langa 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (122) hide show
  1. data/COPYING +674 -0
  2. data/README +69 -0
  3. data/bin/langa +169 -0
  4. data/examples/afrikaans_1953_utf8.txt +1000 -0
  5. data/examples/albanian_utf8.txt +1000 -0
  6. data/examples/amharic_utf8.txt +1000 -0
  7. data/examples/arabic_svd_utf8.txt +1000 -0
  8. data/examples/armenian_western_1853_utf8.txt +1000 -0
  9. data/examples/asv_utf8.txt +1000 -0
  10. data/examples/basque_1571_utf8.txt +1000 -0
  11. data/examples/breton_utf8.txt +1000 -0
  12. data/examples/chinese_ncv_s_utf8.txt +1000 -0
  13. data/examples/chinese_ncv_utf8.txt +1000 -0
  14. data/examples/chinese_union_s_utf8.txt +1000 -0
  15. data/examples/chinese_union_utf8.txt +1000 -0
  16. data/examples/coptic_nt_utf8.txt +1000 -0
  17. data/examples/croatian_utf8.txt +1000 -0
  18. data/examples/czech_bkr_utf8.txt +1000 -0
  19. data/examples/danish_utf8.txt +1000 -0
  20. data/examples/dutch_svv_utf8.txt +1000 -0
  21. data/examples/esperanto_utf8.txt +1000 -0
  22. data/examples/estonian_utf8.txt +1000 -0
  23. data/examples/finnish_pr_1992_utf8.txt +1000 -0
  24. data/examples/french_ostervald_1996_utf8.txt +1000 -0
  25. data/examples/german_schlachter_1951_utf8.txt +1000 -0
  26. data/examples/greek_byzantine_2000_utf8.txt +1000 -0
  27. data/examples/greek_modern_utf8.txt +1000 -0
  28. data/examples/hebrew_modern_utf8.txt +1000 -0
  29. data/examples/hungarian_karoli_utf8.txt +1000 -0
  30. data/examples/italian_riveduta_1927_utf8.txt +1000 -0
  31. data/examples/kabyle_nt_utf8.txt +1000 -0
  32. data/examples/kjv_apocrypha_utf8.txt +1000 -0
  33. data/examples/korean_utf8.txt +1000 -0
  34. data/examples/latin_vulgata_clementina_utf8.txt +1000 -0
  35. data/examples/latvian_nt_utf8.txt +1000 -0
  36. data/examples/lithuanian_utf8.txt +1000 -0
  37. data/examples/manx_gaelic_utf8.txt +1000 -0
  38. data/examples/maori_utf8.txt +1000 -0
  39. data/examples/myanmar_judson_1835_utf8.txt +1000 -0
  40. data/examples/norwegian_utf8.txt +1000 -0
  41. data/examples/peshitta_utf8.txt +1000 -0
  42. data/examples/portuguese_utf8.txt +1000 -0
  43. data/examples/romani_utf8.txt +1000 -0
  44. data/examples/romanian_cornilescu_utf8.txt +1000 -0
  45. data/examples/russian_makarij_utf8.txt +1000 -0
  46. data/examples/spanish_reina_valera_1909_utf8.txt +1000 -0
  47. data/examples/swedish_1917_utf8.txt +1000 -0
  48. data/examples/tagalog_1905_utf8.txt +1000 -0
  49. data/examples/thai_kjv_utf8.txt +1000 -0
  50. data/examples/turkish_nt_utf8.txt +1000 -0
  51. data/examples/turkish_utf8.txt +1000 -0
  52. data/examples/ukrainian_1871_utf8.txt +1000 -0
  53. data/examples/vietnamese_1934_utf8.txt +1000 -0
  54. data/examples/wolof_utf8.txt +1000 -0
  55. data/examples/xhosa_utf8.txt +1000 -0
  56. data/lib/langa.rb +35 -0
  57. data/lib/langa/dna.rb +209 -0
  58. data/lib/langa/file.rb +97 -0
  59. data/lib/langa/langa.dna +406 -0
  60. data/lib/langa/languageanalyzer.rb +134 -0
  61. data/lib/langa/languages.rb +147 -0
  62. data/lib/langa/randomtestfiles.rb +140 -0
  63. data/lib/langa/utilities.rb +53 -0
  64. data/test/tc_file.rb +47 -0
  65. data/test/tc_languages.rb +69 -0
  66. data/test/tc_utilities.rb +42 -0
  67. data/unicode/CaseFolding.txt +1065 -0
  68. data/unicode/CaseFolding.txt.webloc +8 -0
  69. data/unicode/Index of -Public-MAPPINGS.webloc b/data/unicode/Index of → -Public-MAPPINGS.webloc +0 -0
  70. data/unicode/mappings/8859-1.TXT +303 -0
  71. data/unicode/mappings/8859-10.TXT +303 -0
  72. data/unicode/mappings/8859-11.TXT +297 -0
  73. data/unicode/mappings/8859-13.TXT +299 -0
  74. data/unicode/mappings/8859-14.TXT +301 -0
  75. data/unicode/mappings/8859-15.TXT +303 -0
  76. data/unicode/mappings/8859-16.TXT +299 -0
  77. data/unicode/mappings/8859-2.TXT +303 -0
  78. data/unicode/mappings/8859-3.TXT +296 -0
  79. data/unicode/mappings/8859-4.TXT +303 -0
  80. data/unicode/mappings/8859-5.TXT +303 -0
  81. data/unicode/mappings/8859-6.TXT +260 -0
  82. data/unicode/mappings/8859-7.TXT +308 -0
  83. data/unicode/mappings/8859-8.TXT +270 -0
  84. data/unicode/mappings/8859-9.TXT +307 -0
  85. data/unicode/mappings/ATARIST.TXT +313 -0
  86. data/unicode/mappings/CP037.TXT +275 -0
  87. data/unicode/mappings/CP1006.TXT +302 -0
  88. data/unicode/mappings/CP1026.TXT +275 -0
  89. data/unicode/mappings/CP1250.TXT +274 -0
  90. data/unicode/mappings/CP1251.TXT +274 -0
  91. data/unicode/mappings/CP1252.TXT +274 -0
  92. data/unicode/mappings/CP1253.TXT +274 -0
  93. data/unicode/mappings/CP1254.TXT +274 -0
  94. data/unicode/mappings/CP1255.TXT +274 -0
  95. data/unicode/mappings/CP1256.TXT +274 -0
  96. data/unicode/mappings/CP1257.TXT +274 -0
  97. data/unicode/mappings/CP1258.TXT +274 -0
  98. data/unicode/mappings/CP424.TXT +304 -0
  99. data/unicode/mappings/CP437.TXT +274 -0
  100. data/unicode/mappings/CP500.TXT +275 -0
  101. data/unicode/mappings/CP737.TXT +274 -0
  102. data/unicode/mappings/CP775.TXT +275 -0
  103. data/unicode/mappings/CP850.TXT +274 -0
  104. data/unicode/mappings/CP852.TXT +274 -0
  105. data/unicode/mappings/CP855.TXT +275 -0
  106. data/unicode/mappings/CP856.TXT +303 -0
  107. data/unicode/mappings/CP857.TXT +275 -0
  108. data/unicode/mappings/CP860.TXT +275 -0
  109. data/unicode/mappings/CP861.TXT +275 -0
  110. data/unicode/mappings/CP862.TXT +275 -0
  111. data/unicode/mappings/CP863.TXT +275 -0
  112. data/unicode/mappings/CP864.TXT +275 -0
  113. data/unicode/mappings/CP865.TXT +275 -0
  114. data/unicode/mappings/CP866.TXT +275 -0
  115. data/unicode/mappings/CP869.TXT +275 -0
  116. data/unicode/mappings/CP874.TXT +274 -0
  117. data/unicode/mappings/CP875.TXT +275 -0
  118. data/unicode/mappings/KOI8-R.TXT +302 -0
  119. data/unicode/mappings/NEXTSTEP.TXT +173 -0
  120. data/unicode/mappings/ROMAN.TXT +275 -0
  121. data/unicode/mappings/US-ASCII-QUOTES.TXT +198 -0
  122. metadata +180 -0
@@ -0,0 +1,275 @@
1
+ #
2
+ # Name: cp1026_IBMLatin5Turkish 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 cp1026_IBMLatin5Turkish 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 cp1026_IBMLatin5Turkish 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 0x007B #LEFT CURLY BRACKET
91
+ 0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
92
+ 0x4A 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
93
+ 0x4B 0x002E #FULL STOP
94
+ 0x4C 0x003C #LESS-THAN SIGN
95
+ 0x4D 0x0028 #LEFT PARENTHESIS
96
+ 0x4E 0x002B #PLUS SIGN
97
+ 0x4F 0x0021 #EXCLAMATION MARK
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 0x011E #LATIN CAPITAL LETTER G WITH BREVE
109
+ 0x5B 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
110
+ 0x5C 0x002A #ASTERISK
111
+ 0x5D 0x0029 #RIGHT PARENTHESIS
112
+ 0x5E 0x003B #SEMICOLON
113
+ 0x5F 0x005E #CIRCUMFLEX ACCENT
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 0x005B #LEFT SQUARE BRACKET
123
+ 0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
124
+ 0x6A 0x015F #LATIN SMALL LETTER S WITH CEDILLA
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 0x0131 #LATIN SMALL LETTER DOTLESS I
140
+ 0x7A 0x003A #COLON
141
+ 0x7B 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
142
+ 0x7C 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
143
+ 0x7D 0x0027 #APOSTROPHE
144
+ 0x7E 0x003D #EQUALS SIGN
145
+ 0x7F 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
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 0x007D #RIGHT CURLY BRACKET
159
+ 0x8D 0x0060 #GRAVE ACCENT
160
+ 0x8E 0x00A6 #BROKEN BAR
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 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
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 0x005D #RIGHT SQUARE BRACKET
191
+ 0xAD 0x0024 #DOLLAR SIGN
192
+ 0xAE 0x0040 #COMMERCIAL AT
193
+ 0xAF 0x00AE #REGISTERED SIGN
194
+ 0xB0 0x00A2 #CENT SIGN
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 0x00AC #NOT SIGN
205
+ 0xBB 0x007C #VERTICAL LINE
206
+ 0xBC 0x00AF #MACRON
207
+ 0xBD 0x00A8 #DIAERESIS
208
+ 0xBE 0x00B4 #ACUTE ACCENT
209
+ 0xBF 0x00D7 #MULTIPLICATION SIGN
210
+ 0xC0 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
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 0x007E #TILDE
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 0x011F #LATIN SMALL LETTER G WITH BREVE
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 0x005C #REVERSE SOLIDUS
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 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
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 0x0023 #NUMBER SIGN
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 0x0022 #QUOTATION MARK
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 +1,274 @@
1
+ #
2
+ # Name: cp1250 to Unicode table
3
+ # Unicode version: 2.0
4
+ # Table version: 2.01
5
+ # Table format: Format A
6
+ # Date: 04/15/98
7
+ #
8
+ # Contact: Shawn.Steele@microsoft.com
9
+ #
10
+ # General notes: none
11
+ #
12
+ # Format: Three tab-separated columns
13
+ # Column #1 is the cp1250 code (in hex)
14
+ # Column #2 is the Unicode (in hex as 0xXXXX)
15
+ # Column #3 is the Unicode name (follows a comment sign, '#')
16
+ #
17
+ # The entries are in cp1250 order
18
+ #
19
+ 0x00 0x0000 #NULL
20
+ 0x01 0x0001 #START OF HEADING
21
+ 0x02 0x0002 #START OF TEXT
22
+ 0x03 0x0003 #END OF TEXT
23
+ 0x04 0x0004 #END OF TRANSMISSION
24
+ 0x05 0x0005 #ENQUIRY
25
+ 0x06 0x0006 #ACKNOWLEDGE
26
+ 0x07 0x0007 #BELL
27
+ 0x08 0x0008 #BACKSPACE
28
+ 0x09 0x0009 #HORIZONTAL TABULATION
29
+ 0x0A 0x000A #LINE FEED
30
+ 0x0B 0x000B #VERTICAL TABULATION
31
+ 0x0C 0x000C #FORM FEED
32
+ 0x0D 0x000D #CARRIAGE RETURN
33
+ 0x0E 0x000E #SHIFT OUT
34
+ 0x0F 0x000F #SHIFT IN
35
+ 0x10 0x0010 #DATA LINK ESCAPE
36
+ 0x11 0x0011 #DEVICE CONTROL ONE
37
+ 0x12 0x0012 #DEVICE CONTROL TWO
38
+ 0x13 0x0013 #DEVICE CONTROL THREE
39
+ 0x14 0x0014 #DEVICE CONTROL FOUR
40
+ 0x15 0x0015 #NEGATIVE ACKNOWLEDGE
41
+ 0x16 0x0016 #SYNCHRONOUS IDLE
42
+ 0x17 0x0017 #END OF TRANSMISSION BLOCK
43
+ 0x18 0x0018 #CANCEL
44
+ 0x19 0x0019 #END OF MEDIUM
45
+ 0x1A 0x001A #SUBSTITUTE
46
+ 0x1B 0x001B #ESCAPE
47
+ 0x1C 0x001C #FILE SEPARATOR
48
+ 0x1D 0x001D #GROUP SEPARATOR
49
+ 0x1E 0x001E #RECORD SEPARATOR
50
+ 0x1F 0x001F #UNIT SEPARATOR
51
+ 0x20 0x0020 #SPACE
52
+ 0x21 0x0021 #EXCLAMATION MARK
53
+ 0x22 0x0022 #QUOTATION MARK
54
+ 0x23 0x0023 #NUMBER SIGN
55
+ 0x24 0x0024 #DOLLAR SIGN
56
+ 0x25 0x0025 #PERCENT SIGN
57
+ 0x26 0x0026 #AMPERSAND
58
+ 0x27 0x0027 #APOSTROPHE
59
+ 0x28 0x0028 #LEFT PARENTHESIS
60
+ 0x29 0x0029 #RIGHT PARENTHESIS
61
+ 0x2A 0x002A #ASTERISK
62
+ 0x2B 0x002B #PLUS SIGN
63
+ 0x2C 0x002C #COMMA
64
+ 0x2D 0x002D #HYPHEN-MINUS
65
+ 0x2E 0x002E #FULL STOP
66
+ 0x2F 0x002F #SOLIDUS
67
+ 0x30 0x0030 #DIGIT ZERO
68
+ 0x31 0x0031 #DIGIT ONE
69
+ 0x32 0x0032 #DIGIT TWO
70
+ 0x33 0x0033 #DIGIT THREE
71
+ 0x34 0x0034 #DIGIT FOUR
72
+ 0x35 0x0035 #DIGIT FIVE
73
+ 0x36 0x0036 #DIGIT SIX
74
+ 0x37 0x0037 #DIGIT SEVEN
75
+ 0x38 0x0038 #DIGIT EIGHT
76
+ 0x39 0x0039 #DIGIT NINE
77
+ 0x3A 0x003A #COLON
78
+ 0x3B 0x003B #SEMICOLON
79
+ 0x3C 0x003C #LESS-THAN SIGN
80
+ 0x3D 0x003D #EQUALS SIGN
81
+ 0x3E 0x003E #GREATER-THAN SIGN
82
+ 0x3F 0x003F #QUESTION MARK
83
+ 0x40 0x0040 #COMMERCIAL AT
84
+ 0x41 0x0041 #LATIN CAPITAL LETTER A
85
+ 0x42 0x0042 #LATIN CAPITAL LETTER B
86
+ 0x43 0x0043 #LATIN CAPITAL LETTER C
87
+ 0x44 0x0044 #LATIN CAPITAL LETTER D
88
+ 0x45 0x0045 #LATIN CAPITAL LETTER E
89
+ 0x46 0x0046 #LATIN CAPITAL LETTER F
90
+ 0x47 0x0047 #LATIN CAPITAL LETTER G
91
+ 0x48 0x0048 #LATIN CAPITAL LETTER H
92
+ 0x49 0x0049 #LATIN CAPITAL LETTER I
93
+ 0x4A 0x004A #LATIN CAPITAL LETTER J
94
+ 0x4B 0x004B #LATIN CAPITAL LETTER K
95
+ 0x4C 0x004C #LATIN CAPITAL LETTER L
96
+ 0x4D 0x004D #LATIN CAPITAL LETTER M
97
+ 0x4E 0x004E #LATIN CAPITAL LETTER N
98
+ 0x4F 0x004F #LATIN CAPITAL LETTER O
99
+ 0x50 0x0050 #LATIN CAPITAL LETTER P
100
+ 0x51 0x0051 #LATIN CAPITAL LETTER Q
101
+ 0x52 0x0052 #LATIN CAPITAL LETTER R
102
+ 0x53 0x0053 #LATIN CAPITAL LETTER S
103
+ 0x54 0x0054 #LATIN CAPITAL LETTER T
104
+ 0x55 0x0055 #LATIN CAPITAL LETTER U
105
+ 0x56 0x0056 #LATIN CAPITAL LETTER V
106
+ 0x57 0x0057 #LATIN CAPITAL LETTER W
107
+ 0x58 0x0058 #LATIN CAPITAL LETTER X
108
+ 0x59 0x0059 #LATIN CAPITAL LETTER Y
109
+ 0x5A 0x005A #LATIN CAPITAL LETTER Z
110
+ 0x5B 0x005B #LEFT SQUARE BRACKET
111
+ 0x5C 0x005C #REVERSE SOLIDUS
112
+ 0x5D 0x005D #RIGHT SQUARE BRACKET
113
+ 0x5E 0x005E #CIRCUMFLEX ACCENT
114
+ 0x5F 0x005F #LOW LINE
115
+ 0x60 0x0060 #GRAVE ACCENT
116
+ 0x61 0x0061 #LATIN SMALL LETTER A
117
+ 0x62 0x0062 #LATIN SMALL LETTER B
118
+ 0x63 0x0063 #LATIN SMALL LETTER C
119
+ 0x64 0x0064 #LATIN SMALL LETTER D
120
+ 0x65 0x0065 #LATIN SMALL LETTER E
121
+ 0x66 0x0066 #LATIN SMALL LETTER F
122
+ 0x67 0x0067 #LATIN SMALL LETTER G
123
+ 0x68 0x0068 #LATIN SMALL LETTER H
124
+ 0x69 0x0069 #LATIN SMALL LETTER I
125
+ 0x6A 0x006A #LATIN SMALL LETTER J
126
+ 0x6B 0x006B #LATIN SMALL LETTER K
127
+ 0x6C 0x006C #LATIN SMALL LETTER L
128
+ 0x6D 0x006D #LATIN SMALL LETTER M
129
+ 0x6E 0x006E #LATIN SMALL LETTER N
130
+ 0x6F 0x006F #LATIN SMALL LETTER O
131
+ 0x70 0x0070 #LATIN SMALL LETTER P
132
+ 0x71 0x0071 #LATIN SMALL LETTER Q
133
+ 0x72 0x0072 #LATIN SMALL LETTER R
134
+ 0x73 0x0073 #LATIN SMALL LETTER S
135
+ 0x74 0x0074 #LATIN SMALL LETTER T
136
+ 0x75 0x0075 #LATIN SMALL LETTER U
137
+ 0x76 0x0076 #LATIN SMALL LETTER V
138
+ 0x77 0x0077 #LATIN SMALL LETTER W
139
+ 0x78 0x0078 #LATIN SMALL LETTER X
140
+ 0x79 0x0079 #LATIN SMALL LETTER Y
141
+ 0x7A 0x007A #LATIN SMALL LETTER Z
142
+ 0x7B 0x007B #LEFT CURLY BRACKET
143
+ 0x7C 0x007C #VERTICAL LINE
144
+ 0x7D 0x007D #RIGHT CURLY BRACKET
145
+ 0x7E 0x007E #TILDE
146
+ 0x7F 0x007F #DELETE
147
+ 0x80 0x20AC #EURO SIGN
148
+ 0x81 #UNDEFINED
149
+ 0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
150
+ 0x83 #UNDEFINED
151
+ 0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
152
+ 0x85 0x2026 #HORIZONTAL ELLIPSIS
153
+ 0x86 0x2020 #DAGGER
154
+ 0x87 0x2021 #DOUBLE DAGGER
155
+ 0x88 #UNDEFINED
156
+ 0x89 0x2030 #PER MILLE SIGN
157
+ 0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
158
+ 0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
159
+ 0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
160
+ 0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON
161
+ 0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON
162
+ 0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
163
+ 0x90 #UNDEFINED
164
+ 0x91 0x2018 #LEFT SINGLE QUOTATION MARK
165
+ 0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
166
+ 0x93 0x201C #LEFT DOUBLE QUOTATION MARK
167
+ 0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
168
+ 0x95 0x2022 #BULLET
169
+ 0x96 0x2013 #EN DASH
170
+ 0x97 0x2014 #EM DASH
171
+ 0x98 #UNDEFINED
172
+ 0x99 0x2122 #TRADE MARK SIGN
173
+ 0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
174
+ 0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
175
+ 0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE
176
+ 0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON
177
+ 0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON
178
+ 0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE
179
+ 0xA0 0x00A0 #NO-BREAK SPACE
180
+ 0xA1 0x02C7 #CARON
181
+ 0xA2 0x02D8 #BREVE
182
+ 0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
183
+ 0xA4 0x00A4 #CURRENCY SIGN
184
+ 0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
185
+ 0xA6 0x00A6 #BROKEN BAR
186
+ 0xA7 0x00A7 #SECTION SIGN
187
+ 0xA8 0x00A8 #DIAERESIS
188
+ 0xA9 0x00A9 #COPYRIGHT SIGN
189
+ 0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
190
+ 0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
191
+ 0xAC 0x00AC #NOT SIGN
192
+ 0xAD 0x00AD #SOFT HYPHEN
193
+ 0xAE 0x00AE #REGISTERED SIGN
194
+ 0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
195
+ 0xB0 0x00B0 #DEGREE SIGN
196
+ 0xB1 0x00B1 #PLUS-MINUS SIGN
197
+ 0xB2 0x02DB #OGONEK
198
+ 0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE
199
+ 0xB4 0x00B4 #ACUTE ACCENT
200
+ 0xB5 0x00B5 #MICRO SIGN
201
+ 0xB6 0x00B6 #PILCROW SIGN
202
+ 0xB7 0x00B7 #MIDDLE DOT
203
+ 0xB8 0x00B8 #CEDILLA
204
+ 0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK
205
+ 0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA
206
+ 0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
207
+ 0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON
208
+ 0xBD 0x02DD #DOUBLE ACUTE ACCENT
209
+ 0xBE 0x013E #LATIN SMALL LETTER L WITH CARON
210
+ 0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
211
+ 0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
212
+ 0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
213
+ 0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
214
+ 0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
215
+ 0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
216
+ 0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
217
+ 0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
218
+ 0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
219
+ 0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
220
+ 0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
221
+ 0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
222
+ 0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
223
+ 0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON
224
+ 0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
225
+ 0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
226
+ 0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON
227
+ 0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
228
+ 0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
229
+ 0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON
230
+ 0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
231
+ 0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
232
+ 0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
233
+ 0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
234
+ 0xD7 0x00D7 #MULTIPLICATION SIGN
235
+ 0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON
236
+ 0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE
237
+ 0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
238
+ 0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
239
+ 0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
240
+ 0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
241
+ 0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
242
+ 0xDF 0x00DF #LATIN SMALL LETTER SHARP S
243
+ 0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE
244
+ 0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
245
+ 0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
246
+ 0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
247
+ 0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
248
+ 0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE
249
+ 0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE
250
+ 0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
251
+ 0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
252
+ 0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
253
+ 0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK
254
+ 0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
255
+ 0xEC 0x011B #LATIN SMALL LETTER E WITH CARON
256
+ 0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
257
+ 0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
258
+ 0xEF 0x010F #LATIN SMALL LETTER D WITH CARON
259
+ 0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
260
+ 0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
261
+ 0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON
262
+ 0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
263
+ 0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
264
+ 0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
265
+ 0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
266
+ 0xF7 0x00F7 #DIVISION SIGN
267
+ 0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON
268
+ 0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE
269
+ 0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
270
+ 0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
271
+ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
272
+ 0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
273
+ 0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
274
+ 0xFF 0x02D9 #DOT ABOVE