biblicit 1.0 → 2.0.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (406) hide show
  1. data/.gitmodules +3 -0
  2. data/Gemfile +1 -1
  3. data/README.md +125 -30
  4. data/Rakefile +22 -0
  5. data/biblicit.gemspec +9 -7
  6. data/lib/biblicit/cb2bib.rb +10 -11
  7. data/lib/biblicit/citeseer.rb +14 -26
  8. data/lib/biblicit/extractor.rb +40 -19
  9. data/lib/biblicit/parscit.rb +38 -0
  10. data/parscit/.gitignore +8 -0
  11. data/parscit/CHANGELOG +125 -0
  12. data/parscit/COPYING +674 -0
  13. data/parscit/COPYING.LESSER +165 -0
  14. data/parscit/INSTALL +105 -0
  15. data/parscit/README +97 -0
  16. data/{perl/ParsCit/README.TXT → parscit/USAGE} +25 -15
  17. data/parscit/bin/archtest.pl +31 -0
  18. data/parscit/bin/citeExtract.pl +562 -0
  19. data/parscit/bin/conlleval.pl +315 -0
  20. data/parscit/bin/headExtract.pl +40 -0
  21. data/parscit/bin/parsHed/convert2TokenLevel.pl +138 -0
  22. data/parscit/bin/parsHed/keywordGen.pl +308 -0
  23. data/parscit/bin/parsHed/parseXmlHeader.pl +141 -0
  24. data/parscit/bin/parsHed/redo.parsHed.pl +198 -0
  25. data/parscit/bin/parsHed/tr2crfpp_parsHed.pl +521 -0
  26. data/parscit/bin/parseRefStrings.pl +102 -0
  27. data/parscit/bin/phOutput2xml.pl +223 -0
  28. data/parscit/bin/redo.parsCit.pl +105 -0
  29. data/parscit/bin/sectExtract.pl +149 -0
  30. data/parscit/bin/sectLabel/README +110 -0
  31. data/parscit/bin/sectLabel/README.txt +110 -0
  32. data/parscit/bin/sectLabel/genericSect/crossValidation.rb +98 -0
  33. data/parscit/bin/sectLabel/genericSect/extractFeature.rb +104 -0
  34. data/parscit/bin/sectLabel/genericSectExtract.rb +53 -0
  35. data/parscit/bin/sectLabel/getStructureInfo.pl +156 -0
  36. data/parscit/bin/sectLabel/processOmniXML.pl +1427 -0
  37. data/parscit/bin/sectLabel/processOmniXML_new.pl +1025 -0
  38. data/parscit/bin/sectLabel/processOmniXMLv2.pl +1529 -0
  39. data/parscit/bin/sectLabel/processOmniXMLv3.pl +964 -0
  40. data/parscit/bin/sectLabel/redo.sectLabel.pl +219 -0
  41. data/parscit/bin/sectLabel/simplifyOmniXML.pl +382 -0
  42. data/parscit/bin/sectLabel/single2multi.pl +190 -0
  43. data/parscit/bin/sectLabel/tr2crfpp.pl +158 -0
  44. data/parscit/bin/tr2crfpp.pl +260 -0
  45. data/parscit/bin/xml2train.pl +193 -0
  46. data/parscit/lib/CSXUtil/SafeText.pm +130 -0
  47. data/parscit/lib/Omni/Config.pm +93 -0
  48. data/parscit/lib/Omni/Omnicell.pm +263 -0
  49. data/parscit/lib/Omni/Omnicol.pm +292 -0
  50. data/parscit/lib/Omni/Omnidd.pm +328 -0
  51. data/parscit/lib/Omni/Omnidoc.pm +153 -0
  52. data/parscit/lib/Omni/Omniframe.pm +223 -0
  53. data/parscit/lib/Omni/Omniline.pm +423 -0
  54. data/parscit/lib/Omni/Omnipage.pm +282 -0
  55. data/parscit/lib/Omni/Omnipara.pm +232 -0
  56. data/parscit/lib/Omni/Omnirun.pm +303 -0
  57. data/parscit/lib/Omni/Omnitable.pm +336 -0
  58. data/parscit/lib/Omni/Omniword.pm +162 -0
  59. data/parscit/lib/Omni/Traversal.pm +313 -0
  60. data/parscit/lib/ParsCit/.PostProcess.pm.swp +0 -0
  61. data/parscit/lib/ParsCit/Citation.pm +737 -0
  62. data/parscit/lib/ParsCit/CitationContext.pm +220 -0
  63. data/parscit/lib/ParsCit/Config.pm +35 -0
  64. data/parscit/lib/ParsCit/Controller.pm +653 -0
  65. data/parscit/lib/ParsCit/PostProcess.pm +505 -0
  66. data/parscit/lib/ParsCit/PreProcess.pm +1041 -0
  67. data/parscit/lib/ParsCit/Tr2crfpp.pm +1195 -0
  68. data/parscit/lib/ParsHed/Config.pm +49 -0
  69. data/parscit/lib/ParsHed/Controller.pm +143 -0
  70. data/parscit/lib/ParsHed/PostProcess.pm +322 -0
  71. data/parscit/lib/ParsHed/Tr2crfpp.pm +448 -0
  72. data/{perl/ParsCit/lib/ParsCit/Tr2crfpp.pm → parscit/lib/ParsHed/Tr2crfpp_token.pm} +22 -21
  73. data/parscit/lib/SectLabel/AAMatching.pm +1949 -0
  74. data/parscit/lib/SectLabel/Config.pm +88 -0
  75. data/parscit/lib/SectLabel/Controller.pm +332 -0
  76. data/parscit/lib/SectLabel/PostProcess.pm +425 -0
  77. data/parscit/lib/SectLabel/PreProcess.pm +116 -0
  78. data/parscit/lib/SectLabel/Tr2crfpp.pm +1246 -0
  79. data/parscit/resources/parsCit.model +0 -0
  80. data/parscit/resources/parsCit.split.model +0 -0
  81. data/{perl/ParsCit → parscit}/resources/parsCitDict.txt +205 -0
  82. data/parscit/resources/parsHed/bigram +10 -0
  83. data/parscit/resources/parsHed/keywords +10 -0
  84. data/parscit/resources/parsHed/parsHed.model +0 -0
  85. data/parscit/resources/parsHed/parsHed.template +178 -0
  86. data/parscit/resources/sectLabel/affiliation.model +0 -0
  87. data/parscit/resources/sectLabel/author.model +0 -0
  88. data/parscit/resources/sectLabel/funcWord +320 -0
  89. data/parscit/resources/sectLabel/genericSect.model +0 -0
  90. data/parscit/resources/sectLabel/sectLabel.config +42 -0
  91. data/parscit/resources/sectLabel/sectLabel.configXml +42 -0
  92. data/parscit/resources/sectLabel/sectLabel.model +0 -0
  93. data/sh/convert_to_text.sh +20 -0
  94. data/spec/biblicit/extractor_spec.rb +121 -0
  95. data/spec/fixtures/Review_of_Michael_Tyes_Consciousness_Revisited.docx +0 -0
  96. data/spec/fixtures/critical-infrastructures.ps +63951 -0
  97. data/spec/fixtures/txt/E06-1050.txt +867 -0
  98. data/spec/fixtures/txt/sample1.txt +902 -0
  99. data/spec/fixtures/txt/sample2.txt +394 -0
  100. data/spec/spec_helper.rb +3 -0
  101. data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/Function.pm +2 -20
  102. data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm +0 -7
  103. data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/Parser.pm +0 -2
  104. data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm +0 -7
  105. data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/Config/API_Config.pm +6 -1
  106. data/svm-header-parse/HeaderParseService/tmp/.gitignore +4 -0
  107. data/svm-header-parse/extract.pl +75 -0
  108. metadata +351 -317
  109. data/perl/DocFilter/lib/DocFilter/Config.pm +0 -35
  110. data/perl/DocFilter/lib/DocFilter/Filter.pm +0 -51
  111. data/perl/FileConversionService/README.TXT +0 -11
  112. data/perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar +0 -0
  113. data/perl/FileConversionService/lib/CSXUtil/SafeText.pm +0 -140
  114. data/perl/FileConversionService/lib/FileConverter/CheckSum.pm +0 -77
  115. data/perl/FileConversionService/lib/FileConverter/Compression.pm +0 -137
  116. data/perl/FileConversionService/lib/FileConverter/Config.pm +0 -57
  117. data/perl/FileConversionService/lib/FileConverter/Controller.pm +0 -191
  118. data/perl/FileConversionService/lib/FileConverter/JODConverter.pm +0 -61
  119. data/perl/FileConversionService/lib/FileConverter/PDFBox.pm +0 -69
  120. data/perl/FileConversionService/lib/FileConverter/PSConverter.pm +0 -69
  121. data/perl/FileConversionService/lib/FileConverter/PSToText.pm +0 -88
  122. data/perl/FileConversionService/lib/FileConverter/Prescript.pm +0 -68
  123. data/perl/FileConversionService/lib/FileConverter/TET.pm +0 -75
  124. data/perl/FileConversionService/lib/FileConverter/Utils.pm +0 -130
  125. data/perl/HeaderParseService/lib/CSXUtil/SafeText.pm +0 -140
  126. data/perl/HeaderParseService/resources/data/EbizHeaders.txt +0 -24330
  127. data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed +0 -27506
  128. data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old +0 -26495
  129. data/perl/HeaderParseService/resources/data/tagged_headers.txt +0 -40668
  130. data/perl/HeaderParseService/resources/data/test_header.txt +0 -31
  131. data/perl/HeaderParseService/resources/data/test_header.txt.parsed +0 -31
  132. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1 +0 -23
  133. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10 +0 -23
  134. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11 +0 -23
  135. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12 +0 -23
  136. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13 +0 -23
  137. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14 +0 -23
  138. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15 +0 -23
  139. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2 +0 -23
  140. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3 +0 -23
  141. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4 +0 -23
  142. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5 +0 -23
  143. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6 +0 -23
  144. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7 +0 -23
  145. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8 +0 -23
  146. data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9 +0 -23
  147. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1 +0 -23
  148. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10 +0 -23
  149. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11 +0 -23
  150. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12 +0 -23
  151. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13 +0 -23
  152. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14 +0 -23
  153. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15 +0 -23
  154. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2 +0 -23
  155. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3 +0 -23
  156. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4 +0 -23
  157. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5 +0 -23
  158. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6 +0 -23
  159. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7 +0 -23
  160. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8 +0 -23
  161. data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9 +0 -23
  162. data/perl/ParsCit/crfpp/traindata/parsCit.template +0 -60
  163. data/perl/ParsCit/crfpp/traindata/parsCit.train.data +0 -12104
  164. data/perl/ParsCit/crfpp/traindata/tagged_references.txt +0 -500
  165. data/perl/ParsCit/lib/CSXUtil/SafeText.pm +0 -140
  166. data/perl/ParsCit/lib/ParsCit/Citation.pm +0 -462
  167. data/perl/ParsCit/lib/ParsCit/CitationContext.pm +0 -132
  168. data/perl/ParsCit/lib/ParsCit/Config.pm +0 -46
  169. data/perl/ParsCit/lib/ParsCit/Controller.pm +0 -306
  170. data/perl/ParsCit/lib/ParsCit/PostProcess.pm +0 -367
  171. data/perl/ParsCit/lib/ParsCit/PreProcess.pm +0 -333
  172. data/perl/ParsCit/resources/parsCit.model +0 -0
  173. data/perl/extract.pl +0 -199
  174. data/spec/biblicit/cb2bib_spec.rb +0 -48
  175. data/spec/biblicit/citeseer_spec.rb +0 -40
  176. /data/{perl → svm-header-parse}/HeaderParseService/README.TXT +0 -0
  177. /data/{perl/DocFilter → svm-header-parse/HeaderParseService}/lib/CSXUtil/SafeText.pm +0 -0
  178. /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm +0 -0
  179. /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm +0 -0
  180. /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm +0 -0
  181. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/50states +0 -0
  182. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AddrTopWords.txt +0 -0
  183. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AffiTopWords.txt +0 -0
  184. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AffiTopWordsAll.txt +0 -0
  185. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/ChineseSurNames.txt +0 -0
  186. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/Csurnames.bin +0 -0
  187. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/Csurnames_spec.bin +0 -0
  188. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/DomainSuffixes.txt +0 -0
  189. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/LabeledHeader +0 -0
  190. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/README +0 -0
  191. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/TrainMulClassLines +0 -0
  192. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/TrainMulClassLines1 +0 -0
  193. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/abstract.txt +0 -0
  194. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/abstractTopWords +0 -0
  195. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/addr.txt +0 -0
  196. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/affi.txt +0 -0
  197. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/affis.bin +0 -0
  198. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/all_namewords_spec.bin +0 -0
  199. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/allnamewords.bin +0 -0
  200. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cities_US.txt +0 -0
  201. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cities_world.txt +0 -0
  202. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/city.txt +0 -0
  203. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cityname.txt +0 -0
  204. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/country_abbr.txt +0 -0
  205. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/countryname.txt +0 -0
  206. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/dateTopWords +0 -0
  207. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/degree.txt +0 -0
  208. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/email.txt +0 -0
  209. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/excludeWords.txt +0 -0
  210. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/female-names +0 -0
  211. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstNames.txt +0 -0
  212. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstnames.bin +0 -0
  213. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstnames_spec.bin +0 -0
  214. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/intro.txt +0 -0
  215. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/keyword.txt +0 -0
  216. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/keywordTopWords +0 -0
  217. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/male-names +0 -0
  218. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/middleNames.txt +0 -0
  219. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/month.txt +0 -0
  220. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul +0 -0
  221. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.label +0 -0
  222. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.label.old +0 -0
  223. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.processed +0 -0
  224. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mulAuthor +0 -0
  225. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mulClassStat +0 -0
  226. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/nickname.txt +0 -0
  227. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/nicknames.bin +0 -0
  228. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/note.txt +0 -0
  229. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/page.txt +0 -0
  230. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/phone.txt +0 -0
  231. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/postcode.txt +0 -0
  232. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/pubnum.txt +0 -0
  233. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/statename.bin +0 -0
  234. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/statename.txt +0 -0
  235. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/states_and_abbreviations.txt +0 -0
  236. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/stopwords +0 -0
  237. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/stopwords.bin +0 -0
  238. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surNames.txt +0 -0
  239. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surnames.bin +0 -0
  240. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surnames_spec.bin +0 -0
  241. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/A.html +0 -0
  242. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/B.html +0 -0
  243. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/C.html +0 -0
  244. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/D.html +0 -0
  245. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/E.html +0 -0
  246. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/F.html +0 -0
  247. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/G.html +0 -0
  248. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/H.html +0 -0
  249. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/I.html +0 -0
  250. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/J.html +0 -0
  251. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/K.html +0 -0
  252. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/L.html +0 -0
  253. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/M.html +0 -0
  254. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/N.html +0 -0
  255. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/O.html +0 -0
  256. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/P.html +0 -0
  257. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Q.html +0 -0
  258. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/R.html +0 -0
  259. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/S.html +0 -0
  260. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/T.html +0 -0
  261. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/U.html +0 -0
  262. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/V.html +0 -0
  263. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/W.html +0 -0
  264. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/WCSelect.gif +0 -0
  265. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/X.html +0 -0
  266. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Y.html +0 -0
  267. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Z.html +0 -0
  268. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ae.html +0 -0
  269. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/am.html +0 -0
  270. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ar.html +0 -0
  271. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/at.html +0 -0
  272. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/au.html +0 -0
  273. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bd.html +0 -0
  274. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/be.html +0 -0
  275. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bg.html +0 -0
  276. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bh.html +0 -0
  277. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/blueribbon.gif +0 -0
  278. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bm.html +0 -0
  279. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bn.html +0 -0
  280. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/br.html +0 -0
  281. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ca.html +0 -0
  282. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ch.html +0 -0
  283. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cl.html +0 -0
  284. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cn.html +0 -0
  285. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/co.html +0 -0
  286. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cr.html +0 -0
  287. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cy.html +0 -0
  288. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cz.html +0 -0
  289. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/de.html +0 -0
  290. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/dean-mainlink.jpg +0 -0
  291. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/dk.html +0 -0
  292. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ec.html +0 -0
  293. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ee.html +0 -0
  294. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/eg.html +0 -0
  295. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/es.html +0 -0
  296. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/et.html +0 -0
  297. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/faq.html +0 -0
  298. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fi.html +0 -0
  299. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fj.html +0 -0
  300. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fo.html +0 -0
  301. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fr.html +0 -0
  302. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/geog.html +0 -0
  303. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/gr.html +0 -0
  304. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/gu.html +0 -0
  305. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hk.html +0 -0
  306. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hr.html +0 -0
  307. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hu.html +0 -0
  308. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/id.html +0 -0
  309. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ie.html +0 -0
  310. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/il.html +0 -0
  311. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/in.html +0 -0
  312. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/is.html +0 -0
  313. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/it.html +0 -0
  314. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jm.html +0 -0
  315. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jo.html +0 -0
  316. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jp.html +0 -0
  317. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kaplan.gif +0 -0
  318. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kr.html +0 -0
  319. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kw.html +0 -0
  320. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lb.html +0 -0
  321. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/linkbw2.gif +0 -0
  322. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lk.html +0 -0
  323. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lt.html +0 -0
  324. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lu.html +0 -0
  325. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lv.html +0 -0
  326. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ma.html +0 -0
  327. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/maczynski.gif +0 -0
  328. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mirror.tar +0 -0
  329. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mk.html +0 -0
  330. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mo.html +0 -0
  331. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mseawdm.gif +0 -0
  332. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mt.html +0 -0
  333. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mx.html +0 -0
  334. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/my.html +0 -0
  335. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ni.html +0 -0
  336. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/nl.html +0 -0
  337. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/no.html +0 -0
  338. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/nz.html +0 -0
  339. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pa.html +0 -0
  340. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pe.html +0 -0
  341. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ph.html +0 -0
  342. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pl.html +0 -0
  343. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pointcom.gif +0 -0
  344. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pr.html +0 -0
  345. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ps.html +0 -0
  346. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pt.html +0 -0
  347. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/recognition.html +0 -0
  348. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/results.html +0 -0
  349. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ro.html +0 -0
  350. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ru.html +0 -0
  351. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sd.html +0 -0
  352. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/se.html +0 -0
  353. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sg.html +0 -0
  354. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/si.html +0 -0
  355. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sk.html +0 -0
  356. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/th.html +0 -0
  357. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/tr.html +0 -0
  358. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/tw.html +0 -0
  359. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ua.html +0 -0
  360. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/uk.html +0 -0
  361. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/univ-full.html +0 -0
  362. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/univ.html +0 -0
  363. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/uy.html +0 -0
  364. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ve.html +0 -0
  365. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/yu.html +0 -0
  366. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/za.html +0 -0
  367. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/zm.html +0 -0
  368. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list.txt +0 -0
  369. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/url.txt +0 -0
  370. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/webTopWords +0 -0
  371. /data/{perl → svm-header-parse}/HeaderParseService/resources/database/words +0 -0
  372. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/10ContextModelfold1 +0 -0
  373. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/10Modelfold1 +0 -0
  374. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/11ContextModelfold1 +0 -0
  375. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/11Modelfold1 +0 -0
  376. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/12ContextModelfold1 +0 -0
  377. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/12Modelfold1 +0 -0
  378. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/13ContextModelfold1 +0 -0
  379. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/13Modelfold1 +0 -0
  380. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/14ContextModelfold1 +0 -0
  381. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/14Modelfold1 +0 -0
  382. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/15ContextModelfold1 +0 -0
  383. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/15Modelfold1 +0 -0
  384. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/1ContextModelfold1 +0 -0
  385. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/1Modelfold1 +0 -0
  386. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/2ContextModelfold1 +0 -0
  387. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/2Modelfold1 +0 -0
  388. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/3ContextModelfold1 +0 -0
  389. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/3Modelfold1 +0 -0
  390. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/4ContextModelfold1 +0 -0
  391. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/4Modelfold1 +0 -0
  392. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/5ContextModelfold1 +0 -0
  393. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/5Modelfold1 +0 -0
  394. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/6ContextModelfold1 +0 -0
  395. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/6Modelfold1 +0 -0
  396. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/7ContextModelfold1 +0 -0
  397. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/7Modelfold1 +0 -0
  398. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/8ContextModelfold1 +0 -0
  399. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/8Modelfold1 +0 -0
  400. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/9ContextModelfold1 +0 -0
  401. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/9Modelfold1 +0 -0
  402. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/NameSpaceModel +0 -0
  403. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/NameSpaceTrainF +0 -0
  404. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperBaseFeaDict +0 -0
  405. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperContextFeaDict +0 -0
  406. /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict +0 -0
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: biblicit
3
3
  version: !ruby/object:Gem::Version
4
- version: '1.0'
4
+ version: 2.0.3
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors:
@@ -9,7 +9,7 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2013-01-24 00:00:00.000000000 Z
12
+ date: 2013-02-28 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: activesupport
@@ -107,7 +107,7 @@ dependencies:
107
107
  - - ! '>='
108
108
  - !ruby/object:Gem::Version
109
109
  version: '0'
110
- description: Extract citations from PDFs.
110
+ description:
111
111
  email:
112
112
  - david@academia.edu
113
113
  executables: []
@@ -115,6 +115,7 @@ extensions: []
115
115
  extra_rdoc_files: []
116
116
  files:
117
117
  - .gitignore
118
+ - .gitmodules
118
119
  - .rspec
119
120
  - Gemfile
120
121
  - LICENSE.TXT
@@ -125,316 +126,339 @@ files:
125
126
  - lib/biblicit/cb2bib.rb
126
127
  - lib/biblicit/citeseer.rb
127
128
  - lib/biblicit/extractor.rb
128
- - perl/DocFilter/lib/CSXUtil/SafeText.pm
129
- - perl/DocFilter/lib/DocFilter/Config.pm
130
- - perl/DocFilter/lib/DocFilter/Filter.pm
131
- - perl/FileConversionService/README.TXT
132
- - perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar
133
- - perl/FileConversionService/lib/CSXUtil/SafeText.pm
134
- - perl/FileConversionService/lib/FileConverter/CheckSum.pm
135
- - perl/FileConversionService/lib/FileConverter/Compression.pm
136
- - perl/FileConversionService/lib/FileConverter/Config.pm
137
- - perl/FileConversionService/lib/FileConverter/Controller.pm
138
- - perl/FileConversionService/lib/FileConverter/JODConverter.pm
139
- - perl/FileConversionService/lib/FileConverter/PDFBox.pm
140
- - perl/FileConversionService/lib/FileConverter/PSConverter.pm
141
- - perl/FileConversionService/lib/FileConverter/PSToText.pm
142
- - perl/FileConversionService/lib/FileConverter/Prescript.pm
143
- - perl/FileConversionService/lib/FileConverter/TET.pm
144
- - perl/FileConversionService/lib/FileConverter/Utils.pm
145
- - perl/HeaderParseService/README.TXT
146
- - perl/HeaderParseService/lib/CSXUtil/SafeText.pm
147
- - perl/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm
148
- - perl/HeaderParseService/lib/HeaderParse/API/Function.pm
149
- - perl/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm
150
- - perl/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm
151
- - perl/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm
152
- - perl/HeaderParseService/lib/HeaderParse/API/Parser.pm
153
- - perl/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm
154
- - perl/HeaderParseService/lib/HeaderParse/Config/API_Config.pm
155
- - perl/HeaderParseService/resources/data/EbizHeaders.txt
156
- - perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed
157
- - perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old
158
- - perl/HeaderParseService/resources/data/tagged_headers.txt
159
- - perl/HeaderParseService/resources/data/test_header.txt
160
- - perl/HeaderParseService/resources/data/test_header.txt.parsed
161
- - perl/HeaderParseService/resources/database/50states
162
- - perl/HeaderParseService/resources/database/AddrTopWords.txt
163
- - perl/HeaderParseService/resources/database/AffiTopWords.txt
164
- - perl/HeaderParseService/resources/database/AffiTopWordsAll.txt
165
- - perl/HeaderParseService/resources/database/ChineseSurNames.txt
166
- - perl/HeaderParseService/resources/database/Csurnames.bin
167
- - perl/HeaderParseService/resources/database/Csurnames_spec.bin
168
- - perl/HeaderParseService/resources/database/DomainSuffixes.txt
169
- - perl/HeaderParseService/resources/database/LabeledHeader
170
- - perl/HeaderParseService/resources/database/README
171
- - perl/HeaderParseService/resources/database/TrainMulClassLines
172
- - perl/HeaderParseService/resources/database/TrainMulClassLines1
173
- - perl/HeaderParseService/resources/database/abstract.txt
174
- - perl/HeaderParseService/resources/database/abstractTopWords
175
- - perl/HeaderParseService/resources/database/addr.txt
176
- - perl/HeaderParseService/resources/database/affi.txt
177
- - perl/HeaderParseService/resources/database/affis.bin
178
- - perl/HeaderParseService/resources/database/all_namewords_spec.bin
179
- - perl/HeaderParseService/resources/database/allnamewords.bin
180
- - perl/HeaderParseService/resources/database/cities_US.txt
181
- - perl/HeaderParseService/resources/database/cities_world.txt
182
- - perl/HeaderParseService/resources/database/city.txt
183
- - perl/HeaderParseService/resources/database/cityname.txt
184
- - perl/HeaderParseService/resources/database/country_abbr.txt
185
- - perl/HeaderParseService/resources/database/countryname.txt
186
- - perl/HeaderParseService/resources/database/dateTopWords
187
- - perl/HeaderParseService/resources/database/degree.txt
188
- - perl/HeaderParseService/resources/database/email.txt
189
- - perl/HeaderParseService/resources/database/excludeWords.txt
190
- - perl/HeaderParseService/resources/database/female-names
191
- - perl/HeaderParseService/resources/database/firstNames.txt
192
- - perl/HeaderParseService/resources/database/firstnames.bin
193
- - perl/HeaderParseService/resources/database/firstnames_spec.bin
194
- - perl/HeaderParseService/resources/database/intro.txt
195
- - perl/HeaderParseService/resources/database/keyword.txt
196
- - perl/HeaderParseService/resources/database/keywordTopWords
197
- - perl/HeaderParseService/resources/database/male-names
198
- - perl/HeaderParseService/resources/database/middleNames.txt
199
- - perl/HeaderParseService/resources/database/month.txt
200
- - perl/HeaderParseService/resources/database/mul
201
- - perl/HeaderParseService/resources/database/mul.label
202
- - perl/HeaderParseService/resources/database/mul.label.old
203
- - perl/HeaderParseService/resources/database/mul.processed
204
- - perl/HeaderParseService/resources/database/mulAuthor
205
- - perl/HeaderParseService/resources/database/mulClassStat
206
- - perl/HeaderParseService/resources/database/nickname.txt
207
- - perl/HeaderParseService/resources/database/nicknames.bin
208
- - perl/HeaderParseService/resources/database/note.txt
209
- - perl/HeaderParseService/resources/database/page.txt
210
- - perl/HeaderParseService/resources/database/phone.txt
211
- - perl/HeaderParseService/resources/database/postcode.txt
212
- - perl/HeaderParseService/resources/database/pubnum.txt
213
- - perl/HeaderParseService/resources/database/statename.bin
214
- - perl/HeaderParseService/resources/database/statename.txt
215
- - perl/HeaderParseService/resources/database/states_and_abbreviations.txt
216
- - perl/HeaderParseService/resources/database/stopwords
217
- - perl/HeaderParseService/resources/database/stopwords.bin
218
- - perl/HeaderParseService/resources/database/surNames.txt
219
- - perl/HeaderParseService/resources/database/surnames.bin
220
- - perl/HeaderParseService/resources/database/surnames_spec.bin
221
- - perl/HeaderParseService/resources/database/university_list.txt
222
- - perl/HeaderParseService/resources/database/university_list/A.html
223
- - perl/HeaderParseService/resources/database/university_list/B.html
224
- - perl/HeaderParseService/resources/database/university_list/C.html
225
- - perl/HeaderParseService/resources/database/university_list/D.html
226
- - perl/HeaderParseService/resources/database/university_list/E.html
227
- - perl/HeaderParseService/resources/database/university_list/F.html
228
- - perl/HeaderParseService/resources/database/university_list/G.html
229
- - perl/HeaderParseService/resources/database/university_list/H.html
230
- - perl/HeaderParseService/resources/database/university_list/I.html
231
- - perl/HeaderParseService/resources/database/university_list/J.html
232
- - perl/HeaderParseService/resources/database/university_list/K.html
233
- - perl/HeaderParseService/resources/database/university_list/L.html
234
- - perl/HeaderParseService/resources/database/university_list/M.html
235
- - perl/HeaderParseService/resources/database/university_list/N.html
236
- - perl/HeaderParseService/resources/database/university_list/O.html
237
- - perl/HeaderParseService/resources/database/university_list/P.html
238
- - perl/HeaderParseService/resources/database/university_list/Q.html
239
- - perl/HeaderParseService/resources/database/university_list/R.html
240
- - perl/HeaderParseService/resources/database/university_list/S.html
241
- - perl/HeaderParseService/resources/database/university_list/T.html
242
- - perl/HeaderParseService/resources/database/university_list/U.html
243
- - perl/HeaderParseService/resources/database/university_list/V.html
244
- - perl/HeaderParseService/resources/database/university_list/W.html
245
- - perl/HeaderParseService/resources/database/university_list/WCSelect.gif
246
- - perl/HeaderParseService/resources/database/university_list/X.html
247
- - perl/HeaderParseService/resources/database/university_list/Y.html
248
- - perl/HeaderParseService/resources/database/university_list/Z.html
249
- - perl/HeaderParseService/resources/database/university_list/ae.html
250
- - perl/HeaderParseService/resources/database/university_list/am.html
251
- - perl/HeaderParseService/resources/database/university_list/ar.html
252
- - perl/HeaderParseService/resources/database/university_list/at.html
253
- - perl/HeaderParseService/resources/database/university_list/au.html
254
- - perl/HeaderParseService/resources/database/university_list/bd.html
255
- - perl/HeaderParseService/resources/database/university_list/be.html
256
- - perl/HeaderParseService/resources/database/university_list/bg.html
257
- - perl/HeaderParseService/resources/database/university_list/bh.html
258
- - perl/HeaderParseService/resources/database/university_list/blueribbon.gif
259
- - perl/HeaderParseService/resources/database/university_list/bm.html
260
- - perl/HeaderParseService/resources/database/university_list/bn.html
261
- - perl/HeaderParseService/resources/database/university_list/br.html
262
- - perl/HeaderParseService/resources/database/university_list/ca.html
263
- - perl/HeaderParseService/resources/database/university_list/ch.html
264
- - perl/HeaderParseService/resources/database/university_list/cl.html
265
- - perl/HeaderParseService/resources/database/university_list/cn.html
266
- - perl/HeaderParseService/resources/database/university_list/co.html
267
- - perl/HeaderParseService/resources/database/university_list/cr.html
268
- - perl/HeaderParseService/resources/database/university_list/cy.html
269
- - perl/HeaderParseService/resources/database/university_list/cz.html
270
- - perl/HeaderParseService/resources/database/university_list/de.html
271
- - perl/HeaderParseService/resources/database/university_list/dean-mainlink.jpg
272
- - perl/HeaderParseService/resources/database/university_list/dk.html
273
- - perl/HeaderParseService/resources/database/university_list/ec.html
274
- - perl/HeaderParseService/resources/database/university_list/ee.html
275
- - perl/HeaderParseService/resources/database/university_list/eg.html
276
- - perl/HeaderParseService/resources/database/university_list/es.html
277
- - perl/HeaderParseService/resources/database/university_list/et.html
278
- - perl/HeaderParseService/resources/database/university_list/faq.html
279
- - perl/HeaderParseService/resources/database/university_list/fi.html
280
- - perl/HeaderParseService/resources/database/university_list/fj.html
281
- - perl/HeaderParseService/resources/database/university_list/fo.html
282
- - perl/HeaderParseService/resources/database/university_list/fr.html
283
- - perl/HeaderParseService/resources/database/university_list/geog.html
284
- - perl/HeaderParseService/resources/database/university_list/gr.html
285
- - perl/HeaderParseService/resources/database/university_list/gu.html
286
- - perl/HeaderParseService/resources/database/university_list/hk.html
287
- - perl/HeaderParseService/resources/database/university_list/hr.html
288
- - perl/HeaderParseService/resources/database/university_list/hu.html
289
- - perl/HeaderParseService/resources/database/university_list/id.html
290
- - perl/HeaderParseService/resources/database/university_list/ie.html
291
- - perl/HeaderParseService/resources/database/university_list/il.html
292
- - perl/HeaderParseService/resources/database/university_list/in.html
293
- - perl/HeaderParseService/resources/database/university_list/is.html
294
- - perl/HeaderParseService/resources/database/university_list/it.html
295
- - perl/HeaderParseService/resources/database/university_list/jm.html
296
- - perl/HeaderParseService/resources/database/university_list/jo.html
297
- - perl/HeaderParseService/resources/database/university_list/jp.html
298
- - perl/HeaderParseService/resources/database/university_list/kaplan.gif
299
- - perl/HeaderParseService/resources/database/university_list/kr.html
300
- - perl/HeaderParseService/resources/database/university_list/kw.html
301
- - perl/HeaderParseService/resources/database/university_list/lb.html
302
- - perl/HeaderParseService/resources/database/university_list/linkbw2.gif
303
- - perl/HeaderParseService/resources/database/university_list/lk.html
304
- - perl/HeaderParseService/resources/database/university_list/lt.html
305
- - perl/HeaderParseService/resources/database/university_list/lu.html
306
- - perl/HeaderParseService/resources/database/university_list/lv.html
307
- - perl/HeaderParseService/resources/database/university_list/ma.html
308
- - perl/HeaderParseService/resources/database/university_list/maczynski.gif
309
- - perl/HeaderParseService/resources/database/university_list/mirror.tar
310
- - perl/HeaderParseService/resources/database/university_list/mk.html
311
- - perl/HeaderParseService/resources/database/university_list/mo.html
312
- - perl/HeaderParseService/resources/database/university_list/mseawdm.gif
313
- - perl/HeaderParseService/resources/database/university_list/mt.html
314
- - perl/HeaderParseService/resources/database/university_list/mx.html
315
- - perl/HeaderParseService/resources/database/university_list/my.html
316
- - perl/HeaderParseService/resources/database/university_list/ni.html
317
- - perl/HeaderParseService/resources/database/university_list/nl.html
318
- - perl/HeaderParseService/resources/database/university_list/no.html
319
- - perl/HeaderParseService/resources/database/university_list/nz.html
320
- - perl/HeaderParseService/resources/database/university_list/pa.html
321
- - perl/HeaderParseService/resources/database/university_list/pe.html
322
- - perl/HeaderParseService/resources/database/university_list/ph.html
323
- - perl/HeaderParseService/resources/database/university_list/pl.html
324
- - perl/HeaderParseService/resources/database/university_list/pointcom.gif
325
- - perl/HeaderParseService/resources/database/university_list/pr.html
326
- - perl/HeaderParseService/resources/database/university_list/ps.html
327
- - perl/HeaderParseService/resources/database/university_list/pt.html
328
- - perl/HeaderParseService/resources/database/university_list/recognition.html
329
- - perl/HeaderParseService/resources/database/university_list/results.html
330
- - perl/HeaderParseService/resources/database/university_list/ro.html
331
- - perl/HeaderParseService/resources/database/university_list/ru.html
332
- - perl/HeaderParseService/resources/database/university_list/sd.html
333
- - perl/HeaderParseService/resources/database/university_list/se.html
334
- - perl/HeaderParseService/resources/database/university_list/sg.html
335
- - perl/HeaderParseService/resources/database/university_list/si.html
336
- - perl/HeaderParseService/resources/database/university_list/sk.html
337
- - perl/HeaderParseService/resources/database/university_list/th.html
338
- - perl/HeaderParseService/resources/database/university_list/tr.html
339
- - perl/HeaderParseService/resources/database/university_list/tw.html
340
- - perl/HeaderParseService/resources/database/university_list/ua.html
341
- - perl/HeaderParseService/resources/database/university_list/uk.html
342
- - perl/HeaderParseService/resources/database/university_list/univ-full.html
343
- - perl/HeaderParseService/resources/database/university_list/univ.html
344
- - perl/HeaderParseService/resources/database/university_list/uy.html
345
- - perl/HeaderParseService/resources/database/university_list/ve.html
346
- - perl/HeaderParseService/resources/database/university_list/yu.html
347
- - perl/HeaderParseService/resources/database/university_list/za.html
348
- - perl/HeaderParseService/resources/database/university_list/zm.html
349
- - perl/HeaderParseService/resources/database/url.txt
350
- - perl/HeaderParseService/resources/database/webTopWords
351
- - perl/HeaderParseService/resources/database/words
352
- - perl/HeaderParseService/resources/models/10ContextModelfold1
353
- - perl/HeaderParseService/resources/models/10Modelfold1
354
- - perl/HeaderParseService/resources/models/11ContextModelfold1
355
- - perl/HeaderParseService/resources/models/11Modelfold1
356
- - perl/HeaderParseService/resources/models/12ContextModelfold1
357
- - perl/HeaderParseService/resources/models/12Modelfold1
358
- - perl/HeaderParseService/resources/models/13ContextModelfold1
359
- - perl/HeaderParseService/resources/models/13Modelfold1
360
- - perl/HeaderParseService/resources/models/14ContextModelfold1
361
- - perl/HeaderParseService/resources/models/14Modelfold1
362
- - perl/HeaderParseService/resources/models/15ContextModelfold1
363
- - perl/HeaderParseService/resources/models/15Modelfold1
364
- - perl/HeaderParseService/resources/models/1ContextModelfold1
365
- - perl/HeaderParseService/resources/models/1Modelfold1
366
- - perl/HeaderParseService/resources/models/2ContextModelfold1
367
- - perl/HeaderParseService/resources/models/2Modelfold1
368
- - perl/HeaderParseService/resources/models/3ContextModelfold1
369
- - perl/HeaderParseService/resources/models/3Modelfold1
370
- - perl/HeaderParseService/resources/models/4ContextModelfold1
371
- - perl/HeaderParseService/resources/models/4Modelfold1
372
- - perl/HeaderParseService/resources/models/5ContextModelfold1
373
- - perl/HeaderParseService/resources/models/5Modelfold1
374
- - perl/HeaderParseService/resources/models/6ContextModelfold1
375
- - perl/HeaderParseService/resources/models/6Modelfold1
376
- - perl/HeaderParseService/resources/models/7ContextModelfold1
377
- - perl/HeaderParseService/resources/models/7Modelfold1
378
- - perl/HeaderParseService/resources/models/8ContextModelfold1
379
- - perl/HeaderParseService/resources/models/8Modelfold1
380
- - perl/HeaderParseService/resources/models/9ContextModelfold1
381
- - perl/HeaderParseService/resources/models/9Modelfold1
382
- - perl/HeaderParseService/resources/models/NameSpaceModel
383
- - perl/HeaderParseService/resources/models/NameSpaceTrainF
384
- - perl/HeaderParseService/resources/models/WrapperBaseFeaDict
385
- - perl/HeaderParseService/resources/models/WrapperContextFeaDict
386
- - perl/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict
387
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1
388
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10
389
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11
390
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12
391
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13
392
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14
393
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15
394
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2
395
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3
396
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4
397
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5
398
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6
399
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7
400
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8
401
- - perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9
402
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1
403
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10
404
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11
405
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12
406
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13
407
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14
408
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15
409
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2
410
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3
411
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4
412
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5
413
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6
414
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7
415
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8
416
- - perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9
417
- - perl/ParsCit/README.TXT
418
- - perl/ParsCit/crfpp/traindata/parsCit.template
419
- - perl/ParsCit/crfpp/traindata/parsCit.train.data
420
- - perl/ParsCit/crfpp/traindata/tagged_references.txt
421
- - perl/ParsCit/lib/CSXUtil/SafeText.pm
422
- - perl/ParsCit/lib/ParsCit/Citation.pm
423
- - perl/ParsCit/lib/ParsCit/CitationContext.pm
424
- - perl/ParsCit/lib/ParsCit/Config.pm
425
- - perl/ParsCit/lib/ParsCit/Controller.pm
426
- - perl/ParsCit/lib/ParsCit/PostProcess.pm
427
- - perl/ParsCit/lib/ParsCit/PreProcess.pm
428
- - perl/ParsCit/lib/ParsCit/Tr2crfpp.pm
429
- - perl/ParsCit/resources/parsCit.model
430
- - perl/ParsCit/resources/parsCitDict.txt
431
- - perl/extract.pl
432
- - spec/biblicit/cb2bib_spec.rb
433
- - spec/biblicit/citeseer_spec.rb
129
+ - lib/biblicit/parscit.rb
130
+ - sh/convert_to_text.sh
131
+ - spec/biblicit/extractor_spec.rb
132
+ - spec/fixtures/Review_of_Michael_Tyes_Consciousness_Revisited.docx
133
+ - spec/fixtures/critical-infrastructures.ps
434
134
  - spec/fixtures/pdf/10.1.1.109.4049.pdf
435
135
  - spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf
436
136
  - spec/fixtures/pdf/ICINCO_2010.pdf
137
+ - spec/fixtures/txt/E06-1050.txt
138
+ - spec/fixtures/txt/sample1.txt
139
+ - spec/fixtures/txt/sample2.txt
437
140
  - spec/spec_helper.rb
141
+ - svm-header-parse/HeaderParseService/README.TXT
142
+ - svm-header-parse/HeaderParseService/lib/CSXUtil/SafeText.pm
143
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm
144
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/Function.pm
145
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm
146
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm
147
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm
148
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/Parser.pm
149
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm
150
+ - svm-header-parse/HeaderParseService/lib/HeaderParse/Config/API_Config.pm
151
+ - svm-header-parse/HeaderParseService/resources/database/50states
152
+ - svm-header-parse/HeaderParseService/resources/database/AddrTopWords.txt
153
+ - svm-header-parse/HeaderParseService/resources/database/AffiTopWords.txt
154
+ - svm-header-parse/HeaderParseService/resources/database/AffiTopWordsAll.txt
155
+ - svm-header-parse/HeaderParseService/resources/database/ChineseSurNames.txt
156
+ - svm-header-parse/HeaderParseService/resources/database/Csurnames.bin
157
+ - svm-header-parse/HeaderParseService/resources/database/Csurnames_spec.bin
158
+ - svm-header-parse/HeaderParseService/resources/database/DomainSuffixes.txt
159
+ - svm-header-parse/HeaderParseService/resources/database/LabeledHeader
160
+ - svm-header-parse/HeaderParseService/resources/database/README
161
+ - svm-header-parse/HeaderParseService/resources/database/TrainMulClassLines
162
+ - svm-header-parse/HeaderParseService/resources/database/TrainMulClassLines1
163
+ - svm-header-parse/HeaderParseService/resources/database/abstract.txt
164
+ - svm-header-parse/HeaderParseService/resources/database/abstractTopWords
165
+ - svm-header-parse/HeaderParseService/resources/database/addr.txt
166
+ - svm-header-parse/HeaderParseService/resources/database/affi.txt
167
+ - svm-header-parse/HeaderParseService/resources/database/affis.bin
168
+ - svm-header-parse/HeaderParseService/resources/database/all_namewords_spec.bin
169
+ - svm-header-parse/HeaderParseService/resources/database/allnamewords.bin
170
+ - svm-header-parse/HeaderParseService/resources/database/cities_US.txt
171
+ - svm-header-parse/HeaderParseService/resources/database/cities_world.txt
172
+ - svm-header-parse/HeaderParseService/resources/database/city.txt
173
+ - svm-header-parse/HeaderParseService/resources/database/cityname.txt
174
+ - svm-header-parse/HeaderParseService/resources/database/country_abbr.txt
175
+ - svm-header-parse/HeaderParseService/resources/database/countryname.txt
176
+ - svm-header-parse/HeaderParseService/resources/database/dateTopWords
177
+ - svm-header-parse/HeaderParseService/resources/database/degree.txt
178
+ - svm-header-parse/HeaderParseService/resources/database/email.txt
179
+ - svm-header-parse/HeaderParseService/resources/database/excludeWords.txt
180
+ - svm-header-parse/HeaderParseService/resources/database/female-names
181
+ - svm-header-parse/HeaderParseService/resources/database/firstNames.txt
182
+ - svm-header-parse/HeaderParseService/resources/database/firstnames.bin
183
+ - svm-header-parse/HeaderParseService/resources/database/firstnames_spec.bin
184
+ - svm-header-parse/HeaderParseService/resources/database/intro.txt
185
+ - svm-header-parse/HeaderParseService/resources/database/keyword.txt
186
+ - svm-header-parse/HeaderParseService/resources/database/keywordTopWords
187
+ - svm-header-parse/HeaderParseService/resources/database/male-names
188
+ - svm-header-parse/HeaderParseService/resources/database/middleNames.txt
189
+ - svm-header-parse/HeaderParseService/resources/database/month.txt
190
+ - svm-header-parse/HeaderParseService/resources/database/mul
191
+ - svm-header-parse/HeaderParseService/resources/database/mul.label
192
+ - svm-header-parse/HeaderParseService/resources/database/mul.label.old
193
+ - svm-header-parse/HeaderParseService/resources/database/mul.processed
194
+ - svm-header-parse/HeaderParseService/resources/database/mulAuthor
195
+ - svm-header-parse/HeaderParseService/resources/database/mulClassStat
196
+ - svm-header-parse/HeaderParseService/resources/database/nickname.txt
197
+ - svm-header-parse/HeaderParseService/resources/database/nicknames.bin
198
+ - svm-header-parse/HeaderParseService/resources/database/note.txt
199
+ - svm-header-parse/HeaderParseService/resources/database/page.txt
200
+ - svm-header-parse/HeaderParseService/resources/database/phone.txt
201
+ - svm-header-parse/HeaderParseService/resources/database/postcode.txt
202
+ - svm-header-parse/HeaderParseService/resources/database/pubnum.txt
203
+ - svm-header-parse/HeaderParseService/resources/database/statename.bin
204
+ - svm-header-parse/HeaderParseService/resources/database/statename.txt
205
+ - svm-header-parse/HeaderParseService/resources/database/states_and_abbreviations.txt
206
+ - svm-header-parse/HeaderParseService/resources/database/stopwords
207
+ - svm-header-parse/HeaderParseService/resources/database/stopwords.bin
208
+ - svm-header-parse/HeaderParseService/resources/database/surNames.txt
209
+ - svm-header-parse/HeaderParseService/resources/database/surnames.bin
210
+ - svm-header-parse/HeaderParseService/resources/database/surnames_spec.bin
211
+ - svm-header-parse/HeaderParseService/resources/database/university_list.txt
212
+ - svm-header-parse/HeaderParseService/resources/database/university_list/A.html
213
+ - svm-header-parse/HeaderParseService/resources/database/university_list/B.html
214
+ - svm-header-parse/HeaderParseService/resources/database/university_list/C.html
215
+ - svm-header-parse/HeaderParseService/resources/database/university_list/D.html
216
+ - svm-header-parse/HeaderParseService/resources/database/university_list/E.html
217
+ - svm-header-parse/HeaderParseService/resources/database/university_list/F.html
218
+ - svm-header-parse/HeaderParseService/resources/database/university_list/G.html
219
+ - svm-header-parse/HeaderParseService/resources/database/university_list/H.html
220
+ - svm-header-parse/HeaderParseService/resources/database/university_list/I.html
221
+ - svm-header-parse/HeaderParseService/resources/database/university_list/J.html
222
+ - svm-header-parse/HeaderParseService/resources/database/university_list/K.html
223
+ - svm-header-parse/HeaderParseService/resources/database/university_list/L.html
224
+ - svm-header-parse/HeaderParseService/resources/database/university_list/M.html
225
+ - svm-header-parse/HeaderParseService/resources/database/university_list/N.html
226
+ - svm-header-parse/HeaderParseService/resources/database/university_list/O.html
227
+ - svm-header-parse/HeaderParseService/resources/database/university_list/P.html
228
+ - svm-header-parse/HeaderParseService/resources/database/university_list/Q.html
229
+ - svm-header-parse/HeaderParseService/resources/database/university_list/R.html
230
+ - svm-header-parse/HeaderParseService/resources/database/university_list/S.html
231
+ - svm-header-parse/HeaderParseService/resources/database/university_list/T.html
232
+ - svm-header-parse/HeaderParseService/resources/database/university_list/U.html
233
+ - svm-header-parse/HeaderParseService/resources/database/university_list/V.html
234
+ - svm-header-parse/HeaderParseService/resources/database/university_list/W.html
235
+ - svm-header-parse/HeaderParseService/resources/database/university_list/WCSelect.gif
236
+ - svm-header-parse/HeaderParseService/resources/database/university_list/X.html
237
+ - svm-header-parse/HeaderParseService/resources/database/university_list/Y.html
238
+ - svm-header-parse/HeaderParseService/resources/database/university_list/Z.html
239
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ae.html
240
+ - svm-header-parse/HeaderParseService/resources/database/university_list/am.html
241
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ar.html
242
+ - svm-header-parse/HeaderParseService/resources/database/university_list/at.html
243
+ - svm-header-parse/HeaderParseService/resources/database/university_list/au.html
244
+ - svm-header-parse/HeaderParseService/resources/database/university_list/bd.html
245
+ - svm-header-parse/HeaderParseService/resources/database/university_list/be.html
246
+ - svm-header-parse/HeaderParseService/resources/database/university_list/bg.html
247
+ - svm-header-parse/HeaderParseService/resources/database/university_list/bh.html
248
+ - svm-header-parse/HeaderParseService/resources/database/university_list/blueribbon.gif
249
+ - svm-header-parse/HeaderParseService/resources/database/university_list/bm.html
250
+ - svm-header-parse/HeaderParseService/resources/database/university_list/bn.html
251
+ - svm-header-parse/HeaderParseService/resources/database/university_list/br.html
252
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ca.html
253
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ch.html
254
+ - svm-header-parse/HeaderParseService/resources/database/university_list/cl.html
255
+ - svm-header-parse/HeaderParseService/resources/database/university_list/cn.html
256
+ - svm-header-parse/HeaderParseService/resources/database/university_list/co.html
257
+ - svm-header-parse/HeaderParseService/resources/database/university_list/cr.html
258
+ - svm-header-parse/HeaderParseService/resources/database/university_list/cy.html
259
+ - svm-header-parse/HeaderParseService/resources/database/university_list/cz.html
260
+ - svm-header-parse/HeaderParseService/resources/database/university_list/de.html
261
+ - svm-header-parse/HeaderParseService/resources/database/university_list/dean-mainlink.jpg
262
+ - svm-header-parse/HeaderParseService/resources/database/university_list/dk.html
263
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ec.html
264
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ee.html
265
+ - svm-header-parse/HeaderParseService/resources/database/university_list/eg.html
266
+ - svm-header-parse/HeaderParseService/resources/database/university_list/es.html
267
+ - svm-header-parse/HeaderParseService/resources/database/university_list/et.html
268
+ - svm-header-parse/HeaderParseService/resources/database/university_list/faq.html
269
+ - svm-header-parse/HeaderParseService/resources/database/university_list/fi.html
270
+ - svm-header-parse/HeaderParseService/resources/database/university_list/fj.html
271
+ - svm-header-parse/HeaderParseService/resources/database/university_list/fo.html
272
+ - svm-header-parse/HeaderParseService/resources/database/university_list/fr.html
273
+ - svm-header-parse/HeaderParseService/resources/database/university_list/geog.html
274
+ - svm-header-parse/HeaderParseService/resources/database/university_list/gr.html
275
+ - svm-header-parse/HeaderParseService/resources/database/university_list/gu.html
276
+ - svm-header-parse/HeaderParseService/resources/database/university_list/hk.html
277
+ - svm-header-parse/HeaderParseService/resources/database/university_list/hr.html
278
+ - svm-header-parse/HeaderParseService/resources/database/university_list/hu.html
279
+ - svm-header-parse/HeaderParseService/resources/database/university_list/id.html
280
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ie.html
281
+ - svm-header-parse/HeaderParseService/resources/database/university_list/il.html
282
+ - svm-header-parse/HeaderParseService/resources/database/university_list/in.html
283
+ - svm-header-parse/HeaderParseService/resources/database/university_list/is.html
284
+ - svm-header-parse/HeaderParseService/resources/database/university_list/it.html
285
+ - svm-header-parse/HeaderParseService/resources/database/university_list/jm.html
286
+ - svm-header-parse/HeaderParseService/resources/database/university_list/jo.html
287
+ - svm-header-parse/HeaderParseService/resources/database/university_list/jp.html
288
+ - svm-header-parse/HeaderParseService/resources/database/university_list/kaplan.gif
289
+ - svm-header-parse/HeaderParseService/resources/database/university_list/kr.html
290
+ - svm-header-parse/HeaderParseService/resources/database/university_list/kw.html
291
+ - svm-header-parse/HeaderParseService/resources/database/university_list/lb.html
292
+ - svm-header-parse/HeaderParseService/resources/database/university_list/linkbw2.gif
293
+ - svm-header-parse/HeaderParseService/resources/database/university_list/lk.html
294
+ - svm-header-parse/HeaderParseService/resources/database/university_list/lt.html
295
+ - svm-header-parse/HeaderParseService/resources/database/university_list/lu.html
296
+ - svm-header-parse/HeaderParseService/resources/database/university_list/lv.html
297
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ma.html
298
+ - svm-header-parse/HeaderParseService/resources/database/university_list/maczynski.gif
299
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mirror.tar
300
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mk.html
301
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mo.html
302
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mseawdm.gif
303
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mt.html
304
+ - svm-header-parse/HeaderParseService/resources/database/university_list/mx.html
305
+ - svm-header-parse/HeaderParseService/resources/database/university_list/my.html
306
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ni.html
307
+ - svm-header-parse/HeaderParseService/resources/database/university_list/nl.html
308
+ - svm-header-parse/HeaderParseService/resources/database/university_list/no.html
309
+ - svm-header-parse/HeaderParseService/resources/database/university_list/nz.html
310
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pa.html
311
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pe.html
312
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ph.html
313
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pl.html
314
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pointcom.gif
315
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pr.html
316
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ps.html
317
+ - svm-header-parse/HeaderParseService/resources/database/university_list/pt.html
318
+ - svm-header-parse/HeaderParseService/resources/database/university_list/recognition.html
319
+ - svm-header-parse/HeaderParseService/resources/database/university_list/results.html
320
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ro.html
321
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ru.html
322
+ - svm-header-parse/HeaderParseService/resources/database/university_list/sd.html
323
+ - svm-header-parse/HeaderParseService/resources/database/university_list/se.html
324
+ - svm-header-parse/HeaderParseService/resources/database/university_list/sg.html
325
+ - svm-header-parse/HeaderParseService/resources/database/university_list/si.html
326
+ - svm-header-parse/HeaderParseService/resources/database/university_list/sk.html
327
+ - svm-header-parse/HeaderParseService/resources/database/university_list/th.html
328
+ - svm-header-parse/HeaderParseService/resources/database/university_list/tr.html
329
+ - svm-header-parse/HeaderParseService/resources/database/university_list/tw.html
330
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ua.html
331
+ - svm-header-parse/HeaderParseService/resources/database/university_list/uk.html
332
+ - svm-header-parse/HeaderParseService/resources/database/university_list/univ-full.html
333
+ - svm-header-parse/HeaderParseService/resources/database/university_list/univ.html
334
+ - svm-header-parse/HeaderParseService/resources/database/university_list/uy.html
335
+ - svm-header-parse/HeaderParseService/resources/database/university_list/ve.html
336
+ - svm-header-parse/HeaderParseService/resources/database/university_list/yu.html
337
+ - svm-header-parse/HeaderParseService/resources/database/university_list/za.html
338
+ - svm-header-parse/HeaderParseService/resources/database/university_list/zm.html
339
+ - svm-header-parse/HeaderParseService/resources/database/url.txt
340
+ - svm-header-parse/HeaderParseService/resources/database/webTopWords
341
+ - svm-header-parse/HeaderParseService/resources/database/words
342
+ - svm-header-parse/HeaderParseService/resources/models/10ContextModelfold1
343
+ - svm-header-parse/HeaderParseService/resources/models/10Modelfold1
344
+ - svm-header-parse/HeaderParseService/resources/models/11ContextModelfold1
345
+ - svm-header-parse/HeaderParseService/resources/models/11Modelfold1
346
+ - svm-header-parse/HeaderParseService/resources/models/12ContextModelfold1
347
+ - svm-header-parse/HeaderParseService/resources/models/12Modelfold1
348
+ - svm-header-parse/HeaderParseService/resources/models/13ContextModelfold1
349
+ - svm-header-parse/HeaderParseService/resources/models/13Modelfold1
350
+ - svm-header-parse/HeaderParseService/resources/models/14ContextModelfold1
351
+ - svm-header-parse/HeaderParseService/resources/models/14Modelfold1
352
+ - svm-header-parse/HeaderParseService/resources/models/15ContextModelfold1
353
+ - svm-header-parse/HeaderParseService/resources/models/15Modelfold1
354
+ - svm-header-parse/HeaderParseService/resources/models/1ContextModelfold1
355
+ - svm-header-parse/HeaderParseService/resources/models/1Modelfold1
356
+ - svm-header-parse/HeaderParseService/resources/models/2ContextModelfold1
357
+ - svm-header-parse/HeaderParseService/resources/models/2Modelfold1
358
+ - svm-header-parse/HeaderParseService/resources/models/3ContextModelfold1
359
+ - svm-header-parse/HeaderParseService/resources/models/3Modelfold1
360
+ - svm-header-parse/HeaderParseService/resources/models/4ContextModelfold1
361
+ - svm-header-parse/HeaderParseService/resources/models/4Modelfold1
362
+ - svm-header-parse/HeaderParseService/resources/models/5ContextModelfold1
363
+ - svm-header-parse/HeaderParseService/resources/models/5Modelfold1
364
+ - svm-header-parse/HeaderParseService/resources/models/6ContextModelfold1
365
+ - svm-header-parse/HeaderParseService/resources/models/6Modelfold1
366
+ - svm-header-parse/HeaderParseService/resources/models/7ContextModelfold1
367
+ - svm-header-parse/HeaderParseService/resources/models/7Modelfold1
368
+ - svm-header-parse/HeaderParseService/resources/models/8ContextModelfold1
369
+ - svm-header-parse/HeaderParseService/resources/models/8Modelfold1
370
+ - svm-header-parse/HeaderParseService/resources/models/9ContextModelfold1
371
+ - svm-header-parse/HeaderParseService/resources/models/9Modelfold1
372
+ - svm-header-parse/HeaderParseService/resources/models/NameSpaceModel
373
+ - svm-header-parse/HeaderParseService/resources/models/NameSpaceTrainF
374
+ - svm-header-parse/HeaderParseService/resources/models/WrapperBaseFeaDict
375
+ - svm-header-parse/HeaderParseService/resources/models/WrapperContextFeaDict
376
+ - svm-header-parse/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict
377
+ - svm-header-parse/HeaderParseService/tmp/.gitignore
378
+ - svm-header-parse/extract.pl
379
+ - parscit/.gitignore
380
+ - parscit/CHANGELOG
381
+ - parscit/COPYING
382
+ - parscit/COPYING.LESSER
383
+ - parscit/INSTALL
384
+ - parscit/README
385
+ - parscit/USAGE
386
+ - parscit/bin/archtest.pl
387
+ - parscit/bin/citeExtract.pl
388
+ - parscit/bin/conlleval.pl
389
+ - parscit/bin/headExtract.pl
390
+ - parscit/bin/parsHed/convert2TokenLevel.pl
391
+ - parscit/bin/parsHed/keywordGen.pl
392
+ - parscit/bin/parsHed/parseXmlHeader.pl
393
+ - parscit/bin/parsHed/redo.parsHed.pl
394
+ - parscit/bin/parsHed/tr2crfpp_parsHed.pl
395
+ - parscit/bin/parseRefStrings.pl
396
+ - parscit/bin/phOutput2xml.pl
397
+ - parscit/bin/redo.parsCit.pl
398
+ - parscit/bin/sectExtract.pl
399
+ - parscit/bin/sectLabel/README
400
+ - parscit/bin/sectLabel/README.txt
401
+ - parscit/bin/sectLabel/genericSect/crossValidation.rb
402
+ - parscit/bin/sectLabel/genericSect/extractFeature.rb
403
+ - parscit/bin/sectLabel/genericSectExtract.rb
404
+ - parscit/bin/sectLabel/getStructureInfo.pl
405
+ - parscit/bin/sectLabel/processOmniXML.pl
406
+ - parscit/bin/sectLabel/processOmniXML_new.pl
407
+ - parscit/bin/sectLabel/processOmniXMLv2.pl
408
+ - parscit/bin/sectLabel/processOmniXMLv3.pl
409
+ - parscit/bin/sectLabel/redo.sectLabel.pl
410
+ - parscit/bin/sectLabel/simplifyOmniXML.pl
411
+ - parscit/bin/sectLabel/single2multi.pl
412
+ - parscit/bin/sectLabel/tr2crfpp.pl
413
+ - parscit/bin/tr2crfpp.pl
414
+ - parscit/bin/xml2train.pl
415
+ - parscit/lib/CSXUtil/SafeText.pm
416
+ - parscit/lib/Omni/Config.pm
417
+ - parscit/lib/Omni/Omnicell.pm
418
+ - parscit/lib/Omni/Omnicol.pm
419
+ - parscit/lib/Omni/Omnidd.pm
420
+ - parscit/lib/Omni/Omnidoc.pm
421
+ - parscit/lib/Omni/Omniframe.pm
422
+ - parscit/lib/Omni/Omniline.pm
423
+ - parscit/lib/Omni/Omnipage.pm
424
+ - parscit/lib/Omni/Omnipara.pm
425
+ - parscit/lib/Omni/Omnirun.pm
426
+ - parscit/lib/Omni/Omnitable.pm
427
+ - parscit/lib/Omni/Omniword.pm
428
+ - parscit/lib/Omni/Traversal.pm
429
+ - parscit/lib/ParsCit/.PostProcess.pm.swp
430
+ - parscit/lib/ParsCit/Citation.pm
431
+ - parscit/lib/ParsCit/CitationContext.pm
432
+ - parscit/lib/ParsCit/Config.pm
433
+ - parscit/lib/ParsCit/Controller.pm
434
+ - parscit/lib/ParsCit/PostProcess.pm
435
+ - parscit/lib/ParsCit/PreProcess.pm
436
+ - parscit/lib/ParsCit/Tr2crfpp.pm
437
+ - parscit/lib/ParsHed/Config.pm
438
+ - parscit/lib/ParsHed/Controller.pm
439
+ - parscit/lib/ParsHed/PostProcess.pm
440
+ - parscit/lib/ParsHed/Tr2crfpp.pm
441
+ - parscit/lib/ParsHed/Tr2crfpp_token.pm
442
+ - parscit/lib/SectLabel/AAMatching.pm
443
+ - parscit/lib/SectLabel/Config.pm
444
+ - parscit/lib/SectLabel/Controller.pm
445
+ - parscit/lib/SectLabel/PostProcess.pm
446
+ - parscit/lib/SectLabel/PreProcess.pm
447
+ - parscit/lib/SectLabel/Tr2crfpp.pm
448
+ - parscit/resources/parsCit.model
449
+ - parscit/resources/parsCit.split.model
450
+ - parscit/resources/parsCitDict.txt
451
+ - parscit/resources/parsHed/bigram
452
+ - parscit/resources/parsHed/keywords
453
+ - parscit/resources/parsHed/parsHed.model
454
+ - parscit/resources/parsHed/parsHed.template
455
+ - parscit/resources/sectLabel/affiliation.model
456
+ - parscit/resources/sectLabel/author.model
457
+ - parscit/resources/sectLabel/funcWord
458
+ - parscit/resources/sectLabel/genericSect.model
459
+ - parscit/resources/sectLabel/sectLabel.config
460
+ - parscit/resources/sectLabel/sectLabel.configXml
461
+ - parscit/resources/sectLabel/sectLabel.model
438
462
  homepage: http://github.com/academia-edu/biblicit
439
463
  licenses: []
440
464
  post_install_message:
@@ -447,28 +471,38 @@ required_ruby_version: !ruby/object:Gem::Requirement
447
471
  - - ! '>='
448
472
  - !ruby/object:Gem::Version
449
473
  version: '0'
474
+ segments:
475
+ - 0
476
+ hash: 2279876521491945710
450
477
  required_rubygems_version: !ruby/object:Gem::Requirement
451
478
  none: false
452
479
  requirements:
453
480
  - - ! '>='
454
481
  - !ruby/object:Gem::Version
455
482
  version: '0'
483
+ segments:
484
+ - 0
485
+ hash: 2279876521491945710
456
486
  requirements:
457
- - java
458
- - perl
459
- - for the :citeseer algorithm, the CRF++ Conditional Random Fields library (try "which
460
- crf_test")
461
- - for the :cb2bib algorithm, the cb2bib citation extraction tool
487
+ - For PDFs, Poppler or XPDF (try "which pdftotext")
488
+ - For Postscript files, Ghostscript (try "which ps2ascii")
489
+ - For word processor files, AbiWord (try "which abiword")
490
+ - For the :citeseer algorithm, Perl, CPAN, CRF++ (try "which crf_test"), and svm-light
491
+ 5.0, aliased to svm_classify5 (try "svm_classify -h")
492
+ - For the :cb2bib algorithm, cb2Bib (try "which cb2bib")
462
493
  rubyforge_project:
463
494
  rubygems_version: 1.8.23
464
495
  signing_key:
465
496
  specification_version: 3
466
497
  summary: Extract citations from PDFs.
467
498
  test_files:
468
- - spec/biblicit/cb2bib_spec.rb
469
- - spec/biblicit/citeseer_spec.rb
499
+ - spec/biblicit/extractor_spec.rb
500
+ - spec/fixtures/Review_of_Michael_Tyes_Consciousness_Revisited.docx
501
+ - spec/fixtures/critical-infrastructures.ps
470
502
  - spec/fixtures/pdf/10.1.1.109.4049.pdf
471
503
  - spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf
472
504
  - spec/fixtures/pdf/ICINCO_2010.pdf
505
+ - spec/fixtures/txt/E06-1050.txt
506
+ - spec/fixtures/txt/sample1.txt
507
+ - spec/fixtures/txt/sample2.txt
473
508
  - spec/spec_helper.rb
474
- has_rdoc: