biblicit 1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (322) hide show
  1. data/.gitignore +3 -0
  2. data/.rspec +1 -0
  3. data/Gemfile +6 -0
  4. data/LICENSE.TXT +176 -0
  5. data/README.md +120 -0
  6. data/Rakefile +8 -0
  7. data/biblicit.gemspec +33 -0
  8. data/lib/biblicit/cb2bib.rb +83 -0
  9. data/lib/biblicit/citeseer.rb +53 -0
  10. data/lib/biblicit/extractor.rb +37 -0
  11. data/lib/biblicit.rb +6 -0
  12. data/perl/DocFilter/lib/CSXUtil/SafeText.pm +140 -0
  13. data/perl/DocFilter/lib/DocFilter/Config.pm +35 -0
  14. data/perl/DocFilter/lib/DocFilter/Filter.pm +51 -0
  15. data/perl/FileConversionService/README.TXT +11 -0
  16. data/perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar +0 -0
  17. data/perl/FileConversionService/lib/CSXUtil/SafeText.pm +140 -0
  18. data/perl/FileConversionService/lib/FileConverter/CheckSum.pm +77 -0
  19. data/perl/FileConversionService/lib/FileConverter/Compression.pm +137 -0
  20. data/perl/FileConversionService/lib/FileConverter/Config.pm +57 -0
  21. data/perl/FileConversionService/lib/FileConverter/Controller.pm +191 -0
  22. data/perl/FileConversionService/lib/FileConverter/JODConverter.pm +61 -0
  23. data/perl/FileConversionService/lib/FileConverter/PDFBox.pm +69 -0
  24. data/perl/FileConversionService/lib/FileConverter/PSConverter.pm +69 -0
  25. data/perl/FileConversionService/lib/FileConverter/PSToText.pm +88 -0
  26. data/perl/FileConversionService/lib/FileConverter/Prescript.pm +68 -0
  27. data/perl/FileConversionService/lib/FileConverter/TET.pm +75 -0
  28. data/perl/FileConversionService/lib/FileConverter/Utils.pm +130 -0
  29. data/perl/HeaderParseService/README.TXT +80 -0
  30. data/perl/HeaderParseService/lib/CSXUtil/SafeText.pm +140 -0
  31. data/perl/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm +968 -0
  32. data/perl/HeaderParseService/lib/HeaderParse/API/Function.pm +2016 -0
  33. data/perl/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm +444 -0
  34. data/perl/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm +409 -0
  35. data/perl/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm +537 -0
  36. data/perl/HeaderParseService/lib/HeaderParse/API/Parser.pm +68 -0
  37. data/perl/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm +1880 -0
  38. data/perl/HeaderParseService/lib/HeaderParse/Config/API_Config.pm +46 -0
  39. data/perl/HeaderParseService/resources/data/EbizHeaders.txt +24330 -0
  40. data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed +27506 -0
  41. data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old +26495 -0
  42. data/perl/HeaderParseService/resources/data/tagged_headers.txt +40668 -0
  43. data/perl/HeaderParseService/resources/data/test_header.txt +31 -0
  44. data/perl/HeaderParseService/resources/data/test_header.txt.parsed +31 -0
  45. data/perl/HeaderParseService/resources/database/50states +60 -0
  46. data/perl/HeaderParseService/resources/database/AddrTopWords.txt +17 -0
  47. data/perl/HeaderParseService/resources/database/AffiTopWords.txt +35 -0
  48. data/perl/HeaderParseService/resources/database/AffiTopWordsAll.txt +533 -0
  49. data/perl/HeaderParseService/resources/database/ChineseSurNames.txt +276 -0
  50. data/perl/HeaderParseService/resources/database/Csurnames.bin +0 -0
  51. data/perl/HeaderParseService/resources/database/Csurnames_spec.bin +0 -0
  52. data/perl/HeaderParseService/resources/database/DomainSuffixes.txt +242 -0
  53. data/perl/HeaderParseService/resources/database/LabeledHeader +18 -0
  54. data/perl/HeaderParseService/resources/database/README +2 -0
  55. data/perl/HeaderParseService/resources/database/TrainMulClassLines +254 -0
  56. data/perl/HeaderParseService/resources/database/TrainMulClassLines1 +510 -0
  57. data/perl/HeaderParseService/resources/database/abstract.txt +1 -0
  58. data/perl/HeaderParseService/resources/database/abstractTopWords +9 -0
  59. data/perl/HeaderParseService/resources/database/addr.txt +28 -0
  60. data/perl/HeaderParseService/resources/database/affi.txt +34 -0
  61. data/perl/HeaderParseService/resources/database/affis.bin +0 -0
  62. data/perl/HeaderParseService/resources/database/all_namewords_spec.bin +0 -0
  63. data/perl/HeaderParseService/resources/database/allnamewords.bin +0 -0
  64. data/perl/HeaderParseService/resources/database/cities_US.txt +4512 -0
  65. data/perl/HeaderParseService/resources/database/cities_world.txt +4463 -0
  66. data/perl/HeaderParseService/resources/database/city.txt +3150 -0
  67. data/perl/HeaderParseService/resources/database/cityname.txt +3151 -0
  68. data/perl/HeaderParseService/resources/database/country_abbr.txt +243 -0
  69. data/perl/HeaderParseService/resources/database/countryname.txt +262 -0
  70. data/perl/HeaderParseService/resources/database/dateTopWords +30 -0
  71. data/perl/HeaderParseService/resources/database/degree.txt +67 -0
  72. data/perl/HeaderParseService/resources/database/email.txt +3 -0
  73. data/perl/HeaderParseService/resources/database/excludeWords.txt +40 -0
  74. data/perl/HeaderParseService/resources/database/female-names +4960 -0
  75. data/perl/HeaderParseService/resources/database/firstNames.txt +8448 -0
  76. data/perl/HeaderParseService/resources/database/firstnames.bin +0 -0
  77. data/perl/HeaderParseService/resources/database/firstnames_spec.bin +0 -0
  78. data/perl/HeaderParseService/resources/database/intro.txt +2 -0
  79. data/perl/HeaderParseService/resources/database/keyword.txt +5 -0
  80. data/perl/HeaderParseService/resources/database/keywordTopWords +7 -0
  81. data/perl/HeaderParseService/resources/database/male-names +3906 -0
  82. data/perl/HeaderParseService/resources/database/middleNames.txt +2 -0
  83. data/perl/HeaderParseService/resources/database/month.txt +35 -0
  84. data/perl/HeaderParseService/resources/database/mul +868 -0
  85. data/perl/HeaderParseService/resources/database/mul.label +869 -0
  86. data/perl/HeaderParseService/resources/database/mul.label.old +869 -0
  87. data/perl/HeaderParseService/resources/database/mul.processed +762 -0
  88. data/perl/HeaderParseService/resources/database/mulAuthor +619 -0
  89. data/perl/HeaderParseService/resources/database/mulClassStat +45 -0
  90. data/perl/HeaderParseService/resources/database/nickname.txt +58 -0
  91. data/perl/HeaderParseService/resources/database/nicknames.bin +0 -0
  92. data/perl/HeaderParseService/resources/database/note.txt +121 -0
  93. data/perl/HeaderParseService/resources/database/page.txt +1 -0
  94. data/perl/HeaderParseService/resources/database/phone.txt +9 -0
  95. data/perl/HeaderParseService/resources/database/postcode.txt +54 -0
  96. data/perl/HeaderParseService/resources/database/pubnum.txt +45 -0
  97. data/perl/HeaderParseService/resources/database/statename.bin +0 -0
  98. data/perl/HeaderParseService/resources/database/statename.txt +73 -0
  99. data/perl/HeaderParseService/resources/database/states_and_abbreviations.txt +118 -0
  100. data/perl/HeaderParseService/resources/database/stopwords +438 -0
  101. data/perl/HeaderParseService/resources/database/stopwords.bin +0 -0
  102. data/perl/HeaderParseService/resources/database/surNames.txt +19613 -0
  103. data/perl/HeaderParseService/resources/database/surnames.bin +0 -0
  104. data/perl/HeaderParseService/resources/database/surnames_spec.bin +0 -0
  105. data/perl/HeaderParseService/resources/database/university_list/A.html +167 -0
  106. data/perl/HeaderParseService/resources/database/university_list/B.html +161 -0
  107. data/perl/HeaderParseService/resources/database/university_list/C.html +288 -0
  108. data/perl/HeaderParseService/resources/database/university_list/D.html +115 -0
  109. data/perl/HeaderParseService/resources/database/university_list/E.html +147 -0
  110. data/perl/HeaderParseService/resources/database/university_list/F.html +112 -0
  111. data/perl/HeaderParseService/resources/database/university_list/G.html +115 -0
  112. data/perl/HeaderParseService/resources/database/university_list/H.html +140 -0
  113. data/perl/HeaderParseService/resources/database/university_list/I.html +138 -0
  114. data/perl/HeaderParseService/resources/database/university_list/J.html +82 -0
  115. data/perl/HeaderParseService/resources/database/university_list/K.html +115 -0
  116. data/perl/HeaderParseService/resources/database/university_list/L.html +131 -0
  117. data/perl/HeaderParseService/resources/database/university_list/M.html +201 -0
  118. data/perl/HeaderParseService/resources/database/university_list/N.html +204 -0
  119. data/perl/HeaderParseService/resources/database/university_list/O.html +89 -0
  120. data/perl/HeaderParseService/resources/database/university_list/P.html +125 -0
  121. data/perl/HeaderParseService/resources/database/university_list/Q.html +49 -0
  122. data/perl/HeaderParseService/resources/database/university_list/R.html +126 -0
  123. data/perl/HeaderParseService/resources/database/university_list/S.html +296 -0
  124. data/perl/HeaderParseService/resources/database/university_list/T.html +156 -0
  125. data/perl/HeaderParseService/resources/database/university_list/U.html +800 -0
  126. data/perl/HeaderParseService/resources/database/university_list/V.html +75 -0
  127. data/perl/HeaderParseService/resources/database/university_list/W.html +144 -0
  128. data/perl/HeaderParseService/resources/database/university_list/WCSelect.gif +0 -0
  129. data/perl/HeaderParseService/resources/database/university_list/X.html +44 -0
  130. data/perl/HeaderParseService/resources/database/university_list/Y.html +53 -0
  131. data/perl/HeaderParseService/resources/database/university_list/Z.html +43 -0
  132. data/perl/HeaderParseService/resources/database/university_list/ae.html +31 -0
  133. data/perl/HeaderParseService/resources/database/university_list/am.html +30 -0
  134. data/perl/HeaderParseService/resources/database/university_list/ar.html +35 -0
  135. data/perl/HeaderParseService/resources/database/university_list/at.html +43 -0
  136. data/perl/HeaderParseService/resources/database/university_list/au.html +82 -0
  137. data/perl/HeaderParseService/resources/database/university_list/bd.html +28 -0
  138. data/perl/HeaderParseService/resources/database/university_list/be.html +41 -0
  139. data/perl/HeaderParseService/resources/database/university_list/bg.html +28 -0
  140. data/perl/HeaderParseService/resources/database/university_list/bh.html +28 -0
  141. data/perl/HeaderParseService/resources/database/university_list/blueribbon.gif +0 -0
  142. data/perl/HeaderParseService/resources/database/university_list/bm.html +28 -0
  143. data/perl/HeaderParseService/resources/database/university_list/bn.html +28 -0
  144. data/perl/HeaderParseService/resources/database/university_list/br.html +66 -0
  145. data/perl/HeaderParseService/resources/database/university_list/ca.html +174 -0
  146. data/perl/HeaderParseService/resources/database/university_list/ch.html +52 -0
  147. data/perl/HeaderParseService/resources/database/university_list/cl.html +40 -0
  148. data/perl/HeaderParseService/resources/database/university_list/cn.html +87 -0
  149. data/perl/HeaderParseService/resources/database/university_list/co.html +39 -0
  150. data/perl/HeaderParseService/resources/database/university_list/cr.html +34 -0
  151. data/perl/HeaderParseService/resources/database/university_list/cy.html +34 -0
  152. data/perl/HeaderParseService/resources/database/university_list/cz.html +44 -0
  153. data/perl/HeaderParseService/resources/database/university_list/de.html +128 -0
  154. data/perl/HeaderParseService/resources/database/university_list/dean-mainlink.jpg +0 -0
  155. data/perl/HeaderParseService/resources/database/university_list/dk.html +42 -0
  156. data/perl/HeaderParseService/resources/database/university_list/ec.html +31 -0
  157. data/perl/HeaderParseService/resources/database/university_list/ee.html +30 -0
  158. data/perl/HeaderParseService/resources/database/university_list/eg.html +29 -0
  159. data/perl/HeaderParseService/resources/database/university_list/es.html +68 -0
  160. data/perl/HeaderParseService/resources/database/university_list/et.html +28 -0
  161. data/perl/HeaderParseService/resources/database/university_list/faq.html +147 -0
  162. data/perl/HeaderParseService/resources/database/university_list/fi.html +49 -0
  163. data/perl/HeaderParseService/resources/database/university_list/fj.html +28 -0
  164. data/perl/HeaderParseService/resources/database/university_list/fo.html +28 -0
  165. data/perl/HeaderParseService/resources/database/university_list/fr.html +106 -0
  166. data/perl/HeaderParseService/resources/database/university_list/geog.html +150 -0
  167. data/perl/HeaderParseService/resources/database/university_list/gr.html +38 -0
  168. data/perl/HeaderParseService/resources/database/university_list/gu.html +28 -0
  169. data/perl/HeaderParseService/resources/database/university_list/hk.html +34 -0
  170. data/perl/HeaderParseService/resources/database/university_list/hr.html +28 -0
  171. data/perl/HeaderParseService/resources/database/university_list/hu.html +46 -0
  172. data/perl/HeaderParseService/resources/database/university_list/id.html +29 -0
  173. data/perl/HeaderParseService/resources/database/university_list/ie.html +49 -0
  174. data/perl/HeaderParseService/resources/database/university_list/il.html +35 -0
  175. data/perl/HeaderParseService/resources/database/university_list/in.html +109 -0
  176. data/perl/HeaderParseService/resources/database/university_list/is.html +32 -0
  177. data/perl/HeaderParseService/resources/database/university_list/it.html +75 -0
  178. data/perl/HeaderParseService/resources/database/university_list/jm.html +28 -0
  179. data/perl/HeaderParseService/resources/database/university_list/jo.html +28 -0
  180. data/perl/HeaderParseService/resources/database/university_list/jp.html +155 -0
  181. data/perl/HeaderParseService/resources/database/university_list/kaplan.gif +0 -0
  182. data/perl/HeaderParseService/resources/database/university_list/kr.html +65 -0
  183. data/perl/HeaderParseService/resources/database/university_list/kw.html +28 -0
  184. data/perl/HeaderParseService/resources/database/university_list/lb.html +28 -0
  185. data/perl/HeaderParseService/resources/database/university_list/linkbw2.gif +0 -0
  186. data/perl/HeaderParseService/resources/database/university_list/lk.html +30 -0
  187. data/perl/HeaderParseService/resources/database/university_list/lt.html +31 -0
  188. data/perl/HeaderParseService/resources/database/university_list/lu.html +34 -0
  189. data/perl/HeaderParseService/resources/database/university_list/lv.html +30 -0
  190. data/perl/HeaderParseService/resources/database/university_list/ma.html +28 -0
  191. data/perl/HeaderParseService/resources/database/university_list/maczynski.gif +0 -0
  192. data/perl/HeaderParseService/resources/database/university_list/mirror.tar +0 -0
  193. data/perl/HeaderParseService/resources/database/university_list/mk.html +29 -0
  194. data/perl/HeaderParseService/resources/database/university_list/mo.html +29 -0
  195. data/perl/HeaderParseService/resources/database/university_list/mseawdm.gif +0 -0
  196. data/perl/HeaderParseService/resources/database/university_list/mt.html +28 -0
  197. data/perl/HeaderParseService/resources/database/university_list/mx.html +68 -0
  198. data/perl/HeaderParseService/resources/database/university_list/my.html +39 -0
  199. data/perl/HeaderParseService/resources/database/university_list/ni.html +28 -0
  200. data/perl/HeaderParseService/resources/database/university_list/nl.html +51 -0
  201. data/perl/HeaderParseService/resources/database/university_list/no.html +56 -0
  202. data/perl/HeaderParseService/resources/database/university_list/nz.html +41 -0
  203. data/perl/HeaderParseService/resources/database/university_list/pa.html +31 -0
  204. data/perl/HeaderParseService/resources/database/university_list/pe.html +40 -0
  205. data/perl/HeaderParseService/resources/database/university_list/ph.html +41 -0
  206. data/perl/HeaderParseService/resources/database/university_list/pl.html +51 -0
  207. data/perl/HeaderParseService/resources/database/university_list/pointcom.gif +0 -0
  208. data/perl/HeaderParseService/resources/database/university_list/pr.html +31 -0
  209. data/perl/HeaderParseService/resources/database/university_list/ps.html +28 -0
  210. data/perl/HeaderParseService/resources/database/university_list/pt.html +45 -0
  211. data/perl/HeaderParseService/resources/database/university_list/recognition.html +69 -0
  212. data/perl/HeaderParseService/resources/database/university_list/results.html +71 -0
  213. data/perl/HeaderParseService/resources/database/university_list/ro.html +38 -0
  214. data/perl/HeaderParseService/resources/database/university_list/ru.html +48 -0
  215. data/perl/HeaderParseService/resources/database/university_list/sd.html +28 -0
  216. data/perl/HeaderParseService/resources/database/university_list/se.html +57 -0
  217. data/perl/HeaderParseService/resources/database/university_list/sg.html +33 -0
  218. data/perl/HeaderParseService/resources/database/university_list/si.html +30 -0
  219. data/perl/HeaderParseService/resources/database/university_list/sk.html +35 -0
  220. data/perl/HeaderParseService/resources/database/university_list/th.html +45 -0
  221. data/perl/HeaderParseService/resources/database/university_list/tr.html +44 -0
  222. data/perl/HeaderParseService/resources/database/university_list/tw.html +76 -0
  223. data/perl/HeaderParseService/resources/database/university_list/ua.html +29 -0
  224. data/perl/HeaderParseService/resources/database/university_list/uk.html +168 -0
  225. data/perl/HeaderParseService/resources/database/university_list/univ-full.html +3166 -0
  226. data/perl/HeaderParseService/resources/database/university_list/univ.html +122 -0
  227. data/perl/HeaderParseService/resources/database/university_list/uy.html +31 -0
  228. data/perl/HeaderParseService/resources/database/university_list/ve.html +34 -0
  229. data/perl/HeaderParseService/resources/database/university_list/yu.html +28 -0
  230. data/perl/HeaderParseService/resources/database/university_list/za.html +46 -0
  231. data/perl/HeaderParseService/resources/database/university_list/zm.html +28 -0
  232. data/perl/HeaderParseService/resources/database/university_list.txt +3025 -0
  233. data/perl/HeaderParseService/resources/database/url.txt +1 -0
  234. data/perl/HeaderParseService/resources/database/webTopWords +225 -0
  235. data/perl/HeaderParseService/resources/database/words +45402 -0
  236. data/perl/HeaderParseService/resources/models/10ContextModelfold1 +369 -0
  237. data/perl/HeaderParseService/resources/models/10Modelfold1 +376 -0
  238. data/perl/HeaderParseService/resources/models/11ContextModelfold1 +400 -0
  239. data/perl/HeaderParseService/resources/models/11Modelfold1 +526 -0
  240. data/perl/HeaderParseService/resources/models/12ContextModelfold1 +510 -0
  241. data/perl/HeaderParseService/resources/models/12Modelfold1 +423 -0
  242. data/perl/HeaderParseService/resources/models/13ContextModelfold1 +364 -0
  243. data/perl/HeaderParseService/resources/models/13Modelfold1 +677 -0
  244. data/perl/HeaderParseService/resources/models/14ContextModelfold1 +459 -0
  245. data/perl/HeaderParseService/resources/models/14Modelfold1 +325 -0
  246. data/perl/HeaderParseService/resources/models/15ContextModelfold1 +340 -0
  247. data/perl/HeaderParseService/resources/models/15Modelfold1 +390 -0
  248. data/perl/HeaderParseService/resources/models/1ContextModelfold1 +668 -0
  249. data/perl/HeaderParseService/resources/models/1Modelfold1 +1147 -0
  250. data/perl/HeaderParseService/resources/models/2ContextModelfold1 +755 -0
  251. data/perl/HeaderParseService/resources/models/2Modelfold1 +796 -0
  252. data/perl/HeaderParseService/resources/models/3ContextModelfold1 +1299 -0
  253. data/perl/HeaderParseService/resources/models/3Modelfold1 +1360 -0
  254. data/perl/HeaderParseService/resources/models/4ContextModelfold1 +1062 -0
  255. data/perl/HeaderParseService/resources/models/4Modelfold1 +993 -0
  256. data/perl/HeaderParseService/resources/models/5ContextModelfold1 +1339 -0
  257. data/perl/HeaderParseService/resources/models/5Modelfold1 +2098 -0
  258. data/perl/HeaderParseService/resources/models/6ContextModelfold1 +888 -0
  259. data/perl/HeaderParseService/resources/models/6Modelfold1 +620 -0
  260. data/perl/HeaderParseService/resources/models/7ContextModelfold1 +257 -0
  261. data/perl/HeaderParseService/resources/models/7Modelfold1 +228 -0
  262. data/perl/HeaderParseService/resources/models/8ContextModelfold1 +677 -0
  263. data/perl/HeaderParseService/resources/models/8Modelfold1 +1871 -0
  264. data/perl/HeaderParseService/resources/models/9ContextModelfold1 +198 -0
  265. data/perl/HeaderParseService/resources/models/9Modelfold1 +170 -0
  266. data/perl/HeaderParseService/resources/models/NameSpaceModel +181 -0
  267. data/perl/HeaderParseService/resources/models/NameSpaceTrainF +347 -0
  268. data/perl/HeaderParseService/resources/models/WrapperBaseFeaDict +13460 -0
  269. data/perl/HeaderParseService/resources/models/WrapperContextFeaDict +14045 -0
  270. data/perl/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict +510 -0
  271. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1 +23 -0
  272. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10 +23 -0
  273. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11 +23 -0
  274. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12 +23 -0
  275. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13 +23 -0
  276. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14 +23 -0
  277. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15 +23 -0
  278. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2 +23 -0
  279. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3 +23 -0
  280. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4 +23 -0
  281. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5 +23 -0
  282. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6 +23 -0
  283. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7 +23 -0
  284. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8 +23 -0
  285. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9 +23 -0
  286. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1 +23 -0
  287. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10 +23 -0
  288. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11 +23 -0
  289. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12 +23 -0
  290. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13 +23 -0
  291. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14 +23 -0
  292. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15 +23 -0
  293. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2 +23 -0
  294. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3 +23 -0
  295. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4 +23 -0
  296. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5 +23 -0
  297. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6 +23 -0
  298. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7 +23 -0
  299. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8 +23 -0
  300. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9 +23 -0
  301. data/perl/ParsCit/README.TXT +82 -0
  302. data/perl/ParsCit/crfpp/traindata/parsCit.template +60 -0
  303. data/perl/ParsCit/crfpp/traindata/parsCit.train.data +12104 -0
  304. data/perl/ParsCit/crfpp/traindata/tagged_references.txt +500 -0
  305. data/perl/ParsCit/lib/CSXUtil/SafeText.pm +140 -0
  306. data/perl/ParsCit/lib/ParsCit/Citation.pm +462 -0
  307. data/perl/ParsCit/lib/ParsCit/CitationContext.pm +132 -0
  308. data/perl/ParsCit/lib/ParsCit/Config.pm +46 -0
  309. data/perl/ParsCit/lib/ParsCit/Controller.pm +306 -0
  310. data/perl/ParsCit/lib/ParsCit/PostProcess.pm +367 -0
  311. data/perl/ParsCit/lib/ParsCit/PreProcess.pm +333 -0
  312. data/perl/ParsCit/lib/ParsCit/Tr2crfpp.pm +331 -0
  313. data/perl/ParsCit/resources/parsCit.model +0 -0
  314. data/perl/ParsCit/resources/parsCitDict.txt +148783 -0
  315. data/perl/extract.pl +199 -0
  316. data/spec/biblicit/cb2bib_spec.rb +48 -0
  317. data/spec/biblicit/citeseer_spec.rb +40 -0
  318. data/spec/fixtures/pdf/10.1.1.109.4049.pdf +0 -0
  319. data/spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf +0 -0
  320. data/spec/fixtures/pdf/ICINCO_2010.pdf +0 -0
  321. data/spec/spec_helper.rb +3 -0
  322. metadata +474 -0
@@ -0,0 +1,58 @@
1
+ Albert<>Al
2
+ Andrew<>Andy
3
+ Anthony<>Tony
4
+ Arthur<>Art,Arty
5
+ Bernard<>Bernie,Bern
6
+ Charles<>Charlie,Chuck
7
+ Christopher<>Chris
8
+ Daniel<>Dan,Danny
9
+ Donald<>Don
10
+ Edward<>Ed,Eddie
11
+ Eugene<>Gene
12
+ Francis<>Frank,Fran
13
+ Frederick<>Fred,Freddy
14
+ Henry<>Hank
15
+ Irving<>Irv
16
+ James<>Jim,Jimmy
17
+ Joseph<>Joe
18
+ John<>Jack,Jacky
19
+ Lawrence<>Larry
20
+ Leonard<>Leo
21
+ Nathan<>Nat,Nate
22
+ Nicholas<>Nick
23
+ Patrick<>Pat
24
+ Peter<>Pete
25
+ Raymond<>Ray
26
+ Richard<>Dick,Rick
27
+ Robert<>Bob, Bobby, Rob
28
+ Ronald<>Ron, Ronny
29
+ Russell<>Russ
30
+ Samuel<>Sam, Sammy
31
+ Stephan<>Steve
32
+ Stuart<>Stu
33
+ Theodore<>Ted, Teddy
34
+ Thomas<>Tom, Thom, Tommy
35
+ Timothy<>Tim, Timmy
36
+ Walter<>Walt, Wally
37
+ William<>Bill, Billy, Will, Willy
38
+ Amanda<>Mandy
39
+ Catherine<>Cathy, Cath
40
+ Christine<>Chris, Chrissy
41
+ Cynthia<>Cindy, Cynth
42
+ Deborah<>Deb, Debbie
43
+ Elizabeth<>Betty, Beth, Liz, Bess
44
+ Florence<>Flo
45
+ Frances<>Fran, Francie
46
+ Janet<>Jan
47
+ Katherine<>Kathy, Kate
48
+ Janice<>Jan
49
+ Nancy<>Nan
50
+ Pamela<>Pam
51
+ Patricia<>Pat
52
+ Roberta<>Bobbie
53
+ Sophia<>Sophie
54
+ Susan<>Sue, Suzie
55
+ Teresa<>Terry
56
+ Valerie<>Val
57
+ Veronica<>Ronnie
58
+ Yvonne<>Vonna
@@ -0,0 +1,121 @@
1
+ 111 research
2
+ 88 support
3
+ 74 grant
4
+ 64 science
5
+ 52 part
6
+ 42 appear
7
+ 38 nsf
8
+ 38 work
9
+ 32 paper
10
+ 31 author
11
+ 30 contract
12
+ 28 foundation
13
+ 26 acm
14
+ 25 system
15
+ 25 national
16
+ 24 computer
17
+ 24 proceedings
18
+ 24 ccr
19
+ 23 project
20
+ 22 conference
21
+ 21 institute
22
+ 21 department
23
+ 20 agency
24
+ 20 technology
25
+ 19 defense
26
+ 19 advanced
27
+ 19 center
28
+ 18 advanced research
29
+ 18 national science
30
+ 18 report
31
+ 17 office
32
+ 17 science foundation
33
+ 17 computer science
34
+ 17 corporation
35
+ 16 copyright
36
+ 16 artificial
37
+ 16 submit
38
+ 16 project agency
39
+ 16 nsf grant
40
+ 15 computation
41
+ 15 fellowship
42
+ 15 research project
43
+ 14 international
44
+ 14 laboratory
45
+ 13 arpa
46
+ 13 classification
47
+ 13 provided
48
+ 12 copy
49
+ 12 sponsor
50
+ 12 grant ccr
51
+ 12 permission
52
+ 12 version
53
+ 11 naval
54
+ 11 ieee
55
+ 11 onr
56
+ 11 engineering
57
+ 10 partially
58
+ 10 dimac
59
+ 10 fund
60
+ 10 edu
61
+ 10 government
62
+ 10 proc
63
+ 10 subject classification
64
+ 10 defense advanced
65
+ 10 subject
66
+ 10 number
67
+ 9 express
68
+ 9 iri
69
+ 9 ams
70
+ 9 view
71
+ 9 naval research
72
+ 9 partially support
73
+ 9 abstract
74
+ 9 international conference
75
+ 9 neural
76
+ 9 pp
77
+ 9 award
78
+ 9 symposium
79
+ 9 press
80
+ 9 information
81
+ 8 graduate
82
+ 8 address
83
+ 8 describe
84
+ 8 software
85
+ 8 compute
86
+ 8 program
87
+ 8 conclusion
88
+ 8 process
89
+ 7 contained
90
+ 7 interpret
91
+ 7 application
92
+ 7 policy
93
+ 7 workshop
94
+ 7 extend abstract
95
+ 7 extend
96
+ 7 language
97
+ 7 official
98
+ 6 distribute
99
+ 6 technical
100
+ 6 contact
101
+ 6 technology center
102
+ 6 equipment
103
+ 6 parallel
104
+ 6 pub
105
+ 6 paper appear
106
+ 6 imply
107
+ 6 publish
108
+ 6 lab
109
+ 6 represent
110
+ 6 ftp
111
+ 6 digital
112
+ 6 force
113
+ 6 scientific
114
+ 6 commission
115
+ 6 implementation
116
+ 6 official policy
117
+ 5 grant number
118
+ 5 note
119
+ 5 vol
120
+ 5 technical report
121
+ 1 working note
@@ -0,0 +1,9 @@
1
+ 22 fax
2
+ 17 tel
3
+ 12 phone
4
+ 3 tel usa
5
+ 3 usa
6
+ 1 tel int
7
+ 1 int
8
+ 1 telephone
9
+ 1 voice
@@ -0,0 +1,54 @@
1
+ AL
2
+ AK
3
+ AZ
4
+ AR
5
+ CA
6
+ CO
7
+ CT
8
+ DE
9
+ DC
10
+ FL
11
+ GA
12
+ GU
13
+ HI
14
+ ID
15
+ IL
16
+ IN
17
+ IA
18
+ KS
19
+ KY
20
+ LA
21
+ ME
22
+ MD
23
+ MA
24
+ MI
25
+ MN
26
+ MS
27
+ MO
28
+ MT
29
+ NE
30
+ NV
31
+ NH
32
+ NJ
33
+ NM
34
+ NY
35
+ NC
36
+ ND
37
+ OH
38
+ OK
39
+ OR
40
+ PA
41
+ PR
42
+ RI
43
+ SC
44
+ SD
45
+ TN
46
+ TX
47
+ UT
48
+ VT
49
+ VA
50
+ VI
51
+ WA
52
+ WV
53
+ WI
54
+ WY
@@ -0,0 +1,45 @@
1
+ 54 report
2
+ 51 technical
3
+ 50 technical report
4
+ 29 tr
5
+ 6 csrp
6
+ 5 cs tr
7
+ 4 memo
8
+ 4 report csrp
9
+ 4 dimac technical
10
+ 4 dimac
11
+ 3 research
12
+ 3 perceptual
13
+ 3 section
14
+ 3 laboratory
15
+ 3 isi
16
+ 3 section technical
17
+ 3 compute
18
+ 2 report csi
19
+ 2 isi rr
20
+ 2 csi
21
+ 2 memorandum
22
+ 2 paper
23
+ 1 reportnumbox technical
24
+ 1 project
25
+ 1 program technical
26
+ 1 report pcs
27
+ 1 csd tr
28
+ 1 technical note
29
+ 1 program
30
+ 1 serial
31
+ 1 project report
32
+ 1 advanced computer
33
+ 1 advanced
34
+ 1 note
35
+ 1 src
36
+ 1 research report
37
+ 1 university
38
+ 1 science technical
39
+ 1 mathematics
40
+ 1 reportnumbox
41
+ 1 report crg
42
+ 1 report cuc
43
+ 1 research paper
44
+ 1 crpc
45
+ 1 coin technical
@@ -0,0 +1,73 @@
1
+ ALABAMA, AL
2
+ ALASKA, AK
3
+ ARIZONA, AZ
4
+ ARKANSAS, AR
5
+ CALIFORNIA, CA
6
+ COLORADO, CO
7
+ CONNECTICUT, CT
8
+ DELAWARE, DE
9
+ DIST OF COLUMBIA, DE
10
+ FLORIDA, FL
11
+ GEORGIA, GA
12
+ HAWAII, HI
13
+ IDAHO, ID
14
+ ILLINOIS, IL
15
+ INDIANA, IN
16
+ IOWA, IA
17
+ KANSAS, KS
18
+ KENTUCKY, KY
19
+ LOUISIANA, LA
20
+ MAINE, ME
21
+ MARYLAND, MD
22
+ MASSACHUSETTS, MA
23
+ MICHIGAN, MI
24
+ MINNESOTA, MN
25
+ MISSISSIPPI, MS
26
+ MISSOURI, MO
27
+ MONTANA, MT
28
+ NEBRASKA, NE
29
+ NEVADA, NV
30
+ NEW HAMPSHIRE, NH
31
+ NEW JERSEY, NJ
32
+ NEW MEXICO, NM
33
+ NEW YORK, NY
34
+ NORTH CAROLINA, NC
35
+ NORTH DAKOTA, ND
36
+ OHIO, OH
37
+ OKLAHOMA, OK
38
+ OREGON, OR
39
+ PENNSYLVANIA, PA
40
+ RHODE ISLAND, RI
41
+ SOUTH CAROLINA, SC
42
+ SOUTH DAKOTA, SD
43
+ TENNESSEE, TN
44
+ TEXAS, TX
45
+ UTAH, UT
46
+ VERMONT, VT
47
+ VIRGINIA, VA
48
+ WASHINGTON, WA
49
+ WEST VIRGINIA, WV
50
+ WISCONSIN, WI
51
+ WYOMING, WY
52
+ AMERICAN SAMOA, AS
53
+ NORTHERN MARIANA ISLANDS, MP
54
+ FEDERATED STATES of MICRONESIA, FM
55
+ Palau, PW
56
+ GUAM, GU
57
+ Puerto Rico, PR
58
+ MARSHALL ISLANDS, MH
59
+ VIRGIN ISLANDS, VI
60
+
61
+ #Canada
62
+ ALBERTA, AB
63
+ NOVA SCOTIA, NS
64
+ BRITISH COLUMBIA, BC
65
+ ONTARIO, ON
66
+ MANITOBA, MB
67
+ PRINCE EDWARD ISLAND, PE
68
+ NEW BRUNSWICK, NB
69
+ QUEBEC, QC
70
+ NEWFOUNDLAND & LABRADOR, NF
71
+ SASKATCHEWAN, SK
72
+ NORTHWEST TERRITORIES, NT
73
+ YUKON TERRITORY, YK
@@ -0,0 +1,118 @@
1
+ ALABAMA
2
+ AL
3
+ ALASKA
4
+ AK
5
+ AMERICAN SAMOA
6
+ AS
7
+ ARIZONA
8
+ AZ
9
+ ARKANSAS
10
+ AR
11
+ CALIFORNIA
12
+ CA
13
+ COLORADO
14
+ CO
15
+ CONNECTICUT
16
+ CT
17
+ DELAWARE
18
+ DE
19
+ DISTRICT OF COLUMBIA
20
+ DC
21
+ FEDERATED STATES OF MICRONESIA
22
+ FM
23
+ FLORIDA
24
+ FL
25
+ GEORGIA
26
+ GA
27
+ GUAM
28
+ GU
29
+ HAWAII
30
+ HI
31
+ IDAHO
32
+ ID
33
+ ILLINOIS
34
+ IL
35
+ INDIANA
36
+ IN
37
+ IOWA
38
+ IA
39
+ KANSAS
40
+ KS
41
+ KENTUCKY
42
+ KY
43
+ LOUISIANA
44
+ LA
45
+ MAINE
46
+ ME
47
+ MARSHALL ISLANDS
48
+ MH
49
+ MARYLAND
50
+ MD
51
+ MASSACHUSETTS
52
+ MA
53
+ MICHIGAN
54
+ MI
55
+ MINNESOTA
56
+ MN
57
+ MISSISSIPPI
58
+ MS
59
+ MISSOURI
60
+ MO
61
+ MONTANA
62
+ MT
63
+ NEBRASKA
64
+ NE
65
+ NEVADA
66
+ NV
67
+ NEW HAMPSHIRE
68
+ NH
69
+ NEW JERSEY
70
+ NJ
71
+ NEW MEXICO
72
+ NM
73
+ NEW YORK
74
+ NY
75
+ NORTH CAROLINA
76
+ NC
77
+ NORTH DAKOTA
78
+ ND
79
+ NORTHERN MARIANA ISLANDS
80
+ MP
81
+ OHIO
82
+ OH
83
+ OKLAHOMA
84
+ OK
85
+ OREGON
86
+ OR
87
+ PALAU
88
+ PW
89
+ PENNSYLVANIA
90
+ PA1
91
+ PUERTO RICO
92
+ PR
93
+ RHODE ISLAND
94
+ RI
95
+ SOUTH CAROLINA
96
+ SC
97
+ SOUTH DAKOTA
98
+ SD
99
+ TENNESSEE
100
+ TN
101
+ TEXAS
102
+ TX
103
+ UTAH
104
+ UT
105
+ VERMONT
106
+ VT
107
+ VIRGIN ISLANDS
108
+ VI
109
+ VIRGINIA
110
+ VA
111
+ WASHINGTON
112
+ WA
113
+ WEST VIRGINIA
114
+ WV
115
+ WISCONSIN
116
+ WI
117
+ WYOMING
118
+ WY