language_detector 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (172) hide show
  1. data/README.rdoc +24 -0
  2. data/Rakefile +18 -0
  3. data/VERSION +1 -0
  4. data/lib/language_detector.rb +232 -0
  5. data/lib/model-fm.yml +52504 -0
  6. data/lib/model-tc.yml +53985 -0
  7. data/lib/textcat_ngrams/afrikaans.lm +400 -0
  8. data/lib/textcat_ngrams/albanian.lm +400 -0
  9. data/lib/textcat_ngrams/amharic-utf.lm +400 -0
  10. data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
  11. data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
  12. data/lib/textcat_ngrams/armenian.lm +400 -0
  13. data/lib/textcat_ngrams/basque.lm +400 -0
  14. data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
  15. data/lib/textcat_ngrams/bosnian.lm +400 -0
  16. data/lib/textcat_ngrams/breton.lm +400 -0
  17. data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
  18. data/lib/textcat_ngrams/catalan.lm +400 -0
  19. data/lib/textcat_ngrams/chinese-big5.lm +400 -0
  20. data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
  21. data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
  22. data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
  23. data/lib/textcat_ngrams/danish.lm +400 -0
  24. data/lib/textcat_ngrams/dutch.lm +400 -0
  25. data/lib/textcat_ngrams/english.lm +400 -0
  26. data/lib/textcat_ngrams/esperanto.lm +400 -0
  27. data/lib/textcat_ngrams/estonian.lm +400 -0
  28. data/lib/textcat_ngrams/finnish.lm +400 -0
  29. data/lib/textcat_ngrams/french.lm +400 -0
  30. data/lib/textcat_ngrams/frisian.lm +400 -0
  31. data/lib/textcat_ngrams/georgian.lm +400 -0
  32. data/lib/textcat_ngrams/german.lm +400 -0
  33. data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
  34. data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
  35. data/lib/textcat_ngrams/hindi.lm +400 -0
  36. data/lib/textcat_ngrams/hungarian.lm +400 -0
  37. data/lib/textcat_ngrams/icelandic.lm +400 -0
  38. data/lib/textcat_ngrams/indonesian.lm +400 -0
  39. data/lib/textcat_ngrams/irish.lm +400 -0
  40. data/lib/textcat_ngrams/italian.lm +400 -0
  41. data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
  42. data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
  43. data/lib/textcat_ngrams/korean.lm +400 -0
  44. data/lib/textcat_ngrams/latin.lm +400 -0
  45. data/lib/textcat_ngrams/latvian.lm +400 -0
  46. data/lib/textcat_ngrams/lithuanian.lm +400 -0
  47. data/lib/textcat_ngrams/malay.lm +400 -0
  48. data/lib/textcat_ngrams/manx.lm +400 -0
  49. data/lib/textcat_ngrams/marathi.lm +400 -0
  50. data/lib/textcat_ngrams/mingo.lm +400 -0
  51. data/lib/textcat_ngrams/nepali.lm +400 -0
  52. data/lib/textcat_ngrams/norwegian.lm +400 -0
  53. data/lib/textcat_ngrams/persian.lm +400 -0
  54. data/lib/textcat_ngrams/polish.lm +400 -0
  55. data/lib/textcat_ngrams/portuguese.lm +400 -0
  56. data/lib/textcat_ngrams/quechua.lm +400 -0
  57. data/lib/textcat_ngrams/romanian.lm +400 -0
  58. data/lib/textcat_ngrams/rumantsch.lm +400 -0
  59. data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
  60. data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
  61. data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
  62. data/lib/textcat_ngrams/sanskrit.lm +400 -0
  63. data/lib/textcat_ngrams/scots.lm +400 -0
  64. data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
  65. data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
  66. data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
  67. data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
  68. data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
  69. data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
  70. data/lib/textcat_ngrams/spanish.lm +400 -0
  71. data/lib/textcat_ngrams/swahili.lm +400 -0
  72. data/lib/textcat_ngrams/swedish.lm +400 -0
  73. data/lib/textcat_ngrams/tagalog.lm +400 -0
  74. data/lib/textcat_ngrams/tamil.lm +400 -0
  75. data/lib/textcat_ngrams/thai.lm +400 -0
  76. data/lib/textcat_ngrams/turkish.lm +400 -0
  77. data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
  78. data/lib/textcat_ngrams/vietnamese.lm +400 -0
  79. data/lib/textcat_ngrams/welsh.lm +400 -0
  80. data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
  81. data/lib/training_data/ar-utf8.txt +54 -0
  82. data/lib/training_data/bg-utf8.txt +26 -0
  83. data/lib/training_data/cs-utf8.txt +48 -0
  84. data/lib/training_data/da-utf8.txt +159 -0
  85. data/lib/training_data/de-utf8.txt +569 -0
  86. data/lib/training_data/el-utf8.txt +48 -0
  87. data/lib/training_data/en-utf8.txt +81 -0
  88. data/lib/training_data/es-utf8.txt +185 -0
  89. data/lib/training_data/et-utf8.txt +50 -0
  90. data/lib/training_data/fa-utf8.txt +42 -0
  91. data/lib/training_data/fi-utf8.txt +83 -0
  92. data/lib/training_data/fr-utf8.txt +191 -0
  93. data/lib/training_data/fy-utf8.txt +22 -0
  94. data/lib/training_data/ga-utf8.txt +109 -0
  95. data/lib/training_data/he-utf8.txt +116 -0
  96. data/lib/training_data/hi-utf8.txt +49 -0
  97. data/lib/training_data/hr-utf8.txt +80 -0
  98. data/lib/training_data/hu-utf8.txt +87 -0
  99. data/lib/training_data/io-utf8.txt +41 -0
  100. data/lib/training_data/is-utf8.txt +94 -0
  101. data/lib/training_data/it-utf8.txt +228 -0
  102. data/lib/training_data/ja-utf8.txt +200 -0
  103. data/lib/training_data/ko-utf8.txt +147 -0
  104. data/lib/training_data/nl-utf8.txt +215 -0
  105. data/lib/training_data/no-utf8.txt +281 -0
  106. data/lib/training_data/pl-utf8.txt +120 -0
  107. data/lib/training_data/pt-utf8.txt +214 -0
  108. data/lib/training_data/ro-utf8.txt +66 -0
  109. data/lib/training_data/ru-utf8.txt +310 -0
  110. data/lib/training_data/sl-utf8.txt +263 -0
  111. data/lib/training_data/sv-utf8.txt +174 -0
  112. data/lib/training_data/th-utf8.txt +49 -0
  113. data/lib/training_data/tk-utf8.txt +101 -0
  114. data/lib/training_data/todo/af.txt +114 -0
  115. data/lib/training_data/todo/amharic-utf.txt +95 -0
  116. data/lib/training_data/todo/arabic-windows1256.txt +157 -0
  117. data/lib/training_data/todo/armenian.txt +86 -0
  118. data/lib/training_data/todo/basque.txt +136 -0
  119. data/lib/training_data/todo/belarus-windows1251.txt +97 -0
  120. data/lib/training_data/todo/bosnian.txt +97 -0
  121. data/lib/training_data/todo/breton.txt +159 -0
  122. data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
  123. data/lib/training_data/todo/catalan.txt +93 -0
  124. data/lib/training_data/todo/croatian-ascii.txt +104 -0
  125. data/lib/training_data/todo/esperanto.txt +95 -0
  126. data/lib/training_data/todo/estonian.txt +218 -0
  127. data/lib/training_data/todo/frisian.txt +99 -0
  128. data/lib/training_data/todo/georgian.txt +86 -0
  129. data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
  130. data/lib/training_data/todo/hawaian.txt +108 -0
  131. data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
  132. data/lib/training_data/todo/hindi.txt +77 -0
  133. data/lib/training_data/todo/hungarian.txt +102 -0
  134. data/lib/training_data/todo/icelandic.txt +131 -0
  135. data/lib/training_data/todo/indonesian.txt +93 -0
  136. data/lib/training_data/todo/irish.txt +209 -0
  137. data/lib/training_data/todo/latin.txt +120 -0
  138. data/lib/training_data/todo/latvian.txt +126 -0
  139. data/lib/training_data/todo/lithuanian.txt +99 -0
  140. data/lib/training_data/todo/malay.txt +108 -0
  141. data/lib/training_data/todo/manx.txt +78 -0
  142. data/lib/training_data/todo/marathi.txt +100 -0
  143. data/lib/training_data/todo/mf.txt +100 -0
  144. data/lib/training_data/todo/middle_frisian.txt +102 -0
  145. data/lib/training_data/todo/mingo.txt +146 -0
  146. data/lib/training_data/todo/nepali.txt +131 -0
  147. data/lib/training_data/todo/persian.txt +73 -0
  148. data/lib/training_data/todo/quechua.txt +108 -0
  149. data/lib/training_data/todo/romanian.txt +103 -0
  150. data/lib/training_data/todo/rumantsch.txt +110 -0
  151. data/lib/training_data/todo/sanskrit.txt +135 -0
  152. data/lib/training_data/todo/scots.txt +490 -0
  153. data/lib/training_data/todo/scots_gaelic.txt +93 -0
  154. data/lib/training_data/todo/serbian-ascii.txt +121 -0
  155. data/lib/training_data/todo/slovak-ascii.txt +102 -0
  156. data/lib/training_data/todo/slovak-windows1250.txt +115 -0
  157. data/lib/training_data/todo/slovenian-ascii.txt +100 -0
  158. data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
  159. data/lib/training_data/todo/sq.txt +110 -0
  160. data/lib/training_data/todo/swahili.txt +120 -0
  161. data/lib/training_data/todo/tagalog.txt +135 -0
  162. data/lib/training_data/todo/tamil.txt +123 -0
  163. data/lib/training_data/todo/turkish.txt +117 -0
  164. data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
  165. data/lib/training_data/todo/vietnamese.txt +92 -0
  166. data/lib/training_data/todo/welsh.txt +148 -0
  167. data/lib/training_data/todo/yiddish-utf.txt +83 -0
  168. data/lib/training_data/uk-utf8.txt +75 -0
  169. data/lib/training_data/vi-utf8.txt +47 -0
  170. data/lib/training_data/zh-utf8.txt +228 -0
  171. data/test/language_detector_test.rb +78 -0
  172. metadata +232 -0

There are too many changes on this page to be displayed.


The amount of changes on this page would crash your brower.

You can still verify the content by downloading the gem file manually.