biblicit 1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (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 +1,276 @@
1
+ ai
2
+ an
3
+ ang
4
+ au-yong
5
+ ba
6
+ bai
7
+ ban
8
+ bao
9
+ bei
10
+ bi
11
+ bian
12
+ bing
13
+ bo
14
+ bu
15
+ cai
16
+ cao
17
+ cen
18
+ chai
19
+ chaim
20
+ chan
21
+ chang
22
+ chao
23
+ che
24
+ chen
25
+ cheng
26
+ cheung
27
+ chew
28
+ chi
29
+ chieu
30
+ chin
31
+ chong
32
+ chou
33
+ chu
34
+ ci
35
+ cong
36
+ cuan
37
+ cui
38
+ da
39
+ dai
40
+ dan
41
+ deng
42
+ di
43
+ ding
44
+ dong
45
+ dou
46
+ du
47
+ duan
48
+ zong
49
+ fan
50
+ fei
51
+ feng
52
+ foong
53
+ fu
54
+ fung
55
+ gai
56
+ gan
57
+ gao
58
+ ge
59
+ geng
60
+ gong
61
+ gou
62
+ gu
63
+ guan
64
+ guang
65
+ gui
66
+ guo
67
+ han
68
+ hang
69
+ hao
70
+ he
71
+ hong
72
+ hor
73
+ hou
74
+ hsiao
75
+ hu
76
+ hua
77
+ huan
78
+ hui
79
+ huie
80
+ huo
81
+ ji
82
+ jia
83
+ jian
84
+ jiang
85
+ jiao
86
+ jin
87
+ jing
88
+ jiu
89
+ joe
90
+ ju
91
+ juan
92
+ jue
93
+ kan
94
+ kang
95
+ kau
96
+ ke
97
+ khu
98
+ kong
99
+ koo
100
+ kuai
101
+ kuang
102
+ kui
103
+ kwan
104
+ lai
105
+ lam
106
+ lang
107
+ lao
108
+ lau
109
+ law
110
+ le
111
+ lee
112
+ lei
113
+ lew
114
+ li
115
+ lian
116
+ liang
117
+ liao
118
+ lim
119
+ lin
120
+ ling
121
+ liu
122
+ lo
123
+ loh
124
+ long
125
+ loong
126
+ lou
127
+ louis
128
+ lu
129
+ luo
130
+ ma
131
+ mah
132
+ mai
133
+ mak
134
+ man
135
+ mao
136
+ mar
137
+ mei
138
+ meng
139
+ mi
140
+ miao
141
+ min
142
+ ming
143
+ mo
144
+ moy
145
+ mu
146
+ nao
147
+ ng
148
+ ni
149
+ nie
150
+ niu
151
+ ou
152
+ ow-Yang
153
+ pan
154
+ pang
155
+ pei
156
+ peng
157
+ pi
158
+ pian
159
+ ping
160
+ qi
161
+ qian
162
+ qiao
163
+ qin
164
+ qing
165
+ qiu
166
+ qu
167
+ quan
168
+ que
169
+ ran
170
+ rang
171
+ rao
172
+ rong
173
+ ru
174
+ ruan
175
+ rui
176
+ sa
177
+ seah
178
+ seow
179
+ seto
180
+ sha
181
+ shan
182
+ shang
183
+ shao
184
+ she
185
+ shen
186
+ shaw
187
+ sheng
188
+ shi
189
+ shu
190
+ shuai
191
+ shui
192
+ shuo
193
+ si
194
+ siew
195
+ siu
196
+ song
197
+ su-tu
198
+ su
199
+ sui
200
+ sun
201
+ sze-ma
202
+ ta
203
+ tai
204
+ tan
205
+ tang
206
+ tao
207
+ teng
208
+ teoh
209
+ thean
210
+ thian
211
+ thien
212
+ tian
213
+ tong
214
+ tow
215
+ tsang
216
+ tse
217
+ tso
218
+ tu
219
+ tze
220
+ wa
221
+ wan
222
+ wang
223
+ wei
224
+ wen
225
+ weng
226
+ won
227
+ wong
228
+ woo
229
+ wu
230
+ xi
231
+ xian
232
+ xiang
233
+ xiao
234
+ xie
235
+ xin
236
+ xing
237
+ xiong
238
+ xu
239
+ xuan
240
+ xue
241
+ xun
242
+ ya
243
+ yan
244
+ yang
245
+ yao
246
+ yap
247
+ ye
248
+ yee
249
+ yep
250
+ yi
251
+ yin
252
+ ying
253
+ yong
254
+ you
255
+ yu
256
+ yuan
257
+ yue
258
+ zang
259
+ zeng
260
+ zha
261
+ zhai
262
+ zhan
263
+ zhang
264
+ zhao
265
+ zhen
266
+ zheng
267
+ zhi
268
+ zhong
269
+ zhou
270
+ zhu
271
+ zhuan
272
+ zhui
273
+ zhuo
274
+ zi
275
+ zong
276
+ zou
@@ -0,0 +1,242 @@
1
+ .ad Andorra
2
+ .ae United Arab Emirates
3
+ .af Afghanistan
4
+ .ag Antigua and Barbuda
5
+ .ai Anguilla
6
+ .al Albania
7
+ .am Armenia
8
+ .an Netherlands Antilles
9
+ .ao Angola
10
+ .aq Antarctica
11
+ .ar Argentina
12
+ .as American Samoa
13
+ .at Austria
14
+ .au Australia
15
+ .aw Aruba
16
+ .az Azerbaijan
17
+ .ba Bosnia/Herzegovinia
18
+ .bb Barbados
19
+ .bd Bangladesh
20
+ .be Belgium
21
+ .bf Burkina Faso
22
+ .bg Bulgaria
23
+ .bh Bahrain
24
+ .bi Burundi
25
+ .bj Benin
26
+ .bm Bermuda
27
+ .bn Brunei Darussalam
28
+ .bo Bolivia
29
+ .br Brazil
30
+ .bs Bahamas
31
+ .bt Bhutan
32
+ .bv Bouvet Island
33
+ .bw Botswana
34
+ .by Belarus
35
+ .bz Belize
36
+ .ca Canada
37
+ .cc Cocos Islands - Keelings
38
+ .cf Central African Republic
39
+ .cg Congo
40
+ .ch Switzerland
41
+ .ci Ivory Coast
42
+ .ck Cook Islands
43
+ .cl Chile
44
+ .cm Cameroon
45
+ .cn China
46
+ .co Colombia
47
+ .cr Costa Rica
48
+ .cs Czechoslovakia
49
+ .cu Cuba
50
+ .cv Cape Verde
51
+ .cx Christmas Island
52
+ .cy Cyprus
53
+ .cz Czech Republic
54
+ .de Germany
55
+ .dj Djibouti
56
+ .dk Denmark
57
+ .dm Dominica
58
+ .do Dominican Republic
59
+ .dz Algeria
60
+ .ec Ecuador
61
+ .ee Estonia
62
+ .eg Egypt
63
+ .eh Western Sahara
64
+ .er Eritrea
65
+ .es Spain
66
+ .et Ethiopia
67
+ .fi Finland
68
+ .fj Fiji
69
+ .fk Falkland Islands/Malvinas
70
+ .fm Micronesia
71
+ .fo Faroe Islands
72
+ .fr France
73
+ .fx Metropolitan France
74
+ .ga Gabon
75
+ .gb Great Britain
76
+ .gd Grenada
77
+ .ge Georgia
78
+ .gf French Guiana
79
+ .gh Ghana
80
+ .gi Gibraltar
81
+ .gl Greenland
82
+ .gm Gambia
83
+ .gn Guinea
84
+ .gp Guadeloupe
85
+ .gq Equatorial Guinea
86
+ .gr Greece
87
+ .gs South Georgia
88
+ .gt Guatemala
89
+ .gu Guam
90
+ .gw Guinea-Bissau
91
+ .gy Guyana
92
+ .hk Hong Kong
93
+ .hm Heard and McDonald Islands
94
+ .hn Honduras
95
+ .hr Croatia/Hrvatska
96
+ .ht Haiti
97
+ .hu Hungary
98
+ .id Indonesia
99
+ .ie Ireland
100
+ .il Israel
101
+ .in India
102
+ .io British Indian Ocean Territory
103
+ .iq Iraq
104
+ .ir Iran
105
+ .is Iceland
106
+ .it Italy
107
+ .jm Jamaica
108
+ .jo Jordan
109
+ .jp Japan
110
+ .ke Kenya
111
+ .kg Kyrgyzstan
112
+ .kh Cambodia
113
+ .ki Kiribati
114
+ .km Comoros
115
+ .kn Saint Kitts and Nevis
116
+ .kp North Korea
117
+ .kr South Korea
118
+ .kw Kuwait
119
+ .ky Cayman Islands
120
+ .kz Kazakhstan
121
+ .la Laos
122
+ .lb Lebanon
123
+ .lc Saint Lucia
124
+ .li Liechtenstein
125
+ .lk Sri Lanka
126
+ .lr Liberia
127
+ .ls Lesotho
128
+ .lt Lithuania
129
+ .lu Luxembourg
130
+ .lv Latvia
131
+ .ly Libya
132
+ .ma Morocco
133
+ .mc Monaco
134
+ .md Moldova
135
+ .mg Madagascar
136
+ .mh Marshall Islands
137
+ .mk Macedonia
138
+ .ml Mali
139
+ .mm Myanmar
140
+ .mn Mongolia
141
+ .mo Macau
142
+ .mp Northern Mariana Islands
143
+ .mq Martinique
144
+ .mr Mauritania
145
+ .ms Montserrat
146
+ .mt Malta
147
+ .mu Mauritius
148
+ .mv Maldives
149
+ .mw Malawi
150
+ .mx Mexico
151
+ .my Malaysia
152
+ .mz Mozambique
153
+ .na Namibia
154
+ .nc New Caledonia
155
+ .ne Niger
156
+ .nf Norfolk Island
157
+ .ng Nigeria
158
+ .ni Nicaragua
159
+ .nl Netherlands
160
+ .no Norway
161
+ .np Nepal
162
+ .nr Nauru
163
+ .nt Neutral Zone
164
+ .nu Niue
165
+ .nz New Zealand
166
+ .om Oman
167
+ .pa Panama
168
+ .pe Peru
169
+ .pf French Polynesia
170
+ .pg Papua New Guinea
171
+ .ph Philippines
172
+ .pk Pakistan
173
+ .pl Poland
174
+ .pm St. Pierre and Miquelon
175
+ .pn Pitcairn
176
+ .pr Puerto Rico
177
+ .pt Portugal
178
+ .pw Palau
179
+ .py Paraguay
180
+ .qa Qatar
181
+ .re Reunion
182
+ .ro Romania
183
+ .ru Russian Federation
184
+ .rw Rwanda
185
+ .sa Saudi Arabia
186
+ .sb Solomon Islands
187
+ .sc Seychelles
188
+ .sd Sudan
189
+ .se Sweden
190
+ .sg Singapore
191
+ .sh Saint Helena
192
+ .si Slovenia
193
+ .sj Svalbard and Jan Mayen Islands
194
+ .sk Slovakia
195
+ .sl Sierra Leone
196
+ .sm San Marino
197
+ .sn Senegal
198
+ .so Somalia
199
+ .sr Suriname
200
+ .st Sao Torme and Principe
201
+ .su Former USSR
202
+ .sv El Salvador
203
+ .sy Syria
204
+ .sz Swaziland
205
+ .tc Turks and Caicos Islands
206
+ .td Chad
207
+ .tf French Southern Territory
208
+ .tg Togo
209
+ .th Thailand
210
+ .tj Tajikistan
211
+ .tk Tokelau
212
+ .tm Turkmenistan
213
+ .tn Tunisia
214
+ .to Tonga
215
+ .tp East Timor
216
+ .tr Turkey
217
+ .tt Trinidad and Tobago
218
+ .tv Tuvalu
219
+ .tw Taiwan
220
+ .tz Tanzania
221
+ .ua Ukraine
222
+ .ug Uganda
223
+ .uk United Kingdom
224
+ .us United States
225
+ .uy Uruguay
226
+ .uz Uzbekistan
227
+ .va Vatican City State
228
+ .vc Saint Vincent and the Grenadines
229
+ .ve Venezuela
230
+ .vg British Virgin Islands
231
+ .vi U.S. Virgin Islands
232
+ .vn Viet Nam
233
+ .vu Vanuatu
234
+ .wf Wallis and Futuna Islands
235
+ .ws Samoa
236
+ .ye Yemen
237
+ .yt Mayotte
238
+ .yu Yugoslavia
239
+ .za South Africa
240
+ .zm Zambia
241
+ .zr Zaire
242
+ .zw Zimbabwe
@@ -0,0 +1,18 @@
1
+ 1: <title> Stochastic Interaction and Linear Logic</title>
2
+ 2: <author> Patrick D. Lincoln John C. Mitchell Andre Scedrov </author>
3
+ 3: <abstract> Abstract
4
+ 4: We present stochastic interactive semantics for propositional linear
5
+ 5: Logic without modalities. The framework is based on interactive
6
+ 6: protocols considered in computational complexity theory, in which
7
+ ........
8
+ 17:new tool in automated deduction. </abstract>
9
+ 18:<note> A revised version appears in : "Advances in Linear Logic", ed. by J.-Y. Girard et
10
+ 19:al., London Mathematical Society Lecture Notes Series, Volume 222, Cambridge University
11
+ 20:Press, 1995, pp. 147-166. </note>
12
+ 21:<email> lincoln@csl.sri.com </email><affiliation> SRI International Computer Science Laboratory, </affiliation> <address> Menlo Park
13
+ 22:CA 94025 USA. </address> <note> Work supported under NSF Grant CCR-9224858. </note>
14
+ 23:<email> jcm@cs.stanford.edu </email><web> http://theory.stanford.edu/people/jcm/home.html</web> <affiliation> Department of Computer Science, Stanford University, </affiliation> <address Stanford, CA 94305. </address> <note>Supported in part
15
+ 24:by an NSF PYI Award, matching funds from Digital Equipment Corporation, the Powell Foundation, and Xerox Corporation; and the Wallace F. and Lucille M. Davis Faculty
16
+ 25:Scholarship. </note>
17
+ 26:<email> andre@cis.upenn.edu </email><web>http://www.cis.upenn.edu/~andre</web><affiliation> Department of Mathematics, University of Pennsylvania, </affiliation><address> Philadelphia, PA, 19104-6395. </address><note> Partially supported by
18
+ 27:NSF Grants CCR-91-02753 and CCR-94-00907 and by ONR Grant N00014-92-J-1916. Sce-drov is an American Mathematical Society Centennial Research Fellow. </note>
@@ -0,0 +1,2 @@
1
+ #*TopWords generatd by program is modified and selected manually and
2
+ #changed to the name abstract.txt, keyword.txt, etc