unidecode 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 (185) hide show
  1. data/README +56 -0
  2. data/lib/data/x00.yml +257 -0
  3. data/lib/data/x01.yml +257 -0
  4. data/lib/data/x02.yml +256 -0
  5. data/lib/data/x03.yml +256 -0
  6. data/lib/data/x04.yml +256 -0
  7. data/lib/data/x05.yml +256 -0
  8. data/lib/data/x06.yml +256 -0
  9. data/lib/data/x07.yml +256 -0
  10. data/lib/data/x09.yml +256 -0
  11. data/lib/data/x0a.yml +256 -0
  12. data/lib/data/x0b.yml +256 -0
  13. data/lib/data/x0c.yml +256 -0
  14. data/lib/data/x0d.yml +256 -0
  15. data/lib/data/x0e.yml +256 -0
  16. data/lib/data/x0f.yml +256 -0
  17. data/lib/data/x10.yml +256 -0
  18. data/lib/data/x11.yml +256 -0
  19. data/lib/data/x12.yml +257 -0
  20. data/lib/data/x13.yml +256 -0
  21. data/lib/data/x14.yml +257 -0
  22. data/lib/data/x15.yml +257 -0
  23. data/lib/data/x16.yml +256 -0
  24. data/lib/data/x17.yml +256 -0
  25. data/lib/data/x18.yml +256 -0
  26. data/lib/data/x1e.yml +256 -0
  27. data/lib/data/x1f.yml +256 -0
  28. data/lib/data/x20.yml +256 -0
  29. data/lib/data/x21.yml +256 -0
  30. data/lib/data/x22.yml +256 -0
  31. data/lib/data/x23.yml +256 -0
  32. data/lib/data/x24.yml +256 -0
  33. data/lib/data/x25.yml +256 -0
  34. data/lib/data/x26.yml +256 -0
  35. data/lib/data/x27.yml +256 -0
  36. data/lib/data/x28.yml +257 -0
  37. data/lib/data/x2e.yml +256 -0
  38. data/lib/data/x2f.yml +256 -0
  39. data/lib/data/x30.yml +256 -0
  40. data/lib/data/x31.yml +256 -0
  41. data/lib/data/x32.yml +256 -0
  42. data/lib/data/x33.yml +256 -0
  43. data/lib/data/x4d.yml +256 -0
  44. data/lib/data/x4e.yml +257 -0
  45. data/lib/data/x4f.yml +257 -0
  46. data/lib/data/x50.yml +257 -0
  47. data/lib/data/x51.yml +257 -0
  48. data/lib/data/x52.yml +257 -0
  49. data/lib/data/x53.yml +257 -0
  50. data/lib/data/x54.yml +257 -0
  51. data/lib/data/x55.yml +257 -0
  52. data/lib/data/x56.yml +257 -0
  53. data/lib/data/x57.yml +257 -0
  54. data/lib/data/x58.yml +257 -0
  55. data/lib/data/x59.yml +257 -0
  56. data/lib/data/x5a.yml +257 -0
  57. data/lib/data/x5b.yml +257 -0
  58. data/lib/data/x5c.yml +257 -0
  59. data/lib/data/x5d.yml +257 -0
  60. data/lib/data/x5e.yml +257 -0
  61. data/lib/data/x5f.yml +257 -0
  62. data/lib/data/x60.yml +257 -0
  63. data/lib/data/x61.yml +257 -0
  64. data/lib/data/x62.yml +257 -0
  65. data/lib/data/x63.yml +257 -0
  66. data/lib/data/x64.yml +257 -0
  67. data/lib/data/x65.yml +257 -0
  68. data/lib/data/x66.yml +257 -0
  69. data/lib/data/x67.yml +257 -0
  70. data/lib/data/x68.yml +257 -0
  71. data/lib/data/x69.yml +257 -0
  72. data/lib/data/x6a.yml +257 -0
  73. data/lib/data/x6b.yml +257 -0
  74. data/lib/data/x6c.yml +257 -0
  75. data/lib/data/x6d.yml +257 -0
  76. data/lib/data/x6e.yml +257 -0
  77. data/lib/data/x6f.yml +257 -0
  78. data/lib/data/x70.yml +257 -0
  79. data/lib/data/x71.yml +257 -0
  80. data/lib/data/x72.yml +257 -0
  81. data/lib/data/x73.yml +257 -0
  82. data/lib/data/x74.yml +257 -0
  83. data/lib/data/x75.yml +257 -0
  84. data/lib/data/x76.yml +257 -0
  85. data/lib/data/x77.yml +257 -0
  86. data/lib/data/x78.yml +257 -0
  87. data/lib/data/x79.yml +257 -0
  88. data/lib/data/x7a.yml +257 -0
  89. data/lib/data/x7b.yml +257 -0
  90. data/lib/data/x7c.yml +257 -0
  91. data/lib/data/x7d.yml +257 -0
  92. data/lib/data/x7e.yml +257 -0
  93. data/lib/data/x7f.yml +257 -0
  94. data/lib/data/x80.yml +257 -0
  95. data/lib/data/x81.yml +257 -0
  96. data/lib/data/x82.yml +257 -0
  97. data/lib/data/x83.yml +257 -0
  98. data/lib/data/x84.yml +257 -0
  99. data/lib/data/x85.yml +257 -0
  100. data/lib/data/x86.yml +257 -0
  101. data/lib/data/x87.yml +257 -0
  102. data/lib/data/x88.yml +257 -0
  103. data/lib/data/x89.yml +257 -0
  104. data/lib/data/x8a.yml +257 -0
  105. data/lib/data/x8b.yml +257 -0
  106. data/lib/data/x8c.yml +257 -0
  107. data/lib/data/x8d.yml +257 -0
  108. data/lib/data/x8e.yml +257 -0
  109. data/lib/data/x8f.yml +257 -0
  110. data/lib/data/x90.yml +257 -0
  111. data/lib/data/x91.yml +257 -0
  112. data/lib/data/x92.yml +257 -0
  113. data/lib/data/x93.yml +257 -0
  114. data/lib/data/x94.yml +257 -0
  115. data/lib/data/x95.yml +257 -0
  116. data/lib/data/x96.yml +257 -0
  117. data/lib/data/x97.yml +257 -0
  118. data/lib/data/x98.yml +257 -0
  119. data/lib/data/x99.yml +257 -0
  120. data/lib/data/x9a.yml +257 -0
  121. data/lib/data/x9b.yml +257 -0
  122. data/lib/data/x9c.yml +257 -0
  123. data/lib/data/x9d.yml +257 -0
  124. data/lib/data/x9e.yml +257 -0
  125. data/lib/data/x9f.yml +256 -0
  126. data/lib/data/xa0.yml +257 -0
  127. data/lib/data/xa1.yml +257 -0
  128. data/lib/data/xa2.yml +257 -0
  129. data/lib/data/xa3.yml +257 -0
  130. data/lib/data/xa4.yml +256 -0
  131. data/lib/data/xac.yml +257 -0
  132. data/lib/data/xad.yml +257 -0
  133. data/lib/data/xae.yml +257 -0
  134. data/lib/data/xaf.yml +257 -0
  135. data/lib/data/xb0.yml +257 -0
  136. data/lib/data/xb1.yml +257 -0
  137. data/lib/data/xb2.yml +257 -0
  138. data/lib/data/xb3.yml +257 -0
  139. data/lib/data/xb4.yml +257 -0
  140. data/lib/data/xb5.yml +257 -0
  141. data/lib/data/xb6.yml +257 -0
  142. data/lib/data/xb7.yml +257 -0
  143. data/lib/data/xb8.yml +257 -0
  144. data/lib/data/xb9.yml +257 -0
  145. data/lib/data/xba.yml +257 -0
  146. data/lib/data/xbb.yml +257 -0
  147. data/lib/data/xbc.yml +257 -0
  148. data/lib/data/xbd.yml +257 -0
  149. data/lib/data/xbe.yml +257 -0
  150. data/lib/data/xbf.yml +257 -0
  151. data/lib/data/xc0.yml +257 -0
  152. data/lib/data/xc1.yml +257 -0
  153. data/lib/data/xc2.yml +257 -0
  154. data/lib/data/xc3.yml +257 -0
  155. data/lib/data/xc4.yml +257 -0
  156. data/lib/data/xc5.yml +257 -0
  157. data/lib/data/xc6.yml +257 -0
  158. data/lib/data/xc7.yml +257 -0
  159. data/lib/data/xc8.yml +257 -0
  160. data/lib/data/xc9.yml +257 -0
  161. data/lib/data/xca.yml +257 -0
  162. data/lib/data/xcb.yml +257 -0
  163. data/lib/data/xcc.yml +257 -0
  164. data/lib/data/xcd.yml +257 -0
  165. data/lib/data/xce.yml +257 -0
  166. data/lib/data/xcf.yml +257 -0
  167. data/lib/data/xd0.yml +257 -0
  168. data/lib/data/xd1.yml +257 -0
  169. data/lib/data/xd2.yml +257 -0
  170. data/lib/data/xd3.yml +257 -0
  171. data/lib/data/xd4.yml +257 -0
  172. data/lib/data/xd5.yml +257 -0
  173. data/lib/data/xd6.yml +257 -0
  174. data/lib/data/xd7.yml +256 -0
  175. data/lib/data/xf9.yml +257 -0
  176. data/lib/data/xfa.yml +256 -0
  177. data/lib/data/xfb.yml +257 -0
  178. data/lib/data/xfc.yml +257 -0
  179. data/lib/data/xfd.yml +256 -0
  180. data/lib/data/xfe.yml +257 -0
  181. data/lib/data/xff.yml +257 -0
  182. data/lib/unidecode.rb +45 -0
  183. data/lib/unidecode/version.rb +9 -0
  184. data/test/unidecode_test.rb +69 -0
  185. metadata +236 -0
data/README ADDED
@@ -0,0 +1,56 @@
1
+ = unidecode
2
+
3
+ A library for transliteratively converting UTF-8 text to US-ASCII.
4
+
5
+ = Usage
6
+
7
+ require "rubygems"
8
+ require "unidecode"
9
+
10
+ puts "Михаил Горбачёв".to_ascii # => "Mikhail Gorbachiov"
11
+
12
+ = Requirements
13
+
14
+ Just regular, ol' Ruby with the standard YAML library.
15
+
16
+ = Note
17
+
18
+ This code is a Ruby port of Sean M. Burke's Perl library Text::Unidecode,
19
+ http://search.cpan.org/~sburke/Text-Unidecode-0.04/lib/Text/Unidecode.pm. The same caveats,
20
+ notes, and constraints listed there apply here though the Ruby implementation here is
21
+ slightly different, specifically the addition of String#to_ascii.
22
+
23
+ = Contact
24
+
25
+ You can contact me via email (mailto:rsl@luckysneaks.com) or the Google Group I've set up
26
+ at http://groups.google.com/group/unidecode.
27
+
28
+ = Thanks
29
+
30
+ Thanks to Brian Cully <bjc@kublai.com> and RubyPanther for all their patience
31
+ and assistance.
32
+
33
+ = Copyright
34
+
35
+ Copyright (c) 2007 Russell Norris
36
+
37
+ Permission is hereby granted, free of charge, to any person
38
+ obtaining a copy of this software and associated documentation
39
+ files (the "Software"), to deal in the Software without
40
+ restriction, including without limitation the rights to use,
41
+ copy, modify, merge, publish, distribute, sublicense, and/or sell
42
+ copies of the Software, and to permit persons to whom the
43
+ Software is furnished to do so, subject to the following
44
+ conditions:
45
+
46
+ The above copyright notice and this permission notice shall be
47
+ included in all copies or substantial portions of the Software.
48
+
49
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
50
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
51
+ OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
52
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
53
+ HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
54
+ WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
55
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
56
+ OTHER DEALINGS IN THE SOFTWARE.
@@ -0,0 +1,257 @@
1
+ ---
2
+ - "\z"
3
+ - "\x01"
4
+ - "\x02"
5
+ - "\x03"
6
+ - "\x04"
7
+ - "\x05"
8
+ - "\x06"
9
+ - "\a"
10
+ - "\x08"
11
+ - ' '
12
+ - "\n"
13
+ - "\v"
14
+ - "\f"
15
+ - "\r"
16
+ - "\x0e"
17
+ - "\x0f"
18
+ - "\x10"
19
+ - "\x11"
20
+ - "\x12"
21
+ - "\x13"
22
+ - "\x14"
23
+ - "\x15"
24
+ - "\x16"
25
+ - "\x17"
26
+ - "\x18"
27
+ - "\x19"
28
+ - "\x1a"
29
+ - "\e"
30
+ - "\x1c"
31
+ - "\x1d"
32
+ - "\x1e"
33
+ - "\x1f"
34
+ - ' '
35
+ - '!'
36
+ - '"'
37
+ - '#'
38
+ - $
39
+ - '%'
40
+ - '&'
41
+ - "'"
42
+ - (
43
+ - )
44
+ - '*'
45
+ - +
46
+ - ','
47
+ - -
48
+ - .
49
+ - /
50
+ - 0
51
+ - 1
52
+ - 2
53
+ - 3
54
+ - 4
55
+ - 5
56
+ - 6
57
+ - 7
58
+ - 8
59
+ - 9
60
+ - ':'
61
+ - ;
62
+ - <
63
+ - =
64
+ - '>'
65
+ - '?'
66
+ - '@'
67
+ - A
68
+ - B
69
+ - C
70
+ - D
71
+ - E
72
+ - F
73
+ - G
74
+ - H
75
+ - I
76
+ - J
77
+ - K
78
+ - L
79
+ - M
80
+ - N
81
+ - O
82
+ - P
83
+ - Q
84
+ - R
85
+ - S
86
+ - T
87
+ - U
88
+ - V
89
+ - W
90
+ - X
91
+ - Y
92
+ - Z
93
+ - ']'
94
+ - \
95
+ - ']'
96
+ - '^'
97
+ - _
98
+ - '`'
99
+ - a
100
+ - b
101
+ - c
102
+ - d
103
+ - e
104
+ - f
105
+ - g
106
+ - h
107
+ - i
108
+ - j
109
+ - k
110
+ - l
111
+ - m
112
+ - n
113
+ - o
114
+ - p
115
+ - q
116
+ - r
117
+ - s
118
+ - t
119
+ - u
120
+ - v
121
+ - w
122
+ - x
123
+ - y
124
+ - z
125
+ - '{'
126
+ - '|'
127
+ - '}'
128
+ - '~'
129
+ - 
130
+ - ''
131
+ - ''
132
+ - ''
133
+ - ''
134
+ - ''
135
+ - ''
136
+ - ''
137
+ - ''
138
+ - ''
139
+ - ''
140
+ - ''
141
+ - ''
142
+ - ''
143
+ - ''
144
+ - ''
145
+ - ''
146
+ - ''
147
+ - ''
148
+ - ''
149
+ - ''
150
+ - ''
151
+ - ''
152
+ - ''
153
+ - ''
154
+ - ''
155
+ - ''
156
+ - ''
157
+ - ''
158
+ - ''
159
+ - ''
160
+ - ''
161
+ - ''
162
+ - ' '
163
+ - '!'
164
+ - C/
165
+ - PS
166
+ - $?
167
+ - Y=
168
+ - '|'
169
+ - SS
170
+ - '"'
171
+ - (c)
172
+ - a
173
+ - <<
174
+ - '!'
175
+ - ''
176
+ - (r)
177
+ - -
178
+ - deg
179
+ - +-
180
+ - 2
181
+ - 3
182
+ - "'"
183
+ - u
184
+ - P
185
+ - '*'
186
+ - ','
187
+ - 1
188
+ - o
189
+ - '>>'
190
+ - 1/4
191
+ - 1/2
192
+ - 3/4
193
+ - '?'
194
+ - A
195
+ - A
196
+ - A
197
+ - A
198
+ - A
199
+ - A
200
+ - AE
201
+ - C
202
+ - E
203
+ - E
204
+ - E
205
+ - E
206
+ - I
207
+ - I
208
+ - I
209
+ - I
210
+ - D
211
+ - N
212
+ - O
213
+ - O
214
+ - O
215
+ - O
216
+ - O
217
+ - x
218
+ - O
219
+ - U
220
+ - U
221
+ - U
222
+ - U
223
+ - U
224
+ - Th
225
+ - ss
226
+ - a
227
+ - a
228
+ - a
229
+ - a
230
+ - a
231
+ - a
232
+ - ae
233
+ - c
234
+ - e
235
+ - e
236
+ - e
237
+ - e
238
+ - i
239
+ - i
240
+ - i
241
+ - i
242
+ - d
243
+ - n
244
+ - o
245
+ - o
246
+ - o
247
+ - o
248
+ - o
249
+ - /
250
+ - o
251
+ - u
252
+ - u
253
+ - u
254
+ - u
255
+ - y
256
+ - th
257
+ - y
@@ -0,0 +1,257 @@
1
+ ---
2
+ - A
3
+ - a
4
+ - A
5
+ - a
6
+ - A
7
+ - a
8
+ - C
9
+ - c
10
+ - C
11
+ - c
12
+ - C
13
+ - c
14
+ - C
15
+ - c
16
+ - D
17
+ - d
18
+ - D
19
+ - d
20
+ - E
21
+ - e
22
+ - E
23
+ - e
24
+ - E
25
+ - e
26
+ - E
27
+ - e
28
+ - E
29
+ - e
30
+ - G
31
+ - g
32
+ - G
33
+ - g
34
+ - G
35
+ - g
36
+ - G
37
+ - g
38
+ - H
39
+ - h
40
+ - H
41
+ - h
42
+ - I
43
+ - i
44
+ - I
45
+ - i
46
+ - I
47
+ - i
48
+ - I
49
+ - i
50
+ - I
51
+ - i
52
+ - IJ
53
+ - ''
54
+ - J
55
+ - j
56
+ - K
57
+ - k
58
+ - k
59
+ - L
60
+ - l
61
+ - L
62
+ - l
63
+ - L
64
+ - l
65
+ - L
66
+ - l
67
+ - L
68
+ - l
69
+ - N
70
+ - n
71
+ - N
72
+ - n
73
+ - N
74
+ - n
75
+ - "'n"
76
+ - ng
77
+ - NG
78
+ - O
79
+ - o
80
+ - O
81
+ - o
82
+ - O
83
+ - o
84
+ - OE
85
+ - oe
86
+ - R
87
+ - r
88
+ - R
89
+ - r
90
+ - R
91
+ - r
92
+ - S
93
+ - s
94
+ - S
95
+ - s
96
+ - S
97
+ - s
98
+ - S
99
+ - s
100
+ - T
101
+ - t
102
+ - T
103
+ - t
104
+ - T
105
+ - t
106
+ - U
107
+ - u
108
+ - U
109
+ - u
110
+ - U
111
+ - u
112
+ - U
113
+ - u
114
+ - U
115
+ - u
116
+ - U
117
+ - u
118
+ - W
119
+ - w
120
+ - Y
121
+ - y
122
+ - Y
123
+ - Z
124
+ - z
125
+ - Z
126
+ - z
127
+ - Z
128
+ - z
129
+ - s
130
+ - b
131
+ - B
132
+ - B
133
+ - b
134
+ - 6
135
+ - 6
136
+ - O
137
+ - C
138
+ - c
139
+ - D
140
+ - D
141
+ - D
142
+ - d
143
+ - d
144
+ - 3
145
+ - '@'
146
+ - E
147
+ - F
148
+ - f
149
+ - G
150
+ - G
151
+ - hv
152
+ - I
153
+ - I
154
+ - K
155
+ - k
156
+ - l
157
+ - l
158
+ - W
159
+ - N
160
+ - n
161
+ - O
162
+ - O
163
+ - o
164
+ - OI
165
+ - oi
166
+ - P
167
+ - p
168
+ - YR
169
+ - 2
170
+ - 2
171
+ - SH
172
+ - sh
173
+ - t
174
+ - T
175
+ - t
176
+ - T
177
+ - U
178
+ - u
179
+ - Y
180
+ - V
181
+ - Y
182
+ - y
183
+ - Z
184
+ - z
185
+ - ZH
186
+ - ZH
187
+ - zh
188
+ - zh
189
+ - 2
190
+ - 5
191
+ - 5
192
+ - ts
193
+ - w
194
+ - '|'
195
+ - '||'
196
+ - '|='
197
+ - '!'
198
+ - DZ
199
+ - Dz
200
+ - dz
201
+ - LJ
202
+ - Lj
203
+ - lj
204
+ - NJ
205
+ - Nj
206
+ - nj
207
+ - A
208
+ - a
209
+ - I
210
+ - i
211
+ - O
212
+ - o
213
+ - U
214
+ - u
215
+ - U
216
+ - u
217
+ - U
218
+ - u
219
+ - U
220
+ - u
221
+ - U
222
+ - u
223
+ - '@'
224
+ - A
225
+ - a
226
+ - A
227
+ - a
228
+ - AE
229
+ - ae
230
+ - G
231
+ - g
232
+ - G
233
+ - g
234
+ - K
235
+ - k
236
+ - O
237
+ - o
238
+ - O
239
+ - o
240
+ - ZH
241
+ - zh
242
+ - j
243
+ - DZ
244
+ - D
245
+ - dz
246
+ - G
247
+ - g
248
+ - HV
249
+ - W
250
+ - N
251
+ - n
252
+ - A
253
+ - a
254
+ - AE
255
+ - ae
256
+ - O
257
+ - o