1
0
mirror of synced 2026-04-25 20:01:51 +00:00
Files
Interlisp.medley/unicode/xerox/XCCS-0=LATIN.TXT
rmkaplan a84242561a Rmk100 unicode utf 8 update (#1489)
* UNICODE:  a few additional Tedit helpers, revised documentation

* New JIS files (courtesy of Peter)

* Updated mapping files (courtesy of Peter Craven)

* UNICODE:  changed SHOULDNT to ERROR
2024-01-10 10:47:16 -08:00

258 lines
9.6 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# 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: 9-Aug-2021
# 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 # SPACE
0x0021 0x0021 # ! EXCLAMATION MARK
0x0022 0x0022 # " QUOTATION MARK
0x0023 0x0023 # # NUMBER SIGN
# 0x0024 0x00A4 # ¤ CURRENCY SIGN
0x0024 0x0024 # $ DOLLAR SIGN
0x0025 0x0025 # % PERCENT SIGN
0x0026 0x0026 # & AMPERSAND
0x0027 0x0027 # ' APOSTROPHE
0x0028 0x0028 # ( LEFT PARENTHESIS
0x0029 0x0029 # ) RIGHT PARENTHESIS
0x002A 0x002A # * ASTERISK
0x002B 0x002B # + PLUS SIGN
0x002C 0x002C # , COMMA
0x002D 0x002D # - HYPHEN-MINUS
0x002E 0x002E # . FULL STOP
0x002F 0x002F # / SOLIDUS
0x0030 0x0030 # 0 DIGIT ZERO
0x0031 0x0031 # 1 DIGIT ONE
0x0032 0x0032 # 2 DIGIT TWO
0x0033 0x0033 # 3 DIGIT THREE
0x0034 0x0034 # 4 DIGIT FOUR
0x0035 0x0035 # 5 DIGIT FIVE
0x0036 0x0036 # 6 DIGIT SIX
0x0037 0x0037 # 7 DIGIT SEVEN
0x0038 0x0038 # 8 DIGIT EIGHT
0x0039 0x0039 # 9 DIGIT NINE
0x003A 0x003A # : COLON
0x003B 0x003B # ; SEMICOLON
0x003C 0x003C # < LESS-THAN SIGN
0x003D 0x003D # = EQUALS SIGN
0x003E 0x003E # > GREATER-THAN SIGN
0x003F 0x003F # ? QUESTION MARK
0x0040 0x0040 # @ COMMERCIAL AT
0x0041 0x0041 # A LATIN CAPITAL LETTER A
0x0042 0x0042 # B LATIN CAPITAL LETTER B
0x0043 0x0043 # C LATIN CAPITAL LETTER C
0x0044 0x0044 # D LATIN CAPITAL LETTER D
0x0045 0x0045 # E LATIN CAPITAL LETTER E
0x0046 0x0046 # F LATIN CAPITAL LETTER F
0x0047 0x0047 # G LATIN CAPITAL LETTER G
0x0048 0x0048 # H LATIN CAPITAL LETTER H
0x0049 0x0049 # I LATIN CAPITAL LETTER I
0x004A 0x004A # J LATIN CAPITAL LETTER J
0x004B 0x004B # K LATIN CAPITAL LETTER K
0x004C 0x004C # L LATIN CAPITAL LETTER L
0x004D 0x004D # M LATIN CAPITAL LETTER M
0x004E 0x004E # N LATIN CAPITAL LETTER N
0x004F 0x004F # O LATIN CAPITAL LETTER O
0x0050 0x0050 # P LATIN CAPITAL LETTER P
0x0051 0x0051 # Q LATIN CAPITAL LETTER Q
0x0052 0x0052 # R LATIN CAPITAL LETTER R
0x0053 0x0053 # S LATIN CAPITAL LETTER S
0x0054 0x0054 # T LATIN CAPITAL LETTER T
0x0055 0x0055 # U LATIN CAPITAL LETTER U
0x0056 0x0056 # V LATIN CAPITAL LETTER V
0x0057 0x0057 # W LATIN CAPITAL LETTER W
0x0058 0x0058 # X LATIN CAPITAL LETTER X
0x0059 0x0059 # Y LATIN CAPITAL LETTER Y
0x005A 0x005A # Z LATIN CAPITAL LETTER Z
0x005B 0x005B # [ LEFT SQUARE BRACKET
0x005C 0x005C # \ REVERSE SOLIDUS
0x005D 0x005D # ] RIGHT SQUARE BRACKET
0x005E 0x005E # ^ CIRCUMFLEX ACCENT
0x005F 0x005F # _ LOW LINE
0x0060 0x0060 # ` GRAVE ACCENT
0x0061 0x0061 # a LATIN SMALL LETTER A
0x0062 0x0062 # b LATIN SMALL LETTER B
0x0063 0x0063 # c LATIN SMALL LETTER C
0x0064 0x0064 # d LATIN SMALL LETTER D
0x0065 0x0065 # e LATIN SMALL LETTER E
0x0066 0x0066 # f LATIN SMALL LETTER F
0x0067 0x0067 # g LATIN SMALL LETTER G
0x0068 0x0068 # h LATIN SMALL LETTER H
0x0069 0x0069 # i LATIN SMALL LETTER I
0x006A 0x006A # j LATIN SMALL LETTER J
0x006B 0x006B # k LATIN SMALL LETTER K
0x006C 0x006C # l LATIN SMALL LETTER L
0x006D 0x006D # m LATIN SMALL LETTER M
0x006E 0x006E # n LATIN SMALL LETTER N
0x006F 0x006F # o LATIN SMALL LETTER O
0x0070 0x0070 # p LATIN SMALL LETTER P
0x0071 0x0071 # q LATIN SMALL LETTER Q
0x0072 0x0072 # r LATIN SMALL LETTER R
0x0073 0x0073 # s LATIN SMALL LETTER S
0x0074 0x0074 # t LATIN SMALL LETTER T
0x0075 0x0075 # u LATIN SMALL LETTER U
0x0076 0x0076 # v LATIN SMALL LETTER V
0x0077 0x0077 # w LATIN SMALL LETTER W
0x0078 0x0078 # x LATIN SMALL LETTER X
0x0079 0x0079 # y LATIN SMALL LETTER Y
0x007A 0x007A # z LATIN SMALL LETTER Z
0x007B 0x007B # { LEFT CURLY BRACKET
0x007C 0x007C # | VERTICAL LINE
0x007D 0x007D # } RIGHT CURLY BRACKET
0x007E 0x007E # ~ TILDE
0x00A1 0x00A1 # ¡ INVERTED EXCLAMATION MARK
0x00A2 0x00A2 # ¢ CENT SIGN
0x00A3 0x00A3 # £ POUND SIGN
0x00A4 0x0024 # $ DOLLAR SIGN
0x00A5 0x00A5 # ¥ YEN SIGN
0x00A7 0x00A7 # § SECTION SIGN
0x00A9 0x2018 # LEFT SINGLE QUOTATION MARK
0x00AA 0x201C # “ LEFT DOUBLE QUOTATION MARK
0x00AB 0x00AB # « LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC 0x2190 # ← LEFTWARDS ARROW
0x00AD 0x2191 # ↑ UPWARDS ARROW
0x00AE 0x2192 # → RIGHTWARDS ARROW
0x00AF 0x2193 # ↓ DOWNWARDS ARROW
0x00B0 0x00B0 # ° DEGREE SIGN
0x00B1 0x00B1 # ± PLUS-MINUS SIGN
0x00B2 0x00B2 # ² SUPERSCRIPT TWO
0x00B3 0x00B3 # ³ SUPERSCRIPT THREE
0x00B4 0x00D7 # × MULTIPLICATION SIGN
0x00B5 0x00B5 # µ MICRO SIGN
0x00B6 0x00B6 # ¶ PILCROW SIGN
0x00B7 0x00B7 # · MIDDLE DOT
0x00B8 0x00F7 # ÷ DIVISION SIGN
0x00B9 0x2019 # RIGHT SINGLE QUOTATION MARK
0x00BA 0x201D # ” RIGHT DOUBLE QUOTATION MARK
0x00BB 0x00BB # » RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC 0x00BC # ¼ VULGAR FRACTION ONE QUARTER
0x00BD 0x00BD # ½ VULGAR FRACTION ONE HALF
0x00BE 0x00BE # ¾ VULGAR FRACTION THREE QUARTERS
0x00BF 0x00BF # ¿ INVERTED QUESTION MARK
0x00C1 0x0300 # ̀ COMBINING GRAVE ACCENT
0x00C2 0x0301 # ́ COMBINING ACUTE ACCENT
0x00C3 0x0302 # ̂ COMBINING CIRCUMFLEX ACCENT
0x00C4 0x0303 # ̃ COMBINING TILDE
0x00C5 0x0304 # ̄ COMBINING MACRON
0x00C6 0x0306 # ̆ COMBINING BREVE
0x00C7 0x0307 # ̇ COMBINING DOT ABOVE
0x00C8 0x0308 # ̈ COMBINING DIAERESIS
0x00CA 0x030A # ̊ COMBINING RING ABOVE
0x00CB 0x0327 # ̧ COMBINING CEDILLA
0x00CC 0x0332 # ̲ COMBINING LOW LINE
0x00CD 0x030B # ̋ COMBINING DOUBLE ACUTE ACCENT
0x00CE 0x0328 # ̨ COMBINING OGONEK
0x00CF 0x030C # ̌ COMBINING CARON
0x00D0 0x2015 # ― HORIZONTAL BAR
0x00D1 0x00B9 # ¹ SUPERSCRIPT ONE
0x00D2 0x00AE # ® REGISTERED SIGN
0x00D3 0x00A9 # © COPYRIGHT SIGN
0x00D4 0x2122 # ™ TRADE MARK SIGN
0x00D5 0x266A # ♪ EIGHTH NOTE
0x00DC 0x215B # ⅛ VULGAR FRACTION ONE EIGHTH
0x00DD 0x215C # ⅜ VULGAR FRACTION THREE EIGHTHS
0x00DE 0x215D # ⅝ VULGAR FRACTION FIVE EIGHTHS
0x00DF 0x215E # ⅞ VULGAR FRACTION SEVEN EIGHTHS
0x00E0 0x2126 # Ω OHM SIGN
0x00E1 0x00C6 # Æ LATIN CAPITAL LETTER AE
0x00E2 0x00D0 # Đ LATIN CAPITAL LETTER D WITH STROKE (Croatian) Also 0110 ?
0x00E3 0x00AA # ª FEMININE ORDINAL INDICATOR
0x00E4 0x0126 # Ħ LATIN CAPITAL LETTER H WITH STROKE
0x00E5 0x0237 # ȷ LATIN SMALL LETTER DOTLESS J
0x00E6 0x0132 # IJ LATIN CAPITAL LIGATURE IJ
0x00E7 0x013F # Ŀ LATIN CAPITAL LETTER L WITH MIDDLE DOT
0x00E8 0x0141 # Ł LATIN CAPITAL LETTER L WITH STROKE
0x00E9 0x00D8 # Ø LATIN CAPITAL LETTER O WITH STROKE
0x00EA 0x0152 # Œ LATIN CAPITAL LIGATURE OE
0x00EB 0x00BA # º MASCULINE ORDINAL INDICATOR
0x00EC 0x00DE # Þ LATIN CAPITAL LETTER THORN
0x00ED 0x0166 # Ŧ LATIN CAPITAL LETTER T WITH STROKE
0x00EE 0x014A # Ŋ LATIN CAPITAL LETTER ENG
0x00EF 0x0149 # ʼn LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
0x00F0 0x0138 # ᴋ LATIN LETTER SMALL CAPITAL KRA (Greenlandic)
0x00F1 0x00E6 # æ LATIN SMALL LETTER AE
0x00F2 0x0111 # đ LATIN SMALL LETTER D WITH STROKE
0x00F3 0x00F0 # ð LATIN SMALL LETTER ETH
0x00F4 0x0127 # ħ LATIN SMALL LETTER H WITH STROKE
0x00F5 0x0131 # ı LATIN SMALL LETTER DOTLESS I
0x00F6 0x0133 # ij LATIN SMALL LIGATURE IJ
0x00F7 0x0140 # ŀ LATIN SMALL LETTER L WITH MIDDLE DOT
0x00F8 0x0142 # ł LATIN SMALL LETTER L WITH STROKE
0x00F9 0x00F8 # ø LATIN SMALL LETTER O WITH STROKE
0x00FA 0x0153 # œ LATIN SMALL LIGATURE OE
0x00FB 0x00DF # ß LATIN SMALL LETTER SHARP S
0x00FC 0x00FE # þ LATIN SMALL LETTER THORN
0x00FD 0x0167 # ŧ LATIN SMALL LETTER T WITH STROKE
0x00FE 0x014B # ŋ LATIN SMALL LETTER ENG