xref: /php-src/ext/mbstring/tests/data/KOI8-U.txt (revision 335c1b98)
1# KOI8-U.TXT
2# Date: 2016-01-04 23:09:00 GMT [KW]
3# © 2016 Unicode®, Inc.
4# For terms of use, see http://www.unicode.org/terms_of_use.html
5#
6#
7#	Name:             KOI8-U (RFC2319) to Unicode
8#	Unicode version:  5.1
9#	Table version:    2.0
10#	Table format:     Format A
11#	Date:             13 October 2008 (header updated: 2016-January-04)
12#	Authors:          Philippe Verdy <verdy_p AT wanadoo.fr>,
13#	                  Helmut Richter <richter@lrz.de>
14#
15#	General notes:
16#
17#	This table contains the data the Unicode Consortium has on how
18#	KOI8-U characters map into Unicode. The underlying document is the
19#	mapping described in RFC 2319. No statements are made as to whether
20#	this mapping is the same as the mapping defined as "Code Page 878"
21#	with some vendors.
22#
23#	The KOI8-U (RFC2319) encoding is a variant based on KOI8-R (RFC1489),
24#	where the support for four additional Cyrillic letters was added (both small
25#	and capital letters), replacing 8 box-drawing characters. It is still widely
26#	used to encode texts in Ukrainian, Byelorussian and Bulgarian.
27#
28#	Format:  Three tab-separated columns
29#		 Column #1 is the KOI8-U code (in hex as 0xXX)
30#		 Column #2 is the Unicode (in hex as 0xXXXX)
31#		 Column #3 the Unicode name (follows a comment sign, '#')
32#
33#	The entries are in KOI8-U order.
34#
35#	Version history
36#	1.0 version: created.
37#   2.0 version: updates to copyright notice and terms of use; no
38#       changes to character mappings
39#
40#	Updated versions of this file may be found in:
41#		<http://www.unicode.org/Public/MAPPINGS/>
42#
43#	Any comments or problems, contact the Unicode Consortium at:
44#	        <http://www.unicode.org/reporting.html>
45#
460x00	0x0000	#	NULL
470x01	0x0001	#	START OF HEADING
480x02	0x0002	#	START OF TEXT
490x03	0x0003	#	END OF TEXT
500x04	0x0004	#	END OF TRANSMISSION
510x05	0x0005	#	ENQUIRY
520x06	0x0006	#	ACKNOWLEDGE
530x07	0x0007	#	BELL
540x08	0x0008	#	BACKSPACE
550x09	0x0009	#	HORIZONTAL TABULATION
560x0A	0x000A	#	LINE FEED
570x0B	0x000B	#	VERTICAL TABULATION
580x0C	0x000C	#	FORM FEED
590x0D	0x000D	#	CARRIAGE RETURN
600x0E	0x000E	#	SHIFT OUT
610x0F	0x000F	#	SHIFT IN
620x10	0x0010	#	DATA LINK ESCAPE
630x11	0x0011	#	DEVICE CONTROL ONE
640x12	0x0012	#	DEVICE CONTROL TWO
650x13	0x0013	#	DEVICE CONTROL THREE
660x14	0x0014	#	DEVICE CONTROL FOUR
670x15	0x0015	#	NEGATIVE ACKNOWLEDGE
680x16	0x0016	#	SYNCHRONOUS IDLE
690x17	0x0017	#	END OF TRANSMISSION BLOCK
700x18	0x0018	#	CANCEL
710x19	0x0019	#	END OF MEDIUM
720x1A	0x001A	#	SUBSTITUTE
730x1B	0x001B	#	ESCAPE
740x1C	0x001C	#	FILE SEPARATOR
750x1D	0x001D	#	GROUP SEPARATOR
760x1E	0x001E	#	RECORD SEPARATOR
770x1F	0x001F	#	UNIT SEPARATOR
780x20	0x0020	#	SPACE
790x21	0x0021	#	EXCLAMATION MARK
800x22	0x0022	#	QUOTATION MARK
810x23	0x0023	#	NUMBER SIGN
820x24	0x0024	#	DOLLAR SIGN
830x25	0x0025	#	PERCENT SIGN
840x26	0x0026	#	AMPERSAND
850x27	0x0027	#	APOSTROPHE
860x28	0x0028	#	LEFT PARENTHESIS
870x29	0x0029	#	RIGHT PARENTHESIS
880x2A	0x002A	#	ASTERISK
890x2B	0x002B	#	PLUS SIGN
900x2C	0x002C	#	COMMA
910x2D	0x002D	#	HYPHEN-MINUS
920x2E	0x002E	#	FULL STOP
930x2F	0x002F	#	SOLIDUS
940x30	0x0030	#	DIGIT ZERO
950x31	0x0031	#	DIGIT ONE
960x32	0x0032	#	DIGIT TWO
970x33	0x0033	#	DIGIT THREE
980x34	0x0034	#	DIGIT FOUR
990x35	0x0035	#	DIGIT FIVE
1000x36	0x0036	#	DIGIT SIX
1010x37	0x0037	#	DIGIT SEVEN
1020x38	0x0038	#	DIGIT EIGHT
1030x39	0x0039	#	DIGIT NINE
1040x3A	0x003A	#	COLON
1050x3B	0x003B	#	SEMICOLON
1060x3C	0x003C	#	LESS-THAN SIGN
1070x3D	0x003D	#	EQUALS SIGN
1080x3E	0x003E	#	GREATER-THAN SIGN
1090x3F	0x003F	#	QUESTION MARK
1100x40	0x0040	#	COMMERCIAL AT
1110x41	0x0041	#	LATIN CAPITAL LETTER A
1120x42	0x0042	#	LATIN CAPITAL LETTER B
1130x43	0x0043	#	LATIN CAPITAL LETTER C
1140x44	0x0044	#	LATIN CAPITAL LETTER D
1150x45	0x0045	#	LATIN CAPITAL LETTER E
1160x46	0x0046	#	LATIN CAPITAL LETTER F
1170x47	0x0047	#	LATIN CAPITAL LETTER G
1180x48	0x0048	#	LATIN CAPITAL LETTER H
1190x49	0x0049	#	LATIN CAPITAL LETTER I
1200x4A	0x004A	#	LATIN CAPITAL LETTER J
1210x4B	0x004B	#	LATIN CAPITAL LETTER K
1220x4C	0x004C	#	LATIN CAPITAL LETTER L
1230x4D	0x004D	#	LATIN CAPITAL LETTER M
1240x4E	0x004E	#	LATIN CAPITAL LETTER N
1250x4F	0x004F	#	LATIN CAPITAL LETTER O
1260x50	0x0050	#	LATIN CAPITAL LETTER P
1270x51	0x0051	#	LATIN CAPITAL LETTER Q
1280x52	0x0052	#	LATIN CAPITAL LETTER R
1290x53	0x0053	#	LATIN CAPITAL LETTER S
1300x54	0x0054	#	LATIN CAPITAL LETTER T
1310x55	0x0055	#	LATIN CAPITAL LETTER U
1320x56	0x0056	#	LATIN CAPITAL LETTER V
1330x57	0x0057	#	LATIN CAPITAL LETTER W
1340x58	0x0058	#	LATIN CAPITAL LETTER X
1350x59	0x0059	#	LATIN CAPITAL LETTER Y
1360x5A	0x005A	#	LATIN CAPITAL LETTER Z
1370x5B	0x005B	#	LEFT SQUARE BRACKET
1380x5C	0x005C	#	REVERSE SOLIDUS
1390x5D	0x005D	#	RIGHT SQUARE BRACKET
1400x5E	0x005E	#	CIRCUMFLEX ACCENT
1410x5F	0x005F	#	LOW LINE
1420x60	0x0060	#	GRAVE ACCENT
1430x61	0x0061	#	LATIN SMALL LETTER A
1440x62	0x0062	#	LATIN SMALL LETTER B
1450x63	0x0063	#	LATIN SMALL LETTER C
1460x64	0x0064	#	LATIN SMALL LETTER D
1470x65	0x0065	#	LATIN SMALL LETTER E
1480x66	0x0066	#	LATIN SMALL LETTER F
1490x67	0x0067	#	LATIN SMALL LETTER G
1500x68	0x0068	#	LATIN SMALL LETTER H
1510x69	0x0069	#	LATIN SMALL LETTER I
1520x6A	0x006A	#	LATIN SMALL LETTER J
1530x6B	0x006B	#	LATIN SMALL LETTER K
1540x6C	0x006C	#	LATIN SMALL LETTER L
1550x6D	0x006D	#	LATIN SMALL LETTER M
1560x6E	0x006E	#	LATIN SMALL LETTER N
1570x6F	0x006F	#	LATIN SMALL LETTER O
1580x70	0x0070	#	LATIN SMALL LETTER P
1590x71	0x0071	#	LATIN SMALL LETTER Q
1600x72	0x0072	#	LATIN SMALL LETTER R
1610x73	0x0073	#	LATIN SMALL LETTER S
1620x74	0x0074	#	LATIN SMALL LETTER T
1630x75	0x0075	#	LATIN SMALL LETTER U
1640x76	0x0076	#	LATIN SMALL LETTER V
1650x77	0x0077	#	LATIN SMALL LETTER W
1660x78	0x0078	#	LATIN SMALL LETTER X
1670x79	0x0079	#	LATIN SMALL LETTER Y
1680x7A	0x007A	#	LATIN SMALL LETTER Z
1690x7B	0x007B	#	LEFT CURLY BRACKET
1700x7C	0x007C	#	VERTICAL LINE
1710x7D	0x007D	#	RIGHT CURLY BRACKET
1720x7E	0x007E	#	TILDE
1730x7F	0x007F	#	DELETE
1740x80	0x2500	#	BOX DRAWINGS LIGHT HORIZONTAL
1750x81	0x2502	#	BOX DRAWINGS LIGHT VERTICAL
1760x82	0x250C	#	BOX DRAWINGS LIGHT DOWN AND RIGHT
1770x83	0x2510	#	BOX DRAWINGS LIGHT DOWN AND LEFT
1780x84	0x2514	#	BOX DRAWINGS LIGHT UP AND RIGHT
1790x85	0x2518	#	BOX DRAWINGS LIGHT UP AND LEFT
1800x86	0x251C	#	BOX DRAWINGS LIGHT VERTICAL AND RIGHT
1810x87	0x2524	#	BOX DRAWINGS LIGHT VERTICAL AND LEFT
1820x88	0x252C	#	BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
1830x89	0x2534	#	BOX DRAWINGS LIGHT UP AND HORIZONTAL
1840x8A	0x253C	#	BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
1850x8B	0x2580	#	UPPER HALF BLOCK
1860x8C	0x2584	#	LOWER HALF BLOCK
1870x8D	0x2588	#	FULL BLOCK
1880x8E	0x258C	#	LEFT HALF BLOCK
1890x8F	0x2590	#	RIGHT HALF BLOCK
1900x90	0x2591	#	LIGHT SHADE
1910x91	0x2592	#	MEDIUM SHADE
1920x92	0x2593	#	DARK SHADE
1930x93	0x2320	#	TOP HALF INTEGRAL
1940x94	0x25A0	#	BLACK SQUARE
1950x95	0x2219	#	BULLET OPERATOR
1960x96	0x221A	#	SQUARE ROOT
1970x97	0x2248	#	ALMOST EQUAL TO
1980x98	0x2264	#	LESS-THAN OR EQUAL TO
1990x99	0x2265	#	GREATER-THAN OR EQUAL TO
2000x9A	0x00A0	#	NO-BREAK SPACE
2010x9B	0x2321	#	BOTTOM HALF INTEGRAL
2020x9C	0x00B0	#	DEGREE SIGN
2030x9D	0x00B2	#	SUPERSCRIPT TWO
2040x9E	0x00B7	#	MIDDLE DOT
2050x9F	0x00F7	#	DIVISION SIGN
2060xA0	0x2550	#	BOX DRAWINGS DOUBLE HORIZONTAL
2070xA1	0x2551	#	BOX DRAWINGS DOUBLE VERTICAL
2080xA2	0x2552	#	BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
2090xA3	0x0451	#	CYRILLIC SMALL LETTER IO
2100xA4	0x0454	#	CYRILLIC SMALL LETTER UKRAINIAN IE
2110xA5	0x2554	#	BOX DRAWINGS DOUBLE DOWN AND RIGHT
2120xA6	0x0456	#	CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
2130xA7	0x0457	#	CYRILLIC SMALL LETTER YI (UKRAINIAN)
2140xA8	0x2557	#	BOX DRAWINGS DOUBLE DOWN AND LEFT
2150xA9	0x2558	#	BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
2160xAA	0x2559	#	BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
2170xAB	0x255A	#	BOX DRAWINGS DOUBLE UP AND RIGHT
2180xAC	0x255B	#	BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
2190xAD	0x0491	#	CYRILLIC SMALL LETTER GHE WITH UPTURN
2200xAE	0x255D	#	BOX DRAWINGS DOUBLE UP AND LEFT
2210xAF	0x255E	#	BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
2220xB0	0x255F	#	BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
2230xB1	0x2560	#	BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
2240xB2	0x2561	#	BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
2250xB3	0x0401	#	CYRILLIC CAPITAL LETTER IO
2260xB4	0x0404	#	CYRILLIC CAPITAL LETTER UKRAINIAN IE
2270xB5	0x2563	#	BOX DRAWINGS DOUBLE VERTICAL AND LEFT
2280xB6	0x0406	#	CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
2290xB7	0x0407	#	CYRILLIC CAPITAL LETTER YI (UKRAINIAN)
2300xB8	0x2566	#	BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
2310xB9	0x2567	#	BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
2320xBA	0x2568	#	BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
2330xBB	0x2569	#	BOX DRAWINGS DOUBLE UP AND HORIZONTAL
2340xBC	0x256A	#	BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
2350xBD	0x0490	#	CYRILLIC CAPITAL LETTER GHE WITH UPTURN
2360xBE	0x256C	#	BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
2370xBF	0x00A9	#	COPYRIGHT SIGN
2380xC0	0x044E	#	CYRILLIC SMALL LETTER YU
2390xC1	0x0430	#	CYRILLIC SMALL LETTER A
2400xC2	0x0431	#	CYRILLIC SMALL LETTER BE
2410xC3	0x0446	#	CYRILLIC SMALL LETTER TSE
2420xC4	0x0434	#	CYRILLIC SMALL LETTER DE
2430xC5	0x0435	#	CYRILLIC SMALL LETTER IE
2440xC6	0x0444	#	CYRILLIC SMALL LETTER EF
2450xC7	0x0433	#	CYRILLIC SMALL LETTER GHE
2460xC8	0x0445	#	CYRILLIC SMALL LETTER HA
2470xC9	0x0438	#	CYRILLIC SMALL LETTER I
2480xCA	0x0439	#	CYRILLIC SMALL LETTER SHORT I
2490xCB	0x043A	#	CYRILLIC SMALL LETTER KA
2500xCC	0x043B	#	CYRILLIC SMALL LETTER EL
2510xCD	0x043C	#	CYRILLIC SMALL LETTER EM
2520xCE	0x043D	#	CYRILLIC SMALL LETTER EN
2530xCF	0x043E	#	CYRILLIC SMALL LETTER O
2540xD0	0x043F	#	CYRILLIC SMALL LETTER PE
2550xD1	0x044F	#	CYRILLIC SMALL LETTER YA
2560xD2	0x0440	#	CYRILLIC SMALL LETTER ER
2570xD3	0x0441	#	CYRILLIC SMALL LETTER ES
2580xD4	0x0442	#	CYRILLIC SMALL LETTER TE
2590xD5	0x0443	#	CYRILLIC SMALL LETTER U
2600xD6	0x0436	#	CYRILLIC SMALL LETTER ZHE
2610xD7	0x0432	#	CYRILLIC SMALL LETTER VE
2620xD8	0x044C	#	CYRILLIC SMALL LETTER SOFT SIGN
2630xD9	0x044B	#	CYRILLIC SMALL LETTER YERU
2640xDA	0x0437	#	CYRILLIC SMALL LETTER ZE
2650xDB	0x0448	#	CYRILLIC SMALL LETTER SHA
2660xDC	0x044D	#	CYRILLIC SMALL LETTER E
2670xDD	0x0449	#	CYRILLIC SMALL LETTER SHCHA
2680xDE	0x0447	#	CYRILLIC SMALL LETTER CHE
2690xDF	0x044A	#	CYRILLIC SMALL LETTER HARD SIGN
2700xE0	0x042E	#	CYRILLIC CAPITAL LETTER YU
2710xE1	0x0410	#	CYRILLIC CAPITAL LETTER A
2720xE2	0x0411	#	CYRILLIC CAPITAL LETTER BE
2730xE3	0x0426	#	CYRILLIC CAPITAL LETTER TSE
2740xE4	0x0414	#	CYRILLIC CAPITAL LETTER DE
2750xE5	0x0415	#	CYRILLIC CAPITAL LETTER IE
2760xE6	0x0424	#	CYRILLIC CAPITAL LETTER EF
2770xE7	0x0413	#	CYRILLIC CAPITAL LETTER GHE
2780xE8	0x0425	#	CYRILLIC CAPITAL LETTER HA
2790xE9	0x0418	#	CYRILLIC CAPITAL LETTER I
2800xEA	0x0419	#	CYRILLIC CAPITAL LETTER SHORT I
2810xEB	0x041A	#	CYRILLIC CAPITAL LETTER KA
2820xEC	0x041B	#	CYRILLIC CAPITAL LETTER EL
2830xED	0x041C	#	CYRILLIC CAPITAL LETTER EM
2840xEE	0x041D	#	CYRILLIC CAPITAL LETTER EN
2850xEF	0x041E	#	CYRILLIC CAPITAL LETTER O
2860xF0	0x041F	#	CYRILLIC CAPITAL LETTER PE
2870xF1	0x042F	#	CYRILLIC CAPITAL LETTER YA
2880xF2	0x0420	#	CYRILLIC CAPITAL LETTER ER
2890xF3	0x0421	#	CYRILLIC CAPITAL LETTER ES
2900xF4	0x0422	#	CYRILLIC CAPITAL LETTER TE
2910xF5	0x0423	#	CYRILLIC CAPITAL LETTER U
2920xF6	0x0416	#	CYRILLIC CAPITAL LETTER ZHE
2930xF7	0x0412	#	CYRILLIC CAPITAL LETTER VE
2940xF8	0x042C	#	CYRILLIC CAPITAL LETTER SOFT SIGN
2950xF9	0x042B	#	CYRILLIC CAPITAL LETTER YERU
2960xFA	0x0417	#	CYRILLIC CAPITAL LETTER ZE
2970xFB	0x0428	#	CYRILLIC CAPITAL LETTER SHA
2980xFC	0x042D	#	CYRILLIC CAPITAL LETTER E
2990xFD	0x0429	#	CYRILLIC CAPITAL LETTER SHCHA
3000xFE	0x0427	#	CYRILLIC CAPITAL LETTER CHE
3010xFF	0x042A	#	CYRILLIC CAPITAL LETTER HARD SIGN
302