biblicit 1.0 → 2.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitmodules +3 -0
- data/Gemfile +1 -1
- data/README.md +125 -30
- data/Rakefile +22 -0
- data/biblicit.gemspec +9 -7
- data/lib/biblicit/cb2bib.rb +10 -11
- data/lib/biblicit/citeseer.rb +14 -26
- data/lib/biblicit/extractor.rb +40 -19
- data/lib/biblicit/parscit.rb +38 -0
- data/parscit/.gitignore +8 -0
- data/parscit/CHANGELOG +125 -0
- data/parscit/COPYING +674 -0
- data/parscit/COPYING.LESSER +165 -0
- data/parscit/INSTALL +105 -0
- data/parscit/README +97 -0
- data/{perl/ParsCit/README.TXT → parscit/USAGE} +25 -15
- data/parscit/bin/archtest.pl +31 -0
- data/parscit/bin/citeExtract.pl +562 -0
- data/parscit/bin/conlleval.pl +315 -0
- data/parscit/bin/headExtract.pl +40 -0
- data/parscit/bin/parsHed/convert2TokenLevel.pl +138 -0
- data/parscit/bin/parsHed/keywordGen.pl +308 -0
- data/parscit/bin/parsHed/parseXmlHeader.pl +141 -0
- data/parscit/bin/parsHed/redo.parsHed.pl +198 -0
- data/parscit/bin/parsHed/tr2crfpp_parsHed.pl +521 -0
- data/parscit/bin/parseRefStrings.pl +102 -0
- data/parscit/bin/phOutput2xml.pl +223 -0
- data/parscit/bin/redo.parsCit.pl +105 -0
- data/parscit/bin/sectExtract.pl +149 -0
- data/parscit/bin/sectLabel/README +110 -0
- data/parscit/bin/sectLabel/README.txt +110 -0
- data/parscit/bin/sectLabel/genericSect/crossValidation.rb +98 -0
- data/parscit/bin/sectLabel/genericSect/extractFeature.rb +104 -0
- data/parscit/bin/sectLabel/genericSectExtract.rb +53 -0
- data/parscit/bin/sectLabel/getStructureInfo.pl +156 -0
- data/parscit/bin/sectLabel/processOmniXML.pl +1427 -0
- data/parscit/bin/sectLabel/processOmniXML_new.pl +1025 -0
- data/parscit/bin/sectLabel/processOmniXMLv2.pl +1529 -0
- data/parscit/bin/sectLabel/processOmniXMLv3.pl +964 -0
- data/parscit/bin/sectLabel/redo.sectLabel.pl +219 -0
- data/parscit/bin/sectLabel/simplifyOmniXML.pl +382 -0
- data/parscit/bin/sectLabel/single2multi.pl +190 -0
- data/parscit/bin/sectLabel/tr2crfpp.pl +158 -0
- data/parscit/bin/tr2crfpp.pl +260 -0
- data/parscit/bin/xml2train.pl +193 -0
- data/parscit/lib/CSXUtil/SafeText.pm +130 -0
- data/parscit/lib/Omni/Config.pm +93 -0
- data/parscit/lib/Omni/Omnicell.pm +263 -0
- data/parscit/lib/Omni/Omnicol.pm +292 -0
- data/parscit/lib/Omni/Omnidd.pm +328 -0
- data/parscit/lib/Omni/Omnidoc.pm +153 -0
- data/parscit/lib/Omni/Omniframe.pm +223 -0
- data/parscit/lib/Omni/Omniline.pm +423 -0
- data/parscit/lib/Omni/Omnipage.pm +282 -0
- data/parscit/lib/Omni/Omnipara.pm +232 -0
- data/parscit/lib/Omni/Omnirun.pm +303 -0
- data/parscit/lib/Omni/Omnitable.pm +336 -0
- data/parscit/lib/Omni/Omniword.pm +162 -0
- data/parscit/lib/Omni/Traversal.pm +313 -0
- data/parscit/lib/ParsCit/.PostProcess.pm.swp +0 -0
- data/parscit/lib/ParsCit/Citation.pm +737 -0
- data/parscit/lib/ParsCit/CitationContext.pm +220 -0
- data/parscit/lib/ParsCit/Config.pm +35 -0
- data/parscit/lib/ParsCit/Controller.pm +653 -0
- data/parscit/lib/ParsCit/PostProcess.pm +505 -0
- data/parscit/lib/ParsCit/PreProcess.pm +1041 -0
- data/parscit/lib/ParsCit/Tr2crfpp.pm +1195 -0
- data/parscit/lib/ParsHed/Config.pm +49 -0
- data/parscit/lib/ParsHed/Controller.pm +143 -0
- data/parscit/lib/ParsHed/PostProcess.pm +322 -0
- data/parscit/lib/ParsHed/Tr2crfpp.pm +448 -0
- data/{perl/ParsCit/lib/ParsCit/Tr2crfpp.pm → parscit/lib/ParsHed/Tr2crfpp_token.pm} +22 -21
- data/parscit/lib/SectLabel/AAMatching.pm +1949 -0
- data/parscit/lib/SectLabel/Config.pm +88 -0
- data/parscit/lib/SectLabel/Controller.pm +332 -0
- data/parscit/lib/SectLabel/PostProcess.pm +425 -0
- data/parscit/lib/SectLabel/PreProcess.pm +116 -0
- data/parscit/lib/SectLabel/Tr2crfpp.pm +1246 -0
- data/parscit/resources/parsCit.model +0 -0
- data/parscit/resources/parsCit.split.model +0 -0
- data/{perl/ParsCit → parscit}/resources/parsCitDict.txt +205 -0
- data/parscit/resources/parsHed/bigram +10 -0
- data/parscit/resources/parsHed/keywords +10 -0
- data/parscit/resources/parsHed/parsHed.model +0 -0
- data/parscit/resources/parsHed/parsHed.template +178 -0
- data/parscit/resources/sectLabel/affiliation.model +0 -0
- data/parscit/resources/sectLabel/author.model +0 -0
- data/parscit/resources/sectLabel/funcWord +320 -0
- data/parscit/resources/sectLabel/genericSect.model +0 -0
- data/parscit/resources/sectLabel/sectLabel.config +42 -0
- data/parscit/resources/sectLabel/sectLabel.configXml +42 -0
- data/parscit/resources/sectLabel/sectLabel.model +0 -0
- data/sh/convert_to_text.sh +20 -0
- data/spec/biblicit/extractor_spec.rb +121 -0
- data/spec/fixtures/Review_of_Michael_Tyes_Consciousness_Revisited.docx +0 -0
- data/spec/fixtures/critical-infrastructures.ps +63951 -0
- data/spec/fixtures/txt/E06-1050.txt +867 -0
- data/spec/fixtures/txt/sample1.txt +902 -0
- data/spec/fixtures/txt/sample2.txt +394 -0
- data/spec/spec_helper.rb +3 -0
- data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/Function.pm +2 -20
- data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm +0 -7
- data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/Parser.pm +0 -2
- data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm +0 -7
- data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/Config/API_Config.pm +6 -1
- data/svm-header-parse/HeaderParseService/tmp/.gitignore +4 -0
- data/svm-header-parse/extract.pl +75 -0
- metadata +351 -317
- data/perl/DocFilter/lib/DocFilter/Config.pm +0 -35
- data/perl/DocFilter/lib/DocFilter/Filter.pm +0 -51
- data/perl/FileConversionService/README.TXT +0 -11
- data/perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar +0 -0
- data/perl/FileConversionService/lib/CSXUtil/SafeText.pm +0 -140
- data/perl/FileConversionService/lib/FileConverter/CheckSum.pm +0 -77
- data/perl/FileConversionService/lib/FileConverter/Compression.pm +0 -137
- data/perl/FileConversionService/lib/FileConverter/Config.pm +0 -57
- data/perl/FileConversionService/lib/FileConverter/Controller.pm +0 -191
- data/perl/FileConversionService/lib/FileConverter/JODConverter.pm +0 -61
- data/perl/FileConversionService/lib/FileConverter/PDFBox.pm +0 -69
- data/perl/FileConversionService/lib/FileConverter/PSConverter.pm +0 -69
- data/perl/FileConversionService/lib/FileConverter/PSToText.pm +0 -88
- data/perl/FileConversionService/lib/FileConverter/Prescript.pm +0 -68
- data/perl/FileConversionService/lib/FileConverter/TET.pm +0 -75
- data/perl/FileConversionService/lib/FileConverter/Utils.pm +0 -130
- data/perl/HeaderParseService/lib/CSXUtil/SafeText.pm +0 -140
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt +0 -24330
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed +0 -27506
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old +0 -26495
- data/perl/HeaderParseService/resources/data/tagged_headers.txt +0 -40668
- data/perl/HeaderParseService/resources/data/test_header.txt +0 -31
- data/perl/HeaderParseService/resources/data/test_header.txt.parsed +0 -31
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8 +0 -23
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9 +0 -23
- data/perl/ParsCit/crfpp/traindata/parsCit.template +0 -60
- data/perl/ParsCit/crfpp/traindata/parsCit.train.data +0 -12104
- data/perl/ParsCit/crfpp/traindata/tagged_references.txt +0 -500
- data/perl/ParsCit/lib/CSXUtil/SafeText.pm +0 -140
- data/perl/ParsCit/lib/ParsCit/Citation.pm +0 -462
- data/perl/ParsCit/lib/ParsCit/CitationContext.pm +0 -132
- data/perl/ParsCit/lib/ParsCit/Config.pm +0 -46
- data/perl/ParsCit/lib/ParsCit/Controller.pm +0 -306
- data/perl/ParsCit/lib/ParsCit/PostProcess.pm +0 -367
- data/perl/ParsCit/lib/ParsCit/PreProcess.pm +0 -333
- data/perl/ParsCit/resources/parsCit.model +0 -0
- data/perl/extract.pl +0 -199
- data/spec/biblicit/cb2bib_spec.rb +0 -48
- data/spec/biblicit/citeseer_spec.rb +0 -40
- /data/{perl → svm-header-parse}/HeaderParseService/README.TXT +0 -0
- /data/{perl/DocFilter → svm-header-parse/HeaderParseService}/lib/CSXUtil/SafeText.pm +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/50states +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AddrTopWords.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AffiTopWords.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/AffiTopWordsAll.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/ChineseSurNames.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/Csurnames.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/Csurnames_spec.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/DomainSuffixes.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/LabeledHeader +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/README +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/TrainMulClassLines +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/TrainMulClassLines1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/abstract.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/abstractTopWords +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/addr.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/affi.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/affis.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/all_namewords_spec.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/allnamewords.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cities_US.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cities_world.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/city.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/cityname.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/country_abbr.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/countryname.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/dateTopWords +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/degree.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/email.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/excludeWords.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/female-names +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstNames.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstnames.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/firstnames_spec.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/intro.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/keyword.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/keywordTopWords +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/male-names +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/middleNames.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/month.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.label +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.label.old +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mul.processed +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mulAuthor +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/mulClassStat +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/nickname.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/nicknames.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/note.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/page.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/phone.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/postcode.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/pubnum.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/statename.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/statename.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/states_and_abbreviations.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/stopwords +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/stopwords.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surNames.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surnames.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/surnames_spec.bin +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/A.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/B.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/C.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/D.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/E.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/F.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/G.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/H.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/I.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/J.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/K.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/L.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/M.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/N.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/O.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/P.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Q.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/R.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/S.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/T.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/U.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/V.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/W.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/WCSelect.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/X.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Y.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/Z.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ae.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/am.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ar.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/at.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/au.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bd.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/be.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bg.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bh.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/blueribbon.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bm.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/bn.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/br.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ca.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ch.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cl.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cn.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/co.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cy.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/cz.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/de.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/dean-mainlink.jpg +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/dk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ec.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ee.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/eg.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/es.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/et.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/faq.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fi.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fj.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fo.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/fr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/geog.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/gr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/gu.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/hu.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/id.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ie.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/il.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/in.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/is.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/it.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jm.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jo.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/jp.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kaplan.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/kw.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lb.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/linkbw2.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lt.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lu.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/lv.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ma.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/maczynski.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mirror.tar +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mo.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mseawdm.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mt.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/mx.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/my.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ni.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/nl.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/no.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/nz.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pa.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pe.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ph.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pl.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pointcom.gif +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ps.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/pt.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/recognition.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/results.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ro.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ru.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sd.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/se.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sg.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/si.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/sk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/th.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/tr.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/tw.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ua.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/uk.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/univ-full.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/univ.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/uy.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/ve.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/yu.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/za.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list/zm.html +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/university_list.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/url.txt +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/webTopWords +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/database/words +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/10ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/10Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/11ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/11Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/12ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/12Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/13ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/13Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/14ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/14Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/15ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/15Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/1ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/1Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/2ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/2Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/3ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/3Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/4ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/4Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/5ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/5Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/6ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/6Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/7ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/7Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/8ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/8Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/9ContextModelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/9Modelfold1 +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/NameSpaceModel +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/NameSpaceTrainF +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperBaseFeaDict +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperContextFeaDict +0 -0
- /data/{perl → svm-header-parse}/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict +0 -0
@@ -0,0 +1,313 @@
|
|
1
|
+
package Omni::Traversal;
|
2
|
+
|
3
|
+
# Configuration
|
4
|
+
use strict;
|
5
|
+
|
6
|
+
# Local libraries
|
7
|
+
use Omni::Config;
|
8
|
+
|
9
|
+
# Omnilib configuration: object name
|
10
|
+
my $obj_list = $Omni::Config::obj_list;
|
11
|
+
|
12
|
+
###
|
13
|
+
# 16 Feb 2010: Do Hoang Nhat Huy
|
14
|
+
# Omni lib is used to handle the Omnipage XML in a generic
|
15
|
+
# and 'elegent' way. The hierachical structure of the classes
|
16
|
+
# reflects the XML tree as follow
|
17
|
+
# Omnidoc
|
18
|
+
# |
|
19
|
+
# Omnipage (obviously, one document can have many pages)
|
20
|
+
# |__________________________________
|
21
|
+
# || ||
|
22
|
+
# Omnicol (columns in a page) Omnidd (image?)
|
23
|
+
# | |
|
24
|
+
# | Omnidd (nested)
|
25
|
+
# |_________________________________|
|
26
|
+
# | |
|
27
|
+
# Omnipara (a paragraph) Omnitable (a table)
|
28
|
+
# | |
|
29
|
+
# | Omnicell (a cell)
|
30
|
+
# | |
|
31
|
+
# | Omnipara (a paragraph)
|
32
|
+
# |_________________________________|
|
33
|
+
# |
|
34
|
+
# Omniline (a line)
|
35
|
+
# |
|
36
|
+
# Omnirun (a run, text of the same format)
|
37
|
+
# |
|
38
|
+
# Omniword (an individual word)
|
39
|
+
#
|
40
|
+
# This module provide a generic way to travel the whole tree
|
41
|
+
# to access each line of the document. Each line will have a
|
42
|
+
# group of identification (index) as follow
|
43
|
+
# page id;
|
44
|
+
# column id or dd id;
|
45
|
+
# column id or dd id;*
|
46
|
+
# table id;
|
47
|
+
# cell id;
|
48
|
+
# para id;
|
49
|
+
# line id;
|
50
|
+
# *: both dd and column can be nested inside each other
|
51
|
+
###
|
52
|
+
|
53
|
+
###
|
54
|
+
# Huydhn: collect lines whose addresses are selected
|
55
|
+
###
|
56
|
+
sub OmniCollector
|
57
|
+
{
|
58
|
+
my ($doc, $line_addrs, $need_obj) = @_;
|
59
|
+
|
60
|
+
# All the line
|
61
|
+
my @line_content = ();
|
62
|
+
|
63
|
+
# Check the validity
|
64
|
+
if (scalar(@{ $line_addrs }) == 0) { return (\@line_content); }
|
65
|
+
|
66
|
+
# Current position
|
67
|
+
my %current = ();
|
68
|
+
#
|
69
|
+
my $addr_index = 0;
|
70
|
+
|
71
|
+
# All pages in the document
|
72
|
+
my $pages = $doc->get_objs_ref();
|
73
|
+
|
74
|
+
# From page, To page
|
75
|
+
my $start_page = $line_addrs->[ 0 ]->{ 'L1' };
|
76
|
+
my $end_page = $line_addrs->[ -1 ]->{ 'L1' };
|
77
|
+
|
78
|
+
# Break condition: $line_pos is empty or all lines have been retrieved
|
79
|
+
my $break = 0;
|
80
|
+
|
81
|
+
# Tree traveling is 'not' fun. Seriously.
|
82
|
+
# This is like a dungeon seige.
|
83
|
+
for (my $x = $start_page; $x <= $end_page; $x++)
|
84
|
+
{
|
85
|
+
# Column or dd
|
86
|
+
my $level_2 = $pages->[ $x ]->get_objs_ref();
|
87
|
+
my $start_l2 = ($x == $line_addrs->[ 0 ]->{ 'L1' }) ?
|
88
|
+
$line_addrs->[ 0 ]->{ 'L2' } : 0;
|
89
|
+
my $end_l2 = ($x == $line_addrs->[ -1 ]->{ 'L1' }) ?
|
90
|
+
$line_addrs->[ -1 ]->{ 'L2' } : (scalar(@{ $level_2 }) - 1);
|
91
|
+
|
92
|
+
for (my $y = $start_l2; $y <= $end_l2; $y++)
|
93
|
+
{
|
94
|
+
# Table or paragraph
|
95
|
+
my $level_3 = $level_2->[ $y ]->get_objs_ref();
|
96
|
+
my $start_l3 = (($x == $line_addrs->[ 0 ]->{ 'L1' }) && ($y == $line_addrs->[ 0 ]->{ 'L2' })) ?
|
97
|
+
$line_addrs->[ 0 ]->{ 'L3' } : 0;
|
98
|
+
my $end_l3 = (($x == $line_addrs->[ -1 ]->{ 'L1' }) && ($y == $line_addrs->[ -1 ]->{ 'L2' })) ?
|
99
|
+
$line_addrs->[ -1 ]->{ 'L3' } : (scalar(@{ $level_3 }) - 1);
|
100
|
+
|
101
|
+
for (my $z = $start_l3; $z <= $end_l3; $z++)
|
102
|
+
{
|
103
|
+
# Is a paragraph
|
104
|
+
if ($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNIPARA' })
|
105
|
+
{
|
106
|
+
# Line or cell
|
107
|
+
my $level_4 = $level_3->[ $z ]->get_objs_ref();
|
108
|
+
my $start_l4 = (($x == $line_addrs->[ 0 ]->{ 'L1' }) && ($y == $line_addrs->[ 0 ]->{ 'L2' }) && ($z == $line_addrs->[ 0 ]->{ 'L3' })) ?
|
109
|
+
$line_addrs->[ 0 ]->{ 'L4' } : 0;
|
110
|
+
my $end_l4 = (($x == $line_addrs->[ -1 ]->{ 'L1' }) && ($y == $line_addrs->[ -1 ]->{ 'L2' }) && ($z == $line_addrs->[ -1 ]->{ 'L3' })) ?
|
111
|
+
$line_addrs->[ -1 ]->{ 'L4' } : (scalar(@{ $level_4 }) - 1);
|
112
|
+
|
113
|
+
# Lines
|
114
|
+
for (my $t = $start_l4; $t <= $end_l4; $t++)
|
115
|
+
{
|
116
|
+
# Only keep selected line
|
117
|
+
if (($x == $line_addrs->[ $addr_index ]{ 'L1' }) &&
|
118
|
+
($y == $line_addrs->[ $addr_index ]{ 'L2' }) &&
|
119
|
+
($z == $line_addrs->[ $addr_index ]{ 'L3' }) &&
|
120
|
+
($t == $line_addrs->[ $addr_index ]{ 'L4' }))
|
121
|
+
{
|
122
|
+
if ((! defined $need_obj) || ($need_obj == 0))
|
123
|
+
{
|
124
|
+
push @line_content, $level_4->[ $t ]->get_content();
|
125
|
+
}
|
126
|
+
else
|
127
|
+
{
|
128
|
+
push @line_content, $level_4->[ $t ];
|
129
|
+
}
|
130
|
+
|
131
|
+
# Next selected line
|
132
|
+
$addr_index++;
|
133
|
+
# Last one?
|
134
|
+
if ($addr_index == scalar(@{ $line_addrs }))
|
135
|
+
{
|
136
|
+
$break = 1;
|
137
|
+
last;
|
138
|
+
}
|
139
|
+
}
|
140
|
+
}
|
141
|
+
}
|
142
|
+
# Is a table
|
143
|
+
elsif (($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNITABLE' }) || ($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNIFRAME' }))
|
144
|
+
{
|
145
|
+
# TODO: this actually a trick to get it working for now.
|
146
|
+
# We care not about the cell inside the table but the content
|
147
|
+
# of the table only. So the table is consider a paragraph in
|
148
|
+
# which lines are its row
|
149
|
+
my @level_4 = split(/\n/, $level_3->[ $z ]->get_content());
|
150
|
+
|
151
|
+
for (my $t = 0; $t < scalar(@level_4); $t++)
|
152
|
+
{
|
153
|
+
# Current position
|
154
|
+
$current{ 'L4' } = $t;
|
155
|
+
|
156
|
+
# Only keep selected line
|
157
|
+
if (($x == $line_addrs->[ $addr_index ]{ 'L1' }) &&
|
158
|
+
($y == $line_addrs->[ $addr_index ]{ 'L2' }) &&
|
159
|
+
($z == $line_addrs->[ $addr_index ]{ 'L3' }) &&
|
160
|
+
($t == $line_addrs->[ $addr_index ]{ 'L4' }))
|
161
|
+
{
|
162
|
+
if ((! defined $need_obj) || ($need_obj == 0)) { push @line_content, $level_4[ $t ]; }
|
163
|
+
# Next selected line
|
164
|
+
$addr_index++;
|
165
|
+
# Last one?
|
166
|
+
if ($addr_index == scalar(@{ $line_addrs }))
|
167
|
+
{
|
168
|
+
$break = 1;
|
169
|
+
last;
|
170
|
+
}
|
171
|
+
}
|
172
|
+
}
|
173
|
+
}
|
174
|
+
|
175
|
+
# Break or not
|
176
|
+
if ($break == 1) { last; }
|
177
|
+
}
|
178
|
+
|
179
|
+
# Break or not
|
180
|
+
if ($break == 1) { last; }
|
181
|
+
}
|
182
|
+
|
183
|
+
# Break or not
|
184
|
+
if ($break == 1) { last; }
|
185
|
+
}
|
186
|
+
|
187
|
+
return (\@line_content);
|
188
|
+
}
|
189
|
+
|
190
|
+
###
|
191
|
+
# Huydhn: travel the Omnidoc at line level
|
192
|
+
###
|
193
|
+
sub OmniAirline
|
194
|
+
{
|
195
|
+
# Omnidoc object
|
196
|
+
# Starting position
|
197
|
+
# Ending position
|
198
|
+
# Both positons are hash with following members
|
199
|
+
# 'L1' : page
|
200
|
+
# 'L2' : collumn or dd or frame
|
201
|
+
# 'L3' : table or paragraph or frame
|
202
|
+
# 'L4' : line in paragraph or table or frame
|
203
|
+
my ($doc, $start, $end) = @_;
|
204
|
+
|
205
|
+
# All the line
|
206
|
+
my @line_pos = ();
|
207
|
+
my @line_content = ();
|
208
|
+
|
209
|
+
# Current position
|
210
|
+
my %current = ();
|
211
|
+
|
212
|
+
# All pages in the document
|
213
|
+
my $pages = $doc->get_objs_ref();
|
214
|
+
|
215
|
+
# From page, To page
|
216
|
+
my $start_page = (defined $start) ? $start->{ 'L1' } : 0;
|
217
|
+
my $end_page = (defined $end) ? $end->{ 'L1' } : (scalar(@{ $pages }) - 1);
|
218
|
+
|
219
|
+
# Tree traveling is 'not' fun. Seriously.
|
220
|
+
# This is like a dungeon seige.
|
221
|
+
for (my $x = $start_page; $x <= $end_page; $x++)
|
222
|
+
{
|
223
|
+
# Current position
|
224
|
+
$current{ 'L1' } = $x;
|
225
|
+
|
226
|
+
# Column or dd
|
227
|
+
my $level_2 = $pages->[ $x ]->get_objs_ref();
|
228
|
+
my $start_l2 = ((defined $start) && ($x == $start->{ 'L1' })) ?
|
229
|
+
$start->{ 'L2' } : 0;
|
230
|
+
my $end_l2 = ((defined $end) && ($x == $end->{ 'L1' })) ?
|
231
|
+
$end->{ 'L2' } : (scalar(@{ $level_2 }) - 1);
|
232
|
+
|
233
|
+
for (my $y = $start_l2; $y <= $end_l2; $y++)
|
234
|
+
{
|
235
|
+
# Current position
|
236
|
+
$current{ 'L2' } = $y;
|
237
|
+
|
238
|
+
# Table or paragraph
|
239
|
+
my $level_3 = $level_2->[ $y ]->get_objs_ref();
|
240
|
+
my $start_l3 = ((defined $start) && ($x == $start->{ 'L1' }) && ($y == $start->{ 'L2' })) ?
|
241
|
+
$start->{ 'L3' } : 0;
|
242
|
+
my $end_l3 = ((defined $end) &&($x == $end->{ 'L1' }) && ($y == $end->{ 'L2' })) ?
|
243
|
+
$end->{ 'L3' } : (scalar(@{ $level_3 }) - 1);
|
244
|
+
|
245
|
+
for (my $z = $start_l3; $z <= $end_l3; $z++)
|
246
|
+
{
|
247
|
+
# Current position
|
248
|
+
$current{ 'L3' } = $z;
|
249
|
+
|
250
|
+
# Is a paragraph
|
251
|
+
if ($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNIPARA' })
|
252
|
+
{
|
253
|
+
# Line or cell
|
254
|
+
my $level_4 = $level_3->[ $z ]->get_objs_ref();
|
255
|
+
my $start_l4 = ((defined $start) && ($x == $start->{ 'L1' }) && ($y == $start->{ 'L2' }) && ($z == $start->{ 'L3' })) ?
|
256
|
+
$start->{ 'L4' } : 0;
|
257
|
+
my $end_l4 = ((defined $end) && ($x == $end->{ 'L1' }) && ($y == $end->{ 'L2' }) && ($z == $end->{ 'L3' })) ?
|
258
|
+
$end->{ 'L4' } : (scalar(@{ $level_4 }) - 1);
|
259
|
+
|
260
|
+
# Lines
|
261
|
+
for (my $t = $start_l4; $t <= $end_l4; $t++)
|
262
|
+
{
|
263
|
+
# Current position
|
264
|
+
$current{ 'L4' } = $t;
|
265
|
+
|
266
|
+
# Only keep non-empty line
|
267
|
+
my $l = $level_4->[ $t ]->get_content();
|
268
|
+
$l =~ s/^\s+|\s+$//g;
|
269
|
+
|
270
|
+
if ($l ne "")
|
271
|
+
{
|
272
|
+
# Save the current position and the content of the current line
|
273
|
+
push @line_pos, { %current };
|
274
|
+
push @line_content, $level_4->[ $t ]->get_content();
|
275
|
+
}
|
276
|
+
}
|
277
|
+
}
|
278
|
+
# Is a table or frame
|
279
|
+
elsif (($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNITABLE' }) || ($level_3->[ $z ]->get_name() eq $obj_list->{ 'OMNIFRAME' }))
|
280
|
+
{
|
281
|
+
# TODO: this actually a trick to get it working for now.
|
282
|
+
# We care not about the cell inside the table but the content
|
283
|
+
# of the table only. So the table is consider a paragraph in
|
284
|
+
# which lines are its row
|
285
|
+
my @level_4 = split(/\n/, $level_3->[ $z ]->get_content());
|
286
|
+
|
287
|
+
for (my $t = 0; $t <= scalar(@level_4); $t++)
|
288
|
+
{
|
289
|
+
# Current position
|
290
|
+
$current{ 'L4' } = $t;
|
291
|
+
|
292
|
+
# Only keep non-empty line
|
293
|
+
my $l = $level_4[ $t ];
|
294
|
+
$l =~ s/^\s+|\s+$//g;
|
295
|
+
|
296
|
+
if ($l ne "")
|
297
|
+
{
|
298
|
+
# Save the current position and the content of the current line
|
299
|
+
push @line_pos, { %current };
|
300
|
+
push @line_content, $level_4[ $t ];
|
301
|
+
}
|
302
|
+
}
|
303
|
+
}
|
304
|
+
|
305
|
+
|
306
|
+
}
|
307
|
+
}
|
308
|
+
}
|
309
|
+
|
310
|
+
return (\@line_pos, \@line_content);
|
311
|
+
}
|
312
|
+
|
313
|
+
1;
|
Binary file
|