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 +1,275 @@
1
+ #
2
+ # Name: cp864_DOSArabic 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 cp864_DOSArabic 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 cp864_DOSArabic 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 0x066a #ARABIC 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 0x00b0 #DEGREE SIGN
147
+ 0x81 0x00b7 #MIDDLE DOT
148
+ 0x82 0x2219 #BULLET OPERATOR
149
+ 0x83 0x221a #SQUARE ROOT
150
+ 0x84 0x2592 #MEDIUM SHADE
151
+ 0x85 0x2500 #FORMS LIGHT HORIZONTAL
152
+ 0x86 0x2502 #FORMS LIGHT VERTICAL
153
+ 0x87 0x253c #FORMS LIGHT VERTICAL AND HORIZONTAL
154
+ 0x88 0x2524 #FORMS LIGHT VERTICAL AND LEFT
155
+ 0x89 0x252c #FORMS LIGHT DOWN AND HORIZONTAL
156
+ 0x8a 0x251c #FORMS LIGHT VERTICAL AND RIGHT
157
+ 0x8b 0x2534 #FORMS LIGHT UP AND HORIZONTAL
158
+ 0x8c 0x2510 #FORMS LIGHT DOWN AND LEFT
159
+ 0x8d 0x250c #FORMS LIGHT DOWN AND RIGHT
160
+ 0x8e 0x2514 #FORMS LIGHT UP AND RIGHT
161
+ 0x8f 0x2518 #FORMS LIGHT UP AND LEFT
162
+ 0x90 0x03b2 #GREEK SMALL BETA
163
+ 0x91 0x221e #INFINITY
164
+ 0x92 0x03c6 #GREEK SMALL PHI
165
+ 0x93 0x00b1 #PLUS-OR-MINUS SIGN
166
+ 0x94 0x00bd #FRACTION 1/2
167
+ 0x95 0x00bc #FRACTION 1/4
168
+ 0x96 0x2248 #ALMOST EQUAL TO
169
+ 0x97 0x00ab #LEFT POINTING GUILLEMET
170
+ 0x98 0x00bb #RIGHT POINTING GUILLEMET
171
+ 0x99 0xfef7 #ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
172
+ 0x9a 0xfef8 #ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
173
+ 0x9b #UNDEFINED
174
+ 0x9c #UNDEFINED
175
+ 0x9d 0xfefb #ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
176
+ 0x9e 0xfefc #ARABIC LIGATURE LAM WITH ALEF FINAL FORM
177
+ 0x9f #UNDEFINED
178
+ 0xa0 0x00a0 #NON-BREAKING SPACE
179
+ 0xa1 0x00ad #SOFT HYPHEN
180
+ 0xa2 0xfe82 #ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
181
+ 0xa3 0x00a3 #POUND SIGN
182
+ 0xa4 0x00a4 #CURRENCY SIGN
183
+ 0xa5 0xfe84 #ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
184
+ 0xa6 #UNDEFINED
185
+ 0xa7 #UNDEFINED
186
+ 0xa8 0xfe8e #ARABIC LETTER ALEF FINAL FORM
187
+ 0xa9 0xfe8f #ARABIC LETTER BEH ISOLATED FORM
188
+ 0xaa 0xfe95 #ARABIC LETTER TEH ISOLATED FORM
189
+ 0xab 0xfe99 #ARABIC LETTER THEH ISOLATED FORM
190
+ 0xac 0x060c #ARABIC COMMA
191
+ 0xad 0xfe9d #ARABIC LETTER JEEM ISOLATED FORM
192
+ 0xae 0xfea1 #ARABIC LETTER HAH ISOLATED FORM
193
+ 0xaf 0xfea5 #ARABIC LETTER KHAH ISOLATED FORM
194
+ 0xb0 0x0660 #ARABIC-INDIC DIGIT ZERO
195
+ 0xb1 0x0661 #ARABIC-INDIC DIGIT ONE
196
+ 0xb2 0x0662 #ARABIC-INDIC DIGIT TWO
197
+ 0xb3 0x0663 #ARABIC-INDIC DIGIT THREE
198
+ 0xb4 0x0664 #ARABIC-INDIC DIGIT FOUR
199
+ 0xb5 0x0665 #ARABIC-INDIC DIGIT FIVE
200
+ 0xb6 0x0666 #ARABIC-INDIC DIGIT SIX
201
+ 0xb7 0x0667 #ARABIC-INDIC DIGIT SEVEN
202
+ 0xb8 0x0668 #ARABIC-INDIC DIGIT EIGHT
203
+ 0xb9 0x0669 #ARABIC-INDIC DIGIT NINE
204
+ 0xba 0xfed1 #ARABIC LETTER FEH ISOLATED FORM
205
+ 0xbb 0x061b #ARABIC SEMICOLON
206
+ 0xbc 0xfeb1 #ARABIC LETTER SEEN ISOLATED FORM
207
+ 0xbd 0xfeb5 #ARABIC LETTER SHEEN ISOLATED FORM
208
+ 0xbe 0xfeb9 #ARABIC LETTER SAD ISOLATED FORM
209
+ 0xbf 0x061f #ARABIC QUESTION MARK
210
+ 0xc0 0x00a2 #CENT SIGN
211
+ 0xc1 0xfe80 #ARABIC LETTER HAMZA ISOLATED FORM
212
+ 0xc2 0xfe81 #ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
213
+ 0xc3 0xfe83 #ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
214
+ 0xc4 0xfe85 #ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
215
+ 0xc5 0xfeca #ARABIC LETTER AIN FINAL FORM
216
+ 0xc6 0xfe8b #ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
217
+ 0xc7 0xfe8d #ARABIC LETTER ALEF ISOLATED FORM
218
+ 0xc8 0xfe91 #ARABIC LETTER BEH INITIAL FORM
219
+ 0xc9 0xfe93 #ARABIC LETTER TEH MARBUTA ISOLATED FORM
220
+ 0xca 0xfe97 #ARABIC LETTER TEH INITIAL FORM
221
+ 0xcb 0xfe9b #ARABIC LETTER THEH INITIAL FORM
222
+ 0xcc 0xfe9f #ARABIC LETTER JEEM INITIAL FORM
223
+ 0xcd 0xfea3 #ARABIC LETTER HAH INITIAL FORM
224
+ 0xce 0xfea7 #ARABIC LETTER KHAH INITIAL FORM
225
+ 0xcf 0xfea9 #ARABIC LETTER DAL ISOLATED FORM
226
+ 0xd0 0xfeab #ARABIC LETTER THAL ISOLATED FORM
227
+ 0xd1 0xfead #ARABIC LETTER REH ISOLATED FORM
228
+ 0xd2 0xfeaf #ARABIC LETTER ZAIN ISOLATED FORM
229
+ 0xd3 0xfeb3 #ARABIC LETTER SEEN INITIAL FORM
230
+ 0xd4 0xfeb7 #ARABIC LETTER SHEEN INITIAL FORM
231
+ 0xd5 0xfebb #ARABIC LETTER SAD INITIAL FORM
232
+ 0xd6 0xfebf #ARABIC LETTER DAD INITIAL FORM
233
+ 0xd7 0xfec1 #ARABIC LETTER TAH ISOLATED FORM
234
+ 0xd8 0xfec5 #ARABIC LETTER ZAH ISOLATED FORM
235
+ 0xd9 0xfecb #ARABIC LETTER AIN INITIAL FORM
236
+ 0xda 0xfecf #ARABIC LETTER GHAIN INITIAL FORM
237
+ 0xdb 0x00a6 #BROKEN VERTICAL BAR
238
+ 0xdc 0x00ac #NOT SIGN
239
+ 0xdd 0x00f7 #DIVISION SIGN
240
+ 0xde 0x00d7 #MULTIPLICATION SIGN
241
+ 0xdf 0xfec9 #ARABIC LETTER AIN ISOLATED FORM
242
+ 0xe0 0x0640 #ARABIC TATWEEL
243
+ 0xe1 0xfed3 #ARABIC LETTER FEH INITIAL FORM
244
+ 0xe2 0xfed7 #ARABIC LETTER QAF INITIAL FORM
245
+ 0xe3 0xfedb #ARABIC LETTER KAF INITIAL FORM
246
+ 0xe4 0xfedf #ARABIC LETTER LAM INITIAL FORM
247
+ 0xe5 0xfee3 #ARABIC LETTER MEEM INITIAL FORM
248
+ 0xe6 0xfee7 #ARABIC LETTER NOON INITIAL FORM
249
+ 0xe7 0xfeeb #ARABIC LETTER HEH INITIAL FORM
250
+ 0xe8 0xfeed #ARABIC LETTER WAW ISOLATED FORM
251
+ 0xe9 0xfeef #ARABIC LETTER ALEF MAKSURA ISOLATED FORM
252
+ 0xea 0xfef3 #ARABIC LETTER YEH INITIAL FORM
253
+ 0xeb 0xfebd #ARABIC LETTER DAD ISOLATED FORM
254
+ 0xec 0xfecc #ARABIC LETTER AIN MEDIAL FORM
255
+ 0xed 0xfece #ARABIC LETTER GHAIN FINAL FORM
256
+ 0xee 0xfecd #ARABIC LETTER GHAIN ISOLATED FORM
257
+ 0xef 0xfee1 #ARABIC LETTER MEEM ISOLATED FORM
258
+ 0xf0 0xfe7d #ARABIC SHADDA MEDIAL FORM
259
+ 0xf1 0x0651 #ARABIC SHADDAH
260
+ 0xf2 0xfee5 #ARABIC LETTER NOON ISOLATED FORM
261
+ 0xf3 0xfee9 #ARABIC LETTER HEH ISOLATED FORM
262
+ 0xf4 0xfeec #ARABIC LETTER HEH MEDIAL FORM
263
+ 0xf5 0xfef0 #ARABIC LETTER ALEF MAKSURA FINAL FORM
264
+ 0xf6 0xfef2 #ARABIC LETTER YEH FINAL FORM
265
+ 0xf7 0xfed0 #ARABIC LETTER GHAIN MEDIAL FORM
266
+ 0xf8 0xfed5 #ARABIC LETTER QAF ISOLATED FORM
267
+ 0xf9 0xfef5 #ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
268
+ 0xfa 0xfef6 #ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
269
+ 0xfb 0xfedd #ARABIC LETTER LAM ISOLATED FORM
270
+ 0xfc 0xfed9 #ARABIC LETTER KAF ISOLATED FORM
271
+ 0xfd 0xfef1 #ARABIC LETTER YEH ISOLATED FORM
272
+ 0xfe 0x25a0 #BLACK SQUARE
273
+ 0xff #UNDEFINED
274
+
275
+ 
@@ -0,0 +1,275 @@
1
+ #
2
+ # Name: cp865_DOSNordic 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 cp865_DOSNordic 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 cp865_DOSNordic 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 0x00e0 #LATIN SMALL LETTER A WITH GRAVE
152
+ 0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE
153
+ 0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA
154
+ 0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX
155
+ 0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS
156
+ 0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE
157
+ 0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS
158
+ 0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX
159
+ 0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE
160
+ 0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS
161
+ 0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE
162
+ 0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE
163
+ 0x91 0x00e6 #LATIN SMALL LIGATURE AE
164
+ 0x92 0x00c6 #LATIN CAPITAL LIGATURE AE
165
+ 0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
166
+ 0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS
167
+ 0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE
168
+ 0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX
169
+ 0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE
170
+ 0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS
171
+ 0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS
172
+ 0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS
173
+ 0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE
174
+ 0x9c 0x00a3 #POUND SIGN
175
+ 0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE
176
+ 0x9e 0x20a7 #PESETA SIGN
177
+ 0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK
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 0x00f1 #LATIN SMALL LETTER N WITH TILDE
183
+ 0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE
184
+ 0xa6 0x00aa #FEMININE ORDINAL INDICATOR
185
+ 0xa7 0x00ba #MASCULINE ORDINAL INDICATOR
186
+ 0xa8 0x00bf #INVERTED QUESTION MARK
187
+ 0xa9 0x2310 #REVERSED NOT SIGN
188
+ 0xaa 0x00ac #NOT SIGN
189
+ 0xab 0x00bd #VULGAR FRACTION ONE HALF
190
+ 0xac 0x00bc #VULGAR FRACTION ONE QUARTER
191
+ 0xad 0x00a1 #INVERTED EXCLAMATION MARK
192
+ 0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
193
+ 0xaf 0x00a4 #CURRENCY SIGN
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 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
200
+ 0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
201
+ 0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
202
+ 0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
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 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
208
+ 0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
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 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
217
+ 0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
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 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
226
+ 0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
227
+ 0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
228
+ 0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
229
+ 0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
230
+ 0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
231
+ 0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
232
+ 0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
233
+ 0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
234
+ 0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
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 0x258c #LEFT HALF BLOCK
240
+ 0xde 0x2590 #RIGHT HALF BLOCK
241
+ 0xdf 0x2580 #UPPER HALF BLOCK
242
+ 0xe0 0x03b1 #GREEK SMALL LETTER ALPHA
243
+ 0xe1 0x00df #LATIN SMALL LETTER SHARP S
244
+ 0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA
245
+ 0xe3 0x03c0 #GREEK SMALL LETTER PI
246
+ 0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA
247
+ 0xe5 0x03c3 #GREEK SMALL LETTER SIGMA
248
+ 0xe6 0x00b5 #MICRO SIGN
249
+ 0xe7 0x03c4 #GREEK SMALL LETTER TAU
250
+ 0xe8 0x03a6 #GREEK CAPITAL LETTER PHI
251
+ 0xe9 0x0398 #GREEK CAPITAL LETTER THETA
252
+ 0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA
253
+ 0xeb 0x03b4 #GREEK SMALL LETTER DELTA
254
+ 0xec 0x221e #INFINITY
255
+ 0xed 0x03c6 #GREEK SMALL LETTER PHI
256
+ 0xee 0x03b5 #GREEK SMALL LETTER EPSILON
257
+ 0xef 0x2229 #INTERSECTION
258
+ 0xf0 0x2261 #IDENTICAL TO
259
+ 0xf1 0x00b1 #PLUS-MINUS SIGN
260
+ 0xf2 0x2265 #GREATER-THAN OR EQUAL TO
261
+ 0xf3 0x2264 #LESS-THAN OR EQUAL TO
262
+ 0xf4 0x2320 #TOP HALF INTEGRAL
263
+ 0xf5 0x2321 #BOTTOM HALF INTEGRAL
264
+ 0xf6 0x00f7 #DIVISION SIGN
265
+ 0xf7 0x2248 #ALMOST EQUAL TO
266
+ 0xf8 0x00b0 #DEGREE SIGN
267
+ 0xf9 0x2219 #BULLET OPERATOR
268
+ 0xfa 0x00b7 #MIDDLE DOT
269
+ 0xfb 0x221a #SQUARE ROOT
270
+ 0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N
271
+ 0xfd 0x00b2 #SUPERSCRIPT TWO
272
+ 0xfe 0x25a0 #BLACK SQUARE
273
+ 0xff 0x00a0 #NO-BREAK SPACE
274
+
275
+