR_VALUES(0x44, 0x0044, "LATIN CAPITAL LETTER D"),
WCP_UNICODE_STR_VALUES(0x45, 0x0045, "LATIN CAPITAL LETTER E"),
WCP_UNICODE_STR_VALUES(0x46, 0x0046, "LATIN CAPITAL LETTER F"),
WCP_UNICODE_STR_VALUES(0x47, 0x0047, "LATIN CAPITAL LETTER G"),
WCP_UNICODE_STR_VALUES(0x48, 0x0048, "LATIN CAPITAL LETTER H"),
WCP_UNICODE_STR_VALUES(0x49, 0x0049, "LATIN CAPITAL LETTER I"),
WCP_UNICODE_STR_VALUES(0x4A, 0x004A, "LATIN CAPITAL LETTER J"),
WCP_UNICODE_STR_VALUES(0x4B, 0x004B, "LATIN CAPITAL LETTER K"),
WCP_UNICODE_STR_VALUES(0x4C, 0x004C, "LATIN CAPITAL LETTER L"),
WCP_UNICODE_STR_VALUES(0x4D, 0x004D, "LATIN CAPITAL LETTER M"),
WCP_UNICODE_STR_VALUES(0x4E, 0x004E, "LATIN CAPITAL LETTER N"),
WCP_UNICODE_STR_VALUES(0x4F, 0x004F, "LATIN CAPITAL LETTER O"),
WCP_UNICODE_STR_VALUES(0x50, 0x0050, "LATIN CAPITAL LETTER P"),
WCP_UNICODE_STR_VALUES(0x51, 0x0051, "LATIN CAPITAL LETTER Q"),
WCP_UNICODE_STR_VALUES(0x52, 0x0052, "LATIN CAPITAL LETTER R"),
WCP_UNICODE_STR_VALUES(0x53, 0x0053, "LATIN CAPITAL LETTER S"),
WCP_UNICODE_STR_VALUES(0x54, 0x0054, "LATIN CAPITAL LETTER T"),
WCP_UNICODE_STR_VALUES(0x55, 0x0055, "LATIN CAPITAL LETTER U"),
WCP_UNICODE_STR_VALUES(0x56, 0x0056, "LATIN CAPITAL LETTER V"),
WCP_UNICODE_STR_VALUES(0x57, 0x0057, "LATIN CAPITAL LETTER W"),
WCP_UNICODE_STR_VALUES(0x58, 0x0058, "LATIN CAPITAL LETTER X"),
WCP_UNICODE_STR_VALUES(0x59, 0x0059, "LATIN CAPITAL LETTER Y"),
WCP_UNICODE_STR_VALUES(0x5A, 0x005A, "LATIN CAPITAL LETTER Z"),
WCP_UNICODE_STR_VALUES(0x5B, 0x005B, "LEFT SQUARE BRACKET"),
WCP_UNICODE_STR_VALUES(0x5C, 0x005C, "REVERSE SOLIDUS"),
WCP_UNICODE_STR_VALUES(0x5D, 0x005D, "RIGHT SQUARE BRACKET"),
WCP_UNICODE_STR_VALUES(0x5E, 0x005E, "CIRCUMFLEX ACCENT"),
WCP_UNICODE_STR_VALUES(0x5F, 0x005F, "LOW LINE"),
WCP_UNICODE_STR_VALUES(0x60, 0x0060, "GRAVE ACCENT"),
WCP_UNICODE_STR_VALUES(0x61, 0x0061, "LATIN SMALL LETTER A"),
WCP_UNICODE_STR_VALUES(0x62, 0x0062, "LATIN SMALL LETTER B"),
WCP_UNICODE_STR_VALUES(0x63, 0x0063, "LATIN SMALL LETTER C"),
WCP_UNICODE_STR_VALUES(0x64, 0x0064, "LATIN SMALL LETTER D"),
WCP_UNICODE_STR_VALUES(0x65, 0x0065, "LATIN SMALL LETTER E"),
WCP_UNICODE_STR_VALUES(0x66, 0x0066, "LATIN SMALL LETTER F"),
WCP_UNICODE_STR_VALUES(0x67, 0x0067, "LATIN SMALL LETTER G"),
WCP_UNICODE_STR_VALUES(0x68, 0x0068, "LATIN SMALL LETTER H"),
WCP_UNICODE_STR_VALUES(0x69, 0x0069, "LATIN SMALL LETTER I"),
WCP_UNICODE_STR_VALUES(0x6A, 0x006A, "LATIN SMALL LETTER J"),
WCP_UNICODE_STR_VALUES(0x6B, 0x006B, "LATIN SMALL LETTER K"),
WCP_UNICODE_STR_VALUES(0x6C, 0x006C, "LATIN SMALL LETTER L"),
WCP_UNICODE_STR_VALUES(0x6D, 0x006D, "LATIN SMALL LETTER M"),
WCP_UNICODE_STR_VALUES(0x6E, 0x006E, "LATIN SMALL LETTER N"),
WCP_UNICODE_STR_VALUES(0x6F, 0x006F, "LATIN SMALL LETTER O"),
WCP_UNICODE_STR_VALUES(0x70, 0x0070, "LATIN SMALL LETTER P"),
WCP_UNICODE_STR_VALUES(0x71, 0x0071, "LATIN SMALL LETTER Q"),
WCP_UNICODE_STR_VALUES(0x72, 0x0072, "LATIN SMALL LETTER R"),
WCP_UNICODE_STR_VALUES(0x73, 0x0073, "LATIN SMALL LETTER S"),
WCP_UNICODE_STR_VALUES(0x74, 0x0074, "LATIN SMALL LETTER T"),
WCP_UNICODE_STR_VALUES(0x75, 0x0075, "LATIN SMALL LETTER U"),
WCP_UNICODE_STR_VALUES(0x76, 0x0076, "LATIN SMALL LETTER V"),
WCP_UNICODE_STR_VALUES(0x77, 0x0077, "LATIN SMALL LETTER W"),
WCP_UNICODE_STR_VALUES(0x78, 0x0078, "LATIN SMALL LETTER X"),
WCP_UNICODE_STR_VALUES(0x79, 0x0079, "LATIN SMALL LETTER Y"),
WCP_UNICODE_STR_VALUES(0x7A, 0x007A, "LATIN SMALL LETTER Z"),
WCP_UNICODE_STR_VALUES(0x7B, 0x007B, "LEFT CURLY BRACKET"),
WCP_UNICODE_STR_VALUES(0x7C, 0x007C, "VERTICAL LINE"),
WCP_UNICODE_STR_VALUES(0x7D, 0x007D, "RIGHT CURLY BRACKET"),
WCP_UNICODE_STR_VALUES(0x7E, 0x007E, "TILDE"),
WCP_UNICODE_STR_VALUES(0x7F, 0x007F, "DELETE"),
WCP_UNICODE_STR_VALUES(0x80, 0x0410, "CYRILLIC CAPITAL LETTER A"),
WCP_UNICODE_STR_VALUES(0x81, 0x0411, "CYRILLIC CAPITAL LETTER BE"),
WCP_UNICODE_STR_VALUES(0x82, 0x0412, "CYRILLIC CAPITAL LETTER VE"),
WCP_UNICODE_STR_VALUES(0x83, 0x0413, "CYRILLIC CAPITAL LETTER GHE"),
WCP_UNICODE_STR_VALUES(0x84, 0x0414, "CYRILLIC CAPITAL LETTER DE"),
WCP_UNICODE_STR_VALUES(0x85, 0x0415, "CYRILLIC CAPITAL LETTER IE"),
WCP_UNICODE_STR_VALUES(0x86, 0x0416, "CYRILLIC CAPITAL LETTER ZHE"),
WCP_UNICODE_STR_VALUES(0x87, 0x0417, "CYRILLIC CAPITAL LETTER ZE"),
WCP_UNICODE_STR_VALUES(0x88, 0x0418, "CYRILLIC CAPITAL LETTER I"),
WCP_UNICODE_STR_VALUES(0x89, 0x0419, "CYRILLIC CAPITAL LETTER SHORT I"),
WCP_UNICODE_STR_VALUES(0x8A, 0x041A, "CYRILLIC CAPITAL LETTER KA"),
WCP_UNICODE_STR_VALUES(0x8B, 0x041B, "CYRILLIC CAPITAL LETTER EL"),
WCP_UNICODE_STR_VALUES(0x8C, 0x041C, "CYRILLIC CAPITAL LETTER EM"),
WCP_UNICODE_STR_VALUES(0x8D, 0x041D, "CYRILLIC CAPITAL LETTER EN"),
WCP_UNICODE_STR_VALUES(0x8E, 0x041E, "CYRILLIC CAPITAL LETTER O"),
WCP_UNICODE_STR_VALUES(0x8F, 0x041F, "CYRILLIC CAPITAL LETTER PE"),
WCP_UNICODE_STR_VALUES(0x90, 0x0420, "CYRILLIC CAPITAL LETTER ER"),
WCP_UNICODE_STR_VALUES(0x91, 0x0421, "CYRILLIC CAPITAL LETTER ES"),
WCP_UNICODE_STR_VALUES(0x92, 0x0422, "CYRILLIC CAPITAL LETTER TE"),
WCP_UNICODE_STR_VALUES(0x93, 0x0423, "CYRILLIC CAPITAL LETTER U"),
WCP_UNICODE_STR_VALUES(0x94, 0x0424, "CYRILLIC CAPITAL LETTER EF"),
WCP_UNICODE_STR_VALUES(0x95, 0x0425, "CYRILLIC CAPITAL LETTER HA"),
WCP_UNICODE_STR_VALUES(0x96, 0x0426, "CYRILLIC CAPITAL LETTER TSE"),
WCP_UNICODE_STR_VALUES(0x97, 0x0427, "CYRILLIC CAPITAL LETTER CHE"),
WCP_UNICODE_STR_VALUES(0x98, 0x0428, "CYRILLIC CAPITAL LETTER SHA"),
WCP_UNICODE_STR_VALUES(0x99, 0x0429, "CYRILLIC CAPITAL LETTER SHCHA"),
WCP_UNICODE_STR_VALUES(0x9A, 0x042A, "CYRILLIC CAPITAL LETTER HARD SIGN"),
WCP_UNICODE_STR_VALUES(0x9B, 0x042B, "CYRILLIC CAPITAL LETTER YERU"),
WCP_UNICODE_STR_VALUES(0x9C, 0x042C, "CYRILLIC CAPITAL LETTER SOFT SIGN"),
WCP_UNICODE_STR_VALUES(0x9D, 0x042D, "CYRILLIC CAPITAL LETTER E"),
WCP_UNICODE_STR_VALUES(0x9E, 0x042E, "CYRILLIC CAPITAL LETTER YU"),
WCP_UNICODE_STR_VALUES(0x9F, 0x042F, "CYRILLIC CAPITAL LETTER YA"),
WCP_UNICODE_STR_VALUES(0xA0, 0x2020, "DAGGER"),
WCP_UNICODE_STR_VALUES(0xA1, 0x00B0, "DEGREE SIGN"),
WCP_UNICODE_STR_VALUES(0xA2, 0x00A2, "CENT SIGN"),
WCP_UNICODE_STR_VALUES(0xA3, 0x00A3, "POUND SIGN"),
WCP_UNICODE_STR_VALUES(0xA4, 0x00A7, "SECTION SIGN"),
WCP_UNICODE_STR_VALUES(0xA5, 0x2022, "BULLET"),
WCP_UNICODE_STR_VALUES(0xA6, 0x00B6, "PILCROW SIGN"),
WCP_UNICODE_STR_VALUES(0xA7, 0x0406, "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I"),
WCP_UNICODE_STR_VALUES(0xA8, 0x00AE, "REGISTERED SIGN"),
WCP_UNICODE_STR_VALUES(0xA9, 0x00A9, "COPYRIGHT SIGN"),
WCP_UNICODE_STR_VALUES(0xAA, 0x2122, "TRADE MARK SIGN"),
WCP_UNICODE_STR_VALUES(0xAB, 0x0402, "CYRILLIC CAPITAL LETTER DJE"),
WCP_UNICODE_STR_VALUES(0xAC, 0x0452, "CYRILLIC SMALL LETTER DJE"),
WCP_UNICODE_STR_VALUES(0xAD, 0x2260, "NOT EQUAL TO"),
WCP_UNICODE_STR_VALUES(0xAE, 0x0403, "CYRILLIC CAPITAL LETTER GJE"),
WCP_UNICODE_STR_VALUES(0xAF, 0x0453, "CYRILLIC SMALL LETTER GJE"),
WCP_UNICODE_STR_VALUES(0xB0, 0x221E, "INFINITY"),
WCP_UNICODE_STR_VALUES(0xB1, 0x00B1, "PLUS-MINUS SIGN"),
WCP_UNICODE_STR_VALUES(0xB2, 0x2264, "LESS-THAN OR EQUAL TO"),
WCP_UNICODE_STR_VALUES(0xB3, 0x2265, "GREATER-THAN OR EQUAL TO"),
WCP_UNICODE_STR_VALUES(0xB4, 0x0456, "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I"),
WCP_UNICODE_STR_VALUES(0xB5, 0x00B5, "MICRO SIGN"),
WCP_UNICODE_STR_VALUES(0xB6, 0x2202, "PARTIAL DIFFERENTIAL"),
WCP_UNICODE_STR_VALUES(0xB7, 0x0408, "CYRILLIC CAPITAL LETTER JE"),
WCP_UNICODE_STR_VALUES(0xB8, 0x0404, "CYRILLIC CAPITAL LETTER UKRAINIAN IE"),
WCP_UNICODE_STR_VALUES(0xB9, 0x0454, "CYRILLIC SMALL LETTER UKRAINIAN IE"),
WCP_UNICODE_STR_VALUES(0xBA, 0x0407, "CYRILLIC CAPITAL LETTER YI"),
WCP_UNICODE_STR_VALUES(0xBB, 0x0457, "CYRILLIC SMALL LETTER YI"),
WCP_UNICODE_STR_VALUES(0xBC, 0x0409, "CYRILLIC CAPITAL LETTER LJE"),
WCP_UNICODE_STR_VALUES(0xBD, 0x0459, "CYRILLIC SMALL LETTER LJE"),
WCP_UNICODE_STR_VALUES(0xBE, 0x040A, "CYRILLIC CAPITAL LETTER NJE"),
WCP_UNICODE_STR_VALUES(0xBF, 0x045A, "CYRILLIC SMALL LETTER NJE"),
WCP_UNICODE_STR_VALUES(0xC0, 0x0458, "CYRILLIC SMALL LETTER JE"),
WCP_UNICODE_STR_VALUES(0xC1, 0x0405, "CYRILLIC CAPITAL LETTER DZE"),
WCP_UNICODE_STR_VALUES(0xC2, 0x00AC, "NOT SIGN"),
WCP_UNICODE_STR_VALUES(0xC3, 0x221A, "SQUARE ROOT"),
WCP_UNICODE_STR_VALUES(0xC4, 0x0192, "LATIN SMALL LETTER F WITH HOOK"),
WCP_UNICODE_STR_VALUES(0xC5, 0x2248, "ALMOST EQUAL TO"),
WCP_UNICODE_STR_VALUES(0xC6, 0x2206, "INCREMENT"),
WCP_UNICODE_STR_VALUES(0xC7, 0x00AB, "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xC8, 0x00BB, "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xC9, 0x2026, "HORIZONTAL ELLIPSIS"),
WCP_UNICODE_STR_VALUES(0xCA, 0x00A0, "NO-BREAK SPACE"),
WCP_UNICODE_STR_VALUES(0xCB, 0x040B, "CYRILLIC CAPITAL LETTER TSHE"),
WCP_UNICODE_STR_VALUES(0xCC, 0x045B, "CYRILLIC SMALL LETTER TSHE"),
WCP_UNICODE_STR_VALUES(0xCD, 0x040C, "CYRILLIC CAPITAL LETTER KJE"),
WCP_UNICODE_STR_VALUES(0xCE, 0x045C, "CYRILLIC SMALL LETTER KJE"),
WCP_UNICODE_STR_VALUES(0xCF, 0x0455, "CYRILLIC SMALL LETTER DZE"),
WCP_UNICODE_STR_VALUES(0xD0, 0x2013, "EN DASH"),
WCP_UNICODE_STR_VALUES(0xD1, 0x2014, "EM DASH"),
WCP_UNICODE_STR_VALUES(0xD2, 0x201C, "LEFT DOUBLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xD3, 0x201D, "RIGHT DOUBLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xD4, 0x2018, "LEFT SINGLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xD5, 0x2019, "RIGHT SINGLE QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xD6, 0x00F7, "DIVISION SIGN"),
WCP_UNICODE_STR_VALUES(0xD7, 0x201E, "DOUBLE LOW-9 QUOTATION MARK"),
WCP_UNICODE_STR_VALUES(0xD8, 0x040E, "CYRILLIC CAPITAL LETTER SHORT U"),
WCP_UNICODE_STR_VALUES(0xD9, 0x045E, "CYRILLIC SMALL LETTER SHORT U"),
WCP_UNICODE_STR_VALUES(0xDA, 0x040F, "CYRILLIC CAPITAL LETTER DZHE"),
WCP_UNICODE_STR_VALUES(0xDB, 0x045F, "CYRILLIC SMALL LETTER DZHE"),
WCP_UNICODE_STR_VALUES(0xDC, 0x2116, "NUMERO SIGN"),
WCP_UNICODE_STR_VALUES(0xDD, 0x0401, "CYRILLIC CAPITAL LETTER IO"),
WCP_UNICODE_STR_VALUES(0xDE, 0x0451, "CYRILLIC SMALL LETTER IO"),
WCP_UNICODE_STR_VALUES(0xDF, 0x044F, "CYRILLIC SMALL LETTER YA"),
WCP_UNICODE_STR_VALUES(0xE0, 0x0430, "CYRILLIC SMALL LETTER A"),
WCP_UNICODE_STR_VALUES(0xE1, 0x0431, "CYRILLIC SMALL LETTER BE"),
WCP_UNICODE_STR_VALUES(0xE2, 0x0432, "CYRILLIC SMALL LETTER VE"),
WCP_UNICODE_STR_VALUES(0xE3, 0x0433, "CYRILLIC SMALL LETTER GHE"),
WCP_UNICODE_STR_VALUES(0xE4, 0x0434, "CYRILLIC SMALL LETTER DE"),
WCP_UNICODE_STR_VALUES(0xE5, 0x0435, "CYRILLIC SMALL LETTER IE"),
WCP_UNICODE_STR_VALUES(0xE6, 0x0436, "CYRILLIC SMALL LETTER ZHE"),
WCP_UNICODE_STR_VALUES(0xE7, 0x0437, "CYRILLIC SMALL LETTER ZE"),
WCP_UNICODE_STR_VALUES(0xE8, 0x0438, "CYRILLIC SMALL LETTER I"),
WCP_UNICODE_STR_VALUES(0xE9, 0x0439, "CYRILLIC SMALL LETTER SHORT I"),
WCP_UNICODE_STR_VALUES(0xEA, 0x043A, "CYRILLIC SMALL LETTER KA"),
WCP_UNICODE_STR_VALUES(0xEB, 0x043B, "CYRILLIC SMALL LETTER EL"),
WCP_UNICODE_STR_VALUES(0xEC, 0x043C, "CYRILLIC SMALL LETTER EM"),
WCP_UNICODE_STR_VALUES(0xED, 0x043D, "CYRILLIC SMALL LETTER EN"),
WCP_UNICODE_STR_VALUES(0xEE, 0x043E, "CYRILLIC SMALL LETTER O"),
WCP_UNICODE_STR_VALUES(0xEF, 0x043F, "CYRILLIC SMALL LETTER PE"),
WCP_UNICODE_STR_VALUES(0xF0, 0x0440, "CYRILLIC SMALL LETTER ER"),
WCP_UNICODE_STR_VALUES(0xF1, 0x0441, "CYRILLIC SMALL LETTER ES"),
WCP_UNICODE_STR_VALUES(0xF2, 0x0442, "CYRILLIC SMALL LETTER TE"),
WCP_UNICODE_STR_VALUES(0xF3, 0x0443, "CYRILLIC SMALL LETTER U"),
WCP_UNICODE_STR_VALUES(0xF4, 0x0444, "CYRILLIC SMALL LETTER EF"),
WCP_UNICODE_STR_VALUES(0xF5, 0x0445, "CYRILLIC SMALL LETTER HA"),
WCP_UNICODE_STR_VALUES(0xF6, 0x0446, "CYRILLIC SMALL LETTER TSE"),
WCP_UNICODE_STR_VALUES(0xF7, 0x0447, "CYRILLIC SMALL LETTER CHE"),
WCP_UNICODE_STR_VALUES(0xF8, 0x0448, "CYRILLIC SMALL LETTER SHA"),
WCP_UNICODE_STR_VALUES(0xF9, 0x0449, "CYRILLIC SMALL LETTER SHCHA"),
WCP_UNICODE_STR_VALUES(0xFA, 0x044A, "CYRILLIC SMALL LETTER HARD SIGN"),
WCP_UNICODE_STR_VALUES(0xFB, 0x044B, "CYRILLIC SMALL LETTER YERU"),
WCP_UNICODE_STR_VALUES(0xFC, 0x044C, "CYRILLIC SMALL LETTER SOFT SIGN"),
WCP_UNICODE_STR_VALUES(0xFD, 0x044D, "CYRILLIC SMALL LETTER E"),
WCP_UNICODE_STR_VALUES(0xFE, 0x044E, "CYRILLIC SMALL LETTER YU"),
WCP_UNICODE_STR_VALUES(0xFF, 0x00A4, "CURRENCY SIGN")
};
/*
NOTES during the processing of this file:
Inserted standard control values (0,32]...
Inserted Undefined values in range (127,127]...
The WCP values in this file were forced CONSECUTIVE.
*/

539
unicode/vendors/apple/readme.txt vendored Normal file
View File

@@ -0,0 +1,539 @@
Name: 0README.TXT
Background information - mapping tables for the Mac(TM) OS
Version 6: Nov. 15, 1995 - update info for Hebrew and Thai
(Version 5: Apr. 15, 1995)
Peter Edberg, Apple Computer, Inc. <edberg1@applelink.apple.com>
Copyright (C) 1995 by Apple Computer, Inc., all rights reserved.
0. Preliminaries
----------------
For maximum interchangeability, this file and the accompanying MacOS
mapping tables use only ASCII characters and are intended to be
displayed in a monospaced font. Every line terminates with carriage
return.
Apple, the Apple logo, Mac, and Macintosh are trademarks of Apple
Computer, Inc., registered in the United States and other countries.
QuickDraw and TrueType are trademarks of Apple Computer, Inc. Unicode is
a trademark of Unicode Inc. PostScript is a trademark of Adobe Systems
Inc., which may be registered in certain jurisdictions. IBM is a
registered trademark of International Business Machines Corporation. ITC
Zapf Dingbats is a registered trademark of the International Typeface
Corporation. For the sake of brevity, throughout this document and the
accompanying tables, "Unicode" can be used to refer to the Unicode
standard.
Apple Computer, Inc. ("Apple") makes no warranty or representation,
either express or implied, with respect to this document and the
accompanying tables, their quality, accuracy, or fitness for a
particular purpose. In no event will Apple be liable for direct,
indirect, special, incidental, or consequential damages resulting from
any defect or inaccuracy in this document or the accompanying tables.
1. Introduction
---------------
In order to understand the accompanying MacOS mapping tables, you will
need to understand something about the MacOS Unicode Converter. This
converter has been designed to handle the complex issues that can arise
when converting between Unicode and other character sets, including:
* Round-trip fidelity (and the use of corporate characters);
* Supporting various mapping tolerance levels (strict, loose), in order
to provide both round-trip fidelity and a way to handle characters
that have multiple or ambiguous semantics in some character sets;
* Handling character set variants and extensions, which may require
selective inclusion or exclusion of certain mappings or sets of
mappings;
* Mapping single characters in one set to multiple characters in another
or vice versa (in general, a match may map a sequence of 1 to n
characters in one set to a sequence of 0 to m characters in another);
* Handling mappings that may depend on attributes such as resolved
character direction, vertical or horizontal display direction, etc.
The above issues are described in more detail in sections 2-6. Section 7
provides some general information on MacOS character sets and a list of
MacOS character encodings.
This document and all of the accompanying mapping tables and character
lists are preliminary and subject to change. Updated documents and
tables will be available from the Unicode Inc. ftp site (unicode.org),
the Apple ftp site (ftp.info.apple.com), the Apple Computer World-Wide
Web pages (http://www.info.apple.com), and possibly on diskette from
APDA (Apple's mail-order distribution service for developers).
2. Round-trip fidelity and corporate characters
-----------------------------------------------
For the various national and international standards that were sources
for Unicode, Unicode provides round-trip fidelity: Text in one of those
encodings can be mapped to Unicode and back again with no loss of
information. Characters which were distinct in the source standard are
distinct in Unicode.
However, Unicode does not attempt to provide round-trip fidelity for
most vendor standards. Nevertheless, Apple and other platform vendors
may need to provide such round-trip fidelity for their current encodings
(this can be important in file systems, for example). In order to do
this, Apple maps some characters in the current MacOS encodings to
character codes at the upper end of the Unicode private use area (i.e.
the corporate use zone). In general, these are characters that are
rarely used in text that is interchanged with other systems, or
characters for which mistranslation in interchange would have a minimal
impact on most documents. Apple's usage of character codes in the
corporate use zone is documented in the accompanying file
"MacOS_CorpChars".
There is another round-trip fidelity issue that is important for the
MacOS Unicode converter. Among other things, this converter will be used
to convert between two non-Unicode encodings by using Unicode as an
intermediate form. For example, characters in the MacOS standard Roman
encoding could be converted to ISO/IEC 8859-1 by converting them first
to Unicode, and then converting the Unicode text to ISO/IEC 8859-1.
However, not all MacOS standard Roman characters can be represented in a
distinct way in ISO/IEC 8859-1. In such cases it is useful to know the
subset of MacOS Roman characters that can be converted to 8859-1 and
back (via Unicode) with no loss of information.
3. Mapping tolerance: Strict and loose
--------------------------------------
In many character sets, a single character may have multiple semantics,
either by explicit definition, ambiguous definition, or established
usage. For example, the JIS character 0x2142 (Shift-JIS 0x8161) is
specified in the JIS X0208 standard to have two meanings: "double
vertical line" and "parallel". Each of these meanings corresponds to a
different Unicode character: 0x2016 "DOUBLE VERTICAL LINE" and 0x2225
"PARALLEL TO". When mapping from Unicode to JIS, it is normally
desirable to map both of these Unicode characters to the single JIS
character 0x2142. However, when mapping this JIS character to Unicode,
we can choose only one of the possible Unicode characters.
For some character set X, the converse of the X-to-Unicode mappings are
called "strict" mappings from Unicode to X. In general, strict mappings
permit roundtrip conversion from Unicode to X and back for a subset of
Unicode characters. Strict mappings are useful when round-trip fidelity
is desired for an X-to-Unicode-to-Y mapping.
For some characters in X, there may be additional mappings from Unicode
that fall within the range of explicit or established usage for those
characters; these are called "loose" mappings. It is important to note
that the range of allowed loose mappings is determined by the character
set X.
Furthermore, in some cases it is helpful to map a Unicode character to a
sequence of one or more target characters that may not have the same
meaning or use, but which may provide an approximate graphic
representation of the corresponding Unicode character. These are called
"fallback" mappings.
Some examples of strict and loose mappings:
a) In the JIS example above, JIS 0x2142 is usually mapped to Unicode
0x2016 "DOUBLE VERTICAL LINE". Thus the reverse mapping is a strict
mapping from Unicode to JIS, while mapping Unicode 0x2225 "PARALLEL TO"
to JIS 0x2142 is a loose mapping.
b) When mapping ASCII to Unicode, 0x0A "line feed" and 0x0D "carriage
return" are usually mapped to the Unicode code points 0x000A and 0x000D.
When mapping Unicode to ASCII, loose mappings could include mapping
0x2028 "LINE SEPARATOR" to 0x0A and mapping 0x2029 "PARAGRAPH SEPARATOR"
to 0x0D.
c) Other loose mappings from Unicode to ASCII might include mapping
Unicodes 0x2010 "HYPHEN" and 0x2212 "MINUS SIGN" to ASCII 0x2D "hyphen-
minus".
d) In the conventional mapping from ISO/IEC 8859-1 to Unicode, the
8859-1 character 0xE0 "small letter a with grave accent" is mapped to
Unicode 0x00E0 "LATIN SMALL LETTER A WITH GRAVE", so the reverse mapping
is a strict mapping from Unicode to 8859-1. However, the two-character
Unicode sequence 0x0061+0x0300 ("LATIN SMALL LETTER A" + "COMBINING
GRAVE ACCENT") can also be mapped to 8859-1 0xE0 as a loose mapping.
e) Since Shift-JIS distinguishes halfwidth and fullwidth characters,
loose mappings for Shift-JIS must also keep these distinct. For example,
Shift-JIS 0x814D (JIS 0x212E) "grave accent [fullwidth]" is often mapped
to Unicode 0xFF40, "FULLWIDTH GRAVE ACCENT", and the reverse is a strict
mapping. In this case the Unicode sequence 0x3000+0x0300 "IDEOGRAPHIC
SPACE" + "COMBINING GRAVE ACCENT" can also be mapped to Shift-JIS 0x814D
as a loose mapping. However, the Unicode sequence 0x0020+0x0300 "SPACE"
+ "COMBINING GRAVE ACCENT" should not be mapped to Shift-JIS 0x814D as a
loose mapping, although this sequence could be mapped to Shift-JIS 0x60
"grave accent [halfwidth]" as a loose mapping.
Although the MacOS Unicode converter (and its tables) supports strict,
loose, and fallback mappings, the MacOS character mapping tables
accompanying this document provide only the strict mappings.
4. Character set variants and extensions
----------------------------------------
An example illustrates this issue:
The MacOS standard Japanese character set is based on Shift-JIS with
some additional characters. The additions include:
(a) For one-byte characters, five additions and one modification.
(b) Separately-encoded vertical forms for some punctuation and kana
characters from JIS rows 1, 4, and 5. These vertical forms are in
JIS rows 85, 88, and 89.
(c) Apple extension characters, in JIS rows 9-15.
However, in older versions of the Japanese system, some of the fonts
were based on a different encoding which did not include the Apple
extension characters and which encoded vertical forms in JIS rows 11,
14, and 15. Furthermore, PostScript fonts use a different set of
extensions in rows 9-15.
With the MacOS Unicode converter, several variants can be specified for
the MacOS Japanese character set:
* The standard set, with extensions and vertical forms;
* A reduced version of the standard set, without the separately encoded
vertical forms;
* An alternate set that corresponds to the old font variant;
* An alternate set that corresponds to the PostScript variant;
* A basic "least common denominator" set that works with all the old and
new fonts.
The MacOS Japanese character set mappings provided in the accompanying
tables cover only the standard character set, but they are grouped into
three sections: the basic set, the Apple extensions, and the vertical
forms.
5. Mappings that are not one-to-one
-----------------------------------
In some cases, a character in a non-Unicode character set may map to a
sequence of characters in Unicode. To handle the reverse mapping, the
MacOS Unicode converter can break a Unicode stream into appropriate text
elements (which may consist of more than one Unicode character) and can
look up multi-character Unicode sequences.
For example, the Apple extensions in the MacOS standard Japanese
character set include a character for the circled CJK ideograph for
"big". Although Unicode encodes other circled ideographs as single
characters, it does not encode this one. However, this character can be
represented in Unicode as the Unicode sequence 0x5927+0x20DD, the CJK
ideograph for "big" followed by COMBINING ENCLOSING CIRCLE.
In addition, a single Unicode character (or a multi-character Unicode
sequence) may map to a sequence of multiple characters in another
encoding. For example, the Unicode character 0x00BD "VULGAR FRACTION ONE
HALF" cannot be mapped into the MacOS standard Roman character set as a
single character, but it can be mapped to the sequence 0x31+0xDA+0x32,
"digit one" + "fraction slash" + "digit two" (normally this would be a
loose mapping).
Finally, some Unicode characters may be silently consumed when mapping
to some other encodings. For example, when mapping from Unicode to the
MacOS Arabic character set, resolved direction is used to disambiguate
some mappings (this is discussed in the next section). Direction
override characters (Unicodes 0x202C-0x202E) may be used to control the
resolved direction to achieve proper results. Having fulfilled this
role, the direction override characters can then be discarded. They are
included among the Unicode characters that can be represented in the
MacOS Arabic set (they are represented by the direction inherent in
certain characters), but there is no specific output character that
corresponds to them.
The accompanying mapping tables for the MacOS Japanese character set and
the MacOS Arabic character set include one-to-many mappings.
6. Mappings that depend on attributes
-------------------------------------
Mappings from Unicode to other character sets may depend on attributes
such as resolved character direction, the state of symmetric swapping,
and whether the text should use vertical form codes if available (i.e.
whether the text is intended for vertical display on a system that
cannot automatically substitute vertical forms).
a) Resolved character direction
The MacOS Arabic character set was developed in 1986-1987. At that time
the bidirectional line layout algorithm used in the MacOS was fairly
simple; it used only a few direction classes (instead of the 13 or so
now used in the Unicode bidirectional algorithm). In order to permit
users to handle some tricky layout problems, certain punctuation and
symbol characters have duplicate code points, one with a left-right
direction attribute and the other with a right-left direction attribute.
For example, ampersand is encoded at 0x26 with a left-right attribute,
and at 0xA6 with a right-left attribute. However, there is only one
ampersand character in Unicode. We need to have a way to map both of the
MacOS Arabic ampersand characters to Unicode and back again without loss
of information. Mapping one of the MacOS Arabic ampersand characters to
a code in the Unicode corporate use zone is undesirable, since both of
the ampersand characters are likely to be used in text that is
interchanged with other systems.
The problem is solved with the use of direction override characters and
direction-dependent mappings. When mapping from the MacOS Arabic
character set to Unicode, such problem characters are surrounded with an
appropriate direction override:
MacOS Arabic 0x26 ampersand (left)
-> Unicode 0x202D (LRO) + 0x0026 (AMPERSAND) + 0x202C (PDF)
MacOS Arabic 0xA6 ampersand (right)
-> Unicode 0x202E (RLO) + 0x0026 (AMPERSAND) + 0x202C (PDF)
The mappings from Unicode to MacOS Arabic can be disambiguated by the
use of resolved direction:
Unicode 0x0026 -> MacOS Arabic 0x26 (if L) or 0xA6 (if R)
Direction overrides are also used for some other purposes in mapping
MacOS Arabic characters to Unicode. For example, the single MacOS Arabic
ellipsis character has direction class right-left, while the Unicode
HORIZONTAL ELLIPSIS character has direction class neutral. When mapping
the MacOS ellipsis to Unicode, it is surrounded with a direction
override to help preserve proper text layout. However, resolved
direction is not needed or used when mapping the Unicode HORIZONTAL
ELLIPSIS back to MacOS Arabic.
b) Symmetric swapping
In loose mappings from Unicode to the MacOS Arabic character set, the
state of symmetric swapping (which may be changed by the Unicode
characters 0x206A, 0x206B) affects the mapping of paired characters such
as punctuation and brackets. This does not affect the strict mappings
given in the accompanying tables.
c) Horizontal or vertical display
As noted above, the MacOS standard Japanese character set (for
historical reasons) includes separately-encoded vertical forms for some
punctuation and kana. When Unicode characters in the CJK punctuation and
kana ranges are mapped to MacOS Japanese characters and (1) those
characters are intended for vertical display, (2) they will be displayed
in an environment that does not provide automatic vertical form
substitution, and (3) loose mappings are being used, a vertical display
attribute can be used to map certain Unicode characters to the
corresponding vertical form codes in the MacOS Japanese character set.
Note that this capability is only used for loose mappings, and does not
affect the strict mappings given in the accompanying tables. Also note
that this does not affect mapping of the Unicode vertical presentation
forms (which always map to the MacOS Japanese vertical form codes if
those codes are available in the specified variant). Finally, note that
the QuickDraw(TM) GX display environment does provide automatic vertical
forms substitution with appropriate fonts.
7. MacOS character sets
---------------------------
The MacOS can support multiple character sets. In the current MacOS
architecture these character sets are distinguished primarily by script
code: font family IDs are grouped into ranges, and each range is
associated with a script code.
In some cases, there are several variant encodings that share a single
script code. Usually these are minor variants. To distinguish these
variants, additional information is required, such as font name or
system localization code.
The encodings described here (and in the accompanying tables) are the
encodings used in MacOS versions 7.1 and later. In some cases, certain
earlier system versions have used variants of these encodings.
In all MacOS encodings, character codes 0x00-0x7F are identical to ASCII
(except for MacOS Japanese, which changes reverse solidus to yen sign).
Fonts used as "system" fonts (for menus, dialogs, etc.) have four glyphs
at code points 0x11-0x14 for transient use by the Menu Manager. These
glyphs are not intended as characters for use in normal text, and the
associated code points are not generally interpreted as associated with
these glyphs. (However, a "system font variant" mapping table could
provide mappings for these).
Note that in general, character sets cannot be determined from font
layouts (they are not the same thing!). This is most noticeable with
Arabic, Hebrew, and Devanagari.
The following is a list of current MacOS character sets. The
accompanying tables provide mappings from many of these encodings to
Unicode.
a) MacOS encodings for script code 0, smRoman.
* Standard Roman - this is the default for script code 0 (when the
special cases listed below do not apply). It covers several western
European languages, and includes math operators and various symbols.
* Symbol - this is the encoding for the font named "Symbol". It includes
Greek letters, math operators, and miscellaneous symbols. The layout
of the Symbol character set is identical to the layout of the Adobe
Symbol encoding vector, with the addition of the Apple logo at 0xF0.
The Symbol character set encodes some glyph fragments (of arrows,
brackets, etc.) as well as both serif and sans-serif forms for
copyright, registered, and trade mark sign; round-trip mapping of
these characters requires the use of corporate characters.
* Dingbats - this is the encoding for the font named "Zapf Dingbats".
The layout of the Dingbats character set is identical to or a superset
of the layout of the Adobe Zapf Dingbats encoding vector.
* Turkish - this is the encoding if the script code is 0 and the system
region code (system localization) is 24, verTurkey. It has 7 code
point differences from standard Roman.
* Croatian - this is the encoding if the script code is 0 and the system
region code is 68, verCroatia (or 25, verYugoCroatian, only used in
older systems). It has 20 code point differences from standard Roman,
but only 10 differences in repertoire.
* Icelandic - this is the encoding if the script code is 0 and the
system region code is 21, verIceland. It has 6 code point differences
from standard Roman.
* Romanian - this is the encoding if the script code is 0 and the system
region code is 39, verRomania . It has 6 code point differences from
standard Roman.
* Standard Greek (monotonic) - this is the encoding if the script code
is 0 and the system region code is 20, verGreece. Although a script
code is defined for Greek, the Greek localized system does not use it
(the font family IDs are in the smRoman range). This encoding is based
on the ISO/IEC 8859-7 repertoire with additional Roman characters for
French and German, as well as additional symbols.
Greek system 4.1 used a different encoding that matched 8859-7 code
points for Greek letters. Greek system 6.0.7 also used a variant of
the standard encoding, but it was quickly replaced by Greek system
6.0.7.1 which used the standard encoding.
NOTE- The Greek Language Kit, when released, will use the Greek script
code (its Greek fonts will have family IDs in the smGreek range); see
notes under script code 6 below.
See also the Central European Roman encoding under script code 29
below.
b) MacOS encodings for script code 1, smJapanese.
* Standard Japanese - this is the default for script code 1. As
described above, it is based on a Shift-JIS implementation of JIS
X0208-1990 ("fullwidth") and JIS X0201-1976 ("halfwidth"), with 5
additional one-byte characters and one modified character, a set of
Apple extension characters which include many industry standard
extensions, and separate codes for vertical forms of some punctuation
and kana.
There are two variants of standard Japanese associated with specific
fonts: (1) For MaruGothic and HonMincho TrueType fonts in system
software release J-7.1 and Japanese Language Kit 1.0, and (2) for the
PostScript fonts Gothic BBB and Ryumin, which are used with the screen
fonts ChuGothic and SaiMincho. Although they are supported by the
MacOS Unicode converter, these variants are not documented here or
in the accompanying tables. The MacOS Unicode converter also
supports some artificial variants which are just subsets of the
standard Japanese encoding.
c) MacOS encodings for script code 2, smTradChinese.
* Standard Traditional Chinese - this is an extension of Big-5.
d) MacOS encodings for script code 3, smKorean.
* Standard Korean - this is a "shifted" implementation of KSC 5601-1987
(0xA0 is added to the row and to the column), with some additional
characters.
e) MacOS encodings for script code 4, smArabic.
* Standard Arabic - This is based on the ISO/IEC 8859-6 repertoire, with
additional Arabic letters for Persian and Urdu and with additional
Roman letters for European languages. It has the interesting feature
mentioned above that certain ASCII punctuation and symbol characters
are encoded twice, once for each direction. Digit character codes
0x30-0x39 have left-to-right directionality, and may be displayed with
either European digit forms or Arabic digit forms depending on
context. Digit codes 0xB0-0xB9 have right-left directionality and are
always displayed with Arabic digit forms; these are used for special
layout situations such as part numbers.
f) MacOS encodings for script code 5, smHebrew.
* Standard Hebrew - This is based on the ISO/IEC 8859-8 Hebrew letter
repertoire, but adds Hebrew points, some Hebrew ligatures, some
additional Roman letters for European languages, and some non-ASCII
punctuation. As with standard Arabic, certain ASCII punctuation and
symbol characters are encoded twice, once for each direction. This
is also true for the European digits.
There is one minor variant of standard Hebrew associated with
certain fonts, in which LEFT SINGLE QUOTATION MARK at 0xD4 is
replaced by FIGURE SPACE.
g) MacOS encodings for script code 6, smGreek.
This script code will refer to the encoding used with the Greek
Language Kit, when released. It will either be the standard Greek
encoding described above, or a variant that supports polytonic Greek.
h) MacOS encodings for script code 7, smCyrillic.
* Standard Cyrillic - this is the default for script code 7 (when the
special cases listed below do not apply). It is based on the ISO/IEC
8859-5 Cyrillic character repertoire.
* Ukrainian - this is the encoding if the script code is 7 and the
system region code (system localization) is 62, verUkraine. It has 2
code point differences from standard Cyrillic (it adds a case pair
for GHE WITH UPTURN).
* Bulgarian -
An additional Cyrillic variant has been defined to cover the Cyrillic
characters needed for the languages of the central Asian republics
(plus Russian): Uzbek, Kazakh, Kirghiz, Azerbaijani, Turkmen, Tajik).
i) MacOS encodings for script code 9, smDevanagari.
* Standard Devanagari - This is an extension of IS 13194:1991 (ISCII-91)
but is not yet fully defined. The Devanagari encoding used in system
software versions 6.x was different, and was based on ISCII-88.
j) MacOS encodings for script code 21, smThai.
* Standard Thai - This is based on TIS 620-2533, except that three of
the TIS 620-2533 characters are replaced with other characters. Some
undefined code points in TIS 620-2533 are used for additional
punctuation characters.
k) MacOS encodings for script code 25, smSimpChinese.
* Standard simplified Chinese - this is a "shifted" implementation of
GB 2312-1980 (0xA0 is added to the row and to the column), with some
additional characters.
l) MacOS encodings for script code 29, smEastEurRoman.
* Standard Central European - This is similar to standard Roman, but
with a different (and larger) set of European characters and with
fewer symbols. It covers several Slavic languages (Czech, Polish,
Slovak, Slovenian), Hungarian, and the languages of the Baltic
republics (Estonian, Latvian, Lithuanian).
FILE LIST:
The file names here have been changed from the original files
previously published on the Unicode.org FTP server. The mapping
is as follows:
Original Name "8.3" Name
------------------- ------------
MacOS-ReadMe.txt 0README.TXT
MacOS_Cyrillic.txt CYRILLIC.TXT
MacOS_Japanese.txt JAPAN.TXT
MacOS_Turkish.txt TURKISH.TXT
MacOS_Arabic.txt ARABIC.TXT
MacOS_Dingbats.txt DINGBAT.TXT
MacOS_Roman.txt ROMAN.TXT
MacOS_Ukrainian.txt UKRAINE.TXT
MacOS_CentralEuro.txt CNTEURO.TXT
MacOS_Greek.txt GREEK.TXT
MacOS_Romanian.txt ROMANIA.TXT
MacOS_CorpChars.txt CORPCHR.TXT
MacOS_Hebrew.txt HEBREW.TXT
MacOS_Symbol.txt SYMBOL.TXT
MacOS_Croatian.txt CROATIAN.TXT
MacOS_Icelandic.txt ICELAND.TXT
MacOS_Thai.txt THAI.TXT

301
unicode/vendors/apple/roman.txt vendored Normal file
View File

@@ -0,0 +1,301 @@
#
# Name: MacOS_Roman [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <9>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Roman code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Roman code order.
#
# One of these mappings requires the use of a corporate character
# (for the Apple logo character). See the file "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Roman:
# ---------------------
#
# This character set is used for at least the following MacOS
# localizations: U.S., British, Canadian French, French, Swiss
# French, German, Swiss German, Italian, Swiss Italian, Dutch,
# Swedish, Norwegian, Danish, Finnish, Spanish, Catalan,
# Portuguese, Brazilian, and the default International system.
#
# Variants of MacRoman are used for Croatian, Icelandic,
# Turkish, and Romanian. Separate mapping tables are available
# for these encodings.
#
# At least through System 7.5, the bitmap versions of the fonts
# Chicago, New York, Geneva, and Monaco do not implement the
# full Roman character set; they only support MacOS Roman character
# codes up to 0xD8. The TrueType versions of these fonts do
# implement the full character set, as do both the bitmap and
# TrueType versions of the other standard Roman fonts.
#
# In all MacOS encodings, fonts such as Chicago which are used
# as "system" fonts (for menus, dialogs, etc.) have four glyphs
# at code points 0x11-0x14 for transient use by the Menu Manager.
# These glyphs are not intended as characters for use in normal
# text, and the associated code points are not generally
# interpreted as associated with these glyphs; they are usually
# interpreted (if at all) as the control codes DC1-DC4.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x00C6 # LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00A5 # YEN SIGN
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x220F # N-ARY PRODUCT
0xB9 0x03C0 # GREEK SMALL LETTER PI
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
0xBD 0x2126 # OHM SIGN
0xBE 0x00E6 # LATIN SMALL LIGATURE AE
0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 # FRACTION SLASH
0xDB 0x00A4 # CURRENCY SIGN
0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0xFB01 # LATIN SMALL LIGATURE FI
0xDF 0xFB02 # LATIN SMALL LIGATURE FL
0xE0 0x2021 # DOUBLE DAGGER
0xE1 0x00B7 # MIDDLE DOT
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 # PER MILLE SIGN
0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0xF8FF # Apple logo
0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 # LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC # SMALL TILDE
0xF8 0x00AF # MACRON
0xF9 0x02D8 # BREVE
0xFA 0x02D9 # DOT ABOVE
0xFB 0x02DA # RING ABOVE
0xFC 0x00B8 # CEDILLA
0xFD 0x02DD # DOUBLE ACUTE ACCENT
0xFE 0x02DB # OGONEK
0xFF 0x02C7 # CARON

285
unicode/vendors/apple/romania.txt vendored Normal file
View File

@@ -0,0 +1,285 @@
#
# Name: MacOS_Romanian [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <4>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Romanian code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Romanian code order.
#
# One of these mappings requires the use of a corporate character
# (for the Apple logo character). See the file "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Romanian:
# ------------------------
#
# The MacOS Romanian encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Romanian encoding is being used, you must also check if the
# system region code is 39, verRomania.
#
# This character set is a variant of standard MacOS Roman, adding
# upper and lower A breve, S cedilla, and T cedilla. It has 6 code
# point differences from standard Roman.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x0102 # LATIN CAPITAL LETTER A WITH BREVE
0xAF 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00A5 # YEN SIGN
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x220F # N-ARY PRODUCT
0xB9 0x03C0 # GREEK SMALL LETTER PI
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
0xBD 0x2126 # OHM SIGN
0xBE 0x0103 # LATIN SMALL LETTER A WITH BREVE
0xBF 0x015F # LATIN SMALL LETTER S WITH CEDILLA
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 # FRACTION SLASH
0xDB 0x00A4 # CURRENCY SIGN
0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA
0xDF 0x0163 # LATIN SMALL LETTER T WITH CEDILLA
0xE0 0x2021 # DOUBLE DAGGER
0xE1 0x00B7 # MIDDLE DOT
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 # PER MILLE SIGN
0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0xF8FF # Apple logo
0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 # LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC # SMALL TILDE
0xF8 0x00AF # MACRON
0xF9 0x02D8 # BREVE
0xFA 0x02D9 # DOT ABOVE
0xFB 0x02DA # RING ABOVE
0xFC 0x00B8 # CEDILLA
0xFD 0x02DD # DOUBLE ACUTE ACCENT
0xFE 0x02DB # OGONEK
0xFF 0x02C7 # CARON

265
unicode/vendors/apple/symbol.txt vendored Normal file
View File

@@ -0,0 +1,265 @@
#
# Name: MacOS_Symbol [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <4>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Symbol code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Symbol code order.
#
# Several of these mappings require the use of corporate
# characters, including the Apple logo character. See the file
# "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Symbol:
# ----------------------
#
# The MacOS Symbol encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Symbol encoding is being used, you must check if the
# font name is "Symbol".
#
# The layout of the MacOS Symbol character set is identical to
# the layout of the Adobe Symbol encoding vector, with the
# addition of the Apple logo character at 0xF0.
#
# This character set encodes a number of glyph fragments. Some are
# used as extenders: 0x60 is used to extend radical signs, 0xBD and
# 0xBE are used to extend vertical and horizontal arrows, etc. In
# addition, there are top, bottom, and center sections for
# parentheses, brackets, integral signs, and other signs that may
# extend vertically for 2 or more lines of normal text. In general,
# Unicode does not encode such fragments, so corporate characters
# are used for round-trip fidelity.
#
# In addition, Symbol separately encodes both serif and sans-serif
# forms for copyright, trademark, and registered signs. Unicode
# encodes only the abstract characters, so one set of these (the
# sans-serif forms) are mapped using corporate characters.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x2200 # FOR ALL
0x23 0x0023 # NUMBER SIGN
0x24 0x2203 # THERE EXISTS
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x220D # SMALL CONTAINS AS MEMBER
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x2217 # ASTERISK OPERATOR
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x2212 # MINUS SIGN
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x2245 # APPROXIMATELY EQUAL TO
0x41 0x0391 # GREEK CAPITAL LETTER ALPHA
0x42 0x0392 # GREEK CAPITAL LETTER BETA
0x43 0x03A7 # GREEK CAPITAL LETTER CHI
0x44 0x0394 # GREEK CAPITAL LETTER DELTA
0x45 0x0395 # GREEK CAPITAL LETTER EPSILON
0x46 0x03A6 # GREEK CAPITAL LETTER PHI
0x47 0x0393 # GREEK CAPITAL LETTER GAMMA
0x48 0x0397 # GREEK CAPITAL LETTER ETA
0x49 0x0399 # GREEK CAPITAL LETTER IOTA
0x4A 0x03D1 # GREEK THETA SYMBOL
0x4B 0x039A # GREEK CAPITAL LETTER KAPPA
0x4C 0x039B # GREEK CAPITAL LETTER LAMBDA
0x4D 0x039C # GREEK CAPITAL LETTER MU
0x4E 0x039D # GREEK CAPITAL LETTER NU
0x4F 0x039F # GREEK CAPITAL LETTER OMICRON
0x50 0x03A0 # GREEK CAPITAL LETTER PI
0x51 0x0398 # GREEK CAPITAL LETTER THETA
0x52 0x03A1 # GREEK CAPITAL LETTER RHO
0x53 0x03A3 # GREEK CAPITAL LETTER SIGMA
0x54 0x03A4 # GREEK CAPITAL LETTER TAU
0x55 0x03A5 # GREEK CAPITAL LETTER UPSILON
0x56 0x03C2 # GREEK SMALL LETTER FINAL SIGMA
0x57 0x03A9 # GREEK CAPITAL LETTER OMEGA
0x58 0x039E # GREEK CAPITAL LETTER XI
0x59 0x03A8 # GREEK CAPITAL LETTER PSI
0x5A 0x0396 # GREEK CAPITAL LETTER ZETA
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x2234 # THEREFORE
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x22A5 # UP TACK
0x5F 0x005F # LOW LINE
0x60 0xF8E5 # radical extender
0x61 0x03B1 # GREEK SMALL LETTER ALPHA
0x62 0x03B2 # GREEK SMALL LETTER BETA
0x63 0x03C7 # GREEK SMALL LETTER CHI
0x64 0x03B4 # GREEK SMALL LETTER DELTA
0x65 0x03B5 # GREEK SMALL LETTER EPSILON
0x66 0x03C6 # GREEK SMALL LETTER PHI
0x67 0x03B3 # GREEK SMALL LETTER GAMMA
0x68 0x03B7 # GREEK SMALL LETTER ETA
0x69 0x03B9 # GREEK SMALL LETTER IOTA
0x6A 0x03D5 # GREEK PHI SYMBOL
0x6B 0x03BA # GREEK SMALL LETTER KAPPA
0x6C 0x03BB # GREEK SMALL LETTER LAMBDA
0x6D 0x03BC # GREEK SMALL LETTER MU
0x6E 0x03BD # GREEK SMALL LETTER NU
0x6F 0x03BF # GREEK SMALL LETTER OMICRON
0x70 0x03C0 # GREEK SMALL LETTER PI
0x71 0x03B8 # GREEK SMALL LETTER THETA
0x72 0x03C1 # GREEK SMALL LETTER RHO
0x73 0x03C3 # GREEK SMALL LETTER SIGMA
0x74 0x03C4 # GREEK SMALL LETTER TAU
0x75 0x03C5 # GREEK SMALL LETTER UPSILON
0x76 0x03D6 # GREEK PI SYMBOL
0x77 0x03C9 # GREEK SMALL LETTER OMEGA
0x78 0x03BE # GREEK SMALL LETTER XI
0x79 0x03C8 # GREEK SMALL LETTER PSI
0x7A 0x03B6 # GREEK SMALL LETTER ZETA
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x223C # TILDE OPERATOR
0xA1 0x03D2 # GREEK UPSILON WITH HOOK SYMBOL
0xA2 0x2032 # PRIME
0xA3 0x2264 # LESS-THAN OR EQUAL TO
0xA4 0x2044 # FRACTION SLASH
0xA5 0x221E # INFINITY
0xA6 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xA7 0x2663 # BLACK CLUB SUIT
0xA8 0x2666 # BLACK DIAMOND SUIT
0xA9 0x2665 # BLACK HEART SUIT
0xAA 0x2660 # BLACK SPADE SUIT
0xAB 0x2194 # LEFT RIGHT ARROW
0xAC 0x2190 # LEFTWARDS ARROW
0xAD 0x2191 # UPWARDS ARROW
0xAE 0x2192 # RIGHTWARDS ARROW
0xAF 0x2193 # DOWNWARDS ARROW
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2033 # DOUBLE PRIME
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00D7 # MULTIPLICATION SIGN
0xB5 0x221D # PROPORTIONAL TO
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2022 # BULLET
0xB8 0x00F7 # DIVISION SIGN
0xB9 0x2260 # NOT EQUAL TO
0xBA 0x2261 # IDENTICAL TO
0xBB 0x2248 # ALMOST EQUAL TO
0xBC 0x2026 # HORIZONTAL ELLIPSIS
0xBD 0xF8E6 # vertical arrow extender
0xBE 0xF8E7 # horizontal arrow extender
0xBF 0x21B5 # DOWNWARDS ARROW WITH CORNER LEFTWARDS
0xC0 0x2135 # ALEF SYMBOL
0xC1 0x2111 # BLACK-LETTER CAPITAL I
0xC2 0x211C # BLACK-LETTER CAPITAL R
0xC3 0x2118 # SCRIPT CAPITAL P
0xC4 0x2297 # CIRCLED TIMES
0xC5 0x2295 # CIRCLED PLUS
0xC6 0x2205 # EMPTY SET
0xC7 0x2229 # INTERSECTION
0xC8 0x222A # UNION
0xC9 0x2283 # SUPERSET OF
0xCA 0x2287 # SUPERSET OF OR EQUAL TO
0xCB 0x2284 # NOT A SUBSET OF
0xCC 0x2282 # SUBSET OF
0xCD 0x2286 # SUBSET OF OR EQUAL TO
0xCE 0x2208 # ELEMENT OF
0xCF 0x2209 # NOT AN ELEMENT OF
0xD0 0x2220 # ANGLE
0xD1 0x2207 # NABLA
0xD2 0x00AE # REGISTERED SIGN
0xD3 0x00A9 # COPYRIGHT SIGN
0xD4 0x2122 # TRADE MARK SIGN
0xD5 0x220F # N-ARY PRODUCT
0xD6 0x221A # SQUARE ROOT
0xD7 0x22C5 # DOT OPERATOR
0xD8 0x00AC # NOT SIGN
0xD9 0x2227 # LOGICAL AND
0xDA 0x2228 # LOGICAL OR
0xDB 0x21D4 # LEFT RIGHT DOUBLE ARROW
0xDC 0x21D0 # LEFTWARDS DOUBLE ARROW
0xDD 0x21D1 # UPWARDS DOUBLE ARROW
0xDE 0x21D2 # RIGHTWARDS DOUBLE ARROW
0xDF 0x21D3 # DOWNWARDS DOUBLE ARROW
0xE0 0x22C4 # DIAMOND OPERATOR
0xE1 0x2329 # LEFT-POINTING ANGLE BRACKET
0xE2 0xF8E8 # registered sign sans serif
0xE3 0xF8E9 # copyright sign sans serif
0xE4 0xF8EA # trade mark sign sans serif
0xE5 0x2211 # N-ARY SUMMATION
0xE6 0xF8EB # left paren top
0xE7 0xF8EC # left paren extender
0xE8 0xF8ED # left paren bottom
0xE9 0xF8EE # left square bracket top
0xEA 0xF8EF # left square bracket extender
0xEB 0xF8F0 # left square bracket bottom
0xEC 0xF8F1 # left curly bracket top
0xED 0xF8F2 # left curly bracket mid
0xEE 0xF8F3 # left curly bracket bottom
0xEF 0xF8F4 # curly bracket extender
0xF0 0xF8FF # Apple logo
0xF1 0x232A # RIGHT-POINTING ANGLE BRACKET
0xF2 0x222B # INTEGRAL
0xF3 0x2320 # TOP HALF INTEGRAL
0xF4 0xF8F5 # integral extender
0xF5 0x2321 # BOTTOM HALF INTEGRAL
0xF6 0xF8F6 # right paren top
0xF7 0xF8F7 # right paren extender
0xF8 0xF8F8 # right paren bottom
0xF9 0xF8F9 # right square bracket top
0xFA 0xF8FA # right square bracket extender
0xFB 0xF8FB # right square bracket bottom
0xFC 0xF8FC # right curly bracket top
0xFD 0xF8FD # right curly bracket mid
0xFE 0xF8FE # right curly bracket bottom

299
unicode/vendors/apple/thai.txt vendored Normal file
View File

@@ -0,0 +1,299 @@
#
# Name: MacOS_Thai [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <6>)
# Date: 17 November 1995
# Authors: Peter Edberg <edberg1@applelink.apple.com>
# Judy Kettenhofen
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Thai code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Thai code order.
#
# Notes on MacOS Thai:
# --------------------
#
# Codes 0xA1-0xDA and 0xDF-0xFB are the character set from Thai
# standard TIS 620-2533, except that the following changes are
# made:
# 0xEE is TRADE MARK SIGN (instead of THAI CHARACTER YAMAKKAN)
# 0xFA is REGISTERED SIGN (instead of THAI CHARACTER ANGKHANKHU)
# 0xFB is COPYRIGHT SIGN (instead of THAI CHARACTER KHOMUT)
#
# Codes 0x80-0x82, 0x8D-0x8E, 0x91, 0x9D-0x9E, and 0xDB-0xDE are
# various additional punctuation marks (e.g. curly quotes,
# ellipsis), no-break space, and two special characters "word join"
# and "word break".
#
# Codes 0x83-0x8C, 0x8F, and 0x92-0x9C are for positional variants
# of the upper vowels, tone marks, and other signs at 0xD1,
# 0xD4-0xD7, and 0xE7-0xED. The positional variants would normally
# be considered presentation forms only and not characters. In most
# cases they are not typed directly; they are selected automatically
# at display time by the WorldScript software. However, using the
# Thai-DTP keyboard, the presentation forms can in fact be typed
# directly using dead keys. Thus they must be treated as real
# characters in the MacOS Thai encoding, and must be mapped to
# distinct Unicodes - corporate-zone characters in this case - to
# enable roundtrip mapping.
#
# Several code points are undefined and unused (they cannot be
# typed using any of the Mac OS Thai keyboard layouts): 0x90, 0x9F,
# 0xFC-0xFE. In the table below these are mapped to 0xFFFD.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x81 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x82 0x2026 # HORIZONTAL ELLIPSIS
0x83 0xF88C # form for THAI CHARACTER MAI EK, low left position
0x84 0xF88F # form for THAI CHARACTER MAI THO, low left position
0x85 0xF892 # form for THAI CHARACTER MAI TRI, low left position
0x86 0xF895 # form for THAI CHARACTER MAI CHATTAWA, low left position
0x87 0xF898 # form for THAI CHARACTER THANTHAKHAT, low left position
0x88 0xF88B # form for THAI CHARACTER MAI EK, low position
0x89 0xF88E # form for THAI CHARACTER MAI THO, low position
0x8A 0xF891 # form for THAI CHARACTER MAI TRI, low position
0x8B 0xF894 # form for THAI CHARACTER MAI CHATTAWA, low position
0x8C 0xF897 # form for THAI CHARACTER THANTHAKHAT, low position
0x8D 0x201C # LEFT DOUBLE QUOTATION MARK
0x8E 0x201D # RIGHT DOUBLE QUOTATION MARK
0x8F 0xF899 # form for THAI CHARACTER NIKHAHIT, left position
0x90 0xFFFD # (not used, map to Unicode replacement character)
0x91 0x2022 # BULLET
0x92 0xF884 # form for THAI CHARACTER MAI HAN-AKAT, left position
0x93 0xF889 # form for THAI CHARACTER MAITAIKHU, left position
0x94 0xF885 # form for THAI CHARACTER SARA I, left position
0x95 0xF886 # form for THAI CHARACTER SARA II, left position
0x96 0xF887 # form for THAI CHARACTER SARA UE, left position
0x97 0xF888 # form for THAI CHARACTER SARA UEE, left position
0x98 0xF88A # form for THAI CHARACTER MAI EK, left position
0x99 0xF88D # form for THAI CHARACTER MAI THO, left position
0x9A 0xF890 # form for THAI CHARACTER MAI TRI, left position
0x9B 0xF893 # form for THAI CHARACTER MAI CHATTAWA, left position
0x9C 0xF896 # form for THAI CHARACTER THANTHAKHAT, left position
0x9D 0x2018 # LEFT SINGLE QUOTATION MARK
0x9E 0x2019 # RIGHT SINGLE QUOTATION MARK
0x9F 0xFFFD # (not used, map to Unicode replacement character)
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0E01 # THAI CHARACTER KO KAI
0xA2 0x0E02 # THAI CHARACTER KHO KHAI
0xA3 0x0E03 # THAI CHARACTER KHO KHUAT
0xA4 0x0E04 # THAI CHARACTER KHO KHWAI
0xA5 0x0E05 # THAI CHARACTER KHO KHON
0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG
0xA7 0x0E07 # THAI CHARACTER NGO NGU
0xA8 0x0E08 # THAI CHARACTER CHO CHAN
0xA9 0x0E09 # THAI CHARACTER CHO CHING
0xAA 0x0E0A # THAI CHARACTER CHO CHANG
0xAB 0x0E0B # THAI CHARACTER SO SO
0xAC 0x0E0C # THAI CHARACTER CHO CHOE
0xAD 0x0E0D # THAI CHARACTER YO YING
0xAE 0x0E0E # THAI CHARACTER DO CHADA
0xAF 0x0E0F # THAI CHARACTER TO PATAK
0xB0 0x0E10 # THAI CHARACTER THO THAN
0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO
0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO
0xB3 0x0E13 # THAI CHARACTER NO NEN
0xB4 0x0E14 # THAI CHARACTER DO DEK
0xB5 0x0E15 # THAI CHARACTER TO TAO
0xB6 0x0E16 # THAI CHARACTER THO THUNG
0xB7 0x0E17 # THAI CHARACTER THO THAHAN
0xB8 0x0E18 # THAI CHARACTER THO THONG
0xB9 0x0E19 # THAI CHARACTER NO NU
0xBA 0x0E1A # THAI CHARACTER BO BAIMAI
0xBB 0x0E1B # THAI CHARACTER PO PLA
0xBC 0x0E1C # THAI CHARACTER PHO PHUNG
0xBD 0x0E1D # THAI CHARACTER FO FA
0xBE 0x0E1E # THAI CHARACTER PHO PHAN
0xBF 0x0E1F # THAI CHARACTER FO FAN
0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO
0xC1 0x0E21 # THAI CHARACTER MO MA
0xC2 0x0E22 # THAI CHARACTER YO YAK
0xC3 0x0E23 # THAI CHARACTER RO RUA
0xC4 0x0E24 # THAI CHARACTER RU
0xC5 0x0E25 # THAI CHARACTER LO LING
0xC6 0x0E26 # THAI CHARACTER LU
0xC7 0x0E27 # THAI CHARACTER WO WAEN
0xC8 0x0E28 # THAI CHARACTER SO SALA
0xC9 0x0E29 # THAI CHARACTER SO RUSI
0xCA 0x0E2A # THAI CHARACTER SO SUA
0xCB 0x0E2B # THAI CHARACTER HO HIP
0xCC 0x0E2C # THAI CHARACTER LO CHULA
0xCD 0x0E2D # THAI CHARACTER O ANG
0xCE 0x0E2E # THAI CHARACTER HO NOKHUK
0xCF 0x0E2F # THAI CHARACTER PAIYANNOI
0xD0 0x0E30 # THAI CHARACTER SARA A
0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT
0xD2 0x0E32 # THAI CHARACTER SARA AA
0xD3 0x0E33 # THAI CHARACTER SARA AM
0xD4 0x0E34 # THAI CHARACTER SARA I
0xD5 0x0E35 # THAI CHARACTER SARA II
0xD6 0x0E36 # THAI CHARACTER SARA UE
0xD7 0x0E37 # THAI CHARACTER SARA UEE
0xD8 0x0E38 # THAI CHARACTER SARA U
0xD9 0x0E39 # THAI CHARACTER SARA UU
0xDA 0x0E3A # THAI CHARACTER PHINTHU
0xDB 0xFEFF # ZERO WIDTH NO-BREAK SPACE
0xDC 0x200B # ZERO WIDTH SPACE
0xDD 0x2013 # EN DASH
0xDE 0x2014 # EM DASH
0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT
0xE0 0x0E40 # THAI CHARACTER SARA E
0xE1 0x0E41 # THAI CHARACTER SARA AE
0xE2 0x0E42 # THAI CHARACTER SARA O
0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN
0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI
0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO
0xE6 0x0E46 # THAI CHARACTER MAIYAMOK
0xE7 0x0E47 # THAI CHARACTER MAITAIKHU
0xE8 0x0E48 # THAI CHARACTER MAI EK
0xE9 0x0E49 # THAI CHARACTER MAI THO
0xEA 0x0E4A # THAI CHARACTER MAI TRI
0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA
0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT
0xED 0x0E4D # THAI CHARACTER NIKHAHIT
0xEE 0x2122 # TRADE MARK SIGN
0xEF 0x0E4F # THAI CHARACTER FONGMAN
0xF0 0x0E50 # THAI DIGIT ZERO
0xF1 0x0E51 # THAI DIGIT ONE
0xF2 0x0E52 # THAI DIGIT TWO
0xF3 0x0E53 # THAI DIGIT THREE
0xF4 0x0E54 # THAI DIGIT FOUR
0xF5 0x0E55 # THAI DIGIT FIVE
0xF6 0x0E56 # THAI DIGIT SIX
0xF7 0x0E57 # THAI DIGIT SEVEN
0xF8 0x0E58 # THAI DIGIT EIGHT
0xF9 0x0E59 # THAI DIGIT NINE
0xFA 0x00AE # REGISTERED SIGN
0xFB 0x00A9 # COPYRIGHT SIGN
0xFC 0xFFFD # (not used, map to Unicode replacement character)
0xFD 0xFFFD # (not used, map to Unicode replacement character)
0xFE 0xFFFD # (not used, map to Unicode replacement character)
0xFF 0xFFFD # (not used, map to Unicode replacement character)

289
unicode/vendors/apple/turkish.txt vendored Normal file
View File

@@ -0,0 +1,289 @@
#
# Name: MacOS_Turkish [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <4>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Turkish code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Turkish code order.
#
# Two of these mappings requires the use of a corporate character:
# for the Apple logo character, and for the one undefined code
# point. See the file "MacOS-CorpCharList".
# NOTE: The graphic image associated with the Apple logo character
# is not authorized for use without permission of Apple, and
# unauthorized use might constitute trademark infringement.
#
# Notes on MacOS Turkish:
# -----------------------
#
# The MacOS Turkish encoding shares the script code smRoman
# (0) with the standard MacOS Roman encoding. To determine if
# the Turkish encoding is being used, you must also check if the
# system region code is 24, verTurkey.
#
# This character set is a variant of standard MacOS Roman. It adds
# upper & lower G with breve, upper & lower S with cedilla, upper I
# with dot, and moves the dotless lower i from its position at 0xF5
# in standard MacOS Roman to a position at 0xDD here (leaving the
# 0xF5 code point undefined in MacTurkish). This gives a total of 7
# code point differences from standard MacOS Roman.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x00DF # LATIN SMALL LETTER SHARP S
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x00C6 # LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x00A5 # YEN SIGN
0xB5 0x00B5 # MICRO SIGN
0xB6 0x2202 # PARTIAL DIFFERENTIAL
0xB7 0x2211 # N-ARY SUMMATION
0xB8 0x220F # N-ARY PRODUCT
0xB9 0x03C0 # GREEK SMALL LETTER PI
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
0xBD 0x2126 # OHM SIGN
0xBE 0x00E6 # LATIN SMALL LIGATURE AE
0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
0xCF 0x0153 # LATIN SMALL LIGATURE OE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x25CA # LOZENGE
0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x011E # LATIN CAPITAL LETTER G WITH BREVE
0xDB 0x011F # LATIN SMALL LETTER G WITH BREVE
0xDC 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
0xDD 0x0131 # LATIN SMALL LETTER DOTLESS I
0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
0xDF 0x015F # LATIN SMALL LETTER S WITH CEDILLA
0xE0 0x2021 # DOUBLE DAGGER
0xE1 0x00B7 # MIDDLE DOT
0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 # PER MILLE SIGN
0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0xF8FF # Apple logo
0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0xF8A0 # undefined1
0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC # SMALL TILDE
0xF8 0x00AF # MACRON
0xF9 0x02D8 # BREVE
0xFA 0x02D9 # DOT ABOVE
0xFB 0x02DA # RING ABOVE
0xFC 0x00B8 # CEDILLA
0xFD 0x02DD # DOUBLE ACUTE ACCENT
0xFE 0x02DB # OGONEK
0xFF 0x02C7 # CARON

279
unicode/vendors/apple/ukraine.txt vendored Normal file
View File

@@ -0,0 +1,279 @@
#
# Name: MacOS_Ukrainian [to Unicode]
# Unicode versions: 1.1, 2.0
# Table version: 0.2 (from internal ufrm version <4>)
# Date: 15 April 1995
# Author: Peter Edberg <edberg1@applelink.apple.com>
#
# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
# throughout this document, "Macintosh" can be used to refer to
# Macintosh computers and "Unicode" can be used to refer to the
# Unicode standard.
#
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
# These mapping tables and character lists are preliminary and
# subject to change. Updated tables will be available from the
# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
# (http://www.info.apple.com), and possibly on diskette from APDA
# (Apple's mail-order distribution service for developers).
#
# Format:
# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
# Column #1 is the MacOS Ukrainian code (in hex as 0xNN)
# Column #2 is the Unicode (in hex as 0xNNNN)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in MacOS Ukrainian code order.
#
# Notes on MacOS Ukrainian:
# -------------------------
#
# The MacOS Ukrainian encoding shares the script code smCyrillic
# (7) with the standard MacOS Cyrillic encoding. To determine if
# the Ukrainian encoding is being used, you must also check if
# the system region code is 62, verUkraine.
#
# This character set is a variant of standard MacOS Cyrillic. It
# adds upper & lower GHE WITH UPTURN, for a grand total of 2 code
# point differences from standard MacOS Cyrillic.
#
##################
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
#
0x80 0x0410 # CYRILLIC CAPITAL LETTER A
0x81 0x0411 # CYRILLIC CAPITAL LETTER BE
0x82 0x0412 # CYRILLIC CAPITAL LETTER VE
0x83 0x0413 # CYRILLIC CAPITAL LETTER GHE
0x84 0x0414 # CYRILLIC CAPITAL LETTER DE
0x85 0x0415 # CYRILLIC CAPITAL LETTER IE
0x86 0x0416 # CYRILLIC CAPITAL LETTER ZHE
0x87 0x0417 # CYRILLIC CAPITAL LETTER ZE
0x88 0x0418 # CYRILLIC CAPITAL LETTER I
0x89 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
0x8A 0x041A # CYRILLIC CAPITAL LETTER KA
0x8B 0x041B # CYRILLIC CAPITAL LETTER EL
0x8C 0x041C # CYRILLIC CAPITAL LETTER EM
0x8D 0x041D # CYRILLIC CAPITAL LETTER EN
0x8E 0x041E # CYRILLIC CAPITAL LETTER O
0x8F 0x041F # CYRILLIC CAPITAL LETTER PE
0x90 0x0420 # CYRILLIC CAPITAL LETTER ER
0x91 0x0421 # CYRILLIC CAPITAL LETTER ES
0x92 0x0422 # CYRILLIC CAPITAL LETTER TE
0x93 0x0423 # CYRILLIC CAPITAL LETTER U
0x94 0x0424 # CYRILLIC CAPITAL LETTER EF
0x95 0x0425 # CYRILLIC CAPITAL LETTER HA
0x96 0x0426 # CYRILLIC CAPITAL LETTER TSE
0x97 0x0427 # CYRILLIC CAPITAL LETTER CHE
0x98 0x0428 # CYRILLIC CAPITAL LETTER SHA
0x99 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
0x9A 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
0x9B 0x042B # CYRILLIC CAPITAL LETTER YERU
0x9C 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
0x9D 0x042D # CYRILLIC CAPITAL LETTER E
0x9E 0x042E # CYRILLIC CAPITAL LETTER YU
0x9F 0x042F # CYRILLIC CAPITAL LETTER YA
0xA0 0x2020 # DAGGER
0xA1 0x00B0 # DEGREE SIGN
0xA2 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A7 # SECTION SIGN
0xA5 0x2022 # BULLET
0xA6 0x00B6 # PILCROW SIGN
0xA7 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0xA8 0x00AE # REGISTERED SIGN
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x2122 # TRADE MARK SIGN
0xAB 0x0402 # CYRILLIC CAPITAL LETTER DJE
0xAC 0x0452 # CYRILLIC SMALL LETTER DJE
0xAD 0x2260 # NOT EQUAL TO
0xAE 0x0403 # CYRILLIC CAPITAL LETTER GJE
0xAF 0x0453 # CYRILLIC SMALL LETTER GJE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x2264 # LESS-THAN OR EQUAL TO
0xB3 0x2265 # GREATER-THAN OR EQUAL TO
0xB4 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0xB5 0x00B5 # MICRO SIGN
0xB6 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN
0xB7 0x0408 # CYRILLIC CAPITAL LETTER JE
0xB8 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xB9 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
0xBA 0x0407 # CYRILLIC CAPITAL LETTER YI
0xBB 0x0457 # CYRILLIC SMALL LETTER YI
0xBC 0x0409 # CYRILLIC CAPITAL LETTER LJE
0xBD 0x0459 # CYRILLIC SMALL LETTER LJE
0xBE 0x040A # CYRILLIC CAPITAL LETTER NJE
0xBF 0x045A # CYRILLIC SMALL LETTER NJE
0xC0 0x0458 # CYRILLIC SMALL LETTER JE
0xC1 0x0405 # CYRILLIC CAPITAL LETTER DZE
0xC2 0x00AC # NOT SIGN
0xC3 0x221A # SQUARE ROOT
0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 # ALMOST EQUAL TO
0xC6 0x2206 # INCREMENT
0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 # HORIZONTAL ELLIPSIS
0xCA 0x00A0 # NO-BREAK SPACE
0xCB 0x040B # CYRILLIC CAPITAL LETTER TSHE
0xCC 0x045B # CYRILLIC SMALL LETTER TSHE
0xCD 0x040C # CYRILLIC CAPITAL LETTER KJE
0xCE 0x045C # CYRILLIC SMALL LETTER KJE
0xCF 0x0455 # CYRILLIC SMALL LETTER DZE
0xD0 0x2013 # EN DASH
0xD1 0x2014 # EM DASH
0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 # DIVISION SIGN
0xD7 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xD8 0x040E # CYRILLIC CAPITAL LETTER SHORT U
0xD9 0x045E # CYRILLIC SMALL LETTER SHORT U
0xDA 0x040F # CYRILLIC CAPITAL LETTER DZHE
0xDB 0x045F # CYRILLIC SMALL LETTER DZHE
0xDC 0x2116 # NUMERO SIGN
0xDD 0x0401 # CYRILLIC CAPITAL LETTER IO
0xDE 0x0451 # CYRILLIC SMALL LETTER IO
0xDF 0x044F # CYRILLIC SMALL LETTER YA
0xE0 0x0430 # CYRILLIC SMALL LETTER A
0xE1 0x0431 # CYRILLIC SMALL LETTER BE
0xE2 0x0432 # CYRILLIC SMALL LETTER VE
0xE3 0x0433 # CYRILLIC SMALL LETTER GHE
0xE4 0x0434 # CYRILLIC SMALL LETTER DE
0xE5 0x0435 # CYRILLIC SMALL LETTER IE
0xE6 0x0436 # CYRILLIC SMALL LETTER ZHE
0xE7 0x0437 # CYRILLIC SMALL LETTER ZE
0xE8 0x0438 # CYRILLIC SMALL LETTER I
0xE9 0x0439 # CYRILLIC SMALL LETTER SHORT I
0xEA 0x043A # CYRILLIC SMALL LETTER KA
0xEB 0x043B # CYRILLIC SMALL LETTER EL
0xEC 0x043C # CYRILLIC SMALL LETTER EM
0xED 0x043D # CYRILLIC SMALL LETTER EN
0xEE 0x043E # CYRILLIC SMALL LETTER O
0xEF 0x043F # CYRILLIC SMALL LETTER PE
0xF0 0x0440 # CYRILLIC SMALL LETTER ER
0xF1 0x0441 # CYRILLIC SMALL LETTER ES
0xF2 0x0442 # CYRILLIC SMALL LETTER TE
0xF3 0x0443 # CYRILLIC SMALL LETTER U
0xF4 0x0444 # CYRILLIC SMALL LETTER EF
0xF5 0x0445 # CYRILLIC SMALL LETTER HA
0xF6 0x0446 # CYRILLIC SMALL LETTER TSE
0xF7 0x0447 # CYRILLIC SMALL LETTER CHE
0xF8 0x0448 # CYRILLIC SMALL LETTER SHA
0xF9 0x0449 # CYRILLIC SMALL LETTER SHCHA
0xFA 0x044A # CYRILLIC SMALL LETTER HARD SIGN
0xFB 0x044B # CYRILLIC SMALL LETTER YERU
0xFC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
0xFD 0x044D # CYRILLIC SMALL LETTER E
0xFE 0x044E # CYRILLIC SMALL LETTER YU
0xFF 0x00A4 # CURRENCY SIGN

197
unicode/vendors/ibm/readme.txt vendored Normal file
View File

@@ -0,0 +1,197 @@
The following is a listing of the differences between IBM's mappings
of certain IBM code pages and Unicode, and the mappings for IBM code
pages that came from various sources and were earlier made available
at the Unicode ftp site.
The first set of differences refers to tables found originally in the
Microsoft directory at unicode.org. The DBCS tables were in the
EastAsiaMaps directory. The findings are based on the content of the
files as of April 26, 1996. Newer versions may result in fewer
differences.
Note that IBM has many conversion tables to Unicode available in a
binary (machine readable) format on a CD-ROM included with the
document SC09-2190-00 "CDRA Reference and Registry". These tables
are also available in a readable format from IBM. For licensing
information, please contact an IBM representative to the Unicode
council. Currently (March/96) these are:
Dr. V.S. (Uma) Umamaheswaran dorai@vnet.ibm.com
John Gioia gioia@vnet.ibm.com
Lisa Moore lisam@vnet.ibm.com
Or, you may send a note to nltc@vnet.ibm.com.
=======================================================================
Code Pages 00437 (US etc.)
00860 (Portugal)
00861 (Iceland)
00862 (Israel)
00863 (Canadian French)
00865 (Nordic)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
0xE6 U00B5 (MICRO SIGN) U03BC (GREEK SMALL LETTER MU)
The "rotation" of the control characters at 0x1A, 0x1C and
0x7F is due to the frequent use of 0x1A as end-of-file by
PC file systems and applications.
=======================================================================
Code Page 00852
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
0xAA U00AC (NOT SIGN) ---- (Unassigned)
Note that Microsoft code page 852 has a "not sign" in position 0xAA
whereas IBM 852 has 0xAA as unassigned. In IBM mappings, unassigned
code points in a code page are generally mapped to SUB (U001A) in the
binary tables. The readable tables do not contain entries for these
points.
=======================================================================
Code Page 00850 (Latin 1)
00855 (Cyrillic)
00866 (Cyrillic - Russian)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
=======================================================================
Code Page 00857 (Turkish)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
=======================================================================
Code Page 00864 (Arabic)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
0x9B U009B ---- (Unassigned)
0x9C U009C ---- (Unassigned)
0x9F U009F U200C (ZERO WIDTH NON-JOINER)
0xA6 UF8BE ---- (Unassigned)
0xA7 UF8BF ---- (Unassigned)
0xD7 UFEC1 (ISOLATE ARABIC TAH) UFEC3 (MEDIAL ARABIC TAH)
0xD8 UFEC5 (ISOLATE ARABIC DHAH) UFEC7 (MEDIAL ARABIC DHAH)
0xF1 U0651 (ARABIC SHADDAH) UFE7C (ARABIC SPACING SHADDAH)
=======================================================================
Code Page 00869 (Greek)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
0x80 U0080 ---- (Unassigned)
0x81 U0081 ---- (Unassigned)
0x82 U0082 ---- (Unassigned)
0x83 U0083 ---- (Unassigned)
0x84 U0084 ---- (Unassigned)
0x85 U0085 ---- (Unassigned)
0x87 U0087 ---- (Unassigned)
0x88 U00B7 (MIDDLE DOT) U0387 (GREEK ANO TELEIA)
0x93 U0093 ---- (Unassigned)
0x94 U0094 ---- (Unassigned)
0xEF U0384 (GREEK TONOS) U00B4 (ACUTE ACCENT)
=======================================================================
Code Page 00874 (Thai)
Microsoft IBM
--------- -----
0x1A U001A U001C
0x1C U001C U007F
0x7F U007F U001A
0x91 U2018 ---- (Unassigned)
0x92 U2019 ---- (Unassigned)
0x93 U201C ---- (Unassigned)
0x94 U201D ---- (Unassigned)
0x95 U2022 ---- (Unassigned)
0x96 U2013 ---- (Unassigned)
0x97 U2014 ---- (Unassigned)
0xA0 U00A0 U0E48 (THAI CHARACTER MAI EK)
0xDB ---- (Unassigned) U0E49 (THAI CHARACTER MAI THO)
0xDC ---- (Unassigned) U0E4A (THAI CHARACTER MAI TRI)
0xDD ---- (Unassigned) U0E4B (THAI CHARACTER MAI CHATTAW)
0xDE ---- (Unassigned) U0E4C (THAI CHARACTER THANTHAKHAT)
0xFC ---- (Unassigned) U00A2 (CENT SIGN)
0xFD ---- (Unassigned) U00AC (NOT SIGN)
0xFE ---- (Unassigned) U00A6 (BROKEN BAR)
0xFF ---- (Unassigned) U00A0 (NO-BREAK SPACE)
=======================================================================
Regarding the mapping table between Unicode and Asian each country's
National Standard, there are several differences between the tables in
this directory and the table developed by IBM.
The following list shows these differences.
=======================================================================
Japanese (JIS X0208)
Unicode IBM
------- -----
(1) 0x213D U2015 U2014
Note:
(1) According to conversion table defined on JIS X0221 (ISO 10646-1
JIS version), JIS:0x213D is mapped to U2014.
=======================================================================
S-Chinese (GB 2312)
Unicode IBM
------- -----
(1) 0x212C U2225 U2016
(2) 0x2327 UFF07 U00B4
Note:
(1) According to GB2312-80 standard, the character name of
GB2312:0x212C is Double Vertical Line. And, U2016 is
Double Vertical Line.
(2) The character name of GB2312:0x2327 is Single Quotation
Mark Right. Though no same character name exists in Unicode,
glyph of U00B4 looks similar than UFF07.
=======================================================================
Please note that it is IBM policy to create a new code page identifier
when there are any changes (other than additions) to a code page.
This allows data or environment tagged with a specific identifier to
have a precise meaning even after many years, and allows migration of
environments (resources such as keyboard drivers, fonts etc..) to be
managed in an orderly manner. This may result in a mismatch between
an IBM identifier and the same identifier used by another vendor if
that other vendor has modified the contents of the code page without
changing the identifier.
Current known cases of a code page not matching the IBM code page using
the same identifier include:
Microsoft 932 (Japanese)
Microsoft 936 (Simplified Chinese)
Microsoft 949 (Korean)
Microsoft 852 (See above)

275
unicode/vendors/micsft/ebcdic/cp037.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp037_IBMUSCanada to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp037_IBMUSCanada code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp037_IBMUSCanada order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x009C #CONTROL
0x05 0x0009 #HORIZONTAL TABULATION
0x06 0x0086 #CONTROL
0x07 0x007F #DELETE
0x08 0x0097 #CONTROL
0x09 0x008D #CONTROL
0x0A 0x008E #CONTROL
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x009D #CONTROL
0x15 0x0085 #CONTROL
0x16 0x0008 #BACKSPACE
0x17 0x0087 #CONTROL
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x0092 #CONTROL
0x1B 0x008F #CONTROL
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0080 #CONTROL
0x21 0x0081 #CONTROL
0x22 0x0082 #CONTROL
0x23 0x0083 #CONTROL
0x24 0x0084 #CONTROL
0x25 0x000A #LINE FEED
0x26 0x0017 #END OF TRANSMISSION BLOCK
0x27 0x001B #ESCAPE
0x28 0x0088 #CONTROL
0x29 0x0089 #CONTROL
0x2A 0x008A #CONTROL
0x2B 0x008B #CONTROL
0x2C 0x008C #CONTROL
0x2D 0x0005 #ENQUIRY
0x2E 0x0006 #ACKNOWLEDGE
0x2F 0x0007 #BELL
0x30 0x0090 #CONTROL
0x31 0x0091 #CONTROL
0x32 0x0016 #SYNCHRONOUS IDLE
0x33 0x0093 #CONTROL
0x34 0x0094 #CONTROL
0x35 0x0095 #CONTROL
0x36 0x0096 #CONTROL
0x37 0x0004 #END OF TRANSMISSION
0x38 0x0098 #CONTROL
0x39 0x0099 #CONTROL
0x3A 0x009A #CONTROL
0x3B 0x009B #CONTROL
0x3C 0x0014 #DEVICE CONTROL FOUR
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
0x3E 0x009E #CONTROL
0x3F 0x001A #SUBSTITUTE
0x40 0x0020 #SPACE
0x41 0x00A0 #NO-BREAK SPACE
0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x4A 0x00A2 #CENT SIGN
0x4B 0x002E #FULL STOP
0x4C 0x003C #LESS-THAN SIGN
0x4D 0x0028 #LEFT PARENTHESIS
0x4E 0x002B #PLUS SIGN
0x4F 0x007C #VERTICAL LINE
0x50 0x0026 #AMPERSAND
0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
0x5A 0x0021 #EXCLAMATION MARK
0x5B 0x0024 #DOLLAR SIGN
0x5C 0x002A #ASTERISK
0x5D 0x0029 #RIGHT PARENTHESIS
0x5E 0x003B #SEMICOLON
0x5F 0x00AC #NOT SIGN
0x60 0x002D #HYPHEN-MINUS
0x61 0x002F #SOLIDUS
0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x6A 0x00A6 #BROKEN BAR
0x6B 0x002C #COMMA
0x6C 0x0025 #PERCENT SIGN
0x6D 0x005F #LOW LINE
0x6E 0x003E #GREATER-THAN SIGN
0x6F 0x003F #QUESTION MARK
0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0x79 0x0060 #GRAVE ACCENT
0x7A 0x003A #COLON
0x7B 0x0023 #NUMBER SIGN
0x7C 0x0040 #COMMERCIAL AT
0x7D 0x0027 #APOSTROPHE
0x7E 0x003D #EQUALS SIGN
0x7F 0x0022 #QUOTATION MARK
0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0x81 0x0061 #LATIN SMALL LETTER A
0x82 0x0062 #LATIN SMALL LETTER B
0x83 0x0063 #LATIN SMALL LETTER C
0x84 0x0064 #LATIN SMALL LETTER D
0x85 0x0065 #LATIN SMALL LETTER E
0x86 0x0066 #LATIN SMALL LETTER F
0x87 0x0067 #LATIN SMALL LETTER G
0x88 0x0068 #LATIN SMALL LETTER H
0x89 0x0069 #LATIN SMALL LETTER I
0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8C 0x00F0 #LATIN SMALL LETTER ETH (ICELANDIC)
0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0x8E 0x00FE #LATIN SMALL LETTER THORN (ICELANDIC)
0x8F 0x00B1 #PLUS-MINUS SIGN
0x90 0x00B0 #DEGREE SIGN
0x91 0x006A #LATIN SMALL LETTER J
0x92 0x006B #LATIN SMALL LETTER K
0x93 0x006C #LATIN SMALL LETTER L
0x94 0x006D #LATIN SMALL LETTER M
0x95 0x006E #LATIN SMALL LETTER N
0x96 0x006F #LATIN SMALL LETTER O
0x97 0x0070 #LATIN SMALL LETTER P
0x98 0x0071 #LATIN SMALL LETTER Q
0x99 0x0072 #LATIN SMALL LETTER R
0x9A 0x00AA #FEMININE ORDINAL INDICATOR
0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
0x9C 0x00E6 #LATIN SMALL LIGATURE AE
0x9D 0x00B8 #CEDILLA
0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
0x9F 0x00A4 #CURRENCY SIGN
0xA0 0x00B5 #MICRO SIGN
0xA1 0x007E #TILDE
0xA2 0x0073 #LATIN SMALL LETTER S
0xA3 0x0074 #LATIN SMALL LETTER T
0xA4 0x0075 #LATIN SMALL LETTER U
0xA5 0x0076 #LATIN SMALL LETTER V
0xA6 0x0077 #LATIN SMALL LETTER W
0xA7 0x0078 #LATIN SMALL LETTER X
0xA8 0x0079 #LATIN SMALL LETTER Y
0xA9 0x007A #LATIN SMALL LETTER Z
0xAA 0x00A1 #INVERTED EXCLAMATION MARK
0xAB 0x00BF #INVERTED QUESTION MARK
0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (ICELANDIC)
0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xAE 0x00DE #LATIN CAPITAL LETTER THORN (ICELANDIC)
0xAF 0x00AE #REGISTERED SIGN
0xB0 0x005E #CIRCUMFLEX ACCENT
0xB1 0x00A3 #POUND SIGN
0xB2 0x00A5 #YEN SIGN
0xB3 0x00B7 #MIDDLE DOT
0xB4 0x00A9 #COPYRIGHT SIGN
0xB5 0x00A7 #SECTION SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
0xB8 0x00BD #VULGAR FRACTION ONE HALF
0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBA 0x005B #LEFT SQUARE BRACKET
0xBB 0x005D #RIGHT SQUARE BRACKET
0xBC 0x00AF #MACRON
0xBD 0x00A8 #DIAERESIS
0xBE 0x00B4 #ACUTE ACCENT
0xBF 0x00D7 #MULTIPLICATION SIGN
0xC0 0x007B #LEFT CURLY BRACKET
0xC1 0x0041 #LATIN CAPITAL LETTER A
0xC2 0x0042 #LATIN CAPITAL LETTER B
0xC3 0x0043 #LATIN CAPITAL LETTER C
0xC4 0x0044 #LATIN CAPITAL LETTER D
0xC5 0x0045 #LATIN CAPITAL LETTER E
0xC6 0x0046 #LATIN CAPITAL LETTER F
0xC7 0x0047 #LATIN CAPITAL LETTER G
0xC8 0x0048 #LATIN CAPITAL LETTER H
0xC9 0x0049 #LATIN CAPITAL LETTER I
0xCA 0x00AD #SOFT HYPHEN
0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xCC 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0xD0 0x007D #RIGHT CURLY BRACKET
0xD1 0x004A #LATIN CAPITAL LETTER J
0xD2 0x004B #LATIN CAPITAL LETTER K
0xD3 0x004C #LATIN CAPITAL LETTER L
0xD4 0x004D #LATIN CAPITAL LETTER M
0xD5 0x004E #LATIN CAPITAL LETTER N
0xD6 0x004F #LATIN CAPITAL LETTER O
0xD7 0x0050 #LATIN CAPITAL LETTER P
0xD8 0x0051 #LATIN CAPITAL LETTER Q
0xD9 0x0052 #LATIN CAPITAL LETTER R
0xDA 0x00B9 #SUPERSCRIPT ONE
0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xDC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xE0 0x005C #REVERSE SOLIDUS
0xE1 0x00F7 #DIVISION SIGN
0xE2 0x0053 #LATIN CAPITAL LETTER S
0xE3 0x0054 #LATIN CAPITAL LETTER T
0xE4 0x0055 #LATIN CAPITAL LETTER U
0xE5 0x0056 #LATIN CAPITAL LETTER V
0xE6 0x0057 #LATIN CAPITAL LETTER W
0xE7 0x0058 #LATIN CAPITAL LETTER X
0xE8 0x0059 #LATIN CAPITAL LETTER Y
0xE9 0x005A #LATIN CAPITAL LETTER Z
0xEA 0x00B2 #SUPERSCRIPT TWO
0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xEC 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xF0 0x0030 #DIGIT ZERO
0xF1 0x0031 #DIGIT ONE
0xF2 0x0032 #DIGIT TWO
0xF3 0x0033 #DIGIT THREE
0xF4 0x0034 #DIGIT FOUR
0xF5 0x0035 #DIGIT FIVE
0xF6 0x0036 #DIGIT SIX
0xF7 0x0037 #DIGIT SEVEN
0xF8 0x0038 #DIGIT EIGHT
0xF9 0x0039 #DIGIT NINE
0xFA 0x00B3 #SUPERSCRIPT THREE
0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xFC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xFF 0x009F #CONTROL


275
unicode/vendors/micsft/ebcdic/cp1026.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp1026_IBMLatin5Turkish to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1026_IBMLatin5Turkish code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1026_IBMLatin5Turkish order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x009C #CONTROL
0x05 0x0009 #HORIZONTAL TABULATION
0x06 0x0086 #CONTROL
0x07 0x007F #DELETE
0x08 0x0097 #CONTROL
0x09 0x008D #CONTROL
0x0A 0x008E #CONTROL
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x009D #CONTROL
0x15 0x0085 #CONTROL
0x16 0x0008 #BACKSPACE
0x17 0x0087 #CONTROL
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x0092 #CONTROL
0x1B 0x008F #CONTROL
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0080 #CONTROL
0x21 0x0081 #CONTROL
0x22 0x0082 #CONTROL
0x23 0x0083 #CONTROL
0x24 0x0084 #CONTROL
0x25 0x000A #LINE FEED
0x26 0x0017 #END OF TRANSMISSION BLOCK
0x27 0x001B #ESCAPE
0x28 0x0088 #CONTROL
0x29 0x0089 #CONTROL
0x2A 0x008A #CONTROL
0x2B 0x008B #CONTROL
0x2C 0x008C #CONTROL
0x2D 0x0005 #ENQUIRY
0x2E 0x0006 #ACKNOWLEDGE
0x2F 0x0007 #BELL
0x30 0x0090 #CONTROL
0x31 0x0091 #CONTROL
0x32 0x0016 #SYNCHRONOUS IDLE
0x33 0x0093 #CONTROL
0x34 0x0094 #CONTROL
0x35 0x0095 #CONTROL
0x36 0x0096 #CONTROL
0x37 0x0004 #END OF TRANSMISSION
0x38 0x0098 #CONTROL
0x39 0x0099 #CONTROL
0x3A 0x009A #CONTROL
0x3B 0x009B #CONTROL
0x3C 0x0014 #DEVICE CONTROL FOUR
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
0x3E 0x009E #CONTROL
0x3F 0x001A #SUBSTITUTE
0x40 0x0020 #SPACE
0x41 0x00A0 #NO-BREAK SPACE
0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x48 0x007B #LEFT CURLY BRACKET
0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x4A 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x4B 0x002E #FULL STOP
0x4C 0x003C #LESS-THAN SIGN
0x4D 0x0028 #LEFT PARENTHESIS
0x4E 0x002B #PLUS SIGN
0x4F 0x0021 #EXCLAMATION MARK
0x50 0x0026 #AMPERSAND
0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
0x5A 0x011E #LATIN CAPITAL LETTER G WITH BREVE
0x5B 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
0x5C 0x002A #ASTERISK
0x5D 0x0029 #RIGHT PARENTHESIS
0x5E 0x003B #SEMICOLON
0x5F 0x005E #CIRCUMFLEX ACCENT
0x60 0x002D #HYPHEN-MINUS
0x61 0x002F #SOLIDUS
0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x68 0x005B #LEFT SQUARE BRACKET
0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x6A 0x015F #LATIN SMALL LETTER S WITH CEDILLA
0x6B 0x002C #COMMA
0x6C 0x0025 #PERCENT SIGN
0x6D 0x005F #LOW LINE
0x6E 0x003E #GREATER-THAN SIGN
0x6F 0x003F #QUESTION MARK
0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0x79 0x0131 #LATIN SMALL LETTER DOTLESS I
0x7A 0x003A #COLON
0x7B 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x7C 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
0x7D 0x0027 #APOSTROPHE
0x7E 0x003D #EQUALS SIGN
0x7F 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0x81 0x0061 #LATIN SMALL LETTER A
0x82 0x0062 #LATIN SMALL LETTER B
0x83 0x0063 #LATIN SMALL LETTER C
0x84 0x0064 #LATIN SMALL LETTER D
0x85 0x0065 #LATIN SMALL LETTER E
0x86 0x0066 #LATIN SMALL LETTER F
0x87 0x0067 #LATIN SMALL LETTER G
0x88 0x0068 #LATIN SMALL LETTER H
0x89 0x0069 #LATIN SMALL LETTER I
0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8C 0x007D #RIGHT CURLY BRACKET
0x8D 0x0060 #GRAVE ACCENT
0x8E 0x00A6 #BROKEN BAR
0x8F 0x00B1 #PLUS-MINUS SIGN
0x90 0x00B0 #DEGREE SIGN
0x91 0x006A #LATIN SMALL LETTER J
0x92 0x006B #LATIN SMALL LETTER K
0x93 0x006C #LATIN SMALL LETTER L
0x94 0x006D #LATIN SMALL LETTER M
0x95 0x006E #LATIN SMALL LETTER N
0x96 0x006F #LATIN SMALL LETTER O
0x97 0x0070 #LATIN SMALL LETTER P
0x98 0x0071 #LATIN SMALL LETTER Q
0x99 0x0072 #LATIN SMALL LETTER R
0x9A 0x00AA #FEMININE ORDINAL INDICATOR
0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
0x9C 0x00E6 #LATIN SMALL LIGATURE AE
0x9D 0x00B8 #CEDILLA
0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
0x9F 0x00A4 #CURRENCY SIGN
0xA0 0x00B5 #MICRO SIGN
0xA1 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xA2 0x0073 #LATIN SMALL LETTER S
0xA3 0x0074 #LATIN SMALL LETTER T
0xA4 0x0075 #LATIN SMALL LETTER U
0xA5 0x0076 #LATIN SMALL LETTER V
0xA6 0x0077 #LATIN SMALL LETTER W
0xA7 0x0078 #LATIN SMALL LETTER X
0xA8 0x0079 #LATIN SMALL LETTER Y
0xA9 0x007A #LATIN SMALL LETTER Z
0xAA 0x00A1 #INVERTED EXCLAMATION MARK
0xAB 0x00BF #INVERTED QUESTION MARK
0xAC 0x005D #RIGHT SQUARE BRACKET
0xAD 0x0024 #DOLLAR SIGN
0xAE 0x0040 #COMMERCIAL AT
0xAF 0x00AE #REGISTERED SIGN
0xB0 0x00A2 #CENT SIGN
0xB1 0x00A3 #POUND SIGN
0xB2 0x00A5 #YEN SIGN
0xB3 0x00B7 #MIDDLE DOT
0xB4 0x00A9 #COPYRIGHT SIGN
0xB5 0x00A7 #SECTION SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
0xB8 0x00BD #VULGAR FRACTION ONE HALF
0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBA 0x00AC #NOT SIGN
0xBB 0x007C #VERTICAL LINE
0xBC 0x00AF #MACRON
0xBD 0x00A8 #DIAERESIS
0xBE 0x00B4 #ACUTE ACCENT
0xBF 0x00D7 #MULTIPLICATION SIGN
0xC0 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xC1 0x0041 #LATIN CAPITAL LETTER A
0xC2 0x0042 #LATIN CAPITAL LETTER B
0xC3 0x0043 #LATIN CAPITAL LETTER C
0xC4 0x0044 #LATIN CAPITAL LETTER D
0xC5 0x0045 #LATIN CAPITAL LETTER E
0xC6 0x0046 #LATIN CAPITAL LETTER F
0xC7 0x0047 #LATIN CAPITAL LETTER G
0xC8 0x0048 #LATIN CAPITAL LETTER H
0xC9 0x0049 #LATIN CAPITAL LETTER I
0xCA 0x00AD #SOFT HYPHEN
0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xCC 0x007E #TILDE
0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0xD0 0x011F #LATIN SMALL LETTER G WITH BREVE
0xD1 0x004A #LATIN CAPITAL LETTER J
0xD2 0x004B #LATIN CAPITAL LETTER K
0xD3 0x004C #LATIN CAPITAL LETTER L
0xD4 0x004D #LATIN CAPITAL LETTER M
0xD5 0x004E #LATIN CAPITAL LETTER N
0xD6 0x004F #LATIN CAPITAL LETTER O
0xD7 0x0050 #LATIN CAPITAL LETTER P
0xD8 0x0051 #LATIN CAPITAL LETTER Q
0xD9 0x0052 #LATIN CAPITAL LETTER R
0xDA 0x00B9 #SUPERSCRIPT ONE
0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xDC 0x005C #REVERSE SOLIDUS
0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xE0 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xE1 0x00F7 #DIVISION SIGN
0xE2 0x0053 #LATIN CAPITAL LETTER S
0xE3 0x0054 #LATIN CAPITAL LETTER T
0xE4 0x0055 #LATIN CAPITAL LETTER U
0xE5 0x0056 #LATIN CAPITAL LETTER V
0xE6 0x0057 #LATIN CAPITAL LETTER W
0xE7 0x0058 #LATIN CAPITAL LETTER X
0xE8 0x0059 #LATIN CAPITAL LETTER Y
0xE9 0x005A #LATIN CAPITAL LETTER Z
0xEA 0x00B2 #SUPERSCRIPT TWO
0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xEC 0x0023 #NUMBER SIGN
0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xF0 0x0030 #DIGIT ZERO
0xF1 0x0031 #DIGIT ONE
0xF2 0x0032 #DIGIT TWO
0xF3 0x0033 #DIGIT THREE
0xF4 0x0034 #DIGIT FOUR
0xF5 0x0035 #DIGIT FIVE
0xF6 0x0036 #DIGIT SIX
0xF7 0x0037 #DIGIT SEVEN
0xF8 0x0038 #DIGIT EIGHT
0xF9 0x0039 #DIGIT NINE
0xFA 0x00B3 #SUPERSCRIPT THREE
0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xFC 0x0022 #QUOTATION MARK
0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xFF 0x009F #CONTROL


275
unicode/vendors/micsft/ebcdic/cp500.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp500_IBMInternational to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp500_IBMInternational code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp500_IBMInternational order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x009C #CONTROL
0x05 0x0009 #HORIZONTAL TABULATION
0x06 0x0086 #CONTROL
0x07 0x007F #DELETE
0x08 0x0097 #CONTROL
0x09 0x008D #CONTROL
0x0A 0x008E #CONTROL
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x009D #CONTROL
0x15 0x0085 #CONTROL
0x16 0x0008 #BACKSPACE
0x17 0x0087 #CONTROL
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x0092 #CONTROL
0x1B 0x008F #CONTROL
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0080 #CONTROL
0x21 0x0081 #CONTROL
0x22 0x0082 #CONTROL
0x23 0x0083 #CONTROL
0x24 0x0084 #CONTROL
0x25 0x000A #LINE FEED
0x26 0x0017 #END OF TRANSMISSION BLOCK
0x27 0x001B #ESCAPE
0x28 0x0088 #CONTROL
0x29 0x0089 #CONTROL
0x2A 0x008A #CONTROL
0x2B 0x008B #CONTROL
0x2C 0x008C #CONTROL
0x2D 0x0005 #ENQUIRY
0x2E 0x0006 #ACKNOWLEDGE
0x2F 0x0007 #BELL
0x30 0x0090 #CONTROL
0x31 0x0091 #CONTROL
0x32 0x0016 #SYNCHRONOUS IDLE
0x33 0x0093 #CONTROL
0x34 0x0094 #CONTROL
0x35 0x0095 #CONTROL
0x36 0x0096 #CONTROL
0x37 0x0004 #END OF TRANSMISSION
0x38 0x0098 #CONTROL
0x39 0x0099 #CONTROL
0x3A 0x009A #CONTROL
0x3B 0x009B #CONTROL
0x3C 0x0014 #DEVICE CONTROL FOUR
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
0x3E 0x009E #CONTROL
0x3F 0x001A #SUBSTITUTE
0x40 0x0020 #SPACE
0x41 0x00A0 #NO-BREAK SPACE
0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x4A 0x005B #LEFT SQUARE BRACKET
0x4B 0x002E #FULL STOP
0x4C 0x003C #LESS-THAN SIGN
0x4D 0x0028 #LEFT PARENTHESIS
0x4E 0x002B #PLUS SIGN
0x4F 0x0021 #EXCLAMATION MARK
0x50 0x0026 #AMPERSAND
0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
0x5A 0x005D #RIGHT SQUARE BRACKET
0x5B 0x0024 #DOLLAR SIGN
0x5C 0x002A #ASTERISK
0x5D 0x0029 #RIGHT PARENTHESIS
0x5E 0x003B #SEMICOLON
0x5F 0x005E #CIRCUMFLEX ACCENT
0x60 0x002D #HYPHEN-MINUS
0x61 0x002F #SOLIDUS
0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x6A 0x00A6 #BROKEN BAR
0x6B 0x002C #COMMA
0x6C 0x0025 #PERCENT SIGN
0x6D 0x005F #LOW LINE
0x6E 0x003E #GREATER-THAN SIGN
0x6F 0x003F #QUESTION MARK
0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0x79 0x0060 #GRAVE ACCENT
0x7A 0x003A #COLON
0x7B 0x0023 #NUMBER SIGN
0x7C 0x0040 #COMMERCIAL AT
0x7D 0x0027 #APOSTROPHE
0x7E 0x003D #EQUALS SIGN
0x7F 0x0022 #QUOTATION MARK
0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0x81 0x0061 #LATIN SMALL LETTER A
0x82 0x0062 #LATIN SMALL LETTER B
0x83 0x0063 #LATIN SMALL LETTER C
0x84 0x0064 #LATIN SMALL LETTER D
0x85 0x0065 #LATIN SMALL LETTER E
0x86 0x0066 #LATIN SMALL LETTER F
0x87 0x0067 #LATIN SMALL LETTER G
0x88 0x0068 #LATIN SMALL LETTER H
0x89 0x0069 #LATIN SMALL LETTER I
0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x8C 0x00F0 #LATIN SMALL LETTER ETH (ICELANDIC)
0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0x8E 0x00FE #LATIN SMALL LETTER THORN (ICELANDIC)
0x8F 0x00B1 #PLUS-MINUS SIGN
0x90 0x00B0 #DEGREE SIGN
0x91 0x006A #LATIN SMALL LETTER J
0x92 0x006B #LATIN SMALL LETTER K
0x93 0x006C #LATIN SMALL LETTER L
0x94 0x006D #LATIN SMALL LETTER M
0x95 0x006E #LATIN SMALL LETTER N
0x96 0x006F #LATIN SMALL LETTER O
0x97 0x0070 #LATIN SMALL LETTER P
0x98 0x0071 #LATIN SMALL LETTER Q
0x99 0x0072 #LATIN SMALL LETTER R
0x9A 0x00AA #FEMININE ORDINAL INDICATOR
0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
0x9C 0x00E6 #LATIN SMALL LIGATURE AE
0x9D 0x00B8 #CEDILLA
0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
0x9F 0x00A4 #CURRENCY SIGN
0xA0 0x00B5 #MICRO SIGN
0xA1 0x007E #TILDE
0xA2 0x0073 #LATIN SMALL LETTER S
0xA3 0x0074 #LATIN SMALL LETTER T
0xA4 0x0075 #LATIN SMALL LETTER U
0xA5 0x0076 #LATIN SMALL LETTER V
0xA6 0x0077 #LATIN SMALL LETTER W
0xA7 0x0078 #LATIN SMALL LETTER X
0xA8 0x0079 #LATIN SMALL LETTER Y
0xA9 0x007A #LATIN SMALL LETTER Z
0xAA 0x00A1 #INVERTED EXCLAMATION MARK
0xAB 0x00BF #INVERTED QUESTION MARK
0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (ICELANDIC)
0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xAE 0x00DE #LATIN CAPITAL LETTER THORN (ICELANDIC)
0xAF 0x00AE #REGISTERED SIGN
0xB0 0x00A2 #CENT SIGN
0xB1 0x00A3 #POUND SIGN
0xB2 0x00A5 #YEN SIGN
0xB3 0x00B7 #MIDDLE DOT
0xB4 0x00A9 #COPYRIGHT SIGN
0xB5 0x00A7 #SECTION SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
0xB8 0x00BD #VULGAR FRACTION ONE HALF
0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBA 0x00AC #NOT SIGN
0xBB 0x007C #VERTICAL LINE
0xBC 0x00AF #MACRON
0xBD 0x00A8 #DIAERESIS
0xBE 0x00B4 #ACUTE ACCENT
0xBF 0x00D7 #MULTIPLICATION SIGN
0xC0 0x007B #LEFT CURLY BRACKET
0xC1 0x0041 #LATIN CAPITAL LETTER A
0xC2 0x0042 #LATIN CAPITAL LETTER B
0xC3 0x0043 #LATIN CAPITAL LETTER C
0xC4 0x0044 #LATIN CAPITAL LETTER D
0xC5 0x0045 #LATIN CAPITAL LETTER E
0xC6 0x0046 #LATIN CAPITAL LETTER F
0xC7 0x0047 #LATIN CAPITAL LETTER G
0xC8 0x0048 #LATIN CAPITAL LETTER H
0xC9 0x0049 #LATIN CAPITAL LETTER I
0xCA 0x00AD #SOFT HYPHEN
0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xCC 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0xD0 0x007D #RIGHT CURLY BRACKET
0xD1 0x004A #LATIN CAPITAL LETTER J
0xD2 0x004B #LATIN CAPITAL LETTER K
0xD3 0x004C #LATIN CAPITAL LETTER L
0xD4 0x004D #LATIN CAPITAL LETTER M
0xD5 0x004E #LATIN CAPITAL LETTER N
0xD6 0x004F #LATIN CAPITAL LETTER O
0xD7 0x0050 #LATIN CAPITAL LETTER P
0xD8 0x0051 #LATIN CAPITAL LETTER Q
0xD9 0x0052 #LATIN CAPITAL LETTER R
0xDA 0x00B9 #SUPERSCRIPT ONE
0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xDC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xE0 0x005C #REVERSE SOLIDUS
0xE1 0x00F7 #DIVISION SIGN
0xE2 0x0053 #LATIN CAPITAL LETTER S
0xE3 0x0054 #LATIN CAPITAL LETTER T
0xE4 0x0055 #LATIN CAPITAL LETTER U
0xE5 0x0056 #LATIN CAPITAL LETTER V
0xE6 0x0057 #LATIN CAPITAL LETTER W
0xE7 0x0058 #LATIN CAPITAL LETTER X
0xE8 0x0059 #LATIN CAPITAL LETTER Y
0xE9 0x005A #LATIN CAPITAL LETTER Z
0xEA 0x00B2 #SUPERSCRIPT TWO
0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xEC 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xF0 0x0030 #DIGIT ZERO
0xF1 0x0031 #DIGIT ONE
0xF2 0x0032 #DIGIT TWO
0xF3 0x0033 #DIGIT THREE
0xF4 0x0034 #DIGIT FOUR
0xF5 0x0035 #DIGIT FIVE
0xF6 0x0036 #DIGIT SIX
0xF7 0x0037 #DIGIT SEVEN
0xF8 0x0038 #DIGIT EIGHT
0xF9 0x0039 #DIGIT NINE
0xFA 0x00B3 #SUPERSCRIPT THREE
0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xFC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xFF 0x009F #CONTROL


275
unicode/vendors/micsft/ebcdic/cp875.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp875_IBMGreek to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp875_IBMGreek code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp875_IBMGreek order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x009C #CONTROL
0x05 0x0009 #HORIZONTAL TABULATION
0x06 0x0086 #CONTROL
0x07 0x007F #DELETE
0x08 0x0097 #CONTROL
0x09 0x008D #CONTROL
0x0A 0x008E #CONTROL
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x009D #CONTROL
0x15 0x0085 #CONTROL
0x16 0x0008 #BACKSPACE
0x17 0x0087 #CONTROL
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x0092 #CONTROL
0x1B 0x008F #CONTROL
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0080 #CONTROL
0x21 0x0081 #CONTROL
0x22 0x0082 #CONTROL
0x23 0x0083 #CONTROL
0x24 0x0084 #CONTROL
0x25 0x000A #LINE FEED
0x26 0x0017 #END OF TRANSMISSION BLOCK
0x27 0x001B #ESCAPE
0x28 0x0088 #CONTROL
0x29 0x0089 #CONTROL
0x2A 0x008A #CONTROL
0x2B 0x008B #CONTROL
0x2C 0x008C #CONTROL
0x2D 0x0005 #ENQUIRY
0x2E 0x0006 #ACKNOWLEDGE
0x2F 0x0007 #BELL
0x30 0x0090 #CONTROL
0x31 0x0091 #CONTROL
0x32 0x0016 #SYNCHRONOUS IDLE
0x33 0x0093 #CONTROL
0x34 0x0094 #CONTROL
0x35 0x0095 #CONTROL
0x36 0x0096 #CONTROL
0x37 0x0004 #END OF TRANSMISSION
0x38 0x0098 #CONTROL
0x39 0x0099 #CONTROL
0x3A 0x009A #CONTROL
0x3B 0x009B #CONTROL
0x3C 0x0014 #DEVICE CONTROL FOUR
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
0x3E 0x009E #CONTROL
0x3F 0x001A #SUBSTITUTE
0x40 0x0020 #SPACE
0x41 0x0391 #GREEK CAPITAL LETTER ALPHA
0x42 0x0392 #GREEK CAPITAL LETTER BETA
0x43 0x0393 #GREEK CAPITAL LETTER GAMMA
0x44 0x0394 #GREEK CAPITAL LETTER DELTA
0x45 0x0395 #GREEK CAPITAL LETTER EPSILON
0x46 0x0396 #GREEK CAPITAL LETTER ZETA
0x47 0x0397 #GREEK CAPITAL LETTER ETA
0x48 0x0398 #GREEK CAPITAL LETTER THETA
0x49 0x0399 #GREEK CAPITAL LETTER IOTA
0x4A 0x005B #LEFT SQUARE BRACKET
0x4B 0x002E #FULL STOP
0x4C 0x003C #LESS-THAN SIGN
0x4D 0x0028 #LEFT PARENTHESIS
0x4E 0x002B #PLUS SIGN
0x4F 0x0021 #EXCLAMATION MARK
0x50 0x0026 #AMPERSAND
0x51 0x039A #GREEK CAPITAL LETTER KAPPA
0x52 0x039B #GREEK CAPITAL LETTER LAMDA
0x53 0x039C #GREEK CAPITAL LETTER MU
0x54 0x039D #GREEK CAPITAL LETTER NU
0x55 0x039E #GREEK CAPITAL LETTER XI
0x56 0x039F #GREEK CAPITAL LETTER OMICRON
0x57 0x03A0 #GREEK CAPITAL LETTER PI
0x58 0x03A1 #GREEK CAPITAL LETTER RHO
0x59 0x03A3 #GREEK CAPITAL LETTER SIGMA
0x5A 0x005D #RIGHT SQUARE BRACKET
0x5B 0x0024 #DOLLAR SIGN
0x5C 0x002A #ASTERISK
0x5D 0x0029 #RIGHT PARENTHESIS
0x5E 0x003B #SEMICOLON
0x5F 0x005E #CIRCUMFLEX ACCENT
0x60 0x002D #HYPHEN-MINUS
0x61 0x002F #SOLIDUS
0x62 0x03A4 #GREEK CAPITAL LETTER TAU
0x63 0x03A5 #GREEK CAPITAL LETTER UPSILON
0x64 0x03A6 #GREEK CAPITAL LETTER PHI
0x65 0x03A7 #GREEK CAPITAL LETTER CHI
0x66 0x03A8 #GREEK CAPITAL LETTER PSI
0x67 0x03A9 #GREEK CAPITAL LETTER OMEGA
0x68 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0x69 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0x6A 0x007C #VERTICAL LINE
0x6B 0x002C #COMMA
0x6C 0x0025 #PERCENT SIGN
0x6D 0x005F #LOW LINE
0x6E 0x003E #GREATER-THAN SIGN
0x6F 0x003F #QUESTION MARK
0x70 0x00A8 #DIAERESIS
0x71 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
0x72 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
0x73 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
0x74 0x00A0 #NO-BREAK SPACE
0x75 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS
0x76 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS
0x77 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS
0x78 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS
0x79 0x0060 #GRAVE ACCENT
0x7A 0x003A #COLON
0x7B 0x0023 #NUMBER SIGN
0x7C 0x0040 #COMMERCIAL AT
0x7D 0x0027 #APOSTROPHE
0x7E 0x003D #EQUALS SIGN
0x7F 0x0022 #QUOTATION MARK
0x80 0x0385 #GREEK DIALYTIKA TONOS
0x81 0x0061 #LATIN SMALL LETTER A
0x82 0x0062 #LATIN SMALL LETTER B
0x83 0x0063 #LATIN SMALL LETTER C
0x84 0x0064 #LATIN SMALL LETTER D
0x85 0x0065 #LATIN SMALL LETTER E
0x86 0x0066 #LATIN SMALL LETTER F
0x87 0x0067 #LATIN SMALL LETTER G
0x88 0x0068 #LATIN SMALL LETTER H
0x89 0x0069 #LATIN SMALL LETTER I
0x8A 0x03B1 #GREEK SMALL LETTER ALPHA
0x8B 0x03B2 #GREEK SMALL LETTER BETA
0x8C 0x03B3 #GREEK SMALL LETTER GAMMA
0x8D 0x03B4 #GREEK SMALL LETTER DELTA
0x8E 0x03B5 #GREEK SMALL LETTER EPSILON
0x8F 0x03B6 #GREEK SMALL LETTER ZETA
0x90 0x00B0 #DEGREE SIGN
0x91 0x006A #LATIN SMALL LETTER J
0x92 0x006B #LATIN SMALL LETTER K
0x93 0x006C #LATIN SMALL LETTER L
0x94 0x006D #LATIN SMALL LETTER M
0x95 0x006E #LATIN SMALL LETTER N
0x96 0x006F #LATIN SMALL LETTER O
0x97 0x0070 #LATIN SMALL LETTER P
0x98 0x0071 #LATIN SMALL LETTER Q
0x99 0x0072 #LATIN SMALL LETTER R
0x9A 0x03B7 #GREEK SMALL LETTER ETA
0x9B 0x03B8 #GREEK SMALL LETTER THETA
0x9C 0x03B9 #GREEK SMALL LETTER IOTA
0x9D 0x03BA #GREEK SMALL LETTER KAPPA
0x9E 0x03BB #GREEK SMALL LETTER LAMDA
0x9F 0x03BC #GREEK SMALL LETTER MU
0xA0 0x00B4 #ACUTE ACCENT
0xA1 0x007E #TILDE
0xA2 0x0073 #LATIN SMALL LETTER S
0xA3 0x0074 #LATIN SMALL LETTER T
0xA4 0x0075 #LATIN SMALL LETTER U
0xA5 0x0076 #LATIN SMALL LETTER V
0xA6 0x0077 #LATIN SMALL LETTER W
0xA7 0x0078 #LATIN SMALL LETTER X
0xA8 0x0079 #LATIN SMALL LETTER Y
0xA9 0x007A #LATIN SMALL LETTER Z
0xAA 0x03BD #GREEK SMALL LETTER NU
0xAB 0x03BE #GREEK SMALL LETTER XI
0xAC 0x03BF #GREEK SMALL LETTER OMICRON
0xAD 0x03C0 #GREEK SMALL LETTER PI
0xAE 0x03C1 #GREEK SMALL LETTER RHO
0xAF 0x03C3 #GREEK SMALL LETTER SIGMA
0xB0 0x00A3 #POUND SIGN
0xB1 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS
0xB2 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS
0xB3 0x03AE #GREEK SMALL LETTER ETA WITH TONOS
0xB4 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xB5 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS
0xB6 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS
0xB7 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS
0xB8 0x03CB #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xB9 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS
0xBA 0x03C2 #GREEK SMALL LETTER FINAL SIGMA
0xBB 0x03C4 #GREEK SMALL LETTER TAU
0xBC 0x03C5 #GREEK SMALL LETTER UPSILON
0xBD 0x03C6 #GREEK SMALL LETTER PHI
0xBE 0x03C7 #GREEK SMALL LETTER CHI
0xBF 0x03C8 #GREEK SMALL LETTER PSI
0xC0 0x007B #LEFT CURLY BRACKET
0xC1 0x0041 #LATIN CAPITAL LETTER A
0xC2 0x0042 #LATIN CAPITAL LETTER B
0xC3 0x0043 #LATIN CAPITAL LETTER C
0xC4 0x0044 #LATIN CAPITAL LETTER D
0xC5 0x0045 #LATIN CAPITAL LETTER E
0xC6 0x0046 #LATIN CAPITAL LETTER F
0xC7 0x0047 #LATIN CAPITAL LETTER G
0xC8 0x0048 #LATIN CAPITAL LETTER H
0xC9 0x0049 #LATIN CAPITAL LETTER I
0xCA 0x00AD #SOFT HYPHEN
0xCB 0x03C9 #GREEK SMALL LETTER OMEGA
0xCC 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xCD 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xCE 0x2018 #LEFT SINGLE QUOTATION MARK
0xCF 0x2015 #HORIZONTAL BAR
0xD0 0x007D #RIGHT CURLY BRACKET
0xD1 0x004A #LATIN CAPITAL LETTER J
0xD2 0x004B #LATIN CAPITAL LETTER K
0xD3 0x004C #LATIN CAPITAL LETTER L
0xD4 0x004D #LATIN CAPITAL LETTER M
0xD5 0x004E #LATIN CAPITAL LETTER N
0xD6 0x004F #LATIN CAPITAL LETTER O
0xD7 0x0050 #LATIN CAPITAL LETTER P
0xD8 0x0051 #LATIN CAPITAL LETTER Q
0xD9 0x0052 #LATIN CAPITAL LETTER R
0xDA 0x00B1 #PLUS-MINUS SIGN
0xDB 0x00BD #VULGAR FRACTION ONE HALF
0xDC 0x001A #SUBSTITUTE
0xDD 0x0387 #GREEK ANO TELEIA
0xDE 0x2019 #RIGHT SINGLE QUOTATION MARK
0xDF 0x00A6 #BROKEN BAR
0xE0 0x005C #REVERSE SOLIDUS
0xE1 0x001A #SUBSTITUTE
0xE2 0x0053 #LATIN CAPITAL LETTER S
0xE3 0x0054 #LATIN CAPITAL LETTER T
0xE4 0x0055 #LATIN CAPITAL LETTER U
0xE5 0x0056 #LATIN CAPITAL LETTER V
0xE6 0x0057 #LATIN CAPITAL LETTER W
0xE7 0x0058 #LATIN CAPITAL LETTER X
0xE8 0x0059 #LATIN CAPITAL LETTER Y
0xE9 0x005A #LATIN CAPITAL LETTER Z
0xEA 0x00B2 #SUPERSCRIPT TWO
0xEB 0x00A7 #SECTION SIGN
0xEC 0x001A #SUBSTITUTE
0xED 0x001A #SUBSTITUTE
0xEE 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xEF 0x00AC #NOT SIGN
0xF0 0x0030 #DIGIT ZERO
0xF1 0x0031 #DIGIT ONE
0xF2 0x0032 #DIGIT TWO
0xF3 0x0033 #DIGIT THREE
0xF4 0x0034 #DIGIT FOUR
0xF5 0x0035 #DIGIT FIVE
0xF6 0x0036 #DIGIT SIX
0xF7 0x0037 #DIGIT SEVEN
0xF8 0x0038 #DIGIT EIGHT
0xF9 0x0039 #DIGIT NINE
0xFA 0x00B3 #SUPERSCRIPT THREE
0xFB 0x00A9 #COPYRIGHT SIGN
0xFC 0x001A #SUBSTITUTE
0xFD 0x001A #SUBSTITUTE
0xFE 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xFF 0x009F #CONTROL


275
unicode/vendors/micsft/mac/cyrillic.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10007_MacCyrillic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10007_MacCyrillic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10007_MacCyrillic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x0410 #CYRILLIC CAPITAL LETTER A
0x81 0x0411 #CYRILLIC CAPITAL LETTER BE
0x82 0x0412 #CYRILLIC CAPITAL LETTER VE
0x83 0x0413 #CYRILLIC CAPITAL LETTER GHE
0x84 0x0414 #CYRILLIC CAPITAL LETTER DE
0x85 0x0415 #CYRILLIC CAPITAL LETTER IE
0x86 0x0416 #CYRILLIC CAPITAL LETTER ZHE
0x87 0x0417 #CYRILLIC CAPITAL LETTER ZE
0x88 0x0418 #CYRILLIC CAPITAL LETTER I
0x89 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
0x8A 0x041A #CYRILLIC CAPITAL LETTER KA
0x8B 0x041B #CYRILLIC CAPITAL LETTER EL
0x8C 0x041C #CYRILLIC CAPITAL LETTER EM
0x8D 0x041D #CYRILLIC CAPITAL LETTER EN
0x8E 0x041E #CYRILLIC CAPITAL LETTER O
0x8F 0x041F #CYRILLIC CAPITAL LETTER PE
0x90 0x0420 #CYRILLIC CAPITAL LETTER ER
0x91 0x0421 #CYRILLIC CAPITAL LETTER ES
0x92 0x0422 #CYRILLIC CAPITAL LETTER TE
0x93 0x0423 #CYRILLIC CAPITAL LETTER U
0x94 0x0424 #CYRILLIC CAPITAL LETTER EF
0x95 0x0425 #CYRILLIC CAPITAL LETTER HA
0x96 0x0426 #CYRILLIC CAPITAL LETTER TSE
0x97 0x0427 #CYRILLIC CAPITAL LETTER CHE
0x98 0x0428 #CYRILLIC CAPITAL LETTER SHA
0x99 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
0x9A 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN
0x9B 0x042B #CYRILLIC CAPITAL LETTER YERU
0x9C 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN
0x9D 0x042D #CYRILLIC CAPITAL LETTER E
0x9E 0x042E #CYRILLIC CAPITAL LETTER YU
0x9F 0x042F #CYRILLIC CAPITAL LETTER YA
0xA0 0x2020 #DAGGER
0xA1 0x00B0 #DEGREE SIGN
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A7 #SECTION SIGN
0xA5 0x2022 #BULLET
0xA6 0x00B6 #PILCROW SIGN
0xA7 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x2122 #TRADE MARK SIGN
0xAB 0x0402 #CYRILLIC CAPITAL LETTER DJE
0xAC 0x0452 #CYRILLIC SMALL LETTER DJE
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x0403 #CYRILLIC CAPITAL LETTER GJE
0xAF 0x0453 #CYRILLIC SMALL LETTER GJE
0xB0 0x221E #INFINITY
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0xB5 0x00B5 #MICRO SIGN
0xB6 0x2202 #PARTIAL DIFFERENTIAL
0xB7 0x0408 #CYRILLIC CAPITAL LETTER JE
0xB8 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xB9 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
0xBA 0x0407 #CYRILLIC CAPITAL LETTER YI
0xBB 0x0457 #CYRILLIC SMALL LETTER YI
0xBC 0x0409 #CYRILLIC CAPITAL LETTER LJE
0xBD 0x0459 #CYRILLIC SMALL LETTER LJE
0xBE 0x040A #CYRILLIC CAPITAL LETTER NJE
0xBF 0x045A #CYRILLIC SMALL LETTER NJE
0xC0 0x0458 #CYRILLIC SMALL LETTER JE
0xC1 0x0405 #CYRILLIC CAPITAL LETTER DZE
0xC2 0x00AC #NOT SIGN
0xC3 0x221A #SQUARE ROOT
0xC4 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 #ALMOST EQUAL TO
0xC6 0x2206 #INCREMENT
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x040B #CYRILLIC CAPITAL LETTER TSHE
0xCC 0x045B #CYRILLIC SMALL LETTER TSHE
0xCD 0x040C #CYRILLIC CAPITAL LETTER KJE
0xCE 0x045C #CYRILLIC SMALL LETTER KJE
0xCF 0x0455 #CYRILLIC SMALL LETTER DZE
0xD0 0x2013 #EN DASH
0xD1 0x2014 #EM DASH
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x201E #DOUBLE LOW-9 QUOTATION MARK
0xD8 0x040E #CYRILLIC CAPITAL LETTER SHORT U
0xD9 0x045E #CYRILLIC SMALL LETTER SHORT U
0xDA 0x040F #CYRILLIC CAPITAL LETTER DZHE
0xDB 0x045F #CYRILLIC SMALL LETTER DZHE
0xDC 0x2116 #NUMERO SIGN
0xDD 0x0401 #CYRILLIC CAPITAL LETTER IO
0xDE 0x0451 #CYRILLIC SMALL LETTER IO
0xDF 0x044F #CYRILLIC SMALL LETTER YA
0xE0 0x0430 #CYRILLIC SMALL LETTER A
0xE1 0x0431 #CYRILLIC SMALL LETTER BE
0xE2 0x0432 #CYRILLIC SMALL LETTER VE
0xE3 0x0433 #CYRILLIC SMALL LETTER GHE
0xE4 0x0434 #CYRILLIC SMALL LETTER DE
0xE5 0x0435 #CYRILLIC SMALL LETTER IE
0xE6 0x0436 #CYRILLIC SMALL LETTER ZHE
0xE7 0x0437 #CYRILLIC SMALL LETTER ZE
0xE8 0x0438 #CYRILLIC SMALL LETTER I
0xE9 0x0439 #CYRILLIC SMALL LETTER SHORT I
0xEA 0x043A #CYRILLIC SMALL LETTER KA
0xEB 0x043B #CYRILLIC SMALL LETTER EL
0xEC 0x043C #CYRILLIC SMALL LETTER EM
0xED 0x043D #CYRILLIC SMALL LETTER EN
0xEE 0x043E #CYRILLIC SMALL LETTER O
0xEF 0x043F #CYRILLIC SMALL LETTER PE
0xF0 0x0440 #CYRILLIC SMALL LETTER ER
0xF1 0x0441 #CYRILLIC SMALL LETTER ES
0xF2 0x0442 #CYRILLIC SMALL LETTER TE
0xF3 0x0443 #CYRILLIC SMALL LETTER U
0xF4 0x0444 #CYRILLIC SMALL LETTER EF
0xF5 0x0445 #CYRILLIC SMALL LETTER HA
0xF6 0x0446 #CYRILLIC SMALL LETTER TSE
0xF7 0x0447 #CYRILLIC SMALL LETTER CHE
0xF8 0x0448 #CYRILLIC SMALL LETTER SHA
0xF9 0x0449 #CYRILLIC SMALL LETTER SHCHA
0xFA 0x044A #CYRILLIC SMALL LETTER HARD SIGN
0xFB 0x044B #CYRILLIC SMALL LETTER YERU
0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN
0xFD 0x044D #CYRILLIC SMALL LETTER E
0xFE 0x044E #CYRILLIC SMALL LETTER YU
0xFF 0x00A4 #CURRENCY SIGN


275
unicode/vendors/micsft/mac/greek.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10006_MacGreek to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10006_MacGreek code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10006_MacGreek order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00B9 #SUPERSCRIPT ONE
0x82 0x00B2 #SUPERSCRIPT TWO
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00B3 #SUPERSCRIPT THREE
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x0385 #GREEK DIALYTIKA TONOS
0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x0384 #GREEK TONOS
0x8C 0x00A8 #DIAERESIS
0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00A3 #POUND SIGN
0x93 0x2122 #TRADE MARK SIGN
0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x2022 #BULLET
0x97 0x00BD #VULGAR FRACTION ONE HALF
0x98 0x2030 #PER MILLE SIGN
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00A6 #BROKEN BAR
0x9C 0x00AD #SOFT HYPHEN
0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 #DAGGER
0xA1 0x0393 #GREEK CAPITAL LETTER GAMMA
0xA2 0x0394 #GREEK CAPITAL LETTER DELTA
0xA3 0x0398 #GREEK CAPITAL LETTER THETA
0xA4 0x039B #GREEK CAPITAL LETTER LAMBDA
0xA5 0x039E #GREEK CAPITAL LETTER XI
0xA6 0x03A0 #GREEK CAPITAL LETTER PI
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x03A3 #GREEK CAPITAL LETTER SIGMA
0xAB 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0xAC 0x00A7 #SECTION SIGN
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x00B0 #DEGREE SIGN
0xAF 0x0387 #GREEK ANO TELEIA
0xB0 0x0391 #GREEK CAPITAL LETTER ALPHA
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x00A5 #YEN SIGN
0xB5 0x0392 #GREEK CAPITAL LETTER BETA
0xB6 0x0395 #GREEK CAPITAL LETTER EPSILON
0xB7 0x0396 #GREEK CAPITAL LETTER ZETA
0xB8 0x0397 #GREEK CAPITAL LETTER ETA
0xB9 0x0399 #GREEK CAPITAL LETTER IOTA
0xBA 0x039A #GREEK CAPITAL LETTER KAPPA
0xBB 0x039C #GREEK CAPITAL LETTER MU
0xBC 0x03A6 #GREEK CAPITAL LETTER PHI
0xBD 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0xBE 0x03A8 #GREEK CAPITAL LETTER PSI
0xBF 0x03A9 #GREEK CAPITAL LETTER OMEGA
0xC0 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS
0xC1 0x039D #GREEK CAPITAL LETTER NU
0xC2 0x00AC #NOT SIGN
0xC3 0x039F #GREEK CAPITAL LETTER OMICRON
0xC4 0x03A1 #GREEK CAPITAL LETTER RHO
0xC5 0x2248 #ALMOST EQUAL TO
0xC6 0x03A4 #GREEK CAPITAL LETTER TAU
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x03A5 #GREEK CAPITAL LETTER UPSILON
0xCC 0x03A7 #GREEK CAPITAL LETTER CHI
0xCD 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
0xCE 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
0xCF 0x0153 #LATIN SMALL LIGATURE OE
0xD0 0x2013 #EN DASH
0xD1 0x2015 #HORIZONTAL BAR
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
0xD8 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS
0xD9 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS
0xDA 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS
0xDB 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS
0xDC 0x03AE #GREEK SMALL LETTER ETA WITH TONOS
0xDD 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS
0xDE 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS
0xDF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS
0xE0 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS
0xE1 0x03B1 #GREEK SMALL LETTER ALPHA
0xE2 0x03B2 #GREEK SMALL LETTER BETA
0xE3 0x03C8 #GREEK SMALL LETTER PSI
0xE4 0x03B4 #GREEK SMALL LETTER DELTA
0xE5 0x03B5 #GREEK SMALL LETTER EPSILON
0xE6 0x03C6 #GREEK SMALL LETTER PHI
0xE7 0x03B3 #GREEK SMALL LETTER GAMMA
0xE8 0x03B7 #GREEK SMALL LETTER ETA
0xE9 0x03B9 #GREEK SMALL LETTER IOTA
0xEA 0x03BE #GREEK SMALL LETTER XI
0xEB 0x03BA #GREEK SMALL LETTER KAPPA
0xEC 0x03BB #GREEK SMALL LETTER LAMBDA
0xED 0x03BC #GREEK SMALL LETTER MU
0xEE 0x03BD #GREEK SMALL LETTER NU
0xEF 0x03BF #GREEK SMALL LETTER OMICRON
0xF0 0x03C0 #GREEK SMALL LETTER PI
0xF1 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS
0xF2 0x03C1 #GREEK SMALL LETTER RHO
0xF3 0x03C3 #GREEK SMALL LETTER SIGMA
0xF4 0x03C4 #GREEK SMALL LETTER TAU
0xF5 0x03B8 #GREEK SMALL LETTER THETA
0xF6 0x03C9 #GREEK SMALL LETTER OMEGA
0xF7 0x03C2 #GREEK SMALL LETTER FINAL SIGMA
0xF8 0x03C7 #GREEK SMALL LETTER CHI
0xF9 0x03C5 #GREEK SMALL LETTER UPSILON
0xFA 0x03B6 #GREEK SMALL LETTER ZETA
0xFB 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xFC 0x03CB #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xFD 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xFE 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xFF #UNDEFINED


275
unicode/vendors/micsft/mac/iceland.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10079_MacIcelandic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10079_MacIcelandic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10079_MacIcelandic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xA1 0x00B0 #DEGREE SIGN
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A7 #SECTION SIGN
0xA5 0x2022 #BULLET
0xA6 0x00B6 #PILCROW SIGN
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x2122 #TRADE MARK SIGN
0xAB 0x00B4 #ACUTE ACCENT
0xAC 0x00A8 #DIAERESIS
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x00C6 #LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E #INFINITY
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x00A5 #YEN SIGN
0xB5 0x00B5 #MICRO SIGN
0xB6 0x2202 #PARTIAL DIFFERENTIAL
0xB7 0x2211 #N-ARY SUMMATION
0xB8 0x220F #N-ARY PRODUCT
0xB9 0x03C0 #GREEK SMALL LETTER PI
0xBA 0x222B #INTEGRAL
0xBB 0x00AA #FEMININE ORDINAL INDICATOR
0xBC 0x00BA #MASCULINE ORDINAL INDICATOR
0xBD 0x2126 #OHM SIGN
0xBE 0x00E6 #LATIN SMALL LIGATURE AE
0xBF 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF #INVERTED QUESTION MARK
0xC1 0x00A1 #INVERTED EXCLAMATION MARK
0xC2 0x00AC #NOT SIGN
0xC3 0x221A #SQUARE ROOT
0xC4 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 #ALMOST EQUAL TO
0xC6 0x2206 #INCREMENT
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 #LATIN CAPITAL LIGATURE OE
0xCF 0x0153 #LATIN SMALL LIGATURE OE
0xD0 0x2013 #EN DASH
0xD1 0x2014 #EM DASH
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x25CA #LOZENGE
0xD8 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 #FRACTION SLASH
0xDB 0x00A4 #CURRENCY SIGN
0xDC 0x00D0 #LATIN CAPITAL LETTER ETH
0xDD 0x00F0 #LATIN SMALL LETTER ETH
0xDE 0x00DE #LATIN CAPITAL LETTER THORN
0xDF 0x00FE #LATIN SMALL LETTER THORN
0xE0 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0xE1 0x00B7 #MIDDLE DOT
0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 #PER MILLE SIGN
0xE5 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 #UNDEFINED
0xF1 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 #LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC #SMALL TILDE
0xF8 0x00AF #MACRON
0xF9 0x02D8 #BREVE
0xFA 0x02D9 #DOT ABOVE
0xFB 0x02DA #RING ABOVE
0xFC 0x00B8 #CEDILLA
0xFD 0x02DD #DOUBLE ACUTE ACCENT
0xFE 0x02DB #OGONEK
0xFF 0x02C7 #CARON


275
unicode/vendors/micsft/mac/latin2.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10029_MacLatin2 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10029_MacLatin2 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10029_MacLatin2 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x0100 #LATIN CAPITAL LETTER A WITH MACRON
0x82 0x0101 #LATIN SMALL LETTER A WITH MACRON
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x88 0x0105 #LATIN SMALL LETTER A WITH OGONEK
0x89 0x010C #LATIN CAPITAL LETTER C WITH CARON
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x010D #LATIN SMALL LETTER C WITH CARON
0x8C 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
0x8D 0x0107 #LATIN SMALL LETTER C WITH ACUTE
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
0x90 0x017A #LATIN SMALL LETTER Z WITH ACUTE
0x91 0x010E #LATIN CAPITAL LETTER D WITH CARON
0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x93 0x010F #LATIN SMALL LETTER D WITH CARON
0x94 0x0112 #LATIN CAPITAL LETTER E WITH MACRON
0x95 0x0113 #LATIN SMALL LETTER E WITH MACRON
0x96 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE
0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0x98 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0x9D 0x011A #LATIN CAPITAL LETTER E WITH CARON
0x9E 0x011B #LATIN SMALL LETTER E WITH CARON
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 #DAGGER
0xA1 0x00B0 #DEGREE SIGN
0xA2 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A7 #SECTION SIGN
0xA5 0x2022 #BULLET
0xA6 0x00B6 #PILCROW SIGN
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x2122 #TRADE MARK SIGN
0xAB 0x0119 #LATIN SMALL LETTER E WITH OGONEK
0xAC 0x00A8 #DIAERESIS
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x0123 #LATIN SMALL LETTER G WITH CEDILLA
0xAF 0x012E #LATIN CAPITAL LETTER I WITH OGONEK
0xB0 0x012F #LATIN SMALL LETTER I WITH OGONEK
0xB1 0x012A #LATIN CAPITAL LETTER I WITH MACRON
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x012B #LATIN SMALL LETTER I WITH MACRON
0xB5 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA
0xB6 0x2202 #PARTIAL DIFFERENTIAL
0xB7 0x2211 #N-ARY SUMMATION
0xB8 0x0142 #LATIN SMALL LETTER L WITH STROKE
0xB9 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA
0xBA 0x013C #LATIN SMALL LETTER L WITH CEDILLA
0xBB 0x013D #LATIN CAPITAL LETTER L WITH CARON
0xBC 0x013E #LATIN SMALL LETTER L WITH CARON
0xBD 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
0xBE 0x013A #LATIN SMALL LETTER L WITH ACUTE
0xBF 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA
0xC0 0x0146 #LATIN SMALL LETTER N WITH CEDILLA
0xC1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
0xC2 0x00AC #NOT SIGN
0xC3 0x221A #SQUARE ROOT
0xC4 0x0144 #LATIN SMALL LETTER N WITH ACUTE
0xC5 0x0147 #LATIN CAPITAL LETTER N WITH CARON
0xC6 0x2206 #INCREMENT
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x0148 #LATIN SMALL LETTER N WITH CARON
0xCC 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xCF 0x014C #LATIN CAPITAL LETTER O WITH MACRON
0xD0 0x2013 #EN DASH
0xD1 0x2014 #EM DASH
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x25CA #LOZENGE
0xD8 0x014D #LATIN SMALL LETTER O WITH MACRON
0xD9 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
0xDA 0x0155 #LATIN SMALL LETTER R WITH ACUTE
0xDB 0x0158 #LATIN CAPITAL LETTER R WITH CARON
0xDC 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0x0159 #LATIN SMALL LETTER R WITH CARON
0xDF 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA
0xE0 0x0157 #LATIN SMALL LETTER R WITH CEDILLA
0xE1 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK
0xE4 0x0161 #LATIN SMALL LETTER S WITH CARON
0xE5 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
0xE6 0x015B #LATIN SMALL LETTER S WITH ACUTE
0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x0164 #LATIN CAPITAL LETTER T WITH CARON
0xE9 0x0165 #LATIN SMALL LETTER T WITH CARON
0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x017D #LATIN CAPITAL LETTER Z WITH CARON
0xEC 0x017E #LATIN SMALL LETTER Z WITH CARON
0xED 0x016A #LATIN CAPITAL LETTER U WITH MACRON
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 0x016B #LATIN SMALL LETTER U WITH MACRON
0xF1 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE
0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x016F #LATIN SMALL LETTER U WITH RING ABOVE
0xF4 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xF5 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xF6 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK
0xF7 0x0173 #LATIN SMALL LETTER U WITH OGONEK
0xF8 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xF9 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0xFA 0x0137 #LATIN SMALL LETTER K WITH CEDILLA
0xFB 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xFC 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
0xFE 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA
0xFF 0x02C7 #CARON


275
unicode/vendors/micsft/mac/roman.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10000_MacRoman to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10000_MacRoman code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10000_MacRoman order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 #DAGGER
0xA1 0x00B0 #DEGREE SIGN
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A7 #SECTION SIGN
0xA5 0x2022 #BULLET
0xA6 0x00B6 #PILCROW SIGN
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x2122 #TRADE MARK SIGN
0xAB 0x00B4 #ACUTE ACCENT
0xAC 0x00A8 #DIAERESIS
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x00C6 #LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E #INFINITY
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x00A5 #YEN SIGN
0xB5 0x00B5 #MICRO SIGN
0xB6 0x2202 #PARTIAL DIFFERENTIAL
0xB7 0x2211 #N-ARY SUMMATION
0xB8 0x220F #N-ARY PRODUCT
0xB9 0x03C0 #GREEK SMALL LETTER PI
0xBA 0x222B #INTEGRAL
0xBB 0x00AA #FEMININE ORDINAL INDICATOR
0xBC 0x00BA #MASCULINE ORDINAL INDICATOR
0xBD 0x2126 #OHM SIGN
0xBE 0x00E6 #LATIN SMALL LIGATURE AE
0xBF 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF #INVERTED QUESTION MARK
0xC1 0x00A1 #INVERTED EXCLAMATION MARK
0xC2 0x00AC #NOT SIGN
0xC3 0x221A #SQUARE ROOT
0xC4 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 #ALMOST EQUAL TO
0xC6 0x2206 #INCREMENT
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 #LATIN CAPITAL LIGATURE OE
0xCF 0x0153 #LATIN SMALL LIGATURE OE
0xD0 0x2013 #EN DASH
0xD1 0x2014 #EM DASH
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x25CA #LOZENGE
0xD8 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 #FRACTION SLASH
0xDB 0x00A4 #CURRENCY SIGN
0xDC 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0xFB01 #LATIN SMALL LIGATURE FI
0xDF 0xFB02 #LATIN SMALL LIGATURE FL
0xE0 0x2021 #DOUBLE DAGGER
0xE1 0x00B7 #MIDDLE DOT
0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 #PER MILLE SIGN
0xE5 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 #UNDEFINED
0xF1 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xF5 0x0131 #LATIN SMALL LETTER DOTLESS I
0xF6 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC #SMALL TILDE
0xF8 0x00AF #MACRON
0xF9 0x02D8 #BREVE
0xFA 0x02D9 #DOT ABOVE
0xFB 0x02DA #RING ABOVE
0xFC 0x00B8 #CEDILLA
0xFD 0x02DD #DOUBLE ACUTE ACCENT
0xFE 0x02DB #OGONEK
0xFF 0x02C7 #CARON


275
unicode/vendors/micsft/mac/turkish.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp10081_MacTurkish to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp10081_MacTurkish code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp10081_MacTurkish order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x82 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0x84 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0x8B 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0x8C 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0x93 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0x96 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0x98 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xA0 0x2020 #DAGGER
0xA1 0x00B0 #DEGREE SIGN
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A7 #SECTION SIGN
0xA5 0x2022 #BULLET
0xA6 0x00B6 #PILCROW SIGN
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
0xA8 0x00AE #REGISTERED SIGN
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x2122 #TRADE MARK SIGN
0xAB 0x00B4 #ACUTE ACCENT
0xAC 0x00A8 #DIAERESIS
0xAD 0x2260 #NOT EQUAL TO
0xAE 0x00C6 #LATIN CAPITAL LIGATURE AE
0xAF 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E #INFINITY
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x2264 #LESS-THAN OR EQUAL TO
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
0xB4 0x00A5 #YEN SIGN
0xB5 0x00B5 #MICRO SIGN
0xB6 0x2202 #PARTIAL DIFFERENTIAL
0xB7 0x2211 #N-ARY SUMMATION
0xB8 0x220F #N-ARY PRODUCT
0xB9 0x03C0 #GREEK SMALL LETTER PI
0xBA 0x222B #INTEGRAL
0xBB 0x00AA #FEMININE ORDINAL INDICATOR
0xBC 0x00BA #MASCULINE ORDINAL INDICATOR
0xBD 0x2126 #OHM SIGN
0xBE 0x00E6 #LATIN SMALL LIGATURE AE
0xBF 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF #INVERTED QUESTION MARK
0xC1 0x00A1 #INVERTED EXCLAMATION MARK
0xC2 0x00AC #NOT SIGN
0xC3 0x221A #SQUARE ROOT
0xC4 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xC5 0x2248 #ALMOST EQUAL TO
0xC6 0x2206 #INCREMENT
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xC9 0x2026 #HORIZONTAL ELLIPSIS
0xCA 0x00A0 #NO-BREAK SPACE
0xCB 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xCC 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xCE 0x0152 #LATIN CAPITAL LIGATURE OE
0xCF 0x0153 #LATIN SMALL LIGATURE OE
0xD0 0x2013 #EN DASH
0xD1 0x2014 #EM DASH
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
0xD6 0x00F7 #DIVISION SIGN
0xD7 0x25CA #LOZENGE
0xD8 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x011E #LATIN CAPITAL LETTER G WITH BREVE
0xDB 0x011F #LATIN SMALL LETTER G WITH BREVE
0xDC 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
0xDD 0x0131 #LATIN SMALL LETTER DOTLESS I
0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
0xDF 0x015F #LATIN SMALL LETTER S WITH CEDILLA
0xE0 0x2021 #DOUBLE DAGGER
0xE1 0x00B7 #MIDDLE DOT
0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK
0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK
0xE4 0x2030 #PER MILLE SIGN
0xE5 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xE6 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xE8 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xE9 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xEB 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xEC 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xED 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xF0 #UNDEFINED
0xF1 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xF3 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xF4 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xF5 #UNDEFINED
0xF6 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0xF7 0x02DC #SMALL TILDE
0xF8 0x00AF #MACRON
0xF9 0x02D8 #BREVE
0xFA 0x02D9 #DOT ABOVE
0xFB 0x02DA #RING ABOVE
0xFC 0x00B8 #CEDILLA
0xFD 0x02DD #DOUBLE ACUTE ACCENT
0xFE 0x02DB #OGONEK
0xFF 0x02C7 #CARON


274
unicode/vendors/micsft/pc/cp437.txt vendored Normal file
View File

@@ -0,0 +1,274 @@
#
# Name: cp437_DOSLatinUS to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp437_DOSLatinUS code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp437_DOSLatinUS order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00a2 #CENT SIGN
0x9c 0x00a3 #POUND SIGN
0x9d 0x00a5 #YEN SIGN
0x9e 0x20a7 #PESETA SIGN
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x00aa #FEMININE ORDINAL INDICATOR
0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x2310 #REVERSED NOT SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


274
unicode/vendors/micsft/pc/cp737.txt vendored Normal file
View File

@@ -0,0 +1,274 @@
#
# Name: cp737_DOSGreek to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp737_DOSGreek code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp737_DOSGreek order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x0391 #GREEK CAPITAL LETTER ALPHA
0x81 0x0392 #GREEK CAPITAL LETTER BETA
0x82 0x0393 #GREEK CAPITAL LETTER GAMMA
0x83 0x0394 #GREEK CAPITAL LETTER DELTA
0x84 0x0395 #GREEK CAPITAL LETTER EPSILON
0x85 0x0396 #GREEK CAPITAL LETTER ZETA
0x86 0x0397 #GREEK CAPITAL LETTER ETA
0x87 0x0398 #GREEK CAPITAL LETTER THETA
0x88 0x0399 #GREEK CAPITAL LETTER IOTA
0x89 0x039a #GREEK CAPITAL LETTER KAPPA
0x8a 0x039b #GREEK CAPITAL LETTER LAMDA
0x8b 0x039c #GREEK CAPITAL LETTER MU
0x8c 0x039d #GREEK CAPITAL LETTER NU
0x8d 0x039e #GREEK CAPITAL LETTER XI
0x8e 0x039f #GREEK CAPITAL LETTER OMICRON
0x8f 0x03a0 #GREEK CAPITAL LETTER PI
0x90 0x03a1 #GREEK CAPITAL LETTER RHO
0x91 0x03a3 #GREEK CAPITAL LETTER SIGMA
0x92 0x03a4 #GREEK CAPITAL LETTER TAU
0x93 0x03a5 #GREEK CAPITAL LETTER UPSILON
0x94 0x03a6 #GREEK CAPITAL LETTER PHI
0x95 0x03a7 #GREEK CAPITAL LETTER CHI
0x96 0x03a8 #GREEK CAPITAL LETTER PSI
0x97 0x03a9 #GREEK CAPITAL LETTER OMEGA
0x98 0x03b1 #GREEK SMALL LETTER ALPHA
0x99 0x03b2 #GREEK SMALL LETTER BETA
0x9a 0x03b3 #GREEK SMALL LETTER GAMMA
0x9b 0x03b4 #GREEK SMALL LETTER DELTA
0x9c 0x03b5 #GREEK SMALL LETTER EPSILON
0x9d 0x03b6 #GREEK SMALL LETTER ZETA
0x9e 0x03b7 #GREEK SMALL LETTER ETA
0x9f 0x03b8 #GREEK SMALL LETTER THETA
0xa0 0x03b9 #GREEK SMALL LETTER IOTA
0xa1 0x03ba #GREEK SMALL LETTER KAPPA
0xa2 0x03bb #GREEK SMALL LETTER LAMDA
0xa3 0x03bc #GREEK SMALL LETTER MU
0xa4 0x03bd #GREEK SMALL LETTER NU
0xa5 0x03be #GREEK SMALL LETTER XI
0xa6 0x03bf #GREEK SMALL LETTER OMICRON
0xa7 0x03c0 #GREEK SMALL LETTER PI
0xa8 0x03c1 #GREEK SMALL LETTER RHO
0xa9 0x03c3 #GREEK SMALL LETTER SIGMA
0xaa 0x03c2 #GREEK SMALL LETTER FINAL SIGMA
0xab 0x03c4 #GREEK SMALL LETTER TAU
0xac 0x03c5 #GREEK SMALL LETTER UPSILON
0xad 0x03c6 #GREEK SMALL LETTER PHI
0xae 0x03c7 #GREEK SMALL LETTER CHI
0xaf 0x03c8 #GREEK SMALL LETTER PSI
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03c9 #GREEK SMALL LETTER OMEGA
0xe1 0x03ac #GREEK SMALL LETTER ALPHA WITH TONOS
0xe2 0x03ad #GREEK SMALL LETTER EPSILON WITH TONOS
0xe3 0x03ae #GREEK SMALL LETTER ETA WITH TONOS
0xe4 0x03ca #GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xe5 0x03af #GREEK SMALL LETTER IOTA WITH TONOS
0xe6 0x03cc #GREEK SMALL LETTER OMICRON WITH TONOS
0xe7 0x03cd #GREEK SMALL LETTER UPSILON WITH TONOS
0xe8 0x03cb #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xe9 0x03ce #GREEK SMALL LETTER OMEGA WITH TONOS
0xea 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
0xeb 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
0xec 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
0xed 0x038a #GREEK CAPITAL LETTER IOTA WITH TONOS
0xee 0x038c #GREEK CAPITAL LETTER OMICRON WITH TONOS
0xef 0x038e #GREEK CAPITAL LETTER UPSILON WITH TONOS
0xf0 0x038f #GREEK CAPITAL LETTER OMEGA WITH TONOS
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x03aa #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0xf5 0x03ab #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp775.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp775_DOSBaltRim to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp775_DOSBaltRim code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp775_DOSBaltRim order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x0101 #LATIN SMALL LETTER A WITH MACRON
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x0123 #LATIN SMALL LETTER G WITH CEDILLA
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x0107 #LATIN SMALL LETTER C WITH ACUTE
0x88 0x0142 #LATIN SMALL LETTER L WITH STROKE
0x89 0x0113 #LATIN SMALL LETTER E WITH MACRON
0x8a 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA
0x8b 0x0157 #LATIN SMALL LETTER R WITH CEDILLA
0x8c 0x012b #LATIN SMALL LETTER I WITH MACRON
0x8d 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x014d #LATIN SMALL LETTER O WITH MACRON
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA
0x96 0x00a2 #CENT SIGN
0x97 0x015a #LATIN CAPITAL LETTER S WITH ACUTE
0x98 0x015b #LATIN SMALL LETTER S WITH ACUTE
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
0x9e 0x00d7 #MULTIPLICATION SIGN
0x9f 0x00a4 #CURRENCY SIGN
0xa0 0x0100 #LATIN CAPITAL LETTER A WITH MACRON
0xa1 0x012a #LATIN CAPITAL LETTER I WITH MACRON
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x017b #LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xa4 0x017c #LATIN SMALL LETTER Z WITH DOT ABOVE
0xa5 0x017a #LATIN SMALL LETTER Z WITH ACUTE
0xa6 0x201d #RIGHT DOUBLE QUOTATION MARK
0xa7 0x00a6 #BROKEN BAR
0xa8 0x00a9 #COPYRIGHT SIGN
0xa9 0x00ae #REGISTERED SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
0xb6 0x010c #LATIN CAPITAL LETTER C WITH CARON
0xb7 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
0xb8 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x012e #LATIN CAPITAL LETTER I WITH OGONEK
0xbe 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK
0xc7 0x016a #LATIN CAPITAL LETTER U WITH MACRON
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x017d #LATIN CAPITAL LETTER Z WITH CARON
0xd0 0x0105 #LATIN SMALL LETTER A WITH OGONEK
0xd1 0x010d #LATIN SMALL LETTER C WITH CARON
0xd2 0x0119 #LATIN SMALL LETTER E WITH OGONEK
0xd3 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE
0xd4 0x012f #LATIN SMALL LETTER I WITH OGONEK
0xd5 0x0161 #LATIN SMALL LETTER S WITH CARON
0xd6 0x0173 #LATIN SMALL LETTER U WITH OGONEK
0xd7 0x016b #LATIN SMALL LETTER U WITH MACRON
0xd8 0x017e #LATIN SMALL LETTER Z WITH CARON
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xe1 0x00df #LATIN SMALL LETTER SHARP S (GERMAN)
0xe2 0x014c #LATIN CAPITAL LETTER O WITH MACRON
0xe3 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
0xe4 0x00f5 #LATIN SMALL LETTER O WITH TILDE
0xe5 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE
0xe6 0x00b5 #MICRO SIGN
0xe7 0x0144 #LATIN SMALL LETTER N WITH ACUTE
0xe8 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA
0xe9 0x0137 #LATIN SMALL LETTER K WITH CEDILLA
0xea 0x013b #LATIN CAPITAL LETTER L WITH CEDILLA
0xeb 0x013c #LATIN SMALL LETTER L WITH CEDILLA
0xec 0x0146 #LATIN SMALL LETTER N WITH CEDILLA
0xed 0x0112 #LATIN CAPITAL LETTER E WITH MACRON
0xee 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA
0xef 0x2019 #RIGHT SINGLE QUOTATION MARK
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x201c #LEFT DOUBLE QUOTATION MARK
0xf3 0x00be #VULGAR FRACTION THREE QUARTERS
0xf4 0x00b6 #PILCROW SIGN
0xf5 0x00a7 #SECTION SIGN
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x201e #DOUBLE LOW-9 QUOTATION MARK
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x00b9 #SUPERSCRIPT ONE
0xfc 0x00b3 #SUPERSCRIPT THREE
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


274
unicode/vendors/micsft/pc/cp850.txt vendored Normal file
View File

@@ -0,0 +1,274 @@
#
# Name: cp850_DOSLatin1 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp850_DOSLatin1 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp850_DOSLatin1 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
0x9e 0x00d7 #MULTIPLICATION SIGN
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x00aa #FEMININE ORDINAL INDICATOR
0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x00ae #REGISTERED SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xb7 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE
0xb8 0x00a9 #COPYRIGHT SIGN
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x00a2 #CENT SIGN
0xbe 0x00a5 #YEN SIGN
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x00e3 #LATIN SMALL LETTER A WITH TILDE
0xc7 0x00c3 #LATIN CAPITAL LETTER A WITH TILDE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x00a4 #CURRENCY SIGN
0xd0 0x00f0 #LATIN SMALL LETTER ETH
0xd1 0x00d0 #LATIN CAPITAL LETTER ETH
0xd2 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS
0xd4 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE
0xd5 0x0131 #LATIN SMALL LETTER DOTLESS I
0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xd8 0x00cf #LATIN CAPITAL LETTER I WITH DIAERESIS
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x00a6 #BROKEN BAR
0xde 0x00cc #LATIN CAPITAL LETTER I WITH GRAVE
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xe3 0x00d2 #LATIN CAPITAL LETTER O WITH GRAVE
0xe4 0x00f5 #LATIN SMALL LETTER O WITH TILDE
0xe5 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE
0xe6 0x00b5 #MICRO SIGN
0xe7 0x00fe #LATIN SMALL LETTER THORN
0xe8 0x00de #LATIN CAPITAL LETTER THORN
0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
0xea 0x00db #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xeb 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE
0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE
0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE
0xee 0x00af #MACRON
0xef 0x00b4 #ACUTE ACCENT
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2017 #DOUBLE LOW LINE
0xf3 0x00be #VULGAR FRACTION THREE QUARTERS
0xf4 0x00b6 #PILCROW SIGN
0xf5 0x00a7 #SECTION SIGN
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x00b8 #CEDILLA
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x00a8 #DIAERESIS
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x00b9 #SUPERSCRIPT ONE
0xfc 0x00b3 #SUPERSCRIPT THREE
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


274
unicode/vendors/micsft/pc/cp852.txt vendored Normal file
View File

@@ -0,0 +1,274 @@
#
# Name: cp852_DOSLatin2 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp852_DOSLatin2 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp852_DOSLatin2 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x016f #LATIN SMALL LETTER U WITH RING ABOVE
0x86 0x0107 #LATIN SMALL LETTER C WITH ACUTE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x0142 #LATIN SMALL LETTER L WITH STROKE
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0x8b 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
0x92 0x013a #LATIN SMALL LETTER L WITH ACUTE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x013d #LATIN CAPITAL LETTER L WITH CARON
0x96 0x013e #LATIN SMALL LETTER L WITH CARON
0x97 0x015a #LATIN CAPITAL LETTER S WITH ACUTE
0x98 0x015b #LATIN SMALL LETTER S WITH ACUTE
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x0164 #LATIN CAPITAL LETTER T WITH CARON
0x9c 0x0165 #LATIN SMALL LETTER T WITH CARON
0x9d 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
0x9e 0x00d7 #MULTIPLICATION SIGN
0x9f 0x010d #LATIN SMALL LETTER C WITH CARON
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
0xa5 0x0105 #LATIN SMALL LETTER A WITH OGONEK
0xa6 0x017d #LATIN CAPITAL LETTER Z WITH CARON
0xa7 0x017e #LATIN SMALL LETTER Z WITH CARON
0xa8 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
0xa9 0x0119 #LATIN SMALL LETTER E WITH OGONEK
0xaa 0x00ac #NOT SIGN
0xab 0x017a #LATIN SMALL LETTER Z WITH ACUTE
0xac 0x010c #LATIN CAPITAL LETTER C WITH CARON
0xad 0x015f #LATIN SMALL LETTER S WITH CEDILLA
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xb7 0x011a #LATIN CAPITAL LETTER E WITH CARON
0xb8 0x015e #LATIN CAPITAL LETTER S WITH CEDILLA
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x017b #LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xbe 0x017c #LATIN SMALL LETTER Z WITH DOT ABOVE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
0xc7 0x0103 #LATIN SMALL LETTER A WITH BREVE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x00a4 #CURRENCY SIGN
0xd0 0x0111 #LATIN SMALL LETTER D WITH STROKE
0xd1 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
0xd2 0x010e #LATIN CAPITAL LETTER D WITH CARON
0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS
0xd4 0x010f #LATIN SMALL LETTER D WITH CARON
0xd5 0x0147 #LATIN CAPITAL LETTER N WITH CARON
0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xd8 0x011b #LATIN SMALL LETTER E WITH CARON
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
0xde 0x016e #LATIN CAPITAL LETTER U WITH RING ABOVE
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xe3 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
0xe4 0x0144 #LATIN SMALL LETTER N WITH ACUTE
0xe5 0x0148 #LATIN SMALL LETTER N WITH CARON
0xe6 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0xe7 0x0161 #LATIN SMALL LETTER S WITH CARON
0xe8 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
0xea 0x0155 #LATIN SMALL LETTER R WITH ACUTE
0xeb 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE
0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE
0xee 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
0xef 0x00b4 #ACUTE ACCENT
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x02dd #DOUBLE ACUTE ACCENT
0xf2 0x02db #OGONEK
0xf3 0x02c7 #CARON
0xf4 0x02d8 #BREVE
0xf5 0x00a7 #SECTION SIGN
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x00b8 #CEDILLA
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x00a8 #DIAERESIS
0xfa 0x02d9 #DOT ABOVE
0xfb 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xfc 0x0158 #LATIN CAPITAL LETTER R WITH CARON
0xfd 0x0159 #LATIN SMALL LETTER R WITH CARON
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp855.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp855_DOSCyrillic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp855_DOSCyrillic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp855_DOSCyrillic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x0452 #CYRILLIC SMALL LETTER DJE
0x81 0x0402 #CYRILLIC CAPITAL LETTER DJE
0x82 0x0453 #CYRILLIC SMALL LETTER GJE
0x83 0x0403 #CYRILLIC CAPITAL LETTER GJE
0x84 0x0451 #CYRILLIC SMALL LETTER IO
0x85 0x0401 #CYRILLIC CAPITAL LETTER IO
0x86 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
0x87 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
0x88 0x0455 #CYRILLIC SMALL LETTER DZE
0x89 0x0405 #CYRILLIC CAPITAL LETTER DZE
0x8a 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0x8b 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0x8c 0x0457 #CYRILLIC SMALL LETTER YI
0x8d 0x0407 #CYRILLIC CAPITAL LETTER YI
0x8e 0x0458 #CYRILLIC SMALL LETTER JE
0x8f 0x0408 #CYRILLIC CAPITAL LETTER JE
0x90 0x0459 #CYRILLIC SMALL LETTER LJE
0x91 0x0409 #CYRILLIC CAPITAL LETTER LJE
0x92 0x045a #CYRILLIC SMALL LETTER NJE
0x93 0x040a #CYRILLIC CAPITAL LETTER NJE
0x94 0x045b #CYRILLIC SMALL LETTER TSHE
0x95 0x040b #CYRILLIC CAPITAL LETTER TSHE
0x96 0x045c #CYRILLIC SMALL LETTER KJE
0x97 0x040c #CYRILLIC CAPITAL LETTER KJE
0x98 0x045e #CYRILLIC SMALL LETTER SHORT U
0x99 0x040e #CYRILLIC CAPITAL LETTER SHORT U
0x9a 0x045f #CYRILLIC SMALL LETTER DZHE
0x9b 0x040f #CYRILLIC CAPITAL LETTER DZHE
0x9c 0x044e #CYRILLIC SMALL LETTER YU
0x9d 0x042e #CYRILLIC CAPITAL LETTER YU
0x9e 0x044a #CYRILLIC SMALL LETTER HARD SIGN
0x9f 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN
0xa0 0x0430 #CYRILLIC SMALL LETTER A
0xa1 0x0410 #CYRILLIC CAPITAL LETTER A
0xa2 0x0431 #CYRILLIC SMALL LETTER BE
0xa3 0x0411 #CYRILLIC CAPITAL LETTER BE
0xa4 0x0446 #CYRILLIC SMALL LETTER TSE
0xa5 0x0426 #CYRILLIC CAPITAL LETTER TSE
0xa6 0x0434 #CYRILLIC SMALL LETTER DE
0xa7 0x0414 #CYRILLIC CAPITAL LETTER DE
0xa8 0x0435 #CYRILLIC SMALL LETTER IE
0xa9 0x0415 #CYRILLIC CAPITAL LETTER IE
0xaa 0x0444 #CYRILLIC SMALL LETTER EF
0xab 0x0424 #CYRILLIC CAPITAL LETTER EF
0xac 0x0433 #CYRILLIC SMALL LETTER GHE
0xad 0x0413 #CYRILLIC CAPITAL LETTER GHE
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x0445 #CYRILLIC SMALL LETTER HA
0xb6 0x0425 #CYRILLIC CAPITAL LETTER HA
0xb7 0x0438 #CYRILLIC SMALL LETTER I
0xb8 0x0418 #CYRILLIC CAPITAL LETTER I
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x0439 #CYRILLIC SMALL LETTER SHORT I
0xbe 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x043a #CYRILLIC SMALL LETTER KA
0xc7 0x041a #CYRILLIC CAPITAL LETTER KA
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x00a4 #CURRENCY SIGN
0xd0 0x043b #CYRILLIC SMALL LETTER EL
0xd1 0x041b #CYRILLIC CAPITAL LETTER EL
0xd2 0x043c #CYRILLIC SMALL LETTER EM
0xd3 0x041c #CYRILLIC CAPITAL LETTER EM
0xd4 0x043d #CYRILLIC SMALL LETTER EN
0xd5 0x041d #CYRILLIC CAPITAL LETTER EN
0xd6 0x043e #CYRILLIC SMALL LETTER O
0xd7 0x041e #CYRILLIC CAPITAL LETTER O
0xd8 0x043f #CYRILLIC SMALL LETTER PE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x041f #CYRILLIC CAPITAL LETTER PE
0xde 0x044f #CYRILLIC SMALL LETTER YA
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x042f #CYRILLIC CAPITAL LETTER YA
0xe1 0x0440 #CYRILLIC SMALL LETTER ER
0xe2 0x0420 #CYRILLIC CAPITAL LETTER ER
0xe3 0x0441 #CYRILLIC SMALL LETTER ES
0xe4 0x0421 #CYRILLIC CAPITAL LETTER ES
0xe5 0x0442 #CYRILLIC SMALL LETTER TE
0xe6 0x0422 #CYRILLIC CAPITAL LETTER TE
0xe7 0x0443 #CYRILLIC SMALL LETTER U
0xe8 0x0423 #CYRILLIC CAPITAL LETTER U
0xe9 0x0436 #CYRILLIC SMALL LETTER ZHE
0xea 0x0416 #CYRILLIC CAPITAL LETTER ZHE
0xeb 0x0432 #CYRILLIC SMALL LETTER VE
0xec 0x0412 #CYRILLIC CAPITAL LETTER VE
0xed 0x044c #CYRILLIC SMALL LETTER SOFT SIGN
0xee 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN
0xef 0x2116 #NUMERO SIGN
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x044b #CYRILLIC SMALL LETTER YERU
0xf2 0x042b #CYRILLIC CAPITAL LETTER YERU
0xf3 0x0437 #CYRILLIC SMALL LETTER ZE
0xf4 0x0417 #CYRILLIC CAPITAL LETTER ZE
0xf5 0x0448 #CYRILLIC SMALL LETTER SHA
0xf6 0x0428 #CYRILLIC CAPITAL LETTER SHA
0xf7 0x044d #CYRILLIC SMALL LETTER E
0xf8 0x042d #CYRILLIC CAPITAL LETTER E
0xf9 0x0449 #CYRILLIC SMALL LETTER SHCHA
0xfa 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
0xfb 0x0447 #CYRILLIC SMALL LETTER CHE
0xfc 0x0427 #CYRILLIC CAPITAL LETTER CHE
0xfd 0x00a7 #SECTION SIGN
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp857.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp857_DOSTurkish to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp857_DOSTurkish code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp857_DOSTurkish order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x0131 #LATIN SMALL LETTER DOTLESS I
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
0x9e 0x015e #LATIN CAPITAL LETTER S WITH CEDILLA
0x9f 0x015f #LATIN SMALL LETTER S WITH CEDILLA
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x011e #LATIN CAPITAL LETTER G WITH BREVE
0xa7 0x011f #LATIN SMALL LETTER G WITH BREVE
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x00ae #REGISTERED SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xb7 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE
0xb8 0x00a9 #COPYRIGHT SIGN
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x00a2 #CENT SIGN
0xbe 0x00a5 #YEN SIGN
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x00e3 #LATIN SMALL LETTER A WITH TILDE
0xc7 0x00c3 #LATIN CAPITAL LETTER A WITH TILDE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x00a4 #CURRENCY SIGN
0xd0 0x00ba #MASCULINE ORDINAL INDICATOR
0xd1 0x00aa #FEMININE ORDINAL INDICATOR
0xd2 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS
0xd4 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE
0xd5 #UNDEFINED
0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xd8 0x00cf #LATIN CAPITAL LETTER I WITH DIAERESIS
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x00a6 #BROKEN BAR
0xde 0x00cc #LATIN CAPITAL LETTER I WITH GRAVE
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xe3 0x00d2 #LATIN CAPITAL LETTER O WITH GRAVE
0xe4 0x00f5 #LATIN SMALL LETTER O WITH TILDE
0xe5 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE
0xe6 0x00b5 #MICRO SIGN
0xe7 #UNDEFINED
0xe8 0x00d7 #MULTIPLICATION SIGN
0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
0xea 0x00db #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xeb 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE
0xec 0x00ec #LATIN SMALL LETTER I WITH GRAVE
0xed 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS
0xee 0x00af #MACRON
0xef 0x00b4 #ACUTE ACCENT
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 #UNDEFINED
0xf3 0x00be #VULGAR FRACTION THREE QUARTERS
0xf4 0x00b6 #PILCROW SIGN
0xf5 0x00a7 #SECTION SIGN
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x00b8 #CEDILLA
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x00a8 #DIAERESIS
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x00b9 #SUPERSCRIPT ONE
0xfc 0x00b3 #SUPERSCRIPT THREE
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp860.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp860_DOSPortuguese to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp860_DOSPortuguese code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp860_DOSPortuguese order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e3 #LATIN SMALL LETTER A WITH TILDE
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
0x8c 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE
0x8e 0x00c3 #LATIN CAPITAL LETTER A WITH TILDE
0x8f 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE
0x92 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f5 #LATIN SMALL LETTER O WITH TILDE
0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
0x96 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x00cc #LATIN CAPITAL LETTER I WITH GRAVE
0x99 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00a2 #CENT SIGN
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE
0x9e 0x20a7 #PESETA SIGN
0x9f 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x00aa #FEMININE ORDINAL INDICATOR
0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x00d2 #LATIN CAPITAL LETTER O WITH GRAVE
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp861.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp861_DOSIcelandic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp861_DOSIcelandic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp861_DOSIcelandic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00d0 #LATIN CAPITAL LETTER ETH
0x8c 0x00f0 #LATIN SMALL LETTER ETH
0x8d 0x00de #LATIN CAPITAL LETTER THORN
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x00fe #LATIN SMALL LETTER THORN
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE
0x98 0x00fd #LATIN SMALL LETTER Y WITH ACUTE
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
0x9e 0x20a7 #PESETA SIGN
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
0xa5 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
0xa6 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
0xa7 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x2310 #REVERSED NOT SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp862.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp862_DOSHebrew to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp862_DOSHebrew code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp862_DOSHebrew order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x05d0 #HEBREW LETTER ALEF
0x81 0x05d1 #HEBREW LETTER BET
0x82 0x05d2 #HEBREW LETTER GIMEL
0x83 0x05d3 #HEBREW LETTER DALET
0x84 0x05d4 #HEBREW LETTER HE
0x85 0x05d5 #HEBREW LETTER VAV
0x86 0x05d6 #HEBREW LETTER ZAYIN
0x87 0x05d7 #HEBREW LETTER HET
0x88 0x05d8 #HEBREW LETTER TET
0x89 0x05d9 #HEBREW LETTER YOD
0x8a 0x05da #HEBREW LETTER FINAL KAF
0x8b 0x05db #HEBREW LETTER KAF
0x8c 0x05dc #HEBREW LETTER LAMED
0x8d 0x05dd #HEBREW LETTER FINAL MEM
0x8e 0x05de #HEBREW LETTER MEM
0x8f 0x05df #HEBREW LETTER FINAL NUN
0x90 0x05e0 #HEBREW LETTER NUN
0x91 0x05e1 #HEBREW LETTER SAMEKH
0x92 0x05e2 #HEBREW LETTER AYIN
0x93 0x05e3 #HEBREW LETTER FINAL PE
0x94 0x05e4 #HEBREW LETTER PE
0x95 0x05e5 #HEBREW LETTER FINAL TSADI
0x96 0x05e6 #HEBREW LETTER TSADI
0x97 0x05e7 #HEBREW LETTER QOF
0x98 0x05e8 #HEBREW LETTER RESH
0x99 0x05e9 #HEBREW LETTER SHIN
0x9a 0x05ea #HEBREW LETTER TAV
0x9b 0x00a2 #CENT SIGN
0x9c 0x00a3 #POUND SIGN
0x9d 0x00a5 #YEN SIGN
0x9e 0x20a7 #PESETA SIGN
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x00aa #FEMININE ORDINAL INDICATOR
0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x2310 #REVERSED NOT SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S (GERMAN)
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp863.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp863_DOSCanadaF to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp863_DOSCanadaF code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp863_DOSCanadaF order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00b6 #PILCROW SIGN
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x2017 #DOUBLE LOW LINE
0x8e 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE
0x8f 0x00a7 #SECTION SIGN
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE
0x92 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS
0x95 0x00cf #LATIN CAPITAL LETTER I WITH DIAERESIS
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x00a4 #CURRENCY SIGN
0x99 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00a2 #CENT SIGN
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE
0x9e 0x00db #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00a6 #BROKEN BAR
0xa1 0x00b4 #ACUTE ACCENT
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00a8 #DIAERESIS
0xa5 0x00b8 #CEDILLA
0xa6 0x00b3 #SUPERSCRIPT THREE
0xa7 0x00af #MACRON
0xa8 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xa9 0x2310 #REVERSED NOT SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00be #VULGAR FRACTION THREE QUARTERS
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp864.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp864_DOSArabic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp864_DOSArabic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp864_DOSArabic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x066a #ARABIC PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00b0 #DEGREE SIGN
0x81 0x00b7 #MIDDLE DOT
0x82 0x2219 #BULLET OPERATOR
0x83 0x221a #SQUARE ROOT
0x84 0x2592 #MEDIUM SHADE
0x85 0x2500 #FORMS LIGHT HORIZONTAL
0x86 0x2502 #FORMS LIGHT VERTICAL
0x87 0x253c #FORMS LIGHT VERTICAL AND HORIZONTAL
0x88 0x2524 #FORMS LIGHT VERTICAL AND LEFT
0x89 0x252c #FORMS LIGHT DOWN AND HORIZONTAL
0x8a 0x251c #FORMS LIGHT VERTICAL AND RIGHT
0x8b 0x2534 #FORMS LIGHT UP AND HORIZONTAL
0x8c 0x2510 #FORMS LIGHT DOWN AND LEFT
0x8d 0x250c #FORMS LIGHT DOWN AND RIGHT
0x8e 0x2514 #FORMS LIGHT UP AND RIGHT
0x8f 0x2518 #FORMS LIGHT UP AND LEFT
0x90 0x03b2 #GREEK SMALL BETA
0x91 0x221e #INFINITY
0x92 0x03c6 #GREEK SMALL PHI
0x93 0x00b1 #PLUS-OR-MINUS SIGN
0x94 0x00bd #FRACTION 1/2
0x95 0x00bc #FRACTION 1/4
0x96 0x2248 #ALMOST EQUAL TO
0x97 0x00ab #LEFT POINTING GUILLEMET
0x98 0x00bb #RIGHT POINTING GUILLEMET
0x99 0xfef7 #ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
0x9a 0xfef8 #ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
0x9b #UNDEFINED
0x9c #UNDEFINED
0x9d 0xfefb #ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
0x9e 0xfefc #ARABIC LIGATURE LAM WITH ALEF FINAL FORM
0x9f #UNDEFINED
0xa0 0x00a0 #NON-BREAKING SPACE
0xa1 0x00ad #SOFT HYPHEN
0xa2 0xfe82 #ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
0xa3 0x00a3 #POUND SIGN
0xa4 0x00a4 #CURRENCY SIGN
0xa5 0xfe84 #ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
0xa6 #UNDEFINED
0xa7 #UNDEFINED
0xa8 0xfe8e #ARABIC LETTER ALEF FINAL FORM
0xa9 0xfe8f #ARABIC LETTER BEH ISOLATED FORM
0xaa 0xfe95 #ARABIC LETTER TEH ISOLATED FORM
0xab 0xfe99 #ARABIC LETTER THEH ISOLATED FORM
0xac 0x060c #ARABIC COMMA
0xad 0xfe9d #ARABIC LETTER JEEM ISOLATED FORM
0xae 0xfea1 #ARABIC LETTER HAH ISOLATED FORM
0xaf 0xfea5 #ARABIC LETTER KHAH ISOLATED FORM
0xb0 0x0660 #ARABIC-INDIC DIGIT ZERO
0xb1 0x0661 #ARABIC-INDIC DIGIT ONE
0xb2 0x0662 #ARABIC-INDIC DIGIT TWO
0xb3 0x0663 #ARABIC-INDIC DIGIT THREE
0xb4 0x0664 #ARABIC-INDIC DIGIT FOUR
0xb5 0x0665 #ARABIC-INDIC DIGIT FIVE
0xb6 0x0666 #ARABIC-INDIC DIGIT SIX
0xb7 0x0667 #ARABIC-INDIC DIGIT SEVEN
0xb8 0x0668 #ARABIC-INDIC DIGIT EIGHT
0xb9 0x0669 #ARABIC-INDIC DIGIT NINE
0xba 0xfed1 #ARABIC LETTER FEH ISOLATED FORM
0xbb 0x061b #ARABIC SEMICOLON
0xbc 0xfeb1 #ARABIC LETTER SEEN ISOLATED FORM
0xbd 0xfeb5 #ARABIC LETTER SHEEN ISOLATED FORM
0xbe 0xfeb9 #ARABIC LETTER SAD ISOLATED FORM
0xbf 0x061f #ARABIC QUESTION MARK
0xc0 0x00a2 #CENT SIGN
0xc1 0xfe80 #ARABIC LETTER HAMZA ISOLATED FORM
0xc2 0xfe81 #ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
0xc3 0xfe83 #ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
0xc4 0xfe85 #ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
0xc5 0xfeca #ARABIC LETTER AIN FINAL FORM
0xc6 0xfe8b #ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
0xc7 0xfe8d #ARABIC LETTER ALEF ISOLATED FORM
0xc8 0xfe91 #ARABIC LETTER BEH INITIAL FORM
0xc9 0xfe93 #ARABIC LETTER TEH MARBUTA ISOLATED FORM
0xca 0xfe97 #ARABIC LETTER TEH INITIAL FORM
0xcb 0xfe9b #ARABIC LETTER THEH INITIAL FORM
0xcc 0xfe9f #ARABIC LETTER JEEM INITIAL FORM
0xcd 0xfea3 #ARABIC LETTER HAH INITIAL FORM
0xce 0xfea7 #ARABIC LETTER KHAH INITIAL FORM
0xcf 0xfea9 #ARABIC LETTER DAL ISOLATED FORM
0xd0 0xfeab #ARABIC LETTER THAL ISOLATED FORM
0xd1 0xfead #ARABIC LETTER REH ISOLATED FORM
0xd2 0xfeaf #ARABIC LETTER ZAIN ISOLATED FORM
0xd3 0xfeb3 #ARABIC LETTER SEEN INITIAL FORM
0xd4 0xfeb7 #ARABIC LETTER SHEEN INITIAL FORM
0xd5 0xfebb #ARABIC LETTER SAD INITIAL FORM
0xd6 0xfebf #ARABIC LETTER DAD INITIAL FORM
0xd7 0xfec1 #ARABIC LETTER TAH ISOLATED FORM
0xd8 0xfec5 #ARABIC LETTER ZAH ISOLATED FORM
0xd9 0xfecb #ARABIC LETTER AIN INITIAL FORM
0xda 0xfecf #ARABIC LETTER GHAIN INITIAL FORM
0xdb 0x00a6 #BROKEN VERTICAL BAR
0xdc 0x00ac #NOT SIGN
0xdd 0x00f7 #DIVISION SIGN
0xde 0x00d7 #MULTIPLICATION SIGN
0xdf 0xfec9 #ARABIC LETTER AIN ISOLATED FORM
0xe0 0x0640 #ARABIC TATWEEL
0xe1 0xfed3 #ARABIC LETTER FEH INITIAL FORM
0xe2 0xfed7 #ARABIC LETTER QAF INITIAL FORM
0xe3 0xfedb #ARABIC LETTER KAF INITIAL FORM
0xe4 0xfedf #ARABIC LETTER LAM INITIAL FORM
0xe5 0xfee3 #ARABIC LETTER MEEM INITIAL FORM
0xe6 0xfee7 #ARABIC LETTER NOON INITIAL FORM
0xe7 0xfeeb #ARABIC LETTER HEH INITIAL FORM
0xe8 0xfeed #ARABIC LETTER WAW ISOLATED FORM
0xe9 0xfeef #ARABIC LETTER ALEF MAKSURA ISOLATED FORM
0xea 0xfef3 #ARABIC LETTER YEH INITIAL FORM
0xeb 0xfebd #ARABIC LETTER DAD ISOLATED FORM
0xec 0xfecc #ARABIC LETTER AIN MEDIAL FORM
0xed 0xfece #ARABIC LETTER GHAIN FINAL FORM
0xee 0xfecd #ARABIC LETTER GHAIN ISOLATED FORM
0xef 0xfee1 #ARABIC LETTER MEEM ISOLATED FORM
0xf0 0xfe7d #ARABIC SHADDA MEDIAL FORM
0xf1 0x0651 #ARABIC SHADDAH
0xf2 0xfee5 #ARABIC LETTER NOON ISOLATED FORM
0xf3 0xfee9 #ARABIC LETTER HEH ISOLATED FORM
0xf4 0xfeec #ARABIC LETTER HEH MEDIAL FORM
0xf5 0xfef0 #ARABIC LETTER ALEF MAKSURA FINAL FORM
0xf6 0xfef2 #ARABIC LETTER YEH FINAL FORM
0xf7 0xfed0 #ARABIC LETTER GHAIN MEDIAL FORM
0xf8 0xfed5 #ARABIC LETTER QAF ISOLATED FORM
0xf9 0xfef5 #ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
0xfa 0xfef6 #ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
0xfb 0xfedd #ARABIC LETTER LAM ISOLATED FORM
0xfc 0xfed9 #ARABIC LETTER KAF ISOLATED FORM
0xfd 0xfef1 #ARABIC LETTER YEH ISOLATED FORM
0xfe 0x25a0 #BLACK SQUARE
0xff #UNDEFINED


275
unicode/vendors/micsft/pc/cp865.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp865_DOSNordic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp865_DOSNordic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp865_DOSNordic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE
0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
0x91 0x00e6 #LATIN SMALL LIGATURE AE
0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS
0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
0x9c 0x00a3 #POUND SIGN
0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
0x9e 0x20a7 #PESETA SIGN
0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE
0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
0xa6 0x00aa #FEMININE ORDINAL INDICATOR
0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
0xa8 0x00bf #INVERTED QUESTION MARK
0xa9 0x2310 #REVERSED NOT SIGN
0xaa 0x00ac #NOT SIGN
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x00bc #VULGAR FRACTION ONE QUARTER
0xad 0x00a1 #INVERTED EXCLAMATION MARK
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00a4 #CURRENCY SIGN
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
0xe1 0x00df #LATIN SMALL LETTER SHARP S
0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
0xe3 0x03c0 #GREEK SMALL LETTER PI
0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
0xe6 0x00b5 #MICRO SIGN
0xe7 0x03c4 #GREEK SMALL LETTER TAU
0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
0xe9 0x0398 #GREEK CAPITAL LETTER THETA
0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xeb 0x03b4 #GREEK SMALL LETTER DELTA
0xec 0x221e #INFINITY
0xed 0x03c6 #GREEK SMALL LETTER PHI
0xee 0x03b5 #GREEK SMALL LETTER EPSILON
0xef 0x2229 #INTERSECTION
0xf0 0x2261 #IDENTICAL TO
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x2265 #GREATER-THAN OR EQUAL TO
0xf3 0x2264 #LESS-THAN OR EQUAL TO
0xf4 0x2320 #TOP HALF INTEGRAL
0xf5 0x2321 #BOTTOM HALF INTEGRAL
0xf6 0x00f7 #DIVISION SIGN
0xf7 0x2248 #ALMOST EQUAL TO
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
0xfd 0x00b2 #SUPERSCRIPT TWO
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp866.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp866_DOSCyrillicRussian to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp866_DOSCyrillicRussian code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp866_DOSCyrillicRussian order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 0x0410 #CYRILLIC CAPITAL LETTER A
0x81 0x0411 #CYRILLIC CAPITAL LETTER BE
0x82 0x0412 #CYRILLIC CAPITAL LETTER VE
0x83 0x0413 #CYRILLIC CAPITAL LETTER GHE
0x84 0x0414 #CYRILLIC CAPITAL LETTER DE
0x85 0x0415 #CYRILLIC CAPITAL LETTER IE
0x86 0x0416 #CYRILLIC CAPITAL LETTER ZHE
0x87 0x0417 #CYRILLIC CAPITAL LETTER ZE
0x88 0x0418 #CYRILLIC CAPITAL LETTER I
0x89 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
0x8a 0x041a #CYRILLIC CAPITAL LETTER KA
0x8b 0x041b #CYRILLIC CAPITAL LETTER EL
0x8c 0x041c #CYRILLIC CAPITAL LETTER EM
0x8d 0x041d #CYRILLIC CAPITAL LETTER EN
0x8e 0x041e #CYRILLIC CAPITAL LETTER O
0x8f 0x041f #CYRILLIC CAPITAL LETTER PE
0x90 0x0420 #CYRILLIC CAPITAL LETTER ER
0x91 0x0421 #CYRILLIC CAPITAL LETTER ES
0x92 0x0422 #CYRILLIC CAPITAL LETTER TE
0x93 0x0423 #CYRILLIC CAPITAL LETTER U
0x94 0x0424 #CYRILLIC CAPITAL LETTER EF
0x95 0x0425 #CYRILLIC CAPITAL LETTER HA
0x96 0x0426 #CYRILLIC CAPITAL LETTER TSE
0x97 0x0427 #CYRILLIC CAPITAL LETTER CHE
0x98 0x0428 #CYRILLIC CAPITAL LETTER SHA
0x99 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
0x9a 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN
0x9b 0x042b #CYRILLIC CAPITAL LETTER YERU
0x9c 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN
0x9d 0x042d #CYRILLIC CAPITAL LETTER E
0x9e 0x042e #CYRILLIC CAPITAL LETTER YU
0x9f 0x042f #CYRILLIC CAPITAL LETTER YA
0xa0 0x0430 #CYRILLIC SMALL LETTER A
0xa1 0x0431 #CYRILLIC SMALL LETTER BE
0xa2 0x0432 #CYRILLIC SMALL LETTER VE
0xa3 0x0433 #CYRILLIC SMALL LETTER GHE
0xa4 0x0434 #CYRILLIC SMALL LETTER DE
0xa5 0x0435 #CYRILLIC SMALL LETTER IE
0xa6 0x0436 #CYRILLIC SMALL LETTER ZHE
0xa7 0x0437 #CYRILLIC SMALL LETTER ZE
0xa8 0x0438 #CYRILLIC SMALL LETTER I
0xa9 0x0439 #CYRILLIC SMALL LETTER SHORT I
0xaa 0x043a #CYRILLIC SMALL LETTER KA
0xab 0x043b #CYRILLIC SMALL LETTER EL
0xac 0x043c #CYRILLIC SMALL LETTER EM
0xad 0x043d #CYRILLIC SMALL LETTER EN
0xae 0x043e #CYRILLIC SMALL LETTER O
0xaf 0x043f #CYRILLIC SMALL LETTER PE
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x258c #LEFT HALF BLOCK
0xde 0x2590 #RIGHT HALF BLOCK
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x0440 #CYRILLIC SMALL LETTER ER
0xe1 0x0441 #CYRILLIC SMALL LETTER ES
0xe2 0x0442 #CYRILLIC SMALL LETTER TE
0xe3 0x0443 #CYRILLIC SMALL LETTER U
0xe4 0x0444 #CYRILLIC SMALL LETTER EF
0xe5 0x0445 #CYRILLIC SMALL LETTER HA
0xe6 0x0446 #CYRILLIC SMALL LETTER TSE
0xe7 0x0447 #CYRILLIC SMALL LETTER CHE
0xe8 0x0448 #CYRILLIC SMALL LETTER SHA
0xe9 0x0449 #CYRILLIC SMALL LETTER SHCHA
0xea 0x044a #CYRILLIC SMALL LETTER HARD SIGN
0xeb 0x044b #CYRILLIC SMALL LETTER YERU
0xec 0x044c #CYRILLIC SMALL LETTER SOFT SIGN
0xed 0x044d #CYRILLIC SMALL LETTER E
0xee 0x044e #CYRILLIC SMALL LETTER YU
0xef 0x044f #CYRILLIC SMALL LETTER YA
0xf0 0x0401 #CYRILLIC CAPITAL LETTER IO
0xf1 0x0451 #CYRILLIC SMALL LETTER IO
0xf2 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xf3 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
0xf4 0x0407 #CYRILLIC CAPITAL LETTER YI
0xf5 0x0457 #CYRILLIC SMALL LETTER YI
0xf6 0x040e #CYRILLIC CAPITAL LETTER SHORT U
0xf7 0x045e #CYRILLIC SMALL LETTER SHORT U
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x2219 #BULLET OPERATOR
0xfa 0x00b7 #MIDDLE DOT
0xfb 0x221a #SQUARE ROOT
0xfc 0x2116 #NUMERO SIGN
0xfd 0x00a4 #CURRENCY SIGN
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp869.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp869_DOSGreek2 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp869_DOSGreek2 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp869_DOSGreek2 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 #UNDEFINED
0x83 #UNDEFINED
0x84 #UNDEFINED
0x85 #UNDEFINED
0x86 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
0x87 #UNDEFINED
0x88 0x00b7 #MIDDLE DOT
0x89 0x00ac #NOT SIGN
0x8a 0x00a6 #BROKEN BAR
0x8b 0x2018 #LEFT SINGLE QUOTATION MARK
0x8c 0x2019 #RIGHT SINGLE QUOTATION MARK
0x8d 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
0x8e 0x2015 #HORIZONTAL BAR
0x8f 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
0x90 0x038a #GREEK CAPITAL LETTER IOTA WITH TONOS
0x91 0x03aa #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0x92 0x038c #GREEK CAPITAL LETTER OMICRON WITH TONOS
0x93 #UNDEFINED
0x94 #UNDEFINED
0x95 0x038e #GREEK CAPITAL LETTER UPSILON WITH TONOS
0x96 0x03ab #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0x97 0x00a9 #COPYRIGHT SIGN
0x98 0x038f #GREEK CAPITAL LETTER OMEGA WITH TONOS
0x99 0x00b2 #SUPERSCRIPT TWO
0x9a 0x00b3 #SUPERSCRIPT THREE
0x9b 0x03ac #GREEK SMALL LETTER ALPHA WITH TONOS
0x9c 0x00a3 #POUND SIGN
0x9d 0x03ad #GREEK SMALL LETTER EPSILON WITH TONOS
0x9e 0x03ae #GREEK SMALL LETTER ETA WITH TONOS
0x9f 0x03af #GREEK SMALL LETTER IOTA WITH TONOS
0xa0 0x03ca #GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xa1 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xa2 0x03cc #GREEK SMALL LETTER OMICRON WITH TONOS
0xa3 0x03cd #GREEK SMALL LETTER UPSILON WITH TONOS
0xa4 0x0391 #GREEK CAPITAL LETTER ALPHA
0xa5 0x0392 #GREEK CAPITAL LETTER BETA
0xa6 0x0393 #GREEK CAPITAL LETTER GAMMA
0xa7 0x0394 #GREEK CAPITAL LETTER DELTA
0xa8 0x0395 #GREEK CAPITAL LETTER EPSILON
0xa9 0x0396 #GREEK CAPITAL LETTER ZETA
0xaa 0x0397 #GREEK CAPITAL LETTER ETA
0xab 0x00bd #VULGAR FRACTION ONE HALF
0xac 0x0398 #GREEK CAPITAL LETTER THETA
0xad 0x0399 #GREEK CAPITAL LETTER IOTA
0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xb0 0x2591 #LIGHT SHADE
0xb1 0x2592 #MEDIUM SHADE
0xb2 0x2593 #DARK SHADE
0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
0xb5 0x039a #GREEK CAPITAL LETTER KAPPA
0xb6 0x039b #GREEK CAPITAL LETTER LAMDA
0xb7 0x039c #GREEK CAPITAL LETTER MU
0xb8 0x039d #GREEK CAPITAL LETTER NU
0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
0xbd 0x039e #GREEK CAPITAL LETTER XI
0xbe 0x039f #GREEK CAPITAL LETTER OMICRON
0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0xc6 0x03a0 #GREEK CAPITAL LETTER PI
0xc7 0x03a1 #GREEK CAPITAL LETTER RHO
0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0xcf 0x03a3 #GREEK CAPITAL LETTER SIGMA
0xd0 0x03a4 #GREEK CAPITAL LETTER TAU
0xd1 0x03a5 #GREEK CAPITAL LETTER UPSILON
0xd2 0x03a6 #GREEK CAPITAL LETTER PHI
0xd3 0x03a7 #GREEK CAPITAL LETTER CHI
0xd4 0x03a8 #GREEK CAPITAL LETTER PSI
0xd5 0x03a9 #GREEK CAPITAL LETTER OMEGA
0xd6 0x03b1 #GREEK SMALL LETTER ALPHA
0xd7 0x03b2 #GREEK SMALL LETTER BETA
0xd8 0x03b3 #GREEK SMALL LETTER GAMMA
0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
0xdb 0x2588 #FULL BLOCK
0xdc 0x2584 #LOWER HALF BLOCK
0xdd 0x03b4 #GREEK SMALL LETTER DELTA
0xde 0x03b5 #GREEK SMALL LETTER EPSILON
0xdf 0x2580 #UPPER HALF BLOCK
0xe0 0x03b6 #GREEK SMALL LETTER ZETA
0xe1 0x03b7 #GREEK SMALL LETTER ETA
0xe2 0x03b8 #GREEK SMALL LETTER THETA
0xe3 0x03b9 #GREEK SMALL LETTER IOTA
0xe4 0x03ba #GREEK SMALL LETTER KAPPA
0xe5 0x03bb #GREEK SMALL LETTER LAMDA
0xe6 0x03bc #GREEK SMALL LETTER MU
0xe7 0x03bd #GREEK SMALL LETTER NU
0xe8 0x03be #GREEK SMALL LETTER XI
0xe9 0x03bf #GREEK SMALL LETTER OMICRON
0xea 0x03c0 #GREEK SMALL LETTER PI
0xeb 0x03c1 #GREEK SMALL LETTER RHO
0xec 0x03c3 #GREEK SMALL LETTER SIGMA
0xed 0x03c2 #GREEK SMALL LETTER FINAL SIGMA
0xee 0x03c4 #GREEK SMALL LETTER TAU
0xef 0x0384 #GREEK TONOS
0xf0 0x00ad #SOFT HYPHEN
0xf1 0x00b1 #PLUS-MINUS SIGN
0xf2 0x03c5 #GREEK SMALL LETTER UPSILON
0xf3 0x03c6 #GREEK SMALL LETTER PHI
0xf4 0x03c7 #GREEK SMALL LETTER CHI
0xf5 0x00a7 #SECTION SIGN
0xf6 0x03c8 #GREEK SMALL LETTER PSI
0xf7 0x0385 #GREEK DIALYTIKA TONOS
0xf8 0x00b0 #DEGREE SIGN
0xf9 0x00a8 #DIAERESIS
0xfa 0x03c9 #GREEK SMALL LETTER OMEGA
0xfb 0x03cb #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xfc 0x03b0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xfd 0x03ce #GREEK SMALL LETTER OMEGA WITH TONOS
0xfe 0x25a0 #BLACK SQUARE
0xff 0x00a0 #NO-BREAK SPACE


275
unicode/vendors/micsft/pc/cp874.txt vendored Normal file
View File

@@ -0,0 +1,275 @@
#
# Name: cp874_DOSThai to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp874_DOSThai code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp874_DOSThai order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0a 0x000a #LINE FEED
0x0b 0x000b #VERTICAL TABULATION
0x0c 0x000c #FORM FEED
0x0d 0x000d #CARRIAGE RETURN
0x0e 0x000e #SHIFT OUT
0x0f 0x000f #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1a 0x001a #SUBSTITUTE
0x1b 0x001b #ESCAPE
0x1c 0x001c #FILE SEPARATOR
0x1d 0x001d #GROUP SEPARATOR
0x1e 0x001e #RECORD SEPARATOR
0x1f 0x001f #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2a 0x002a #ASTERISK
0x2b 0x002b #PLUS SIGN
0x2c 0x002c #COMMA
0x2d 0x002d #HYPHEN-MINUS
0x2e 0x002e #FULL STOP
0x2f 0x002f #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3a 0x003a #COLON
0x3b 0x003b #SEMICOLON
0x3c 0x003c #LESS-THAN SIGN
0x3d 0x003d #EQUALS SIGN
0x3e 0x003e #GREATER-THAN SIGN
0x3f 0x003f #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4a 0x004a #LATIN CAPITAL LETTER J
0x4b 0x004b #LATIN CAPITAL LETTER K
0x4c 0x004c #LATIN CAPITAL LETTER L
0x4d 0x004d #LATIN CAPITAL LETTER M
0x4e 0x004e #LATIN CAPITAL LETTER N
0x4f 0x004f #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5a 0x005a #LATIN CAPITAL LETTER Z
0x5b 0x005b #LEFT SQUARE BRACKET
0x5c 0x005c #REVERSE SOLIDUS
0x5d 0x005d #RIGHT SQUARE BRACKET
0x5e 0x005e #CIRCUMFLEX ACCENT
0x5f 0x005f #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6a 0x006a #LATIN SMALL LETTER J
0x6b 0x006b #LATIN SMALL LETTER K
0x6c 0x006c #LATIN SMALL LETTER L
0x6d 0x006d #LATIN SMALL LETTER M
0x6e 0x006e #LATIN SMALL LETTER N
0x6f 0x006f #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7a 0x007a #LATIN SMALL LETTER Z
0x7b 0x007b #LEFT CURLY BRACKET
0x7c 0x007c #VERTICAL LINE
0x7d 0x007d #RIGHT CURLY BRACKET
0x7e 0x007e #TILDE
0x7f 0x007f #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 #UNDEFINED
0x83 #UNDEFINED
0x84 #UNDEFINED
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 #UNDEFINED
0x87 #UNDEFINED
0x88 #UNDEFINED
0x89 #UNDEFINED
0x8a #UNDEFINED
0x8b #UNDEFINED
0x8c #UNDEFINED
0x8d #UNDEFINED
0x8e #UNDEFINED
0x8f #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #SINGLE TURNED COMMA QUOTATION MARK
0x92 0x2019 #SINGLE COMMA QUOTATION MARK
0x93 0x201c #DOUBLE TURNED COMMA QUOTATION MARK
0x94 0x201d #DOUBLE COMMA QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 #UNDEFINED
0x9a #UNDEFINED
0x9b #UNDEFINED
0x9c #UNDEFINED
0x9d #UNDEFINED
0x9e #UNDEFINED
0x9f #UNDEFINED
0xa0 0x00a0 #NON-BREAKING SPACE
0xa1 0x0e01 #THAI LETTER KO KAI
0xa2 0x0e02 #THAI LETTER KHO KHAI
0xa3 0x0e03 #THAI LETTER KHO KHUAT
0xa4 0x0e04 #THAI LETTER KHO KHWAI
0xa5 0x0e05 #THAI LETTER KHO KHON
0xa6 0x0e06 #THAI LETTER KHO RAKHANG
0xa7 0x0e07 #THAI LETTER NGO NGU
0xa8 0x0e08 #THAI LETTER CHO CHAN
0xa9 0x0e09 #THAI LETTER CHO CHING
0xaa 0x0e0a #THAI LETTER CHO CHANG
0xab 0x0e0b #THAI LETTER SO SO
0xac 0x0e0c #THAI LETTER CHO CHOE
0xad 0x0e0d #THAI LETTER YO YING
0xae 0x0e0e #THAI LETTER DO CHADA
0xaf 0x0e0f #THAI LETTER TO PATAK
0xb0 0x0e10 #THAI LETTER THO THAN
0xb1 0x0e11 #THAI LETTER THO NANGMONTHO
0xb2 0x0e12 #THAI LETTER THO PHUTHAO
0xb3 0x0e13 #THAI LETTER NO NEN
0xb4 0x0e14 #THAI LETTER DO DEK
0xb5 0x0e15 #THAI LETTER TO TAO
0xb6 0x0e16 #THAI LETTER THO THUNG
0xb7 0x0e17 #THAI LETTER THO THAHAN
0xb8 0x0e18 #THAI LETTER THO THONG
0xb9 0x0e19 #THAI LETTER NO NU
0xba 0x0e1a #THAI LETTER BO BAIMAI
0xbb 0x0e1b #THAI LETTER PO PLA
0xbc 0x0e1c #THAI LETTER PHO PHUNG
0xbd 0x0e1d #THAI LETTER FO FA
0xbe 0x0e1e #THAI LETTER PHO PHAN
0xbf 0x0e1f #THAI LETTER FO FAN
0xc0 0x0e20 #THAI LETTER PHO SAMPHAO
0xc1 0x0e21 #THAI LETTER MO MA
0xc2 0x0e22 #THAI LETTER YO YAK
0xc3 0x0e23 #THAI LETTER RO RUA
0xc4 0x0e24 #THAI LETTER RU
0xc5 0x0e25 #THAI LETTER LO LING
0xc6 0x0e26 #THAI LETTER LU
0xc7 0x0e27 #THAI LETTER WO WAEN
0xc8 0x0e28 #THAI LETTER SO SALA
0xc9 0x0e29 #THAI LETTER SO RUSI
0xca 0x0e2a #THAI LETTER SO SUA
0xcb 0x0e2b #THAI LETTER HO HIP
0xcc 0x0e2c #THAI LETTER LO CHULA
0xcd 0x0e2d #THAI LETTER O ANG
0xce 0x0e2e #THAI LETTER HO NOK HUK
0xcf 0x0e2f #THAI PAI YAN NOI
0xd0 0x0e30 #THAI VOWEL SIGN SARA A
0xd1 0x0e31 #THAI VOWEL SIGN MAI HAN-AKAT
0xd2 0x0e32 #THAI VOWEL SIGN SARA AA
0xd3 0x0e33 #THAI VOWEL SIGN SARA AM
0xd4 0x0e34 #THAI VOWEL SIGN SARA I
0xd5 0x0e35 #THAI VOWEL SIGN SARA II
0xd6 0x0e36 #THAI VOWEL SIGN SARA UE
0xd7 0x0e37 #THAI VOWEL SIGN SARA UEE
0xd8 0x0e38 #THAI VOWEL SIGN SARA U
0xd9 0x0e39 #THAI VOWEL SIGN SARA UU
0xda 0x0e3a #THAI VOWEL SIGN PHINTHU
0xdb #UNDEFINED
0xdc #UNDEFINED
0xdd #UNDEFINED
0xde #UNDEFINED
0xdf 0x0e3f #THAI BAHT SIGN
0xe0 0x0e40 #THAI VOWEL SIGN SARA E
0xe1 0x0e41 #THAI VOWEL SIGN SARA AE
0xe2 0x0e42 #THAI VOWEL SIGN SARA O
0xe3 0x0e43 #THAI VOWEL SIGN SARA MAI MUAN
0xe4 0x0e44 #THAI VOWEL SIGN SARA MAI MALAI
0xe5 0x0e45 #THAI LAK KHANG YAO
0xe6 0x0e46 #THAI MAI YAMOK
0xe7 0x0e47 #THAI VOWEL SIGN MAI TAI KHU
0xe8 0x0e48 #THAI TONE MAI EK
0xe9 0x0e49 #THAI TONE MAI THO
0xea 0x0e4a #THAI TONE MAI TRI
0xeb 0x0e4b #THAI TONE MAI CHATTAWA
0xec 0x0e4c #THAI THANTHAKHAT
0xed 0x0e4d #THAI NIKKHAHIT
0xee 0x0e4e #THAI YAMAKKAN
0xef 0x0e4f #THAI FONGMAN
0xf0 0x0e50 #THAI DIGIT 0
0xf1 0x0e51 #THAI DIGIT 1
0xf2 0x0e52 #THAI DIGIT 2
0xf3 0x0e53 #THAI DIGIT 3
0xf4 0x0e54 #THAI DIGIT 4
0xf5 0x0e55 #THAI DIGIT 5
0xf6 0x0e56 #THAI DIGIT 6
0xf7 0x0e57 #THAI DIGIT 7
0xf8 0x0e58 #THAI DIGIT 8
0xf9 0x0e59 #THAI DIGIT 9
0xfa 0x0e5a #THAI ANGKHANKHU
0xfb 0x0e5b #THAI KHOMUT
0xfc #UNDEFINED
0xfd #UNDEFINED
0xfe #UNDEFINED
0xff #UNDEFINED


View File

@@ -0,0 +1,275 @@
#
# Name: cp1250_WinLatin2 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1250_WinLatin2 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1250_WinLatin2 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 #UNDEFINED
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 #UNDEFINED
0x89 0x2030 #PER MILLE SIGN
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON
0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON
0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADE MARK SIGN
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE
0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON
0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON
0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x02C7 #CARON
0xA2 0x02D8 #BREVE
0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC #UNDEFINED
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x02DB #OGONEK
0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE
0xB4 0x00B4 #ACUTE ACCENT
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #CEDILLA
0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK
0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON
0xBD 0x02DD #DOUBLE ACUTE ACCENT
0xBE 0x013E #LATIN SMALL LETTER L WITH CARON
0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON
0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON
0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE
0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x011B #LATIN SMALL LETTER E WITH CARON
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x010F #LATIN SMALL LETTER D WITH CARON
0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON
0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
0xFF 0x02D9 #DOT ABOVE


View File

@@ -0,0 +1,275 @@
#
# Name: cp1251_WinCyrillic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1251_WinCyrillic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1251_WinCyrillic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 0x0402 #CYRILLIC CAPITAL LETTER DJE
0x81 0x0403 #CYRILLIC CAPITAL LETTER GJE
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 0x0453 #CYRILLIC SMALL LETTER GJE
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 #UNDEFINED
0x89 0x2030 #PER MILLE SIGN
0x8A 0x0409 #CYRILLIC CAPITAL LETTER LJE
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x040A #CYRILLIC CAPITAL LETTER NJE
0x8D 0x040C #CYRILLIC CAPITAL LETTER KJE
0x8E 0x040B #CYRILLIC CAPITAL LETTER TSHE
0x8F 0x040F #CYRILLIC CAPITAL LETTER DZHE
0x90 0x0452 #CYRILLIC SMALL LETTER DJE
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADE MARK SIGN
0x9A 0x0459 #CYRILLIC SMALL LETTER LJE
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x045A #CYRILLIC SMALL LETTER NJE
0x9D 0x045C #CYRILLIC SMALL LETTER KJE
0x9E 0x045B #CYRILLIC SMALL LETTER TSHE
0x9F 0x045F #CYRILLIC SMALL LETTER DZHE
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x040E #CYRILLIC CAPITAL LETTER SHORT U
0xA2 0x045E #CYRILLIC SMALL LETTER SHORT U
0xA3 0x0408 #CYRILLIC CAPITAL LETTER JE
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x0401 #CYRILLIC CAPITAL LETTER IO
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x0407 #CYRILLIC CAPITAL LETTER YI
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0xB3 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0xB4 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x0451 #CYRILLIC SMALL LETTER IO
0xB9 0x2116 #NUMERO SIGN
0xBA 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x0458 #CYRILLIC SMALL LETTER JE
0xBD 0x0405 #CYRILLIC CAPITAL LETTER DZE
0xBE 0x0455 #CYRILLIC SMALL LETTER DZE
0xBF 0x0457 #CYRILLIC SMALL LETTER YI
0xC0 0x0410 #CYRILLIC CAPITAL LETTER A
0xC1 0x0411 #CYRILLIC CAPITAL LETTER BE
0xC2 0x0412 #CYRILLIC CAPITAL LETTER VE
0xC3 0x0413 #CYRILLIC CAPITAL LETTER GHE
0xC4 0x0414 #CYRILLIC CAPITAL LETTER DE
0xC5 0x0415 #CYRILLIC CAPITAL LETTER IE
0xC6 0x0416 #CYRILLIC CAPITAL LETTER ZHE
0xC7 0x0417 #CYRILLIC CAPITAL LETTER ZE
0xC8 0x0418 #CYRILLIC CAPITAL LETTER I
0xC9 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
0xCA 0x041A #CYRILLIC CAPITAL LETTER KA
0xCB 0x041B #CYRILLIC CAPITAL LETTER EL
0xCC 0x041C #CYRILLIC CAPITAL LETTER EM
0xCD 0x041D #CYRILLIC CAPITAL LETTER EN
0xCE 0x041E #CYRILLIC CAPITAL LETTER O
0xCF 0x041F #CYRILLIC CAPITAL LETTER PE
0xD0 0x0420 #CYRILLIC CAPITAL LETTER ER
0xD1 0x0421 #CYRILLIC CAPITAL LETTER ES
0xD2 0x0422 #CYRILLIC CAPITAL LETTER TE
0xD3 0x0423 #CYRILLIC CAPITAL LETTER U
0xD4 0x0424 #CYRILLIC CAPITAL LETTER EF
0xD5 0x0425 #CYRILLIC CAPITAL LETTER HA
0xD6 0x0426 #CYRILLIC CAPITAL LETTER TSE
0xD7 0x0427 #CYRILLIC CAPITAL LETTER CHE
0xD8 0x0428 #CYRILLIC CAPITAL LETTER SHA
0xD9 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
0xDA 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN
0xDB 0x042B #CYRILLIC CAPITAL LETTER YERU
0xDC 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN
0xDD 0x042D #CYRILLIC CAPITAL LETTER E
0xDE 0x042E #CYRILLIC CAPITAL LETTER YU
0xDF 0x042F #CYRILLIC CAPITAL LETTER YA
0xE0 0x0430 #CYRILLIC SMALL LETTER A
0xE1 0x0431 #CYRILLIC SMALL LETTER BE
0xE2 0x0432 #CYRILLIC SMALL LETTER VE
0xE3 0x0433 #CYRILLIC SMALL LETTER GHE
0xE4 0x0434 #CYRILLIC SMALL LETTER DE
0xE5 0x0435 #CYRILLIC SMALL LETTER IE
0xE6 0x0436 #CYRILLIC SMALL LETTER ZHE
0xE7 0x0437 #CYRILLIC SMALL LETTER ZE
0xE8 0x0438 #CYRILLIC SMALL LETTER I
0xE9 0x0439 #CYRILLIC SMALL LETTER SHORT I
0xEA 0x043A #CYRILLIC SMALL LETTER KA
0xEB 0x043B #CYRILLIC SMALL LETTER EL
0xEC 0x043C #CYRILLIC SMALL LETTER EM
0xED 0x043D #CYRILLIC SMALL LETTER EN
0xEE 0x043E #CYRILLIC SMALL LETTER O
0xEF 0x043F #CYRILLIC SMALL LETTER PE
0xF0 0x0440 #CYRILLIC SMALL LETTER ER
0xF1 0x0441 #CYRILLIC SMALL LETTER ES
0xF2 0x0442 #CYRILLIC SMALL LETTER TE
0xF3 0x0443 #CYRILLIC SMALL LETTER U
0xF4 0x0444 #CYRILLIC SMALL LETTER EF
0xF5 0x0445 #CYRILLIC SMALL LETTER HA
0xF6 0x0446 #CYRILLIC SMALL LETTER TSE
0xF7 0x0447 #CYRILLIC SMALL LETTER CHE
0xF8 0x0448 #CYRILLIC SMALL LETTER SHA
0xF9 0x0449 #CYRILLIC SMALL LETTER SHCHA
0xFA 0x044A #CYRILLIC SMALL LETTER HARD SIGN
0xFB 0x044B #CYRILLIC SMALL LETTER YERU
0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN
0xFD 0x044D #CYRILLIC SMALL LETTER E
0xFE 0x044E #CYRILLIC SMALL LETTER YU
0xFF 0x044F #CYRILLIC SMALL LETTER YA


View File

@@ -0,0 +1,275 @@
#
# Name: cp1252_WinLatin1 to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1252_WinLatin1 code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1252_WinLatin1 order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0x89 0x2030 #PER MILLE SIGN
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
0x8D #UNDEFINED
0x8E #UNDEFINED
0x8F #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 0x02DC #SMALL TILDE
0x99 0x2122 #TRADE MARK SIGN
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x0153 #LATIN SMALL LIGATURE OE
0x9D #UNDEFINED
0x9E #UNDEFINED
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x00AF #MACRON
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT TWO
0xB3 0x00B3 #SUPERSCRIPT THREE
0xB4 0x00B4 #ACUTE ACCENT
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #CEDILLA
0xB9 0x00B9 #SUPERSCRIPT ONE
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
0xBD 0x00BD #VULGAR FRACTION ONE HALF
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBF 0x00BF #INVERTED QUESTION MARK
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 #LATIN CAPITAL LIGATURE AE
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x00D0 #LATIN CAPITAL LETTER ETH
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x00DE #LATIN CAPITAL LETTER THORN
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 #LATIN SMALL LIGATURE AE
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x00F0 #LATIN SMALL LETTER ETH
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x00FE #LATIN SMALL LETTER THORN
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS


View File

@@ -0,0 +1,275 @@
#
# Name: cp1253_WinGreek to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1253_WinGreek code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1253_WinGreek order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 #UNDEFINED
0x89 0x2030 #PER MILLE SIGN
0x8A #UNDEFINED
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C #UNDEFINED
0x8D #UNDEFINED
0x8E #UNDEFINED
0x8F #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADE MARK SIGN
0x9A #UNDEFINED
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C #UNDEFINED
0x9D #UNDEFINED
0x9E #UNDEFINED
0x9F #UNDEFINED
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x0385 #GREEK DIALYTIKA TONOS
0xA2 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA #UNDEFINED
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x2015 #HORIZONTAL BAR
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT TWO
0xB3 0x00B3 #SUPERSCRIPT THREE
0xB4 0x0384 #GREEK TONOS
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
0xB9 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
0xBA 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS
0xBD 0x00BD #VULGAR FRACTION ONE HALF
0xBE 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS
0xBF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS
0xC0 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0xC1 0x0391 #GREEK CAPITAL LETTER ALPHA
0xC2 0x0392 #GREEK CAPITAL LETTER BETA
0xC3 0x0393 #GREEK CAPITAL LETTER GAMMA
0xC4 0x0394 #GREEK CAPITAL LETTER DELTA
0xC5 0x0395 #GREEK CAPITAL LETTER EPSILON
0xC6 0x0396 #GREEK CAPITAL LETTER ZETA
0xC7 0x0397 #GREEK CAPITAL LETTER ETA
0xC8 0x0398 #GREEK CAPITAL LETTER THETA
0xC9 0x0399 #GREEK CAPITAL LETTER IOTA
0xCA 0x039A #GREEK CAPITAL LETTER KAPPA
0xCB 0x039B #GREEK CAPITAL LETTER LAMDA
0xCC 0x039C #GREEK CAPITAL LETTER MU
0xCD 0x039D #GREEK CAPITAL LETTER NU
0xCE 0x039E #GREEK CAPITAL LETTER XI
0xCF 0x039F #GREEK CAPITAL LETTER OMICRON
0xD0 0x03A0 #GREEK CAPITAL LETTER PI
0xD1 0x03A1 #GREEK CAPITAL LETTER RHO
0xD2 #UNDEFINED
0xD3 0x03A3 #GREEK CAPITAL LETTER SIGMA
0xD4 0x03A4 #GREEK CAPITAL LETTER TAU
0xD5 0x03A5 #GREEK CAPITAL LETTER UPSILON
0xD6 0x03A6 #GREEK CAPITAL LETTER PHI
0xD7 0x03A7 #GREEK CAPITAL LETTER CHI
0xD8 0x03A8 #GREEK CAPITAL LETTER PSI
0xD9 0x03A9 #GREEK CAPITAL LETTER OMEGA
0xDA 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0xDB 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0xDC 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS
0xDD 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS
0xDE 0x03AE #GREEK SMALL LETTER ETA WITH TONOS
0xDF 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS
0xE0 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0xE1 0x03B1 #GREEK SMALL LETTER ALPHA
0xE2 0x03B2 #GREEK SMALL LETTER BETA
0xE3 0x03B3 #GREEK SMALL LETTER GAMMA
0xE4 0x03B4 #GREEK SMALL LETTER DELTA
0xE5 0x03B5 #GREEK SMALL LETTER EPSILON
0xE6 0x03B6 #GREEK SMALL LETTER ZETA
0xE7 0x03B7 #GREEK SMALL LETTER ETA
0xE8 0x03B8 #GREEK SMALL LETTER THETA
0xE9 0x03B9 #GREEK SMALL LETTER IOTA
0xEA 0x03BA #GREEK SMALL LETTER KAPPA
0xEB 0x03BB #GREEK SMALL LETTER LAMDA
0xEC 0x03BC #GREEK SMALL LETTER MU
0xED 0x03BD #GREEK SMALL LETTER NU
0xEE 0x03BE #GREEK SMALL LETTER XI
0xEF 0x03BF #GREEK SMALL LETTER OMICRON
0xF0 0x03C0 #GREEK SMALL LETTER PI
0xF1 0x03C1 #GREEK SMALL LETTER RHO
0xF2 0x03C2 #GREEK SMALL LETTER FINAL SIGMA
0xF3 0x03C3 #GREEK SMALL LETTER SIGMA
0xF4 0x03C4 #GREEK SMALL LETTER TAU
0xF5 0x03C5 #GREEK SMALL LETTER UPSILON
0xF6 0x03C6 #GREEK SMALL LETTER PHI
0xF7 0x03C7 #GREEK SMALL LETTER CHI
0xF8 0x03C8 #GREEK SMALL LETTER PSI
0xF9 0x03C9 #GREEK SMALL LETTER OMEGA
0xFA 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA
0xFB 0x03CB #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0xFC 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS
0xFD 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS
0xFE 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS
0xFF #UNDEFINED


View File

@@ -0,0 +1,275 @@
#
# Name: cp1254_WinTurkish to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1254_WinTurkish code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1254_WinTurkish order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0x89 0x2030 #PER MILLE SIGN
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
0x8D #UNDEFINED
0x8E #UNDEFINED
0x8F #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 0x02DC #SMALL TILDE
0x99 0x2122 #TRADE MARK SIGN
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x0153 #LATIN SMALL LIGATURE OE
0x9D #UNDEFINED
0x9E #UNDEFINED
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x00AF #MACRON
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT TWO
0xB3 0x00B3 #SUPERSCRIPT THREE
0xB4 0x00B4 #ACUTE ACCENT
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #CEDILLA
0xB9 0x00B9 #SUPERSCRIPT ONE
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
0xBD 0x00BD #VULGAR FRACTION ONE HALF
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBF 0x00BF #INVERTED QUESTION MARK
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 #LATIN CAPITAL LIGATURE AE
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 #LATIN SMALL LIGATURE AE
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x0131 #LATIN SMALL LETTER DOTLESS I
0xFE 0x015F #LATIN SMALL LETTER S WITH CEDILLA
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS


View File

@@ -0,0 +1,275 @@
#
# Name: cp1255_WinHebrew to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1255_WinHebrew code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1255_WinHebrew order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE-QUOTE
0x28 0x0028 #OPENING PARENTHESIS
0x29 0x0029 #CLOSING PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #PERIOD
0x2F 0x002F #SLASH
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #OPENING SQUARE BRACKET
0x5C 0x005C #BACKSLASH
0x5D 0x005D #CLOSING SQUARE BRACKET
0x5E 0x005E #SPACING CIRCUMFLEX
0x5F 0x005F #SPACING UNDERSCORE
0x60 0x0060 #SPACING GRAVE
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #OPENING CURLY BRACKET
0x7C 0x007C #VERTICAL BAR
0x7D 0x007D #CLOSING CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #LOW SINGLE COMMA QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER SCRIPT F
0x84 0x201E #LOW DOUBLE COMMA QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX
0x89 0x2030 #PER MILLE SIGN
0x8A #UNDEFINED
0x8B 0x2039 #LEFT POINTING SINGLE GUILLEMET
0x8C #UNDEFINED
0x8D #UNDEFINED
0x8E #UNDEFINED
0x8F #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #SINGLE TURNED COMMA QUOTATION MARK
0x92 0x2019 #SINGLE COMMA QUOTATION MARK
0x93 0x201C #DOUBLE TURNED COMMA QUOTATION MARK
0x94 0x201D #DOUBLE COMMA QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 0x02DC #SPACING TILDE
0x99 0x2122 #TRADEMARK
0x9A #UNDEFINED
0x9B 0x203A #RIGHT POINTING SINGLE GUILLEMET
0x9C #UNDEFINED
0x9D #UNDEFINED
0x9E #UNDEFINED
0x9F #UNDEFINED
0xA0 0x00A0 #NON-BREAKING SPACE
0xA1 #UNDEFINED
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x20AA #NEW SHEQEL SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN VERTICAL BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #SPACING DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA #UNDEFINED
0xAB 0x00AB #LEFT POINTING GUILLEMET
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED TRADE MARK SIGN
0xAF 0x00AF #SPACING MACRON
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-OR-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT DIGIT TWO
0xB3 0x00B3 #SUPERSCRIPT DIGIT THREE
0xB4 0x00B4 #SPACING ACUTE
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PARAGRAPH SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 #UNDEFINED
0xB9 0x00B9 #SUPERSCRIPT DIGIT ONE
0xBA #UNDEFINED
0xBB 0x00BB #RIGHT POINTING GUILLEMET
0xBC 0x00BC #FRACTION ONE QUARTER
0xBD 0x00BD #FRACTION ONE HALF
0xBE 0x00BE #FRACTION THREE QUARTERS
0xBF #UNDEFINED
0xC0 0x05B0 #HEBREW POINT SHEVA
0xC1 0x05B1 #HEBREW POINT HATAF SEGOL
0xC2 0x05B2 #HEBREW POINT HATAF PATAH
0xC3 0x05B3 #HEBREW POINT HATAF QAMATS
0xC4 0x05B4 #HEBREW POINT HIRIQ
0xC5 0x05B5 #HEBREW POINT TSERE
0xC6 0x05B6 #HEBREW POINT SEGOL
0xC7 0x05B7 #HEBREW POINT PATAH
0xC8 0x05B8 #HEBREW POINT QAMATS
0xC9 0x05B9 #HEBREW POINT HOLAM
0xCA 0x05BA #HEBREW POINT
0xCB 0x05BB #HEBREW POINT QUBUTS
0xCC 0x05BC #HEBREW POINT DAGESH
0xCD 0x05BD #HEBREW POINT METEG
0xCE 0x05BE #HEBREW PUNCTUATION MAQAF
0xCF 0x05BF #HEBREW POINT RAFE
0xD0 0x05C0 #HEBREW POINT PASEQ
0xD1 0x05C1 #HEBREW POINT SHIN DOT
0xD2 0x05C2 #HEBREW POINT SIN DOT
0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ
0xD4 0x05F0 #HEBREW LETTER DOUBLE VAV
0xD5 0x05F1 #HEBREW LETTER VAV YOD
0xD6 0x05F2 #HEBREW LETTER DOUBLE YOD
0xD7 #UNDEFINED
0xD8 #UNDEFINED
0xD9 #UNDEFINED
0xDA #UNDEFINED
0xDB #UNDEFINED
0xDC #UNDEFINED
0xDD #UNDEFINED
0xDE #UNDEFINED
0xDF #UNDEFINED
0xE0 0x05D0 #HEBREW LETTER ALEF
0xE1 0x05D1 #HEBREW LETTER BET
0xE2 0x05D2 #HEBREW LETTER GIMEL
0xE3 0x05D3 #HEBREW LETTER DALET
0xE4 0x05D4 #HEBREW LETTER HE
0xE5 0x05D5 #HEBREW LETTER VAV
0xE6 0x05D6 #HEBREW LETTER ZAYIN
0xE7 0x05D7 #HEBREW LETTER HET
0xE8 0x05D8 #HEBREW LETTER TET
0xE9 0x05D9 #HEBREW LETTER YOD
0xEA 0x05DA #HEBREW LETTER FINAL KAF
0xEB 0x05DB #HEBREW LETTER KAF
0xEC 0x05DC #HEBREW LETTER LAMED
0xED 0x05DD #HEBREW LETTER FINAL MEM
0xEE 0x05DE #HEBREW LETTER MEM
0xEF 0x05DF #HEBREW LETTER FINAL NUN
0xF0 0x05E0 #HEBREW LETTER NUN
0xF1 0x05E1 #HEBREW LETTER SAMEKH
0xF2 0x05E2 #HEBREW LETTER AYIN
0xF3 0x05E3 #HEBREW LETTER FINAL PE
0xF4 0x05E4 #HEBREW LETTER PE
0xF5 0x05E5 #HEBREW LETTER FINAL TSADI
0xF6 0x05E6 #HEBREW LETTER TSADI
0xF7 0x05E7 #HEBREW LETTER QOF
0xF8 0x05E8 #HEBREW LETTER RESH
0xF9 0x05E9 #HEBREW LETTER SHIN
0xFA 0x05EA #HEBREW LETTER TAV
0xFB #UNDEFINED
0xFC #UNDEFINED
0xFD 0x200E #LEFT-TO-RIGHT MARK
0xFE 0x200F #RIGHT-TO-LEFT MARK
0xFF #UNDEFINED


View File

@@ -0,0 +1,275 @@
#
# Name: cp1256_WinArabic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1256_WinArabic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1256_WinArabic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE-QUOTE
0x28 0x0028 #OPENING PARENTHESIS
0x29 0x0029 #CLOSING PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #PERIOD
0x2F 0x002F #SLASH
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #OPENING SQUARE BRACKET
0x5C 0x005C #BACKSLASH
0x5D 0x005D #CLOSING SQUARE BRACKET
0x5E 0x005E #SPACING CIRCUMFLEX
0x5F 0x005F #SPACING UNDERSCORE
0x60 0x0060 #SPACING GRAVE
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #OPENING CURLY BRACKET
0x7C 0x007C #VERTICAL BAR
0x7D 0x007D #CLOSING CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 0x067E #ARABIC TAA WITH THREE DOTS BELOW
0x82 0x201A #LOW SINGLE COMMA QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER SCRIPT F
0x84 0x201E #LOW DOUBLE COMMA QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX
0x89 0x2030 #PER MILLE SIGN
0x8A #UNDEFINED
0x8B 0x2039 #LEFT POINTING SINGLE GUILLEMET
0x8C 0x0152 #LATIN CAPITAL LETTER O E
0x8D 0x0686 #ARABIC HAA WITH MIDDLE THREE DOTS DOWNWARD
0x8E 0x0698 #ARABIC RA WITH THREE DOTS ABOVE
0x8F #UNDEFINED
0x90 0x06AF #ARABIC GAF
0x91 0x2018 #SINGLE TURNED COMMA QUOTATION MARK
0x92 0x2019 #SINGLE COMMA QUOTATION MARK
0x93 0x201C #DOUBLE TURNED COMMA QUOTATION MARK
0x94 0x201D #DOUBLE COMMA QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADEMARK
0x9A #UNDEFINED
0x9B 0x203A #RIGHT POINTING SINGLE GUILLEMET
0x9C 0x0153 #LATIN SMALL LETTER O E
0x9D 0x200C #ZERO WIDTH NON-JOINER
0x9E 0x200D #ZERO WIDTH JOINER
0x9F #UNDEFINED
0xA0 0x00A0 #NON-BREAKING SPACE
0xA1 0x060C #ARABIC COMMA
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN VERTICAL BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #SPACING DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA #UNDEFINED
0xAB 0x00AB #LEFT POINTING GUILLEMET
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED TRADE MARK SIGN
0xAF 0x00AF #SPACING MACRON
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-OR-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT DIGIT TWO
0xB3 0x00B3 #SUPERSCRIPT DIGIT THREE
0xB4 0x00B4 #SPACING ACUTE
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PARAGRAPH SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #SPACING CEDILLA
0xB9 0x00B9 #SUPERSCRIPT DIGIT ONE
0xBA 0x061B #ARABIC SEMICOLON
0xBB 0x00BB #RIGHT POINTING GUILLEMET
0xBC 0x00BC #FRACTION ONE QUARTER
0xBD 0x00BD #FRACTION ONE HALF
0xBE 0x00BE #FRACTION THREE QUARTERS
0xBF 0x061F #ARABIC QUESTION MARK
0xC0 #UNDEFINED
0xC1 0x0621 #ARABIC LETTER HAMZAH
0xC2 0x0622 #ARABIC LETTER MADDAH ON ALEF
0xC3 0x0623 #ARABIC LETTER HAMZAH ON ALEF
0xC4 0x0624 #ARABIC LETTER HAMZAH ON WAW
0xC5 0x0625 #ARABIC LETTER HAMZAH UNDER ALEF
0xC6 0x0626 #ARABIC LETTER HAMZAH ON YA
0xC7 0x0627 #ARABIC LETTER ALEF
0xC8 0x0628 #ARABIC LETTER BAA
0xC9 0x0629 #ARABIC LETTER TAA MARBUTAH
0xCA 0x062A #ARABIC LETTER TAA
0xCB 0x062B #ARABIC LETTER THAA
0xCC 0x062C #ARABIC LETTER JEEM
0xCD 0x062D #ARABIC LETTER HAA
0xCE 0x062E #ARABIC LETTER KHAA
0xCF 0x062F #ARABIC LETTER DAL
0xD0 0x0630 #ARABIC LETTER THAL
0xD1 0x0631 #ARABIC LETTER RA
0xD2 0x0632 #ARABIC LETTER ZAIN
0xD3 0x0633 #ARABIC LETTER SEEN
0xD4 0x0634 #ARABIC LETTER SHEEN
0xD5 0x0635 #ARABIC LETTER SAD
0xD6 0x0636 #ARABIC LETTER DAD
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x0637 #ARABIC LETTER TAH
0xD9 0x0638 #ARABIC LETTER DHAH
0xDA 0x0639 #ARABIC LETTER AIN
0xDB 0x063A #ARABIC LETTER GHAIN
0xDC 0x0640 #ARABIC TATWEEL
0xDD 0x0641 #ARABIC LETTER FA
0xDE 0x0642 #ARABIC LETTER QAF
0xDF 0x0643 #ARABIC LETTER CAF
0xE0 0x00E0 #LATIN SMALL LETTER A GRAVE
0xE1 0x0644 #ARABIC LETTER LAM
0xE2 0x00E2 #LATIN SMALL LETTER A CIRCUMFLEX
0xE3 0x0645 #ARABIC LETTER MEEM
0xE4 0x0646 #ARABIC LETTER NOON
0xE5 0x0647 #ARABIC LETTER HA
0xE6 0x0648 #ARABIC LETTER WAW
0xE7 0x00E7 #LATIN SMALL LETTER C CEDILLA
0xE8 0x00E8 #LATIN SMALL LETTER E GRAVE
0xE9 0x00E9 #LATIN SMALL LETTER E ACUTE
0xEA 0x00EA #LATIN SMALL LETTER E CIRCUMFLEX
0xEB 0x00EB #LATIN SMALL LETTER E DIAERESIS
0xEC 0x0649 #ARABIC LETTER ALEF MAQSURAH
0xED 0x064A #ARABIC LETTER YA
0xEE 0x00EE #LATIN SMALL LETTER I CIRCUMFLEX
0xEF 0x00EF #LATIN SMALL LETTER I DIAERESIS
0xF0 0x064B #ARABIC FATHATAN
0xF1 0x064C #ARABIC DAMMATAN
0xF2 0x064D #ARABIC KASRATAN
0xF3 0x064E #ARABIC FATHAH
0xF4 0x00F4 #LATIN SMALL LETTER O CIRCUMFLEX
0xF5 0x064F #ARABIC DAMMAH
0xF6 0x0650 #ARABIC KASRAH
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x0651 #ARABIC SHADDAH
0xF9 0x00F9 #LATIN SMALL LETTER U GRAVE
0xFA 0x0652 #ARABIC SUKUN
0xFB 0x00FB #LATIN SMALL LETTER U CIRCUMFLEX
0xFC 0x00FC #LATIN SMALL LETTER U DIAERESIS
0xFD 0x200E #LEFT-TO-RIGHT MARK
0xFE 0x200F #RIGHT-TO-LEFT MARK
0xFF #UNDEFINED


View File

@@ -0,0 +1,275 @@
#
# Name: cp1257_WinBaltic to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1257_WinBaltic code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1257_WinBaltic order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT 0
0x31 0x0031 #DIGIT 1
0x32 0x0032 #DIGIT 2
0x33 0x0033 #DIGIT 3
0x34 0x0034 #DIGIT 4
0x35 0x0035 #DIGIT 5
0x36 0x0036 #DIGIT 6
0x37 0x0037 #DIGIT 7
0x38 0x0038 #DIGIT 8
0x39 0x0039 #DIGIT 9
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL A
0x42 0x0042 #LATIN CAPITAL B
0x43 0x0043 #LATIN CAPITAL C
0x44 0x0044 #LATIN CAPITAL D
0x45 0x0045 #LATIN CAPITAL E
0x46 0x0046 #LATIN CAPITAL F
0x47 0x0047 #LATIN CAPITAL G
0x48 0x0048 #LATIN CAPITAL H
0x49 0x0049 #LATIN CAPITAL I
0x4A 0x004A #LATIN CAPITAL J
0x4B 0x004B #LATIN CAPITAL K
0x4C 0x004C #LATIN CAPITAL L
0x4D 0x004D #LATIN CAPITAL M
0x4E 0x004E #LATIN CAPITAL N
0x4F 0x004F #LATIN CAPITAL O
0x50 0x0050 #LATIN CAPITAL P
0x51 0x0051 #LATIN CAPITAL Q
0x52 0x0052 #LATIN CAPITAL R
0x53 0x0053 #LATIN CAPITAL S
0x54 0x0054 #LATIN CAPITAL T
0x55 0x0055 #LATIN CAPITAL U
0x56 0x0056 #LATIN CAPITAL V
0x57 0x0057 #LATIN CAPITAL W
0x58 0x0058 #LATIN CAPITAL X
0x59 0x0059 #LATIN CAPITAL Y
0x5A 0x005A #LATIN CAPITAL Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #BACKSLASH
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE
0x61 0x0061 #LATIN SMALL A
0x62 0x0062 #LATIN SMALL B
0x63 0x0063 #LATIN SMALL C
0x64 0x0064 #LATIN SMALL D
0x65 0x0065 #LATIN SMALL E
0x66 0x0066 #LATIN SMALL F
0x67 0x0067 #LATIN SMALL G
0x68 0x0068 #LATIN SMALL H
0x69 0x0069 #LATIN SMALL I
0x6A 0x006A #LATIN SMALL J
0x6B 0x006B #LATIN SMALL K
0x6C 0x006C #LATIN SMALL L
0x6D 0x006D #LATIN SMALL M
0x6E 0x006E #LATIN SMALL N
0x6F 0x006F #LATIN SMALL O
0x70 0x0070 #LATIN SMALL P
0x71 0x0071 #LATIN SMALL Q
0x72 0x0072 #LATIN SMALL R
0x73 0x0073 #LATIN SMALL S
0x74 0x0074 #LATIN SMALL T
0x75 0x0075 #LATIN SMALL U
0x76 0x0076 #LATIN SMALL V
0x77 0x0077 #LATIN SMALL W
0x78 0x0078 #LATIN SMALL X
0x79 0x0079 #LATIN SMALL Y
0x7A 0x007A #LATIN SMALL Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #LOW SINGLE COMMA QUOTATION MARK
0x83 #UNDEFINED
0x84 0x201E #LOW DOUBLE COMMA QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 #UNDEFINED
0x89 0x2030 #PER MILLE SIGN
0x8A #UNDEFINED
0x8B 0x2039 #LEFT POINTING SINGLE GUILLEMENT
0x8C #UNDEFINED
0x8D 0x00A8 #DIAERESIS
0x8E 0x02C7 #HACEK
0x8F 0x00B8 #CEDILLA
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 #UNDEFINED
0x99 0x2122 #TRADE MARK SIGN
0x9A #UNDEFINED
0x9B 0x203A #RIGHT POINTING SINGLE GUILLEMENT
0x9C #UNDEFINED
0x9D 0x00AF #MACRON
0x9E 0x02DB #OGONEK
0x9F #UNDEFINED
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 #UNDEFINED
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 #UNDEFINED
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00D8 #LATIN CAPITAL O STROKE
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x0156 #LATIN CAPITAL R CEDILLA
0xAB 0x00AB #LEFT POINTING GUILLEMENT
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x00C6 #LATIN CAPITAL AE LIGATURE
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT 2
0xB3 0x00B3 #SUPERSCRIPT 3
0xB4 0x00B4 #ACUTE
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00F8 #LATIN SAMLL O STROKE
0xB9 0x00B9 #SUPERSCRIPT ONE
0xBA 0x0157 #LATIN SMALL R CEDILLA
0xBB 0x00BB #RIGHT POINTING GUILLEMENT
0xBC 0x00BC #FRACTION 1/4
0xBD 0x00BD #FRACTION 1/2
0xBE 0x00BE #FRACTION 3/4
0xBF 0x00E6 #LATIN SMALL AE LIGATURE
0xC0 0x0104 #LATIN CAPITAL A OGONEK
0xC1 0x012E #LATIN CAPITAL I OGONEK
0xC2 0x0100 #LATIN CAPITAL A MACRON
0xC3 0x0106 #LATIN CAPITAL C ACUTE
0xC4 0x00C4 #LATIN CAPITAL A DIAERESIS
0xC5 0x00C5 #LATIN CAPITAL A RING ABOVE
0xC6 0x0118 #LATIN CAPITAL E OGONEK
0xC7 0x0112 #LATIN CAPITAL E MACRON
0xC8 0x010C #LATIN CAPITAL C HACEK
0xC9 0x00C9 #LATIN CAPITAL E ACUTE
0xCA 0x0179 #LATIN CAPITAL Z ACUTE
0xCB 0x0116 #LATIN CAPITAL E DOT ABOVE
0xCC 0x0122 #LATIN CAPITAL G CEDILLA
0xCD 0x0136 #LATIN CAPITAL K CEDILLA
0xCE 0x012A #LATIN CAPITAL I MACRON
0xCF 0x013B #LATIN CAPITAL L CEDILLA
0xD0 0x0160 #LATIN CAPITAL S HACEK
0xD1 0x0143 #LATIN CAPITAL N ACUTE
0xD2 0x0145 #LATIN CAPITAL N CEDILLA
0xD3 0x00D3 #LATIN CAPITAL O ACUTE
0xD4 0x014C #LATIN CAPITAL O MACRON
0xD5 0x00D5 #LATIN CAPITAL O TILDE
0xD6 0x00D6 #LATIN CAPITAL O DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x0172 #LATIN CAPITAL U OGONEK
0xD9 0x0141 #LATIN CAPITAL L STROKE
0xDA 0x015A #LATIN CAPITAL S ACUTE
0xDB 0x016A #LATIN CAPITAL U MACRON
0xDC 0x00DC #LATIN CAPITAL U DIAERESIS
0xDD 0x017B #LATIN CAPITAL Z DOT ABOVE
0xDE 0x017D #LATIN CAPITAL Z HACEK
0xDF 0x00DF #LATIN SMALL SHARP SS
0xE0 0x0105 #LATIN SMALL A OGONEK
0xE1 0x012F #LATIN SMALL I OGONEK
0xE2 0x0101 #LATIN SMALL A MACRON
0xE3 0x0107 #LATIN SMALL C ACUTE
0xE4 0x00E4 #LATIN SMALL A DIAERESIS
0xE5 0x00E5 #LATIN SMALL A RING ABOVE
0xE6 0x0119 #LATIN SMALL E OGONEK
0xE7 0x0113 #LATIN SMALL E MACRON
0xE8 0x010D #LATIN SMALL C HACEK
0xE9 0x00E9 #LATIN SMALL E ACUTE
0xEA 0x017A #LATIN SMALL Z ACUTE
0xEB 0x0117 #LATIN SMALL E DOT ABOVE
0xEC 0x0123 #LATIN SMALL G CEDILLA
0xED 0x0137 #LATIN SMALL K CEDILLA
0xEE 0x012B #LATIN SMALL I MACRON
0xEF 0x013C #LATIN SMALL L CEDILLA
0xF0 0x0161 #LATIN SMALL S HACEK
0xF1 0x0144 #LATIN SMALL N ACUTE
0xF2 0x0146 #LATIN SMALL N CEDILLA
0xF3 0x00F3 #LATIN SMALL O ACUTE
0xF4 0x014D #LATIN SMALL O MACRON
0xF5 0x00F5 #LATIN SMALL O TILDE
0xF6 0x00F6 #LATIN SMALL O DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x0173 #LATIN SMALL U OGONEK
0xF9 0x0142 #LATIN SMALL L STROKE
0xFA 0x015B #LATIN SMALL S ACUTE
0xFB 0x016B #LATIN SMALL U MACRON
0xFC 0x00FC #LATIN SMALL U DIAERESIS
0xFD 0x017C #LATIN SMALL Z DOT ABOVE
0xFE 0x017E #LATIN SMALL Z HACEK
0xFF 0x02D9 #DOT ABOVE


View File

@@ -0,0 +1,275 @@
#
# Name: cp1258_WinVietnamese to Unicode table
# Unicode version: 2.0
# Table version: 2.00
# Table format: Format A
# Date: 04/24/96
# Authors: Lori Brownell <loribr@microsoft.com>
# K.D. Chang <a-kchang@microsoft.com>
# General notes: none
#
# Format: Three tab-separated columns
# Column #1 is the cp1258_WinVietnamese code (in hex)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 is the Unicode name (follows a comment sign, '#')
#
# The entries are in cp1258_WinVietnamese order
#
0x00 0x0000 #NULL
0x01 0x0001 #START OF HEADING
0x02 0x0002 #START OF TEXT
0x03 0x0003 #END OF TEXT
0x04 0x0004 #END OF TRANSMISSION
0x05 0x0005 #ENQUIRY
0x06 0x0006 #ACKNOWLEDGE
0x07 0x0007 #BELL
0x08 0x0008 #BACKSPACE
0x09 0x0009 #HORIZONTAL TABULATION
0x0A 0x000A #LINE FEED
0x0B 0x000B #VERTICAL TABULATION
0x0C 0x000C #FORM FEED
0x0D 0x000D #CARRIAGE RETURN
0x0E 0x000E #SHIFT OUT
0x0F 0x000F #SHIFT IN
0x10 0x0010 #DATA LINK ESCAPE
0x11 0x0011 #DEVICE CONTROL ONE
0x12 0x0012 #DEVICE CONTROL TWO
0x13 0x0013 #DEVICE CONTROL THREE
0x14 0x0014 #DEVICE CONTROL FOUR
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
0x16 0x0016 #SYNCHRONOUS IDLE
0x17 0x0017 #END OF TRANSMISSION BLOCK
0x18 0x0018 #CANCEL
0x19 0x0019 #END OF MEDIUM
0x1A 0x001A #SUBSTITUTE
0x1B 0x001B #ESCAPE
0x1C 0x001C #FILE SEPARATOR
0x1D 0x001D #GROUP SEPARATOR
0x1E 0x001E #RECORD SEPARATOR
0x1F 0x001F #UNIT SEPARATOR
0x20 0x0020 #SPACE
0x21 0x0021 #EXCLAMATION MARK
0x22 0x0022 #QUOTATION MARK
0x23 0x0023 #NUMBER SIGN
0x24 0x0024 #DOLLAR SIGN
0x25 0x0025 #PERCENT SIGN
0x26 0x0026 #AMPERSAND
0x27 0x0027 #APOSTROPHE
0x28 0x0028 #LEFT PARENTHESIS
0x29 0x0029 #RIGHT PARENTHESIS
0x2A 0x002A #ASTERISK
0x2B 0x002B #PLUS SIGN
0x2C 0x002C #COMMA
0x2D 0x002D #HYPHEN-MINUS
0x2E 0x002E #FULL STOP
0x2F 0x002F #SOLIDUS
0x30 0x0030 #DIGIT ZERO
0x31 0x0031 #DIGIT ONE
0x32 0x0032 #DIGIT TWO
0x33 0x0033 #DIGIT THREE
0x34 0x0034 #DIGIT FOUR
0x35 0x0035 #DIGIT FIVE
0x36 0x0036 #DIGIT SIX
0x37 0x0037 #DIGIT SEVEN
0x38 0x0038 #DIGIT EIGHT
0x39 0x0039 #DIGIT NINE
0x3A 0x003A #COLON
0x3B 0x003B #SEMICOLON
0x3C 0x003C #LESS-THAN SIGN
0x3D 0x003D #EQUALS SIGN
0x3E 0x003E #GREATER-THAN SIGN
0x3F 0x003F #QUESTION MARK
0x40 0x0040 #COMMERCIAL AT
0x41 0x0041 #LATIN CAPITAL LETTER A
0x42 0x0042 #LATIN CAPITAL LETTER B
0x43 0x0043 #LATIN CAPITAL LETTER C
0x44 0x0044 #LATIN CAPITAL LETTER D
0x45 0x0045 #LATIN CAPITAL LETTER E
0x46 0x0046 #LATIN CAPITAL LETTER F
0x47 0x0047 #LATIN CAPITAL LETTER G
0x48 0x0048 #LATIN CAPITAL LETTER H
0x49 0x0049 #LATIN CAPITAL LETTER I
0x4A 0x004A #LATIN CAPITAL LETTER J
0x4B 0x004B #LATIN CAPITAL LETTER K
0x4C 0x004C #LATIN CAPITAL LETTER L
0x4D 0x004D #LATIN CAPITAL LETTER M
0x4E 0x004E #LATIN CAPITAL LETTER N
0x4F 0x004F #LATIN CAPITAL LETTER O
0x50 0x0050 #LATIN CAPITAL LETTER P
0x51 0x0051 #LATIN CAPITAL LETTER Q
0x52 0x0052 #LATIN CAPITAL LETTER R
0x53 0x0053 #LATIN CAPITAL LETTER S
0x54 0x0054 #LATIN CAPITAL LETTER T
0x55 0x0055 #LATIN CAPITAL LETTER U
0x56 0x0056 #LATIN CAPITAL LETTER V
0x57 0x0057 #LATIN CAPITAL LETTER W
0x58 0x0058 #LATIN CAPITAL LETTER X
0x59 0x0059 #LATIN CAPITAL LETTER Y
0x5A 0x005A #LATIN CAPITAL LETTER Z
0x5B 0x005B #LEFT SQUARE BRACKET
0x5C 0x005C #REVERSE SOLIDUS
0x5D 0x005D #RIGHT SQUARE BRACKET
0x5E 0x005E #CIRCUMFLEX ACCENT
0x5F 0x005F #LOW LINE
0x60 0x0060 #GRAVE ACCENT
0x61 0x0061 #LATIN SMALL LETTER A
0x62 0x0062 #LATIN SMALL LETTER B
0x63 0x0063 #LATIN SMALL LETTER C
0x64 0x0064 #LATIN SMALL LETTER D
0x65 0x0065 #LATIN SMALL LETTER E
0x66 0x0066 #LATIN SMALL LETTER F
0x67 0x0067 #LATIN SMALL LETTER G
0x68 0x0068 #LATIN SMALL LETTER H
0x69 0x0069 #LATIN SMALL LETTER I
0x6A 0x006A #LATIN SMALL LETTER J
0x6B 0x006B #LATIN SMALL LETTER K
0x6C 0x006C #LATIN SMALL LETTER L
0x6D 0x006D #LATIN SMALL LETTER M
0x6E 0x006E #LATIN SMALL LETTER N
0x6F 0x006F #LATIN SMALL LETTER O
0x70 0x0070 #LATIN SMALL LETTER P
0x71 0x0071 #LATIN SMALL LETTER Q
0x72 0x0072 #LATIN SMALL LETTER R
0x73 0x0073 #LATIN SMALL LETTER S
0x74 0x0074 #LATIN SMALL LETTER T
0x75 0x0075 #LATIN SMALL LETTER U
0x76 0x0076 #LATIN SMALL LETTER V
0x77 0x0077 #LATIN SMALL LETTER W
0x78 0x0078 #LATIN SMALL LETTER X
0x79 0x0079 #LATIN SMALL LETTER Y
0x7A 0x007A #LATIN SMALL LETTER Z
0x7B 0x007B #LEFT CURLY BRACKET
0x7C 0x007C #VERTICAL LINE
0x7D 0x007D #RIGHT CURLY BRACKET
0x7E 0x007E #TILDE
0x7F 0x007F #DELETE
0x80 #UNDEFINED
0x81 #UNDEFINED
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
0x85 0x2026 #HORIZONTAL ELLIPSIS
0x86 0x2020 #DAGGER
0x87 0x2021 #DOUBLE DAGGER
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
0x89 0x2030 #PER MILLE SIGN
0x8A #UNDEFINED
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
0x8D #UNDEFINED
0x8E #UNDEFINED
0x8F #UNDEFINED
0x90 #UNDEFINED
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
0x95 0x2022 #BULLET
0x96 0x2013 #EN DASH
0x97 0x2014 #EM DASH
0x98 0x02DC #SMALL TILDE
0x99 0x2122 #TRADE MARK SIGN
0x9A #UNDEFINED
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x9C 0x0153 #LATIN SMALL LIGATURE OE
0x9D #UNDEFINED
0x9E #UNDEFINED
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
0xA0 0x00A0 #NO-BREAK SPACE
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
0xA2 0x00A2 #CENT SIGN
0xA3 0x00A3 #POUND SIGN
0xA4 0x00A4 #CURRENCY SIGN
0xA5 0x00A5 #YEN SIGN
0xA6 0x00A6 #BROKEN BAR
0xA7 0x00A7 #SECTION SIGN
0xA8 0x00A8 #DIAERESIS
0xA9 0x00A9 #COPYRIGHT SIGN
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x00AC #NOT SIGN
0xAD 0x00AD #SOFT HYPHEN
0xAE 0x00AE #REGISTERED SIGN
0xAF 0x00AF #MACRON
0xB0 0x00B0 #DEGREE SIGN
0xB1 0x00B1 #PLUS-MINUS SIGN
0xB2 0x00B2 #SUPERSCRIPT TWO
0xB3 0x00B3 #SUPERSCRIPT THREE
0xB4 0x00B4 #ACUTE ACCENT
0xB5 0x00B5 #MICRO SIGN
0xB6 0x00B6 #PILCROW SIGN
0xB7 0x00B7 #MIDDLE DOT
0xB8 0x00B8 #CEDILLA
0xB9 0x00B9 #SUPERSCRIPT ONE
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
0xBD 0x00BD #VULGAR FRACTION ONE HALF
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
0xBF 0x00BF #INVERTED QUESTION MARK
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
0xC6 0x00C6 #LATIN CAPITAL LIGATURE AE
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
0xCC 0x0340 #NON-SPACING GRAVE TONE MARK
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x0110 #LATIN CAPITAL LETTER D BAR
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
0xD2 0x0309 #COMBINING HOOK ABOVE
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x00D7 #MULTIPLICATION SIGN
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN
0xDE 0x0303 #COMBINING TILDE
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
0xE6 0x00E6 #LATIN SMALL LIGATURE AE
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
0xEC 0x0341 #NON-SPACING ACUTE TONE MARK
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x0111 #LATIN SMALL LETTER D BAR
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
0xF2 0x0323 #COMBINING DOT BELOW
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x00F7 #DIVISION SIGN
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
0xFD 0x01B0 #LATIN SMALL LETTER U WITH HORN
0xFE 0x20AB #DONG SIGN
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS


7999
unicode/vendors/micsft/windows/cp932.txt vendored Normal file

File diff suppressed because it is too large Load Diff

22066
unicode/vendors/micsft/windows/cp936.txt vendored Normal file

File diff suppressed because it is too large Load Diff

17321
unicode/vendors/micsft/windows/cp949.txt vendored Normal file

File diff suppressed because it is too large Load Diff

13777
unicode/vendors/micsft/windows/cp950.txt vendored Normal file

File diff suppressed because it is too large Load Diff

90
unicode/vendors/misc/ibmgraph.txt vendored Normal file
View File

@@ -0,0 +1,90 @@
#
# Name: IBM PC memory-mapped video graphics to Unicode
# Unicode version: 2.0
# Table version: 1.0
# Table format: Format A
# Date: 21-May-96
# Authors: Ken Whistler <kenw@sybase.com>
#
# Copyright (c) 1996 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic or optical media by Unicode, Inc.,
# the sole remedy for any claim will be exchange of defective media
# within 90 days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# IBM PC memory-mapped video graphics map into Unicode. These are
# the characters commonly seen in positions 0x01..0x1F and 0x7F in
# IBM PC code pages (e.g. code page 437, 850, etc.)
#
# Format: Four tab-separated columns
# Column #1 is the Unicode value (in hex as XXXX)
# Column #2 is the general IBM PC code page values
# for 0x01..0x1F, 0x7F (in hex as XX). For completeness,
# Unicode values which only appear as memory-mapped
# video graphics in code page 864 are shown with their
# standard PC code page values here as well.
# Column #3 is specific to IBM PC code page 864 (Arabic)
# Column #4 the Unicode name (follows a comment sign, '#')
#
# The entries are in Unicode order.
#
# Any comments or problems, contact <kenw@sybase.com>.
# This table is provided by The Unicode Consortium and is
# not an IBM-supplied mapping.
#
00A7 15 15 # SECTION SIGN
00B6 14 14 # PILCROW SIGN
2022 07 -- # BULLET
203C 13 13 # DOUBLE EXCLAMATION MARK
2190 1B 1B # LEFTWARDS ARROW
2191 18 18 # UPWARDS ARROW
2192 1A 1A # RIGHTWARDS ARROW
2193 19 19 # DOWNWARDS ARROW
2194 1D 1D # LEFT RIGHT ARROW
2195 12 12 # UP DOWN ARROW
21A8 17 17 # UP DOWN ARROW WITH BASE
221F 1C 1C # RIGHT ANGLE
2302 7F 7F # HOUSE
2550 CD 05 # BOX DRAWINGS DOUBLE HORIZONTAL
2551 BA 06 # BOX DRAWINGS DOUBLE VERTICAL
2554 C9 0D # BOX DRAWINGS DOUBLE DOWN AND RIGHT
2557 BB 0C # BOW DRAWINGS DOUBLE DOWN AND LEFT
255A C8 0E # BOX DRAWINGS DOUBLE UP AND RIGHT
255D BC 0F # BOX DRAWINGS DOUBLE UP AND LEFT
2560 CC 0A # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
2563 B9 08 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
2566 CB 09 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
2569 CA 0B # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
256C CE 07 # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
25AC 16 16 # BLACK RECTANGLE
25B2 1E 1E # BLACK UP-POINTING TRIANGLE
25BA 10 10 # BLACK RIGHT-POINTING POINTER
25BC 1F 1F # BLACK DOWN-POINTING TRIANGLE
25C4 11 11 # BLACK LEFT-POINTING POINTER
25CB 09 -- # WHITE CIRCLE
25D8 08 -- # INVERSE BULLET
25D9 0A -- # INVERSE WHITE CIRCLE
263A 01 01 # WHITE SMILING FACE
263B 02 -- # BLACK SMILING FACE
263C 0F 04 # WHITE SUN WITH RAYS
2640 0C -- # FEMALE SIGN
2642 0B -- # MALE SIGN
2660 06 -- # BLACK SPADE SUIT
2663 05 -- # BLACK CLUB SUIT
2665 03 -- # BLACK HEART SUIT
2666 04 -- # BLACK DIAMOND SUIT
266A 0D 02 # EIGHTH NOTE
266B 0E 03 # BEAMED EIGHTH NOTES

168
unicode/vendors/next/nextstep.txt vendored Normal file
View File

@@ -0,0 +1,168 @@
#
# Name: NextStep Encoding to Unicode
# Unicode version: 1.1
# Table version: 0.1
# Table format: Format A
# Date: 14 February 1995
# Authors: Rick McGowan (rick@unicode.org)
#
# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# NextStep Encoding characters map into Unicode. Since the first
# 128 characters (0x0 - 0x7f) are identical to ASCII and Unicode,
# this table only maps the NextStep range from 0x80 - 0xFF.
#
# Format: Three tab-separated columns
# Column #1 is the NextStep code (in hex as 0xXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 NextStep name, Unicode name (follows a comment sign, '#')
#
# The entries are in NextStep order
#
# Any comments or problems, contact rick@unicode.org
#
0x80 0x00a0 # NO-BREAK SPACE
0x81 0x00c0 # LATIN CAPITAL LETTER A WITH GRAVE
0x82 0x00c1 # LATIN CAPITAL LETTER A WITH ACUTE
0x83 0x00c2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x84 0x00c3 # LATIN CAPITAL LETTER A WITH TILDE
0x85 0x00c4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0x86 0x00c5 # LATIN CAPITAL LETTER A WITH RING
0x87 0x00c7 # LATIN CAPITAL LETTER C WITH CEDILLA
0x88 0x00c8 # LATIN CAPITAL LETTER E WITH GRAVE
0x89 0x00c9 # LATIN CAPITAL LETTER E WITH ACUTE
0x8a 0x00ca # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x8b 0x00cb # LATIN CAPITAL LETTER E WITH DIAERESIS
0x8c 0x00cc # LATIN CAPITAL LETTER I WITH GRAVE
0x8d 0x00cd # LATIN CAPITAL LETTER I WITH ACUTE
0x8e 0x00ce # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x8f 0x00cf # LATIN CAPITAL LETTER I WITH DIAERESIS
0x90 0x00d0 # LATIN CAPITAL LETTER ETH
0x91 0x00d1 # LATIN CAPITAL LETTER N WITH TILDE
0x92 0x00d2 # LATIN CAPITAL LETTER O WITH GRAVE
0x93 0x00d3 # LATIN CAPITAL LETTER O WITH ACUTE
0x94 0x00d4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x95 0x00d5 # LATIN CAPITAL LETTER O WITH TILDE
0x96 0x00d6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0x97 0x00d9 # LATIN CAPITAL LETTER U WITH GRAVE
0x98 0x00da # LATIN CAPITAL LETTER U WITH ACUTE
0x99 0x00db # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x9a 0x00dc # LATIN CAPITAL LETTER U WITH DIAERESIS
0x9b 0x00dd # LATIN CAPITAL LETTER Y WITH ACUTE
0x9c 0x00de # LATIN CAPITAL LETTER THORN
0x9d 0x00b5 # MICRO SIGN
0x9e 0x00d7 # MULTIPLICATION SIGN
0x9f 0x00f7 # DIVISION SIGN
0xa0 0x00a9 # COPYRIGHT SIGN
0xa1 0x00a1 # INVERTED EXCLAMATION MARK
0xa2 0x00a2 # CENT SIGN
0xa3 0x00a3 # POUND SIGN
0xa4 0x2044 # FRACTION SLASH
0xa5 0x00a5 # YEN SIGN
0xa6 0x0192 # LATIN SMALL LETTER F WITH HOOK
0xa7 0x00a7 # SECTION SIGN
0xa8 0x00a4 # CURRENCY SIGN
0xa9 0x2019 # RIGHT SINGLE QUOTATION MARK
0xaa 0x201c # LEFT DOUBLE QUOTATION MARK
0xab 0x00ab # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xac 0x2039 # LATIN SMALL LETTER
0xad 0x203a # LATIN SMALL LETTER
0xae 0xfb01 # LATIN SMALL LIGATURE FI
0xaf 0xfb02 # LATIN SMALL LIGATURE FL
0xb0 0x00ae # REGISTERED SIGN
0xb1 0x2013 # EN DASH
0xb2 0x2020 # DAGGER
0xb3 0x2021 # DOUBLE DAGGER
0xb4 0x00b7 # MIDDLE DOT
0xb5 0x00a6 # BROKEN BAR
0xb6 0x00b6 # PILCROW SIGN
0xb7 0x2022 # BULLET
0xb8 0x201a # SINGLE LOW-9 QUOTATION MARK
0xb9 0x201e # DOUBLE LOW-9 QUOTATION MARK
0xba 0x201d # RIGHT DOUBLE QUOTATION MARK
0xbb 0x00bb # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xbc 0x2026 # HORIZONTAL ELLIPSIS
0xbd 0x2030 # PER MILLE SIGN
0xbe 0x00ac # NOT SIGN
0xbf 0x00bf # INVERTED QUESTION MARK
0xc0 0x00b9 # SUPERSCRIPT ONE
0xc1 0x02cb # MODIFIER LETTER GRAVE ACCENT
0xc2 0x00b4 # ACUTE ACCENT
0xc3 0x02c6 # MODIFIER LETTER CIRCUMFLEX ACCENT
0xc4 0x02dc # SMALL TILDE
0xc5 0x00af # MACRON
0xc6 0x02d8 # BREVE
0xc7 0x02d9 # DOT ABOVE
0xc8 0x00a8 # DIAERESIS
0xc9 0x00b2 # SUPERSCRIPT TWO
0xca 0x02da # RING ABOVE
0xcb 0x00b8 # CEDILLA
0xcc 0x00b3 # SUPERSCRIPT THREE
0xcd 0x02dd # DOUBLE ACUTE ACCENT
0xce 0x02db # OGONEK
0xcf 0x02c7 # CARON
0xd0 0x2014 # EM DASH
0xd1 0x00b1 # PLUS-MINUS SIGN
0xd2 0x00bc # VULGAR FRACTION ONE QUARTER
0xd3 0x00bd # VULGAR FRACTION ONE HALF
0xd4 0x00be # VULGAR FRACTION THREE QUARTERS
0xd5 0x00e0 # LATIN SMALL LETTER A WITH GRAVE
0xd6 0x00e1 # LATIN SMALL LETTER A WITH ACUTE
0xd7 0x00e2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
0xd8 0x00e3 # LATIN SMALL LETTER A WITH TILDE
0xd9 0x00e4 # LATIN SMALL LETTER A WITH DIAERESIS
0xda 0x00e5 # LATIN SMALL LETTER A WITH RING ABOVE
0xdb 0x00e7 # LATIN SMALL LETTER C WITH CEDILLA
0xdc 0x00e8 # LATIN SMALL LETTER E WITH GRAVE
0xdd 0x00e9 # LATIN SMALL LETTER E WITH ACUTE
0xde 0x00ea # LATIN SMALL LETTER E WITH CIRCUMFLEX
0xdf 0x00eb # LATIN SMALL LETTER E WITH DIAERESIS
0xe0 0x00ec # LATIN SMALL LETTER I WITH GRAVE
0xe1 0x00c6 # LATIN CAPITAL LETTER AE
0xe2 0x00ed # LATIN SMALL LETTER I WITH ACUTE
0xe3 0x00aa # FEMININE ORDINAL INDICATOR
0xe4 0x00ee # LATIN SMALL LETTER I WITH CIRCUMFLEX
0xe5 0x00ef # LATIN SMALL LETTER I WITH DIAERESIS
0xe6 0x00f0 # LATIN SMALL LETTER ETH
0xe7 0x00f1 # LATIN SMALL LETTER N WITH TILDE
0xe8 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
0xe9 0x00d8 # LATIN CAPITAL LETTER O WITH STROKE
0xea 0x0152 # LATIN CAPITAL LIGATURE OE
0xeb 0x00ba # MASCULINE ORDINAL INDICATOR
0xec 0x00f2 # LATIN SMALL LETTER O WITH GRAVE
0xed 0x00f3 # LATIN SMALL LETTER O WITH ACUTE
0xee 0x00f4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
0xef 0x00f5 # LATIN SMALL LETTER O WITH TILDE
0xf0 0x00f6 # LATIN SMALL LETTER O WITH DIAERESIS
0xf1 0x00e6 # LATIN SMALL LETTER AE
0xf2 0x00f9 # LATIN SMALL LETTER U WITH GRAVE
0xf3 0x00fa # LATIN SMALL LETTER U WITH ACUTE
0xf4 0x00fb # LATIN SMALL LETTER U WITH CIRCUMFLEX
0xf5 0x0131 # LATIN SMALL LETTER DOTLESS I
0xf6 0x00fc # LATIN SMALL LETTER U WITH DIAERESIS
0xf7 0x00fd # LATIN SMALL LETTER Y WITH ACUTE
0xf8 0x0142 # LATIN SMALL LETTER L WITH STROKE
0xf9 0x00f8 # LATIN SMALL LETTER O WITH STROKE
0xfa 0x0153 # LATIN SMALL LIGATURE OE
0xfb 0x00df # LATIN SMALL LETTER SHARP S
0xfc 0x00fe # LATIN SMALL LETTER THORN
0xfd 0x00ff # LATIN SMALL LETTER Y WITH DIAERESIS
0xfe 0xfffd # .notdef, REPLACEMENT CHARACTER
0xff 0xfffd # .notdef, REPLACEMENT CHARACTER

46
unicode/xerox/README.TXT Normal file
View File

@@ -0,0 +1,46 @@
(Author: Ron Kaplan)
The XCCS files contain mappings from the Xerox Character Code Standard (version XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of XCCS that corresponds to the (incomplete) fonts in the Medley system. Unlike the mappings in sister directories, the Xerox mappings did not come from the Unicode CDROM, they were constructed by adjudicating information from the binary file XCCStoUni (of unknown provenance; see below) with code mappings scraped in July 2020 from the Wikipedia page https://en.wikipedia.org/wiki/Xerox_Character_Code_Standard.
Both sources are errorful and incomplete, so the original data was inspected and modified by hand. The data here may be the currently best specification of these mapping, but the mappings may still contain errors--no guarantees. Obviously, the reverse mappings from Unicode to XCCS are by definition incomplete.
Each file may contain the mappings for one or more XCCS character sets. By convention, the name of the file indicates the character set mappings it contains. A file with a single mapping has a name of the form XCCS-<csnumber>=<csname>.TXT, where csnumber is the octal number of the character set and csname is a cover term for its mappings. For example, XCCS-341=HEBREW.TXT contains the mappings for Hebrew.
If a file contains several character sets, its name specifies just the numbers of those sets. For example, XCCS-0,41-50,340-344,356-361.TXT contains mappings for character set 0, 41 through 50, 340 through 344, and 356 through 361 (basically, all the non JIS character sets).
The format of each file conforms to the format of the other Unicode-supplied mapping files:
Three white-space (tab or spaces) separated columns:
Column 1 is the XCCS code (as hex 0xXXXX)
Column 2 is the corresponding Unicode (as hex 0xXXXX)
Column 3 (after #) is a comment column.
For convenience, it contains the Unicode character itself (since the
Unicode character names are not available).
Unicode FFFF is used for the piece-meal (as opposed to systematic) undefined XCCS codes (Column 3 is UNDEFINED). (Long runs of undefined codes may not be explicitly marked.) Presumably undefined XCCS codes will never appear in XCCS files.
Unicode FFFE is used for defined XCCS codes whose Unicode mapping has not been determined (Column 3 is MISSING). These may be rare, but until/unless these are filled in, XCCS documents contain them them will not be properly represented in Unicode. Thus, this value flags the need for additional Unicode sleuthing.
Like the other Unicode mapping files, this file can be read by common Unicode routines. Also, it is encoded in UTF8, so that the Unicode characters are properly displayed in Column 3 and can be edited by standard Unicode-enabled editors (e.g. Mac Textedit).
These files and the mapping files in sister directories can also be read by the function READ-UNICODE-MAPPING in the UNICODE Medley library package, and they can be written by WRITE-UNICODE-MAPPING.
The entries are in XCCS order and grouped by character sets. In front of each character set, for convenience, there is a #-comment line with the octal XCCS character set and the character-set name (e.g. # "341" HEBREW).
Note that a given XCCS code might map to codes in several different Unicode positions, since there are repetitions in the Unicode standard.
Any comments or problems, contact <ron.kaplan@post.harvard.edu>
-------
The source of the file XCCStoUni is unknown, and there is no specification for its structure. It appears to be a sequence of 2-byte hex Unicode characters with all the Unicode characters in a given character set laid out in ascending XCCS code order.
It seems to have entries only for 188 characters per character set, with no 2-byte cells for the undefined regions of the two 128 code panels of each XCCS character set. So code 127 is skipped at each panel boundary and the running XCCS code is then bumped by 33. The hexcode at file position 0 is for octal 41 (exclamation mark); the space 40 isnt represented.
Within that, Unicode FFFD (the unicode missing-character slug) is used for XCCS codes whose Unicode equivalent is not specified, and it seems that FFFF is used when whole panels are missing (the higher order panel for most of the Japanese).
Finally, no cells are allocated for the unused/reserved character sets (1 through octal 40), so that the Unicode after octal 376 is for 41,41. But the order of character sets is a little jumbled, so that the JIS character sets (60 through 163), for example, start at 75 (octal) in the file sequence--some higher number character sets appear earlier in the file than they should.
The JIS character sets seem to be complete and accurate. There are sporadic missing codes and errors in some of the other sets that required hand correction.

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,256 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 0 LATIN
# Table version: 0.1
# Table format: Format A
# Date: 6-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "0" LATIN
0x0000 0x0000 # ^@
0x0001 0x0001 # ^A
0x0002 0x0002 # ^B
0x0003 0x0003 # ^C
0x0004 0x0004 # ^D
0x0005 0x0005 # ^E
0x0006 0x0006 # ^F
0x0007 0x0007 # ^G
0x0008 0x0008 # ^H
0x0009 0x0009 # ^I
0x000A 0x000A # ^J
0x000B 0x000B # ^K
0x000C 0x000C # ^L
0x000D 0x000D # ^M
0x000E 0x000E # ^N
0x000F 0x000F # ^O
0x0010 0x0010 # ^P
0x0011 0x0011 # ^Q
0x0012 0x0012 # ^R
0x0013 0x0013 # ^S
0x0014 0x0014 # ^T
0x0015 0x0015 # ^U
0x0016 0x0016 # ^V
0x0017 0x0017 # ^W
0x0018 0x0018 # ^X
0x0019 0x0019 # ^Y
0x001A 0x001A # ^Z
0x001B 0x001B # ^[
0x001C 0x001C # ^\
0x001D 0x001D # ^]
0x001E 0x001E # ^^
0x001F 0x001F # ^_
0x0020 0x0020 #
0x0021 0x0021 # !
0x0022 0x0022 # "
0x0023 0x0023 # #
0x0024 0x0024 # $
0x0025 0x0025 # %
0x0026 0x0026 # &
0x0027 0x0027 # '
0x0028 0x0028 # (
0x0029 0x0029 # )
0x002A 0x002A # *
0x002B 0x002B # +
0x002C 0x002C # ,
0x002D 0x002D # -
0x002E 0x002E # .
0x002F 0x002F # /
0x0030 0x0030 # 0
0x0031 0x0031 # 1
0x0032 0x0032 # 2
0x0033 0x0033 # 3
0x0034 0x0034 # 4
0x0035 0x0035 # 5
0x0036 0x0036 # 6
0x0037 0x0037 # 7
0x0038 0x0038 # 8
0x0039 0x0039 # 9
0x003A 0x003A # :
0x003B 0x003B # ;
0x003C 0x003C # <
0x003D 0x003D # =
0x003E 0x003E # >
0x003F 0x003F # ?
0x0040 0x0040 # @
0x0041 0x0041 # A
0x0042 0x0042 # B
0x0043 0x0043 # C
0x0044 0x0044 # D
0x0045 0x0045 # E
0x0046 0x0046 # F
0x0047 0x0047 # G
0x0048 0x0048 # H
0x0049 0x0049 # I
0x004A 0x004A # J
0x004B 0x004B # K
0x004C 0x004C # L
0x004D 0x004D # M
0x004E 0x004E # N
0x004F 0x004F # O
0x0050 0x0050 # P
0x0051 0x0051 # Q
0x0052 0x0052 # R
0x0053 0x0053 # S
0x0054 0x0054 # T
0x0055 0x0055 # U
0x0056 0x0056 # V
0x0057 0x0057 # W
0x0058 0x0058 # X
0x0059 0x0059 # Y
0x005A 0x005A # Z
0x005B 0x005B # [
0x005C 0x005C # \
0x005D 0x005D # ]
0x005E 0x005E # ^
0x005F 0x005F # _
0x0060 0x0060 # `
0x0061 0x0061 # a
0x0062 0x0062 # b
0x0063 0x0063 # c
0x0064 0x0064 # d
0x0065 0x0065 # e
0x0066 0x0066 # f
0x0067 0x0067 # g
0x0068 0x0068 # h
0x0069 0x0069 # i
0x006A 0x006A # j
0x006B 0x006B # k
0x006C 0x006C # l
0x006D 0x006D # m
0x006E 0x006E # n
0x006F 0x006F # o
0x0070 0x0070 # p
0x0071 0x0071 # q
0x0072 0x0072 # r
0x0073 0x0073 # s
0x0074 0x0074 # t
0x0075 0x0075 # u
0x0076 0x0076 # v
0x0077 0x0077 # w
0x0078 0x0078 # x
0x0079 0x0079 # y
0x007A 0x007A # z
0x007B 0x007B # {
0x007C 0x007C # |
0x007D 0x007D # }
0x007E 0x007E # ~
0x00A1 0x00A1 # ¡
0x00A2 0x00A2 # ¢
0x00A3 0x00A3 # £
0x00A4 0x0024 # $
0x00A5 0x00A5 # ¥
0x00A7 0x00A7 # §
0x00A9 0x2018 #
0x00AA 0x201C # “
0x00AB 0x00AB # «
0x00AC 0x2190 # ←
0x00AD 0x2191 # ↑
0x00AE 0x2192 # →
0x00AF 0x2193 # ↓
0x00B0 0x00B0 # °
0x00B1 0x00B1 # ±
0x00B2 0x00B2 # ²
0x00B3 0x00B3 # ³
0x00B4 0x00D7 # ×
0x00B5 0x00B5 # µ
0x00B6 0x00B6 # ¶
0x00B7 0x00B7 # ·
0x00B8 0x00F7 # ÷
0x00B9 0x2019 #
0x00BA 0x201D # ”
0x00BB 0x00BB # »
0x00BC 0x00BC # ¼
0x00BD 0x00BD # ½
0x00BE 0x00BE # ¾
0x00BF 0x00BF # ¿
0x00C1 0x0300 # ̀
0x00C2 0x0301 # ́
0x00C3 0x0302 # ̂
0x00C4 0x0303 # ̃
0x00C5 0x0304 # ̄
0x00C6 0x0306 # ̆
0x00C7 0x0307 # ̇
0x00C8 0x0308 # ̈
0x00CA 0x030A # ̊
0x00CB 0x0327 # ̧
0x00CC 0x0332 # ̲
0x00CD 0x030B # ̋
0x00CE 0x0328 # ̨
0x00CF 0x030C # ̌
0x00D0 0x2015 # ―
0x00D1 0x00B9 # ¹
0x00D2 0x00AE # ®
0x00D3 0x00A9 # ©
0x00D4 0x2122 # ™
0x00D5 0x266A # ♪
0x00DC 0x215B # ⅛
0x00DD 0x215C # ⅜
0x00DE 0x215D # ⅝
0x00DF 0x215E # ⅞
0x00E0 0x2126 # Ω
0x00E1 0x00C6 # Æ
0x00E2 0x00D0 # Ð
0x00E3 0x00AA # ª
0x00E4 0x0126 # Ħ
0x00E5 0x0237 # ȷ
0x00E6 0x0132 # IJ
0x00E7 0x013F # Ŀ
0x00E8 0x0141 # Ł
0x00E9 0x00D8 # Ø
0x00EA 0x0152 # Œ
0x00EB 0x00BA # º
0x00EC 0x00DE # Þ
0x00ED 0x0166 # Ŧ
0x00EE 0x014A # Ŋ
0x00EF 0x0149 # ʼn
0x00F0 0x0138 # ĸ
0x00F1 0x00E6 # æ
0x00F2 0x0111 # đ
0x00F3 0x00F0 # ð
0x00F4 0x0127 # ħ
0x00F5 0x0131 # ı
0x00F6 0x0133 # ij
0x00F7 0x0140 # ŀ
0x00F8 0x0142 # ł
0x00F9 0x00F8 # ø
0x00FA 0x0153 # œ
0x00FB 0x00DF # ß
0x00FC 0x00FE # þ
0x00FD 0x0167 # ŧ
0x00FE 0x014B # ŋ

View File

@@ -0,0 +1,202 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 340 ARABIC
# Table version: 0.1
# Table format: Format A
# Date: 4-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "340" ARABIC
0xE025 0x066A # ٪
0xE02C 0x060C # ،
0xE02E 0x06D4 # ۔
0xE030 0x0660 # ٠
0xE031 0x0661 # ١
0xE032 0x0662 # ٢
0xE033 0x0663 # ٣
0xE034 0x0664 # ٤
0xE035 0x0665 # ٥
0xE036 0x0666 # ٦
0xE037 0x0667 # ٧
0xE038 0x0668 # ٨
0xE039 0x0669 # ٩
0xE03B 0x061B # ؛
0xE03F 0x061F # ؟
0xE041 0x0621 # ء
0xE042 0x0622 # آ
0xE043 0x0623 # أ
0xE044 0x0624 # ؤ
0xE045 0x0625 # إ
0xE046 0x0626 # ئ
0xE047 0x0627 # ا
0xE048 0x0628 # ب
0xE049 0x0629 # ة
0xE04A 0x062A # ت
0xE04B 0x062B # ث
0xE04C 0x062C # ج
0xE04D 0x062D # ح
0xE04E 0x062E # خ
0xE04F 0x062F # د
0xE050 0x0630 # ذ
0xE051 0x0631 # ر
0xE052 0x0632 # ز
0xE053 0x0633 # س
0xE054 0x0634 # ش
0xE055 0x0635 # ص
0xE056 0x0636 # ض
0xE057 0x0637 # ط
0xE058 0x0638 # ظ
0xE059 0x0639 # ع
0xE05A 0x063A # غ
0xE060 0x0640 # ـ
0xE061 0x0641 # ف
0xE062 0x0642 # ق
0xE063 0x0643 # ك
0xE064 0x0644 # ل
0xE065 0x0645 # م
0xE066 0x0646 # ن
0xE067 0x0647 # ه
0xE068 0x0648 # و
0xE069 0x0649 # ى
0xE06A 0x064A # ي
0xE06B 0x064B # ً
0xE06C 0x064C # ٌ
0xE06D 0x064D # ٍ
0xE06E 0x064E # َ
0xE06F 0x064F # ُ
0xE070 0x0650 # ِ
0xE071 0x0651 # ّ
0xE072 0x0652 # ْ
0xE073 0x0670 # ٰ
0xE074 0x0671 # ٱ
0xE075 0x066B # ٫
0xE076 0x066C # ٬
0xE077 0x0657 # ٗ
0xE0A1 0x06A4 # ڤ
0xE0A2 0x067E # پ
0xE0A3 0x0686 # چ
0xE0A4 0x0698 # ژ
0xE0A5 0x06AF # گ
0xE0A6 0x06C0 # ۀ
0xE0A7 0x0679 # ٹ
0xE0A8 0x0688 # ڈ
0xE0A9 0x0691 # ڑ
0xE0AA 0x06BA # ں
0xE0AB 0x06BE # ھ
0xE0AC 0x06C1 # ہ
0xE0AD 0x06C3 # ۃ
0xE0AE 0x06C2 # ۂ
0xE0AF 0x06D2 # ے
0xE0B1 0x067C # ټ
0xE0B2 0x0681 # ځ
0xE0B3 0x0685 # څ
0xE0B4 0x0689 # ډ
0xE0B5 0x0693 # ړ
0xE0B6 0x0696 # ږ
0xE0B7 0x069A # ښ
0xE0B8 0x06BC # ڼ
0xE0B9 0x06D0 # ې
0xE0BA 0x06CD # ۍ
0xE0BB 0x0672 # ٲ
0xE0BC 0x0673 # ٳ
0xE0BD 0x06D3 # ۓ
0xE0BE 0x06D5 # ە
0xE0BF 0xFBD3 # ﯓ
0xE0C0 0x06C7 # ۇ
0xE0C1 0x06C6 # ۆ
0xE0C2 0x06C8 # ۈ
0xE0C3 0xFBDD # ﯝ
0xE0C4 0x06CB # ۋ
0xE0C5 0x06C5 # ۅ
0xE0C6 0x06C9 # ۉ
0xE0C7 0x0674 # ٴ
0xE0C8 0x0675 # ٵ
0xE0C9 0x0676 # ٶ
0xE0CA 0x0682 # ڂ
0xE0CB 0x0677 # ٷ
0xE0CC 0x0678 # ٸ
0xE0CD 0x067D # ٽ
0xE0CE 0x068A # ڊ
0xE0CF 0x068B # ڋ
0xE0D0 0x06AB # ګ
0xE0D1 0x068F # ڏ
0xE0D2 0x0690 # ڐ
0xE0D3 0x06CC # ی
0xE0D4 0x067B # ٻ
0xE0D5 0x0680 # ڀ
0xE0D6 0x067A # ٺ
0xE0D7 0x067F # ٿ
0xE0D8 0x06A6 # ڦ
0xE0D9 0x0684 # ڄ
0xE0DA 0x0683 # ڃ
0xE0DB 0x0687 # ڇ
0xE0DC 0x068D # ڍ
0xE0DD 0x068C # ڌ
0xE0DE 0x068E # ڎ
0xE0DF 0x06A9 # ک
0xE0E0 0x06B3 # ڳ
0xE0E1 0x06B1 # ڱ
0xE0E2 0x06BB # ڻ
0xE0E3 0x0692 # ڒ
0xE0E4 0x0694 # ڔ
0xE0E5 0x0695 # ڕ
0xE0E6 0x0697 # ڗ
0xE0E7 0x0699 # ڙ
0xE0E8 0x069B # ڛ
0xE0E9 0x069C # ڜ
0xE0EA 0x069D # ڝ
0xE0EB 0x069E # ڞ
0xE0EC 0x069F # ڟ
0xE0ED 0x06A0 # ڠ
0xE0EE 0x06A1 # ڡ
0xE0EF 0x06A2 # ڢ
0xE0F0 0x06A3 # ڣ
0xE0F1 0x06A5 # ڥ
0xE0F2 0x06A7 # ڧ
0xE0F3 0x06A8 # ڨ
0xE0F4 0x06AA # ڪ
0xE0F5 0x06AC # ڬ
0xE0F6 0x06AD # ڭ
0xE0F8 0x06AE # ڮ
0xE0F9 0x06B0 # ڰ
0xE0FA 0x06B2 # ڲ
0xE0FB 0x06B4 # ڴ
0xE0FC 0x200E #
0xE0FD 0x200F #
0xE0FE 0x200D #

View File

@@ -0,0 +1,137 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 341 HEBREW
# Table version: 0.1
# Table format: Format A
# Date: 4-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "341" HEBREW
0xE140 0x05D0 # א
0xE141 0x05D1 # ב
0xE142 0x05D2 # ג
0xE143 0x05D3 # ד
0xE144 0x05D4 # ה
0xE145 0x05D5 # ו
0xE146 0x05D6 # ז
0xE147 0x05D7 # ח
0xE148 0x05D8 # ט
0xE149 0x05D9 # י
0xE14A 0x05DA # ך
0xE14B 0x05DB # כ
0xE14C 0x05DC # ל
0xE14D 0x05DD # ם
0xE14E 0x05DE # מ
0xE14F 0x05DF # ן
0xE150 0x05E0 # נ
0xE151 0x05E1 # ס
0xE152 0x05E2 # ע
0xE153 0x05E3 # ף
0xE154 0x05E4 # פ
0xE155 0x05E5 # ץ
0xE156 0x05E6 # צ
0xE157 0x05E7 # ק
0xE158 0x05E8 # ר
0xE159 0x05E9 # ש
0xE15A 0x05EA # ת
0xE15B 0xFB31 # בּ
0xE15C 0xFB3B # כּ
0xE15D 0xFB44 # פּ
0xE15E 0xFB2A # שׁ
0xE15F 0xFB2B # שׂ
0xE160 0xFB2C # שּׁ
0xE161 0xFB2D # שּׂ
0xE162 0xFB2E # אַ
0xE163 0xFB2F # אָ
0xE164 0xFB4B # וֹ
0xE165 0xFB4C # בֿ
0xE166 0xFB4D # כֿ
0xE167 0xFB4E # פֿ
0xE168 0xFB4F # ﭏ
0xE169 0xFB1F # ײַ
0xE16A 0xFB20 # ﬠ
0xE16B 0xFB21 # ﬡ
0xE16C 0xFB22 # ﬢ
0xE16D 0xFB23 # ﬣ
0xE16E 0xFB24 # ﬤ
0xE16F 0xFB25 # ﬥ
0xE170 0xFB26 # ﬦ
0xE171 0xFB27 # ﬧ
0xE172 0xFB28 # ﬨ
0xE173 0xFB29 # ﬩
0xE174 0x05F0 # װ
0xE175 0x05F1 # ױ
0xE176 0x05F2 # ײ
0xE177 0xFB30 # אּ
0xE178 0xFB32 # גּ
0xE179 0xFB33 # דּ
0xE17A 0xFB34 # הּ
0xE17B 0xFB35 # וּ
0xE17C 0xFB36 # זּ
0xE17D 0xFB38 # טּ
0xE17E 0xFB39 # יּ
0xE1A1 0xFB3A # ךּ
0xE1A2 0xFB3C # לּ
0xE1A3 0xFB3E # מּ
0xE1A4 0xFB40 # נּ
0xE1A5 0xFB41 # סּ
0xE1A6 0xFB43 # ףּ
0xE1A7 0xFB46 # צּ
0xE1A8 0xFB47 # קּ
0xE1A9 0xFB48 # רּ
0xE1AA 0xFB49 # שּ
0xE1AB 0xFB4A # תּ
0xE1C1 0x05B4 # ִ
0xE1C2 0x05B5 # ֵ
0xE1C3 0x05B6 # ֶ
0xE1C4 0x05BB # ֻ
0xE1C5 0x05B8 # ָ
0xE1C6 0x05B7 # ַ
0xE1C7 0x05B0 # ְ
0xE1C8 0x05B2 # ֲ
0xE1C9 0x05B1 # ֱ
0xE1CA 0x05B3 # ֳ
0xE1CB 0x05C2 # ׂ
0xE1CC 0x05C1 # ׁ
0xE1CE 0x05B9 # ֹ
0xE1CF 0x05BC # ּ
0xE1EF 0x05BD # ֽ
0xE1F0 0xFB1E # ﬞ
0xE1F1 0x05BF # ֿ
0xE1F2 0x05C0 # ׀

View File

@@ -0,0 +1,66 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 342 IPA
# Table version: 0.1
# Table format: Format A
# Date: 4-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "342" IPA
0xE2DB 0x029D # ʝ
0xE2DC 0x028E # ʎ
0xE2DD 0x014B # ŋ
0xE2DE 0x006B # k
0xE2DF 0x0261 # ɡ
0xE2E0 0x0078 # x
0xE2E1 0x0263 # ɣ
0xE2E2 0x0270 # ɰ
0xE2E3 0x0260 # ɠ
0xE2E4 0x0274 # ɴ
0xE2E5 0x019E # ƞ
0xE2E6 0x0071 # q
0xE2E7 0x0262 # ɢ
0xE2E8 0x03C7 # χ
0xE2E9 0x0281 # ʁ
0xE2EA 0x0280 # ʀ
0xE2EB 0x0127 # ħ
0xE2EC 0x0295 # ʕ
0xE2ED 0x0294 # ʔ
0xE2EE 0x0068 # h
0xE2EF 0x0266 # ɦ

View File

@@ -0,0 +1,97 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 343 HANGUL
# Table version: 0.1
# Table format: Format A
# Date: 4-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "343" HANGUL
0xE3A2 0xFFE6 # ₩
0xE3C1 0xFFA1 # ᄀ
0xE3C2 0xFFA2 # ᄁ
0xE3C3 0xFFA3 # ᆪ
0xE3C4 0xFFA4 # ᄂ
0xE3C5 0xFFA5 # ᆬ
0xE3C6 0xFFA6 # ᆭ
0xE3C7 0xFFA7 # ᄃ
0xE3C8 0xFFA8 # ᄄ
0xE3C9 0xFFA9 # ᄅ
0xE3CA 0xFFAA # ᆰ
0xE3CB 0xFFAB # ᆱ
0xE3CC 0xFFAC # ᆲ
0xE3CD 0xFFAD # ᆳ
0xE3CE 0xFFAE # ᆴ
0xE3CF 0xFFAF # ᆵ
0xE3D0 0xFFB0 # ᄚ
0xE3D1 0xFFB1 # ᄆ
0xE3D2 0xFFB2 # ᄇ
0xE3D3 0xFFB3 # ᄈ
0xE3D4 0xFFB4 # ᄡ
0xE3D5 0xFFB5 # ᄉ
0xE3D6 0xFFB6 # ᄊ
0xE3D7 0xFFB7 # ᄋ
0xE3D8 0xFFB8 # ᄌ
0xE3D9 0xFFB9 # ᄍ
0xE3DA 0xFFBA # ᄎ
0xE3DB 0xFFBB # ᄏ
0xE3DC 0xFFBC # ᄐ
0xE3DD 0xFFBD # ᄑ
0xE3DE 0xFFBE # ᄒ
0xE3E2 0xFFC2 # ᅡ
0xE3E3 0xFFC3 # ᅢ
0xE3E4 0xFFC4 # ᅣ
0xE3E5 0xFFC5 # ᅤ
0xE3E6 0xFFC6 # ᅥ
0xE3E7 0xFFC7 # ᅦ
0xE3EA 0xFFCA # ᅧ
0xE3EB 0xFFCB # ᅨ
0xE3EC 0xFFCC # ᅩ
0xE3ED 0xFFCD # ᅪ
0xE3EE 0xFFCE # ᅫ
0xE3EF 0xFFCF # ᅬ
0xE3F2 0xFFD2 # ᅭ
0xE3F3 0xFFD3 # ᅮ
0xE3F4 0xFFD4 # ᅯ
0xE3F5 0xFFD5 # ᅰ
0xE3F6 0xFFD6 # ᅱ
0xE3F7 0xFFD7 # ᅲ
0xE3FA 0xFFDA # ᅳ
0xE3FB 0xFFDB # ᅴ
0xE3FC 0xFFDC # ᅵ

View File

@@ -0,0 +1,141 @@
#
# Name: XCCS (XC-3-1-1-0) to Unicode
# Unicode version: 3.0
# XCCS charset: 344 GEORGIAN-ARMENIAN
# Table version: 0.1
# Table format: Format A
# Date: 4-Aug-2020
# Author: Ron Kaplan <Ron.Kaplan@post.harvard.edu>
#
# This file contains mappings from the Xerox Character Code Standard (version
# XC1-3-3-0, 1987) into Unicode 3.0. standard codes. That is the version of
# XCCS corresponding to the fonts in the Medley system.
#
# The format of this file conforms to the format of the other Unicode-supplied
# mapping files:
# Three white-space (tab or spaces) separated columns:
# Column 1 is the XCCS code (as hex 0xXXXX)
# Column 2 is the corresponding Unicode (as hex 0xXXXX)
# Column 3 (after #) is a comment column. For convenience, it contains the
# Unicode character itself (since the Unicode character names
# are not available)
# Unicode FFFF is used for undefined XCCS codes (Column 3 = UNDEFINED
# Unicode FFFE is used for XCCS codes that have not yet been filled in.
# (Column 3 = MISSING)
#
# This file is encoded in UTF8, so that the Unicode characters
# are properly displayed in Column 3 and can be edited by standard
# Unicode-enabled editors (e.g. Mac Textedit).
#
# This file can also be read by the function
# READ-UNICODE-MAPPING in the UNICODE Medley library package.
#
# The entries are in XCCS order and grouped by character sets. In front of
# the mappings, for convenience, there is a line with the octal XCCS
# character set, after #.
#
# Note that a given XCCS code might map to codes in several different Unicode
# positions, since there are repetitions in the Unicode standard.
#
# For more details, see the associated README.TXT file.
#
# Any comments or problems, contact <ron.kaplan@post.harvard.edu>
# "344" GEORGIAN-ARMENIAN
0xE421 0x10D0 # ა
0xE421 0x0966 #
0xE422 0x10D1 # ბ
0xE422 0x0967 # १
0xE423 0x10D2 # გ
0xE423 0x0968 # २
0xE424 0x10D3 # დ
0xE424 0x0969 # ३
0xE425 0x10D4 # ე
0xE425 0x096A # ४
0xE426 0x10D5 # ვ
0xE426 0x096B # ५
0xE427 0x10D6 # ზ
0xE427 0x096C # ६
0xE428 0x10F1 # ჱ
0xE428 0x096D # ७
0xE429 0x10D7 # თ
0xE429 0x096E # ८
0xE42A 0x10D8 # ი
0xE42A 0x096F # ९
0xE42B 0x10D9 # კ
0xE42C 0x10DA # ლ
0xE42D 0x10DB # მ
0xE42E 0x10DC # ნ
0xE42F 0x10F2 # ჲ
0xE42F 0x20A8 # ₨
0xE430 0x10DD # ო
0xE431 0x10DE # პ
0xE432 0x10DF # ჟ
0xE433 0x10E0 # რ
0xE434 0x10E1 # ს
0xE435 0x10E2 # ტ
0xE436 0x10E3 # უ
0xE437 0x10F3 # ჳ
0xE438 0x10E4 # ფ
0xE439 0x10E5 # ქ
0xE43A 0x10E6 # ღ
0xE43B 0x10E7 #
0xE43C 0x10E8 # შ
0xE43D 0x10E9 # ჩ
0xE43E 0x10EA # ც
0xE43F 0x10EB # ძ
0xE440 0x10EC # წ
0xE441 0x10ED # ჭ
0xE442 0x10EE # ხ
0xE443 0x10F4 # ჴ
0xE444 0x10EF # ჯ
0xE445 0x10F0 # ჰ
0xE446 0x10F5 # ჵ
0xE447 0x10F6 # ჶ
0xE44E 0x0589 # ։
0xE44F 0x10FB # ჻
0xE451 0x10A0 # Ⴀ
0xE452 0x10A1 # Ⴁ
0xE453 0x10A2 # Ⴂ
0xE454 0x10A3 # Ⴃ
0xE455 0x10A4 # Ⴄ
0xE456 0x10A5 # Ⴅ
0xE457 0x10A6 # Ⴆ
0xE458 0x10C1 # Ⴡ
0xE459 0x10A7 # Ⴇ
0xE45A 0x10A8 # Ⴈ
0xE45B 0x10A9 # Ⴉ
0xE45C 0x10AA # Ⴊ
0xE45D 0x10AB # Ⴋ
0xE45E 0x10AC # Ⴌ
0xE45F 0x10C2 # Ⴢ
0xE460 0x10AD # Ⴍ
0xE461 0x10AE # Ⴎ
0xE462 0x10AF # Ⴏ
0xE463 0x10B0 # Ⴐ
0xE464 0x10B1 # Ⴑ
0xE465 0x10B2 # Ⴒ
0xE466 0x10B3 # Ⴓ
0xE467 0x10C3 # Ⴣ
0xE468 0x10B4 # Ⴔ
0xE469 0x10B5 # Ⴕ
0xE46A 0x10B6 # Ⴖ
0xE46B 0x10B7 # Ⴗ
0xE46C 0x10B8 # Ⴘ
0xE46D 0x10B9 # Ⴙ
0xE46E 0x10BA # Ⴚ
0xE46F 0x10BB # Ⴛ
0xE470 0x10BC # Ⴜ
0xE470 0x094A # ॊ
0xE471 0x10BD # Ⴝ
0xE471 0x0951 # ॑
0xE472 0x10BE # Ⴞ
0xE472 0x0952 # ॒
0xE473 0x10C4 # Ⴤ
0xE473 0x0953 # ॓
0xE474 0x10BF # Ⴟ
0xE474 0x0954 # ॔
0xE475 0x10C0 # Ⴠ
0xE475 0x0965 # ॥
0xE476 0x10C5 # Ⴥ

Some files were not shown because too many files have changed in this diff Show More