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
@@ -0,0 +1,423 @@
1
+ package Omni::Omniline;
2
+
3
+ # Configuration
4
+ use strict;
5
+
6
+ # Local libraries
7
+ use Omni::Config;
8
+ use Omni::Omniword;
9
+ use Omni::Omnirun;
10
+
11
+ # Extern libraries
12
+ use XML::Twig;
13
+ use XML::Parser;
14
+ use XML::Writer;
15
+ use XML::Writer::String;
16
+
17
+ # Global variables
18
+ my $tag_list = $Omni::Config::tag_list;
19
+ my $att_list = $Omni::Config::att_list;
20
+ my $obj_list = $Omni::Config::obj_list;
21
+
22
+ # Temporary variables
23
+ my $tmp_content = undef;
24
+ my $tmp_baseline = undef;
25
+ my $tmp_bottom = undef;
26
+ my $tmp_top = undef;
27
+ my $tmp_left = undef;
28
+ my $tmp_right = undef;
29
+ my @tmp_objs = ();
30
+
31
+ ###
32
+ # A line object in Omnipage xml: a line can contain one or many runs
33
+ #
34
+ # Do Hoang Nhat Huy, 09 Jan 2011
35
+ ###
36
+ # Initialization
37
+ sub new
38
+ {
39
+ my ($class) = @_;
40
+
41
+ # A line can have multiple runs or words
42
+ my @objs = ();
43
+
44
+ # Class members
45
+ my $self = { '_self' => $obj_list->{ 'OMNILINE' },
46
+ '_raw' => undef,
47
+ '_content' => undef,
48
+ '_baseline' => undef,
49
+ '_bottom' => undef,
50
+ '_top' => undef,
51
+ '_left' => undef,
52
+ '_right' => undef,
53
+ '_bullet' => undef,
54
+ '_objs' => \@objs };
55
+
56
+ bless $self, $class;
57
+ return $self;
58
+ }
59
+
60
+ #
61
+ sub set_raw
62
+ {
63
+ my ($self, $raw) = @_;
64
+
65
+ # Save the raw xml <ln> ... </ln>
66
+ $self->{ '_raw' } = $raw;
67
+
68
+ # Parse the raw string
69
+ my $twig_roots = { $tag_list->{ 'LINE' } => 1 };
70
+ my $twig_handlers = { $tag_list->{ 'LINE' } => \&parse};
71
+
72
+ # XML::Twig
73
+ my $twig = new XML::Twig( twig_roots => $twig_roots,
74
+ twig_handlers => $twig_handlers,
75
+ pretty_print => 'indented' );
76
+
77
+ # Start the XML parsing
78
+ $twig->parse($raw);
79
+ $twig->purge;
80
+
81
+ # Copy information from temporary variables to class members
82
+ $self->{ '_baseline' } = $tmp_baseline;
83
+ $self->{ '_bottom' } = $tmp_bottom;
84
+ $self->{ '_top' } = $tmp_top;
85
+ $self->{ '_left' } = $tmp_left;
86
+ $self->{ '_right' } = $tmp_right;
87
+
88
+ # Copy all objects
89
+ @{ $self->{ '_objs' } } = @tmp_objs;
90
+
91
+ # Copy content
92
+ $self->{ '_content' } = $tmp_content;
93
+ }
94
+
95
+ sub get_raw
96
+ {
97
+ my ($self) = @_;
98
+ return $self->{ '_raw' };
99
+ }
100
+
101
+ sub parse
102
+ {
103
+ my ($twig, $node) = @_;
104
+
105
+ # At first, content is blank
106
+ $tmp_content = "";
107
+ # because there's no run
108
+ @tmp_objs = ();
109
+
110
+ # Get <line> node attributes
111
+ $tmp_bottom = GetNodeAttr($node, $att_list->{ 'BOTTOM' });
112
+ $tmp_top = GetNodeAttr($node, $att_list->{ 'TOP' });
113
+ $tmp_left = GetNodeAttr($node, $att_list->{ 'LEFT' });
114
+ $tmp_right = GetNodeAttr($node, $att_list->{ 'RIGHT' });
115
+ $tmp_baseline = GetNodeAttr($node, $att_list->{ 'BASELINE' });
116
+
117
+ # Get <line> node possible attributes
118
+ my $tmp_font_face = GetNodeAttr($node, $att_list->{ 'FONTFACE' });
119
+ my $tmp_font_family = GetNodeAttr($node, $att_list->{ 'FONTFAMILY' });
120
+ my $tmp_font_pitch = GetNodeAttr($node, $att_list->{ 'FONTPITCH' });
121
+ my $tmp_font_size = GetNodeAttr($node, $att_list->{ 'FONTSIZE' });
122
+ my $tmp_spacing = GetNodeAttr($node, $att_list->{ 'SPACING' });
123
+ my $tmp_su_script = GetNodeAttr($node, $att_list->{ 'SUSCRIPT' }); # sub-script or super-script
124
+ my $tmp_underline = GetNodeAttr($node, $att_list->{ 'UNDERLINE' });
125
+ my $tmp_bold = GetNodeAttr($node, $att_list->{ 'BOLD' });
126
+ my $tmp_italic = GetNodeAttr($node, $att_list->{ 'ITALIC' });
127
+
128
+ # Check if there's any run
129
+ my @all_runs = $node->descendants( $tag_list->{ 'RUN' });
130
+ # There is not
131
+ if (scalar(@all_runs) == 0)
132
+ {
133
+ my $output = XML::Writer::String->new();
134
+ my $writer = new XML::Writer(OUTPUT => $output, UNSAFE => 'true');
135
+
136
+ # Form the fake <run>
137
+ $writer->startTag( "run",
138
+ $att_list->{ 'FONTFACE' } => $tmp_font_face,
139
+ $att_list->{ 'FONTFAMILY' } => $tmp_font_family,
140
+ $att_list->{ 'FONTPITCH' } => $tmp_font_pitch,
141
+ $att_list->{ 'FONTSIZE' } => $tmp_font_size,
142
+ $att_list->{ 'SPACING' } => $tmp_spacing,
143
+ $att_list->{ 'SUSCRIPT' } => $tmp_su_script,
144
+ $att_list->{ 'UNDERLINE' } => $tmp_underline,
145
+ $att_list->{ 'BOLD' } => $tmp_bold,
146
+ $att_list->{ 'ITALIC' } => $tmp_italic );
147
+
148
+ # Get the inner line content
149
+ $writer->raw( $node->xml_string() );
150
+ $writer->endTag("run");
151
+ $writer->end();
152
+
153
+ # Fake run
154
+ my $run = new Omni::Omnirun();
155
+
156
+ # Set raw content
157
+ $run->set_raw($output->value());
158
+
159
+ # Update run list
160
+ push @tmp_objs, $run;
161
+
162
+ # Update content
163
+ $tmp_content = $tmp_content . $run->get_content();
164
+ }
165
+ else
166
+ {
167
+ # Get the first child in the line
168
+ my $child = $node->first_child();
169
+
170
+ # Some type of child
171
+ my $space_tag = $tag_list->{ 'SPACE' };
172
+ my $tab_tag = $tag_list->{ 'TAB' };
173
+ my $newline_tag = $tag_list->{ 'NEWLINE' };
174
+ my $word_tag = $tag_list->{ 'WORD' };
175
+ my $run_tag = $tag_list->{ 'RUN' };
176
+
177
+ # A damn line can contain both <run> and <wd>
178
+ while (defined $child)
179
+ {
180
+ my $xpath = $child->path();
181
+
182
+ # if this child is <run>
183
+ if ($xpath =~ m/\/$run_tag$/)
184
+ {
185
+ my $run = new Omni::Omnirun();
186
+
187
+ # Set raw content
188
+ $run->set_raw($child->sprint());
189
+
190
+ # Update object list
191
+ push @tmp_objs, $run;
192
+
193
+ # Update content
194
+ $tmp_content = $tmp_content . $run->get_content();
195
+ }
196
+ # if this child is <wd>
197
+ elsif ($xpath =~ m/\/$word_tag$/)
198
+ {
199
+ # One word can contain many <run>
200
+ my $grand_child = $child->first_child( $tag_list->{ 'RUN' } );
201
+
202
+ # The first <run> is a special child
203
+ if (defined $grand_child)
204
+ {
205
+ while (defined $grand_child)
206
+ {
207
+ # NOTE: The following code is controvery. Consider the case when a word
208
+ # contain two runs, which means that this word has two parts in two different
209
+ # format.
210
+ #
211
+ # If I want to keep all these format info, I need to consider that this word
212
+ # is actually two words with no space between them
213
+ #
214
+ # But for compatible with Thang's code, there must be only one word here and
215
+ # subsequently only one run. So I only keep the first run
216
+
217
+ # NOTE: The first <run> in <wd> will has the word position information
218
+ my $output = XML::Writer::String->new();
219
+ my $writer = new XML::Writer(OUTPUT => $output, UNSAFE => 'true');
220
+
221
+ # Form the fake <run>
222
+ $writer->startTag( "run",
223
+ $att_list->{ 'FONTFACE' } => GetNodeAttr($grand_child, $att_list->{ 'FONTFACE' }),
224
+ $att_list->{ 'FONTFAMILY' } => GetNodeAttr($grand_child, $att_list->{ 'FONTFAMILY' }),
225
+ $att_list->{ 'FONTPITCH' } => GetNodeAttr($grand_child, $att_list->{ 'FONTPITCH' }),
226
+ $att_list->{ 'FONTSIZE' } => GetNodeAttr($grand_child, $att_list->{ 'FONTSIZE' }),
227
+ $att_list->{ 'SPACING' } => GetNodeAttr($grand_child, $att_list->{ 'SPACING' }),
228
+ $att_list->{ 'SUSCRIPT' } => GetNodeAttr($grand_child, $att_list->{ 'SUSCRIPT' }),
229
+ $att_list->{ 'UNDERLINE' } => GetNodeAttr($grand_child, $att_list->{ 'UNDERLINE' }),
230
+ $att_list->{ 'BOLD' } => GetNodeAttr($grand_child, $att_list->{ 'BOLD' }),
231
+ $att_list->{ 'ITALIC' } => GetNodeAttr($grand_child, $att_list->{ 'ITALIC' }) );
232
+ # Form the fake <wd>
233
+ $writer->startTag( "wd",
234
+ $att_list->{ 'BOTTOM' } => GetNodeAttr($child, $att_list->{ 'BOTTOM' }),
235
+ $att_list->{ 'TOP' } => GetNodeAttr($child, $att_list->{ 'TOP' }),
236
+ $att_list->{ 'LEFT' } => GetNodeAttr($child, $att_list->{ 'LEFT' }),
237
+ $att_list->{ 'RIGHT' } => GetNodeAttr($child, $att_list->{ 'RIGHT' }) );
238
+
239
+ $writer->raw( $grand_child->xml_string() );
240
+ $writer->endTag("wd");
241
+ $writer->endTag("run");
242
+ $writer->end();
243
+
244
+ # Fake run
245
+ my $run = new Omni::Omnirun();
246
+
247
+ # Set raw content
248
+ $run->set_raw($output->value());
249
+
250
+ # Update run list
251
+ push @tmp_objs, $run;
252
+
253
+ # Update content
254
+ $tmp_content = $tmp_content . $run->get_content();
255
+
256
+ # Little brother
257
+ if ($grand_child->is_last_child)
258
+ {
259
+ last;
260
+ }
261
+ else
262
+ {
263
+ $grand_child = $grand_child->next_sibling( $tag_list->{ 'RUN' } );
264
+ }
265
+ }
266
+ }
267
+ # Special case: <wd> contains no <run> but stores the format itself
268
+ else
269
+ {
270
+ my $output = XML::Writer::String->new();
271
+ my $writer = new XML::Writer(OUTPUT => $output, UNSAFE => 'true');
272
+
273
+ # Form the fake <run>
274
+ $writer->startTag( "run",
275
+ $att_list->{ 'FONTFACE' } => GetNodeAttr($child, $att_list->{ 'FONTFACE' }),
276
+ $att_list->{ 'FONTFAMILY' } => GetNodeAttr($child, $att_list->{ 'FONTFAMILY' }),
277
+ $att_list->{ 'FONTPITCH' } => GetNodeAttr($child, $att_list->{ 'FONTPITCH' }),
278
+ $att_list->{ 'FONTSIZE' } => GetNodeAttr($child, $att_list->{ 'FONTSIZE' }),
279
+ $att_list->{ 'SPACING' } => GetNodeAttr($child, $att_list->{ 'SPACING' }),
280
+ $att_list->{ 'SUSCRIPT' } => GetNodeAttr($child, $att_list->{ 'SUSCRIPT' }),
281
+ $att_list->{ 'UNDERLINE' } => GetNodeAttr($child, $att_list->{ 'UNDERLINE' }),
282
+ $att_list->{ 'BOLD' } => GetNodeAttr($child, $att_list->{ 'BOLD' }),
283
+ $att_list->{ 'ITALIC' } => GetNodeAttr($child, $att_list->{ 'ITALIC' }) );
284
+ # Form the fake <wd>
285
+ $writer->startTag( "wd",
286
+ $att_list->{ 'BOTTOM' } => GetNodeAttr($child, $att_list->{ 'BOTTOM' }),
287
+ $att_list->{ 'TOP' } => GetNodeAttr($child, $att_list->{ 'TOP' }),
288
+ $att_list->{ 'LEFT' } => GetNodeAttr($child, $att_list->{ 'LEFT' }),
289
+ $att_list->{ 'RIGHT' } => GetNodeAttr($child, $att_list->{ 'RIGHT' }) );
290
+ # Get the inner <wd> content
291
+ $writer->raw( $child->xml_string() );
292
+ $writer->endTag("wd");
293
+ $writer->endTag("run");
294
+ $writer->end();
295
+
296
+ # Fake run
297
+ my $run = new Omni::Omnirun();
298
+
299
+ # Set raw content
300
+ $run->set_raw($output->value());
301
+
302
+ # Update run list
303
+ push @tmp_objs, $run;
304
+
305
+ # Update content
306
+ $tmp_content = $tmp_content . $run->get_content();
307
+ }
308
+ }
309
+ elsif ($xpath =~ m/\/$space_tag$/)
310
+ {
311
+ # Update content
312
+ $tmp_content = $tmp_content . " ";
313
+ }
314
+ elsif ($xpath =~ m/\/$tab_tag$/)
315
+ {
316
+ # Update content
317
+ $tmp_content = $tmp_content . "\t";
318
+ }
319
+ elsif ($xpath =~ m/\/$newline_tag$/)
320
+ {
321
+ # Update content
322
+ $tmp_content = $tmp_content . "\n";
323
+ }
324
+
325
+ # Little brother
326
+ if ($child->is_last_child)
327
+ {
328
+ last;
329
+ }
330
+ else
331
+ {
332
+ $child = $child->next_sibling();
333
+ }
334
+ }
335
+ }
336
+ }
337
+
338
+ sub get_bullet
339
+ {
340
+ my ($self) = @_;
341
+ return $self->{ '_bullet' };
342
+ }
343
+
344
+ sub set_bullet
345
+ {
346
+ my ($self, $bullet) = @_;
347
+ $self->{ '_bullet' } = $bullet;
348
+ }
349
+
350
+ sub get_name
351
+ {
352
+ my ($self) = @_;
353
+ return $self->{ '_self' };
354
+ }
355
+
356
+ sub get_objs_ref
357
+ {
358
+ my ($self) = @_;
359
+ return $self->{ '_objs' };
360
+ }
361
+
362
+ sub get_content
363
+ {
364
+ my ($self) = @_;
365
+ return $self->{ '_content' };
366
+ }
367
+
368
+ sub get_baseline
369
+ {
370
+ my ($self) = @_;
371
+ return $self->{ '_baseline' };
372
+ }
373
+
374
+ sub get_bottom_pos
375
+ {
376
+ my ($self) = @_;
377
+ return $self->{ '_bottom' };
378
+ }
379
+
380
+ sub get_top_pos
381
+ {
382
+ my ($self) = @_;
383
+ return $self->{ '_top' };
384
+ }
385
+
386
+ sub get_left_pos
387
+ {
388
+ my ($self) = @_;
389
+ return $self->{ '_left' };
390
+ }
391
+
392
+ sub get_right_pos
393
+ {
394
+ my ($self) = @_;
395
+ return $self->{ '_right' };
396
+ }
397
+
398
+ # Support functions
399
+ sub GetNodeAttr
400
+ {
401
+ my ($node, $attr) = @_;
402
+ return ($node->att($attr) ? $node->att($attr) : "");
403
+ }
404
+
405
+ sub SetNodeAttr
406
+ {
407
+ my ($node, $attr, $value) = @_;
408
+ $node->set_att($attr, $value);
409
+ }
410
+
411
+ sub GetNodeText
412
+ {
413
+ my ($node) = @_;
414
+ return $node->text;
415
+ }
416
+
417
+ sub SetNodeText
418
+ {
419
+ my ($node, $value) = @_;
420
+ $node->set_text($value);
421
+ }
422
+
423
+ 1;
@@ -0,0 +1,282 @@
1
+ package Omni::Omnipage;
2
+
3
+ # Configuration
4
+ use strict;
5
+
6
+ # Local libraries
7
+ use Omni::Config;
8
+ use Omni::Omnidd;
9
+ use Omni::Omnicol;
10
+ use Omni::Omniframe;
11
+
12
+ # Extern libraries
13
+ use XML::Twig;
14
+ use XML::Parser;
15
+
16
+ # Global variables
17
+ my $tag_list = $Omni::Config::tag_list;
18
+ my $att_list = $Omni::Config::att_list;
19
+ my $obj_list = $Omni::Config::obj_list;
20
+
21
+ # Temporary variables
22
+ my $tmp_content = undef;
23
+ my @tmp_objs = ();
24
+
25
+ ###
26
+ # A page object in Omnipage xml: a page contains zero or many collums
27
+ #
28
+ # Do Hoang Nhat Huy, 09 Jan 2011
29
+ ###
30
+ # Initialization
31
+ sub new
32
+ {
33
+ my ($class) = @_;
34
+
35
+ # Page: a page can have many columns, many tables, or many images
36
+ my @objs = ();
37
+
38
+ # Class members
39
+ my $self = { '_self' => $obj_list->{ 'OMNIPAGE' },
40
+ '_raw' => undef,
41
+ '_content' => undef,
42
+ '_objs' => \@objs };
43
+
44
+ bless $self, $class;
45
+ return $self;
46
+ }
47
+
48
+ #
49
+ sub set_raw
50
+ {
51
+ my ($self, $raw) = @_;
52
+
53
+ # Save the raw xml <page> ... </page>
54
+ $self->{ '_raw' } = $raw;
55
+
56
+ # Parse the raw string
57
+ my $twig_roots = { $tag_list->{ 'PAGE' } => 1 };
58
+ my $twig_handlers = { $tag_list->{ 'PAGE' } => \&parse};
59
+
60
+ # XML::Twig
61
+ my $twig = new XML::Twig( twig_roots => $twig_roots,
62
+ twig_handlers => $twig_handlers,
63
+ pretty_print => 'indented' );
64
+
65
+ # Start the XML parsing
66
+ $twig->parse($raw);
67
+ $twig->purge;
68
+
69
+ # Copy information from temporary variables to class members
70
+
71
+ # Copy all columns
72
+ @{$self->{ '_objs' } } = @tmp_objs;
73
+
74
+ # Copy content
75
+ $self->{ '_content' } = $tmp_content;
76
+ }
77
+
78
+ sub get_raw
79
+ {
80
+ my ($self) = @_;
81
+ return $self->{ '_raw' };
82
+ }
83
+
84
+ sub parse
85
+ {
86
+ my ($twig, $node) = @_;
87
+
88
+ # At first, content is blank
89
+ $tmp_content = "";
90
+ # because there's no columnm, table or image
91
+ @tmp_objs = ();
92
+
93
+ # Get <page> node attributes
94
+ # At version 16, Omnipage page does not have any interesting atribute
95
+
96
+ my $child = undef;
97
+ # Get the body text
98
+ $child = $node->first_child( $tag_list->{ 'BODY' } );
99
+ # Page with no body, return
100
+ if (! defined $child) { return; }
101
+
102
+ # Get the first child in the body text
103
+ $child = $child->first_child();
104
+
105
+ # The child of <page> is usually <section> but it's not always the case
106
+ my $section_tag = $tag_list->{ 'SECTION' };
107
+
108
+ # <dd>, <col> are usually not the children but the
109
+ # desendents of <page> but I'm not sure about this
110
+ my $dd_tag = $tag_list->{ 'DD' };
111
+ my $column_tag = $tag_list->{ 'COL' };
112
+ my $frame_tag = $tag_list->{ 'FRAME' };
113
+
114
+ # Check if there's any column or dd, what the heck is dd
115
+ while (defined $child)
116
+ {
117
+ my $xpath = $child->path();
118
+
119
+ # if this child is <section>, then <column> and <dd> tag are grandchild of <page>
120
+ if ($xpath =~ m/\/$section_tag$/)
121
+ {
122
+ # Get the first grand child
123
+ my $grand_child = $child->first_child();
124
+
125
+ # Subloop
126
+ while (defined $grand_child)
127
+ {
128
+ my $grand_xpath = $grand_child->path();
129
+
130
+ # if this child is <column>
131
+ if ($grand_xpath =~ m/\/$column_tag$/)
132
+ {
133
+ my $column = new Omni::Omnicol();
134
+
135
+ # Set raw content
136
+ $column->set_raw($grand_child->sprint());
137
+
138
+ # Update column list
139
+ push @tmp_objs, $column;
140
+
141
+ # Update content
142
+ $tmp_content = $tmp_content . $column->get_content() . "\n";
143
+ }
144
+ # if this child is <dd>
145
+ elsif ($grand_xpath =~ m/\/$dd_tag$/)
146
+ {
147
+ my $dd = new Omni::Omnidd();
148
+
149
+ # Set raw content
150
+ $dd->set_raw($child->sprint());
151
+
152
+ # Update column list
153
+ push @tmp_objs, $dd;
154
+
155
+ # Update content
156
+ $tmp_content = $tmp_content . $dd->get_content() . "\n";
157
+ }
158
+ # if this child is <frame>
159
+ elsif ($xpath =~ m/\/$frame_tag$/)
160
+ {
161
+ my $frame = new Omni::Omniframe();
162
+
163
+ # Set raw content
164
+ $frame->set_raw($child->sprint());
165
+
166
+ # Update column list
167
+ push @tmp_objs, $frame;
168
+
169
+ # Update content
170
+ $tmp_content = $tmp_content . $frame->get_content() . "\n";
171
+ }
172
+
173
+ # Little brother
174
+ if ($grand_child->is_last_child)
175
+ {
176
+ last;
177
+ }
178
+ else
179
+ {
180
+ $grand_child = $grand_child->next_sibling();
181
+ }
182
+ }
183
+ }
184
+ # if this child is <column>
185
+ elsif ($xpath =~ m/\/$column_tag$/)
186
+ {
187
+ my $column = new Omni::Omnicol();
188
+
189
+ # Set raw content
190
+ $column->set_raw($child->sprint());
191
+
192
+ # Update column list
193
+ push @tmp_objs, $column;
194
+
195
+ # Update content
196
+ $tmp_content = $tmp_content . $column->get_content() . "\n";
197
+ }
198
+ # if this child is <dd>
199
+ elsif ($xpath =~ m/\/$dd_tag$/)
200
+ {
201
+ my $dd = new Omni::Omnidd();
202
+
203
+ # Set raw content
204
+ $dd->set_raw($child->sprint());
205
+
206
+ # Update column list
207
+ push @tmp_objs, $dd;
208
+
209
+ # Update content
210
+ $tmp_content = $tmp_content . $dd->get_content() . "\n";
211
+ }
212
+ # if this child is <frame>
213
+ elsif ($xpath =~ m/\/$frame_tag$/)
214
+ {
215
+ my $frame = new Omni::Omniframe();
216
+
217
+ # Set raw content
218
+ $frame->set_raw($child->sprint());
219
+
220
+ # Update column list
221
+ push @tmp_objs, $frame;
222
+
223
+ # Update content
224
+ $tmp_content = $tmp_content . $frame->get_content() . "\n";
225
+ }
226
+
227
+ # Little brother
228
+ if ($child->is_last_child)
229
+ {
230
+ last;
231
+ }
232
+ else
233
+ {
234
+ $child = $child->next_sibling();
235
+ }
236
+ }
237
+ }
238
+
239
+ sub get_name
240
+ {
241
+ my ($self) = @_;
242
+ return $self->{ '_self' };
243
+ }
244
+
245
+ sub get_objs_ref
246
+ {
247
+ my ($self) = @_;
248
+ return $self->{ '_objs' };
249
+ }
250
+
251
+ sub get_content
252
+ {
253
+ my ($self) = @_;
254
+ return $self->{ '_content' };
255
+ }
256
+
257
+ # Support functions
258
+ sub GetNodeAttr
259
+ {
260
+ my ($node, $attr) = @_;
261
+ return ($node->att($attr) ? $node->att($attr) : "");
262
+ }
263
+
264
+ sub SetNodeAttr
265
+ {
266
+ my ($node, $attr, $value) = @_;
267
+ $node->set_att($attr, $value);
268
+ }
269
+
270
+ sub GetNodeText
271
+ {
272
+ my ($node) = @_;
273
+ return $node->text;
274
+ }
275
+
276
+ sub SetNodeText
277
+ {
278
+ my ($node, $value) = @_;
279
+ $node->set_text($value);
280
+ }
281
+
282
+ 1;