xref: /php-src/ext/mbstring/tests/data/KOI8-R.txt (revision 9db4387f)
1# KOI8-R.TXT
2# Date: 2016-01-04 23:05:00 GMT [KW]
3# © 2016 Unicode®, Inc.
4# For terms of use, see http://www.unicode.org/terms_of_use.html
5#
6#	Name:             KOI8-R (RFC1489) to Unicode
7#	Unicode version:  3.0
8#	Table version:    2.0
9#	Table format:     Format A
10#	Date:             18 August 1999 (header updated: 2016-January-04)
11#	Authors:          Helmut Richter <richter@lrz.de>
12#
13#	General notes:
14#
15#	This table contains the data the Unicode Consortium has on how
16#       KOI8-R characters map into Unicode. The underlying document is the
17#	mapping described in RFC 1489. No statements are made as to whether
18#	this mapping is the same as the mapping defined as "Code Page 878"
19#	with some vendors.
20#
21#	Format:  Three tab-separated columns
22#		 Column #1 is the KOI8-R code (in hex as 0xXX)
23#		 Column #2 is the Unicode (in hex as 0xXXXX)
24#		 Column #3 the Unicode name (follows a comment sign, '#')
25#
26#	The entries are in KOI8-R order.
27#
28#	Version history
29#	1.0 version: created.
30#   2.0 version: updates to copyright notice and terms of use; no
31#       changes to character mappings
32#
33#	Updated versions of this file may be found in:
34#		http://www.unicode.org/Public/MAPPINGS/
35#
36#	Any comments or problems, contact us at:
37#       http://www.unicode.org/reporting.html
38#
390x00	0x0000	#	NULL
400x01	0x0001	#	START OF HEADING
410x02	0x0002	#	START OF TEXT
420x03	0x0003	#	END OF TEXT
430x04	0x0004	#	END OF TRANSMISSION
440x05	0x0005	#	ENQUIRY
450x06	0x0006	#	ACKNOWLEDGE
460x07	0x0007	#	BELL
470x08	0x0008	#	BACKSPACE
480x09	0x0009	#	HORIZONTAL TABULATION
490x0A	0x000A	#	LINE FEED
500x0B	0x000B	#	VERTICAL TABULATION
510x0C	0x000C	#	FORM FEED
520x0D	0x000D	#	CARRIAGE RETURN
530x0E	0x000E	#	SHIFT OUT
540x0F	0x000F	#	SHIFT IN
550x10	0x0010	#	DATA LINK ESCAPE
560x11	0x0011	#	DEVICE CONTROL ONE
570x12	0x0012	#	DEVICE CONTROL TWO
580x13	0x0013	#	DEVICE CONTROL THREE
590x14	0x0014	#	DEVICE CONTROL FOUR
600x15	0x0015	#	NEGATIVE ACKNOWLEDGE
610x16	0x0016	#	SYNCHRONOUS IDLE
620x17	0x0017	#	END OF TRANSMISSION BLOCK
630x18	0x0018	#	CANCEL
640x19	0x0019	#	END OF MEDIUM
650x1A	0x001A	#	SUBSTITUTE
660x1B	0x001B	#	ESCAPE
670x1C	0x001C	#	FILE SEPARATOR
680x1D	0x001D	#	GROUP SEPARATOR
690x1E	0x001E	#	RECORD SEPARATOR
700x1F	0x001F	#	UNIT SEPARATOR
710x20	0x0020	#	SPACE
720x21	0x0021	#	EXCLAMATION MARK
730x22	0x0022	#	QUOTATION MARK
740x23	0x0023	#	NUMBER SIGN
750x24	0x0024	#	DOLLAR SIGN
760x25	0x0025	#	PERCENT SIGN
770x26	0x0026	#	AMPERSAND
780x27	0x0027	#	APOSTROPHE
790x28	0x0028	#	LEFT PARENTHESIS
800x29	0x0029	#	RIGHT PARENTHESIS
810x2A	0x002A	#	ASTERISK
820x2B	0x002B	#	PLUS SIGN
830x2C	0x002C	#	COMMA
840x2D	0x002D	#	HYPHEN-MINUS
850x2E	0x002E	#	FULL STOP
860x2F	0x002F	#	SOLIDUS
870x30	0x0030	#	DIGIT ZERO
880x31	0x0031	#	DIGIT ONE
890x32	0x0032	#	DIGIT TWO
900x33	0x0033	#	DIGIT THREE
910x34	0x0034	#	DIGIT FOUR
920x35	0x0035	#	DIGIT FIVE
930x36	0x0036	#	DIGIT SIX
940x37	0x0037	#	DIGIT SEVEN
950x38	0x0038	#	DIGIT EIGHT
960x39	0x0039	#	DIGIT NINE
970x3A	0x003A	#	COLON
980x3B	0x003B	#	SEMICOLON
990x3C	0x003C	#	LESS-THAN SIGN
1000x3D	0x003D	#	EQUALS SIGN
1010x3E	0x003E	#	GREATER-THAN SIGN
1020x3F	0x003F	#	QUESTION MARK
1030x40	0x0040	#	COMMERCIAL AT
1040x41	0x0041	#	LATIN CAPITAL LETTER A
1050x42	0x0042	#	LATIN CAPITAL LETTER B
1060x43	0x0043	#	LATIN CAPITAL LETTER C
1070x44	0x0044	#	LATIN CAPITAL LETTER D
1080x45	0x0045	#	LATIN CAPITAL LETTER E
1090x46	0x0046	#	LATIN CAPITAL LETTER F
1100x47	0x0047	#	LATIN CAPITAL LETTER G
1110x48	0x0048	#	LATIN CAPITAL LETTER H
1120x49	0x0049	#	LATIN CAPITAL LETTER I
1130x4A	0x004A	#	LATIN CAPITAL LETTER J
1140x4B	0x004B	#	LATIN CAPITAL LETTER K
1150x4C	0x004C	#	LATIN CAPITAL LETTER L
1160x4D	0x004D	#	LATIN CAPITAL LETTER M
1170x4E	0x004E	#	LATIN CAPITAL LETTER N
1180x4F	0x004F	#	LATIN CAPITAL LETTER O
1190x50	0x0050	#	LATIN CAPITAL LETTER P
1200x51	0x0051	#	LATIN CAPITAL LETTER Q
1210x52	0x0052	#	LATIN CAPITAL LETTER R
1220x53	0x0053	#	LATIN CAPITAL LETTER S
1230x54	0x0054	#	LATIN CAPITAL LETTER T
1240x55	0x0055	#	LATIN CAPITAL LETTER U
1250x56	0x0056	#	LATIN CAPITAL LETTER V
1260x57	0x0057	#	LATIN CAPITAL LETTER W
1270x58	0x0058	#	LATIN CAPITAL LETTER X
1280x59	0x0059	#	LATIN CAPITAL LETTER Y
1290x5A	0x005A	#	LATIN CAPITAL LETTER Z
1300x5B	0x005B	#	LEFT SQUARE BRACKET
1310x5C	0x005C	#	REVERSE SOLIDUS
1320x5D	0x005D	#	RIGHT SQUARE BRACKET
1330x5E	0x005E	#	CIRCUMFLEX ACCENT
1340x5F	0x005F	#	LOW LINE
1350x60	0x0060	#	GRAVE ACCENT
1360x61	0x0061	#	LATIN SMALL LETTER A
1370x62	0x0062	#	LATIN SMALL LETTER B
1380x63	0x0063	#	LATIN SMALL LETTER C
1390x64	0x0064	#	LATIN SMALL LETTER D
1400x65	0x0065	#	LATIN SMALL LETTER E
1410x66	0x0066	#	LATIN SMALL LETTER F
1420x67	0x0067	#	LATIN SMALL LETTER G
1430x68	0x0068	#	LATIN SMALL LETTER H
1440x69	0x0069	#	LATIN SMALL LETTER I
1450x6A	0x006A	#	LATIN SMALL LETTER J
1460x6B	0x006B	#	LATIN SMALL LETTER K
1470x6C	0x006C	#	LATIN SMALL LETTER L
1480x6D	0x006D	#	LATIN SMALL LETTER M
1490x6E	0x006E	#	LATIN SMALL LETTER N
1500x6F	0x006F	#	LATIN SMALL LETTER O
1510x70	0x0070	#	LATIN SMALL LETTER P
1520x71	0x0071	#	LATIN SMALL LETTER Q
1530x72	0x0072	#	LATIN SMALL LETTER R
1540x73	0x0073	#	LATIN SMALL LETTER S
1550x74	0x0074	#	LATIN SMALL LETTER T
1560x75	0x0075	#	LATIN SMALL LETTER U
1570x76	0x0076	#	LATIN SMALL LETTER V
1580x77	0x0077	#	LATIN SMALL LETTER W
1590x78	0x0078	#	LATIN SMALL LETTER X
1600x79	0x0079	#	LATIN SMALL LETTER Y
1610x7A	0x007A	#	LATIN SMALL LETTER Z
1620x7B	0x007B	#	LEFT CURLY BRACKET
1630x7C	0x007C	#	VERTICAL LINE
1640x7D	0x007D	#	RIGHT CURLY BRACKET
1650x7E	0x007E	#	TILDE
1660x7F	0x007F	#	DELETE
1670x80	0x2500	#	BOX DRAWINGS LIGHT HORIZONTAL
1680x81	0x2502	#	BOX DRAWINGS LIGHT VERTICAL
1690x82	0x250C	#	BOX DRAWINGS LIGHT DOWN AND RIGHT
1700x83	0x2510	#	BOX DRAWINGS LIGHT DOWN AND LEFT
1710x84	0x2514	#	BOX DRAWINGS LIGHT UP AND RIGHT
1720x85	0x2518	#	BOX DRAWINGS LIGHT UP AND LEFT
1730x86	0x251C	#	BOX DRAWINGS LIGHT VERTICAL AND RIGHT
1740x87	0x2524	#	BOX DRAWINGS LIGHT VERTICAL AND LEFT
1750x88	0x252C	#	BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
1760x89	0x2534	#	BOX DRAWINGS LIGHT UP AND HORIZONTAL
1770x8A	0x253C	#	BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
1780x8B	0x2580	#	UPPER HALF BLOCK
1790x8C	0x2584	#	LOWER HALF BLOCK
1800x8D	0x2588	#	FULL BLOCK
1810x8E	0x258C	#	LEFT HALF BLOCK
1820x8F	0x2590	#	RIGHT HALF BLOCK
1830x90	0x2591	#	LIGHT SHADE
1840x91	0x2592	#	MEDIUM SHADE
1850x92	0x2593	#	DARK SHADE
1860x93	0x2320	#	TOP HALF INTEGRAL
1870x94	0x25A0	#	BLACK SQUARE
1880x95	0x2219	#	BULLET OPERATOR
1890x96	0x221A	#	SQUARE ROOT
1900x97	0x2248	#	ALMOST EQUAL TO
1910x98	0x2264	#	LESS-THAN OR EQUAL TO
1920x99	0x2265	#	GREATER-THAN OR EQUAL TO
1930x9A	0x00A0	#	NO-BREAK SPACE
1940x9B	0x2321	#	BOTTOM HALF INTEGRAL
1950x9C	0x00B0	#	DEGREE SIGN
1960x9D	0x00B2	#	SUPERSCRIPT TWO
1970x9E	0x00B7	#	MIDDLE DOT
1980x9F	0x00F7	#	DIVISION SIGN
1990xA0	0x2550	#	BOX DRAWINGS DOUBLE HORIZONTAL
2000xA1	0x2551	#	BOX DRAWINGS DOUBLE VERTICAL
2010xA2	0x2552	#	BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
2020xA3	0x0451	#	CYRILLIC SMALL LETTER IO
2030xA4	0x2553	#	BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
2040xA5	0x2554	#	BOX DRAWINGS DOUBLE DOWN AND RIGHT
2050xA6	0x2555	#	BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
2060xA7	0x2556	#	BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
2070xA8	0x2557	#	BOX DRAWINGS DOUBLE DOWN AND LEFT
2080xA9	0x2558	#	BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
2090xAA	0x2559	#	BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
2100xAB	0x255A	#	BOX DRAWINGS DOUBLE UP AND RIGHT
2110xAC	0x255B	#	BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
2120xAD	0x255C	#	BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
2130xAE	0x255D	#	BOX DRAWINGS DOUBLE UP AND LEFT
2140xAF	0x255E	#	BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
2150xB0	0x255F	#	BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
2160xB1	0x2560	#	BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
2170xB2	0x2561	#	BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
2180xB3	0x0401	#	CYRILLIC CAPITAL LETTER IO
2190xB4	0x2562	#	BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
2200xB5	0x2563	#	BOX DRAWINGS DOUBLE VERTICAL AND LEFT
2210xB6	0x2564	#	BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
2220xB7	0x2565	#	BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
2230xB8	0x2566	#	BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
2240xB9	0x2567	#	BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
2250xBA	0x2568	#	BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
2260xBB	0x2569	#	BOX DRAWINGS DOUBLE UP AND HORIZONTAL
2270xBC	0x256A	#	BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
2280xBD	0x256B	#	BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
2290xBE	0x256C	#	BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
2300xBF	0x00A9	#	COPYRIGHT SIGN
2310xC0	0x044E	#	CYRILLIC SMALL LETTER YU
2320xC1	0x0430	#	CYRILLIC SMALL LETTER A
2330xC2	0x0431	#	CYRILLIC SMALL LETTER BE
2340xC3	0x0446	#	CYRILLIC SMALL LETTER TSE
2350xC4	0x0434	#	CYRILLIC SMALL LETTER DE
2360xC5	0x0435	#	CYRILLIC SMALL LETTER IE
2370xC6	0x0444	#	CYRILLIC SMALL LETTER EF
2380xC7	0x0433	#	CYRILLIC SMALL LETTER GHE
2390xC8	0x0445	#	CYRILLIC SMALL LETTER HA
2400xC9	0x0438	#	CYRILLIC SMALL LETTER I
2410xCA	0x0439	#	CYRILLIC SMALL LETTER SHORT I
2420xCB	0x043A	#	CYRILLIC SMALL LETTER KA
2430xCC	0x043B	#	CYRILLIC SMALL LETTER EL
2440xCD	0x043C	#	CYRILLIC SMALL LETTER EM
2450xCE	0x043D	#	CYRILLIC SMALL LETTER EN
2460xCF	0x043E	#	CYRILLIC SMALL LETTER O
2470xD0	0x043F	#	CYRILLIC SMALL LETTER PE
2480xD1	0x044F	#	CYRILLIC SMALL LETTER YA
2490xD2	0x0440	#	CYRILLIC SMALL LETTER ER
2500xD3	0x0441	#	CYRILLIC SMALL LETTER ES
2510xD4	0x0442	#	CYRILLIC SMALL LETTER TE
2520xD5	0x0443	#	CYRILLIC SMALL LETTER U
2530xD6	0x0436	#	CYRILLIC SMALL LETTER ZHE
2540xD7	0x0432	#	CYRILLIC SMALL LETTER VE
2550xD8	0x044C	#	CYRILLIC SMALL LETTER SOFT SIGN
2560xD9	0x044B	#	CYRILLIC SMALL LETTER YERU
2570xDA	0x0437	#	CYRILLIC SMALL LETTER ZE
2580xDB	0x0448	#	CYRILLIC SMALL LETTER SHA
2590xDC	0x044D	#	CYRILLIC SMALL LETTER E
2600xDD	0x0449	#	CYRILLIC SMALL LETTER SHCHA
2610xDE	0x0447	#	CYRILLIC SMALL LETTER CHE
2620xDF	0x044A	#	CYRILLIC SMALL LETTER HARD SIGN
2630xE0	0x042E	#	CYRILLIC CAPITAL LETTER YU
2640xE1	0x0410	#	CYRILLIC CAPITAL LETTER A
2650xE2	0x0411	#	CYRILLIC CAPITAL LETTER BE
2660xE3	0x0426	#	CYRILLIC CAPITAL LETTER TSE
2670xE4	0x0414	#	CYRILLIC CAPITAL LETTER DE
2680xE5	0x0415	#	CYRILLIC CAPITAL LETTER IE
2690xE6	0x0424	#	CYRILLIC CAPITAL LETTER EF
2700xE7	0x0413	#	CYRILLIC CAPITAL LETTER GHE
2710xE8	0x0425	#	CYRILLIC CAPITAL LETTER HA
2720xE9	0x0418	#	CYRILLIC CAPITAL LETTER I
2730xEA	0x0419	#	CYRILLIC CAPITAL LETTER SHORT I
2740xEB	0x041A	#	CYRILLIC CAPITAL LETTER KA
2750xEC	0x041B	#	CYRILLIC CAPITAL LETTER EL
2760xED	0x041C	#	CYRILLIC CAPITAL LETTER EM
2770xEE	0x041D	#	CYRILLIC CAPITAL LETTER EN
2780xEF	0x041E	#	CYRILLIC CAPITAL LETTER O
2790xF0	0x041F	#	CYRILLIC CAPITAL LETTER PE
2800xF1	0x042F	#	CYRILLIC CAPITAL LETTER YA
2810xF2	0x0420	#	CYRILLIC CAPITAL LETTER ER
2820xF3	0x0421	#	CYRILLIC CAPITAL LETTER ES
2830xF4	0x0422	#	CYRILLIC CAPITAL LETTER TE
2840xF5	0x0423	#	CYRILLIC CAPITAL LETTER U
2850xF6	0x0416	#	CYRILLIC CAPITAL LETTER ZHE
2860xF7	0x0412	#	CYRILLIC CAPITAL LETTER VE
2870xF8	0x042C	#	CYRILLIC CAPITAL LETTER SOFT SIGN
2880xF9	0x042B	#	CYRILLIC CAPITAL LETTER YERU
2890xFA	0x0417	#	CYRILLIC CAPITAL LETTER ZE
2900xFB	0x0428	#	CYRILLIC CAPITAL LETTER SHA
2910xFC	0x042D	#	CYRILLIC CAPITAL LETTER E
2920xFD	0x0429	#	CYRILLIC CAPITAL LETTER SHCHA
2930xFE	0x0427	#	CYRILLIC CAPITAL LETTER CHE
2940xFF	0x042A	#	CYRILLIC CAPITAL LETTER HARD SIGN
295