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 +1,297 @@
1
+ #
2
+ # Name: ISO/IEC 8859-11:2001 to Unicode
3
+ # Unicode version: 3.2
4
+ # Table version: 1.0
5
+ # Table format: Format A
6
+ # Date: 2002 October 7
7
+ # Authors: Ken Whistler <kenw@sybase.com>
8
+ #
9
+ # Copyright (c) 2002 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
+ # ISO/IEC 8859-11:2001 characters map into Unicode.
29
+ #
30
+ # ISO/IEC 8859-11:2001 is equivalent to TIS 620-2533 (1990) with
31
+ # the addition of 0xA0 NO-BREAK SPACE.
32
+ #
33
+ # Format: Three tab-separated columns
34
+ # Column #1 is the ISO/IEC 8859-11 code (in hex as 0xXX)
35
+ # Column #2 is the Unicode (in hex as 0xXXXX)
36
+ # Column #3 the Unicode name (follows a comment sign, '#')
37
+ #
38
+ # The entries are in ISO/IEC 8859-11 order.
39
+ #
40
+ # Version history:
41
+ # 2002 October 7 Created
42
+ #
43
+ # Updated versions of this file may be found in:
44
+ # <ftp://ftp.unicode.org/Public/MAPPINGS/>
45
+ #
46
+ # For any comments or problems, please use the Unicode
47
+ # web contact form at:
48
+ # http://www.unicode.org/unicode/reporting.html
49
+ #
50
+ 0x00 0x0000 # NULL
51
+ 0x01 0x0001 # START OF HEADING
52
+ 0x02 0x0002 # START OF TEXT
53
+ 0x03 0x0003 # END OF TEXT
54
+ 0x04 0x0004 # END OF TRANSMISSION
55
+ 0x05 0x0005 # ENQUIRY
56
+ 0x06 0x0006 # ACKNOWLEDGE
57
+ 0x07 0x0007 # BELL
58
+ 0x08 0x0008 # BACKSPACE
59
+ 0x09 0x0009 # HORIZONTAL TABULATION
60
+ 0x0A 0x000A # LINE FEED
61
+ 0x0B 0x000B # VERTICAL TABULATION
62
+ 0x0C 0x000C # FORM FEED
63
+ 0x0D 0x000D # CARRIAGE RETURN
64
+ 0x0E 0x000E # SHIFT OUT
65
+ 0x0F 0x000F # SHIFT IN
66
+ 0x10 0x0010 # DATA LINK ESCAPE
67
+ 0x11 0x0011 # DEVICE CONTROL ONE
68
+ 0x12 0x0012 # DEVICE CONTROL TWO
69
+ 0x13 0x0013 # DEVICE CONTROL THREE
70
+ 0x14 0x0014 # DEVICE CONTROL FOUR
71
+ 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
72
+ 0x16 0x0016 # SYNCHRONOUS IDLE
73
+ 0x17 0x0017 # END OF TRANSMISSION BLOCK
74
+ 0x18 0x0018 # CANCEL
75
+ 0x19 0x0019 # END OF MEDIUM
76
+ 0x1A 0x001A # SUBSTITUTE
77
+ 0x1B 0x001B # ESCAPE
78
+ 0x1C 0x001C # FILE SEPARATOR
79
+ 0x1D 0x001D # GROUP SEPARATOR
80
+ 0x1E 0x001E # RECORD SEPARATOR
81
+ 0x1F 0x001F # UNIT SEPARATOR
82
+ 0x20 0x0020 # SPACE
83
+ 0x21 0x0021 # EXCLAMATION MARK
84
+ 0x22 0x0022 # QUOTATION MARK
85
+ 0x23 0x0023 # NUMBER SIGN
86
+ 0x24 0x0024 # DOLLAR SIGN
87
+ 0x25 0x0025 # PERCENT SIGN
88
+ 0x26 0x0026 # AMPERSAND
89
+ 0x27 0x0027 # APOSTROPHE
90
+ 0x28 0x0028 # LEFT PARENTHESIS
91
+ 0x29 0x0029 # RIGHT PARENTHESIS
92
+ 0x2A 0x002A # ASTERISK
93
+ 0x2B 0x002B # PLUS SIGN
94
+ 0x2C 0x002C # COMMA
95
+ 0x2D 0x002D # HYPHEN-MINUS
96
+ 0x2E 0x002E # FULL STOP
97
+ 0x2F 0x002F # SOLIDUS
98
+ 0x30 0x0030 # DIGIT ZERO
99
+ 0x31 0x0031 # DIGIT ONE
100
+ 0x32 0x0032 # DIGIT TWO
101
+ 0x33 0x0033 # DIGIT THREE
102
+ 0x34 0x0034 # DIGIT FOUR
103
+ 0x35 0x0035 # DIGIT FIVE
104
+ 0x36 0x0036 # DIGIT SIX
105
+ 0x37 0x0037 # DIGIT SEVEN
106
+ 0x38 0x0038 # DIGIT EIGHT
107
+ 0x39 0x0039 # DIGIT NINE
108
+ 0x3A 0x003A # COLON
109
+ 0x3B 0x003B # SEMICOLON
110
+ 0x3C 0x003C # LESS-THAN SIGN
111
+ 0x3D 0x003D # EQUALS SIGN
112
+ 0x3E 0x003E # GREATER-THAN SIGN
113
+ 0x3F 0x003F # QUESTION MARK
114
+ 0x40 0x0040 # COMMERCIAL AT
115
+ 0x41 0x0041 # LATIN CAPITAL LETTER A
116
+ 0x42 0x0042 # LATIN CAPITAL LETTER B
117
+ 0x43 0x0043 # LATIN CAPITAL LETTER C
118
+ 0x44 0x0044 # LATIN CAPITAL LETTER D
119
+ 0x45 0x0045 # LATIN CAPITAL LETTER E
120
+ 0x46 0x0046 # LATIN CAPITAL LETTER F
121
+ 0x47 0x0047 # LATIN CAPITAL LETTER G
122
+ 0x48 0x0048 # LATIN CAPITAL LETTER H
123
+ 0x49 0x0049 # LATIN CAPITAL LETTER I
124
+ 0x4A 0x004A # LATIN CAPITAL LETTER J
125
+ 0x4B 0x004B # LATIN CAPITAL LETTER K
126
+ 0x4C 0x004C # LATIN CAPITAL LETTER L
127
+ 0x4D 0x004D # LATIN CAPITAL LETTER M
128
+ 0x4E 0x004E # LATIN CAPITAL LETTER N
129
+ 0x4F 0x004F # LATIN CAPITAL LETTER O
130
+ 0x50 0x0050 # LATIN CAPITAL LETTER P
131
+ 0x51 0x0051 # LATIN CAPITAL LETTER Q
132
+ 0x52 0x0052 # LATIN CAPITAL LETTER R
133
+ 0x53 0x0053 # LATIN CAPITAL LETTER S
134
+ 0x54 0x0054 # LATIN CAPITAL LETTER T
135
+ 0x55 0x0055 # LATIN CAPITAL LETTER U
136
+ 0x56 0x0056 # LATIN CAPITAL LETTER V
137
+ 0x57 0x0057 # LATIN CAPITAL LETTER W
138
+ 0x58 0x0058 # LATIN CAPITAL LETTER X
139
+ 0x59 0x0059 # LATIN CAPITAL LETTER Y
140
+ 0x5A 0x005A # LATIN CAPITAL LETTER Z
141
+ 0x5B 0x005B # LEFT SQUARE BRACKET
142
+ 0x5C 0x005C # REVERSE SOLIDUS
143
+ 0x5D 0x005D # RIGHT SQUARE BRACKET
144
+ 0x5E 0x005E # CIRCUMFLEX ACCENT
145
+ 0x5F 0x005F # LOW LINE
146
+ 0x60 0x0060 # GRAVE ACCENT
147
+ 0x61 0x0061 # LATIN SMALL LETTER A
148
+ 0x62 0x0062 # LATIN SMALL LETTER B
149
+ 0x63 0x0063 # LATIN SMALL LETTER C
150
+ 0x64 0x0064 # LATIN SMALL LETTER D
151
+ 0x65 0x0065 # LATIN SMALL LETTER E
152
+ 0x66 0x0066 # LATIN SMALL LETTER F
153
+ 0x67 0x0067 # LATIN SMALL LETTER G
154
+ 0x68 0x0068 # LATIN SMALL LETTER H
155
+ 0x69 0x0069 # LATIN SMALL LETTER I
156
+ 0x6A 0x006A # LATIN SMALL LETTER J
157
+ 0x6B 0x006B # LATIN SMALL LETTER K
158
+ 0x6C 0x006C # LATIN SMALL LETTER L
159
+ 0x6D 0x006D # LATIN SMALL LETTER M
160
+ 0x6E 0x006E # LATIN SMALL LETTER N
161
+ 0x6F 0x006F # LATIN SMALL LETTER O
162
+ 0x70 0x0070 # LATIN SMALL LETTER P
163
+ 0x71 0x0071 # LATIN SMALL LETTER Q
164
+ 0x72 0x0072 # LATIN SMALL LETTER R
165
+ 0x73 0x0073 # LATIN SMALL LETTER S
166
+ 0x74 0x0074 # LATIN SMALL LETTER T
167
+ 0x75 0x0075 # LATIN SMALL LETTER U
168
+ 0x76 0x0076 # LATIN SMALL LETTER V
169
+ 0x77 0x0077 # LATIN SMALL LETTER W
170
+ 0x78 0x0078 # LATIN SMALL LETTER X
171
+ 0x79 0x0079 # LATIN SMALL LETTER Y
172
+ 0x7A 0x007A # LATIN SMALL LETTER Z
173
+ 0x7B 0x007B # LEFT CURLY BRACKET
174
+ 0x7C 0x007C # VERTICAL LINE
175
+ 0x7D 0x007D # RIGHT CURLY BRACKET
176
+ 0x7E 0x007E # TILDE
177
+ 0x7F 0x007F # DELETE
178
+ 0x80 0x0080 # <control>
179
+ 0x81 0x0081 # <control>
180
+ 0x82 0x0082 # <control>
181
+ 0x83 0x0083 # <control>
182
+ 0x84 0x0084 # <control>
183
+ 0x85 0x0085 # <control>
184
+ 0x86 0x0086 # <control>
185
+ 0x87 0x0087 # <control>
186
+ 0x88 0x0088 # <control>
187
+ 0x89 0x0089 # <control>
188
+ 0x8A 0x008A # <control>
189
+ 0x8B 0x008B # <control>
190
+ 0x8C 0x008C # <control>
191
+ 0x8D 0x008D # <control>
192
+ 0x8E 0x008E # <control>
193
+ 0x8F 0x008F # <control>
194
+ 0x90 0x0090 # <control>
195
+ 0x91 0x0091 # <control>
196
+ 0x92 0x0092 # <control>
197
+ 0x93 0x0093 # <control>
198
+ 0x94 0x0094 # <control>
199
+ 0x95 0x0095 # <control>
200
+ 0x96 0x0096 # <control>
201
+ 0x97 0x0097 # <control>
202
+ 0x98 0x0098 # <control>
203
+ 0x99 0x0099 # <control>
204
+ 0x9A 0x009A # <control>
205
+ 0x9B 0x009B # <control>
206
+ 0x9C 0x009C # <control>
207
+ 0x9D 0x009D # <control>
208
+ 0x9E 0x009E # <control>
209
+ 0x9F 0x009F # <control>
210
+ 0xA0 0x00A0 # NO-BREAK SPACE
211
+ 0xA1 0x0E01 # THAI CHARACTER KO KAI
212
+ 0xA2 0x0E02 # THAI CHARACTER KHO KHAI
213
+ 0xA3 0x0E03 # THAI CHARACTER KHO KHUAT
214
+ 0xA4 0x0E04 # THAI CHARACTER KHO KHWAI
215
+ 0xA5 0x0E05 # THAI CHARACTER KHO KHON
216
+ 0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG
217
+ 0xA7 0x0E07 # THAI CHARACTER NGO NGU
218
+ 0xA8 0x0E08 # THAI CHARACTER CHO CHAN
219
+ 0xA9 0x0E09 # THAI CHARACTER CHO CHING
220
+ 0xAA 0x0E0A # THAI CHARACTER CHO CHANG
221
+ 0xAB 0x0E0B # THAI CHARACTER SO SO
222
+ 0xAC 0x0E0C # THAI CHARACTER CHO CHOE
223
+ 0xAD 0x0E0D # THAI CHARACTER YO YING
224
+ 0xAE 0x0E0E # THAI CHARACTER DO CHADA
225
+ 0xAF 0x0E0F # THAI CHARACTER TO PATAK
226
+ 0xB0 0x0E10 # THAI CHARACTER THO THAN
227
+ 0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO
228
+ 0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO
229
+ 0xB3 0x0E13 # THAI CHARACTER NO NEN
230
+ 0xB4 0x0E14 # THAI CHARACTER DO DEK
231
+ 0xB5 0x0E15 # THAI CHARACTER TO TAO
232
+ 0xB6 0x0E16 # THAI CHARACTER THO THUNG
233
+ 0xB7 0x0E17 # THAI CHARACTER THO THAHAN
234
+ 0xB8 0x0E18 # THAI CHARACTER THO THONG
235
+ 0xB9 0x0E19 # THAI CHARACTER NO NU
236
+ 0xBA 0x0E1A # THAI CHARACTER BO BAIMAI
237
+ 0xBB 0x0E1B # THAI CHARACTER PO PLA
238
+ 0xBC 0x0E1C # THAI CHARACTER PHO PHUNG
239
+ 0xBD 0x0E1D # THAI CHARACTER FO FA
240
+ 0xBE 0x0E1E # THAI CHARACTER PHO PHAN
241
+ 0xBF 0x0E1F # THAI CHARACTER FO FAN
242
+ 0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO
243
+ 0xC1 0x0E21 # THAI CHARACTER MO MA
244
+ 0xC2 0x0E22 # THAI CHARACTER YO YAK
245
+ 0xC3 0x0E23 # THAI CHARACTER RO RUA
246
+ 0xC4 0x0E24 # THAI CHARACTER RU
247
+ 0xC5 0x0E25 # THAI CHARACTER LO LING
248
+ 0xC6 0x0E26 # THAI CHARACTER LU
249
+ 0xC7 0x0E27 # THAI CHARACTER WO WAEN
250
+ 0xC8 0x0E28 # THAI CHARACTER SO SALA
251
+ 0xC9 0x0E29 # THAI CHARACTER SO RUSI
252
+ 0xCA 0x0E2A # THAI CHARACTER SO SUA
253
+ 0xCB 0x0E2B # THAI CHARACTER HO HIP
254
+ 0xCC 0x0E2C # THAI CHARACTER LO CHULA
255
+ 0xCD 0x0E2D # THAI CHARACTER O ANG
256
+ 0xCE 0x0E2E # THAI CHARACTER HO NOKHUK
257
+ 0xCF 0x0E2F # THAI CHARACTER PAIYANNOI
258
+ 0xD0 0x0E30 # THAI CHARACTER SARA A
259
+ 0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT
260
+ 0xD2 0x0E32 # THAI CHARACTER SARA AA
261
+ 0xD3 0x0E33 # THAI CHARACTER SARA AM
262
+ 0xD4 0x0E34 # THAI CHARACTER SARA I
263
+ 0xD5 0x0E35 # THAI CHARACTER SARA II
264
+ 0xD6 0x0E36 # THAI CHARACTER SARA UE
265
+ 0xD7 0x0E37 # THAI CHARACTER SARA UEE
266
+ 0xD8 0x0E38 # THAI CHARACTER SARA U
267
+ 0xD9 0x0E39 # THAI CHARACTER SARA UU
268
+ 0xDA 0x0E3A # THAI CHARACTER PHINTHU
269
+ 0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT
270
+ 0xE0 0x0E40 # THAI CHARACTER SARA E
271
+ 0xE1 0x0E41 # THAI CHARACTER SARA AE
272
+ 0xE2 0x0E42 # THAI CHARACTER SARA O
273
+ 0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN
274
+ 0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI
275
+ 0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO
276
+ 0xE6 0x0E46 # THAI CHARACTER MAIYAMOK
277
+ 0xE7 0x0E47 # THAI CHARACTER MAITAIKHU
278
+ 0xE8 0x0E48 # THAI CHARACTER MAI EK
279
+ 0xE9 0x0E49 # THAI CHARACTER MAI THO
280
+ 0xEA 0x0E4A # THAI CHARACTER MAI TRI
281
+ 0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA
282
+ 0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT
283
+ 0xED 0x0E4D # THAI CHARACTER NIKHAHIT
284
+ 0xEE 0x0E4E # THAI CHARACTER YAMAKKAN
285
+ 0xEF 0x0E4F # THAI CHARACTER FONGMAN
286
+ 0xF0 0x0E50 # THAI DIGIT ZERO
287
+ 0xF1 0x0E51 # THAI DIGIT ONE
288
+ 0xF2 0x0E52 # THAI DIGIT TWO
289
+ 0xF3 0x0E53 # THAI DIGIT THREE
290
+ 0xF4 0x0E54 # THAI DIGIT FOUR
291
+ 0xF5 0x0E55 # THAI DIGIT FIVE
292
+ 0xF6 0x0E56 # THAI DIGIT SIX
293
+ 0xF7 0x0E57 # THAI DIGIT SEVEN
294
+ 0xF8 0x0E58 # THAI DIGIT EIGHT
295
+ 0xF9 0x0E59 # THAI DIGIT NINE
296
+ 0xFA 0x0E5A # THAI CHARACTER ANGKHANKHU
297
+ 0xFB 0x0E5B # THAI CHARACTER KHOMUT
@@ -0,0 +1,299 @@
1
+ #
2
+ # Name: ISO/IEC 8859-13:1998 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
+ # ISO/IEC 8859-13:1998 characters map into Unicode.
29
+ #
30
+ # Format: Three tab-separated columns
31
+ # Column #1 is the ISO/IEC 8859-13 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 ISO/IEC 8859-13 order.
36
+ #
37
+ # Updated versions of this file may be found in:
38
+ # <ftp://ftp.unicode.org/Public/MAPPINGS/>
39
+ #
40
+ # Any comments or problems, contact <errata@unicode.org>
41
+ # Please note that <errata@unicode.org> is an archival address;
42
+ # notices will be checked, but do not expect an immediate response.
43
+ #
44
+ 0x00 0x0000 # NULL
45
+ 0x01 0x0001 # START OF HEADING
46
+ 0x02 0x0002 # START OF TEXT
47
+ 0x03 0x0003 # END OF TEXT
48
+ 0x04 0x0004 # END OF TRANSMISSION
49
+ 0x05 0x0005 # ENQUIRY
50
+ 0x06 0x0006 # ACKNOWLEDGE
51
+ 0x07 0x0007 # BELL
52
+ 0x08 0x0008 # BACKSPACE
53
+ 0x09 0x0009 # HORIZONTAL TABULATION
54
+ 0x0A 0x000A # LINE FEED
55
+ 0x0B 0x000B # VERTICAL TABULATION
56
+ 0x0C 0x000C # FORM FEED
57
+ 0x0D 0x000D # CARRIAGE RETURN
58
+ 0x0E 0x000E # SHIFT OUT
59
+ 0x0F 0x000F # SHIFT IN
60
+ 0x10 0x0010 # DATA LINK ESCAPE
61
+ 0x11 0x0011 # DEVICE CONTROL ONE
62
+ 0x12 0x0012 # DEVICE CONTROL TWO
63
+ 0x13 0x0013 # DEVICE CONTROL THREE
64
+ 0x14 0x0014 # DEVICE CONTROL FOUR
65
+ 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
66
+ 0x16 0x0016 # SYNCHRONOUS IDLE
67
+ 0x17 0x0017 # END OF TRANSMISSION BLOCK
68
+ 0x18 0x0018 # CANCEL
69
+ 0x19 0x0019 # END OF MEDIUM
70
+ 0x1A 0x001A # SUBSTITUTE
71
+ 0x1B 0x001B # ESCAPE
72
+ 0x1C 0x001C # FILE SEPARATOR
73
+ 0x1D 0x001D # GROUP SEPARATOR
74
+ 0x1E 0x001E # RECORD SEPARATOR
75
+ 0x1F 0x001F # UNIT SEPARATOR
76
+ 0x20 0x0020 # SPACE
77
+ 0x21 0x0021 # EXCLAMATION MARK
78
+ 0x22 0x0022 # QUOTATION MARK
79
+ 0x23 0x0023 # NUMBER SIGN
80
+ 0x24 0x0024 # DOLLAR SIGN
81
+ 0x25 0x0025 # PERCENT SIGN
82
+ 0x26 0x0026 # AMPERSAND
83
+ 0x27 0x0027 # APOSTROPHE
84
+ 0x28 0x0028 # LEFT PARENTHESIS
85
+ 0x29 0x0029 # RIGHT PARENTHESIS
86
+ 0x2A 0x002A # ASTERISK
87
+ 0x2B 0x002B # PLUS SIGN
88
+ 0x2C 0x002C # COMMA
89
+ 0x2D 0x002D # HYPHEN-MINUS
90
+ 0x2E 0x002E # FULL STOP
91
+ 0x2F 0x002F # SOLIDUS
92
+ 0x30 0x0030 # DIGIT ZERO
93
+ 0x31 0x0031 # DIGIT ONE
94
+ 0x32 0x0032 # DIGIT TWO
95
+ 0x33 0x0033 # DIGIT THREE
96
+ 0x34 0x0034 # DIGIT FOUR
97
+ 0x35 0x0035 # DIGIT FIVE
98
+ 0x36 0x0036 # DIGIT SIX
99
+ 0x37 0x0037 # DIGIT SEVEN
100
+ 0x38 0x0038 # DIGIT EIGHT
101
+ 0x39 0x0039 # DIGIT NINE
102
+ 0x3A 0x003A # COLON
103
+ 0x3B 0x003B # SEMICOLON
104
+ 0x3C 0x003C # LESS-THAN SIGN
105
+ 0x3D 0x003D # EQUALS SIGN
106
+ 0x3E 0x003E # GREATER-THAN SIGN
107
+ 0x3F 0x003F # QUESTION MARK
108
+ 0x40 0x0040 # COMMERCIAL AT
109
+ 0x41 0x0041 # LATIN CAPITAL LETTER A
110
+ 0x42 0x0042 # LATIN CAPITAL LETTER B
111
+ 0x43 0x0043 # LATIN CAPITAL LETTER C
112
+ 0x44 0x0044 # LATIN CAPITAL LETTER D
113
+ 0x45 0x0045 # LATIN CAPITAL LETTER E
114
+ 0x46 0x0046 # LATIN CAPITAL LETTER F
115
+ 0x47 0x0047 # LATIN CAPITAL LETTER G
116
+ 0x48 0x0048 # LATIN CAPITAL LETTER H
117
+ 0x49 0x0049 # LATIN CAPITAL LETTER I
118
+ 0x4A 0x004A # LATIN CAPITAL LETTER J
119
+ 0x4B 0x004B # LATIN CAPITAL LETTER K
120
+ 0x4C 0x004C # LATIN CAPITAL LETTER L
121
+ 0x4D 0x004D # LATIN CAPITAL LETTER M
122
+ 0x4E 0x004E # LATIN CAPITAL LETTER N
123
+ 0x4F 0x004F # LATIN CAPITAL LETTER O
124
+ 0x50 0x0050 # LATIN CAPITAL LETTER P
125
+ 0x51 0x0051 # LATIN CAPITAL LETTER Q
126
+ 0x52 0x0052 # LATIN CAPITAL LETTER R
127
+ 0x53 0x0053 # LATIN CAPITAL LETTER S
128
+ 0x54 0x0054 # LATIN CAPITAL LETTER T
129
+ 0x55 0x0055 # LATIN CAPITAL LETTER U
130
+ 0x56 0x0056 # LATIN CAPITAL LETTER V
131
+ 0x57 0x0057 # LATIN CAPITAL LETTER W
132
+ 0x58 0x0058 # LATIN CAPITAL LETTER X
133
+ 0x59 0x0059 # LATIN CAPITAL LETTER Y
134
+ 0x5A 0x005A # LATIN CAPITAL LETTER Z
135
+ 0x5B 0x005B # LEFT SQUARE BRACKET
136
+ 0x5C 0x005C # REVERSE SOLIDUS
137
+ 0x5D 0x005D # RIGHT SQUARE BRACKET
138
+ 0x5E 0x005E # CIRCUMFLEX ACCENT
139
+ 0x5F 0x005F # LOW LINE
140
+ 0x60 0x0060 # GRAVE ACCENT
141
+ 0x61 0x0061 # LATIN SMALL LETTER A
142
+ 0x62 0x0062 # LATIN SMALL LETTER B
143
+ 0x63 0x0063 # LATIN SMALL LETTER C
144
+ 0x64 0x0064 # LATIN SMALL LETTER D
145
+ 0x65 0x0065 # LATIN SMALL LETTER E
146
+ 0x66 0x0066 # LATIN SMALL LETTER F
147
+ 0x67 0x0067 # LATIN SMALL LETTER G
148
+ 0x68 0x0068 # LATIN SMALL LETTER H
149
+ 0x69 0x0069 # LATIN SMALL LETTER I
150
+ 0x6A 0x006A # LATIN SMALL LETTER J
151
+ 0x6B 0x006B # LATIN SMALL LETTER K
152
+ 0x6C 0x006C # LATIN SMALL LETTER L
153
+ 0x6D 0x006D # LATIN SMALL LETTER M
154
+ 0x6E 0x006E # LATIN SMALL LETTER N
155
+ 0x6F 0x006F # LATIN SMALL LETTER O
156
+ 0x70 0x0070 # LATIN SMALL LETTER P
157
+ 0x71 0x0071 # LATIN SMALL LETTER Q
158
+ 0x72 0x0072 # LATIN SMALL LETTER R
159
+ 0x73 0x0073 # LATIN SMALL LETTER S
160
+ 0x74 0x0074 # LATIN SMALL LETTER T
161
+ 0x75 0x0075 # LATIN SMALL LETTER U
162
+ 0x76 0x0076 # LATIN SMALL LETTER V
163
+ 0x77 0x0077 # LATIN SMALL LETTER W
164
+ 0x78 0x0078 # LATIN SMALL LETTER X
165
+ 0x79 0x0079 # LATIN SMALL LETTER Y
166
+ 0x7A 0x007A # LATIN SMALL LETTER Z
167
+ 0x7B 0x007B # LEFT CURLY BRACKET
168
+ 0x7C 0x007C # VERTICAL LINE
169
+ 0x7D 0x007D # RIGHT CURLY BRACKET
170
+ 0x7E 0x007E # TILDE
171
+ 0x7F 0x007F # DELETE
172
+ 0x80 0x0080 # <control>
173
+ 0x81 0x0081 # <control>
174
+ 0x82 0x0082 # <control>
175
+ 0x83 0x0083 # <control>
176
+ 0x84 0x0084 # <control>
177
+ 0x85 0x0085 # <control>
178
+ 0x86 0x0086 # <control>
179
+ 0x87 0x0087 # <control>
180
+ 0x88 0x0088 # <control>
181
+ 0x89 0x0089 # <control>
182
+ 0x8A 0x008A # <control>
183
+ 0x8B 0x008B # <control>
184
+ 0x8C 0x008C # <control>
185
+ 0x8D 0x008D # <control>
186
+ 0x8E 0x008E # <control>
187
+ 0x8F 0x008F # <control>
188
+ 0x90 0x0090 # <control>
189
+ 0x91 0x0091 # <control>
190
+ 0x92 0x0092 # <control>
191
+ 0x93 0x0093 # <control>
192
+ 0x94 0x0094 # <control>
193
+ 0x95 0x0095 # <control>
194
+ 0x96 0x0096 # <control>
195
+ 0x97 0x0097 # <control>
196
+ 0x98 0x0098 # <control>
197
+ 0x99 0x0099 # <control>
198
+ 0x9A 0x009A # <control>
199
+ 0x9B 0x009B # <control>
200
+ 0x9C 0x009C # <control>
201
+ 0x9D 0x009D # <control>
202
+ 0x9E 0x009E # <control>
203
+ 0x9F 0x009F # <control>
204
+ 0xA0 0x00A0 # NO-BREAK SPACE
205
+ 0xA1 0x201D # RIGHT DOUBLE QUOTATION MARK
206
+ 0xA2 0x00A2 # CENT SIGN
207
+ 0xA3 0x00A3 # POUND SIGN
208
+ 0xA4 0x00A4 # CURRENCY SIGN
209
+ 0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
210
+ 0xA6 0x00A6 # BROKEN BAR
211
+ 0xA7 0x00A7 # SECTION SIGN
212
+ 0xA8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
213
+ 0xA9 0x00A9 # COPYRIGHT SIGN
214
+ 0xAA 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
215
+ 0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
216
+ 0xAC 0x00AC # NOT SIGN
217
+ 0xAD 0x00AD # SOFT HYPHEN
218
+ 0xAE 0x00AE # REGISTERED SIGN
219
+ 0xAF 0x00C6 # LATIN CAPITAL LETTER AE
220
+ 0xB0 0x00B0 # DEGREE SIGN
221
+ 0xB1 0x00B1 # PLUS-MINUS SIGN
222
+ 0xB2 0x00B2 # SUPERSCRIPT TWO
223
+ 0xB3 0x00B3 # SUPERSCRIPT THREE
224
+ 0xB4 0x201C # LEFT DOUBLE QUOTATION MARK
225
+ 0xB5 0x00B5 # MICRO SIGN
226
+ 0xB6 0x00B6 # PILCROW SIGN
227
+ 0xB7 0x00B7 # MIDDLE DOT
228
+ 0xB8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
229
+ 0xB9 0x00B9 # SUPERSCRIPT ONE
230
+ 0xBA 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
231
+ 0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
232
+ 0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
233
+ 0xBD 0x00BD # VULGAR FRACTION ONE HALF
234
+ 0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
235
+ 0xBF 0x00E6 # LATIN SMALL LETTER AE
236
+ 0xC0 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
237
+ 0xC1 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
238
+ 0xC2 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
239
+ 0xC3 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
240
+ 0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
241
+ 0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
242
+ 0xC6 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
243
+ 0xC7 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
244
+ 0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
245
+ 0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
246
+ 0xCA 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
247
+ 0xCB 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
248
+ 0xCC 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
249
+ 0xCD 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
250
+ 0xCE 0x012A # LATIN CAPITAL LETTER I WITH MACRON
251
+ 0xCF 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
252
+ 0xD0 0x0160 # LATIN CAPITAL LETTER S WITH CARON
253
+ 0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
254
+ 0xD2 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
255
+ 0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
256
+ 0xD4 0x014C # LATIN CAPITAL LETTER O WITH MACRON
257
+ 0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
258
+ 0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
259
+ 0xD7 0x00D7 # MULTIPLICATION SIGN
260
+ 0xD8 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
261
+ 0xD9 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
262
+ 0xDA 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
263
+ 0xDB 0x016A # LATIN CAPITAL LETTER U WITH MACRON
264
+ 0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
265
+ 0xDD 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
266
+ 0xDE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
267
+ 0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
268
+ 0xE0 0x0105 # LATIN SMALL LETTER A WITH OGONEK
269
+ 0xE1 0x012F # LATIN SMALL LETTER I WITH OGONEK
270
+ 0xE2 0x0101 # LATIN SMALL LETTER A WITH MACRON
271
+ 0xE3 0x0107 # LATIN SMALL LETTER C WITH ACUTE
272
+ 0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
273
+ 0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
274
+ 0xE6 0x0119 # LATIN SMALL LETTER E WITH OGONEK
275
+ 0xE7 0x0113 # LATIN SMALL LETTER E WITH MACRON
276
+ 0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
277
+ 0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
278
+ 0xEA 0x017A # LATIN SMALL LETTER Z WITH ACUTE
279
+ 0xEB 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
280
+ 0xEC 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
281
+ 0xED 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
282
+ 0xEE 0x012B # LATIN SMALL LETTER I WITH MACRON
283
+ 0xEF 0x013C # LATIN SMALL LETTER L WITH CEDILLA
284
+ 0xF0 0x0161 # LATIN SMALL LETTER S WITH CARON
285
+ 0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
286
+ 0xF2 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
287
+ 0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
288
+ 0xF4 0x014D # LATIN SMALL LETTER O WITH MACRON
289
+ 0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
290
+ 0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
291
+ 0xF7 0x00F7 # DIVISION SIGN
292
+ 0xF8 0x0173 # LATIN SMALL LETTER U WITH OGONEK
293
+ 0xF9 0x0142 # LATIN SMALL LETTER L WITH STROKE
294
+ 0xFA 0x015B # LATIN SMALL LETTER S WITH ACUTE
295
+ 0xFB 0x016B # LATIN SMALL LETTER U WITH MACRON
296
+ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
297
+ 0xFD 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
298
+ 0xFE 0x017E # LATIN SMALL LETTER Z WITH CARON
299
+ 0xFF 0x2019 # RIGHT SINGLE QUOTATION MARK