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 +1,304 @@
1
+ #
2
+ # Name: IBM EBCDIC CP424 (Hebrew) to Unicode table
3
+ # Unicode version: 3.0
4
+ # Table version: 1.0
5
+ # Table format: Format A
6
+ # Date: 1999 July 27
7
+ # Authors: Ken Whistler <kenw@sybase.com>
8
+ #
9
+ # Copyright (c) 1998 - 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
+ # CP424 characters map into Unicode.
29
+ #
30
+ # Format: Three tab-separated columns
31
+ # Column #1 is the CP424 code (in hex)
32
+ # Column #2 is the Unicode (in hex as 0xXXXX)
33
+ # Column #3 is the Unicode name (follows a comment sign, '#')
34
+ # (or for EBCDIC controls, the EBCDIC name in C1 space)
35
+ #
36
+ # The entries are in CP424 order
37
+ #
38
+ # Version history
39
+ # 1.0 version new.
40
+ #
41
+ # Updated versions of this file may be found in:
42
+ # <ftp://ftp.unicode.org/Public/MAPPINGS/>
43
+ #
44
+ # Any comments or problems, contact <errata@unicode.org>
45
+ # Please note that <errata@unicode.org> is an archival address;
46
+ # notices will be checked, but do not expect an immediate response.
47
+ #
48
+ 0x00 0x0000 #NULL
49
+ 0x01 0x0001 #START OF HEADING
50
+ 0x02 0x0002 #START OF TEXT
51
+ 0x03 0x0003 #END OF TEXT
52
+ 0x04 0x009C #SELECT
53
+ 0x05 0x0009 #HORIZONTAL TABULATION
54
+ 0x06 0x0086 #REQUIRED NEW LINE
55
+ 0x07 0x007F #DELETE
56
+ 0x08 0x0097 #GRAPHIC ESCAPE
57
+ 0x09 0x008D #SUPERSCRIPT
58
+ 0x0A 0x008E #REPEAT
59
+ 0x0B 0x000B #VERTICAL TABULATION
60
+ 0x0C 0x000C #FORM FEED
61
+ 0x0D 0x000D #CARRIAGE RETURN
62
+ 0x0E 0x000E #SHIFT OUT
63
+ 0x0F 0x000F #SHIFT IN
64
+ 0x10 0x0010 #DATA LINK ESCAPE
65
+ 0x11 0x0011 #DEVICE CONTROL ONE
66
+ 0x12 0x0012 #DEVICE CONTROL TWO
67
+ 0x13 0x0013 #DEVICE CONTROL THREE
68
+ 0x14 0x009D #RESTORE/ENABLE PRESENTATION
69
+ 0x15 0x0085 #NEW LINE
70
+ 0x16 0x0008 #BACKSPACE
71
+ 0x17 0x0087 #PROGRAM OPERATOR COMMUNICATION
72
+ 0x18 0x0018 #CANCEL
73
+ 0x19 0x0019 #END OF MEDIUM
74
+ 0x1A 0x0092 #UNIT BACK SPACE
75
+ 0x1B 0x008F #CUSTOMER USE ONE
76
+ 0x1C 0x001C #FILE SEPARATOR
77
+ 0x1D 0x001D #GROUP SEPARATOR
78
+ 0x1E 0x001E #RECORD SEPARATOR
79
+ 0x1F 0x001F #UNIT SEPARATOR
80
+ 0x20 0x0080 #DIGIT SELECT
81
+ 0x21 0x0081 #START OF SIGNIFICANCE
82
+ 0x22 0x0082 #FIELD SEPARATOR
83
+ 0x23 0x0083 #WORD UNDERSCORE
84
+ 0x24 0x0084 #BYPASS OR INHIBIT PRESENTATION
85
+ 0x25 0x000A #LINE FEED
86
+ 0x26 0x0017 #END OF TRANSMISSION BLOCK
87
+ 0x27 0x001B #ESCAPE
88
+ 0x28 0x0088 #SET ATTRIBUTE
89
+ 0x29 0x0089 #START FIELD EXTENDED
90
+ 0x2A 0x008A #SET MODE OR SWITCH
91
+ 0x2B 0x008B #CONTROL SEQUENCE PREFIX
92
+ 0x2C 0x008C #MODIFY FIELD ATTRIBUTE
93
+ 0x2D 0x0005 #ENQUIRY
94
+ 0x2E 0x0006 #ACKNOWLEDGE
95
+ 0x2F 0x0007 #BELL
96
+ 0x30 0x0090 #<reserved>
97
+ 0x31 0x0091 #<reserved>
98
+ 0x32 0x0016 #SYNCHRONOUS IDLE
99
+ 0x33 0x0093 #INDEX RETURN
100
+ 0x34 0x0094 #PRESENTATION POSITION
101
+ 0x35 0x0095 #TRANSPARENT
102
+ 0x36 0x0096 #NUMERIC BACKSPACE
103
+ 0x37 0x0004 #END OF TRANSMISSION
104
+ 0x38 0x0098 #SUBSCRIPT
105
+ 0x39 0x0099 #INDENT TABULATION
106
+ 0x3A 0x009A #REVERSE FORM FEED
107
+ 0x3B 0x009B #CUSTOMER USE THREE
108
+ 0x3C 0x0014 #DEVICE CONTROL FOUR
109
+ 0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
110
+ 0x3E 0x009E #<reserved>
111
+ 0x3F 0x001A #SUBSTITUTE
112
+
113
+ 0x40 0x0020 #SPACE
114
+ 0x41 0x05D0 #HEBREW LETTER ALEF
115
+ 0x42 0x05D1 #HEBREW LETTER BET
116
+ 0x43 0x05D2 #HEBREW LETTER GIMEL
117
+ 0x44 0x05D3 #HEBREW LETTER DALET
118
+ 0x45 0x05D4 #HEBREW LETTER HE
119
+ 0x46 0x05D5 #HEBREW LETTER VAV
120
+ 0x47 0x05D6 #HEBREW LETTER ZAYIN
121
+ 0x48 0x05D7 #HEBREW LETTER HET
122
+ 0x49 0x05D8 #HEBREW LETTER TET
123
+ 0x4A 0x00A2 #CENT SIGN
124
+ 0x4B 0x002E #FULL STOP
125
+ 0x4C 0x003C #LESS-THAN SIGN
126
+ 0x4D 0x0028 #LEFT PARENTHESIS
127
+ 0x4E 0x002B #PLUS SIGN
128
+ 0x4F 0x007C #VERTICAL LINE
129
+ 0x50 0x0026 #AMPERSAND
130
+ 0x51 0x05D9 #HEBREW LETTER YOD
131
+ 0x52 0x05DA #HEBREW LETTER FINAL KAF
132
+ 0x53 0x05DB #HEBREW LETTER KAF
133
+ 0x54 0x05DC #HEBREW LETTER LAMED
134
+ 0x55 0x05DD #HEBREW LETTER FINAL MEM
135
+ 0x56 0x05DE #HEBREW LETTER MEM
136
+ 0x57 0x05DF #HEBREW LETTER FINAL NUN
137
+ 0x58 0x05E0 #HEBREW LETTER NUN
138
+ 0x59 0x05E1 #HEBREW LETTER SAMEKH
139
+ 0x5A 0x0021 #EXCLAMATION MARK
140
+ 0x5B 0x0024 #DOLLAR SIGN
141
+ 0x5C 0x002A #ASTERISK
142
+ 0x5D 0x0029 #RIGHT PARENTHESIS
143
+ 0x5E 0x003B #SEMICOLON
144
+ 0x5F 0x00AC #NOT SIGN
145
+ 0x60 0x002D #HYPHEN-MINUS
146
+ 0x61 0x002F #SOLIDUS
147
+ 0x62 0x05E2 #HEBREW LETTER AYIN
148
+ 0x63 0x05E3 #HEBREW LETTER FINAL PE
149
+ 0x64 0x05E4 #HEBREW LETTER PE
150
+ 0x65 0x05E5 #HEBREW LETTER FINAL TSADI
151
+ 0x66 0x05E6 #HEBREW LETTER TSADI
152
+ 0x67 0x05E7 #HEBREW LETTER QOF
153
+ 0x68 0x05E8 #HEBREW LETTER RESH
154
+ 0x69 0x05E9 #HEBREW LETTER SHIN
155
+ 0x6A 0x00A6 #BROKEN BAR
156
+ 0x6B 0x002C #COMMA
157
+ 0x6C 0x0025 #PERCENT SIGN
158
+ 0x6D 0x005F #LOW LINE
159
+ 0x6E 0x003E #GREATER-THAN SIGN
160
+ 0x6F 0x003F #QUESTION MARK
161
+ 0x70 #UNDEFINED
162
+ 0x71 0x05EA #HEBREW LETTER TAV
163
+ 0x72 #UNDEFINED
164
+ 0x73 #UNDEFINED
165
+ 0x74 0x00A0 #NO-BREAK SPACE
166
+ 0x75 #UNDEFINED
167
+ 0x76 #UNDEFINED
168
+ 0x77 #UNDEFINED
169
+ 0x78 0x2017 #DOUBLE LOW LINE
170
+ 0x79 0x0060 #GRAVE ACCENT
171
+ 0x7A 0x003A #COLON
172
+ 0x7B 0x0023 #NUMBER SIGN
173
+ 0x7C 0x0040 #COMMERCIAL AT
174
+ 0x7D 0x0027 #APOSTROPHE
175
+ 0x7E 0x003D #EQUALS SIGN
176
+ 0x7F 0x0022 #QUOTATION MARK
177
+ 0x80 #UNDEFINED
178
+ 0x81 0x0061 #LATIN SMALL LETTER A
179
+ 0x82 0x0062 #LATIN SMALL LETTER B
180
+ 0x83 0x0063 #LATIN SMALL LETTER C
181
+ 0x84 0x0064 #LATIN SMALL LETTER D
182
+ 0x85 0x0065 #LATIN SMALL LETTER E
183
+ 0x86 0x0066 #LATIN SMALL LETTER F
184
+ 0x87 0x0067 #LATIN SMALL LETTER G
185
+ 0x88 0x0068 #LATIN SMALL LETTER H
186
+ 0x89 0x0069 #LATIN SMALL LETTER I
187
+ 0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
188
+ 0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
189
+ 0x8C #UNDEFINED
190
+ 0x8D #UNDEFINED
191
+ 0x8E #UNDEFINED
192
+ 0x8F 0x00B1 #PLUS-MINUS SIGN
193
+ 0x90 0x00B0 #DEGREE SIGN
194
+ 0x91 0x006A #LATIN SMALL LETTER J
195
+ 0x92 0x006B #LATIN SMALL LETTER K
196
+ 0x93 0x006C #LATIN SMALL LETTER L
197
+ 0x94 0x006D #LATIN SMALL LETTER M
198
+ 0x95 0x006E #LATIN SMALL LETTER N
199
+ 0x96 0x006F #LATIN SMALL LETTER O
200
+ 0x97 0x0070 #LATIN SMALL LETTER P
201
+ 0x98 0x0071 #LATIN SMALL LETTER Q
202
+ 0x99 0x0072 #LATIN SMALL LETTER R
203
+ 0x9A #UNDEFINED
204
+ 0x9B #UNDEFINED
205
+ 0x9C #UNDEFINED
206
+ 0x9D 0x00B8 #CEDILLA
207
+ 0x9E #UNDEFINED
208
+ 0x9F 0x00A4 #CURRENCY SIGN
209
+ 0xA0 0x00B5 #MICRO SIGN
210
+ 0xA1 0x007E #TILDE
211
+ 0xA2 0x0073 #LATIN SMALL LETTER S
212
+ 0xA3 0x0074 #LATIN SMALL LETTER T
213
+ 0xA4 0x0075 #LATIN SMALL LETTER U
214
+ 0xA5 0x0076 #LATIN SMALL LETTER V
215
+ 0xA6 0x0077 #LATIN SMALL LETTER W
216
+ 0xA7 0x0078 #LATIN SMALL LETTER X
217
+ 0xA8 0x0079 #LATIN SMALL LETTER Y
218
+ 0xA9 0x007A #LATIN SMALL LETTER Z
219
+ 0xAA #UNDEFINED
220
+ 0xAB #UNDEFINED
221
+ 0xAC #UNDEFINED
222
+ 0xAD #UNDEFINED
223
+ 0xAE #UNDEFINED
224
+ 0xAF 0x00AE #REGISTERED SIGN
225
+ 0xB0 0x005E #CIRCUMFLEX ACCENT
226
+ 0xB1 0x00A3 #POUND SIGN
227
+ 0xB2 0x00A5 #YEN SIGN
228
+ 0xB3 0x00B7 #MIDDLE DOT
229
+ 0xB4 0x00A9 #COPYRIGHT SIGN
230
+ 0xB5 0x00A7 #SECTION SIGN
231
+ 0xB6 0x00B6 #PILCROW SIGN
232
+ 0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
233
+ 0xB8 0x00BD #VULGAR FRACTION ONE HALF
234
+ 0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
235
+ 0xBA 0x005B #LEFT SQUARE BRACKET
236
+ 0xBB 0x005D #RIGHT SQUARE BRACKET
237
+ 0xBC 0x00AF #MACRON
238
+ 0xBD 0x00A8 #DIAERESIS
239
+ 0xBE 0x00B4 #ACUTE ACCENT
240
+ 0xBF 0x00D7 #MULTIPLICATION SIGN
241
+ 0xC0 0x007B #LEFT CURLY BRACKET
242
+ 0xC1 0x0041 #LATIN CAPITAL LETTER A
243
+ 0xC2 0x0042 #LATIN CAPITAL LETTER B
244
+ 0xC3 0x0043 #LATIN CAPITAL LETTER C
245
+ 0xC4 0x0044 #LATIN CAPITAL LETTER D
246
+ 0xC5 0x0045 #LATIN CAPITAL LETTER E
247
+ 0xC6 0x0046 #LATIN CAPITAL LETTER F
248
+ 0xC7 0x0047 #LATIN CAPITAL LETTER G
249
+ 0xC8 0x0048 #LATIN CAPITAL LETTER H
250
+ 0xC9 0x0049 #LATIN CAPITAL LETTER I
251
+ 0xCA 0x00AD #SOFT HYPHEN
252
+ 0xCB #UNDEFINED
253
+ 0xCC #UNDEFINED
254
+ 0xCD #UNDEFINED
255
+ 0xCE #UNDEFINED
256
+ 0xCF #UNDEFINED
257
+ 0xD0 0x007D #RIGHT CURLY BRACKET
258
+ 0xD1 0x004A #LATIN CAPITAL LETTER J
259
+ 0xD2 0x004B #LATIN CAPITAL LETTER K
260
+ 0xD3 0x004C #LATIN CAPITAL LETTER L
261
+ 0xD4 0x004D #LATIN CAPITAL LETTER M
262
+ 0xD5 0x004E #LATIN CAPITAL LETTER N
263
+ 0xD6 0x004F #LATIN CAPITAL LETTER O
264
+ 0xD7 0x0050 #LATIN CAPITAL LETTER P
265
+ 0xD8 0x0051 #LATIN CAPITAL LETTER Q
266
+ 0xD9 0x0052 #LATIN CAPITAL LETTER R
267
+ 0xDA 0x00B9 #SUPERSCRIPT ONE
268
+ 0xDB #UNDEFINED
269
+ 0xDC #UNDEFINED
270
+ 0xDD #UNDEFINED
271
+ 0xDE #UNDEFINED
272
+ 0xDF #UNDEFINED
273
+ 0xE0 0x005C #REVERSE SOLIDUS
274
+ 0xE1 0x00F7 #DIVISION SIGN
275
+ 0xE2 0x0053 #LATIN CAPITAL LETTER S
276
+ 0xE3 0x0054 #LATIN CAPITAL LETTER T
277
+ 0xE4 0x0055 #LATIN CAPITAL LETTER U
278
+ 0xE5 0x0056 #LATIN CAPITAL LETTER V
279
+ 0xE6 0x0057 #LATIN CAPITAL LETTER W
280
+ 0xE7 0x0058 #LATIN CAPITAL LETTER X
281
+ 0xE8 0x0059 #LATIN CAPITAL LETTER Y
282
+ 0xE9 0x005A #LATIN CAPITAL LETTER Z
283
+ 0xEA 0x00B2 #SUPERSCRIPT TWO
284
+ 0xEB #UNDEFINED
285
+ 0xEC #UNDEFINED
286
+ 0xED #UNDEFINED
287
+ 0xEE #UNDEFINED
288
+ 0xEF #UNDEFINED
289
+ 0xF0 0x0030 #DIGIT ZERO
290
+ 0xF1 0x0031 #DIGIT ONE
291
+ 0xF2 0x0032 #DIGIT TWO
292
+ 0xF3 0x0033 #DIGIT THREE
293
+ 0xF4 0x0034 #DIGIT FOUR
294
+ 0xF5 0x0035 #DIGIT FIVE
295
+ 0xF6 0x0036 #DIGIT SIX
296
+ 0xF7 0x0037 #DIGIT SEVEN
297
+ 0xF8 0x0038 #DIGIT EIGHT
298
+ 0xF9 0x0039 #DIGIT NINE
299
+ 0xFA 0x00B3 #SUPERSCRIPT THREE
300
+ 0xFB #UNDEFINED
301
+ 0xFC #UNDEFINED
302
+ 0xFD #UNDEFINED
303
+ 0xFE #UNDEFINED
304
+ 0xFF 0x009F #EIGHT ONES
@@ -0,0 +1,274 @@
1
+ #
2
+ # Name: cp437_DOSLatinUS 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 cp437_DOSLatinUS 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 cp437_DOSLatinUS 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 0x00a2 #CENT SIGN
174
+ 0x9c 0x00a3 #POUND SIGN
175
+ 0x9d 0x00a5 #YEN SIGN
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 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 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
+