mittens 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (137) hide show
  1. checksums.yaml +7 -0
  2. data/CHANGELOG.md +3 -0
  3. data/Gemfile +7 -0
  4. data/LICENSE.txt +30 -0
  5. data/README.md +62 -0
  6. data/Rakefile +21 -0
  7. data/ext/mittens/ext.c +96 -0
  8. data/ext/mittens/extconf.rb +12 -0
  9. data/lib/mittens/version.rb +3 -0
  10. data/lib/mittens.rb +7 -0
  11. data/mittens.gemspec +22 -0
  12. data/vendor/snowball/.gitignore +26 -0
  13. data/vendor/snowball/.travis.yml +112 -0
  14. data/vendor/snowball/AUTHORS +27 -0
  15. data/vendor/snowball/CONTRIBUTING.rst +216 -0
  16. data/vendor/snowball/COPYING +29 -0
  17. data/vendor/snowball/GNUmakefile +742 -0
  18. data/vendor/snowball/NEWS +754 -0
  19. data/vendor/snowball/README.rst +37 -0
  20. data/vendor/snowball/ada/README.md +74 -0
  21. data/vendor/snowball/ada/generate/generate.adb +83 -0
  22. data/vendor/snowball/ada/generate.gpr +21 -0
  23. data/vendor/snowball/ada/src/stemmer.adb +620 -0
  24. data/vendor/snowball/ada/src/stemmer.ads +219 -0
  25. data/vendor/snowball/ada/src/stemwords.adb +70 -0
  26. data/vendor/snowball/ada/stemmer_config.gpr +83 -0
  27. data/vendor/snowball/ada/stemwords.gpr +21 -0
  28. data/vendor/snowball/algorithms/arabic.sbl +558 -0
  29. data/vendor/snowball/algorithms/armenian.sbl +301 -0
  30. data/vendor/snowball/algorithms/basque.sbl +149 -0
  31. data/vendor/snowball/algorithms/catalan.sbl +202 -0
  32. data/vendor/snowball/algorithms/danish.sbl +93 -0
  33. data/vendor/snowball/algorithms/dutch.sbl +164 -0
  34. data/vendor/snowball/algorithms/english.sbl +229 -0
  35. data/vendor/snowball/algorithms/finnish.sbl +197 -0
  36. data/vendor/snowball/algorithms/french.sbl +254 -0
  37. data/vendor/snowball/algorithms/german.sbl +139 -0
  38. data/vendor/snowball/algorithms/german2.sbl +145 -0
  39. data/vendor/snowball/algorithms/greek.sbl +701 -0
  40. data/vendor/snowball/algorithms/hindi.sbl +323 -0
  41. data/vendor/snowball/algorithms/hungarian.sbl +241 -0
  42. data/vendor/snowball/algorithms/indonesian.sbl +192 -0
  43. data/vendor/snowball/algorithms/irish.sbl +149 -0
  44. data/vendor/snowball/algorithms/italian.sbl +202 -0
  45. data/vendor/snowball/algorithms/kraaij_pohlmann.sbl +240 -0
  46. data/vendor/snowball/algorithms/lithuanian.sbl +373 -0
  47. data/vendor/snowball/algorithms/lovins.sbl +208 -0
  48. data/vendor/snowball/algorithms/nepali.sbl +92 -0
  49. data/vendor/snowball/algorithms/norwegian.sbl +80 -0
  50. data/vendor/snowball/algorithms/porter.sbl +139 -0
  51. data/vendor/snowball/algorithms/portuguese.sbl +218 -0
  52. data/vendor/snowball/algorithms/romanian.sbl +236 -0
  53. data/vendor/snowball/algorithms/russian.sbl +221 -0
  54. data/vendor/snowball/algorithms/serbian.sbl +2379 -0
  55. data/vendor/snowball/algorithms/spanish.sbl +230 -0
  56. data/vendor/snowball/algorithms/swedish.sbl +72 -0
  57. data/vendor/snowball/algorithms/tamil.sbl +405 -0
  58. data/vendor/snowball/algorithms/turkish.sbl +470 -0
  59. data/vendor/snowball/algorithms/yiddish.sbl +460 -0
  60. data/vendor/snowball/charsets/ISO-8859-2.sbl +98 -0
  61. data/vendor/snowball/charsets/KOI8-R.sbl +74 -0
  62. data/vendor/snowball/charsets/cp850.sbl +130 -0
  63. data/vendor/snowball/compiler/analyser.c +1547 -0
  64. data/vendor/snowball/compiler/driver.c +615 -0
  65. data/vendor/snowball/compiler/generator.c +1748 -0
  66. data/vendor/snowball/compiler/generator_ada.c +1702 -0
  67. data/vendor/snowball/compiler/generator_csharp.c +1322 -0
  68. data/vendor/snowball/compiler/generator_go.c +1278 -0
  69. data/vendor/snowball/compiler/generator_java.c +1313 -0
  70. data/vendor/snowball/compiler/generator_js.c +1316 -0
  71. data/vendor/snowball/compiler/generator_pascal.c +1387 -0
  72. data/vendor/snowball/compiler/generator_python.c +1337 -0
  73. data/vendor/snowball/compiler/generator_rust.c +1295 -0
  74. data/vendor/snowball/compiler/header.h +418 -0
  75. data/vendor/snowball/compiler/space.c +286 -0
  76. data/vendor/snowball/compiler/syswords.h +86 -0
  77. data/vendor/snowball/compiler/syswords2.h +13 -0
  78. data/vendor/snowball/compiler/tokeniser.c +567 -0
  79. data/vendor/snowball/csharp/.gitignore +8 -0
  80. data/vendor/snowball/csharp/Snowball/Algorithms/.gitignore +1 -0
  81. data/vendor/snowball/csharp/Snowball/Among.cs +108 -0
  82. data/vendor/snowball/csharp/Snowball/AssemblyInfo.cs +36 -0
  83. data/vendor/snowball/csharp/Snowball/Stemmer.cs +660 -0
  84. data/vendor/snowball/csharp/Stemwords/App.config +6 -0
  85. data/vendor/snowball/csharp/Stemwords/Program.cs +114 -0
  86. data/vendor/snowball/doc/TODO +12 -0
  87. data/vendor/snowball/doc/libstemmer_c_README +148 -0
  88. data/vendor/snowball/doc/libstemmer_csharp_README +53 -0
  89. data/vendor/snowball/doc/libstemmer_java_README +67 -0
  90. data/vendor/snowball/doc/libstemmer_js_README +48 -0
  91. data/vendor/snowball/doc/libstemmer_python_README +113 -0
  92. data/vendor/snowball/examples/stemwords.c +204 -0
  93. data/vendor/snowball/go/README.md +55 -0
  94. data/vendor/snowball/go/among.go +16 -0
  95. data/vendor/snowball/go/env.go +403 -0
  96. data/vendor/snowball/go/stemwords/generate.go +68 -0
  97. data/vendor/snowball/go/stemwords/main.go +68 -0
  98. data/vendor/snowball/go/util.go +34 -0
  99. data/vendor/snowball/iconv.py +50 -0
  100. data/vendor/snowball/include/libstemmer.h +78 -0
  101. data/vendor/snowball/java/org/tartarus/snowball/Among.java +29 -0
  102. data/vendor/snowball/java/org/tartarus/snowball/SnowballProgram.java +381 -0
  103. data/vendor/snowball/java/org/tartarus/snowball/SnowballStemmer.java +8 -0
  104. data/vendor/snowball/java/org/tartarus/snowball/TestApp.java +75 -0
  105. data/vendor/snowball/javascript/base-stemmer.js +294 -0
  106. data/vendor/snowball/javascript/stemwords.js +106 -0
  107. data/vendor/snowball/libstemmer/libstemmer_c.in +96 -0
  108. data/vendor/snowball/libstemmer/mkalgorithms.pl +90 -0
  109. data/vendor/snowball/libstemmer/mkmodules.pl +267 -0
  110. data/vendor/snowball/libstemmer/modules.txt +63 -0
  111. data/vendor/snowball/libstemmer/test.c +34 -0
  112. data/vendor/snowball/pascal/.gitignore +4 -0
  113. data/vendor/snowball/pascal/SnowballProgram.pas +430 -0
  114. data/vendor/snowball/pascal/generate.pl +23 -0
  115. data/vendor/snowball/pascal/stemwords-template.dpr +78 -0
  116. data/vendor/snowball/python/MANIFEST.in +7 -0
  117. data/vendor/snowball/python/create_init.py +54 -0
  118. data/vendor/snowball/python/setup.cfg +6 -0
  119. data/vendor/snowball/python/setup.py +81 -0
  120. data/vendor/snowball/python/snowballstemmer/among.py +13 -0
  121. data/vendor/snowball/python/snowballstemmer/basestemmer.py +323 -0
  122. data/vendor/snowball/python/stemwords.py +101 -0
  123. data/vendor/snowball/python/testapp.py +28 -0
  124. data/vendor/snowball/runtime/api.c +58 -0
  125. data/vendor/snowball/runtime/api.h +32 -0
  126. data/vendor/snowball/runtime/header.h +61 -0
  127. data/vendor/snowball/runtime/utilities.c +513 -0
  128. data/vendor/snowball/rust/Cargo.toml +7 -0
  129. data/vendor/snowball/rust/build.rs +55 -0
  130. data/vendor/snowball/rust/rust-pre-1.27-compat.patch +30 -0
  131. data/vendor/snowball/rust/src/main.rs +102 -0
  132. data/vendor/snowball/rust/src/snowball/algorithms/mod.rs +2 -0
  133. data/vendor/snowball/rust/src/snowball/among.rs +6 -0
  134. data/vendor/snowball/rust/src/snowball/mod.rs +6 -0
  135. data/vendor/snowball/rust/src/snowball/snowball_env.rs +421 -0
  136. data/vendor/snowball/tests/stemtest.c +95 -0
  137. metadata +178 -0
@@ -0,0 +1,130 @@
1
+ // Code page 850 (MSDOS Latin 1) character mappings.
2
+
3
+ stringdef U+00A0 hex 'FF'
4
+ stringdef U+00A1 hex 'AD'
5
+ stringdef U+00A2 hex 'BD'
6
+ stringdef U+00A3 hex '9C'
7
+ stringdef U+00A4 hex 'CF'
8
+ stringdef U+00A5 hex 'BE'
9
+ stringdef U+00A6 hex 'DD'
10
+ stringdef U+00A7 hex 'F5'
11
+ stringdef U+00A8 hex 'F9'
12
+ stringdef U+00A9 hex 'B8'
13
+ stringdef U+00AA hex 'A6'
14
+ stringdef U+00AB hex 'AE'
15
+ stringdef U+00AC hex 'AA'
16
+ stringdef U+00AD hex 'F0'
17
+ stringdef U+00AE hex 'A9'
18
+ stringdef U+00AF hex 'EE'
19
+ stringdef U+00B0 hex 'F8'
20
+ stringdef U+00B1 hex 'F1'
21
+ stringdef U+00B2 hex 'FD'
22
+ stringdef U+00B3 hex 'FC'
23
+ stringdef U+00B4 hex 'EF'
24
+ stringdef U+00B5 hex 'E6'
25
+ stringdef U+00B6 hex 'F4'
26
+ stringdef U+00B7 hex 'FA'
27
+ stringdef U+00B8 hex 'F7'
28
+ stringdef U+00B9 hex 'FB'
29
+ stringdef U+00BA hex 'A7'
30
+ stringdef U+00BB hex 'AF'
31
+ stringdef U+00BC hex 'AC'
32
+ stringdef U+00BD hex 'AB'
33
+ stringdef U+00BE hex 'F3'
34
+ stringdef U+00BF hex 'A8'
35
+ stringdef U+00C0 hex 'B7'
36
+ stringdef U+00C1 hex 'B5'
37
+ stringdef U+00C2 hex 'B6'
38
+ stringdef U+00C3 hex 'C7'
39
+ stringdef U+00C4 hex '8E'
40
+ stringdef U+00C5 hex '8F'
41
+ stringdef U+00C6 hex '92'
42
+ stringdef U+00C7 hex '80'
43
+ stringdef U+00C8 hex 'D4'
44
+ stringdef U+00C9 hex '90'
45
+ stringdef U+00CA hex 'D2'
46
+ stringdef U+00CB hex 'D3'
47
+ stringdef U+00CC hex 'DE'
48
+ stringdef U+00CD hex 'D6'
49
+ stringdef U+00CE hex 'D7'
50
+ stringdef U+00CF hex 'D8'
51
+ stringdef U+00D0 hex 'D1'
52
+ stringdef U+00D1 hex 'A5'
53
+ stringdef U+00D2 hex 'E3'
54
+ stringdef U+00D3 hex 'E0'
55
+ stringdef U+00D4 hex 'E2'
56
+ stringdef U+00D5 hex 'E5'
57
+ stringdef U+00D6 hex '99'
58
+ stringdef U+00D7 hex '9E'
59
+ stringdef U+00D8 hex '9D'
60
+ stringdef U+00D9 hex 'EB'
61
+ stringdef U+00DA hex 'E9'
62
+ stringdef U+00DB hex 'EA'
63
+ stringdef U+00DC hex '9A'
64
+ stringdef U+00DD hex 'ED'
65
+ stringdef U+00DE hex 'E8'
66
+ stringdef U+00DF hex 'E1'
67
+ stringdef U+00E0 hex '85'
68
+ stringdef U+00E1 hex 'A0'
69
+ stringdef U+00E2 hex '83'
70
+ stringdef U+00E3 hex 'C6'
71
+ stringdef U+00E4 hex '84'
72
+ stringdef U+00E5 hex '86'
73
+ stringdef U+00E6 hex '91'
74
+ stringdef U+00E7 hex '87'
75
+ stringdef U+00E8 hex '8A'
76
+ stringdef U+00E9 hex '82'
77
+ stringdef U+00EA hex '88'
78
+ stringdef U+00EB hex '89'
79
+ stringdef U+00EC hex '8D'
80
+ stringdef U+00ED hex 'A1'
81
+ stringdef U+00EE hex '8C'
82
+ stringdef U+00EF hex '8B'
83
+ stringdef U+00F0 hex 'D0'
84
+ stringdef U+00F1 hex 'A4'
85
+ stringdef U+00F2 hex '95'
86
+ stringdef U+00F3 hex 'A2'
87
+ stringdef U+00F4 hex '93'
88
+ stringdef U+00F5 hex 'E4'
89
+ stringdef U+00F6 hex '94'
90
+ stringdef U+00F7 hex 'F6'
91
+ stringdef U+00F8 hex '9B'
92
+ stringdef U+00F9 hex '97'
93
+ stringdef U+00FA hex 'A3'
94
+ stringdef U+00FB hex '96'
95
+ stringdef U+00FC hex '81'
96
+ stringdef U+00FD hex 'EC'
97
+ stringdef U+00FE hex 'E7'
98
+ stringdef U+00FF hex '98'
99
+ stringdef U+0131 hex 'D5'
100
+ stringdef U+0192 hex '9F'
101
+ stringdef U+2017 hex 'F2'
102
+ stringdef U+2500 hex 'C4'
103
+ stringdef U+2502 hex 'B3'
104
+ stringdef U+250C hex 'DA'
105
+ stringdef U+2510 hex 'BF'
106
+ stringdef U+2514 hex 'C0'
107
+ stringdef U+2518 hex 'D9'
108
+ stringdef U+251C hex 'C3'
109
+ stringdef U+2524 hex 'B4'
110
+ stringdef U+252C hex 'C2'
111
+ stringdef U+2534 hex 'C1'
112
+ stringdef U+253C hex 'C5'
113
+ stringdef U+2550 hex 'CD'
114
+ stringdef U+2551 hex 'BA'
115
+ stringdef U+2554 hex 'C9'
116
+ stringdef U+2557 hex 'BB'
117
+ stringdef U+255A hex 'C8'
118
+ stringdef U+255D hex 'BC'
119
+ stringdef U+2560 hex 'CC'
120
+ stringdef U+2563 hex 'B9'
121
+ stringdef U+2566 hex 'CB'
122
+ stringdef U+2569 hex 'CA'
123
+ stringdef U+256C hex 'CE'
124
+ stringdef U+2580 hex 'DF'
125
+ stringdef U+2584 hex 'DC'
126
+ stringdef U+2588 hex 'DB'
127
+ stringdef U+2591 hex 'B0'
128
+ stringdef U+2592 hex 'B1'
129
+ stringdef U+2593 hex 'B2'
130
+ stringdef U+25A0 hex 'FE'