langa 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
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 +1,274 @@
1
+ #
2
+ # Name: cp852_DOSLatin2 to Unicode table
3
+ # Unicode version: 2.0
4
+ # Table version: 2.00
5
+ # Table format: Format A
6
+ # Date: 04/24/96
7
+ # Contact: Shawn.Steele@microsoft.com
8
+ #
9
+ # General notes: none
10
+ #
11
+ # Format: Three tab-separated columns
12
+ # Column #1 is the cp852_DOSLatin2 code (in hex)
13
+ # Column #2 is the Unicode (in hex as 0xXXXX)
14
+ # Column #3 is the Unicode name (follows a comment sign, '#')
15
+ #
16
+ # The entries are in cp852_DOSLatin2 order
17
+ #
18
+ 0x00 0x0000 #NULL
19
+ 0x01 0x0001 #START OF HEADING
20
+ 0x02 0x0002 #START OF TEXT
21
+ 0x03 0x0003 #END OF TEXT
22
+ 0x04 0x0004 #END OF TRANSMISSION
23
+ 0x05 0x0005 #ENQUIRY
24
+ 0x06 0x0006 #ACKNOWLEDGE
25
+ 0x07 0x0007 #BELL
26
+ 0x08 0x0008 #BACKSPACE
27
+ 0x09 0x0009 #HORIZONTAL TABULATION
28
+ 0x0a 0x000a #LINE FEED
29
+ 0x0b 0x000b #VERTICAL TABULATION
30
+ 0x0c 0x000c #FORM FEED
31
+ 0x0d 0x000d #CARRIAGE RETURN
32
+ 0x0e 0x000e #SHIFT OUT
33
+ 0x0f 0x000f #SHIFT IN
34
+ 0x10 0x0010 #DATA LINK ESCAPE
35
+ 0x11 0x0011 #DEVICE CONTROL ONE
36
+ 0x12 0x0012 #DEVICE CONTROL TWO
37
+ 0x13 0x0013 #DEVICE CONTROL THREE
38
+ 0x14 0x0014 #DEVICE CONTROL FOUR
39
+ 0x15 0x0015 #NEGATIVE ACKNOWLEDGE
40
+ 0x16 0x0016 #SYNCHRONOUS IDLE
41
+ 0x17 0x0017 #END OF TRANSMISSION BLOCK
42
+ 0x18 0x0018 #CANCEL
43
+ 0x19 0x0019 #END OF MEDIUM
44
+ 0x1a 0x001a #SUBSTITUTE
45
+ 0x1b 0x001b #ESCAPE
46
+ 0x1c 0x001c #FILE SEPARATOR
47
+ 0x1d 0x001d #GROUP SEPARATOR
48
+ 0x1e 0x001e #RECORD SEPARATOR
49
+ 0x1f 0x001f #UNIT SEPARATOR
50
+ 0x20 0x0020 #SPACE
51
+ 0x21 0x0021 #EXCLAMATION MARK
52
+ 0x22 0x0022 #QUOTATION MARK
53
+ 0x23 0x0023 #NUMBER SIGN
54
+ 0x24 0x0024 #DOLLAR SIGN
55
+ 0x25 0x0025 #PERCENT SIGN
56
+ 0x26 0x0026 #AMPERSAND
57
+ 0x27 0x0027 #APOSTROPHE
58
+ 0x28 0x0028 #LEFT PARENTHESIS
59
+ 0x29 0x0029 #RIGHT PARENTHESIS
60
+ 0x2a 0x002a #ASTERISK
61
+ 0x2b 0x002b #PLUS SIGN
62
+ 0x2c 0x002c #COMMA
63
+ 0x2d 0x002d #HYPHEN-MINUS
64
+ 0x2e 0x002e #FULL STOP
65
+ 0x2f 0x002f #SOLIDUS
66
+ 0x30 0x0030 #DIGIT ZERO
67
+ 0x31 0x0031 #DIGIT ONE
68
+ 0x32 0x0032 #DIGIT TWO
69
+ 0x33 0x0033 #DIGIT THREE
70
+ 0x34 0x0034 #DIGIT FOUR
71
+ 0x35 0x0035 #DIGIT FIVE
72
+ 0x36 0x0036 #DIGIT SIX
73
+ 0x37 0x0037 #DIGIT SEVEN
74
+ 0x38 0x0038 #DIGIT EIGHT
75
+ 0x39 0x0039 #DIGIT NINE
76
+ 0x3a 0x003a #COLON
77
+ 0x3b 0x003b #SEMICOLON
78
+ 0x3c 0x003c #LESS-THAN SIGN
79
+ 0x3d 0x003d #EQUALS SIGN
80
+ 0x3e 0x003e #GREATER-THAN SIGN
81
+ 0x3f 0x003f #QUESTION MARK
82
+ 0x40 0x0040 #COMMERCIAL AT
83
+ 0x41 0x0041 #LATIN CAPITAL LETTER A
84
+ 0x42 0x0042 #LATIN CAPITAL LETTER B
85
+ 0x43 0x0043 #LATIN CAPITAL LETTER C
86
+ 0x44 0x0044 #LATIN CAPITAL LETTER D
87
+ 0x45 0x0045 #LATIN CAPITAL LETTER E
88
+ 0x46 0x0046 #LATIN CAPITAL LETTER F
89
+ 0x47 0x0047 #LATIN CAPITAL LETTER G
90
+ 0x48 0x0048 #LATIN CAPITAL LETTER H
91
+ 0x49 0x0049 #LATIN CAPITAL LETTER I
92
+ 0x4a 0x004a #LATIN CAPITAL LETTER J
93
+ 0x4b 0x004b #LATIN CAPITAL LETTER K
94
+ 0x4c 0x004c #LATIN CAPITAL LETTER L
95
+ 0x4d 0x004d #LATIN CAPITAL LETTER M
96
+ 0x4e 0x004e #LATIN CAPITAL LETTER N
97
+ 0x4f 0x004f #LATIN CAPITAL LETTER O
98
+ 0x50 0x0050 #LATIN CAPITAL LETTER P
99
+ 0x51 0x0051 #LATIN CAPITAL LETTER Q
100
+ 0x52 0x0052 #LATIN CAPITAL LETTER R
101
+ 0x53 0x0053 #LATIN CAPITAL LETTER S
102
+ 0x54 0x0054 #LATIN CAPITAL LETTER T
103
+ 0x55 0x0055 #LATIN CAPITAL LETTER U
104
+ 0x56 0x0056 #LATIN CAPITAL LETTER V
105
+ 0x57 0x0057 #LATIN CAPITAL LETTER W
106
+ 0x58 0x0058 #LATIN CAPITAL LETTER X
107
+ 0x59 0x0059 #LATIN CAPITAL LETTER Y
108
+ 0x5a 0x005a #LATIN CAPITAL LETTER Z
109
+ 0x5b 0x005b #LEFT SQUARE BRACKET
110
+ 0x5c 0x005c #REVERSE SOLIDUS
111
+ 0x5d 0x005d #RIGHT SQUARE BRACKET
112
+ 0x5e 0x005e #CIRCUMFLEX ACCENT
113
+ 0x5f 0x005f #LOW LINE
114
+ 0x60 0x0060 #GRAVE ACCENT
115
+ 0x61 0x0061 #LATIN SMALL LETTER A
116
+ 0x62 0x0062 #LATIN SMALL LETTER B
117
+ 0x63 0x0063 #LATIN SMALL LETTER C
118
+ 0x64 0x0064 #LATIN SMALL LETTER D
119
+ 0x65 0x0065 #LATIN SMALL LETTER E
120
+ 0x66 0x0066 #LATIN SMALL LETTER F
121
+ 0x67 0x0067 #LATIN SMALL LETTER G
122
+ 0x68 0x0068 #LATIN SMALL LETTER H
123
+ 0x69 0x0069 #LATIN SMALL LETTER I
124
+ 0x6a 0x006a #LATIN SMALL LETTER J
125
+ 0x6b 0x006b #LATIN SMALL LETTER K
126
+ 0x6c 0x006c #LATIN SMALL LETTER L
127
+ 0x6d 0x006d #LATIN SMALL LETTER M
128
+ 0x6e 0x006e #LATIN SMALL LETTER N
129
+ 0x6f 0x006f #LATIN SMALL LETTER O
130
+ 0x70 0x0070 #LATIN SMALL LETTER P
131
+ 0x71 0x0071 #LATIN SMALL LETTER Q
132
+ 0x72 0x0072 #LATIN SMALL LETTER R
133
+ 0x73 0x0073 #LATIN SMALL LETTER S
134
+ 0x74 0x0074 #LATIN SMALL LETTER T
135
+ 0x75 0x0075 #LATIN SMALL LETTER U
136
+ 0x76 0x0076 #LATIN SMALL LETTER V
137
+ 0x77 0x0077 #LATIN SMALL LETTER W
138
+ 0x78 0x0078 #LATIN SMALL LETTER X
139
+ 0x79 0x0079 #LATIN SMALL LETTER Y
140
+ 0x7a 0x007a #LATIN SMALL LETTER Z
141
+ 0x7b 0x007b #LEFT CURLY BRACKET
142
+ 0x7c 0x007c #VERTICAL LINE
143
+ 0x7d 0x007d #RIGHT CURLY BRACKET
144
+ 0x7e 0x007e #TILDE
145
+ 0x7f 0x007f #DELETE
146
+ 0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA
147
+ 0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS
148
+ 0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE
149
+ 0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
150
+ 0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS
151
+ 0x85 0x016f #LATIN SMALL LETTER U WITH RING ABOVE
152
+ 0x86 0x0107 #LATIN SMALL LETTER C WITH ACUTE
153
+ 0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
154
+ 0x88 0x0142 #LATIN SMALL LETTER L WITH STROKE
155
+ 0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
156
+ 0x8a 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
157
+ 0x8b 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
158
+ 0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
159
+ 0x8d 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
160
+ 0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
161
+ 0x8f 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
162
+ 0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
163
+ 0x91 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
164
+ 0x92 0x013a #LATIN SMALL LETTER L WITH ACUTE
165
+ 0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
166
+ 0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
167
+ 0x95 0x013d #LATIN CAPITAL LETTER L WITH CARON
168
+ 0x96 0x013e #LATIN SMALL LETTER L WITH CARON
169
+ 0x97 0x015a #LATIN CAPITAL LETTER S WITH ACUTE
170
+ 0x98 0x015b #LATIN SMALL LETTER S WITH ACUTE
171
+ 0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
172
+ 0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
173
+ 0x9b 0x0164 #LATIN CAPITAL LETTER T WITH CARON
174
+ 0x9c 0x0165 #LATIN SMALL LETTER T WITH CARON
175
+ 0x9d 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
176
+ 0x9e 0x00d7 #MULTIPLICATION SIGN
177
+ 0x9f 0x010d #LATIN SMALL LETTER C WITH CARON
178
+ 0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE
179
+ 0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE
180
+ 0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE
181
+ 0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE
182
+ 0xa4 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
183
+ 0xa5 0x0105 #LATIN SMALL LETTER A WITH OGONEK
184
+ 0xa6 0x017d #LATIN CAPITAL LETTER Z WITH CARON
185
+ 0xa7 0x017e #LATIN SMALL LETTER Z WITH CARON
186
+ 0xa8 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
187
+ 0xa9 0x0119 #LATIN SMALL LETTER E WITH OGONEK
188
+ 0xaa 0x00ac #NOT SIGN
189
+ 0xab 0x017a #LATIN SMALL LETTER Z WITH ACUTE
190
+ 0xac 0x010c #LATIN CAPITAL LETTER C WITH CARON
191
+ 0xad 0x015f #LATIN SMALL LETTER S WITH CEDILLA
192
+ 0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
193
+ 0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
194
+ 0xb0 0x2591 #LIGHT SHADE
195
+ 0xb1 0x2592 #MEDIUM SHADE
196
+ 0xb2 0x2593 #DARK SHADE
197
+ 0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
198
+ 0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
199
+ 0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE
200
+ 0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
201
+ 0xb7 0x011a #LATIN CAPITAL LETTER E WITH CARON
202
+ 0xb8 0x015e #LATIN CAPITAL LETTER S WITH CEDILLA
203
+ 0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
204
+ 0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
205
+ 0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
206
+ 0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
207
+ 0xbd 0x017b #LATIN CAPITAL LETTER Z WITH DOT ABOVE
208
+ 0xbe 0x017c #LATIN SMALL LETTER Z WITH DOT ABOVE
209
+ 0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
210
+ 0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
211
+ 0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
212
+ 0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
213
+ 0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
214
+ 0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
215
+ 0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
216
+ 0xc6 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
217
+ 0xc7 0x0103 #LATIN SMALL LETTER A WITH BREVE
218
+ 0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
219
+ 0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
220
+ 0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
221
+ 0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
222
+ 0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
223
+ 0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
224
+ 0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
225
+ 0xcf 0x00a4 #CURRENCY SIGN
226
+ 0xd0 0x0111 #LATIN SMALL LETTER D WITH STROKE
227
+ 0xd1 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
228
+ 0xd2 0x010e #LATIN CAPITAL LETTER D WITH CARON
229
+ 0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS
230
+ 0xd4 0x010f #LATIN SMALL LETTER D WITH CARON
231
+ 0xd5 0x0147 #LATIN CAPITAL LETTER N WITH CARON
232
+ 0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE
233
+ 0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
234
+ 0xd8 0x011b #LATIN SMALL LETTER E WITH CARON
235
+ 0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
236
+ 0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
237
+ 0xdb 0x2588 #FULL BLOCK
238
+ 0xdc 0x2584 #LOWER HALF BLOCK
239
+ 0xdd 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
240
+ 0xde 0x016e #LATIN CAPITAL LETTER U WITH RING ABOVE
241
+ 0xdf 0x2580 #UPPER HALF BLOCK
242
+ 0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE
243
+ 0xe1 0x00df #LATIN SMALL LETTER SHARP S
244
+ 0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
245
+ 0xe3 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
246
+ 0xe4 0x0144 #LATIN SMALL LETTER N WITH ACUTE
247
+ 0xe5 0x0148 #LATIN SMALL LETTER N WITH CARON
248
+ 0xe6 0x0160 #LATIN CAPITAL LETTER S WITH CARON
249
+ 0xe7 0x0161 #LATIN SMALL LETTER S WITH CARON
250
+ 0xe8 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
251
+ 0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE
252
+ 0xea 0x0155 #LATIN SMALL LETTER R WITH ACUTE
253
+ 0xeb 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
254
+ 0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE
255
+ 0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE
256
+ 0xee 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
257
+ 0xef 0x00b4 #ACUTE ACCENT
258
+ 0xf0 0x00ad #SOFT HYPHEN
259
+ 0xf1 0x02dd #DOUBLE ACUTE ACCENT
260
+ 0xf2 0x02db #OGONEK
261
+ 0xf3 0x02c7 #CARON
262
+ 0xf4 0x02d8 #BREVE
263
+ 0xf5 0x00a7 #SECTION SIGN
264
+ 0xf6 0x00f7 #DIVISION SIGN
265
+ 0xf7 0x00b8 #CEDILLA
266
+ 0xf8 0x00b0 #DEGREE SIGN
267
+ 0xf9 0x00a8 #DIAERESIS
268
+ 0xfa 0x02d9 #DOT ABOVE
269
+ 0xfb 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
270
+ 0xfc 0x0158 #LATIN CAPITAL LETTER R WITH CARON
271
+ 0xfd 0x0159 #LATIN SMALL LETTER R WITH CARON
272
+ 0xfe 0x25a0 #BLACK SQUARE
273
+ 0xff 0x00a0 #NO-BREAK SPACE
274
+ 
@@ -0,0 +1,275 @@
1
+ #
2
+ # Name: cp855_DOSCyrillic to Unicode table
3
+ # Unicode version: 2.0
4
+ # Table version: 2.00
5
+ # Table format: Format A
6
+ # Date: 04/24/96
7
+ # Contact: Shawn.Steele@microsoft.com
8
+ #
9
+ # General notes: none
10
+ #
11
+ # Format: Three tab-separated columns
12
+ # Column #1 is the cp855_DOSCyrillic code (in hex)
13
+ # Column #2 is the Unicode (in hex as 0xXXXX)
14
+ # Column #3 is the Unicode name (follows a comment sign, '#')
15
+ #
16
+ # The entries are in cp855_DOSCyrillic order
17
+ #
18
+ 0x00 0x0000 #NULL
19
+ 0x01 0x0001 #START OF HEADING
20
+ 0x02 0x0002 #START OF TEXT
21
+ 0x03 0x0003 #END OF TEXT
22
+ 0x04 0x0004 #END OF TRANSMISSION
23
+ 0x05 0x0005 #ENQUIRY
24
+ 0x06 0x0006 #ACKNOWLEDGE
25
+ 0x07 0x0007 #BELL
26
+ 0x08 0x0008 #BACKSPACE
27
+ 0x09 0x0009 #HORIZONTAL TABULATION
28
+ 0x0a 0x000a #LINE FEED
29
+ 0x0b 0x000b #VERTICAL TABULATION
30
+ 0x0c 0x000c #FORM FEED
31
+ 0x0d 0x000d #CARRIAGE RETURN
32
+ 0x0e 0x000e #SHIFT OUT
33
+ 0x0f 0x000f #SHIFT IN
34
+ 0x10 0x0010 #DATA LINK ESCAPE
35
+ 0x11 0x0011 #DEVICE CONTROL ONE
36
+ 0x12 0x0012 #DEVICE CONTROL TWO
37
+ 0x13 0x0013 #DEVICE CONTROL THREE
38
+ 0x14 0x0014 #DEVICE CONTROL FOUR
39
+ 0x15 0x0015 #NEGATIVE ACKNOWLEDGE
40
+ 0x16 0x0016 #SYNCHRONOUS IDLE
41
+ 0x17 0x0017 #END OF TRANSMISSION BLOCK
42
+ 0x18 0x0018 #CANCEL
43
+ 0x19 0x0019 #END OF MEDIUM
44
+ 0x1a 0x001a #SUBSTITUTE
45
+ 0x1b 0x001b #ESCAPE
46
+ 0x1c 0x001c #FILE SEPARATOR
47
+ 0x1d 0x001d #GROUP SEPARATOR
48
+ 0x1e 0x001e #RECORD SEPARATOR
49
+ 0x1f 0x001f #UNIT SEPARATOR
50
+ 0x20 0x0020 #SPACE
51
+ 0x21 0x0021 #EXCLAMATION MARK
52
+ 0x22 0x0022 #QUOTATION MARK
53
+ 0x23 0x0023 #NUMBER SIGN
54
+ 0x24 0x0024 #DOLLAR SIGN
55
+ 0x25 0x0025 #PERCENT SIGN
56
+ 0x26 0x0026 #AMPERSAND
57
+ 0x27 0x0027 #APOSTROPHE
58
+ 0x28 0x0028 #LEFT PARENTHESIS
59
+ 0x29 0x0029 #RIGHT PARENTHESIS
60
+ 0x2a 0x002a #ASTERISK
61
+ 0x2b 0x002b #PLUS SIGN
62
+ 0x2c 0x002c #COMMA
63
+ 0x2d 0x002d #HYPHEN-MINUS
64
+ 0x2e 0x002e #FULL STOP
65
+ 0x2f 0x002f #SOLIDUS
66
+ 0x30 0x0030 #DIGIT ZERO
67
+ 0x31 0x0031 #DIGIT ONE
68
+ 0x32 0x0032 #DIGIT TWO
69
+ 0x33 0x0033 #DIGIT THREE
70
+ 0x34 0x0034 #DIGIT FOUR
71
+ 0x35 0x0035 #DIGIT FIVE
72
+ 0x36 0x0036 #DIGIT SIX
73
+ 0x37 0x0037 #DIGIT SEVEN
74
+ 0x38 0x0038 #DIGIT EIGHT
75
+ 0x39 0x0039 #DIGIT NINE
76
+ 0x3a 0x003a #COLON
77
+ 0x3b 0x003b #SEMICOLON
78
+ 0x3c 0x003c #LESS-THAN SIGN
79
+ 0x3d 0x003d #EQUALS SIGN
80
+ 0x3e 0x003e #GREATER-THAN SIGN
81
+ 0x3f 0x003f #QUESTION MARK
82
+ 0x40 0x0040 #COMMERCIAL AT
83
+ 0x41 0x0041 #LATIN CAPITAL LETTER A
84
+ 0x42 0x0042 #LATIN CAPITAL LETTER B
85
+ 0x43 0x0043 #LATIN CAPITAL LETTER C
86
+ 0x44 0x0044 #LATIN CAPITAL LETTER D
87
+ 0x45 0x0045 #LATIN CAPITAL LETTER E
88
+ 0x46 0x0046 #LATIN CAPITAL LETTER F
89
+ 0x47 0x0047 #LATIN CAPITAL LETTER G
90
+ 0x48 0x0048 #LATIN CAPITAL LETTER H
91
+ 0x49 0x0049 #LATIN CAPITAL LETTER I
92
+ 0x4a 0x004a #LATIN CAPITAL LETTER J
93
+ 0x4b 0x004b #LATIN CAPITAL LETTER K
94
+ 0x4c 0x004c #LATIN CAPITAL LETTER L
95
+ 0x4d 0x004d #LATIN CAPITAL LETTER M
96
+ 0x4e 0x004e #LATIN CAPITAL LETTER N
97
+ 0x4f 0x004f #LATIN CAPITAL LETTER O
98
+ 0x50 0x0050 #LATIN CAPITAL LETTER P
99
+ 0x51 0x0051 #LATIN CAPITAL LETTER Q
100
+ 0x52 0x0052 #LATIN CAPITAL LETTER R
101
+ 0x53 0x0053 #LATIN CAPITAL LETTER S
102
+ 0x54 0x0054 #LATIN CAPITAL LETTER T
103
+ 0x55 0x0055 #LATIN CAPITAL LETTER U
104
+ 0x56 0x0056 #LATIN CAPITAL LETTER V
105
+ 0x57 0x0057 #LATIN CAPITAL LETTER W
106
+ 0x58 0x0058 #LATIN CAPITAL LETTER X
107
+ 0x59 0x0059 #LATIN CAPITAL LETTER Y
108
+ 0x5a 0x005a #LATIN CAPITAL LETTER Z
109
+ 0x5b 0x005b #LEFT SQUARE BRACKET
110
+ 0x5c 0x005c #REVERSE SOLIDUS
111
+ 0x5d 0x005d #RIGHT SQUARE BRACKET
112
+ 0x5e 0x005e #CIRCUMFLEX ACCENT
113
+ 0x5f 0x005f #LOW LINE
114
+ 0x60 0x0060 #GRAVE ACCENT
115
+ 0x61 0x0061 #LATIN SMALL LETTER A
116
+ 0x62 0x0062 #LATIN SMALL LETTER B
117
+ 0x63 0x0063 #LATIN SMALL LETTER C
118
+ 0x64 0x0064 #LATIN SMALL LETTER D
119
+ 0x65 0x0065 #LATIN SMALL LETTER E
120
+ 0x66 0x0066 #LATIN SMALL LETTER F
121
+ 0x67 0x0067 #LATIN SMALL LETTER G
122
+ 0x68 0x0068 #LATIN SMALL LETTER H
123
+ 0x69 0x0069 #LATIN SMALL LETTER I
124
+ 0x6a 0x006a #LATIN SMALL LETTER J
125
+ 0x6b 0x006b #LATIN SMALL LETTER K
126
+ 0x6c 0x006c #LATIN SMALL LETTER L
127
+ 0x6d 0x006d #LATIN SMALL LETTER M
128
+ 0x6e 0x006e #LATIN SMALL LETTER N
129
+ 0x6f 0x006f #LATIN SMALL LETTER O
130
+ 0x70 0x0070 #LATIN SMALL LETTER P
131
+ 0x71 0x0071 #LATIN SMALL LETTER Q
132
+ 0x72 0x0072 #LATIN SMALL LETTER R
133
+ 0x73 0x0073 #LATIN SMALL LETTER S
134
+ 0x74 0x0074 #LATIN SMALL LETTER T
135
+ 0x75 0x0075 #LATIN SMALL LETTER U
136
+ 0x76 0x0076 #LATIN SMALL LETTER V
137
+ 0x77 0x0077 #LATIN SMALL LETTER W
138
+ 0x78 0x0078 #LATIN SMALL LETTER X
139
+ 0x79 0x0079 #LATIN SMALL LETTER Y
140
+ 0x7a 0x007a #LATIN SMALL LETTER Z
141
+ 0x7b 0x007b #LEFT CURLY BRACKET
142
+ 0x7c 0x007c #VERTICAL LINE
143
+ 0x7d 0x007d #RIGHT CURLY BRACKET
144
+ 0x7e 0x007e #TILDE
145
+ 0x7f 0x007f #DELETE
146
+ 0x80 0x0452 #CYRILLIC SMALL LETTER DJE
147
+ 0x81 0x0402 #CYRILLIC CAPITAL LETTER DJE
148
+ 0x82 0x0453 #CYRILLIC SMALL LETTER GJE
149
+ 0x83 0x0403 #CYRILLIC CAPITAL LETTER GJE
150
+ 0x84 0x0451 #CYRILLIC SMALL LETTER IO
151
+ 0x85 0x0401 #CYRILLIC CAPITAL LETTER IO
152
+ 0x86 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
153
+ 0x87 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
154
+ 0x88 0x0455 #CYRILLIC SMALL LETTER DZE
155
+ 0x89 0x0405 #CYRILLIC CAPITAL LETTER DZE
156
+ 0x8a 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
157
+ 0x8b 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
158
+ 0x8c 0x0457 #CYRILLIC SMALL LETTER YI
159
+ 0x8d 0x0407 #CYRILLIC CAPITAL LETTER YI
160
+ 0x8e 0x0458 #CYRILLIC SMALL LETTER JE
161
+ 0x8f 0x0408 #CYRILLIC CAPITAL LETTER JE
162
+ 0x90 0x0459 #CYRILLIC SMALL LETTER LJE
163
+ 0x91 0x0409 #CYRILLIC CAPITAL LETTER LJE
164
+ 0x92 0x045a #CYRILLIC SMALL LETTER NJE
165
+ 0x93 0x040a #CYRILLIC CAPITAL LETTER NJE
166
+ 0x94 0x045b #CYRILLIC SMALL LETTER TSHE
167
+ 0x95 0x040b #CYRILLIC CAPITAL LETTER TSHE
168
+ 0x96 0x045c #CYRILLIC SMALL LETTER KJE
169
+ 0x97 0x040c #CYRILLIC CAPITAL LETTER KJE
170
+ 0x98 0x045e #CYRILLIC SMALL LETTER SHORT U
171
+ 0x99 0x040e #CYRILLIC CAPITAL LETTER SHORT U
172
+ 0x9a 0x045f #CYRILLIC SMALL LETTER DZHE
173
+ 0x9b 0x040f #CYRILLIC CAPITAL LETTER DZHE
174
+ 0x9c 0x044e #CYRILLIC SMALL LETTER YU
175
+ 0x9d 0x042e #CYRILLIC CAPITAL LETTER YU
176
+ 0x9e 0x044a #CYRILLIC SMALL LETTER HARD SIGN
177
+ 0x9f 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN
178
+ 0xa0 0x0430 #CYRILLIC SMALL LETTER A
179
+ 0xa1 0x0410 #CYRILLIC CAPITAL LETTER A
180
+ 0xa2 0x0431 #CYRILLIC SMALL LETTER BE
181
+ 0xa3 0x0411 #CYRILLIC CAPITAL LETTER BE
182
+ 0xa4 0x0446 #CYRILLIC SMALL LETTER TSE
183
+ 0xa5 0x0426 #CYRILLIC CAPITAL LETTER TSE
184
+ 0xa6 0x0434 #CYRILLIC SMALL LETTER DE
185
+ 0xa7 0x0414 #CYRILLIC CAPITAL LETTER DE
186
+ 0xa8 0x0435 #CYRILLIC SMALL LETTER IE
187
+ 0xa9 0x0415 #CYRILLIC CAPITAL LETTER IE
188
+ 0xaa 0x0444 #CYRILLIC SMALL LETTER EF
189
+ 0xab 0x0424 #CYRILLIC CAPITAL LETTER EF
190
+ 0xac 0x0433 #CYRILLIC SMALL LETTER GHE
191
+ 0xad 0x0413 #CYRILLIC CAPITAL LETTER GHE
192
+ 0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
193
+ 0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
194
+ 0xb0 0x2591 #LIGHT SHADE
195
+ 0xb1 0x2592 #MEDIUM SHADE
196
+ 0xb2 0x2593 #DARK SHADE
197
+ 0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL
198
+ 0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
199
+ 0xb5 0x0445 #CYRILLIC SMALL LETTER HA
200
+ 0xb6 0x0425 #CYRILLIC CAPITAL LETTER HA
201
+ 0xb7 0x0438 #CYRILLIC SMALL LETTER I
202
+ 0xb8 0x0418 #CYRILLIC CAPITAL LETTER I
203
+ 0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
204
+ 0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
205
+ 0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
206
+ 0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT
207
+ 0xbd 0x0439 #CYRILLIC SMALL LETTER SHORT I
208
+ 0xbe 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
209
+ 0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
210
+ 0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
211
+ 0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
212
+ 0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
213
+ 0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
214
+ 0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
215
+ 0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
216
+ 0xc6 0x043a #CYRILLIC SMALL LETTER KA
217
+ 0xc7 0x041a #CYRILLIC CAPITAL LETTER KA
218
+ 0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT
219
+ 0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
220
+ 0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
221
+ 0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
222
+ 0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
223
+ 0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
224
+ 0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
225
+ 0xcf 0x00a4 #CURRENCY SIGN
226
+ 0xd0 0x043b #CYRILLIC SMALL LETTER EL
227
+ 0xd1 0x041b #CYRILLIC CAPITAL LETTER EL
228
+ 0xd2 0x043c #CYRILLIC SMALL LETTER EM
229
+ 0xd3 0x041c #CYRILLIC CAPITAL LETTER EM
230
+ 0xd4 0x043d #CYRILLIC SMALL LETTER EN
231
+ 0xd5 0x041d #CYRILLIC CAPITAL LETTER EN
232
+ 0xd6 0x043e #CYRILLIC SMALL LETTER O
233
+ 0xd7 0x041e #CYRILLIC CAPITAL LETTER O
234
+ 0xd8 0x043f #CYRILLIC SMALL LETTER PE
235
+ 0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
236
+ 0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT
237
+ 0xdb 0x2588 #FULL BLOCK
238
+ 0xdc 0x2584 #LOWER HALF BLOCK
239
+ 0xdd 0x041f #CYRILLIC CAPITAL LETTER PE
240
+ 0xde 0x044f #CYRILLIC SMALL LETTER YA
241
+ 0xdf 0x2580 #UPPER HALF BLOCK
242
+ 0xe0 0x042f #CYRILLIC CAPITAL LETTER YA
243
+ 0xe1 0x0440 #CYRILLIC SMALL LETTER ER
244
+ 0xe2 0x0420 #CYRILLIC CAPITAL LETTER ER
245
+ 0xe3 0x0441 #CYRILLIC SMALL LETTER ES
246
+ 0xe4 0x0421 #CYRILLIC CAPITAL LETTER ES
247
+ 0xe5 0x0442 #CYRILLIC SMALL LETTER TE
248
+ 0xe6 0x0422 #CYRILLIC CAPITAL LETTER TE
249
+ 0xe7 0x0443 #CYRILLIC SMALL LETTER U
250
+ 0xe8 0x0423 #CYRILLIC CAPITAL LETTER U
251
+ 0xe9 0x0436 #CYRILLIC SMALL LETTER ZHE
252
+ 0xea 0x0416 #CYRILLIC CAPITAL LETTER ZHE
253
+ 0xeb 0x0432 #CYRILLIC SMALL LETTER VE
254
+ 0xec 0x0412 #CYRILLIC CAPITAL LETTER VE
255
+ 0xed 0x044c #CYRILLIC SMALL LETTER SOFT SIGN
256
+ 0xee 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN
257
+ 0xef 0x2116 #NUMERO SIGN
258
+ 0xf0 0x00ad #SOFT HYPHEN
259
+ 0xf1 0x044b #CYRILLIC SMALL LETTER YERU
260
+ 0xf2 0x042b #CYRILLIC CAPITAL LETTER YERU
261
+ 0xf3 0x0437 #CYRILLIC SMALL LETTER ZE
262
+ 0xf4 0x0417 #CYRILLIC CAPITAL LETTER ZE
263
+ 0xf5 0x0448 #CYRILLIC SMALL LETTER SHA
264
+ 0xf6 0x0428 #CYRILLIC CAPITAL LETTER SHA
265
+ 0xf7 0x044d #CYRILLIC SMALL LETTER E
266
+ 0xf8 0x042d #CYRILLIC CAPITAL LETTER E
267
+ 0xf9 0x0449 #CYRILLIC SMALL LETTER SHCHA
268
+ 0xfa 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
269
+ 0xfb 0x0447 #CYRILLIC SMALL LETTER CHE
270
+ 0xfc 0x0427 #CYRILLIC CAPITAL LETTER CHE
271
+ 0xfd 0x00a7 #SECTION SIGN
272
+ 0xfe 0x25a0 #BLACK SQUARE
273
+ 0xff 0x00a0 #NO-BREAK SPACE
274
+
275
+