despamilator 0.3 → 0.4

Sign up to get free protection for your applications and to get access to all the features.
Files changed (619) hide show
  1. data/History.txt +11 -0
  2. data/Manifest.txt +612 -0
  3. data/despamliator.gemspec +39 -0
  4. data/lib/despamilator/filter/funky_consonant.rb +21 -0
  5. data/lib/despamilator/filter/long_words.rb +13 -0
  6. data/lib/despamilator/filter/naughty_q.rb +5 -2
  7. data/lib/despamilator/filter/naughty_words.rb +28 -0
  8. data/lib/despamilator/filter/square_brackets.rb +13 -0
  9. data/lib/despamilator/filter/urls.rb +11 -0
  10. data/lib/despamilator.rb +1 -1
  11. data/scripts/despamilator_score.rb +25 -0
  12. data/spec/clean_corpus/101.txt.gz +0 -0
  13. data/spec/clean_corpus/103.txt.gz +0 -0
  14. data/spec/clean_corpus/105.txt.gz +0 -0
  15. data/spec/clean_corpus/107.txt.gz +0 -0
  16. data/spec/clean_corpus/109.txt.gz +0 -0
  17. data/spec/clean_corpus/111.txt.gz +0 -0
  18. data/spec/clean_corpus/113.txt.gz +0 -0
  19. data/spec/clean_corpus/115.txt.gz +0 -0
  20. data/spec/clean_corpus/117.txt.gz +0 -0
  21. data/spec/clean_corpus/119.txt.gz +0 -0
  22. data/spec/clean_corpus/121.txt.gz +0 -0
  23. data/spec/clean_corpus/123.txt.gz +0 -0
  24. data/spec/clean_corpus/125.txt.gz +0 -0
  25. data/spec/clean_corpus/127.txt.gz +0 -0
  26. data/spec/clean_corpus/129.txt.gz +0 -0
  27. data/spec/clean_corpus/131.txt.gz +0 -0
  28. data/spec/clean_corpus/133.txt.gz +0 -0
  29. data/spec/clean_corpus/135.txt.gz +0 -0
  30. data/spec/clean_corpus/137.txt.gz +0 -0
  31. data/spec/clean_corpus/139.txt.gz +0 -0
  32. data/spec/clean_corpus/141.txt.gz +0 -0
  33. data/spec/clean_corpus/143.txt.gz +0 -0
  34. data/spec/clean_corpus/145.txt.gz +0 -0
  35. data/spec/clean_corpus/147.txt.gz +0 -0
  36. data/spec/clean_corpus/149.txt.gz +0 -0
  37. data/spec/clean_corpus/151.txt.gz +0 -0
  38. data/spec/clean_corpus/153.txt.gz +0 -0
  39. data/spec/clean_corpus/155.txt.gz +0 -0
  40. data/spec/clean_corpus/157.txt.gz +0 -0
  41. data/spec/clean_corpus/159.txt.gz +0 -0
  42. data/spec/clean_corpus/161.txt.gz +0 -0
  43. data/spec/clean_corpus/163.txt.gz +0 -0
  44. data/spec/clean_corpus/165.txt.gz +0 -0
  45. data/spec/clean_corpus/167.txt.gz +0 -0
  46. data/spec/clean_corpus/169.txt.gz +0 -0
  47. data/spec/clean_corpus/171.txt.gz +0 -0
  48. data/spec/clean_corpus/173.txt.gz +0 -0
  49. data/spec/clean_corpus/175.txt.gz +0 -0
  50. data/spec/clean_corpus/177.txt.gz +0 -0
  51. data/spec/clean_corpus/179.txt.gz +0 -0
  52. data/spec/clean_corpus/18.txt.gz +0 -0
  53. data/spec/clean_corpus/181.txt.gz +0 -0
  54. data/spec/clean_corpus/183.txt.gz +0 -0
  55. data/spec/clean_corpus/185.txt.gz +0 -0
  56. data/spec/clean_corpus/187.txt.gz +0 -0
  57. data/spec/clean_corpus/189.txt.gz +0 -0
  58. data/spec/clean_corpus/191.txt.gz +0 -0
  59. data/spec/clean_corpus/193.txt.gz +0 -0
  60. data/spec/clean_corpus/195.txt.gz +0 -0
  61. data/spec/clean_corpus/197.txt.gz +0 -0
  62. data/spec/clean_corpus/199.txt.gz +0 -0
  63. data/spec/clean_corpus/20.txt.gz +0 -0
  64. data/spec/clean_corpus/201.txt.gz +0 -0
  65. data/spec/clean_corpus/203.txt.gz +0 -0
  66. data/spec/clean_corpus/205.txt.gz +0 -0
  67. data/spec/clean_corpus/207.txt.gz +0 -0
  68. data/spec/clean_corpus/209.txt.gz +0 -0
  69. data/spec/clean_corpus/211.txt.gz +0 -0
  70. data/spec/clean_corpus/213.txt.gz +0 -0
  71. data/spec/clean_corpus/215.txt.gz +0 -0
  72. data/spec/clean_corpus/217.txt.gz +0 -0
  73. data/spec/clean_corpus/219.txt.gz +0 -0
  74. data/spec/clean_corpus/22.txt.gz +0 -0
  75. data/spec/clean_corpus/221.txt.gz +0 -0
  76. data/spec/clean_corpus/223.txt.gz +0 -0
  77. data/spec/clean_corpus/225.txt.gz +0 -0
  78. data/spec/clean_corpus/24.txt.gz +0 -0
  79. data/spec/clean_corpus/26.txt.gz +0 -0
  80. data/spec/clean_corpus/27.txt.gz +0 -0
  81. data/spec/clean_corpus/29.txt.gz +0 -0
  82. data/spec/clean_corpus/31.txt.gz +0 -0
  83. data/spec/clean_corpus/33.txt.gz +0 -0
  84. data/spec/clean_corpus/35.txt.gz +0 -0
  85. data/spec/clean_corpus/37.txt.gz +0 -0
  86. data/spec/clean_corpus/39.txt.gz +0 -0
  87. data/spec/clean_corpus/41.txt.gz +0 -0
  88. data/spec/clean_corpus/43.txt.gz +0 -0
  89. data/spec/clean_corpus/45.txt.gz +0 -0
  90. data/spec/clean_corpus/47.txt.gz +0 -0
  91. data/spec/clean_corpus/49.txt.gz +0 -0
  92. data/spec/clean_corpus/51.txt.gz +0 -0
  93. data/spec/clean_corpus/53.txt.gz +0 -0
  94. data/spec/clean_corpus/55.txt.gz +0 -0
  95. data/spec/clean_corpus/57.txt.gz +0 -0
  96. data/spec/clean_corpus/59.txt.gz +0 -0
  97. data/spec/clean_corpus/61.txt.gz +0 -0
  98. data/spec/clean_corpus/63.txt.gz +0 -0
  99. data/spec/clean_corpus/65.txt.gz +0 -0
  100. data/spec/clean_corpus/67.txt.gz +0 -0
  101. data/spec/clean_corpus/69.txt.gz +0 -0
  102. data/spec/clean_corpus/71.txt.gz +0 -0
  103. data/spec/clean_corpus/73.txt.gz +0 -0
  104. data/spec/clean_corpus/75.txt.gz +0 -0
  105. data/spec/clean_corpus/77.txt.gz +0 -0
  106. data/spec/clean_corpus/79.txt.gz +0 -0
  107. data/spec/clean_corpus/81.txt.gz +0 -0
  108. data/spec/clean_corpus/83.txt.gz +0 -0
  109. data/spec/clean_corpus/85.txt.gz +0 -0
  110. data/spec/clean_corpus/87.txt.gz +0 -0
  111. data/spec/clean_corpus/89.txt.gz +0 -0
  112. data/spec/clean_corpus/91.txt.gz +0 -0
  113. data/spec/clean_corpus/93.txt.gz +0 -0
  114. data/spec/clean_corpus/95.txt.gz +0 -0
  115. data/spec/clean_corpus/97.txt.gz +0 -0
  116. data/spec/clean_corpus/99.txt.gz +0 -0
  117. data/spec/clean_corpus_spec.rb +11 -0
  118. data/spec/filters/funky_consonant_spec.rb +39 -0
  119. data/spec/filters/long_words_spec.rb +34 -0
  120. data/spec/filters/naughty_q_spec.rb +3 -3
  121. data/spec/filters/naughty_words_spec.rb +39 -0
  122. data/spec/filters/square_brackets_spec.rb +35 -0
  123. data/spec/filters/urls_spec.rb +39 -0
  124. data/spec/spam_corpus/0.txt.gz +0 -0
  125. data/spec/spam_corpus/1.txt.gz +0 -0
  126. data/spec/spam_corpus/10.txt.gz +0 -0
  127. data/spec/spam_corpus/100.txt.gz +0 -0
  128. data/spec/spam_corpus/102.txt.gz +0 -0
  129. data/spec/spam_corpus/104.txt.gz +0 -0
  130. data/spec/spam_corpus/106.txt.gz +0 -0
  131. data/spec/spam_corpus/108.txt.gz +0 -0
  132. data/spec/spam_corpus/11.txt.gz +0 -0
  133. data/spec/spam_corpus/110.txt.gz +0 -0
  134. data/spec/spam_corpus/112.txt.gz +0 -0
  135. data/spec/spam_corpus/114.txt.gz +0 -0
  136. data/spec/spam_corpus/116.txt.gz +0 -0
  137. data/spec/spam_corpus/118.txt.gz +0 -0
  138. data/spec/spam_corpus/12.txt.gz +0 -0
  139. data/spec/spam_corpus/120.txt.gz +0 -0
  140. data/spec/spam_corpus/122.txt.gz +0 -0
  141. data/spec/spam_corpus/124.txt.gz +0 -0
  142. data/spec/spam_corpus/126.txt.gz +0 -0
  143. data/spec/spam_corpus/128.txt.gz +0 -0
  144. data/spec/spam_corpus/13.txt.gz +0 -0
  145. data/spec/spam_corpus/130.txt.gz +0 -0
  146. data/spec/spam_corpus/132.txt.gz +0 -0
  147. data/spec/spam_corpus/134.txt.gz +0 -0
  148. data/spec/spam_corpus/136.txt.gz +0 -0
  149. data/spec/spam_corpus/138.txt.gz +0 -0
  150. data/spec/spam_corpus/14.txt.gz +0 -0
  151. data/spec/spam_corpus/140.txt.gz +0 -0
  152. data/spec/spam_corpus/142.txt.gz +0 -0
  153. data/spec/spam_corpus/144.txt.gz +0 -0
  154. data/spec/spam_corpus/146.txt.gz +0 -0
  155. data/spec/spam_corpus/148.txt.gz +0 -0
  156. data/spec/spam_corpus/15.txt.gz +0 -0
  157. data/spec/spam_corpus/150.txt.gz +0 -0
  158. data/spec/spam_corpus/152.txt.gz +0 -0
  159. data/spec/spam_corpus/154.txt.gz +0 -0
  160. data/spec/spam_corpus/156.txt.gz +0 -0
  161. data/spec/spam_corpus/158.txt.gz +0 -0
  162. data/spec/spam_corpus/16.txt.gz +0 -0
  163. data/spec/spam_corpus/160.txt.gz +0 -0
  164. data/spec/spam_corpus/162.txt.gz +0 -0
  165. data/spec/spam_corpus/164.txt.gz +0 -0
  166. data/spec/spam_corpus/166.txt.gz +0 -0
  167. data/spec/spam_corpus/168.txt.gz +0 -0
  168. data/spec/spam_corpus/170.txt.gz +0 -0
  169. data/spec/spam_corpus/172.txt.gz +0 -0
  170. data/spec/spam_corpus/174.txt.gz +0 -0
  171. data/spec/spam_corpus/176.txt.gz +0 -0
  172. data/spec/spam_corpus/178.txt.gz +0 -0
  173. data/spec/spam_corpus/180.txt.gz +0 -0
  174. data/spec/spam_corpus/182.txt.gz +0 -0
  175. data/spec/spam_corpus/184.txt.gz +0 -0
  176. data/spec/spam_corpus/186.txt.gz +0 -0
  177. data/spec/spam_corpus/188.txt.gz +0 -0
  178. data/spec/spam_corpus/190.txt.gz +0 -0
  179. data/spec/spam_corpus/192.txt.gz +0 -0
  180. data/spec/spam_corpus/194.txt.gz +0 -0
  181. data/spec/spam_corpus/196.txt.gz +0 -0
  182. data/spec/spam_corpus/198.txt.gz +0 -0
  183. data/spec/spam_corpus/2.txt.gz +0 -0
  184. data/spec/spam_corpus/200.txt.gz +0 -0
  185. data/spec/spam_corpus/202.txt.gz +0 -0
  186. data/spec/spam_corpus/204.txt.gz +0 -0
  187. data/spec/spam_corpus/206.txt.gz +0 -0
  188. data/spec/spam_corpus/208.txt.gz +0 -0
  189. data/spec/spam_corpus/210.txt.gz +0 -0
  190. data/spec/spam_corpus/212.txt.gz +0 -0
  191. data/spec/spam_corpus/214.txt.gz +0 -0
  192. data/spec/spam_corpus/216.txt.gz +0 -0
  193. data/spec/spam_corpus/218.txt.gz +0 -0
  194. data/spec/spam_corpus/220.txt.gz +0 -0
  195. data/spec/spam_corpus/222.txt.gz +0 -0
  196. data/spec/spam_corpus/224.txt.gz +0 -0
  197. data/spec/spam_corpus/226.txt.gz +0 -0
  198. data/spec/spam_corpus/228.txt.gz +0 -0
  199. data/spec/spam_corpus/230.txt.gz +0 -0
  200. data/spec/spam_corpus/232.txt.gz +0 -0
  201. data/spec/spam_corpus/234.txt.gz +0 -0
  202. data/spec/spam_corpus/236.txt.gz +0 -0
  203. data/spec/spam_corpus/238.txt.gz +0 -0
  204. data/spec/spam_corpus/240.txt.gz +0 -0
  205. data/spec/spam_corpus/242.txt.gz +0 -0
  206. data/spec/spam_corpus/244.txt.gz +0 -0
  207. data/spec/spam_corpus/246.txt.gz +0 -0
  208. data/spec/spam_corpus/248.txt.gz +0 -0
  209. data/spec/spam_corpus/250.txt.gz +0 -0
  210. data/spec/spam_corpus/252.txt.gz +0 -0
  211. data/spec/spam_corpus/254.txt.gz +0 -0
  212. data/spec/spam_corpus/256.txt.gz +0 -0
  213. data/spec/spam_corpus/258.txt.gz +0 -0
  214. data/spec/spam_corpus/260.txt.gz +0 -0
  215. data/spec/spam_corpus/262.txt.gz +0 -0
  216. data/spec/spam_corpus/264.txt.gz +0 -0
  217. data/spec/spam_corpus/266.txt.gz +0 -0
  218. data/spec/spam_corpus/268.txt.gz +0 -0
  219. data/spec/spam_corpus/270.txt.gz +0 -0
  220. data/spec/spam_corpus/272.txt.gz +0 -0
  221. data/spec/spam_corpus/274.txt.gz +0 -0
  222. data/spec/spam_corpus/276.txt.gz +0 -0
  223. data/spec/spam_corpus/278.txt.gz +0 -0
  224. data/spec/spam_corpus/28.txt.gz +0 -0
  225. data/spec/spam_corpus/280.txt.gz +0 -0
  226. data/spec/spam_corpus/282.txt.gz +0 -0
  227. data/spec/spam_corpus/284.txt.gz +0 -0
  228. data/spec/spam_corpus/286.txt.gz +0 -0
  229. data/spec/spam_corpus/288.txt.gz +0 -0
  230. data/spec/spam_corpus/290.txt.gz +0 -0
  231. data/spec/spam_corpus/292.txt.gz +0 -0
  232. data/spec/spam_corpus/294.txt.gz +0 -0
  233. data/spec/spam_corpus/296.txt.gz +0 -0
  234. data/spec/spam_corpus/298.txt.gz +0 -0
  235. data/spec/spam_corpus/3.txt.gz +0 -0
  236. data/spec/spam_corpus/30.txt.gz +0 -0
  237. data/spec/spam_corpus/300.txt.gz +0 -0
  238. data/spec/spam_corpus/302.txt.gz +0 -0
  239. data/spec/spam_corpus/304.txt.gz +0 -0
  240. data/spec/spam_corpus/306.txt.gz +0 -0
  241. data/spec/spam_corpus/308.txt.gz +0 -0
  242. data/spec/spam_corpus/310.txt.gz +0 -0
  243. data/spec/spam_corpus/312.txt.gz +0 -0
  244. data/spec/spam_corpus/314.txt.gz +0 -0
  245. data/spec/spam_corpus/316.txt.gz +0 -0
  246. data/spec/spam_corpus/318.txt.gz +0 -0
  247. data/spec/spam_corpus/32.txt.gz +0 -0
  248. data/spec/spam_corpus/320.txt.gz +0 -0
  249. data/spec/spam_corpus/322.txt.gz +0 -0
  250. data/spec/spam_corpus/324.txt.gz +0 -0
  251. data/spec/spam_corpus/326.txt.gz +0 -0
  252. data/spec/spam_corpus/328.txt.gz +0 -0
  253. data/spec/spam_corpus/330.txt.gz +0 -0
  254. data/spec/spam_corpus/332.txt.gz +0 -0
  255. data/spec/spam_corpus/334.txt.gz +0 -0
  256. data/spec/spam_corpus/336.txt.gz +0 -0
  257. data/spec/spam_corpus/338.txt.gz +0 -0
  258. data/spec/spam_corpus/34.txt.gz +0 -0
  259. data/spec/spam_corpus/340.txt.gz +0 -0
  260. data/spec/spam_corpus/342.txt.gz +0 -0
  261. data/spec/spam_corpus/344.txt.gz +0 -0
  262. data/spec/spam_corpus/346.txt.gz +0 -0
  263. data/spec/spam_corpus/348.txt.gz +0 -0
  264. data/spec/spam_corpus/350.txt.gz +0 -0
  265. data/spec/spam_corpus/352.txt.gz +0 -0
  266. data/spec/spam_corpus/354.txt.gz +0 -0
  267. data/spec/spam_corpus/356.txt.gz +0 -0
  268. data/spec/spam_corpus/358.txt.gz +0 -0
  269. data/spec/spam_corpus/36.txt.gz +0 -0
  270. data/spec/spam_corpus/360.txt.gz +0 -0
  271. data/spec/spam_corpus/362.txt.gz +0 -0
  272. data/spec/spam_corpus/364.txt.gz +0 -0
  273. data/spec/spam_corpus/366.txt.gz +0 -0
  274. data/spec/spam_corpus/368.txt.gz +0 -0
  275. data/spec/spam_corpus/370.txt.gz +0 -0
  276. data/spec/spam_corpus/372.txt.gz +0 -0
  277. data/spec/spam_corpus/374.txt.gz +0 -0
  278. data/spec/spam_corpus/376.txt.gz +0 -0
  279. data/spec/spam_corpus/378.txt.gz +0 -0
  280. data/spec/spam_corpus/38.txt.gz +0 -0
  281. data/spec/spam_corpus/380.txt.gz +0 -0
  282. data/spec/spam_corpus/382.txt.gz +0 -0
  283. data/spec/spam_corpus/384.txt.gz +0 -0
  284. data/spec/spam_corpus/386.txt.gz +0 -0
  285. data/spec/spam_corpus/388.txt.gz +0 -0
  286. data/spec/spam_corpus/390.txt.gz +0 -0
  287. data/spec/spam_corpus/392.txt.gz +0 -0
  288. data/spec/spam_corpus/394.txt.gz +0 -0
  289. data/spec/spam_corpus/396.txt.gz +0 -0
  290. data/spec/spam_corpus/398.txt.gz +0 -0
  291. data/spec/spam_corpus/4.txt.gz +0 -0
  292. data/spec/spam_corpus/40.txt.gz +0 -0
  293. data/spec/spam_corpus/400.txt.gz +0 -0
  294. data/spec/spam_corpus/402.txt.gz +0 -0
  295. data/spec/spam_corpus/404.txt.gz +0 -0
  296. data/spec/spam_corpus/406.txt.gz +0 -0
  297. data/spec/spam_corpus/408.txt.gz +0 -0
  298. data/spec/spam_corpus/410.txt.gz +0 -0
  299. data/spec/spam_corpus/412.txt.gz +0 -0
  300. data/spec/spam_corpus/414.txt.gz +0 -0
  301. data/spec/spam_corpus/416.txt.gz +0 -0
  302. data/spec/spam_corpus/418.txt.gz +0 -0
  303. data/spec/spam_corpus/42.txt.gz +0 -0
  304. data/spec/spam_corpus/420.txt.gz +0 -0
  305. data/spec/spam_corpus/422.txt.gz +0 -0
  306. data/spec/spam_corpus/424.txt.gz +0 -0
  307. data/spec/spam_corpus/426.txt.gz +0 -0
  308. data/spec/spam_corpus/428.txt.gz +0 -0
  309. data/spec/spam_corpus/430.txt.gz +0 -0
  310. data/spec/spam_corpus/432.txt.gz +0 -0
  311. data/spec/spam_corpus/434.txt.gz +0 -0
  312. data/spec/spam_corpus/436.txt.gz +0 -0
  313. data/spec/spam_corpus/438.txt.gz +0 -0
  314. data/spec/spam_corpus/44.txt.gz +0 -0
  315. data/spec/spam_corpus/440.txt.gz +0 -0
  316. data/spec/spam_corpus/442.txt.gz +0 -0
  317. data/spec/spam_corpus/444.txt.gz +0 -0
  318. data/spec/spam_corpus/446.txt.gz +0 -0
  319. data/spec/spam_corpus/448.txt.gz +0 -0
  320. data/spec/spam_corpus/450.txt.gz +0 -0
  321. data/spec/spam_corpus/452.txt.gz +0 -0
  322. data/spec/spam_corpus/454.txt.gz +0 -0
  323. data/spec/spam_corpus/456.txt.gz +0 -0
  324. data/spec/spam_corpus/458.txt.gz +0 -0
  325. data/spec/spam_corpus/46.txt.gz +0 -0
  326. data/spec/spam_corpus/460.txt.gz +0 -0
  327. data/spec/spam_corpus/462.txt.gz +0 -0
  328. data/spec/spam_corpus/464.txt.gz +0 -0
  329. data/spec/spam_corpus/466.txt.gz +0 -0
  330. data/spec/spam_corpus/468.txt.gz +0 -0
  331. data/spec/spam_corpus/470.txt.gz +0 -0
  332. data/spec/spam_corpus/472.txt.gz +0 -0
  333. data/spec/spam_corpus/474.txt.gz +0 -0
  334. data/spec/spam_corpus/476.txt.gz +0 -0
  335. data/spec/spam_corpus/478.txt.gz +0 -0
  336. data/spec/spam_corpus/48.txt.gz +0 -0
  337. data/spec/spam_corpus/480.txt.gz +0 -0
  338. data/spec/spam_corpus/482.txt.gz +0 -0
  339. data/spec/spam_corpus/484.txt.gz +0 -0
  340. data/spec/spam_corpus/486.txt.gz +0 -0
  341. data/spec/spam_corpus/488.txt.gz +0 -0
  342. data/spec/spam_corpus/490.txt.gz +0 -0
  343. data/spec/spam_corpus/492.txt.gz +0 -0
  344. data/spec/spam_corpus/494.txt.gz +0 -0
  345. data/spec/spam_corpus/496.txt.gz +0 -0
  346. data/spec/spam_corpus/498.txt.gz +0 -0
  347. data/spec/spam_corpus/5.txt.gz +0 -0
  348. data/spec/spam_corpus/50.txt.gz +0 -0
  349. data/spec/spam_corpus/500.txt.gz +0 -0
  350. data/spec/spam_corpus/502.txt.gz +0 -0
  351. data/spec/spam_corpus/504.txt.gz +0 -0
  352. data/spec/spam_corpus/506.txt.gz +0 -0
  353. data/spec/spam_corpus/508.txt.gz +0 -0
  354. data/spec/spam_corpus/510.txt.gz +0 -0
  355. data/spec/spam_corpus/512.txt.gz +0 -0
  356. data/spec/spam_corpus/514.txt.gz +0 -0
  357. data/spec/spam_corpus/516.txt.gz +0 -0
  358. data/spec/spam_corpus/518.txt.gz +0 -0
  359. data/spec/spam_corpus/52.txt.gz +0 -0
  360. data/spec/spam_corpus/520.txt.gz +0 -0
  361. data/spec/spam_corpus/522.txt.gz +0 -0
  362. data/spec/spam_corpus/524.txt.gz +0 -0
  363. data/spec/spam_corpus/526.txt.gz +0 -0
  364. data/spec/spam_corpus/528.txt.gz +0 -0
  365. data/spec/spam_corpus/530.txt.gz +0 -0
  366. data/spec/spam_corpus/532.txt.gz +0 -0
  367. data/spec/spam_corpus/534.txt.gz +0 -0
  368. data/spec/spam_corpus/536.txt.gz +0 -0
  369. data/spec/spam_corpus/538.txt.gz +0 -0
  370. data/spec/spam_corpus/54.txt.gz +0 -0
  371. data/spec/spam_corpus/540.txt.gz +0 -0
  372. data/spec/spam_corpus/542.txt.gz +0 -0
  373. data/spec/spam_corpus/544.txt.gz +0 -0
  374. data/spec/spam_corpus/546.txt.gz +0 -0
  375. data/spec/spam_corpus/548.txt.gz +0 -0
  376. data/spec/spam_corpus/550.txt.gz +0 -0
  377. data/spec/spam_corpus/552.txt.gz +0 -0
  378. data/spec/spam_corpus/554.txt.gz +0 -0
  379. data/spec/spam_corpus/556.txt.gz +0 -0
  380. data/spec/spam_corpus/558.txt.gz +0 -0
  381. data/spec/spam_corpus/56.txt.gz +0 -0
  382. data/spec/spam_corpus/560.txt.gz +0 -0
  383. data/spec/spam_corpus/562.txt.gz +0 -0
  384. data/spec/spam_corpus/564.txt.gz +0 -0
  385. data/spec/spam_corpus/566.txt.gz +0 -0
  386. data/spec/spam_corpus/568.txt.gz +0 -0
  387. data/spec/spam_corpus/570.txt.gz +0 -0
  388. data/spec/spam_corpus/572.txt.gz +0 -0
  389. data/spec/spam_corpus/574.txt.gz +0 -0
  390. data/spec/spam_corpus/576.txt.gz +0 -0
  391. data/spec/spam_corpus/578.txt.gz +0 -0
  392. data/spec/spam_corpus/58.txt.gz +0 -0
  393. data/spec/spam_corpus/580.txt.gz +0 -0
  394. data/spec/spam_corpus/582.txt.gz +0 -0
  395. data/spec/spam_corpus/584.txt.gz +0 -0
  396. data/spec/spam_corpus/586.txt.gz +0 -0
  397. data/spec/spam_corpus/588.txt.gz +0 -0
  398. data/spec/spam_corpus/590.txt.gz +0 -0
  399. data/spec/spam_corpus/592.txt.gz +0 -0
  400. data/spec/spam_corpus/594.txt.gz +0 -0
  401. data/spec/spam_corpus/596.txt.gz +0 -0
  402. data/spec/spam_corpus/598.txt.gz +0 -0
  403. data/spec/spam_corpus/6.txt.gz +0 -0
  404. data/spec/spam_corpus/60.txt.gz +0 -0
  405. data/spec/spam_corpus/600.txt.gz +0 -0
  406. data/spec/spam_corpus/602.txt.gz +0 -0
  407. data/spec/spam_corpus/604.txt.gz +0 -0
  408. data/spec/spam_corpus/606.txt.gz +0 -0
  409. data/spec/spam_corpus/608.txt.gz +0 -0
  410. data/spec/spam_corpus/610.txt.gz +0 -0
  411. data/spec/spam_corpus/612.txt.gz +0 -0
  412. data/spec/spam_corpus/614.txt.gz +0 -0
  413. data/spec/spam_corpus/616.txt.gz +0 -0
  414. data/spec/spam_corpus/618.txt.gz +0 -0
  415. data/spec/spam_corpus/62.txt.gz +0 -0
  416. data/spec/spam_corpus/620.txt.gz +0 -0
  417. data/spec/spam_corpus/622.txt.gz +0 -0
  418. data/spec/spam_corpus/624.txt.gz +0 -0
  419. data/spec/spam_corpus/626.txt.gz +0 -0
  420. data/spec/spam_corpus/628.txt.gz +0 -0
  421. data/spec/spam_corpus/630.txt.gz +0 -0
  422. data/spec/spam_corpus/632.txt.gz +0 -0
  423. data/spec/spam_corpus/634.txt.gz +0 -0
  424. data/spec/spam_corpus/636.txt.gz +0 -0
  425. data/spec/spam_corpus/638.txt.gz +0 -0
  426. data/spec/spam_corpus/64.txt.gz +0 -0
  427. data/spec/spam_corpus/640.txt.gz +0 -0
  428. data/spec/spam_corpus/642.txt.gz +0 -0
  429. data/spec/spam_corpus/644.txt.gz +0 -0
  430. data/spec/spam_corpus/646.txt.gz +0 -0
  431. data/spec/spam_corpus/648.txt.gz +0 -0
  432. data/spec/spam_corpus/650.txt.gz +0 -0
  433. data/spec/spam_corpus/652.txt.gz +0 -0
  434. data/spec/spam_corpus/654.txt.gz +0 -0
  435. data/spec/spam_corpus/656.txt.gz +0 -0
  436. data/spec/spam_corpus/658.txt.gz +0 -0
  437. data/spec/spam_corpus/66.txt.gz +0 -0
  438. data/spec/spam_corpus/660.txt.gz +0 -0
  439. data/spec/spam_corpus/662.txt.gz +0 -0
  440. data/spec/spam_corpus/664.txt.gz +0 -0
  441. data/spec/spam_corpus/666.txt.gz +0 -0
  442. data/spec/spam_corpus/668.txt.gz +0 -0
  443. data/spec/spam_corpus/670.txt.gz +0 -0
  444. data/spec/spam_corpus/672.txt.gz +0 -0
  445. data/spec/spam_corpus/674.txt.gz +0 -0
  446. data/spec/spam_corpus/676.txt.gz +0 -0
  447. data/spec/spam_corpus/678.txt.gz +0 -0
  448. data/spec/spam_corpus/68.txt.gz +0 -0
  449. data/spec/spam_corpus/680.txt.gz +0 -0
  450. data/spec/spam_corpus/682.txt.gz +0 -0
  451. data/spec/spam_corpus/684.txt.gz +0 -0
  452. data/spec/spam_corpus/686.txt.gz +0 -0
  453. data/spec/spam_corpus/688.txt.gz +0 -0
  454. data/spec/spam_corpus/690.txt.gz +0 -0
  455. data/spec/spam_corpus/692.txt.gz +0 -0
  456. data/spec/spam_corpus/694.txt.gz +0 -0
  457. data/spec/spam_corpus/696.txt.gz +0 -0
  458. data/spec/spam_corpus/698.txt.gz +0 -0
  459. data/spec/spam_corpus/7.txt.gz +0 -0
  460. data/spec/spam_corpus/70.txt.gz +0 -0
  461. data/spec/spam_corpus/700.txt.gz +0 -0
  462. data/spec/spam_corpus/702.txt.gz +0 -0
  463. data/spec/spam_corpus/704.txt.gz +0 -0
  464. data/spec/spam_corpus/706.txt.gz +0 -0
  465. data/spec/spam_corpus/708.txt.gz +0 -0
  466. data/spec/spam_corpus/710.txt.gz +0 -0
  467. data/spec/spam_corpus/712.txt.gz +0 -0
  468. data/spec/spam_corpus/714.txt.gz +0 -0
  469. data/spec/spam_corpus/716.txt.gz +0 -0
  470. data/spec/spam_corpus/718.txt.gz +0 -0
  471. data/spec/spam_corpus/72.txt.gz +0 -0
  472. data/spec/spam_corpus/720.txt.gz +0 -0
  473. data/spec/spam_corpus/722.txt.gz +0 -0
  474. data/spec/spam_corpus/724.txt.gz +0 -0
  475. data/spec/spam_corpus/726.txt.gz +0 -0
  476. data/spec/spam_corpus/728.txt.gz +0 -0
  477. data/spec/spam_corpus/730.txt.gz +0 -0
  478. data/spec/spam_corpus/732.txt.gz +0 -0
  479. data/spec/spam_corpus/734.txt.gz +0 -0
  480. data/spec/spam_corpus/736.txt.gz +0 -0
  481. data/spec/spam_corpus/738.txt.gz +0 -0
  482. data/spec/spam_corpus/74.txt.gz +0 -0
  483. data/spec/spam_corpus/740.txt.gz +0 -0
  484. data/spec/spam_corpus/742.txt.gz +0 -0
  485. data/spec/spam_corpus/744.txt.gz +0 -0
  486. data/spec/spam_corpus/746.txt.gz +0 -0
  487. data/spec/spam_corpus/748.txt.gz +0 -0
  488. data/spec/spam_corpus/750.txt.gz +0 -0
  489. data/spec/spam_corpus/752.txt.gz +0 -0
  490. data/spec/spam_corpus/754.txt.gz +0 -0
  491. data/spec/spam_corpus/756.txt.gz +0 -0
  492. data/spec/spam_corpus/758.txt.gz +0 -0
  493. data/spec/spam_corpus/76.txt.gz +0 -0
  494. data/spec/spam_corpus/760.txt.gz +0 -0
  495. data/spec/spam_corpus/762.txt.gz +0 -0
  496. data/spec/spam_corpus/764.txt.gz +0 -0
  497. data/spec/spam_corpus/766.txt.gz +0 -0
  498. data/spec/spam_corpus/768.txt.gz +0 -0
  499. data/spec/spam_corpus/770.txt.gz +0 -0
  500. data/spec/spam_corpus/772.txt.gz +0 -0
  501. data/spec/spam_corpus/774.txt.gz +0 -0
  502. data/spec/spam_corpus/776.txt.gz +0 -0
  503. data/spec/spam_corpus/778.txt.gz +0 -0
  504. data/spec/spam_corpus/78.txt.gz +0 -0
  505. data/spec/spam_corpus/780.txt.gz +0 -0
  506. data/spec/spam_corpus/782.txt.gz +0 -0
  507. data/spec/spam_corpus/784.txt.gz +0 -0
  508. data/spec/spam_corpus/786.txt.gz +0 -0
  509. data/spec/spam_corpus/788.txt.gz +0 -0
  510. data/spec/spam_corpus/790.txt.gz +0 -0
  511. data/spec/spam_corpus/792.txt.gz +0 -0
  512. data/spec/spam_corpus/794.txt.gz +0 -0
  513. data/spec/spam_corpus/796.txt.gz +0 -0
  514. data/spec/spam_corpus/798.txt.gz +0 -0
  515. data/spec/spam_corpus/8.txt.gz +0 -0
  516. data/spec/spam_corpus/80.txt.gz +0 -0
  517. data/spec/spam_corpus/800.txt.gz +0 -0
  518. data/spec/spam_corpus/802.txt.gz +0 -0
  519. data/spec/spam_corpus/804.txt.gz +0 -0
  520. data/spec/spam_corpus/806.txt.gz +0 -0
  521. data/spec/spam_corpus/808.txt.gz +0 -0
  522. data/spec/spam_corpus/810.txt.gz +0 -0
  523. data/spec/spam_corpus/812.txt.gz +0 -0
  524. data/spec/spam_corpus/814.txt.gz +0 -0
  525. data/spec/spam_corpus/816.txt.gz +0 -0
  526. data/spec/spam_corpus/818.txt.gz +0 -0
  527. data/spec/spam_corpus/82.txt.gz +0 -0
  528. data/spec/spam_corpus/820.txt.gz +0 -0
  529. data/spec/spam_corpus/822.txt.gz +0 -0
  530. data/spec/spam_corpus/824.txt.gz +0 -0
  531. data/spec/spam_corpus/826.txt.gz +0 -0
  532. data/spec/spam_corpus/828.txt.gz +0 -0
  533. data/spec/spam_corpus/830.txt.gz +0 -0
  534. data/spec/spam_corpus/832.txt.gz +0 -0
  535. data/spec/spam_corpus/834.txt.gz +0 -0
  536. data/spec/spam_corpus/836.txt.gz +0 -0
  537. data/spec/spam_corpus/838.txt.gz +0 -0
  538. data/spec/spam_corpus/84.txt.gz +0 -0
  539. data/spec/spam_corpus/840.txt.gz +0 -0
  540. data/spec/spam_corpus/842.txt.gz +0 -0
  541. data/spec/spam_corpus/844.txt.gz +0 -0
  542. data/spec/spam_corpus/846.txt.gz +0 -0
  543. data/spec/spam_corpus/848.txt.gz +0 -0
  544. data/spec/spam_corpus/850.txt.gz +0 -0
  545. data/spec/spam_corpus/852.txt.gz +0 -0
  546. data/spec/spam_corpus/854.txt.gz +0 -0
  547. data/spec/spam_corpus/856.txt.gz +0 -0
  548. data/spec/spam_corpus/858.txt.gz +0 -0
  549. data/spec/spam_corpus/86.txt.gz +0 -0
  550. data/spec/spam_corpus/860.txt.gz +0 -0
  551. data/spec/spam_corpus/862.txt.gz +0 -0
  552. data/spec/spam_corpus/864.txt.gz +0 -0
  553. data/spec/spam_corpus/866.txt.gz +0 -0
  554. data/spec/spam_corpus/868.txt.gz +0 -0
  555. data/spec/spam_corpus/870.txt.gz +0 -0
  556. data/spec/spam_corpus/872.txt.gz +0 -0
  557. data/spec/spam_corpus/874.txt.gz +0 -0
  558. data/spec/spam_corpus/876.txt.gz +0 -0
  559. data/spec/spam_corpus/878.txt.gz +0 -0
  560. data/spec/spam_corpus/88.txt.gz +0 -0
  561. data/spec/spam_corpus/880.txt.gz +0 -0
  562. data/spec/spam_corpus/882.txt.gz +0 -0
  563. data/spec/spam_corpus/884.txt.gz +0 -0
  564. data/spec/spam_corpus/886.txt.gz +0 -0
  565. data/spec/spam_corpus/888.txt.gz +0 -0
  566. data/spec/spam_corpus/890.txt.gz +0 -0
  567. data/spec/spam_corpus/892.txt.gz +0 -0
  568. data/spec/spam_corpus/894.txt.gz +0 -0
  569. data/spec/spam_corpus/896.txt.gz +0 -0
  570. data/spec/spam_corpus/898.txt.gz +0 -0
  571. data/spec/spam_corpus/9.txt.gz +0 -0
  572. data/spec/spam_corpus/90.txt.gz +0 -0
  573. data/spec/spam_corpus/900.txt.gz +0 -0
  574. data/spec/spam_corpus/902.txt.gz +0 -0
  575. data/spec/spam_corpus/904.txt.gz +0 -0
  576. data/spec/spam_corpus/906.txt.gz +0 -0
  577. data/spec/spam_corpus/908.txt.gz +0 -0
  578. data/spec/spam_corpus/910.txt.gz +0 -0
  579. data/spec/spam_corpus/912.txt.gz +0 -0
  580. data/spec/spam_corpus/914.txt.gz +0 -0
  581. data/spec/spam_corpus/916.txt.gz +0 -0
  582. data/spec/spam_corpus/918.txt.gz +0 -0
  583. data/spec/spam_corpus/92.txt.gz +0 -0
  584. data/spec/spam_corpus/920.txt.gz +0 -0
  585. data/spec/spam_corpus/922.txt.gz +0 -0
  586. data/spec/spam_corpus/924.txt.gz +0 -0
  587. data/spec/spam_corpus/926.txt.gz +0 -0
  588. data/spec/spam_corpus/928.txt.gz +0 -0
  589. data/spec/spam_corpus/930.txt.gz +0 -0
  590. data/spec/spam_corpus/932.txt.gz +0 -0
  591. data/spec/spam_corpus/934.txt.gz +0 -0
  592. data/spec/spam_corpus/936.txt.gz +0 -0
  593. data/spec/spam_corpus/938.txt.gz +0 -0
  594. data/spec/spam_corpus/94.txt.gz +0 -0
  595. data/spec/spam_corpus/940.txt.gz +0 -0
  596. data/spec/spam_corpus/942.txt.gz +0 -0
  597. data/spec/spam_corpus/944.txt.gz +0 -0
  598. data/spec/spam_corpus/946.txt.gz +0 -0
  599. data/spec/spam_corpus/948.txt.gz +0 -0
  600. data/spec/spam_corpus/950.txt.gz +0 -0
  601. data/spec/spam_corpus/952.txt.gz +0 -0
  602. data/spec/spam_corpus/954.txt.gz +0 -0
  603. data/spec/spam_corpus/956.txt.gz +0 -0
  604. data/spec/spam_corpus/958.txt.gz +0 -0
  605. data/spec/spam_corpus/96.txt.gz +0 -0
  606. data/spec/spam_corpus/960.txt.gz +0 -0
  607. data/spec/spam_corpus/962.txt.gz +0 -0
  608. data/spec/spam_corpus/964.txt.gz +0 -0
  609. data/spec/spam_corpus/966.txt.gz +0 -0
  610. data/spec/spam_corpus/968.txt.gz +0 -0
  611. data/spec/spam_corpus/970.txt.gz +0 -0
  612. data/spec/spam_corpus/972.txt.gz +0 -0
  613. data/spec/spam_corpus/974.txt.gz +0 -0
  614. data/spec/spam_corpus/98.txt.gz +0 -0
  615. data/spec/spam_corpus/debugyouradd.com.txt.gz +0 -0
  616. data/spec/spam_corpus/humandesignconsulting.comm.txt.gz +0 -0
  617. data/spec/spam_corpus_spec.rb +11 -0
  618. data/spec/spec_helper.rb +6 -0
  619. metadata +617 -5
@@ -0,0 +1,39 @@
1
+ # -*- encoding: utf-8 -*-
2
+
3
+ Gem::Specification.new do |s|
4
+ s.name = %q{despamilator}
5
+ s.version = "0.4"
6
+
7
+ s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
8
+ s.authors = ["Stephen Hardisty"]
9
+ s.date = %q{2010-08-31}
10
+ s.description = %q{Despamilator is a plugin based spam detector designed for use on your web forms borne out of two annoyances:
11
+ Spam being submitted in my web forms and CAPTCHAS being intrusive. Despamilator will apply
12
+ some commonly used heuristics from the world of anti-spam to help you decide whether your users are human or machine.}
13
+ s.email = ["moowahaha@hotmail.com"]
14
+ s.extra_rdoc_files = ["History.txt", "Manifest.txt", "PostInstall.txt"]
15
+ s.files = ["History.txt", "Manifest.txt", "PostInstall.txt", "README.rdoc", "Rakefile", "despamilator.gemspec", "despamliator.gemspec", "lib/despamilator.rb", "lib/despamilator/filter.rb", "lib/despamilator/filter/funky_consonant.rb", "lib/despamilator/filter/html_tags.rb", "lib/despamilator/filter/ip_address_url.rb", "lib/despamilator/filter/long_words.rb", "lib/despamilator/filter/naughty_q.rb", "lib/despamilator/filter/naughty_words.rb", "lib/despamilator/filter/numbers_and_words.rb", "lib/despamilator/filter/script_tag.rb", "lib/despamilator/filter/shouting.rb", "lib/despamilator/filter/square_brackets.rb", "lib/despamilator/filter/urls.rb", "lib/despamilator/filter_base.rb", "scripts/despamilator_score.rb", "spec/clean_corpus/101.txt.gz", "spec/clean_corpus/103.txt.gz", "spec/clean_corpus/105.txt.gz", "spec/clean_corpus/107.txt.gz", "spec/clean_corpus/109.txt.gz", "spec/clean_corpus/111.txt.gz", "spec/clean_corpus/113.txt.gz", "spec/clean_corpus/115.txt.gz", "spec/clean_corpus/117.txt.gz", "spec/clean_corpus/119.txt.gz", "spec/clean_corpus/121.txt.gz", "spec/clean_corpus/123.txt.gz", "spec/clean_corpus/125.txt.gz", "spec/clean_corpus/127.txt.gz", "spec/clean_corpus/129.txt.gz", "spec/clean_corpus/131.txt.gz", "spec/clean_corpus/133.txt.gz", "spec/clean_corpus/135.txt.gz", "spec/clean_corpus/137.txt.gz", "spec/clean_corpus/139.txt.gz", "spec/clean_corpus/141.txt.gz", "spec/clean_corpus/143.txt.gz", "spec/clean_corpus/145.txt.gz", "spec/clean_corpus/147.txt.gz", "spec/clean_corpus/149.txt.gz", "spec/clean_corpus/151.txt.gz", "spec/clean_corpus/153.txt.gz", "spec/clean_corpus/155.txt.gz", "spec/clean_corpus/157.txt.gz", "spec/clean_corpus/159.txt.gz", "spec/clean_corpus/161.txt.gz", "spec/clean_corpus/163.txt.gz", "spec/clean_corpus/165.txt.gz", "spec/clean_corpus/167.txt.gz", "spec/clean_corpus/169.txt.gz", "spec/clean_corpus/171.txt.gz", "spec/clean_corpus/173.txt.gz", "spec/clean_corpus/175.txt.gz", "spec/clean_corpus/177.txt.gz", "spec/clean_corpus/179.txt.gz", "spec/clean_corpus/18.txt.gz", "spec/clean_corpus/181.txt.gz", "spec/clean_corpus/183.txt.gz", "spec/clean_corpus/185.txt.gz", "spec/clean_corpus/187.txt.gz", "spec/clean_corpus/189.txt.gz", "spec/clean_corpus/191.txt.gz", "spec/clean_corpus/193.txt.gz", "spec/clean_corpus/195.txt.gz", "spec/clean_corpus/197.txt.gz", "spec/clean_corpus/199.txt.gz", "spec/clean_corpus/20.txt.gz", "spec/clean_corpus/201.txt.gz", "spec/clean_corpus/203.txt.gz", "spec/clean_corpus/205.txt.gz", "spec/clean_corpus/207.txt.gz", "spec/clean_corpus/209.txt.gz", "spec/clean_corpus/211.txt.gz", "spec/clean_corpus/213.txt.gz", "spec/clean_corpus/215.txt.gz", "spec/clean_corpus/217.txt.gz", "spec/clean_corpus/219.txt.gz", "spec/clean_corpus/22.txt.gz", "spec/clean_corpus/221.txt.gz", "spec/clean_corpus/223.txt.gz", "spec/clean_corpus/225.txt.gz", "spec/clean_corpus/24.txt.gz", "spec/clean_corpus/26.txt.gz", "spec/clean_corpus/27.txt.gz", "spec/clean_corpus/29.txt.gz", "spec/clean_corpus/31.txt.gz", "spec/clean_corpus/33.txt.gz", "spec/clean_corpus/35.txt.gz", "spec/clean_corpus/37.txt.gz", "spec/clean_corpus/39.txt.gz", "spec/clean_corpus/41.txt.gz", "spec/clean_corpus/43.txt.gz", "spec/clean_corpus/45.txt.gz", "spec/clean_corpus/47.txt.gz", "spec/clean_corpus/49.txt.gz", "spec/clean_corpus/51.txt.gz", "spec/clean_corpus/53.txt.gz", "spec/clean_corpus/55.txt.gz", "spec/clean_corpus/57.txt.gz", "spec/clean_corpus/59.txt.gz", "spec/clean_corpus/61.txt.gz", "spec/clean_corpus/63.txt.gz", "spec/clean_corpus/65.txt.gz", "spec/clean_corpus/67.txt.gz", "spec/clean_corpus/69.txt.gz", "spec/clean_corpus/71.txt.gz", "spec/clean_corpus/73.txt.gz", "spec/clean_corpus/75.txt.gz", "spec/clean_corpus/77.txt.gz", "spec/clean_corpus/79.txt.gz", "spec/clean_corpus/81.txt.gz", "spec/clean_corpus/83.txt.gz", "spec/clean_corpus/85.txt.gz", "spec/clean_corpus/87.txt.gz", "spec/clean_corpus/89.txt.gz", "spec/clean_corpus/91.txt.gz", "spec/clean_corpus/93.txt.gz", "spec/clean_corpus/95.txt.gz", "spec/clean_corpus/97.txt.gz", "spec/clean_corpus/99.txt.gz", "spec/clean_corpus_spec.rb", "spec/despamilator_spec.rb", "spec/filters/funky_consonant_spec.rb", "spec/filters/html_tags_spec.rb", "spec/filters/ip_address_url_spec.rb", "spec/filters/long_words_spec.rb", "spec/filters/naughty_q_spec.rb", "spec/filters/naughty_words_spec.rb", "spec/filters/numbers_and_words_spec.rb", "spec/filters/script_tag_spec.rb", "spec/filters/shouting_spec.rb", "spec/filters/square_brackets_spec.rb", "spec/filters/urls_spec.rb", "spec/spam_corpus/0.txt.gz", "spec/spam_corpus/1.txt.gz", "spec/spam_corpus/10.txt.gz", "spec/spam_corpus/100.txt.gz", "spec/spam_corpus/102.txt.gz", "spec/spam_corpus/104.txt.gz", "spec/spam_corpus/106.txt.gz", "spec/spam_corpus/108.txt.gz", "spec/spam_corpus/11.txt.gz", "spec/spam_corpus/110.txt.gz", "spec/spam_corpus/112.txt.gz", "spec/spam_corpus/114.txt.gz", "spec/spam_corpus/116.txt.gz", "spec/spam_corpus/118.txt.gz", "spec/spam_corpus/12.txt.gz", "spec/spam_corpus/120.txt.gz", "spec/spam_corpus/122.txt.gz", "spec/spam_corpus/124.txt.gz", "spec/spam_corpus/126.txt.gz", "spec/spam_corpus/128.txt.gz", "spec/spam_corpus/13.txt.gz", "spec/spam_corpus/130.txt.gz", "spec/spam_corpus/132.txt.gz", "spec/spam_corpus/134.txt.gz", "spec/spam_corpus/136.txt.gz", "spec/spam_corpus/138.txt.gz", "spec/spam_corpus/14.txt.gz", "spec/spam_corpus/140.txt.gz", "spec/spam_corpus/142.txt.gz", "spec/spam_corpus/144.txt.gz", "spec/spam_corpus/146.txt.gz", "spec/spam_corpus/148.txt.gz", "spec/spam_corpus/15.txt.gz", "spec/spam_corpus/150.txt.gz", "spec/spam_corpus/152.txt.gz", "spec/spam_corpus/154.txt.gz", "spec/spam_corpus/156.txt.gz", "spec/spam_corpus/158.txt.gz", "spec/spam_corpus/16.txt.gz", "spec/spam_corpus/160.txt.gz", "spec/spam_corpus/162.txt.gz", "spec/spam_corpus/164.txt.gz", "spec/spam_corpus/166.txt.gz", "spec/spam_corpus/168.txt.gz", "spec/spam_corpus/170.txt.gz", "spec/spam_corpus/172.txt.gz", "spec/spam_corpus/174.txt.gz", "spec/spam_corpus/176.txt.gz", "spec/spam_corpus/178.txt.gz", "spec/spam_corpus/180.txt.gz", "spec/spam_corpus/182.txt.gz", "spec/spam_corpus/184.txt.gz", "spec/spam_corpus/186.txt.gz", "spec/spam_corpus/188.txt.gz", "spec/spam_corpus/190.txt.gz", "spec/spam_corpus/192.txt.gz", "spec/spam_corpus/194.txt.gz", "spec/spam_corpus/196.txt.gz", "spec/spam_corpus/198.txt.gz", "spec/spam_corpus/2.txt.gz", "spec/spam_corpus/200.txt.gz", "spec/spam_corpus/202.txt.gz", "spec/spam_corpus/204.txt.gz", "spec/spam_corpus/206.txt.gz", "spec/spam_corpus/208.txt.gz", "spec/spam_corpus/210.txt.gz", "spec/spam_corpus/212.txt.gz", "spec/spam_corpus/214.txt.gz", "spec/spam_corpus/216.txt.gz", "spec/spam_corpus/218.txt.gz", "spec/spam_corpus/220.txt.gz", "spec/spam_corpus/222.txt.gz", "spec/spam_corpus/224.txt.gz", "spec/spam_corpus/226.txt.gz", "spec/spam_corpus/228.txt.gz", "spec/spam_corpus/230.txt.gz", "spec/spam_corpus/232.txt.gz", "spec/spam_corpus/234.txt.gz", "spec/spam_corpus/236.txt.gz", "spec/spam_corpus/238.txt.gz", "spec/spam_corpus/240.txt.gz", "spec/spam_corpus/242.txt.gz", "spec/spam_corpus/244.txt.gz", "spec/spam_corpus/246.txt.gz", "spec/spam_corpus/248.txt.gz", "spec/spam_corpus/250.txt.gz", "spec/spam_corpus/252.txt.gz", "spec/spam_corpus/254.txt.gz", "spec/spam_corpus/256.txt.gz", "spec/spam_corpus/258.txt.gz", "spec/spam_corpus/260.txt.gz", "spec/spam_corpus/262.txt.gz", "spec/spam_corpus/264.txt.gz", "spec/spam_corpus/266.txt.gz", "spec/spam_corpus/268.txt.gz", "spec/spam_corpus/270.txt.gz", "spec/spam_corpus/272.txt.gz", "spec/spam_corpus/274.txt.gz", "spec/spam_corpus/276.txt.gz", "spec/spam_corpus/278.txt.gz", "spec/spam_corpus/28.txt.gz", "spec/spam_corpus/280.txt.gz", "spec/spam_corpus/282.txt.gz", "spec/spam_corpus/284.txt.gz", "spec/spam_corpus/286.txt.gz", "spec/spam_corpus/288.txt.gz", "spec/spam_corpus/290.txt.gz", "spec/spam_corpus/292.txt.gz", "spec/spam_corpus/294.txt.gz", "spec/spam_corpus/296.txt.gz", "spec/spam_corpus/298.txt.gz", "spec/spam_corpus/3.txt.gz", "spec/spam_corpus/30.txt.gz", "spec/spam_corpus/300.txt.gz", "spec/spam_corpus/302.txt.gz", "spec/spam_corpus/304.txt.gz", "spec/spam_corpus/306.txt.gz", "spec/spam_corpus/308.txt.gz", "spec/spam_corpus/310.txt.gz", "spec/spam_corpus/312.txt.gz", "spec/spam_corpus/314.txt.gz", "spec/spam_corpus/316.txt.gz", "spec/spam_corpus/318.txt.gz", "spec/spam_corpus/32.txt.gz", "spec/spam_corpus/320.txt.gz", "spec/spam_corpus/322.txt.gz", "spec/spam_corpus/324.txt.gz", "spec/spam_corpus/326.txt.gz", "spec/spam_corpus/328.txt.gz", "spec/spam_corpus/330.txt.gz", "spec/spam_corpus/332.txt.gz", "spec/spam_corpus/334.txt.gz", "spec/spam_corpus/336.txt.gz", "spec/spam_corpus/338.txt.gz", "spec/spam_corpus/34.txt.gz", "spec/spam_corpus/340.txt.gz", "spec/spam_corpus/342.txt.gz", "spec/spam_corpus/344.txt.gz", "spec/spam_corpus/346.txt.gz", "spec/spam_corpus/348.txt.gz", "spec/spam_corpus/350.txt.gz", "spec/spam_corpus/352.txt.gz", "spec/spam_corpus/354.txt.gz", "spec/spam_corpus/356.txt.gz", "spec/spam_corpus/358.txt.gz", "spec/spam_corpus/36.txt.gz", "spec/spam_corpus/360.txt.gz", "spec/spam_corpus/362.txt.gz", "spec/spam_corpus/364.txt.gz", "spec/spam_corpus/366.txt.gz", "spec/spam_corpus/368.txt.gz", "spec/spam_corpus/370.txt.gz", "spec/spam_corpus/372.txt.gz", "spec/spam_corpus/374.txt.gz", "spec/spam_corpus/376.txt.gz", "spec/spam_corpus/378.txt.gz", "spec/spam_corpus/38.txt.gz", "spec/spam_corpus/380.txt.gz", "spec/spam_corpus/382.txt.gz", "spec/spam_corpus/384.txt.gz", "spec/spam_corpus/386.txt.gz", "spec/spam_corpus/388.txt.gz", "spec/spam_corpus/390.txt.gz", "spec/spam_corpus/392.txt.gz", "spec/spam_corpus/394.txt.gz", "spec/spam_corpus/396.txt.gz", "spec/spam_corpus/398.txt.gz", "spec/spam_corpus/4.txt.gz", "spec/spam_corpus/40.txt.gz", "spec/spam_corpus/400.txt.gz", "spec/spam_corpus/402.txt.gz", "spec/spam_corpus/404.txt.gz", "spec/spam_corpus/406.txt.gz", "spec/spam_corpus/408.txt.gz", "spec/spam_corpus/410.txt.gz", "spec/spam_corpus/412.txt.gz", "spec/spam_corpus/414.txt.gz", "spec/spam_corpus/416.txt.gz", "spec/spam_corpus/418.txt.gz", "spec/spam_corpus/42.txt.gz", "spec/spam_corpus/420.txt.gz", "spec/spam_corpus/422.txt.gz", "spec/spam_corpus/424.txt.gz", "spec/spam_corpus/426.txt.gz", "spec/spam_corpus/428.txt.gz", "spec/spam_corpus/430.txt.gz", "spec/spam_corpus/432.txt.gz", "spec/spam_corpus/434.txt.gz", "spec/spam_corpus/436.txt.gz", "spec/spam_corpus/438.txt.gz", "spec/spam_corpus/44.txt.gz", "spec/spam_corpus/440.txt.gz", "spec/spam_corpus/442.txt.gz", "spec/spam_corpus/444.txt.gz", "spec/spam_corpus/446.txt.gz", "spec/spam_corpus/448.txt.gz", "spec/spam_corpus/450.txt.gz", "spec/spam_corpus/452.txt.gz", "spec/spam_corpus/454.txt.gz", "spec/spam_corpus/456.txt.gz", "spec/spam_corpus/458.txt.gz", "spec/spam_corpus/46.txt.gz", "spec/spam_corpus/460.txt.gz", "spec/spam_corpus/462.txt.gz", "spec/spam_corpus/464.txt.gz", "spec/spam_corpus/466.txt.gz", "spec/spam_corpus/468.txt.gz", "spec/spam_corpus/470.txt.gz", "spec/spam_corpus/472.txt.gz", "spec/spam_corpus/474.txt.gz", "spec/spam_corpus/476.txt.gz", "spec/spam_corpus/478.txt.gz", "spec/spam_corpus/48.txt.gz", "spec/spam_corpus/480.txt.gz", "spec/spam_corpus/482.txt.gz", "spec/spam_corpus/484.txt.gz", "spec/spam_corpus/486.txt.gz", "spec/spam_corpus/488.txt.gz", "spec/spam_corpus/490.txt.gz", "spec/spam_corpus/492.txt.gz", "spec/spam_corpus/494.txt.gz", "spec/spam_corpus/496.txt.gz", "spec/spam_corpus/498.txt.gz", "spec/spam_corpus/5.txt.gz", "spec/spam_corpus/50.txt.gz", "spec/spam_corpus/500.txt.gz", "spec/spam_corpus/502.txt.gz", "spec/spam_corpus/504.txt.gz", "spec/spam_corpus/506.txt.gz", "spec/spam_corpus/508.txt.gz", "spec/spam_corpus/510.txt.gz", "spec/spam_corpus/512.txt.gz", "spec/spam_corpus/514.txt.gz", "spec/spam_corpus/516.txt.gz", "spec/spam_corpus/518.txt.gz", "spec/spam_corpus/52.txt.gz", "spec/spam_corpus/520.txt.gz", "spec/spam_corpus/522.txt.gz", "spec/spam_corpus/524.txt.gz", "spec/spam_corpus/526.txt.gz", "spec/spam_corpus/528.txt.gz", "spec/spam_corpus/530.txt.gz", "spec/spam_corpus/532.txt.gz", "spec/spam_corpus/534.txt.gz", "spec/spam_corpus/536.txt.gz", "spec/spam_corpus/538.txt.gz", "spec/spam_corpus/54.txt.gz", "spec/spam_corpus/540.txt.gz", "spec/spam_corpus/542.txt.gz", "spec/spam_corpus/544.txt.gz", "spec/spam_corpus/546.txt.gz", "spec/spam_corpus/548.txt.gz", "spec/spam_corpus/550.txt.gz", "spec/spam_corpus/552.txt.gz", "spec/spam_corpus/554.txt.gz", "spec/spam_corpus/556.txt.gz", "spec/spam_corpus/558.txt.gz", "spec/spam_corpus/56.txt.gz", "spec/spam_corpus/560.txt.gz", "spec/spam_corpus/562.txt.gz", "spec/spam_corpus/564.txt.gz", "spec/spam_corpus/566.txt.gz", "spec/spam_corpus/568.txt.gz", "spec/spam_corpus/570.txt.gz", "spec/spam_corpus/572.txt.gz", "spec/spam_corpus/574.txt.gz", "spec/spam_corpus/576.txt.gz", "spec/spam_corpus/578.txt.gz", "spec/spam_corpus/58.txt.gz", "spec/spam_corpus/580.txt.gz", "spec/spam_corpus/582.txt.gz", "spec/spam_corpus/584.txt.gz", "spec/spam_corpus/586.txt.gz", "spec/spam_corpus/588.txt.gz", "spec/spam_corpus/590.txt.gz", "spec/spam_corpus/592.txt.gz", "spec/spam_corpus/594.txt.gz", "spec/spam_corpus/596.txt.gz", "spec/spam_corpus/598.txt.gz", "spec/spam_corpus/6.txt.gz", "spec/spam_corpus/60.txt.gz", "spec/spam_corpus/600.txt.gz", "spec/spam_corpus/602.txt.gz", "spec/spam_corpus/604.txt.gz", "spec/spam_corpus/606.txt.gz", "spec/spam_corpus/608.txt.gz", "spec/spam_corpus/610.txt.gz", "spec/spam_corpus/612.txt.gz", "spec/spam_corpus/614.txt.gz", "spec/spam_corpus/616.txt.gz", "spec/spam_corpus/618.txt.gz", "spec/spam_corpus/62.txt.gz", "spec/spam_corpus/620.txt.gz", "spec/spam_corpus/622.txt.gz", "spec/spam_corpus/624.txt.gz", "spec/spam_corpus/626.txt.gz", "spec/spam_corpus/628.txt.gz", "spec/spam_corpus/630.txt.gz", "spec/spam_corpus/632.txt.gz", "spec/spam_corpus/634.txt.gz", "spec/spam_corpus/636.txt.gz", "spec/spam_corpus/638.txt.gz", "spec/spam_corpus/64.txt.gz", "spec/spam_corpus/640.txt.gz", "spec/spam_corpus/642.txt.gz", "spec/spam_corpus/644.txt.gz", "spec/spam_corpus/646.txt.gz", "spec/spam_corpus/648.txt.gz", "spec/spam_corpus/650.txt.gz", "spec/spam_corpus/652.txt.gz", "spec/spam_corpus/654.txt.gz", "spec/spam_corpus/656.txt.gz", "spec/spam_corpus/658.txt.gz", "spec/spam_corpus/66.txt.gz", "spec/spam_corpus/660.txt.gz", "spec/spam_corpus/662.txt.gz", "spec/spam_corpus/664.txt.gz", "spec/spam_corpus/666.txt.gz", "spec/spam_corpus/668.txt.gz", "spec/spam_corpus/670.txt.gz", "spec/spam_corpus/672.txt.gz", "spec/spam_corpus/674.txt.gz", "spec/spam_corpus/676.txt.gz", "spec/spam_corpus/678.txt.gz", "spec/spam_corpus/68.txt.gz", "spec/spam_corpus/680.txt.gz", "spec/spam_corpus/682.txt.gz", "spec/spam_corpus/684.txt.gz", "spec/spam_corpus/686.txt.gz", "spec/spam_corpus/688.txt.gz", "spec/spam_corpus/690.txt.gz", "spec/spam_corpus/692.txt.gz", "spec/spam_corpus/694.txt.gz", "spec/spam_corpus/696.txt.gz", "spec/spam_corpus/698.txt.gz", "spec/spam_corpus/7.txt.gz", "spec/spam_corpus/70.txt.gz", "spec/spam_corpus/700.txt.gz", "spec/spam_corpus/702.txt.gz", "spec/spam_corpus/704.txt.gz", "spec/spam_corpus/706.txt.gz", "spec/spam_corpus/708.txt.gz", "spec/spam_corpus/710.txt.gz", "spec/spam_corpus/712.txt.gz", "spec/spam_corpus/714.txt.gz", "spec/spam_corpus/716.txt.gz", "spec/spam_corpus/718.txt.gz", "spec/spam_corpus/72.txt.gz", "spec/spam_corpus/720.txt.gz", "spec/spam_corpus/722.txt.gz", "spec/spam_corpus/724.txt.gz", "spec/spam_corpus/726.txt.gz", "spec/spam_corpus/728.txt.gz", "spec/spam_corpus/730.txt.gz", "spec/spam_corpus/732.txt.gz", "spec/spam_corpus/734.txt.gz", "spec/spam_corpus/736.txt.gz", "spec/spam_corpus/738.txt.gz", "spec/spam_corpus/74.txt.gz", "spec/spam_corpus/740.txt.gz", "spec/spam_corpus/742.txt.gz", "spec/spam_corpus/744.txt.gz", "spec/spam_corpus/746.txt.gz", "spec/spam_corpus/748.txt.gz", "spec/spam_corpus/750.txt.gz", "spec/spam_corpus/752.txt.gz", "spec/spam_corpus/754.txt.gz", "spec/spam_corpus/756.txt.gz", "spec/spam_corpus/758.txt.gz", "spec/spam_corpus/76.txt.gz", "spec/spam_corpus/760.txt.gz", "spec/spam_corpus/762.txt.gz", "spec/spam_corpus/764.txt.gz", "spec/spam_corpus/766.txt.gz", "spec/spam_corpus/768.txt.gz", "spec/spam_corpus/770.txt.gz", "spec/spam_corpus/772.txt.gz", "spec/spam_corpus/774.txt.gz", "spec/spam_corpus/776.txt.gz", "spec/spam_corpus/778.txt.gz", "spec/spam_corpus/78.txt.gz", "spec/spam_corpus/780.txt.gz", "spec/spam_corpus/782.txt.gz", "spec/spam_corpus/784.txt.gz", "spec/spam_corpus/786.txt.gz", "spec/spam_corpus/788.txt.gz", "spec/spam_corpus/790.txt.gz", "spec/spam_corpus/792.txt.gz", "spec/spam_corpus/794.txt.gz", "spec/spam_corpus/796.txt.gz", "spec/spam_corpus/798.txt.gz", "spec/spam_corpus/8.txt.gz", "spec/spam_corpus/80.txt.gz", "spec/spam_corpus/800.txt.gz", "spec/spam_corpus/802.txt.gz", "spec/spam_corpus/804.txt.gz", "spec/spam_corpus/806.txt.gz", "spec/spam_corpus/808.txt.gz", "spec/spam_corpus/810.txt.gz", "spec/spam_corpus/812.txt.gz", "spec/spam_corpus/814.txt.gz", "spec/spam_corpus/816.txt.gz", "spec/spam_corpus/818.txt.gz", "spec/spam_corpus/82.txt.gz", "spec/spam_corpus/820.txt.gz", "spec/spam_corpus/822.txt.gz", "spec/spam_corpus/824.txt.gz", "spec/spam_corpus/826.txt.gz", "spec/spam_corpus/828.txt.gz", "spec/spam_corpus/830.txt.gz", "spec/spam_corpus/832.txt.gz", "spec/spam_corpus/834.txt.gz", "spec/spam_corpus/836.txt.gz", "spec/spam_corpus/838.txt.gz", "spec/spam_corpus/84.txt.gz", "spec/spam_corpus/840.txt.gz", "spec/spam_corpus/842.txt.gz", "spec/spam_corpus/844.txt.gz", "spec/spam_corpus/846.txt.gz", "spec/spam_corpus/848.txt.gz", "spec/spam_corpus/850.txt.gz", "spec/spam_corpus/852.txt.gz", "spec/spam_corpus/854.txt.gz", "spec/spam_corpus/856.txt.gz", "spec/spam_corpus/858.txt.gz", "spec/spam_corpus/86.txt.gz", "spec/spam_corpus/860.txt.gz", "spec/spam_corpus/862.txt.gz", "spec/spam_corpus/864.txt.gz", "spec/spam_corpus/866.txt.gz", "spec/spam_corpus/868.txt.gz", "spec/spam_corpus/870.txt.gz", "spec/spam_corpus/872.txt.gz", "spec/spam_corpus/874.txt.gz", "spec/spam_corpus/876.txt.gz", "spec/spam_corpus/878.txt.gz", "spec/spam_corpus/88.txt.gz", "spec/spam_corpus/880.txt.gz", "spec/spam_corpus/882.txt.gz", "spec/spam_corpus/884.txt.gz", "spec/spam_corpus/886.txt.gz", "spec/spam_corpus/888.txt.gz", "spec/spam_corpus/890.txt.gz", "spec/spam_corpus/892.txt.gz", "spec/spam_corpus/894.txt.gz", "spec/spam_corpus/896.txt.gz", "spec/spam_corpus/898.txt.gz", "spec/spam_corpus/9.txt.gz", "spec/spam_corpus/90.txt.gz", "spec/spam_corpus/900.txt.gz", "spec/spam_corpus/902.txt.gz", "spec/spam_corpus/904.txt.gz", "spec/spam_corpus/906.txt.gz", "spec/spam_corpus/908.txt.gz", "spec/spam_corpus/910.txt.gz", "spec/spam_corpus/912.txt.gz", "spec/spam_corpus/914.txt.gz", "spec/spam_corpus/916.txt.gz", "spec/spam_corpus/918.txt.gz", "spec/spam_corpus/92.txt.gz", "spec/spam_corpus/920.txt.gz", "spec/spam_corpus/922.txt.gz", "spec/spam_corpus/924.txt.gz", "spec/spam_corpus/926.txt.gz", "spec/spam_corpus/928.txt.gz", "spec/spam_corpus/930.txt.gz", "spec/spam_corpus/932.txt.gz", "spec/spam_corpus/934.txt.gz", "spec/spam_corpus/936.txt.gz", "spec/spam_corpus/938.txt.gz", "spec/spam_corpus/94.txt.gz", "spec/spam_corpus/940.txt.gz", "spec/spam_corpus/942.txt.gz", "spec/spam_corpus/944.txt.gz", "spec/spam_corpus/946.txt.gz", "spec/spam_corpus/948.txt.gz", "spec/spam_corpus/950.txt.gz", "spec/spam_corpus/952.txt.gz", "spec/spam_corpus/954.txt.gz", "spec/spam_corpus/956.txt.gz", "spec/spam_corpus/958.txt.gz", "spec/spam_corpus/96.txt.gz", "spec/spam_corpus/960.txt.gz", "spec/spam_corpus/962.txt.gz", "spec/spam_corpus/964.txt.gz", "spec/spam_corpus/966.txt.gz", "spec/spam_corpus/968.txt.gz", "spec/spam_corpus/970.txt.gz", "spec/spam_corpus/972.txt.gz", "spec/spam_corpus/974.txt.gz", "spec/spam_corpus/98.txt.gz", "spec/spam_corpus/debugyouradd.com.txt.gz", "spec/spam_corpus/humandesignconsulting.comm.txt.gz", "spec/spam_corpus_spec.rb", "spec/spec.opts", "spec/spec_helper.rb", "tasks/rspec.rake"]
16
+ s.homepage = %q{http://github.com/moowahaha/despamliator}
17
+ s.post_install_message = %q{PostInstall.txt}
18
+ s.rdoc_options = ["--main", "README.rdoc"]
19
+ s.require_paths = ["lib"]
20
+ s.rubyforge_project = %q{despamilator}
21
+ s.rubygems_version = %q{1.3.6}
22
+ s.summary = %q{Despamilator is a plugin based spam detector designed for use on your web forms borne out of two annoyances: Spam being submitted in my web forms and CAPTCHAS being intrusive}
23
+
24
+ if s.respond_to? :specification_version then
25
+ current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
26
+ s.specification_version = 3
27
+
28
+ if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
29
+ s.add_development_dependency(%q<rubyforge>, [">= 2.0.4"])
30
+ s.add_development_dependency(%q<hoe>, [">= 2.6.1"])
31
+ else
32
+ s.add_dependency(%q<rubyforge>, [">= 2.0.4"])
33
+ s.add_dependency(%q<hoe>, [">= 2.6.1"])
34
+ end
35
+ else
36
+ s.add_dependency(%q<rubyforge>, [">= 2.0.4"])
37
+ s.add_dependency(%q<hoe>, [">= 2.6.1"])
38
+ end
39
+ end
@@ -0,0 +1,21 @@
1
+ def name
2
+ 'Funky Consonant'
3
+ end
4
+
5
+ def description
6
+ 'Detects and scores each occurrence of a consonant next to an unlikely character'
7
+ end
8
+
9
+ def parse
10
+ text = self.text.downcase
11
+
12
+ consonant_pairs.each do |pair|
13
+ [pair, pair.reverse].each do |combo_pair|
14
+ self.append_score = 0.05 unless text.scan(/#{combo_pair}/).empty?
15
+ end
16
+ end
17
+ end
18
+
19
+ def consonant_pairs
20
+ %w{ zt gb vk vt jk mj dm jm }
21
+ end
@@ -0,0 +1,13 @@
1
+ def name
2
+ 'Long Words'
3
+ end
4
+
5
+ def description
6
+ 'Detects long and unbroken strings'
7
+ end
8
+
9
+ def parse
10
+ self.text.split(/\W+/).each do |word|
11
+ self.append_score = 0.1 if word.length > 20
12
+ end
13
+ end
@@ -7,12 +7,15 @@ def description
7
7
  end
8
8
 
9
9
  def parse
10
- matches = self.text.downcase.scan(/q(\w|\d)/)
10
+ post_matches = self.text.downcase.scan(/q(\w|\d)/)
11
+ pre_matches = self.text.downcase.scan(/(\w|\d)q/)
12
+
13
+ matches = post_matches + pre_matches
11
14
 
12
15
  return unless matches
13
16
 
14
17
  matches.each do |match|
15
18
  match = match.first
16
- self.append_score = 0.2 unless match == 'u' or match == 'a'
19
+ self.append_score = 0.2 unless match == 'u' or match == 'a' or match == 'k'
17
20
  end
18
21
  end
@@ -0,0 +1,28 @@
1
+ def name
2
+ 'Naughty Words'
3
+ end
4
+
5
+ def description
6
+ 'Detects cheeky words'
7
+ end
8
+
9
+ def parse
10
+ text = self.text.downcase
11
+
12
+ naughty_words.each do |word|
13
+ self.append_score = 0.1 if text =~ /\b#{word}\b/
14
+ end
15
+ end
16
+
17
+ def naughty_words
18
+ %w{
19
+ penis
20
+ viagra
21
+ bondage
22
+ cunt
23
+ fuck
24
+ shit
25
+ dick
26
+ tits
27
+ }
28
+ end
@@ -0,0 +1,13 @@
1
+ def name
2
+ 'Square Brackets'
3
+ end
4
+
5
+ def description
6
+ 'Detects each square bracket in a string'
7
+ end
8
+
9
+ def parse
10
+ self.text.downcase.scan(/(\[|\])/).each do |match|
11
+ self.append_score = 0.05
12
+ end
13
+ end
@@ -0,0 +1,11 @@
1
+ def name
2
+ 'URLs'
3
+ end
4
+
5
+ def description
6
+ 'Detects each url in a string'
7
+ end
8
+
9
+ def parse
10
+ self.append_score = 0.15 * self.text.downcase.scan(/http:\/\//).length
11
+ end
data/lib/despamilator.rb CHANGED
@@ -3,7 +3,7 @@ $:.unshift(File.dirname(__FILE__)) unless $:.include?(File.dirname(__FILE__)) ||
3
3
  require 'despamilator/filter'
4
4
 
5
5
  class Despamilator
6
- VERSION = "0.3"
6
+ VERSION = "0.4"
7
7
 
8
8
  def initialize text
9
9
  @filters = Despamilator::Filter.new text
@@ -0,0 +1,25 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require File.join(File.dirname(__FILE__), '..', 'lib', 'despamilator')
4
+ require 'zlib'
5
+
6
+ file = ARGV[0] || raise("Usage: despamilator_spec.rb [filename]")
7
+
8
+ text = file =~ /\.gz$/i ? Zlib::GzipReader.open(file).read : File.open(file).read
9
+
10
+ puts "Testing:"
11
+ puts "========================"
12
+ puts text
13
+ puts "========================"
14
+ puts "\n"
15
+
16
+ dspam = Despamilator.new(text)
17
+
18
+ puts "Total Score: #{dspam.score}\n\n"
19
+
20
+ puts "Matched by..." unless dspam.matched_by.empty?
21
+ dspam.matched_by.each do |match|
22
+ puts "\tFilter: #{match.name}"
23
+ puts "\tScore: #{match.score}"
24
+ puts "\n"
25
+ end
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
@@ -0,0 +1,11 @@
1
+ require File.dirname(__FILE__) + '/spec_helper.rb'
2
+
3
+ describe Despamilator do
4
+
5
+ Dir.glob(File.join(File.dirname(__FILE__), 'clean_corpus', '*.txt.gz')).each do |sample|
6
+ it "should give #{sample} a score less than 1" do
7
+ Despamilator.new(unzip_file(sample)).score.should < 1
8
+ end
9
+ end
10
+
11
+ end
@@ -0,0 +1,39 @@
1
+ require File.dirname(__FILE__) + '/../spec_helper.rb'
2
+
3
+ describe "FunkyConsonant" do
4
+ it "should return a score for 1 misplaced z" do
5
+ dspam = Despamilator.new('zt')
6
+ dspam.score.should == 0.05
7
+ end
8
+
9
+ describe 'attributes' do
10
+ before :each do
11
+ @filter = Despamilator.new('vtjk').matched_by.first
12
+ end
13
+
14
+ it "should have a filename" do
15
+ @filter.filename.should == 'funky_consonant.rb'
16
+ end
17
+
18
+ it "should have a name" do
19
+ @filter.name.should == 'Funky Consonant'
20
+ end
21
+
22
+ it "should have a description" do
23
+ @filter.description.should == 'Detects and scores each occurrence of a consonant next to an unlikely character'
24
+ end
25
+
26
+ it "should have a number of matches" do
27
+ @filter.matches.should == 2
28
+ end
29
+
30
+ it "should have a score" do
31
+ @filter.score.should == 0.1
32
+ end
33
+ end
34
+
35
+ it "should score more for 3 misplaced q's" do
36
+ dspam = Despamilator.new('ztgb')
37
+ dspam.score.to_s.should == 0.1.to_s
38
+ end
39
+ end
@@ -0,0 +1,34 @@
1
+ require File.dirname(__FILE__) + '/../spec_helper.rb'
2
+
3
+ describe "LongWords" do
4
+ it "should return a score for 1 long word" do
5
+ dspam = Despamilator.new('honorificabilitudinitatibus')
6
+ dspam.score.should == 0.1
7
+ end
8
+
9
+ describe 'attributes' do
10
+ before :each do
11
+ @filter = Despamilator.new('honorificabilitudinitatibus antidisestablishmentarianism').matched_by.first
12
+ end
13
+
14
+ it "should have a filename" do
15
+ @filter.filename.should == 'long_words.rb'
16
+ end
17
+
18
+ it "should have a name" do
19
+ @filter.name.should == 'Long Words'
20
+ end
21
+
22
+ it "should have a description" do
23
+ @filter.description.should == 'Detects long and unbroken strings'
24
+ end
25
+
26
+ it "should have a number of matches" do
27
+ @filter.matches.should == 2
28
+ end
29
+
30
+ it "should have a score" do
31
+ @filter.score.to_s.should == 0.2.to_s
32
+ end
33
+ end
34
+ end