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 +1,296 @@
1
+ #
2
+ # Name: ISO/IEC 8859-3:1999 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) 1991-1999 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 8859-3:1999 characters map into Unicode.
29
+ #
30
+ # Format: Three tab-separated columns
31
+ # Column #1 is the ISO/IEC 8859-3 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 8859-3 order.
36
+ #
37
+ # Version history
38
+ # 1.0 version updates 0.1 version by adding mappings for all
39
+ # control characters.
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 0x0004 # END OF TRANSMISSION
53
+ 0x05 0x0005 # ENQUIRY
54
+ 0x06 0x0006 # ACKNOWLEDGE
55
+ 0x07 0x0007 # BELL
56
+ 0x08 0x0008 # BACKSPACE
57
+ 0x09 0x0009 # HORIZONTAL TABULATION
58
+ 0x0A 0x000A # LINE FEED
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 0x0014 # DEVICE CONTROL FOUR
69
+ 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
70
+ 0x16 0x0016 # SYNCHRONOUS IDLE
71
+ 0x17 0x0017 # END OF TRANSMISSION BLOCK
72
+ 0x18 0x0018 # CANCEL
73
+ 0x19 0x0019 # END OF MEDIUM
74
+ 0x1A 0x001A # SUBSTITUTE
75
+ 0x1B 0x001B # ESCAPE
76
+ 0x1C 0x001C # FILE SEPARATOR
77
+ 0x1D 0x001D # GROUP SEPARATOR
78
+ 0x1E 0x001E # RECORD SEPARATOR
79
+ 0x1F 0x001F # UNIT SEPARATOR
80
+ 0x20 0x0020 # SPACE
81
+ 0x21 0x0021 # EXCLAMATION MARK
82
+ 0x22 0x0022 # QUOTATION MARK
83
+ 0x23 0x0023 # NUMBER SIGN
84
+ 0x24 0x0024 # DOLLAR SIGN
85
+ 0x25 0x0025 # PERCENT SIGN
86
+ 0x26 0x0026 # AMPERSAND
87
+ 0x27 0x0027 # APOSTROPHE
88
+ 0x28 0x0028 # LEFT PARENTHESIS
89
+ 0x29 0x0029 # RIGHT PARENTHESIS
90
+ 0x2A 0x002A # ASTERISK
91
+ 0x2B 0x002B # PLUS SIGN
92
+ 0x2C 0x002C # COMMA
93
+ 0x2D 0x002D # HYPHEN-MINUS
94
+ 0x2E 0x002E # FULL STOP
95
+ 0x2F 0x002F # SOLIDUS
96
+ 0x30 0x0030 # DIGIT ZERO
97
+ 0x31 0x0031 # DIGIT ONE
98
+ 0x32 0x0032 # DIGIT TWO
99
+ 0x33 0x0033 # DIGIT THREE
100
+ 0x34 0x0034 # DIGIT FOUR
101
+ 0x35 0x0035 # DIGIT FIVE
102
+ 0x36 0x0036 # DIGIT SIX
103
+ 0x37 0x0037 # DIGIT SEVEN
104
+ 0x38 0x0038 # DIGIT EIGHT
105
+ 0x39 0x0039 # DIGIT NINE
106
+ 0x3A 0x003A # COLON
107
+ 0x3B 0x003B # SEMICOLON
108
+ 0x3C 0x003C # LESS-THAN SIGN
109
+ 0x3D 0x003D # EQUALS SIGN
110
+ 0x3E 0x003E # GREATER-THAN SIGN
111
+ 0x3F 0x003F # QUESTION MARK
112
+ 0x40 0x0040 # COMMERCIAL AT
113
+ 0x41 0x0041 # LATIN CAPITAL LETTER A
114
+ 0x42 0x0042 # LATIN CAPITAL LETTER B
115
+ 0x43 0x0043 # LATIN CAPITAL LETTER C
116
+ 0x44 0x0044 # LATIN CAPITAL LETTER D
117
+ 0x45 0x0045 # LATIN CAPITAL LETTER E
118
+ 0x46 0x0046 # LATIN CAPITAL LETTER F
119
+ 0x47 0x0047 # LATIN CAPITAL LETTER G
120
+ 0x48 0x0048 # LATIN CAPITAL LETTER H
121
+ 0x49 0x0049 # LATIN CAPITAL LETTER I
122
+ 0x4A 0x004A # LATIN CAPITAL LETTER J
123
+ 0x4B 0x004B # LATIN CAPITAL LETTER K
124
+ 0x4C 0x004C # LATIN CAPITAL LETTER L
125
+ 0x4D 0x004D # LATIN CAPITAL LETTER M
126
+ 0x4E 0x004E # LATIN CAPITAL LETTER N
127
+ 0x4F 0x004F # LATIN CAPITAL LETTER O
128
+ 0x50 0x0050 # LATIN CAPITAL LETTER P
129
+ 0x51 0x0051 # LATIN CAPITAL LETTER Q
130
+ 0x52 0x0052 # LATIN CAPITAL LETTER R
131
+ 0x53 0x0053 # LATIN CAPITAL LETTER S
132
+ 0x54 0x0054 # LATIN CAPITAL LETTER T
133
+ 0x55 0x0055 # LATIN CAPITAL LETTER U
134
+ 0x56 0x0056 # LATIN CAPITAL LETTER V
135
+ 0x57 0x0057 # LATIN CAPITAL LETTER W
136
+ 0x58 0x0058 # LATIN CAPITAL LETTER X
137
+ 0x59 0x0059 # LATIN CAPITAL LETTER Y
138
+ 0x5A 0x005A # LATIN CAPITAL LETTER Z
139
+ 0x5B 0x005B # LEFT SQUARE BRACKET
140
+ 0x5C 0x005C # REVERSE SOLIDUS
141
+ 0x5D 0x005D # RIGHT SQUARE BRACKET
142
+ 0x5E 0x005E # CIRCUMFLEX ACCENT
143
+ 0x5F 0x005F # LOW LINE
144
+ 0x60 0x0060 # GRAVE ACCENT
145
+ 0x61 0x0061 # LATIN SMALL LETTER A
146
+ 0x62 0x0062 # LATIN SMALL LETTER B
147
+ 0x63 0x0063 # LATIN SMALL LETTER C
148
+ 0x64 0x0064 # LATIN SMALL LETTER D
149
+ 0x65 0x0065 # LATIN SMALL LETTER E
150
+ 0x66 0x0066 # LATIN SMALL LETTER F
151
+ 0x67 0x0067 # LATIN SMALL LETTER G
152
+ 0x68 0x0068 # LATIN SMALL LETTER H
153
+ 0x69 0x0069 # LATIN SMALL LETTER I
154
+ 0x6A 0x006A # LATIN SMALL LETTER J
155
+ 0x6B 0x006B # LATIN SMALL LETTER K
156
+ 0x6C 0x006C # LATIN SMALL LETTER L
157
+ 0x6D 0x006D # LATIN SMALL LETTER M
158
+ 0x6E 0x006E # LATIN SMALL LETTER N
159
+ 0x6F 0x006F # LATIN SMALL LETTER O
160
+ 0x70 0x0070 # LATIN SMALL LETTER P
161
+ 0x71 0x0071 # LATIN SMALL LETTER Q
162
+ 0x72 0x0072 # LATIN SMALL LETTER R
163
+ 0x73 0x0073 # LATIN SMALL LETTER S
164
+ 0x74 0x0074 # LATIN SMALL LETTER T
165
+ 0x75 0x0075 # LATIN SMALL LETTER U
166
+ 0x76 0x0076 # LATIN SMALL LETTER V
167
+ 0x77 0x0077 # LATIN SMALL LETTER W
168
+ 0x78 0x0078 # LATIN SMALL LETTER X
169
+ 0x79 0x0079 # LATIN SMALL LETTER Y
170
+ 0x7A 0x007A # LATIN SMALL LETTER Z
171
+ 0x7B 0x007B # LEFT CURLY BRACKET
172
+ 0x7C 0x007C # VERTICAL LINE
173
+ 0x7D 0x007D # RIGHT CURLY BRACKET
174
+ 0x7E 0x007E # TILDE
175
+ 0x7F 0x007F # DELETE
176
+ 0x80 0x0080 # <control>
177
+ 0x81 0x0081 # <control>
178
+ 0x82 0x0082 # <control>
179
+ 0x83 0x0083 # <control>
180
+ 0x84 0x0084 # <control>
181
+ 0x85 0x0085 # <control>
182
+ 0x86 0x0086 # <control>
183
+ 0x87 0x0087 # <control>
184
+ 0x88 0x0088 # <control>
185
+ 0x89 0x0089 # <control>
186
+ 0x8A 0x008A # <control>
187
+ 0x8B 0x008B # <control>
188
+ 0x8C 0x008C # <control>
189
+ 0x8D 0x008D # <control>
190
+ 0x8E 0x008E # <control>
191
+ 0x8F 0x008F # <control>
192
+ 0x90 0x0090 # <control>
193
+ 0x91 0x0091 # <control>
194
+ 0x92 0x0092 # <control>
195
+ 0x93 0x0093 # <control>
196
+ 0x94 0x0094 # <control>
197
+ 0x95 0x0095 # <control>
198
+ 0x96 0x0096 # <control>
199
+ 0x97 0x0097 # <control>
200
+ 0x98 0x0098 # <control>
201
+ 0x99 0x0099 # <control>
202
+ 0x9A 0x009A # <control>
203
+ 0x9B 0x009B # <control>
204
+ 0x9C 0x009C # <control>
205
+ 0x9D 0x009D # <control>
206
+ 0x9E 0x009E # <control>
207
+ 0x9F 0x009F # <control>
208
+ 0xA0 0x00A0 # NO-BREAK SPACE
209
+ 0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE
210
+ 0xA2 0x02D8 # BREVE
211
+ 0xA3 0x00A3 # POUND SIGN
212
+ 0xA4 0x00A4 # CURRENCY SIGN
213
+ 0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
214
+ 0xA7 0x00A7 # SECTION SIGN
215
+ 0xA8 0x00A8 # DIAERESIS
216
+ 0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
217
+ 0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
218
+ 0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE
219
+ 0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
220
+ 0xAD 0x00AD # SOFT HYPHEN
221
+ 0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
222
+ 0xB0 0x00B0 # DEGREE SIGN
223
+ 0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE
224
+ 0xB2 0x00B2 # SUPERSCRIPT TWO
225
+ 0xB3 0x00B3 # SUPERSCRIPT THREE
226
+ 0xB4 0x00B4 # ACUTE ACCENT
227
+ 0xB5 0x00B5 # MICRO SIGN
228
+ 0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX
229
+ 0xB7 0x00B7 # MIDDLE DOT
230
+ 0xB8 0x00B8 # CEDILLA
231
+ 0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I
232
+ 0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
233
+ 0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE
234
+ 0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX
235
+ 0xBD 0x00BD # VULGAR FRACTION ONE HALF
236
+ 0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
237
+ 0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
238
+ 0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
239
+ 0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
240
+ 0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
241
+ 0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
242
+ 0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
243
+ 0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
244
+ 0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
245
+ 0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
246
+ 0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
247
+ 0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
248
+ 0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
249
+ 0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
250
+ 0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
251
+ 0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
252
+ 0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
253
+ 0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
254
+ 0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
255
+ 0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
256
+ 0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
257
+ 0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
258
+ 0xD7 0x00D7 # MULTIPLICATION SIGN
259
+ 0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
260
+ 0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
261
+ 0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
262
+ 0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
263
+ 0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
264
+ 0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE
265
+ 0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
266
+ 0xDF 0x00DF # LATIN SMALL LETTER SHARP S
267
+ 0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
268
+ 0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
269
+ 0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
270
+ 0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
271
+ 0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
272
+ 0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX
273
+ 0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
274
+ 0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
275
+ 0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
276
+ 0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
277
+ 0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
278
+ 0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
279
+ 0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
280
+ 0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
281
+ 0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
282
+ 0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
283
+ 0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
284
+ 0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
285
+ 0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
286
+ 0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
287
+ 0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
288
+ 0xF7 0x00F7 # DIVISION SIGN
289
+ 0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX
290
+ 0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
291
+ 0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
292
+ 0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
293
+ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
294
+ 0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE
295
+ 0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX
296
+ 0xFF 0x02D9 # DOT ABOVE
@@ -0,0 +1,303 @@
1
+ #
2
+ # Name: ISO/IEC 8859-4:1998 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) 1991-1999 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 8859-4:1998 characters map into Unicode.
29
+ #
30
+ # Format: Three tab-separated columns
31
+ # Column #1 is the ISO/IEC 8859-4 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 8859-4 order.
36
+ #
37
+ # Version history
38
+ # 1.0 version updates 0.1 version by adding mappings for all
39
+ # control characters.
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 0x0004 # END OF TRANSMISSION
53
+ 0x05 0x0005 # ENQUIRY
54
+ 0x06 0x0006 # ACKNOWLEDGE
55
+ 0x07 0x0007 # BELL
56
+ 0x08 0x0008 # BACKSPACE
57
+ 0x09 0x0009 # HORIZONTAL TABULATION
58
+ 0x0A 0x000A # LINE FEED
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 0x0014 # DEVICE CONTROL FOUR
69
+ 0x15 0x0015 # NEGATIVE ACKNOWLEDGE
70
+ 0x16 0x0016 # SYNCHRONOUS IDLE
71
+ 0x17 0x0017 # END OF TRANSMISSION BLOCK
72
+ 0x18 0x0018 # CANCEL
73
+ 0x19 0x0019 # END OF MEDIUM
74
+ 0x1A 0x001A # SUBSTITUTE
75
+ 0x1B 0x001B # ESCAPE
76
+ 0x1C 0x001C # FILE SEPARATOR
77
+ 0x1D 0x001D # GROUP SEPARATOR
78
+ 0x1E 0x001E # RECORD SEPARATOR
79
+ 0x1F 0x001F # UNIT SEPARATOR
80
+ 0x20 0x0020 # SPACE
81
+ 0x21 0x0021 # EXCLAMATION MARK
82
+ 0x22 0x0022 # QUOTATION MARK
83
+ 0x23 0x0023 # NUMBER SIGN
84
+ 0x24 0x0024 # DOLLAR SIGN
85
+ 0x25 0x0025 # PERCENT SIGN
86
+ 0x26 0x0026 # AMPERSAND
87
+ 0x27 0x0027 # APOSTROPHE
88
+ 0x28 0x0028 # LEFT PARENTHESIS
89
+ 0x29 0x0029 # RIGHT PARENTHESIS
90
+ 0x2A 0x002A # ASTERISK
91
+ 0x2B 0x002B # PLUS SIGN
92
+ 0x2C 0x002C # COMMA
93
+ 0x2D 0x002D # HYPHEN-MINUS
94
+ 0x2E 0x002E # FULL STOP
95
+ 0x2F 0x002F # SOLIDUS
96
+ 0x30 0x0030 # DIGIT ZERO
97
+ 0x31 0x0031 # DIGIT ONE
98
+ 0x32 0x0032 # DIGIT TWO
99
+ 0x33 0x0033 # DIGIT THREE
100
+ 0x34 0x0034 # DIGIT FOUR
101
+ 0x35 0x0035 # DIGIT FIVE
102
+ 0x36 0x0036 # DIGIT SIX
103
+ 0x37 0x0037 # DIGIT SEVEN
104
+ 0x38 0x0038 # DIGIT EIGHT
105
+ 0x39 0x0039 # DIGIT NINE
106
+ 0x3A 0x003A # COLON
107
+ 0x3B 0x003B # SEMICOLON
108
+ 0x3C 0x003C # LESS-THAN SIGN
109
+ 0x3D 0x003D # EQUALS SIGN
110
+ 0x3E 0x003E # GREATER-THAN SIGN
111
+ 0x3F 0x003F # QUESTION MARK
112
+ 0x40 0x0040 # COMMERCIAL AT
113
+ 0x41 0x0041 # LATIN CAPITAL LETTER A
114
+ 0x42 0x0042 # LATIN CAPITAL LETTER B
115
+ 0x43 0x0043 # LATIN CAPITAL LETTER C
116
+ 0x44 0x0044 # LATIN CAPITAL LETTER D
117
+ 0x45 0x0045 # LATIN CAPITAL LETTER E
118
+ 0x46 0x0046 # LATIN CAPITAL LETTER F
119
+ 0x47 0x0047 # LATIN CAPITAL LETTER G
120
+ 0x48 0x0048 # LATIN CAPITAL LETTER H
121
+ 0x49 0x0049 # LATIN CAPITAL LETTER I
122
+ 0x4A 0x004A # LATIN CAPITAL LETTER J
123
+ 0x4B 0x004B # LATIN CAPITAL LETTER K
124
+ 0x4C 0x004C # LATIN CAPITAL LETTER L
125
+ 0x4D 0x004D # LATIN CAPITAL LETTER M
126
+ 0x4E 0x004E # LATIN CAPITAL LETTER N
127
+ 0x4F 0x004F # LATIN CAPITAL LETTER O
128
+ 0x50 0x0050 # LATIN CAPITAL LETTER P
129
+ 0x51 0x0051 # LATIN CAPITAL LETTER Q
130
+ 0x52 0x0052 # LATIN CAPITAL LETTER R
131
+ 0x53 0x0053 # LATIN CAPITAL LETTER S
132
+ 0x54 0x0054 # LATIN CAPITAL LETTER T
133
+ 0x55 0x0055 # LATIN CAPITAL LETTER U
134
+ 0x56 0x0056 # LATIN CAPITAL LETTER V
135
+ 0x57 0x0057 # LATIN CAPITAL LETTER W
136
+ 0x58 0x0058 # LATIN CAPITAL LETTER X
137
+ 0x59 0x0059 # LATIN CAPITAL LETTER Y
138
+ 0x5A 0x005A # LATIN CAPITAL LETTER Z
139
+ 0x5B 0x005B # LEFT SQUARE BRACKET
140
+ 0x5C 0x005C # REVERSE SOLIDUS
141
+ 0x5D 0x005D # RIGHT SQUARE BRACKET
142
+ 0x5E 0x005E # CIRCUMFLEX ACCENT
143
+ 0x5F 0x005F # LOW LINE
144
+ 0x60 0x0060 # GRAVE ACCENT
145
+ 0x61 0x0061 # LATIN SMALL LETTER A
146
+ 0x62 0x0062 # LATIN SMALL LETTER B
147
+ 0x63 0x0063 # LATIN SMALL LETTER C
148
+ 0x64 0x0064 # LATIN SMALL LETTER D
149
+ 0x65 0x0065 # LATIN SMALL LETTER E
150
+ 0x66 0x0066 # LATIN SMALL LETTER F
151
+ 0x67 0x0067 # LATIN SMALL LETTER G
152
+ 0x68 0x0068 # LATIN SMALL LETTER H
153
+ 0x69 0x0069 # LATIN SMALL LETTER I
154
+ 0x6A 0x006A # LATIN SMALL LETTER J
155
+ 0x6B 0x006B # LATIN SMALL LETTER K
156
+ 0x6C 0x006C # LATIN SMALL LETTER L
157
+ 0x6D 0x006D # LATIN SMALL LETTER M
158
+ 0x6E 0x006E # LATIN SMALL LETTER N
159
+ 0x6F 0x006F # LATIN SMALL LETTER O
160
+ 0x70 0x0070 # LATIN SMALL LETTER P
161
+ 0x71 0x0071 # LATIN SMALL LETTER Q
162
+ 0x72 0x0072 # LATIN SMALL LETTER R
163
+ 0x73 0x0073 # LATIN SMALL LETTER S
164
+ 0x74 0x0074 # LATIN SMALL LETTER T
165
+ 0x75 0x0075 # LATIN SMALL LETTER U
166
+ 0x76 0x0076 # LATIN SMALL LETTER V
167
+ 0x77 0x0077 # LATIN SMALL LETTER W
168
+ 0x78 0x0078 # LATIN SMALL LETTER X
169
+ 0x79 0x0079 # LATIN SMALL LETTER Y
170
+ 0x7A 0x007A # LATIN SMALL LETTER Z
171
+ 0x7B 0x007B # LEFT CURLY BRACKET
172
+ 0x7C 0x007C # VERTICAL LINE
173
+ 0x7D 0x007D # RIGHT CURLY BRACKET
174
+ 0x7E 0x007E # TILDE
175
+ 0x7F 0x007F # DELETE
176
+ 0x80 0x0080 # <control>
177
+ 0x81 0x0081 # <control>
178
+ 0x82 0x0082 # <control>
179
+ 0x83 0x0083 # <control>
180
+ 0x84 0x0084 # <control>
181
+ 0x85 0x0085 # <control>
182
+ 0x86 0x0086 # <control>
183
+ 0x87 0x0087 # <control>
184
+ 0x88 0x0088 # <control>
185
+ 0x89 0x0089 # <control>
186
+ 0x8A 0x008A # <control>
187
+ 0x8B 0x008B # <control>
188
+ 0x8C 0x008C # <control>
189
+ 0x8D 0x008D # <control>
190
+ 0x8E 0x008E # <control>
191
+ 0x8F 0x008F # <control>
192
+ 0x90 0x0090 # <control>
193
+ 0x91 0x0091 # <control>
194
+ 0x92 0x0092 # <control>
195
+ 0x93 0x0093 # <control>
196
+ 0x94 0x0094 # <control>
197
+ 0x95 0x0095 # <control>
198
+ 0x96 0x0096 # <control>
199
+ 0x97 0x0097 # <control>
200
+ 0x98 0x0098 # <control>
201
+ 0x99 0x0099 # <control>
202
+ 0x9A 0x009A # <control>
203
+ 0x9B 0x009B # <control>
204
+ 0x9C 0x009C # <control>
205
+ 0x9D 0x009D # <control>
206
+ 0x9E 0x009E # <control>
207
+ 0x9F 0x009F # <control>
208
+ 0xA0 0x00A0 # NO-BREAK SPACE
209
+ 0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
210
+ 0xA2 0x0138 # LATIN SMALL LETTER KRA
211
+ 0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
212
+ 0xA4 0x00A4 # CURRENCY SIGN
213
+ 0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
214
+ 0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
215
+ 0xA7 0x00A7 # SECTION SIGN
216
+ 0xA8 0x00A8 # DIAERESIS
217
+ 0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
218
+ 0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
219
+ 0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
220
+ 0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
221
+ 0xAD 0x00AD # SOFT HYPHEN
222
+ 0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
223
+ 0xAF 0x00AF # MACRON
224
+ 0xB0 0x00B0 # DEGREE SIGN
225
+ 0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
226
+ 0xB2 0x02DB # OGONEK
227
+ 0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
228
+ 0xB4 0x00B4 # ACUTE ACCENT
229
+ 0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
230
+ 0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA
231
+ 0xB7 0x02C7 # CARON
232
+ 0xB8 0x00B8 # CEDILLA
233
+ 0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
234
+ 0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON
235
+ 0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
236
+ 0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE
237
+ 0xBD 0x014A # LATIN CAPITAL LETTER ENG
238
+ 0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
239
+ 0xBF 0x014B # LATIN SMALL LETTER ENG
240
+ 0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
241
+ 0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
242
+ 0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
243
+ 0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
244
+ 0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
245
+ 0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
246
+ 0xC6 0x00C6 # LATIN CAPITAL LETTER AE
247
+ 0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
248
+ 0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
249
+ 0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
250
+ 0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
251
+ 0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
252
+ 0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
253
+ 0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
254
+ 0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
255
+ 0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON
256
+ 0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
257
+ 0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
258
+ 0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
259
+ 0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
260
+ 0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
261
+ 0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
262
+ 0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
263
+ 0xD7 0x00D7 # MULTIPLICATION SIGN
264
+ 0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
265
+ 0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
266
+ 0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
267
+ 0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
268
+ 0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
269
+ 0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
270
+ 0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
271
+ 0xDF 0x00DF # LATIN SMALL LETTER SHARP S
272
+ 0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
273
+ 0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
274
+ 0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
275
+ 0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
276
+ 0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
277
+ 0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
278
+ 0xE6 0x00E6 # LATIN SMALL LETTER AE
279
+ 0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK
280
+ 0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
281
+ 0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
282
+ 0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
283
+ 0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
284
+ 0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
285
+ 0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
286
+ 0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
287
+ 0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON
288
+ 0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
289
+ 0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
290
+ 0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
291
+ 0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
292
+ 0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
293
+ 0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
294
+ 0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
295
+ 0xF7 0x00F7 # DIVISION SIGN
296
+ 0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
297
+ 0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK
298
+ 0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
299
+ 0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
300
+ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
301
+ 0xFD 0x0169 # LATIN SMALL LETTER U WITH TILDE
302
+ 0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON
303
+ 0xFF 0x02D9 # DOT ABOVE