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 +1,232 @@
|
|
1
|
+
package Omni::Omnipara;
|
2
|
+
|
3
|
+
# Configuration
|
4
|
+
use strict;
|
5
|
+
|
6
|
+
# Local libraries
|
7
|
+
use Omni::Config;
|
8
|
+
use Omni::Omniword;
|
9
|
+
use Omni::Omnirun;
|
10
|
+
use Omni::Omniline;
|
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_bottom = undef;
|
24
|
+
my $tmp_top = undef;
|
25
|
+
my $tmp_left = undef;
|
26
|
+
my $tmp_right = undef;
|
27
|
+
my $tmp_language = undef;
|
28
|
+
my $tmp_alignment = undef;
|
29
|
+
my $tmp_spaceb = undef;
|
30
|
+
my @tmp_lines = ();
|
31
|
+
|
32
|
+
###
|
33
|
+
# A para object in Omnipage xml: a paragraph contains zero or many lines
|
34
|
+
#
|
35
|
+
# Do Hoang Nhat Huy, 09 Jan 2011
|
36
|
+
###
|
37
|
+
# Initialization
|
38
|
+
sub new
|
39
|
+
{
|
40
|
+
my ($class) = @_;
|
41
|
+
|
42
|
+
# Lines: a paragraph can have multiple lines
|
43
|
+
my @lines = ();
|
44
|
+
|
45
|
+
# Class members
|
46
|
+
my $self = { '_self' => $obj_list->{ 'OMNIPARA' },
|
47
|
+
'_raw' => undef,
|
48
|
+
'_content' => undef,
|
49
|
+
'_bottom' => undef,
|
50
|
+
'_top' => undef,
|
51
|
+
'_left' => undef,
|
52
|
+
'_right' => undef,
|
53
|
+
'_language' => undef,
|
54
|
+
'_alignment' => undef,
|
55
|
+
'_spaceb' => undef,
|
56
|
+
'_lines' => \@lines };
|
57
|
+
|
58
|
+
bless $self, $class;
|
59
|
+
return $self;
|
60
|
+
}
|
61
|
+
|
62
|
+
#
|
63
|
+
sub set_raw
|
64
|
+
{
|
65
|
+
my ($self, $raw) = @_;
|
66
|
+
|
67
|
+
# Save the raw xml <para> ... </para>
|
68
|
+
$self->{ '_raw' } = $raw;
|
69
|
+
|
70
|
+
# Parse the raw string
|
71
|
+
my $twig_roots = { $tag_list->{ 'PARA' } => 1 };
|
72
|
+
my $twig_handlers = { $tag_list->{ 'PARA' } => \&parse};
|
73
|
+
|
74
|
+
# XML::Twig
|
75
|
+
my $twig = new XML::Twig( twig_roots => $twig_roots,
|
76
|
+
twig_handlers => $twig_handlers,
|
77
|
+
pretty_print => 'indented' );
|
78
|
+
|
79
|
+
# Start the XML parsing
|
80
|
+
$twig->parse($raw);
|
81
|
+
$twig->purge;
|
82
|
+
|
83
|
+
# Copy information from temporary variables to class members
|
84
|
+
$self->{ '_bottom' } = $tmp_bottom;
|
85
|
+
$self->{ '_top' } = $tmp_top;
|
86
|
+
$self->{ '_left' } = $tmp_left;
|
87
|
+
$self->{ '_right' } = $tmp_right;
|
88
|
+
$self->{ '_language' } = $tmp_language;
|
89
|
+
$self->{ '_alignment' } = $tmp_alignment;
|
90
|
+
$self->{ '_spaceb' } = $tmp_spaceb;
|
91
|
+
|
92
|
+
# Copy all lines
|
93
|
+
@{$self->{ '_lines' } } = @tmp_lines;
|
94
|
+
|
95
|
+
# Copy content
|
96
|
+
$self->{ '_content' } = $tmp_content;
|
97
|
+
}
|
98
|
+
|
99
|
+
sub get_raw
|
100
|
+
{
|
101
|
+
my ($self) = @_;
|
102
|
+
return $self->{ '_raw' };
|
103
|
+
}
|
104
|
+
|
105
|
+
sub parse
|
106
|
+
{
|
107
|
+
my ($twig, $node) = @_;
|
108
|
+
|
109
|
+
# At first, content is blank
|
110
|
+
$tmp_content = "";
|
111
|
+
# because there's no line
|
112
|
+
@tmp_lines = ();
|
113
|
+
|
114
|
+
# Get <para> node attributes
|
115
|
+
$tmp_bottom = GetNodeAttr($node, $att_list->{ 'BOTTOM' });
|
116
|
+
$tmp_top = GetNodeAttr($node, $att_list->{ 'TOP' });
|
117
|
+
$tmp_left = GetNodeAttr($node, $att_list->{ 'LEFT' });
|
118
|
+
$tmp_right = GetNodeAttr($node, $att_list->{ 'RIGHT' });
|
119
|
+
$tmp_language = GetNodeAttr($node, $att_list->{ 'LANGUAGE' });
|
120
|
+
$tmp_alignment = GetNodeAttr($node, $att_list->{ 'ALIGN' });
|
121
|
+
$tmp_spaceb = GetNodeAttr($node, $att_list->{ 'SPACEB' });
|
122
|
+
|
123
|
+
# Check if there's any bullet
|
124
|
+
my $bullet = $node->first_child( $tag_list->{ 'BULLET' } );
|
125
|
+
my $has_bullet = (defined $bullet) ? 1 : 0;
|
126
|
+
|
127
|
+
# Check if there's any line
|
128
|
+
my @all_lines = $node->descendants( $tag_list->{ 'LINE' } );
|
129
|
+
foreach my $ln (@all_lines)
|
130
|
+
{
|
131
|
+
my $line = new Omni::Omniline();
|
132
|
+
|
133
|
+
# Set raw content
|
134
|
+
$line->set_raw($ln->sprint());
|
135
|
+
|
136
|
+
# Set bullet if needed
|
137
|
+
if ($has_bullet == 1) { $line->set_bullet('true'); }
|
138
|
+
|
139
|
+
# Update line list
|
140
|
+
push @tmp_lines, $line;
|
141
|
+
|
142
|
+
# Update content
|
143
|
+
$tmp_content = $tmp_content . $line->get_content() . "\n";
|
144
|
+
}
|
145
|
+
}
|
146
|
+
|
147
|
+
sub get_name
|
148
|
+
{
|
149
|
+
my ($self) = @_;
|
150
|
+
return $self->{ '_self' };
|
151
|
+
}
|
152
|
+
|
153
|
+
sub get_objs_ref
|
154
|
+
{
|
155
|
+
my ($self) = @_;
|
156
|
+
return $self->{ '_lines' };
|
157
|
+
}
|
158
|
+
|
159
|
+
sub get_content
|
160
|
+
{
|
161
|
+
my ($self) = @_;
|
162
|
+
return $self->{ '_content' };
|
163
|
+
}
|
164
|
+
|
165
|
+
sub get_bottom_pos
|
166
|
+
{
|
167
|
+
my ($self) = @_;
|
168
|
+
return $self->{ '_bottom' };
|
169
|
+
}
|
170
|
+
|
171
|
+
sub get_top_pos
|
172
|
+
{
|
173
|
+
my ($self) = @_;
|
174
|
+
return $self->{ '_top' };
|
175
|
+
}
|
176
|
+
|
177
|
+
sub get_left_pos
|
178
|
+
{
|
179
|
+
my ($self) = @_;
|
180
|
+
return $self->{ '_left' };
|
181
|
+
}
|
182
|
+
|
183
|
+
sub get_right_pos
|
184
|
+
{
|
185
|
+
my ($self) = @_;
|
186
|
+
return $self->{ '_right' };
|
187
|
+
}
|
188
|
+
|
189
|
+
sub get_language
|
190
|
+
{
|
191
|
+
my ($self) = @_;
|
192
|
+
return $self->{ '_language' };
|
193
|
+
}
|
194
|
+
|
195
|
+
sub get_alignment
|
196
|
+
{
|
197
|
+
my ($self) = @_;
|
198
|
+
return $self->{ '_alignment' };
|
199
|
+
}
|
200
|
+
|
201
|
+
sub get_space_before
|
202
|
+
{
|
203
|
+
my ($self) = @_;
|
204
|
+
return $self->{ '_spaceb' };
|
205
|
+
}
|
206
|
+
|
207
|
+
# Support functions
|
208
|
+
sub GetNodeAttr
|
209
|
+
{
|
210
|
+
my ($node, $attr) = @_;
|
211
|
+
return ($node->att($attr) ? $node->att($attr) : "");
|
212
|
+
}
|
213
|
+
|
214
|
+
sub SetNodeAttr
|
215
|
+
{
|
216
|
+
my ($node, $attr, $value) = @_;
|
217
|
+
$node->set_att($attr, $value);
|
218
|
+
}
|
219
|
+
|
220
|
+
sub GetNodeText
|
221
|
+
{
|
222
|
+
my ($node) = @_;
|
223
|
+
return $node->text;
|
224
|
+
}
|
225
|
+
|
226
|
+
sub SetNodeText
|
227
|
+
{
|
228
|
+
my ($node, $value) = @_;
|
229
|
+
$node->set_text($value);
|
230
|
+
}
|
231
|
+
|
232
|
+
1;
|
@@ -0,0 +1,303 @@
|
|
1
|
+
package Omni::Omnirun;
|
2
|
+
|
3
|
+
# Configuration
|
4
|
+
use strict;
|
5
|
+
|
6
|
+
# Local libraries
|
7
|
+
use Omni::Config;
|
8
|
+
use Omni::Omniword;
|
9
|
+
|
10
|
+
# Extern libraries
|
11
|
+
use XML::Twig;
|
12
|
+
use XML::Parser;
|
13
|
+
|
14
|
+
# Global variables
|
15
|
+
my $tag_list = $Omni::Config::tag_list;
|
16
|
+
my $att_list = $Omni::Config::att_list;
|
17
|
+
my $obj_list = $Omni::Config::obj_list;
|
18
|
+
|
19
|
+
# Temporary variables
|
20
|
+
my $tmp_content = undef;
|
21
|
+
my $tmp_font_face = undef;
|
22
|
+
my $tmp_font_family = undef;
|
23
|
+
my $tmp_font_pitch = undef;
|
24
|
+
my $tmp_font_size = undef;
|
25
|
+
my $tmp_spacing = undef;
|
26
|
+
my $tmp_su_script = undef; # sub-script or super-script
|
27
|
+
my $tmp_underline = undef;
|
28
|
+
my $tmp_bold = undef;
|
29
|
+
my $tmp_italic = undef;
|
30
|
+
my @tmp_words = ();
|
31
|
+
|
32
|
+
###
|
33
|
+
# A run object in Omnipage xml: a run contains zero or many words
|
34
|
+
#
|
35
|
+
# Do Hoang Nhat Huy, 07 Jan 2011
|
36
|
+
###
|
37
|
+
# Initialization
|
38
|
+
sub new
|
39
|
+
{
|
40
|
+
my ($class) = @_;
|
41
|
+
|
42
|
+
# Words: a run can have multiple words
|
43
|
+
my @words = ();
|
44
|
+
|
45
|
+
# Class members
|
46
|
+
my $self = { '_self' => $obj_list->{ 'OMNIRUN' },
|
47
|
+
'_raw' => undef,
|
48
|
+
'_content' => undef,
|
49
|
+
'_font_face' => undef,
|
50
|
+
'_font_family' => undef,
|
51
|
+
'_font_pitch' => undef,
|
52
|
+
'_font_size' => undef,
|
53
|
+
'_spacing' => undef,
|
54
|
+
'_su_script' => undef, # sub-script or super-script
|
55
|
+
'_underline' => undef,
|
56
|
+
'_bold' => undef,
|
57
|
+
'_italic' => undef,
|
58
|
+
'_words' => \@words };
|
59
|
+
|
60
|
+
bless $self, $class;
|
61
|
+
return $self;
|
62
|
+
}
|
63
|
+
|
64
|
+
#
|
65
|
+
sub set_raw
|
66
|
+
{
|
67
|
+
my ($self, $raw) = @_;
|
68
|
+
|
69
|
+
# Save the raw xml <run> ... </run>
|
70
|
+
$self->{ '_raw' } = $raw;
|
71
|
+
|
72
|
+
# Parse the raw string
|
73
|
+
my $twig_roots = { $tag_list->{ 'RUN' } => 1 };
|
74
|
+
my $twig_handlers = { $tag_list->{ 'RUN' } => \&parse};
|
75
|
+
|
76
|
+
# XML::Twig
|
77
|
+
my $twig= new XML::Twig( twig_roots => $twig_roots,
|
78
|
+
twig_handlers => $twig_handlers,
|
79
|
+
pretty_print => 'indented' );
|
80
|
+
|
81
|
+
# Start the XML parsing
|
82
|
+
$twig->parse($raw);
|
83
|
+
$twig->purge;
|
84
|
+
|
85
|
+
# Copy information from temporary variables to class members
|
86
|
+
$self->{ '_font_face' } = $tmp_font_face;
|
87
|
+
$self->{ '_font_family' } = $tmp_font_family;
|
88
|
+
$self->{ '_font_pitch' } = $tmp_font_pitch;
|
89
|
+
$self->{ '_font_size' } = $tmp_font_size;
|
90
|
+
$self->{ '_spacing' } = $tmp_spacing;
|
91
|
+
$self->{ '_su_script' } = $tmp_su_script;
|
92
|
+
$self->{ '_underline' } = $tmp_underline;
|
93
|
+
$self->{ '_bold' } = $tmp_bold;
|
94
|
+
$self->{ '_italic' } = $tmp_italic;
|
95
|
+
|
96
|
+
# Copy all words
|
97
|
+
@{ $self->{ '_words' } } = @tmp_words;
|
98
|
+
|
99
|
+
# Copy content
|
100
|
+
$self->{ '_content' } = $tmp_content;
|
101
|
+
}
|
102
|
+
|
103
|
+
sub get_raw
|
104
|
+
{
|
105
|
+
my ($self) = @_;
|
106
|
+
return $self->{ '_raw' };
|
107
|
+
}
|
108
|
+
|
109
|
+
sub parse
|
110
|
+
{
|
111
|
+
my ($twig, $node) = @_;
|
112
|
+
|
113
|
+
# Get <run> node attributes
|
114
|
+
$tmp_font_face = GetNodeAttr($node, $att_list->{ 'FONTFACE' });
|
115
|
+
$tmp_font_family = GetNodeAttr($node, $att_list->{ 'FONTFAMILY' });
|
116
|
+
$tmp_font_pitch = GetNodeAttr($node, $att_list->{ 'FONTPITCH' });
|
117
|
+
$tmp_font_size = GetNodeAttr($node, $att_list->{ 'FONTSIZE' });
|
118
|
+
$tmp_spacing = GetNodeAttr($node, $att_list->{ 'SPACING' });
|
119
|
+
$tmp_su_script = GetNodeAttr($node, $att_list->{ 'SUSCRIPT' }); # sub-script or super-script
|
120
|
+
$tmp_underline = GetNodeAttr($node, $att_list->{ 'UNDERLINE' });
|
121
|
+
$tmp_bold = GetNodeAttr($node, $att_list->{ 'BOLD' });
|
122
|
+
$tmp_italic = GetNodeAttr($node, $att_list->{ 'ITALIC' });
|
123
|
+
|
124
|
+
# At first, content is blank
|
125
|
+
$tmp_content = "";
|
126
|
+
# because there's no word
|
127
|
+
@tmp_words = ();
|
128
|
+
|
129
|
+
# Check if there's any child
|
130
|
+
my $child = $node->first_child();
|
131
|
+
|
132
|
+
# Has some child
|
133
|
+
# #PCDATA$ is the returned path from XML::Twig if $child is data content
|
134
|
+
if ((defined $child) && ($child->path() =~ m/#PCDATA$/))
|
135
|
+
{
|
136
|
+
my $content = undef;
|
137
|
+
$content = GetNodeText($node);
|
138
|
+
$content =~ s/^\s+|\s+$//g;
|
139
|
+
|
140
|
+
# Save the content
|
141
|
+
$tmp_content = $tmp_content . $content;
|
142
|
+
}
|
143
|
+
else
|
144
|
+
{
|
145
|
+
# Some type of separator
|
146
|
+
my $space_tag = $tag_list->{ 'SPACE' };
|
147
|
+
my $tab_tag = $tag_list->{ 'TAB' };
|
148
|
+
my $newline_tag = $tag_list->{ 'NEWLINE' };
|
149
|
+
my $word_tag = $tag_list->{ 'WORD' };
|
150
|
+
|
151
|
+
# Get every word in the <run> together with <space> and <tab> ...
|
152
|
+
my $obj = $node->first_child();
|
153
|
+
while (defined $obj)
|
154
|
+
{
|
155
|
+
my $xpath = $obj->path();
|
156
|
+
|
157
|
+
# if this child is <wd>
|
158
|
+
if ($xpath =~ m/\/$word_tag$/)
|
159
|
+
{
|
160
|
+
my $word = new Omni::Omniword();
|
161
|
+
|
162
|
+
# Set raw content
|
163
|
+
$word->set_raw($obj->sprint);
|
164
|
+
|
165
|
+
# Update word list
|
166
|
+
push @tmp_words, $word;
|
167
|
+
|
168
|
+
# Update content
|
169
|
+
$tmp_content = $tmp_content . $word->get_content;
|
170
|
+
}
|
171
|
+
# if this child is <space>
|
172
|
+
elsif ($xpath =~ m/\/$space_tag$/)
|
173
|
+
{
|
174
|
+
$tmp_content = $tmp_content . " ";
|
175
|
+
}
|
176
|
+
# if this child is <tab>
|
177
|
+
elsif ($xpath =~ m/\/$tab_tag$/)
|
178
|
+
{
|
179
|
+
$tmp_content = $tmp_content . "\t";
|
180
|
+
}
|
181
|
+
# if this child is <nl>
|
182
|
+
#elsif ($xpath =~ m/\/$newline_tag$/)
|
183
|
+
#{
|
184
|
+
# $tmp_content = $tmp_content . "\n";
|
185
|
+
#}
|
186
|
+
|
187
|
+
# Little brother
|
188
|
+
if ($obj->is_last_child)
|
189
|
+
{
|
190
|
+
last;
|
191
|
+
}
|
192
|
+
else
|
193
|
+
{
|
194
|
+
$obj = $obj->next_sibling();
|
195
|
+
}
|
196
|
+
}
|
197
|
+
}
|
198
|
+
}
|
199
|
+
|
200
|
+
sub add_word
|
201
|
+
{
|
202
|
+
my ($self, $word) = @_;
|
203
|
+
push @{ $self->{ '_words' } }, $word;
|
204
|
+
}
|
205
|
+
|
206
|
+
sub get_name
|
207
|
+
{
|
208
|
+
my ($self) = @_;
|
209
|
+
return $self->{ '_self' };
|
210
|
+
}
|
211
|
+
|
212
|
+
sub get_objs_ref
|
213
|
+
{
|
214
|
+
my ($self) = @_;
|
215
|
+
return $self->{ '_words' };
|
216
|
+
}
|
217
|
+
|
218
|
+
sub get_content
|
219
|
+
{
|
220
|
+
my ($self) = @_;
|
221
|
+
return $self->{ '_content' };
|
222
|
+
}
|
223
|
+
|
224
|
+
sub get_font_face
|
225
|
+
{
|
226
|
+
my ($self) = @_;
|
227
|
+
return $self->{ '_font_face' };
|
228
|
+
}
|
229
|
+
|
230
|
+
sub get_font_family
|
231
|
+
{
|
232
|
+
my ($self) = @_;
|
233
|
+
return $self->{ '_font_family' };
|
234
|
+
}
|
235
|
+
|
236
|
+
sub get_font_pitch
|
237
|
+
{
|
238
|
+
my ($self) = @_;
|
239
|
+
return $self->{ '_font_pitch' };
|
240
|
+
}
|
241
|
+
|
242
|
+
sub get_font_size
|
243
|
+
{
|
244
|
+
my ($self) = @_;
|
245
|
+
return $self->{ '_font_size' };
|
246
|
+
}
|
247
|
+
|
248
|
+
sub get_spacing
|
249
|
+
{
|
250
|
+
my ($self) = @_;
|
251
|
+
return $self->{ '_spacing' };
|
252
|
+
}
|
253
|
+
|
254
|
+
sub get_suscript
|
255
|
+
{
|
256
|
+
my ($self) = @_;
|
257
|
+
return $self->{ '_su_script' };
|
258
|
+
}
|
259
|
+
|
260
|
+
sub get_underline
|
261
|
+
{
|
262
|
+
my ($self) = @_;
|
263
|
+
return $self->{ '_underline' };
|
264
|
+
}
|
265
|
+
|
266
|
+
sub get_bold
|
267
|
+
{
|
268
|
+
my ($self) = @_;
|
269
|
+
return $self->{ '_bold' };
|
270
|
+
}
|
271
|
+
|
272
|
+
sub get_italic
|
273
|
+
{
|
274
|
+
my ($self) = @_;
|
275
|
+
return $self->{ '_italic' };
|
276
|
+
}
|
277
|
+
|
278
|
+
# Support functions
|
279
|
+
sub GetNodeAttr
|
280
|
+
{
|
281
|
+
my ($node, $attr) = @_;
|
282
|
+
return ($node->att($attr) ? $node->att($attr) : "");
|
283
|
+
}
|
284
|
+
|
285
|
+
sub SetNodeAttr
|
286
|
+
{
|
287
|
+
my ($node, $attr, $value) = @_;
|
288
|
+
$node->set_att($attr, $value);
|
289
|
+
}
|
290
|
+
|
291
|
+
sub GetNodeText
|
292
|
+
{
|
293
|
+
my ($node) = @_;
|
294
|
+
return $node->text;
|
295
|
+
}
|
296
|
+
|
297
|
+
sub SetNodeText
|
298
|
+
{
|
299
|
+
my ($node, $value) = @_;
|
300
|
+
$node->set_text($value);
|
301
|
+
}
|
302
|
+
|
303
|
+
1;
|