xref: /plan9/sys/lib/antiword/Unicode01 (revision f5736e95f14e1485b3a0291fa82d86cca323ab61)
1#
2#	Name:             ISO/IEC 8859-1:1998 to Unicode
3#	Unicode version:  3.0
4#	Table version:    1.0
5#	Table format:     Format A
6#	Date:             1999 July 27
7#	Authors:          Ken Whistler <kenw@sybase.com>
8#
9#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
10#
11#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
12#	No claims are made as to fitness for any particular purpose.  No
13#	warranties of any kind are expressed or implied.  The recipient
14#	agrees to determine applicability of information provided.  If this
15#	file has been provided on optical media by Unicode, Inc., the sole
16#	remedy for any claim will be exchange of defective media within 90
17#	days of receipt.
18#
19#	Unicode, Inc. hereby grants the right to freely use the information
20#	supplied in this file in the creation of products supporting the
21#	Unicode Standard, and to make copies of this file in any form for
22#	internal or external distribution as long as this notice remains
23#	attached.
24#
25#	General notes:
26#
27#	This table contains the data the Unicode Consortium has on how
28#       ISO/IEC 8859-1:1998 characters map into Unicode.
29#
30#	Format:  Three tab-separated columns
31#		 Column #1 is the ISO/IEC 8859-1 code (in hex as 0xXX)
32#		 Column #2 is the Unicode (in hex as 0xXXXX)
33#		 Column #3 the Unicode name (follows a comment sign, '#')
34#
35#	The entries are in ISO/IEC 8859-1 order.
36#
37#	Version history
38#	1.0 version updates 0.1 version by adding mappings for all
39#	control characters.
40#
41#	Updated versions of this file may be found in:
42#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
43#
44#	Any comments or problems, contact <errata@unicode.org>
45#	Please note that <errata@unicode.org> is an archival address;
46#	notices will be checked, but do not expect an immediate response.
47#
48#RISC OS
49# This file was changed to match RISC OS specific characters (0x80 - 0x9f)
50#RISC OS
510x00	0x0000	#	NULL
520x01	0x0001	#	START OF HEADING
530x02	0x0002	#	START OF TEXT
540x03	0x0003	#	END OF TEXT
550x04	0x0004	#	END OF TRANSMISSION
560x05	0x0005	#	ENQUIRY
570x06	0x0006	#	ACKNOWLEDGE
580x07	0x0007	#	BELL
590x08	0x0008	#	BACKSPACE
600x09	0x0009	#	HORIZONTAL TABULATION
610x0A	0x000A	#	LINE FEED
620x0B	0x000B	#	VERTICAL TABULATION
630x0C	0x000C	#	FORM FEED
640x0D	0x000D	#	CARRIAGE RETURN
650x0E	0x000E	#	SHIFT OUT
660x0F	0x000F	#	SHIFT IN
670x10	0x0010	#	DATA LINK ESCAPE
680x11	0x0011	#	DEVICE CONTROL ONE
690x12	0x0012	#	DEVICE CONTROL TWO
700x13	0x0013	#	DEVICE CONTROL THREE
710x14	0x0014	#	DEVICE CONTROL FOUR
720x15	0x0015	#	NEGATIVE ACKNOWLEDGE
730x16	0x0016	#	SYNCHRONOUS IDLE
740x17	0x0017	#	END OF TRANSMISSION BLOCK
750x18	0x0018	#	CANCEL
760x19	0x0019	#	END OF MEDIUM
770x1A	0x001A	#	SUBSTITUTE
780x1B	0x001B	#	ESCAPE
790x1C	0x001C	#	FILE SEPARATOR
800x1D	0x001D	#	GROUP SEPARATOR
810x1E	0x001E	#	RECORD SEPARATOR
820x1F	0x001F	#	UNIT SEPARATOR
830x20	0x0020	#	SPACE
840x21	0x0021	#	EXCLAMATION MARK
850x22	0x0022	#	QUOTATION MARK
860x23	0x0023	#	NUMBER SIGN
870x24	0x0024	#	DOLLAR SIGN
880x25	0x0025	#	PERCENT SIGN
890x26	0x0026	#	AMPERSAND
900x27	0x0027	#	APOSTROPHE
910x28	0x0028	#	LEFT PARENTHESIS
920x29	0x0029	#	RIGHT PARENTHESIS
930x2A	0x002A	#	ASTERISK
940x2B	0x002B	#	PLUS SIGN
950x2C	0x002C	#	COMMA
960x2D	0x002D	#	HYPHEN-MINUS
970x2E	0x002E	#	FULL STOP
980x2F	0x002F	#	SOLIDUS
990x30	0x0030	#	DIGIT ZERO
1000x31	0x0031	#	DIGIT ONE
1010x32	0x0032	#	DIGIT TWO
1020x33	0x0033	#	DIGIT THREE
1030x34	0x0034	#	DIGIT FOUR
1040x35	0x0035	#	DIGIT FIVE
1050x36	0x0036	#	DIGIT SIX
1060x37	0x0037	#	DIGIT SEVEN
1070x38	0x0038	#	DIGIT EIGHT
1080x39	0x0039	#	DIGIT NINE
1090x3A	0x003A	#	COLON
1100x3B	0x003B	#	SEMICOLON
1110x3C	0x003C	#	LESS-THAN SIGN
1120x3D	0x003D	#	EQUALS SIGN
1130x3E	0x003E	#	GREATER-THAN SIGN
1140x3F	0x003F	#	QUESTION MARK
1150x40	0x0040	#	COMMERCIAL AT
1160x41	0x0041	#	LATIN CAPITAL LETTER A
1170x42	0x0042	#	LATIN CAPITAL LETTER B
1180x43	0x0043	#	LATIN CAPITAL LETTER C
1190x44	0x0044	#	LATIN CAPITAL LETTER D
1200x45	0x0045	#	LATIN CAPITAL LETTER E
1210x46	0x0046	#	LATIN CAPITAL LETTER F
1220x47	0x0047	#	LATIN CAPITAL LETTER G
1230x48	0x0048	#	LATIN CAPITAL LETTER H
1240x49	0x0049	#	LATIN CAPITAL LETTER I
1250x4A	0x004A	#	LATIN CAPITAL LETTER J
1260x4B	0x004B	#	LATIN CAPITAL LETTER K
1270x4C	0x004C	#	LATIN CAPITAL LETTER L
1280x4D	0x004D	#	LATIN CAPITAL LETTER M
1290x4E	0x004E	#	LATIN CAPITAL LETTER N
1300x4F	0x004F	#	LATIN CAPITAL LETTER O
1310x50	0x0050	#	LATIN CAPITAL LETTER P
1320x51	0x0051	#	LATIN CAPITAL LETTER Q
1330x52	0x0052	#	LATIN CAPITAL LETTER R
1340x53	0x0053	#	LATIN CAPITAL LETTER S
1350x54	0x0054	#	LATIN CAPITAL LETTER T
1360x55	0x0055	#	LATIN CAPITAL LETTER U
1370x56	0x0056	#	LATIN CAPITAL LETTER V
1380x57	0x0057	#	LATIN CAPITAL LETTER W
1390x58	0x0058	#	LATIN CAPITAL LETTER X
1400x59	0x0059	#	LATIN CAPITAL LETTER Y
1410x5A	0x005A	#	LATIN CAPITAL LETTER Z
1420x5B	0x005B	#	LEFT SQUARE BRACKET
1430x5C	0x005C	#	REVERSE SOLIDUS
1440x5D	0x005D	#	RIGHT SQUARE BRACKET
1450x5E	0x005E	#	CIRCUMFLEX ACCENT
1460x5F	0x005F	#	LOW LINE
1470x60	0x0060	#	GRAVE ACCENT
1480x61	0x0061	#	LATIN SMALL LETTER A
1490x62	0x0062	#	LATIN SMALL LETTER B
1500x63	0x0063	#	LATIN SMALL LETTER C
1510x64	0x0064	#	LATIN SMALL LETTER D
1520x65	0x0065	#	LATIN SMALL LETTER E
1530x66	0x0066	#	LATIN SMALL LETTER F
1540x67	0x0067	#	LATIN SMALL LETTER G
1550x68	0x0068	#	LATIN SMALL LETTER H
1560x69	0x0069	#	LATIN SMALL LETTER I
1570x6A	0x006A	#	LATIN SMALL LETTER J
1580x6B	0x006B	#	LATIN SMALL LETTER K
1590x6C	0x006C	#	LATIN SMALL LETTER L
1600x6D	0x006D	#	LATIN SMALL LETTER M
1610x6E	0x006E	#	LATIN SMALL LETTER N
1620x6F	0x006F	#	LATIN SMALL LETTER O
1630x70	0x0070	#	LATIN SMALL LETTER P
1640x71	0x0071	#	LATIN SMALL LETTER Q
1650x72	0x0072	#	LATIN SMALL LETTER R
1660x73	0x0073	#	LATIN SMALL LETTER S
1670x74	0x0074	#	LATIN SMALL LETTER T
1680x75	0x0075	#	LATIN SMALL LETTER U
1690x76	0x0076	#	LATIN SMALL LETTER V
1700x77	0x0077	#	LATIN SMALL LETTER W
1710x78	0x0078	#	LATIN SMALL LETTER X
1720x79	0x0079	#	LATIN SMALL LETTER Y
1730x7A	0x007A	#	LATIN SMALL LETTER Z
1740x7B	0x007B	#	LEFT CURLY BRACKET
1750x7C	0x007C	#	VERTICAL LINE
1760x7D	0x007D	#	RIGHT CURLY BRACKET
1770x7E	0x007E	#	TILDE
1780x7F	0x007F	#	DELETE
1790x80	0x0080	#	<control>
1800x81	0x0174	#	CAPITAL W CIRCUMFLEX ACCENT
1810x82	0x0175	#	SMALL W CIRCUMFLEX ACCENT
1820x83	0x0083	#	<control>
1830x84	0x0084	#	<control>
1840x85	0x0176	#	CAPITAL Y CIRCUMFLEX ACCENT
1850x86	0x0177	#	SMALL Y CIRCUMFLEX ACCENT
1860x87	0x0087	#	<control>
1870x88	0x0088	#	<control>
1880x89	0x0089	#	<control>
1890x8A	0x008A	#	<control>
1900x8B	0x008B	#	<control>
1910x8C	0x2026	#	ELLIPSIS
1920x8D	0x2122	#	TRADEMARK
1930x8E	0x2030	#	PER MILLE SIGN
1940x8F	0x2022	#	BULLET
1950x90	0x2018	#	LEFT SINGLE QUOTE
1960x91	0x2019	#	RIGHT SINGLE QUOTE
1970x92	0x2039	#	LEFT SINGLE QUOTATION MARK
1980x93	0x203A	#	RIGHT SINGLE QUOTATION MARK
1990x94	0x201C	#	OPENING DOUBLE QUOTE
2000x95	0x201D	#	CLOSING DOUBLE QUOTE
2010x96	0x201E	#	LOW DOUBLE QUOTE
2020x97	0x2013	#	EN DASH
2030x98	0x2014	#	EM_DASH
2040x99	0x2011	#	NON BREAKING HYPHEN
2050x9A	0x0152	#	LATIN CAPITAL LIGATURE OE
2060x9B	0x0153	#	LATIN SMALL LIGATURE OE
2070x9C	0x2020	#	DAGGER
2080x9D	0x2021	#	DOUBLE DAGGER
2090x9E	0xFB01	#	Fi
2100x9F	0xFB02	#	Fl
2110xA0	0x00A0	#	NO-BREAK SPACE
2120xA1	0x00A1	#	INVERTED EXCLAMATION MARK
2130xA2	0x00A2	#	CENT SIGN
2140xA3	0x00A3	#	POUND SIGN
2150xA4	0x00A4	#	CURRENCY SIGN
2160xA5	0x00A5	#	YEN SIGN
2170xA6	0x00A6	#	BROKEN BAR
2180xA7	0x00A7	#	SECTION SIGN
2190xA8	0x00A8	#	DIAERESIS
2200xA9	0x00A9	#	COPYRIGHT SIGN
2210xAA	0x00AA	#	FEMININE ORDINAL INDICATOR
2220xAB	0x00AB	#	LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
2230xAC	0x00AC	#	NOT SIGN
2240xAD	0x00AD	#	SOFT HYPHEN
2250xAE	0x00AE	#	REGISTERED SIGN
2260xAF	0x00AF	#	MACRON
2270xB0	0x00B0	#	DEGREE SIGN
2280xB1	0x00B1	#	PLUS-MINUS SIGN
2290xB2	0x00B2	#	SUPERSCRIPT TWO
2300xB3	0x00B3	#	SUPERSCRIPT THREE
2310xB4	0x00B4	#	ACUTE ACCENT
2320xB5	0x00B5	#	MICRO SIGN
2330xB6	0x00B6	#	PILCROW SIGN
2340xB7	0x00B7	#	MIDDLE DOT
2350xB8	0x00B8	#	CEDILLA
2360xB9	0x00B9	#	SUPERSCRIPT ONE
2370xBA	0x00BA	#	MASCULINE ORDINAL INDICATOR
2380xBB	0x00BB	#	RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
2390xBC	0x00BC	#	VULGAR FRACTION ONE QUARTER
2400xBD	0x00BD	#	VULGAR FRACTION ONE HALF
2410xBE	0x00BE	#	VULGAR FRACTION THREE QUARTERS
2420xBF	0x00BF	#	INVERTED QUESTION MARK
2430xC0	0x00C0	#	LATIN CAPITAL LETTER A WITH GRAVE
2440xC1	0x00C1	#	LATIN CAPITAL LETTER A WITH ACUTE
2450xC2	0x00C2	#	LATIN CAPITAL LETTER A WITH CIRCUMFLEX
2460xC3	0x00C3	#	LATIN CAPITAL LETTER A WITH TILDE
2470xC4	0x00C4	#	LATIN CAPITAL LETTER A WITH DIAERESIS
2480xC5	0x00C5	#	LATIN CAPITAL LETTER A WITH RING ABOVE
2490xC6	0x00C6	#	LATIN CAPITAL LETTER AE
2500xC7	0x00C7	#	LATIN CAPITAL LETTER C WITH CEDILLA
2510xC8	0x00C8	#	LATIN CAPITAL LETTER E WITH GRAVE
2520xC9	0x00C9	#	LATIN CAPITAL LETTER E WITH ACUTE
2530xCA	0x00CA	#	LATIN CAPITAL LETTER E WITH CIRCUMFLEX
2540xCB	0x00CB	#	LATIN CAPITAL LETTER E WITH DIAERESIS
2550xCC	0x00CC	#	LATIN CAPITAL LETTER I WITH GRAVE
2560xCD	0x00CD	#	LATIN CAPITAL LETTER I WITH ACUTE
2570xCE	0x00CE	#	LATIN CAPITAL LETTER I WITH CIRCUMFLEX
2580xCF	0x00CF	#	LATIN CAPITAL LETTER I WITH DIAERESIS
2590xD0	0x00D0	#	LATIN CAPITAL LETTER ETH (Icelandic)
2600xD1	0x00D1	#	LATIN CAPITAL LETTER N WITH TILDE
2610xD2	0x00D2	#	LATIN CAPITAL LETTER O WITH GRAVE
2620xD3	0x00D3	#	LATIN CAPITAL LETTER O WITH ACUTE
2630xD4	0x00D4	#	LATIN CAPITAL LETTER O WITH CIRCUMFLEX
2640xD5	0x00D5	#	LATIN CAPITAL LETTER O WITH TILDE
2650xD6	0x00D6	#	LATIN CAPITAL LETTER O WITH DIAERESIS
2660xD7	0x00D7	#	MULTIPLICATION SIGN
2670xD8	0x00D8	#	LATIN CAPITAL LETTER O WITH STROKE
2680xD9	0x00D9	#	LATIN CAPITAL LETTER U WITH GRAVE
2690xDA	0x00DA	#	LATIN CAPITAL LETTER U WITH ACUTE
2700xDB	0x00DB	#	LATIN CAPITAL LETTER U WITH CIRCUMFLEX
2710xDC	0x00DC	#	LATIN CAPITAL LETTER U WITH DIAERESIS
2720xDD	0x00DD	#	LATIN CAPITAL LETTER Y WITH ACUTE
2730xDE	0x00DE	#	LATIN CAPITAL LETTER THORN (Icelandic)
2740xDF	0x00DF	#	LATIN SMALL LETTER SHARP S (German)
2750xE0	0x00E0	#	LATIN SMALL LETTER A WITH GRAVE
2760xE1	0x00E1	#	LATIN SMALL LETTER A WITH ACUTE
2770xE2	0x00E2	#	LATIN SMALL LETTER A WITH CIRCUMFLEX
2780xE3	0x00E3	#	LATIN SMALL LETTER A WITH TILDE
2790xE4	0x00E4	#	LATIN SMALL LETTER A WITH DIAERESIS
2800xE5	0x00E5	#	LATIN SMALL LETTER A WITH RING ABOVE
2810xE6	0x00E6	#	LATIN SMALL LETTER AE
2820xE7	0x00E7	#	LATIN SMALL LETTER C WITH CEDILLA
2830xE8	0x00E8	#	LATIN SMALL LETTER E WITH GRAVE
2840xE9	0x00E9	#	LATIN SMALL LETTER E WITH ACUTE
2850xEA	0x00EA	#	LATIN SMALL LETTER E WITH CIRCUMFLEX
2860xEB	0x00EB	#	LATIN SMALL LETTER E WITH DIAERESIS
2870xEC	0x00EC	#	LATIN SMALL LETTER I WITH GRAVE
2880xED	0x00ED	#	LATIN SMALL LETTER I WITH ACUTE
2890xEE	0x00EE	#	LATIN SMALL LETTER I WITH CIRCUMFLEX
2900xEF	0x00EF	#	LATIN SMALL LETTER I WITH DIAERESIS
2910xF0	0x00F0	#	LATIN SMALL LETTER ETH (Icelandic)
2920xF1	0x00F1	#	LATIN SMALL LETTER N WITH TILDE
2930xF2	0x00F2	#	LATIN SMALL LETTER O WITH GRAVE
2940xF3	0x00F3	#	LATIN SMALL LETTER O WITH ACUTE
2950xF4	0x00F4	#	LATIN SMALL LETTER O WITH CIRCUMFLEX
2960xF5	0x00F5	#	LATIN SMALL LETTER O WITH TILDE
2970xF6	0x00F6	#	LATIN SMALL LETTER O WITH DIAERESIS
2980xF7	0x00F7	#	DIVISION SIGN
2990xF8	0x00F8	#	LATIN SMALL LETTER O WITH STROKE
3000xF9	0x00F9	#	LATIN SMALL LETTER U WITH GRAVE
3010xFA	0x00FA	#	LATIN SMALL LETTER U WITH ACUTE
3020xFB	0x00FB	#	LATIN SMALL LETTER U WITH CIRCUMFLEX
3030xFC	0x00FC	#	LATIN SMALL LETTER U WITH DIAERESIS
3040xFD	0x00FD	#	LATIN SMALL LETTER Y WITH ACUTE
3050xFE	0x00FE	#	LATIN SMALL LETTER THORN (Icelandic)
3060xFF	0x00FF	#	LATIN SMALL LETTER Y WITH DIAERESIS
307