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 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,23 @@
1
+ 1 1:0.06730769 4:0.14285714 5:0.14285714 7:0.14285714 14:0.28571429 18:0.01428571 19:0.06666667 38:0.33333333 41:0.22222222 54:0.11111111 56:0.04918033 58:0.20000000 115:0.33333333 224:0.50000000 391:0.50000000 408:1.00000000 504:1.00000000 510:1.00000000 642:1.00000000 961:1.00000000 1520:1.00000000
2
+ 1 1:0.05769231 4:0.16666667 7:0.33333333 14:0.16666667 17:0.16666667 18:0.02857143 41:0.11111111 43:0.20000000 54:0.11111111 56:0.01639344 96:0.33333333 119:0.25000000 161:1.00000000 181:0.16666667 221:0.20000000 357:0.12500000 364:0.50000000 465:1.00000000 987:0.50000000 1778:1.00000000
3
+ 1 1:0.06730769 5:0.71428571 6:0.28571429 18:0.04285714 19:0.33333333 23:0.42857143 29:0.20000000 130:1.00000000 134:0.50000000
4
+ 1 1:0.01923077 5:0.50000000 18:0.05714286 19:0.06666667 192:0.50000000 334:1.00000000
5
+ 1 1:0.06730769 5:0.14285714 6:0.42857143 18:0.07142857 19:0.06666667 29:0.30000000 43:0.20000000 130:0.50000000 148:0.20000000 192:0.50000000 337:0.25000000 391:0.50000000 1433:1.00000000 1779:1.00000000
6
+ 1 1:0.10576923 3:0.54545455 5:0.09090909 6:0.18181818 17:0.09090909 18:0.08571429 19:0.06666667 22:0.07317073 29:0.10000000 30:0.10000000 44:0.04615385 59:0.25000000 61:0.25000000 100:0.25000000 130:0.50000000 174:0.25000000 210:0.33333333 1608:1.00000000 1610:1.00000000
7
+ 1 1:0.12500000 3:0.69230769 4:0.07692308 5:0.15384615 14:0.07692308 18:0.10000000 19:0.13333333 20:0.20000000 22:0.10975610 41:0.11111111 44:0.10769231 47:0.20000000 48:0.16666667 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 161:1.00000000
8
+ 1 1:0.13461538 3:0.50000000 4:0.21428571 18:0.11428571 22:0.08536585 27:0.14285714 44:0.04615385 47:0.40000000 48:0.16666667 53:0.14285714 54:0.33333333 55:0.16666667 61:0.25000000 78:0.66666667 133:0.16666667 197:1.00000000 216:1.00000000 218:1.00000000 477:0.50000000
9
+ 1 1:0.14423077 3:0.80000000 4:0.06666667 5:0.06666667 18:0.12857143 19:0.06666667 20:0.20000000 22:0.14634146 27:0.14285714 44:0.13846154 47:0.20000000 53:0.14285714 54:0.11111111 55:0.16666667 56:0.01639344 57:0.20000000 58:0.20000000
10
+ 1 1:0.13461538 3:0.78571429 4:0.07142857 5:0.14285714 18:0.14285714 19:0.13333333 20:0.40000000 22:0.13414634 44:0.12307692 47:0.20000000 54:0.11111111 56:0.03278689 57:0.20000000 58:0.40000000 173:1.00000000
11
+ 1 1:0.12500000 3:0.76923077 5:0.07692308 18:0.15714286 19:0.06666667 22:0.12195122 27:0.28571429 44:0.10769231 53:0.28571429 55:0.33333333 56:0.01639344 57:0.20000000 58:0.20000000
12
+ 1 1:0.16346154 3:0.64705882 7:0.11764706 17:0.05882353 18:0.17142857 22:0.13414634 27:0.14285714 43:0.20000000 44:0.12307692 53:0.14285714 61:0.25000000 78:0.33333333 112:0.50000000 181:0.33333333 216:1.00000000 221:0.40000000 477:0.50000000 608:0.16666667 731:1.00000000 734:1.00000000 944:1.00000000
13
+ 1 1:0.12500000 3:0.92307692 5:0.07692308 18:0.18571429 19:0.06666667 20:0.20000000 22:0.14634146 44:0.15384615 56:0.01639344 57:0.20000000 58:0.20000000
14
+ 1 1:0.14423077 3:0.80000000 5:0.06666667 18:0.20000000 19:0.06666667 22:0.14634146 43:0.10000000 44:0.13846154 51:0.12500000 56:0.01639344 57:0.20000000 58:0.20000000 78:0.66666667 189:0.16666667 216:1.00000000 477:1.00000000
15
+ 1 1:0.05769231 3:0.66666667 4:0.33333333 18:0.21428571 22:0.04878049 44:0.03076923 47:0.40000000 48:0.16666667 54:0.22222222
16
+ 1 1:0.09615385 3:0.60000000 4:0.10000000 5:0.10000000 6:0.10000000 18:0.22857143 19:0.06666667 20:0.20000000 22:0.07317073 29:0.10000000 42:0.33333333 43:0.30000000 44:0.01538462 47:0.20000000 51:0.25000000 54:0.11111111 56:0.01639344 57:0.20000000 58:0.20000000 78:0.33333333 287:0.33333333 476:0.50000000 477:0.50000000
17
+ 1 1:0.05769231 3:0.16666667 14:0.33333333 17:0.50000000 18:0.24285714 22:0.01219512 41:0.22222222 43:0.20000000 56:0.01639344 57:0.20000000 109:0.25000000 224:0.50000000
18
+ 1 1:0.01923077 10:0.50000000 17:0.50000000 18:0.25714286 183:0.50000000 229:1.00000000 230:1.00000000
19
+ 1 1:0.13461538 3:0.78571429 5:0.07142857 18:0.27142857 19:0.06666667 20:0.20000000 22:0.13414634 27:0.14285714 44:0.13846154 53:0.14285714 55:0.16666667 59:0.25000000 61:0.25000000
20
+ 1 1:0.09615385 3:0.80000000 4:0.10000000 18:0.28571429 22:0.09756098 44:0.07692308 47:0.20000000 54:0.11111111 78:0.33333333 150:0.01333333 248:1.00000000 353:1.00000000 477:0.50000000 1332:1.00000000
21
+ 1 1:0.02884615 4:0.33333333 18:0.30000000 43:0.10000000 54:0.11111111
22
+ 1 1:0.03846154 3:0.50000000 4:0.25000000 18:0.31428571 22:0.02439024 47:0.20000000 54:0.11111111 78:0.33333333 477:0.50000000 1332:1.00000000
23
+ 1 1:0.02884615 4:0.33333333 18:0.32857143 43:0.10000000 54:0.11111111
@@ -0,0 +1,82 @@
1
+ ParsCit README
2
+ IGC
3
+
4
+ ParsCit is a utility for extracting citations from research papers
5
+ based on Conditional Random Fields and heuristic regularization.
6
+
7
+ Installation:
8
+
9
+ In order to use the ParsCit web service you will need the following
10
+ modules in your perl library:
11
+
12
+ Log::Log4perl
13
+ Log::Dispatch
14
+
15
+ Edit lib/ParsCit/Config.pm to provide values appropriate for your
16
+ environment. Also edit wsdl/ParsCitService.wsdl to reflect any
17
+ changes to your service URL.
18
+
19
+ Command Line Usage:
20
+
21
+ Command line utilities are provided for extracting citations from
22
+ text documents. By default, text files are expected to be encoded
23
+ in UTF-8, but the expected encoding can be adjusted using perl
24
+ command line switches. To run ParsCit on a single document, execute
25
+ the following command:
26
+
27
+ citeExtract.pl textfile [outfile]
28
+
29
+ If "outfile" is specified, the XML output will be written to that
30
+ file; otherwise, the XML will be printed to STDOUT.
31
+
32
+ There is also a web service interface available, using the
33
+ SOAP::Lite perl module. To start the service, just execute:
34
+
35
+ parscit-service.pl
36
+
37
+ By default, the service will start on port 10555, but this is
38
+ configurable in the ParsCit::Config library module. A WSDL file is
39
+ provided with the distribution that outlines the message details
40
+ expected by the ParsCit service. If the service port is changed,
41
+ the WSDL file must also be modified to reflect that change. Expected
42
+ parameters in the input message are "filePath" (a path to the text
43
+ file to parse) and "repositoryID". The ParsCit service is designed
44
+ for deployment in an environment where text files may be located on
45
+ file systems mounted from arbitrary machines on the network. Thus,
46
+ "repositoryID" provides a means to map a given shared file system to
47
+ it's mount point. Repository mappings are configurable in the Config
48
+ module. The "filePath" parameter provides a path to the text file
49
+ relative to the repository mount point. The local file system may be
50
+ specified using the reserved repository ID "LOCAL". In that case, an
51
+ absolute path to the text file may be specified.
52
+
53
+ A perl client is also provided that demonstrates how to use the
54
+ service. Execute the client with the following command:
55
+
56
+ parscit-client.pl filePath repositoryID
57
+
58
+ If the call is successful, the XML output will be printed to STDOUT.
59
+
60
+ API:
61
+
62
+ The ParsCit libraries may be used directly from external perl
63
+ applications. The interface module is ParsCit::Controller. If XML
64
+ output is desired, use the
65
+
66
+ ParsCit::Controller::extractCitations($filePath)
67
+
68
+ subroutine. If it is desirable to have faster, more structured access
69
+ to citation data from the external code, it may be more convenient to
70
+ use the
71
+
72
+ ParsCit::Controller::extractCitationsImpl($filePath)
73
+
74
+ subroutine instead. Rather than returning the data in XML
75
+ representation, the parameters returned are a status code (code > 0
76
+ indicates success), an error message (blank if no error), a reference
77
+ to a list of ParsCit::Citation objects containing the parsed citation
78
+ data, and a reference to the body text identified during pre-processing.
79
+
80
+ If the ParsCit library is used from external Perl applications, remember
81
+ to use the "-CSD" perl option for global unicode stream support (or
82
+ otherwise handle encoding) or risk string corruption.
@@ -0,0 +1,60 @@
1
+ b# Unigram
2
+ U00:%x[-3,0]
3
+ U01:%x[-2,0]
4
+ U02:%x[-1,0]
5
+ U03:%x[0,0]
6
+ U04:%x[1,0]
7
+ U05:%x[2,0]
8
+ U06:%x[3,0]
9
+ U07:%x[-1,0]/%x[0,0]
10
+ U08:%x[0,0]/%x[1,0]
11
+
12
+ # last Char
13
+ U10:%x[0,1]
14
+ U11:%x[-1,1]
15
+
16
+ # first 1-4
17
+ U20:%x[0,2]
18
+ U21:%x[0,3]
19
+ U22:%x[0,4]
20
+ U23:%x[0,5]
21
+
22
+ # last 1-4
23
+ U30:%x[0,6]
24
+ U31:%x[0,7]
25
+ U32:%x[0,8]
26
+ U33:%x[0,9]
27
+
28
+ # Lowercased, no punct
29
+ U40:%x[-2,10]
30
+ U41:%x[-1,10]
31
+ U42:%x[0,10]
32
+ U43:%x[1,10]
33
+ U44:%x[2,10]
34
+
35
+ # Capitalization
36
+ U50:%x[0,11]
37
+
38
+ # Numbers
39
+ U60:%x[0,12]
40
+
41
+ # Dict info
42
+ U70:%x[0,13]
43
+ U71:%x[0,14]
44
+ U72:%x[0,15]
45
+ U73:%x[0,16]
46
+ U74:%x[0,17]
47
+ U75:%x[0,18]
48
+ U76:%x[0,19]
49
+
50
+ # Possible editor?
51
+ U80:%x[0,20]
52
+
53
+ # Position
54
+ U90:%x[0,21]
55
+
56
+ # Punctuation
57
+ UA0:%x[0,22]
58
+
59
+ # Bigram
60
+ B