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: cp037_IBMUSCanada 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 cp037_IBMUSCanada 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 cp037_IBMUSCanada 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 0x009C #CONTROL
23
+ 0x05 0x0009 #HORIZONTAL TABULATION
24
+ 0x06 0x0086 #CONTROL
25
+ 0x07 0x007F #DELETE
26
+ 0x08 0x0097 #CONTROL
27
+ 0x09 0x008D #CONTROL
28
+ 0x0A 0x008E #CONTROL
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 0x009D #CONTROL
39
+ 0x15 0x0085 #CONTROL
40
+ 0x16 0x0008 #BACKSPACE
41
+ 0x17 0x0087 #CONTROL
42
+ 0x18 0x0018 #CANCEL
43
+ 0x19 0x0019 #END OF MEDIUM
44
+ 0x1A 0x0092 #CONTROL
45
+ 0x1B 0x008F #CONTROL
46
+ 0x1C 0x001C #FILE SEPARATOR
47
+ 0x1D 0x001D #GROUP SEPARATOR
48
+ 0x1E 0x001E #RECORD SEPARATOR
49
+ 0x1F 0x001F #UNIT SEPARATOR
50
+ 0x20 0x0080 #CONTROL
51
+ 0x21 0x0081 #CONTROL
52
+ 0x22 0x0082 #CONTROL
53
+ 0x23 0x0083 #CONTROL
54
+ 0x24 0x0084 #CONTROL
55
+ 0x25 0x000A #LINE FEED
56
+ 0x26 0x0017 #END OF TRANSMISSION BLOCK
57
+ 0x27 0x001B #ESCAPE
58
+ 0x28 0x0088 #CONTROL
59
+ 0x29 0x0089 #CONTROL
60
+ 0x2A 0x008A #CONTROL
61
+ 0x2B 0x008B #CONTROL
62
+ 0x2C 0x008C #CONTROL
63
+ 0x2D 0x0005 #ENQUIRY
64
+ 0x2E 0x0006 #ACKNOWLEDGE
65
+ 0x2F 0x0007 #BELL
66
+ 0x30 0x0090 #CONTROL
67
+ 0x31 0x0091 #CONTROL
68
+ 0x32 0x0016 #SYNCHRONOUS IDLE
69
+ 0x33 0x0093 #CONTROL
70
+ 0x34 0x0094 #CONTROL
71
+ 0x35 0x0095 #CONTROL
72
+ 0x36 0x0096 #CONTROL
73
+ 0x37 0x0004 #END OF TRANSMISSION
74
+ 0x38 0x0098 #CONTROL
75
+ 0x39 0x0099 #CONTROL
76
+ 0x3A 0x009A #CONTROL
77
+ 0x3B 0x009B #CONTROL
78
+ 0x3C 0x0014 #DEVICE CONTROL FOUR
79
+ 0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
80
+ 0x3E 0x009E #CONTROL
81
+ 0x3F 0x001A #SUBSTITUTE
82
+ 0x40 0x0020 #SPACE
83
+ 0x41 0x00A0 #NO-BREAK SPACE
84
+ 0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
85
+ 0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
86
+ 0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
87
+ 0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
88
+ 0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
89
+ 0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
90
+ 0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
91
+ 0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
92
+ 0x4A 0x00A2 #CENT SIGN
93
+ 0x4B 0x002E #FULL STOP
94
+ 0x4C 0x003C #LESS-THAN SIGN
95
+ 0x4D 0x0028 #LEFT PARENTHESIS
96
+ 0x4E 0x002B #PLUS SIGN
97
+ 0x4F 0x007C #VERTICAL LINE
98
+ 0x50 0x0026 #AMPERSAND
99
+ 0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
100
+ 0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
101
+ 0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
102
+ 0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
103
+ 0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
104
+ 0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
105
+ 0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
106
+ 0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
107
+ 0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
108
+ 0x5A 0x0021 #EXCLAMATION MARK
109
+ 0x5B 0x0024 #DOLLAR SIGN
110
+ 0x5C 0x002A #ASTERISK
111
+ 0x5D 0x0029 #RIGHT PARENTHESIS
112
+ 0x5E 0x003B #SEMICOLON
113
+ 0x5F 0x00AC #NOT SIGN
114
+ 0x60 0x002D #HYPHEN-MINUS
115
+ 0x61 0x002F #SOLIDUS
116
+ 0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
117
+ 0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
118
+ 0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
119
+ 0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
120
+ 0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
121
+ 0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
122
+ 0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
123
+ 0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
124
+ 0x6A 0x00A6 #BROKEN BAR
125
+ 0x6B 0x002C #COMMA
126
+ 0x6C 0x0025 #PERCENT SIGN
127
+ 0x6D 0x005F #LOW LINE
128
+ 0x6E 0x003E #GREATER-THAN SIGN
129
+ 0x6F 0x003F #QUESTION MARK
130
+ 0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
131
+ 0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
132
+ 0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
133
+ 0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
134
+ 0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
135
+ 0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
136
+ 0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
137
+ 0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
138
+ 0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
139
+ 0x79 0x0060 #GRAVE ACCENT
140
+ 0x7A 0x003A #COLON
141
+ 0x7B 0x0023 #NUMBER SIGN
142
+ 0x7C 0x0040 #COMMERCIAL AT
143
+ 0x7D 0x0027 #APOSTROPHE
144
+ 0x7E 0x003D #EQUALS SIGN
145
+ 0x7F 0x0022 #QUOTATION MARK
146
+ 0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
147
+ 0x81 0x0061 #LATIN SMALL LETTER A
148
+ 0x82 0x0062 #LATIN SMALL LETTER B
149
+ 0x83 0x0063 #LATIN SMALL LETTER C
150
+ 0x84 0x0064 #LATIN SMALL LETTER D
151
+ 0x85 0x0065 #LATIN SMALL LETTER E
152
+ 0x86 0x0066 #LATIN SMALL LETTER F
153
+ 0x87 0x0067 #LATIN SMALL LETTER G
154
+ 0x88 0x0068 #LATIN SMALL LETTER H
155
+ 0x89 0x0069 #LATIN SMALL LETTER I
156
+ 0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
157
+ 0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
158
+ 0x8C 0x00F0 #LATIN SMALL LETTER ETH (ICELANDIC)
159
+ 0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
160
+ 0x8E 0x00FE #LATIN SMALL LETTER THORN (ICELANDIC)
161
+ 0x8F 0x00B1 #PLUS-MINUS SIGN
162
+ 0x90 0x00B0 #DEGREE SIGN
163
+ 0x91 0x006A #LATIN SMALL LETTER J
164
+ 0x92 0x006B #LATIN SMALL LETTER K
165
+ 0x93 0x006C #LATIN SMALL LETTER L
166
+ 0x94 0x006D #LATIN SMALL LETTER M
167
+ 0x95 0x006E #LATIN SMALL LETTER N
168
+ 0x96 0x006F #LATIN SMALL LETTER O
169
+ 0x97 0x0070 #LATIN SMALL LETTER P
170
+ 0x98 0x0071 #LATIN SMALL LETTER Q
171
+ 0x99 0x0072 #LATIN SMALL LETTER R
172
+ 0x9A 0x00AA #FEMININE ORDINAL INDICATOR
173
+ 0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
174
+ 0x9C 0x00E6 #LATIN SMALL LIGATURE AE
175
+ 0x9D 0x00B8 #CEDILLA
176
+ 0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
177
+ 0x9F 0x00A4 #CURRENCY SIGN
178
+ 0xA0 0x00B5 #MICRO SIGN
179
+ 0xA1 0x007E #TILDE
180
+ 0xA2 0x0073 #LATIN SMALL LETTER S
181
+ 0xA3 0x0074 #LATIN SMALL LETTER T
182
+ 0xA4 0x0075 #LATIN SMALL LETTER U
183
+ 0xA5 0x0076 #LATIN SMALL LETTER V
184
+ 0xA6 0x0077 #LATIN SMALL LETTER W
185
+ 0xA7 0x0078 #LATIN SMALL LETTER X
186
+ 0xA8 0x0079 #LATIN SMALL LETTER Y
187
+ 0xA9 0x007A #LATIN SMALL LETTER Z
188
+ 0xAA 0x00A1 #INVERTED EXCLAMATION MARK
189
+ 0xAB 0x00BF #INVERTED QUESTION MARK
190
+ 0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (ICELANDIC)
191
+ 0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
192
+ 0xAE 0x00DE #LATIN CAPITAL LETTER THORN (ICELANDIC)
193
+ 0xAF 0x00AE #REGISTERED SIGN
194
+ 0xB0 0x005E #CIRCUMFLEX ACCENT
195
+ 0xB1 0x00A3 #POUND SIGN
196
+ 0xB2 0x00A5 #YEN SIGN
197
+ 0xB3 0x00B7 #MIDDLE DOT
198
+ 0xB4 0x00A9 #COPYRIGHT SIGN
199
+ 0xB5 0x00A7 #SECTION SIGN
200
+ 0xB6 0x00B6 #PILCROW SIGN
201
+ 0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
202
+ 0xB8 0x00BD #VULGAR FRACTION ONE HALF
203
+ 0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
204
+ 0xBA 0x005B #LEFT SQUARE BRACKET
205
+ 0xBB 0x005D #RIGHT SQUARE BRACKET
206
+ 0xBC 0x00AF #MACRON
207
+ 0xBD 0x00A8 #DIAERESIS
208
+ 0xBE 0x00B4 #ACUTE ACCENT
209
+ 0xBF 0x00D7 #MULTIPLICATION SIGN
210
+ 0xC0 0x007B #LEFT CURLY BRACKET
211
+ 0xC1 0x0041 #LATIN CAPITAL LETTER A
212
+ 0xC2 0x0042 #LATIN CAPITAL LETTER B
213
+ 0xC3 0x0043 #LATIN CAPITAL LETTER C
214
+ 0xC4 0x0044 #LATIN CAPITAL LETTER D
215
+ 0xC5 0x0045 #LATIN CAPITAL LETTER E
216
+ 0xC6 0x0046 #LATIN CAPITAL LETTER F
217
+ 0xC7 0x0047 #LATIN CAPITAL LETTER G
218
+ 0xC8 0x0048 #LATIN CAPITAL LETTER H
219
+ 0xC9 0x0049 #LATIN CAPITAL LETTER I
220
+ 0xCA 0x00AD #SOFT HYPHEN
221
+ 0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
222
+ 0xCC 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
223
+ 0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
224
+ 0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
225
+ 0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
226
+ 0xD0 0x007D #RIGHT CURLY BRACKET
227
+ 0xD1 0x004A #LATIN CAPITAL LETTER J
228
+ 0xD2 0x004B #LATIN CAPITAL LETTER K
229
+ 0xD3 0x004C #LATIN CAPITAL LETTER L
230
+ 0xD4 0x004D #LATIN CAPITAL LETTER M
231
+ 0xD5 0x004E #LATIN CAPITAL LETTER N
232
+ 0xD6 0x004F #LATIN CAPITAL LETTER O
233
+ 0xD7 0x0050 #LATIN CAPITAL LETTER P
234
+ 0xD8 0x0051 #LATIN CAPITAL LETTER Q
235
+ 0xD9 0x0052 #LATIN CAPITAL LETTER R
236
+ 0xDA 0x00B9 #SUPERSCRIPT ONE
237
+ 0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
238
+ 0xDC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
239
+ 0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
240
+ 0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
241
+ 0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
242
+ 0xE0 0x005C #REVERSE SOLIDUS
243
+ 0xE1 0x00F7 #DIVISION SIGN
244
+ 0xE2 0x0053 #LATIN CAPITAL LETTER S
245
+ 0xE3 0x0054 #LATIN CAPITAL LETTER T
246
+ 0xE4 0x0055 #LATIN CAPITAL LETTER U
247
+ 0xE5 0x0056 #LATIN CAPITAL LETTER V
248
+ 0xE6 0x0057 #LATIN CAPITAL LETTER W
249
+ 0xE7 0x0058 #LATIN CAPITAL LETTER X
250
+ 0xE8 0x0059 #LATIN CAPITAL LETTER Y
251
+ 0xE9 0x005A #LATIN CAPITAL LETTER Z
252
+ 0xEA 0x00B2 #SUPERSCRIPT TWO
253
+ 0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
254
+ 0xEC 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
255
+ 0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
256
+ 0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
257
+ 0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
258
+ 0xF0 0x0030 #DIGIT ZERO
259
+ 0xF1 0x0031 #DIGIT ONE
260
+ 0xF2 0x0032 #DIGIT TWO
261
+ 0xF3 0x0033 #DIGIT THREE
262
+ 0xF4 0x0034 #DIGIT FOUR
263
+ 0xF5 0x0035 #DIGIT FIVE
264
+ 0xF6 0x0036 #DIGIT SIX
265
+ 0xF7 0x0037 #DIGIT SEVEN
266
+ 0xF8 0x0038 #DIGIT EIGHT
267
+ 0xF9 0x0039 #DIGIT NINE
268
+ 0xFA 0x00B3 #SUPERSCRIPT THREE
269
+ 0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
270
+ 0xFC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
271
+ 0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
272
+ 0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
273
+ 0xFF 0x009F #CONTROL
274
+
275
+ 
@@ -0,0 +1,302 @@
1
+ #
2
+ # Name: IBM CP1006 to Unicode
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
+ # IBM CP1006 characters map into Unicode.
29
+ #
30
+ # Format: Three tab-separated columns
31
+ # Column #1 is the CP1006 code (in hex as 0xXX)
32
+ # Column #2 is the Unicode (in hex as 0xXXXX)
33
+ # Column #3 the Unicode name (follows a comment sign, '#')
34
+ #
35
+ # The entries are in IBM CP1006 order.
36
+ #
37
+ # Version history
38
+ # 1.0 version new.
39
+ #
40
+ # Updated versions of this file may be found in:
41
+ # <ftp://ftp.unicode.org/Public/MAPPINGS/>
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 0x0080 # <control>
176
+ 0x81 0x0081 # <control>
177
+ 0x82 0x0082 # <control>
178
+ 0x83 0x0083 # <control>
179
+ 0x84 0x0084 # <control>
180
+ 0x85 0x0085 # <control>
181
+ 0x86 0x0086 # <control>
182
+ 0x87 0x0087 # <control>
183
+ 0x88 0x0088 # <control>
184
+ 0x89 0x0089 # <control>
185
+ 0x8A 0x008A # <control>
186
+ 0x8B 0x008B # <control>
187
+ 0x8C 0x008C # <control>
188
+ 0x8D 0x008D # <control>
189
+ 0x8E 0x008E # <control>
190
+ 0x8F 0x008F # <control>
191
+ 0x90 0x0090 # <control>
192
+ 0x91 0x0091 # <control>
193
+ 0x92 0x0092 # <control>
194
+ 0x93 0x0093 # <control>
195
+ 0x94 0x0094 # <control>
196
+ 0x95 0x0095 # <control>
197
+ 0x96 0x0096 # <control>
198
+ 0x97 0x0097 # <control>
199
+ 0x98 0x0098 # <control>
200
+ 0x99 0x0099 # <control>
201
+ 0x9A 0x009A # <control>
202
+ 0x9B 0x009B # <control>
203
+ 0x9C 0x009C # <control>
204
+ 0x9D 0x009D # <control>
205
+ 0x9E 0x009E # <control>
206
+ 0x9F 0x009F # <control>
207
+ 0xA0 0x00A0 # NO-BREAK SPACE
208
+ 0xA1 0x06F0 # EXTENDED ARABIC-INDIC DIGIT ZERO
209
+ 0xA2 0x06F1 # EXTENDED ARABIC-INDIC DIGIT ONE
210
+ 0xA3 0x06F2 # EXTENDED ARABIC-INDIC DIGIT TWO
211
+ 0xA4 0x06F3 # EXTENDED ARABIC-INDIC DIGIT THREE
212
+ 0xA5 0x06F4 # EXTENDED ARABIC-INDIC DIGIT FOUR
213
+ 0xA6 0x06F5 # EXTENDED ARABIC-INDIC DIGIT FIVE
214
+ 0xA7 0x06F6 # EXTENDED ARABIC-INDIC DIGIT SIX
215
+ 0xA8 0x06F7 # EXTENDED ARABIC-INDIC DIGIT SEVEN
216
+ 0xA9 0x06F8 # EXTENDED ARABIC-INDIC DIGIT EIGHT
217
+ 0xAA 0x06F9 # EXTENDED ARABIC-INDIC DIGIT NINE
218
+ 0xAB 0x060C # ARABIC COMMA
219
+ 0xAC 0x061B # ARABIC SEMICOLON
220
+ 0xAD 0x00AD # SOFT HYPHEN
221
+ 0xAE 0x061F # ARABIC QUESTION MARK
222
+ 0xAF 0xFE81 # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
223
+ 0xB0 0xFE8D # ARABIC LETTER ALEF ISOLATED FORM
224
+ 0xB1 0xFE8E # ARABIC LETTER ALEF FINAL FORM
225
+ 0xB2 0xFE8E # ARABIC LETTER ALEF FINAL FORM
226
+ 0xB3 0xFE8F # ARABIC LETTER BEH ISOLATED FORM
227
+ 0xB4 0xFE91 # ARABIC LETTER BEH INITIAL FORM
228
+ 0xB5 0xFB56 # ARABIC LETTER PEH ISOLATED FORM
229
+ 0xB6 0xFB58 # ARABIC LETTER PEH INITIAL FORM
230
+ 0xB7 0xFE93 # ARABIC LETTER TEH MARBUTA ISOLATED FORM
231
+ 0xB8 0xFE95 # ARABIC LETTER TEH ISOLATED FORM
232
+ 0xB9 0xFE97 # ARABIC LETTER TEH INITIAL FORM
233
+ 0xBA 0xFB66 # ARABIC LETTER TTEH ISOLATED FORM
234
+ 0xBB 0xFB68 # ARABIC LETTER TTEH INITIAL FORM
235
+ 0xBC 0xFE99 # ARABIC LETTER THEH ISOLATED FORM
236
+ 0xBD 0xFE9B # ARABIC LETTER THEH INITIAL FORM
237
+ 0xBE 0xFE9D # ARABIC LETTER JEEM ISOLATED FORM
238
+ 0xBF 0xFE9F # ARABIC LETTER JEEM INITIAL FORM
239
+ 0xC0 0xFB7A # ARABIC LETTER TCHEH ISOLATED FORM
240
+ 0xC1 0xFB7C # ARABIC LETTER TCHEH INITIAL FORM
241
+ 0xC2 0xFEA1 # ARABIC LETTER HAH ISOLATED FORM
242
+ 0xC3 0xFEA3 # ARABIC LETTER HAH INITIAL FORM
243
+ 0xC4 0xFEA5 # ARABIC LETTER KHAH ISOLATED FORM
244
+ 0xC5 0xFEA7 # ARABIC LETTER KHAH INITIAL FORM
245
+ 0xC6 0xFEA9 # ARABIC LETTER DAL ISOLATED FORM
246
+ 0xC7 0xFB84 # ARABIC LETTER DAHAL ISOLATED FORMN
247
+ 0xC8 0xFEAB # ARABIC LETTER THAL ISOLATED FORM
248
+ 0xC9 0xFEAD # ARABIC LETTER REH ISOLATED FORM
249
+ 0xCA 0xFB8C # ARABIC LETTER RREH ISOLATED FORM
250
+ 0xCB 0xFEAF # ARABIC LETTER ZAIN ISOLATED FORM
251
+ 0xCC 0xFB8A # ARABIC LETTER JEH ISOLATED FORM
252
+ 0xCD 0xFEB1 # ARABIC LETTER SEEN ISOLATED FORM
253
+ 0xCE 0xFEB3 # ARABIC LETTER SEEN INITIAL FORM
254
+ 0xCF 0xFEB5 # ARABIC LETTER SHEEN ISOLATED FORM
255
+ 0xD0 0xFEB7 # ARABIC LETTER SHEEN INITIAL FORM
256
+ 0xD1 0xFEB9 # ARABIC LETTER SAD ISOLATED FORM
257
+ 0xD2 0xFEBB # ARABIC LETTER SAD INITIAL FORM
258
+ 0xD3 0xFEBD # ARABIC LETTER DAD ISOLATED FORM
259
+ 0xD4 0xFEBF # ARABIC LETTER DAD INITIAL FORM
260
+ 0xD5 0xFEC1 # ARABIC LETTER TAH ISOLATED FORM
261
+ 0xD6 0xFEC5 # ARABIC LETTER ZAH ISOLATED FORM
262
+ 0xD7 0xFEC9 # ARABIC LETTER AIN ISOLATED FORM
263
+ 0xD8 0xFECA # ARABIC LETTER AIN FINAL FORM
264
+ 0xD9 0xFECB # ARABIC LETTER AIN INITIAL FORM
265
+ 0xDA 0xFECC # ARABIC LETTER AIN MEDIAL FORM
266
+ 0xDB 0xFECD # ARABIC LETTER GHAIN ISOLATED FORM
267
+ 0xDC 0xFECE # ARABIC LETTER GHAIN FINAL FORM
268
+ 0xDD 0xFECF # ARABIC LETTER GHAIN INITIAL FORM
269
+ 0xDE 0xFED0 # ARABIC LETTER GHAIN MEDIAL FORM
270
+ 0xDF 0xFED1 # ARABIC LETTER FEH ISOLATED FORM
271
+ 0xE0 0xFED3 # ARABIC LETTER FEH INITIAL FORM
272
+ 0xE1 0xFED5 # ARABIC LETTER QAF ISOLATED FORM
273
+ 0xE2 0xFED7 # ARABIC LETTER QAF INITIAL FORM
274
+ 0xE3 0xFED9 # ARABIC LETTER KAF ISOLATED FORM
275
+ 0xE4 0xFEDB # ARABIC LETTER KAF INITIAL FORM
276
+ 0xE5 0xFB92 # ARABIC LETTER GAF ISOLATED FORM
277
+ 0xE6 0xFB94 # ARABIC LETTER GAF INITIAL FORM
278
+ 0xE7 0xFEDD # ARABIC LETTER LAM ISOLATED FORM
279
+ 0xE8 0xFEDF # ARABIC LETTER LAM INITIAL FORM
280
+ 0xE9 0xFEE0 # ARABIC LETTER LAM MEDIAL FORM
281
+ 0xEA 0xFEE1 # ARABIC LETTER MEEM ISOLATED FORM
282
+ 0xEB 0xFEE3 # ARABIC LETTER MEEM INITIAL FORM
283
+ 0xEC 0xFB9E # ARABIC LETTER NOON GHUNNA ISOLATED FORM
284
+ 0xED 0xFEE5 # ARABIC LETTER NOON ISOLATED FORM
285
+ 0xEE 0xFEE7 # ARABIC LETTER NOON INITIAL FORM
286
+ 0xEF 0xFE85 # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
287
+ 0xF0 0xFEED # ARABIC LETTER WAW ISOLATED FORM
288
+ 0xF1 0xFBA6 # ARABIC LETTER HEH GOAL ISOLATED FORM
289
+ 0xF2 0xFBA8 # ARABIC LETTER HEH GOAL INITIAL FORM
290
+ 0xF3 0xFBA9 # ARABIC LETTER HEH GOAL MEDIAL FORM
291
+ 0xF4 0xFBAA # ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM
292
+ 0xF5 0xFE80 # ARABIC LETTER HAMZA ISOLATED FORM
293
+ 0xF6 0xFE89 # ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM
294
+ 0xF7 0xFE8A # ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM
295
+ 0xF8 0xFE8B # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
296
+ 0xF9 0xFEF1 # ARABIC LETTER YEH ISOLATED FORM
297
+ 0xFA 0xFEF2 # ARABIC LETTER YEH FINAL FORM
298
+ 0xFB 0xFEF3 # ARABIC LETTER YEH INITIAL FORM
299
+ 0xFC 0xFBB0 # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM
300
+ 0xFD 0xFBAE # ARABIC LETTER YEH BARREE ISOLATED FORM
301
+ 0xFE 0xFE7C # ARABIC SHADDA ISOLATED FORM
302
+ 0xFF 0xFE7D # ARABIC SHADDA MEDIAL FORM