langa 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (122) hide show
  1. data/COPYING +674 -0
  2. data/README +69 -0
  3. data/bin/langa +169 -0
  4. data/examples/afrikaans_1953_utf8.txt +1000 -0
  5. data/examples/albanian_utf8.txt +1000 -0
  6. data/examples/amharic_utf8.txt +1000 -0
  7. data/examples/arabic_svd_utf8.txt +1000 -0
  8. data/examples/armenian_western_1853_utf8.txt +1000 -0
  9. data/examples/asv_utf8.txt +1000 -0
  10. data/examples/basque_1571_utf8.txt +1000 -0
  11. data/examples/breton_utf8.txt +1000 -0
  12. data/examples/chinese_ncv_s_utf8.txt +1000 -0
  13. data/examples/chinese_ncv_utf8.txt +1000 -0
  14. data/examples/chinese_union_s_utf8.txt +1000 -0
  15. data/examples/chinese_union_utf8.txt +1000 -0
  16. data/examples/coptic_nt_utf8.txt +1000 -0
  17. data/examples/croatian_utf8.txt +1000 -0
  18. data/examples/czech_bkr_utf8.txt +1000 -0
  19. data/examples/danish_utf8.txt +1000 -0
  20. data/examples/dutch_svv_utf8.txt +1000 -0
  21. data/examples/esperanto_utf8.txt +1000 -0
  22. data/examples/estonian_utf8.txt +1000 -0
  23. data/examples/finnish_pr_1992_utf8.txt +1000 -0
  24. data/examples/french_ostervald_1996_utf8.txt +1000 -0
  25. data/examples/german_schlachter_1951_utf8.txt +1000 -0
  26. data/examples/greek_byzantine_2000_utf8.txt +1000 -0
  27. data/examples/greek_modern_utf8.txt +1000 -0
  28. data/examples/hebrew_modern_utf8.txt +1000 -0
  29. data/examples/hungarian_karoli_utf8.txt +1000 -0
  30. data/examples/italian_riveduta_1927_utf8.txt +1000 -0
  31. data/examples/kabyle_nt_utf8.txt +1000 -0
  32. data/examples/kjv_apocrypha_utf8.txt +1000 -0
  33. data/examples/korean_utf8.txt +1000 -0
  34. data/examples/latin_vulgata_clementina_utf8.txt +1000 -0
  35. data/examples/latvian_nt_utf8.txt +1000 -0
  36. data/examples/lithuanian_utf8.txt +1000 -0
  37. data/examples/manx_gaelic_utf8.txt +1000 -0
  38. data/examples/maori_utf8.txt +1000 -0
  39. data/examples/myanmar_judson_1835_utf8.txt +1000 -0
  40. data/examples/norwegian_utf8.txt +1000 -0
  41. data/examples/peshitta_utf8.txt +1000 -0
  42. data/examples/portuguese_utf8.txt +1000 -0
  43. data/examples/romani_utf8.txt +1000 -0
  44. data/examples/romanian_cornilescu_utf8.txt +1000 -0
  45. data/examples/russian_makarij_utf8.txt +1000 -0
  46. data/examples/spanish_reina_valera_1909_utf8.txt +1000 -0
  47. data/examples/swedish_1917_utf8.txt +1000 -0
  48. data/examples/tagalog_1905_utf8.txt +1000 -0
  49. data/examples/thai_kjv_utf8.txt +1000 -0
  50. data/examples/turkish_nt_utf8.txt +1000 -0
  51. data/examples/turkish_utf8.txt +1000 -0
  52. data/examples/ukrainian_1871_utf8.txt +1000 -0
  53. data/examples/vietnamese_1934_utf8.txt +1000 -0
  54. data/examples/wolof_utf8.txt +1000 -0
  55. data/examples/xhosa_utf8.txt +1000 -0
  56. data/lib/langa.rb +35 -0
  57. data/lib/langa/dna.rb +209 -0
  58. data/lib/langa/file.rb +97 -0
  59. data/lib/langa/langa.dna +406 -0
  60. data/lib/langa/languageanalyzer.rb +134 -0
  61. data/lib/langa/languages.rb +147 -0
  62. data/lib/langa/randomtestfiles.rb +140 -0
  63. data/lib/langa/utilities.rb +53 -0
  64. data/test/tc_file.rb +47 -0
  65. data/test/tc_languages.rb +69 -0
  66. data/test/tc_utilities.rb +42 -0
  67. data/unicode/CaseFolding.txt +1065 -0
  68. data/unicode/CaseFolding.txt.webloc +8 -0
  69. data/unicode/Index of -Public-MAPPINGS.webloc b/data/unicode/Index of → -Public-MAPPINGS.webloc +0 -0
  70. data/unicode/mappings/8859-1.TXT +303 -0
  71. data/unicode/mappings/8859-10.TXT +303 -0
  72. data/unicode/mappings/8859-11.TXT +297 -0
  73. data/unicode/mappings/8859-13.TXT +299 -0
  74. data/unicode/mappings/8859-14.TXT +301 -0
  75. data/unicode/mappings/8859-15.TXT +303 -0
  76. data/unicode/mappings/8859-16.TXT +299 -0
  77. data/unicode/mappings/8859-2.TXT +303 -0
  78. data/unicode/mappings/8859-3.TXT +296 -0
  79. data/unicode/mappings/8859-4.TXT +303 -0
  80. data/unicode/mappings/8859-5.TXT +303 -0
  81. data/unicode/mappings/8859-6.TXT +260 -0
  82. data/unicode/mappings/8859-7.TXT +308 -0
  83. data/unicode/mappings/8859-8.TXT +270 -0
  84. data/unicode/mappings/8859-9.TXT +307 -0
  85. data/unicode/mappings/ATARIST.TXT +313 -0
  86. data/unicode/mappings/CP037.TXT +275 -0
  87. data/unicode/mappings/CP1006.TXT +302 -0
  88. data/unicode/mappings/CP1026.TXT +275 -0
  89. data/unicode/mappings/CP1250.TXT +274 -0
  90. data/unicode/mappings/CP1251.TXT +274 -0
  91. data/unicode/mappings/CP1252.TXT +274 -0
  92. data/unicode/mappings/CP1253.TXT +274 -0
  93. data/unicode/mappings/CP1254.TXT +274 -0
  94. data/unicode/mappings/CP1255.TXT +274 -0
  95. data/unicode/mappings/CP1256.TXT +274 -0
  96. data/unicode/mappings/CP1257.TXT +274 -0
  97. data/unicode/mappings/CP1258.TXT +274 -0
  98. data/unicode/mappings/CP424.TXT +304 -0
  99. data/unicode/mappings/CP437.TXT +274 -0
  100. data/unicode/mappings/CP500.TXT +275 -0
  101. data/unicode/mappings/CP737.TXT +274 -0
  102. data/unicode/mappings/CP775.TXT +275 -0
  103. data/unicode/mappings/CP850.TXT +274 -0
  104. data/unicode/mappings/CP852.TXT +274 -0
  105. data/unicode/mappings/CP855.TXT +275 -0
  106. data/unicode/mappings/CP856.TXT +303 -0
  107. data/unicode/mappings/CP857.TXT +275 -0
  108. data/unicode/mappings/CP860.TXT +275 -0
  109. data/unicode/mappings/CP861.TXT +275 -0
  110. data/unicode/mappings/CP862.TXT +275 -0
  111. data/unicode/mappings/CP863.TXT +275 -0
  112. data/unicode/mappings/CP864.TXT +275 -0
  113. data/unicode/mappings/CP865.TXT +275 -0
  114. data/unicode/mappings/CP866.TXT +275 -0
  115. data/unicode/mappings/CP869.TXT +275 -0
  116. data/unicode/mappings/CP874.TXT +274 -0
  117. data/unicode/mappings/CP875.TXT +275 -0
  118. data/unicode/mappings/KOI8-R.TXT +302 -0
  119. data/unicode/mappings/NEXTSTEP.TXT +173 -0
  120. data/unicode/mappings/ROMAN.TXT +275 -0
  121. data/unicode/mappings/US-ASCII-QUOTES.TXT +198 -0
  122. metadata +180 -0
@@ -0,0 +1,302 @@
1
+ #
2
+ # Name: KOI8-R (RFC1489) to Unicode
3
+ # Unicode version: 3.0
4
+ # Table version: 1.0
5
+ # Table format: Format A
6
+ # Date: 18 August 1999
7
+ # Authors: Helmut Richter <richter@lrz.de>
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
+ # KOI8-R characters map into Unicode. The underlying document is the
29
+ # mapping described in RFC 1489. No statements are made as to whether
30
+ # this mapping is the same as the mapping defined as "Code Page 878"
31
+ # with some vendors.
32
+ #
33
+ # Format: Three tab-separated columns
34
+ # Column #1 is the KOI8-R code (in hex as 0xXX)
35
+ # Column #2 is the Unicode (in hex as 0xXXXX)
36
+ # Column #3 the Unicode name (follows a comment sign, '#')
37
+ #
38
+ # The entries are in KOI8-R order.
39
+ #
40
+ # Version history
41
+ # 1.0 version: created.
42
+ #
43
+ # Any comments or problems, contact <errata@unicode.org>
44
+ # Please note that <errata@unicode.org> is an archival address;
45
+ # notices will be checked, but do not expect an immediate response.
46
+ #
47
+ 0x00 0x0000 # NULL
48
+ 0x01 0x0001 # START OF HEADING
49
+ 0x02 0x0002 # START OF TEXT
50
+ 0x03 0x0003 # END OF TEXT
51
+ 0x04 0x0004 # END OF TRANSMISSION
52
+ 0x05 0x0005 # ENQUIRY
53
+ 0x06 0x0006 # ACKNOWLEDGE
54
+ 0x07 0x0007 # BELL
55
+ 0x08 0x0008 # BACKSPACE
56
+ 0x09 0x0009 # HORIZONTAL TABULATION
57
+ 0x0A 0x000A # LINE FEED
58
+ 0x0B 0x000B # VERTICAL TABULATION
59
+ 0x0C 0x000C # FORM FEED
60
+ 0x0D 0x000D # CARRIAGE RETURN
61
+ 0x0E 0x000E # SHIFT OUT
62
+ 0x0F 0x000F # SHIFT IN
63
+ 0x10 0x0010 # DATA LINK ESCAPE
64
+ 0x11 0x0011 # DEVICE CONTROL ONE
65
+ 0x12 0x0012 # DEVICE CONTROL TWO
66
+ 0x13 0x0013 # DEVICE CONTROL THREE
67
+ 0x14 0x0014 # DEVICE CONTROL FOUR
68
+ 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
69
+ 0x16 0x0016 # SYNCHRONOUS IDLE
70
+ 0x17 0x0017 # END OF TRANSMISSION BLOCK
71
+ 0x18 0x0018 # CANCEL
72
+ 0x19 0x0019 # END OF MEDIUM
73
+ 0x1A 0x001A # SUBSTITUTE
74
+ 0x1B 0x001B # ESCAPE
75
+ 0x1C 0x001C # FILE SEPARATOR
76
+ 0x1D 0x001D # GROUP SEPARATOR
77
+ 0x1E 0x001E # RECORD SEPARATOR
78
+ 0x1F 0x001F # UNIT SEPARATOR
79
+ 0x20 0x0020 # SPACE
80
+ 0x21 0x0021 # EXCLAMATION MARK
81
+ 0x22 0x0022 # QUOTATION MARK
82
+ 0x23 0x0023 # NUMBER SIGN
83
+ 0x24 0x0024 # DOLLAR SIGN
84
+ 0x25 0x0025 # PERCENT SIGN
85
+ 0x26 0x0026 # AMPERSAND
86
+ 0x27 0x0027 # APOSTROPHE
87
+ 0x28 0x0028 # LEFT PARENTHESIS
88
+ 0x29 0x0029 # RIGHT PARENTHESIS
89
+ 0x2A 0x002A # ASTERISK
90
+ 0x2B 0x002B # PLUS SIGN
91
+ 0x2C 0x002C # COMMA
92
+ 0x2D 0x002D # HYPHEN-MINUS
93
+ 0x2E 0x002E # FULL STOP
94
+ 0x2F 0x002F # SOLIDUS
95
+ 0x30 0x0030 # DIGIT ZERO
96
+ 0x31 0x0031 # DIGIT ONE
97
+ 0x32 0x0032 # DIGIT TWO
98
+ 0x33 0x0033 # DIGIT THREE
99
+ 0x34 0x0034 # DIGIT FOUR
100
+ 0x35 0x0035 # DIGIT FIVE
101
+ 0x36 0x0036 # DIGIT SIX
102
+ 0x37 0x0037 # DIGIT SEVEN
103
+ 0x38 0x0038 # DIGIT EIGHT
104
+ 0x39 0x0039 # DIGIT NINE
105
+ 0x3A 0x003A # COLON
106
+ 0x3B 0x003B # SEMICOLON
107
+ 0x3C 0x003C # LESS-THAN SIGN
108
+ 0x3D 0x003D # EQUALS SIGN
109
+ 0x3E 0x003E # GREATER-THAN SIGN
110
+ 0x3F 0x003F # QUESTION MARK
111
+ 0x40 0x0040 # COMMERCIAL AT
112
+ 0x41 0x0041 # LATIN CAPITAL LETTER A
113
+ 0x42 0x0042 # LATIN CAPITAL LETTER B
114
+ 0x43 0x0043 # LATIN CAPITAL LETTER C
115
+ 0x44 0x0044 # LATIN CAPITAL LETTER D
116
+ 0x45 0x0045 # LATIN CAPITAL LETTER E
117
+ 0x46 0x0046 # LATIN CAPITAL LETTER F
118
+ 0x47 0x0047 # LATIN CAPITAL LETTER G
119
+ 0x48 0x0048 # LATIN CAPITAL LETTER H
120
+ 0x49 0x0049 # LATIN CAPITAL LETTER I
121
+ 0x4A 0x004A # LATIN CAPITAL LETTER J
122
+ 0x4B 0x004B # LATIN CAPITAL LETTER K
123
+ 0x4C 0x004C # LATIN CAPITAL LETTER L
124
+ 0x4D 0x004D # LATIN CAPITAL LETTER M
125
+ 0x4E 0x004E # LATIN CAPITAL LETTER N
126
+ 0x4F 0x004F # LATIN CAPITAL LETTER O
127
+ 0x50 0x0050 # LATIN CAPITAL LETTER P
128
+ 0x51 0x0051 # LATIN CAPITAL LETTER Q
129
+ 0x52 0x0052 # LATIN CAPITAL LETTER R
130
+ 0x53 0x0053 # LATIN CAPITAL LETTER S
131
+ 0x54 0x0054 # LATIN CAPITAL LETTER T
132
+ 0x55 0x0055 # LATIN CAPITAL LETTER U
133
+ 0x56 0x0056 # LATIN CAPITAL LETTER V
134
+ 0x57 0x0057 # LATIN CAPITAL LETTER W
135
+ 0x58 0x0058 # LATIN CAPITAL LETTER X
136
+ 0x59 0x0059 # LATIN CAPITAL LETTER Y
137
+ 0x5A 0x005A # LATIN CAPITAL LETTER Z
138
+ 0x5B 0x005B # LEFT SQUARE BRACKET
139
+ 0x5C 0x005C # REVERSE SOLIDUS
140
+ 0x5D 0x005D # RIGHT SQUARE BRACKET
141
+ 0x5E 0x005E # CIRCUMFLEX ACCENT
142
+ 0x5F 0x005F # LOW LINE
143
+ 0x60 0x0060 # GRAVE ACCENT
144
+ 0x61 0x0061 # LATIN SMALL LETTER A
145
+ 0x62 0x0062 # LATIN SMALL LETTER B
146
+ 0x63 0x0063 # LATIN SMALL LETTER C
147
+ 0x64 0x0064 # LATIN SMALL LETTER D
148
+ 0x65 0x0065 # LATIN SMALL LETTER E
149
+ 0x66 0x0066 # LATIN SMALL LETTER F
150
+ 0x67 0x0067 # LATIN SMALL LETTER G
151
+ 0x68 0x0068 # LATIN SMALL LETTER H
152
+ 0x69 0x0069 # LATIN SMALL LETTER I
153
+ 0x6A 0x006A # LATIN SMALL LETTER J
154
+ 0x6B 0x006B # LATIN SMALL LETTER K
155
+ 0x6C 0x006C # LATIN SMALL LETTER L
156
+ 0x6D 0x006D # LATIN SMALL LETTER M
157
+ 0x6E 0x006E # LATIN SMALL LETTER N
158
+ 0x6F 0x006F # LATIN SMALL LETTER O
159
+ 0x70 0x0070 # LATIN SMALL LETTER P
160
+ 0x71 0x0071 # LATIN SMALL LETTER Q
161
+ 0x72 0x0072 # LATIN SMALL LETTER R
162
+ 0x73 0x0073 # LATIN SMALL LETTER S
163
+ 0x74 0x0074 # LATIN SMALL LETTER T
164
+ 0x75 0x0075 # LATIN SMALL LETTER U
165
+ 0x76 0x0076 # LATIN SMALL LETTER V
166
+ 0x77 0x0077 # LATIN SMALL LETTER W
167
+ 0x78 0x0078 # LATIN SMALL LETTER X
168
+ 0x79 0x0079 # LATIN SMALL LETTER Y
169
+ 0x7A 0x007A # LATIN SMALL LETTER Z
170
+ 0x7B 0x007B # LEFT CURLY BRACKET
171
+ 0x7C 0x007C # VERTICAL LINE
172
+ 0x7D 0x007D # RIGHT CURLY BRACKET
173
+ 0x7E 0x007E # TILDE
174
+ 0x7F 0x007F # DELETE
175
+ 0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
176
+ 0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
177
+ 0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
178
+ 0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
179
+ 0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
180
+ 0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
181
+ 0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
182
+ 0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
183
+ 0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
184
+ 0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
185
+ 0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
186
+ 0x8B 0x2580 # UPPER HALF BLOCK
187
+ 0x8C 0x2584 # LOWER HALF BLOCK
188
+ 0x8D 0x2588 # FULL BLOCK
189
+ 0x8E 0x258C # LEFT HALF BLOCK
190
+ 0x8F 0x2590 # RIGHT HALF BLOCK
191
+ 0x90 0x2591 # LIGHT SHADE
192
+ 0x91 0x2592 # MEDIUM SHADE
193
+ 0x92 0x2593 # DARK SHADE
194
+ 0x93 0x2320 # TOP HALF INTEGRAL
195
+ 0x94 0x25A0 # BLACK SQUARE
196
+ 0x95 0x2219 # BULLET OPERATOR
197
+ 0x96 0x221A # SQUARE ROOT
198
+ 0x97 0x2248 # ALMOST EQUAL TO
199
+ 0x98 0x2264 # LESS-THAN OR EQUAL TO
200
+ 0x99 0x2265 # GREATER-THAN OR EQUAL TO
201
+ 0x9A 0x00A0 # NO-BREAK SPACE
202
+ 0x9B 0x2321 # BOTTOM HALF INTEGRAL
203
+ 0x9C 0x00B0 # DEGREE SIGN
204
+ 0x9D 0x00B2 # SUPERSCRIPT TWO
205
+ 0x9E 0x00B7 # MIDDLE DOT
206
+ 0x9F 0x00F7 # DIVISION SIGN
207
+ 0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
208
+ 0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
209
+ 0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
210
+ 0xA3 0x0451 # CYRILLIC SMALL LETTER IO
211
+ 0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
212
+ 0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
213
+ 0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
214
+ 0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
215
+ 0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
216
+ 0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
217
+ 0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
218
+ 0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
219
+ 0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
220
+ 0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
221
+ 0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
222
+ 0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
223
+ 0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
224
+ 0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
225
+ 0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
226
+ 0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
227
+ 0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
228
+ 0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
229
+ 0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
230
+ 0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
231
+ 0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
232
+ 0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
233
+ 0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
234
+ 0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
235
+ 0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
236
+ 0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
237
+ 0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
238
+ 0xBF 0x00A9 # COPYRIGHT SIGN
239
+ 0xC0 0x044E # CYRILLIC SMALL LETTER YU
240
+ 0xC1 0x0430 # CYRILLIC SMALL LETTER A
241
+ 0xC2 0x0431 # CYRILLIC SMALL LETTER BE
242
+ 0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
243
+ 0xC4 0x0434 # CYRILLIC SMALL LETTER DE
244
+ 0xC5 0x0435 # CYRILLIC SMALL LETTER IE
245
+ 0xC6 0x0444 # CYRILLIC SMALL LETTER EF
246
+ 0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
247
+ 0xC8 0x0445 # CYRILLIC SMALL LETTER HA
248
+ 0xC9 0x0438 # CYRILLIC SMALL LETTER I
249
+ 0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
250
+ 0xCB 0x043A # CYRILLIC SMALL LETTER KA
251
+ 0xCC 0x043B # CYRILLIC SMALL LETTER EL
252
+ 0xCD 0x043C # CYRILLIC SMALL LETTER EM
253
+ 0xCE 0x043D # CYRILLIC SMALL LETTER EN
254
+ 0xCF 0x043E # CYRILLIC SMALL LETTER O
255
+ 0xD0 0x043F # CYRILLIC SMALL LETTER PE
256
+ 0xD1 0x044F # CYRILLIC SMALL LETTER YA
257
+ 0xD2 0x0440 # CYRILLIC SMALL LETTER ER
258
+ 0xD3 0x0441 # CYRILLIC SMALL LETTER ES
259
+ 0xD4 0x0442 # CYRILLIC SMALL LETTER TE
260
+ 0xD5 0x0443 # CYRILLIC SMALL LETTER U
261
+ 0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
262
+ 0xD7 0x0432 # CYRILLIC SMALL LETTER VE
263
+ 0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
264
+ 0xD9 0x044B # CYRILLIC SMALL LETTER YERU
265
+ 0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
266
+ 0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
267
+ 0xDC 0x044D # CYRILLIC SMALL LETTER E
268
+ 0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
269
+ 0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
270
+ 0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
271
+ 0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
272
+ 0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
273
+ 0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
274
+ 0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
275
+ 0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
276
+ 0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
277
+ 0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
278
+ 0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
279
+ 0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
280
+ 0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
281
+ 0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
282
+ 0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
283
+ 0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
284
+ 0xED 0x041C # CYRILLIC CAPITAL LETTER EM
285
+ 0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
286
+ 0xEF 0x041E # CYRILLIC CAPITAL LETTER O
287
+ 0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
288
+ 0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
289
+ 0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
290
+ 0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
291
+ 0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
292
+ 0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
293
+ 0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
294
+ 0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
295
+ 0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
296
+ 0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
297
+ 0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
298
+ 0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
299
+ 0xFC 0x042D # CYRILLIC CAPITAL LETTER E
300
+ 0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
301
+ 0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
302
+ 0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
@@ -0,0 +1,173 @@
1
+ #
2
+ # Name: NextStep Encoding to Unicode
3
+ # Unicode version: 1.1
4
+ # Table version: 0.1
5
+ # Table format: Format A
6
+ # Date: 1999 September 23
7
+ # Authors: Rick McGowan
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
+ # NextStep Encoding characters map into Unicode. Since the first
29
+ # 128 characters (0x0 - 0x7f) are identical to ASCII and Unicode,
30
+ # this table only maps the NextStep range from 0x80 - 0xFF.
31
+ #
32
+ # This file is provided for historical reference only and pertains
33
+ # to NextStep and OpenStep products shipped prior to the aquisition
34
+ # of NeXT by Apple Computer, Inc. See http://www.apple.com for
35
+ # further information.
36
+ #
37
+ # Format: Three tab-separated columns
38
+ # Column #1 is the NextStep code (in hex as 0xXX)
39
+ # Column #2 is the Unicode (in hex as 0xXXXX)
40
+ # Column #3 NextStep name, Unicode name (follows a comment sign, '#')
41
+ #
42
+ # The entries are in NextStep order
43
+ #
44
+ # Any comments or problems, contact info@unicode.org
45
+ #
46
+ 0x80 0x00a0 # NO-BREAK SPACE
47
+ 0x81 0x00c0 # LATIN CAPITAL LETTER A WITH GRAVE
48
+ 0x82 0x00c1 # LATIN CAPITAL LETTER A WITH ACUTE
49
+ 0x83 0x00c2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
50
+ 0x84 0x00c3 # LATIN CAPITAL LETTER A WITH TILDE
51
+ 0x85 0x00c4 # LATIN CAPITAL LETTER A WITH DIAERESIS
52
+ 0x86 0x00c5 # LATIN CAPITAL LETTER A WITH RING
53
+ 0x87 0x00c7 # LATIN CAPITAL LETTER C WITH CEDILLA
54
+ 0x88 0x00c8 # LATIN CAPITAL LETTER E WITH GRAVE
55
+ 0x89 0x00c9 # LATIN CAPITAL LETTER E WITH ACUTE
56
+ 0x8a 0x00ca # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
57
+ 0x8b 0x00cb # LATIN CAPITAL LETTER E WITH DIAERESIS
58
+ 0x8c 0x00cc # LATIN CAPITAL LETTER I WITH GRAVE
59
+ 0x8d 0x00cd # LATIN CAPITAL LETTER I WITH ACUTE
60
+ 0x8e 0x00ce # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
61
+ 0x8f 0x00cf # LATIN CAPITAL LETTER I WITH DIAERESIS
62
+ 0x90 0x00d0 # LATIN CAPITAL LETTER ETH
63
+ 0x91 0x00d1 # LATIN CAPITAL LETTER N WITH TILDE
64
+ 0x92 0x00d2 # LATIN CAPITAL LETTER O WITH GRAVE
65
+ 0x93 0x00d3 # LATIN CAPITAL LETTER O WITH ACUTE
66
+ 0x94 0x00d4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
67
+ 0x95 0x00d5 # LATIN CAPITAL LETTER O WITH TILDE
68
+ 0x96 0x00d6 # LATIN CAPITAL LETTER O WITH DIAERESIS
69
+ 0x97 0x00d9 # LATIN CAPITAL LETTER U WITH GRAVE
70
+ 0x98 0x00da # LATIN CAPITAL LETTER U WITH ACUTE
71
+ 0x99 0x00db # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
72
+ 0x9a 0x00dc # LATIN CAPITAL LETTER U WITH DIAERESIS
73
+ 0x9b 0x00dd # LATIN CAPITAL LETTER Y WITH ACUTE
74
+ 0x9c 0x00de # LATIN CAPITAL LETTER THORN
75
+ 0x9d 0x00b5 # MICRO SIGN
76
+ 0x9e 0x00d7 # MULTIPLICATION SIGN
77
+ 0x9f 0x00f7 # DIVISION SIGN
78
+ 0xa0 0x00a9 # COPYRIGHT SIGN
79
+ 0xa1 0x00a1 # INVERTED EXCLAMATION MARK
80
+ 0xa2 0x00a2 # CENT SIGN
81
+ 0xa3 0x00a3 # POUND SIGN
82
+ 0xa4 0x2044 # FRACTION SLASH
83
+ 0xa5 0x00a5 # YEN SIGN
84
+ 0xa6 0x0192 # LATIN SMALL LETTER F WITH HOOK
85
+ 0xa7 0x00a7 # SECTION SIGN
86
+ 0xa8 0x00a4 # CURRENCY SIGN
87
+ 0xa9 0x2019 # RIGHT SINGLE QUOTATION MARK
88
+ 0xaa 0x201c # LEFT DOUBLE QUOTATION MARK
89
+ 0xab 0x00ab # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
90
+ 0xac 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
91
+ 0xad 0x203a # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
92
+ 0xae 0xfb01 # LATIN SMALL LIGATURE FI
93
+ 0xaf 0xfb02 # LATIN SMALL LIGATURE FL
94
+ 0xb0 0x00ae # REGISTERED SIGN
95
+ 0xb1 0x2013 # EN DASH
96
+ 0xb2 0x2020 # DAGGER
97
+ 0xb3 0x2021 # DOUBLE DAGGER
98
+ 0xb4 0x00b7 # MIDDLE DOT
99
+ 0xb5 0x00a6 # BROKEN BAR
100
+ 0xb6 0x00b6 # PILCROW SIGN
101
+ 0xb7 0x2022 # BULLET
102
+ 0xb8 0x201a # SINGLE LOW-9 QUOTATION MARK
103
+ 0xb9 0x201e # DOUBLE LOW-9 QUOTATION MARK
104
+ 0xba 0x201d # RIGHT DOUBLE QUOTATION MARK
105
+ 0xbb 0x00bb # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
106
+ 0xbc 0x2026 # HORIZONTAL ELLIPSIS
107
+ 0xbd 0x2030 # PER MILLE SIGN
108
+ 0xbe 0x00ac # NOT SIGN
109
+ 0xbf 0x00bf # INVERTED QUESTION MARK
110
+ 0xc0 0x00b9 # SUPERSCRIPT ONE
111
+ 0xc1 0x02cb # MODIFIER LETTER GRAVE ACCENT
112
+ 0xc2 0x00b4 # ACUTE ACCENT
113
+ 0xc3 0x02c6 # MODIFIER LETTER CIRCUMFLEX ACCENT
114
+ 0xc4 0x02dc # SMALL TILDE
115
+ 0xc5 0x00af # MACRON
116
+ 0xc6 0x02d8 # BREVE
117
+ 0xc7 0x02d9 # DOT ABOVE
118
+ 0xc8 0x00a8 # DIAERESIS
119
+ 0xc9 0x00b2 # SUPERSCRIPT TWO
120
+ 0xca 0x02da # RING ABOVE
121
+ 0xcb 0x00b8 # CEDILLA
122
+ 0xcc 0x00b3 # SUPERSCRIPT THREE
123
+ 0xcd 0x02dd # DOUBLE ACUTE ACCENT
124
+ 0xce 0x02db # OGONEK
125
+ 0xcf 0x02c7 # CARON
126
+ 0xd0 0x2014 # EM DASH
127
+ 0xd1 0x00b1 # PLUS-MINUS SIGN
128
+ 0xd2 0x00bc # VULGAR FRACTION ONE QUARTER
129
+ 0xd3 0x00bd # VULGAR FRACTION ONE HALF
130
+ 0xd4 0x00be # VULGAR FRACTION THREE QUARTERS
131
+ 0xd5 0x00e0 # LATIN SMALL LETTER A WITH GRAVE
132
+ 0xd6 0x00e1 # LATIN SMALL LETTER A WITH ACUTE
133
+ 0xd7 0x00e2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
134
+ 0xd8 0x00e3 # LATIN SMALL LETTER A WITH TILDE
135
+ 0xd9 0x00e4 # LATIN SMALL LETTER A WITH DIAERESIS
136
+ 0xda 0x00e5 # LATIN SMALL LETTER A WITH RING ABOVE
137
+ 0xdb 0x00e7 # LATIN SMALL LETTER C WITH CEDILLA
138
+ 0xdc 0x00e8 # LATIN SMALL LETTER E WITH GRAVE
139
+ 0xdd 0x00e9 # LATIN SMALL LETTER E WITH ACUTE
140
+ 0xde 0x00ea # LATIN SMALL LETTER E WITH CIRCUMFLEX
141
+ 0xdf 0x00eb # LATIN SMALL LETTER E WITH DIAERESIS
142
+ 0xe0 0x00ec # LATIN SMALL LETTER I WITH GRAVE
143
+ 0xe1 0x00c6 # LATIN CAPITAL LETTER AE
144
+ 0xe2 0x00ed # LATIN SMALL LETTER I WITH ACUTE
145
+ 0xe3 0x00aa # FEMININE ORDINAL INDICATOR
146
+ 0xe4 0x00ee # LATIN SMALL LETTER I WITH CIRCUMFLEX
147
+ 0xe5 0x00ef # LATIN SMALL LETTER I WITH DIAERESIS
148
+ 0xe6 0x00f0 # LATIN SMALL LETTER ETH
149
+ 0xe7 0x00f1 # LATIN SMALL LETTER N WITH TILDE
150
+ 0xe8 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
151
+ 0xe9 0x00d8 # LATIN CAPITAL LETTER O WITH STROKE
152
+ 0xea 0x0152 # LATIN CAPITAL LIGATURE OE
153
+ 0xeb 0x00ba # MASCULINE ORDINAL INDICATOR
154
+ 0xec 0x00f2 # LATIN SMALL LETTER O WITH GRAVE
155
+ 0xed 0x00f3 # LATIN SMALL LETTER O WITH ACUTE
156
+ 0xee 0x00f4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
157
+ 0xef 0x00f5 # LATIN SMALL LETTER O WITH TILDE
158
+ 0xf0 0x00f6 # LATIN SMALL LETTER O WITH DIAERESIS
159
+ 0xf1 0x00e6 # LATIN SMALL LETTER AE
160
+ 0xf2 0x00f9 # LATIN SMALL LETTER U WITH GRAVE
161
+ 0xf3 0x00fa # LATIN SMALL LETTER U WITH ACUTE
162
+ 0xf4 0x00fb # LATIN SMALL LETTER U WITH CIRCUMFLEX
163
+ 0xf5 0x0131 # LATIN SMALL LETTER DOTLESS I
164
+ 0xf6 0x00fc # LATIN SMALL LETTER U WITH DIAERESIS
165
+ 0xf7 0x00fd # LATIN SMALL LETTER Y WITH ACUTE
166
+ 0xf8 0x0142 # LATIN SMALL LETTER L WITH STROKE
167
+ 0xf9 0x00f8 # LATIN SMALL LETTER O WITH STROKE
168
+ 0xfa 0x0153 # LATIN SMALL LIGATURE OE
169
+ 0xfb 0x00df # LATIN SMALL LETTER SHARP S
170
+ 0xfc 0x00fe # LATIN SMALL LETTER THORN
171
+ 0xfd 0x00ff # LATIN SMALL LETTER Y WITH DIAERESIS
172
+ 0xfe 0xfffd # .notdef, REPLACEMENT CHARACTER
173
+ 0xff 0xfffd # .notdef, REPLACEMENT CHARACTER