xref: /PHP-8.1/ext/mbstring/tests/data/8859-1.txt (revision 84c180d8)
1# 8859-1.TXT
2# Date: 2015-12-02 20:19:00 GMT [KW]
3# © 2015 Unicode®, Inc.
4# For terms of use, see http://www.unicode.org/terms_of_use.html
5#
6#	Name:             ISO/IEC 8859-1:1998 to Unicode
7#	Unicode version:  3.0
8#	Table version:    2.0
9#	Table format:     Format A
10#	Date:             1999 July 27 (header updated: 2015 December 02)
11#	Authors:          Ken Whistler <ken@unicode.org>
12#
13#	General notes:
14#
15#	This table contains the data the Unicode Consortium has on how
16#       ISO/IEC 8859-1:1998 characters map into Unicode.
17#
18#	Format:  Three tab-separated columns
19#		 Column #1 is the ISO/IEC 8859-1 code (in hex as 0xXX)
20#		 Column #2 is the Unicode (in hex as 0xXXXX)
21#		 Column #3 the Unicode name (follows a comment sign, '#')
22#
23#	The entries are in ISO/IEC 8859-1 order.
24#
25#	Version history
26#   1.0 version: updates 0.1 version by adding mappings for all
27#       control characters.
28#   2.0 version: updates to copyright notice and terms of use; no
29#       changes to character mappings
30#
31#	Updated versions of this file may be found in:
32#		http://www.unicode.org/Public/MAPPINGS/
33#
34#	Any comments or problems, contact us at:
35#       http://www.unicode.org/reporting.html
36#
370x00	0x0000	#	NULL
380x01	0x0001	#	START OF HEADING
390x02	0x0002	#	START OF TEXT
400x03	0x0003	#	END OF TEXT
410x04	0x0004	#	END OF TRANSMISSION
420x05	0x0005	#	ENQUIRY
430x06	0x0006	#	ACKNOWLEDGE
440x07	0x0007	#	BELL
450x08	0x0008	#	BACKSPACE
460x09	0x0009	#	HORIZONTAL TABULATION
470x0A	0x000A	#	LINE FEED
480x0B	0x000B	#	VERTICAL TABULATION
490x0C	0x000C	#	FORM FEED
500x0D	0x000D	#	CARRIAGE RETURN
510x0E	0x000E	#	SHIFT OUT
520x0F	0x000F	#	SHIFT IN
530x10	0x0010	#	DATA LINK ESCAPE
540x11	0x0011	#	DEVICE CONTROL ONE
550x12	0x0012	#	DEVICE CONTROL TWO
560x13	0x0013	#	DEVICE CONTROL THREE
570x14	0x0014	#	DEVICE CONTROL FOUR
580x15	0x0015	#	NEGATIVE ACKNOWLEDGE
590x16	0x0016	#	SYNCHRONOUS IDLE
600x17	0x0017	#	END OF TRANSMISSION BLOCK
610x18	0x0018	#	CANCEL
620x19	0x0019	#	END OF MEDIUM
630x1A	0x001A	#	SUBSTITUTE
640x1B	0x001B	#	ESCAPE
650x1C	0x001C	#	FILE SEPARATOR
660x1D	0x001D	#	GROUP SEPARATOR
670x1E	0x001E	#	RECORD SEPARATOR
680x1F	0x001F	#	UNIT SEPARATOR
690x20	0x0020	#	SPACE
700x21	0x0021	#	EXCLAMATION MARK
710x22	0x0022	#	QUOTATION MARK
720x23	0x0023	#	NUMBER SIGN
730x24	0x0024	#	DOLLAR SIGN
740x25	0x0025	#	PERCENT SIGN
750x26	0x0026	#	AMPERSAND
760x27	0x0027	#	APOSTROPHE
770x28	0x0028	#	LEFT PARENTHESIS
780x29	0x0029	#	RIGHT PARENTHESIS
790x2A	0x002A	#	ASTERISK
800x2B	0x002B	#	PLUS SIGN
810x2C	0x002C	#	COMMA
820x2D	0x002D	#	HYPHEN-MINUS
830x2E	0x002E	#	FULL STOP
840x2F	0x002F	#	SOLIDUS
850x30	0x0030	#	DIGIT ZERO
860x31	0x0031	#	DIGIT ONE
870x32	0x0032	#	DIGIT TWO
880x33	0x0033	#	DIGIT THREE
890x34	0x0034	#	DIGIT FOUR
900x35	0x0035	#	DIGIT FIVE
910x36	0x0036	#	DIGIT SIX
920x37	0x0037	#	DIGIT SEVEN
930x38	0x0038	#	DIGIT EIGHT
940x39	0x0039	#	DIGIT NINE
950x3A	0x003A	#	COLON
960x3B	0x003B	#	SEMICOLON
970x3C	0x003C	#	LESS-THAN SIGN
980x3D	0x003D	#	EQUALS SIGN
990x3E	0x003E	#	GREATER-THAN SIGN
1000x3F	0x003F	#	QUESTION MARK
1010x40	0x0040	#	COMMERCIAL AT
1020x41	0x0041	#	LATIN CAPITAL LETTER A
1030x42	0x0042	#	LATIN CAPITAL LETTER B
1040x43	0x0043	#	LATIN CAPITAL LETTER C
1050x44	0x0044	#	LATIN CAPITAL LETTER D
1060x45	0x0045	#	LATIN CAPITAL LETTER E
1070x46	0x0046	#	LATIN CAPITAL LETTER F
1080x47	0x0047	#	LATIN CAPITAL LETTER G
1090x48	0x0048	#	LATIN CAPITAL LETTER H
1100x49	0x0049	#	LATIN CAPITAL LETTER I
1110x4A	0x004A	#	LATIN CAPITAL LETTER J
1120x4B	0x004B	#	LATIN CAPITAL LETTER K
1130x4C	0x004C	#	LATIN CAPITAL LETTER L
1140x4D	0x004D	#	LATIN CAPITAL LETTER M
1150x4E	0x004E	#	LATIN CAPITAL LETTER N
1160x4F	0x004F	#	LATIN CAPITAL LETTER O
1170x50	0x0050	#	LATIN CAPITAL LETTER P
1180x51	0x0051	#	LATIN CAPITAL LETTER Q
1190x52	0x0052	#	LATIN CAPITAL LETTER R
1200x53	0x0053	#	LATIN CAPITAL LETTER S
1210x54	0x0054	#	LATIN CAPITAL LETTER T
1220x55	0x0055	#	LATIN CAPITAL LETTER U
1230x56	0x0056	#	LATIN CAPITAL LETTER V
1240x57	0x0057	#	LATIN CAPITAL LETTER W
1250x58	0x0058	#	LATIN CAPITAL LETTER X
1260x59	0x0059	#	LATIN CAPITAL LETTER Y
1270x5A	0x005A	#	LATIN CAPITAL LETTER Z
1280x5B	0x005B	#	LEFT SQUARE BRACKET
1290x5C	0x005C	#	REVERSE SOLIDUS
1300x5D	0x005D	#	RIGHT SQUARE BRACKET
1310x5E	0x005E	#	CIRCUMFLEX ACCENT
1320x5F	0x005F	#	LOW LINE
1330x60	0x0060	#	GRAVE ACCENT
1340x61	0x0061	#	LATIN SMALL LETTER A
1350x62	0x0062	#	LATIN SMALL LETTER B
1360x63	0x0063	#	LATIN SMALL LETTER C
1370x64	0x0064	#	LATIN SMALL LETTER D
1380x65	0x0065	#	LATIN SMALL LETTER E
1390x66	0x0066	#	LATIN SMALL LETTER F
1400x67	0x0067	#	LATIN SMALL LETTER G
1410x68	0x0068	#	LATIN SMALL LETTER H
1420x69	0x0069	#	LATIN SMALL LETTER I
1430x6A	0x006A	#	LATIN SMALL LETTER J
1440x6B	0x006B	#	LATIN SMALL LETTER K
1450x6C	0x006C	#	LATIN SMALL LETTER L
1460x6D	0x006D	#	LATIN SMALL LETTER M
1470x6E	0x006E	#	LATIN SMALL LETTER N
1480x6F	0x006F	#	LATIN SMALL LETTER O
1490x70	0x0070	#	LATIN SMALL LETTER P
1500x71	0x0071	#	LATIN SMALL LETTER Q
1510x72	0x0072	#	LATIN SMALL LETTER R
1520x73	0x0073	#	LATIN SMALL LETTER S
1530x74	0x0074	#	LATIN SMALL LETTER T
1540x75	0x0075	#	LATIN SMALL LETTER U
1550x76	0x0076	#	LATIN SMALL LETTER V
1560x77	0x0077	#	LATIN SMALL LETTER W
1570x78	0x0078	#	LATIN SMALL LETTER X
1580x79	0x0079	#	LATIN SMALL LETTER Y
1590x7A	0x007A	#	LATIN SMALL LETTER Z
1600x7B	0x007B	#	LEFT CURLY BRACKET
1610x7C	0x007C	#	VERTICAL LINE
1620x7D	0x007D	#	RIGHT CURLY BRACKET
1630x7E	0x007E	#	TILDE
1640x7F	0x007F	#	DELETE
1650x80	0x0080	#	<control>
1660x81	0x0081	#	<control>
1670x82	0x0082	#	<control>
1680x83	0x0083	#	<control>
1690x84	0x0084	#	<control>
1700x85	0x0085	#	<control>
1710x86	0x0086	#	<control>
1720x87	0x0087	#	<control>
1730x88	0x0088	#	<control>
1740x89	0x0089	#	<control>
1750x8A	0x008A	#	<control>
1760x8B	0x008B	#	<control>
1770x8C	0x008C	#	<control>
1780x8D	0x008D	#	<control>
1790x8E	0x008E	#	<control>
1800x8F	0x008F	#	<control>
1810x90	0x0090	#	<control>
1820x91	0x0091	#	<control>
1830x92	0x0092	#	<control>
1840x93	0x0093	#	<control>
1850x94	0x0094	#	<control>
1860x95	0x0095	#	<control>
1870x96	0x0096	#	<control>
1880x97	0x0097	#	<control>
1890x98	0x0098	#	<control>
1900x99	0x0099	#	<control>
1910x9A	0x009A	#	<control>
1920x9B	0x009B	#	<control>
1930x9C	0x009C	#	<control>
1940x9D	0x009D	#	<control>
1950x9E	0x009E	#	<control>
1960x9F	0x009F	#	<control>
1970xA0	0x00A0	#	NO-BREAK SPACE
1980xA1	0x00A1	#	INVERTED EXCLAMATION MARK
1990xA2	0x00A2	#	CENT SIGN
2000xA3	0x00A3	#	POUND SIGN
2010xA4	0x00A4	#	CURRENCY SIGN
2020xA5	0x00A5	#	YEN SIGN
2030xA6	0x00A6	#	BROKEN BAR
2040xA7	0x00A7	#	SECTION SIGN
2050xA8	0x00A8	#	DIAERESIS
2060xA9	0x00A9	#	COPYRIGHT SIGN
2070xAA	0x00AA	#	FEMININE ORDINAL INDICATOR
2080xAB	0x00AB	#	LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
2090xAC	0x00AC	#	NOT SIGN
2100xAD	0x00AD	#	SOFT HYPHEN
2110xAE	0x00AE	#	REGISTERED SIGN
2120xAF	0x00AF	#	MACRON
2130xB0	0x00B0	#	DEGREE SIGN
2140xB1	0x00B1	#	PLUS-MINUS SIGN
2150xB2	0x00B2	#	SUPERSCRIPT TWO
2160xB3	0x00B3	#	SUPERSCRIPT THREE
2170xB4	0x00B4	#	ACUTE ACCENT
2180xB5	0x00B5	#	MICRO SIGN
2190xB6	0x00B6	#	PILCROW SIGN
2200xB7	0x00B7	#	MIDDLE DOT
2210xB8	0x00B8	#	CEDILLA
2220xB9	0x00B9	#	SUPERSCRIPT ONE
2230xBA	0x00BA	#	MASCULINE ORDINAL INDICATOR
2240xBB	0x00BB	#	RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
2250xBC	0x00BC	#	VULGAR FRACTION ONE QUARTER
2260xBD	0x00BD	#	VULGAR FRACTION ONE HALF
2270xBE	0x00BE	#	VULGAR FRACTION THREE QUARTERS
2280xBF	0x00BF	#	INVERTED QUESTION MARK
2290xC0	0x00C0	#	LATIN CAPITAL LETTER A WITH GRAVE
2300xC1	0x00C1	#	LATIN CAPITAL LETTER A WITH ACUTE
2310xC2	0x00C2	#	LATIN CAPITAL LETTER A WITH CIRCUMFLEX
2320xC3	0x00C3	#	LATIN CAPITAL LETTER A WITH TILDE
2330xC4	0x00C4	#	LATIN CAPITAL LETTER A WITH DIAERESIS
2340xC5	0x00C5	#	LATIN CAPITAL LETTER A WITH RING ABOVE
2350xC6	0x00C6	#	LATIN CAPITAL LETTER AE
2360xC7	0x00C7	#	LATIN CAPITAL LETTER C WITH CEDILLA
2370xC8	0x00C8	#	LATIN CAPITAL LETTER E WITH GRAVE
2380xC9	0x00C9	#	LATIN CAPITAL LETTER E WITH ACUTE
2390xCA	0x00CA	#	LATIN CAPITAL LETTER E WITH CIRCUMFLEX
2400xCB	0x00CB	#	LATIN CAPITAL LETTER E WITH DIAERESIS
2410xCC	0x00CC	#	LATIN CAPITAL LETTER I WITH GRAVE
2420xCD	0x00CD	#	LATIN CAPITAL LETTER I WITH ACUTE
2430xCE	0x00CE	#	LATIN CAPITAL LETTER I WITH CIRCUMFLEX
2440xCF	0x00CF	#	LATIN CAPITAL LETTER I WITH DIAERESIS
2450xD0	0x00D0	#	LATIN CAPITAL LETTER ETH (Icelandic)
2460xD1	0x00D1	#	LATIN CAPITAL LETTER N WITH TILDE
2470xD2	0x00D2	#	LATIN CAPITAL LETTER O WITH GRAVE
2480xD3	0x00D3	#	LATIN CAPITAL LETTER O WITH ACUTE
2490xD4	0x00D4	#	LATIN CAPITAL LETTER O WITH CIRCUMFLEX
2500xD5	0x00D5	#	LATIN CAPITAL LETTER O WITH TILDE
2510xD6	0x00D6	#	LATIN CAPITAL LETTER O WITH DIAERESIS
2520xD7	0x00D7	#	MULTIPLICATION SIGN
2530xD8	0x00D8	#	LATIN CAPITAL LETTER O WITH STROKE
2540xD9	0x00D9	#	LATIN CAPITAL LETTER U WITH GRAVE
2550xDA	0x00DA	#	LATIN CAPITAL LETTER U WITH ACUTE
2560xDB	0x00DB	#	LATIN CAPITAL LETTER U WITH CIRCUMFLEX
2570xDC	0x00DC	#	LATIN CAPITAL LETTER U WITH DIAERESIS
2580xDD	0x00DD	#	LATIN CAPITAL LETTER Y WITH ACUTE
2590xDE	0x00DE	#	LATIN CAPITAL LETTER THORN (Icelandic)
2600xDF	0x00DF	#	LATIN SMALL LETTER SHARP S (German)
2610xE0	0x00E0	#	LATIN SMALL LETTER A WITH GRAVE
2620xE1	0x00E1	#	LATIN SMALL LETTER A WITH ACUTE
2630xE2	0x00E2	#	LATIN SMALL LETTER A WITH CIRCUMFLEX
2640xE3	0x00E3	#	LATIN SMALL LETTER A WITH TILDE
2650xE4	0x00E4	#	LATIN SMALL LETTER A WITH DIAERESIS
2660xE5	0x00E5	#	LATIN SMALL LETTER A WITH RING ABOVE
2670xE6	0x00E6	#	LATIN SMALL LETTER AE
2680xE7	0x00E7	#	LATIN SMALL LETTER C WITH CEDILLA
2690xE8	0x00E8	#	LATIN SMALL LETTER E WITH GRAVE
2700xE9	0x00E9	#	LATIN SMALL LETTER E WITH ACUTE
2710xEA	0x00EA	#	LATIN SMALL LETTER E WITH CIRCUMFLEX
2720xEB	0x00EB	#	LATIN SMALL LETTER E WITH DIAERESIS
2730xEC	0x00EC	#	LATIN SMALL LETTER I WITH GRAVE
2740xED	0x00ED	#	LATIN SMALL LETTER I WITH ACUTE
2750xEE	0x00EE	#	LATIN SMALL LETTER I WITH CIRCUMFLEX
2760xEF	0x00EF	#	LATIN SMALL LETTER I WITH DIAERESIS
2770xF0	0x00F0	#	LATIN SMALL LETTER ETH (Icelandic)
2780xF1	0x00F1	#	LATIN SMALL LETTER N WITH TILDE
2790xF2	0x00F2	#	LATIN SMALL LETTER O WITH GRAVE
2800xF3	0x00F3	#	LATIN SMALL LETTER O WITH ACUTE
2810xF4	0x00F4	#	LATIN SMALL LETTER O WITH CIRCUMFLEX
2820xF5	0x00F5	#	LATIN SMALL LETTER O WITH TILDE
2830xF6	0x00F6	#	LATIN SMALL LETTER O WITH DIAERESIS
2840xF7	0x00F7	#	DIVISION SIGN
2850xF8	0x00F8	#	LATIN SMALL LETTER O WITH STROKE
2860xF9	0x00F9	#	LATIN SMALL LETTER U WITH GRAVE
2870xFA	0x00FA	#	LATIN SMALL LETTER U WITH ACUTE
2880xFB	0x00FB	#	LATIN SMALL LETTER U WITH CIRCUMFLEX
2890xFC	0x00FC	#	LATIN SMALL LETTER U WITH DIAERESIS
2900xFD	0x00FD	#	LATIN SMALL LETTER Y WITH ACUTE
2910xFE	0x00FE	#	LATIN SMALL LETTER THORN (Icelandic)
2920xFF	0x00FF	#	LATIN SMALL LETTER Y WITH DIAERESIS
293