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 +1,737 @@
|
|
1
|
+
package ParsCit::Citation;
|
2
|
+
###
|
3
|
+
# Container object for citation data. Stores all metadata fields
|
4
|
+
# associated with a citation and utility methods for data access
|
5
|
+
# and transformation.
|
6
|
+
#
|
7
|
+
# Isaac Councill, 7/19/07
|
8
|
+
###
|
9
|
+
|
10
|
+
use strict;
|
11
|
+
use CSXUtil::SafeText qw(cleanAll cleanXML);
|
12
|
+
|
13
|
+
sub new
|
14
|
+
{
|
15
|
+
my ($class) = @_;
|
16
|
+
|
17
|
+
my @authors = ();
|
18
|
+
my @contexts = ();
|
19
|
+
###
|
20
|
+
# Huydhn: volume is now an array of subvolume
|
21
|
+
###
|
22
|
+
my @volumes = ();
|
23
|
+
########## modified by Nick Friedrich
|
24
|
+
### added array @positions for storing position of the marker of a context
|
25
|
+
#
|
26
|
+
# HISTORY: Nick (v081201)
|
27
|
+
#
|
28
|
+
# As Joran wrote I added functionality to find the position of a
|
29
|
+
# reference (context) in the (body)text. I added an array "positions"
|
30
|
+
# and also an add-method und get-method to Citation.pm. To find the
|
31
|
+
# positions I modified CitationContext::getCitationContext. When a
|
32
|
+
# context is found, the position of the match (subtract the context
|
33
|
+
# radius) is stored in an array. The method returns an array with the
|
34
|
+
# positions in addition to the array with the
|
35
|
+
# contexts.Controller::extractCitationsImpl is modified accordingly.
|
36
|
+
my @positions = ();
|
37
|
+
my @citStrs = (); # Thang Nov 09 add in-text citation strings e.g. Brown et al., 1990 which might differ from the marker Brown, Pietra, deSouza, Lai, Mercer, 1990
|
38
|
+
|
39
|
+
# Thang May 10 add positions (word unit, 0-based) for in-text citation strings
|
40
|
+
my @startWordPositions = (); my @endWordPositions = ();
|
41
|
+
|
42
|
+
my $self = {
|
43
|
+
'_rawString' => undef,
|
44
|
+
'_markerType' => undef,
|
45
|
+
'_marker' => undef,
|
46
|
+
'_authors' => \@authors,
|
47
|
+
'_title' => undef,
|
48
|
+
'_year' => undef,
|
49
|
+
'_publisher' => undef,
|
50
|
+
'_location' => undef,
|
51
|
+
'_booktitle' => undef,
|
52
|
+
'_journal' => undef,
|
53
|
+
'_pages' => undef,
|
54
|
+
'_volume' => \@volumes,
|
55
|
+
'_number' => undef,
|
56
|
+
'_contexts' => \@contexts,
|
57
|
+
'_tech' => undef,
|
58
|
+
'_institution' => undef,
|
59
|
+
'_editor' => undef,
|
60
|
+
'_note' => undef,
|
61
|
+
'_positions' => \@positions,
|
62
|
+
# Thang Nov 09 add in-text citation strings
|
63
|
+
'_citStrs' => \@citStrs,
|
64
|
+
# Thang May 10
|
65
|
+
'_startWordPositions' => \@startWordPositions,
|
66
|
+
'_endWordPositions' => \@endWordPositions
|
67
|
+
};
|
68
|
+
|
69
|
+
bless $self, $class;
|
70
|
+
# Our work here is done
|
71
|
+
return $self;
|
72
|
+
}
|
73
|
+
|
74
|
+
###
|
75
|
+
# Looks for various combinations of data that could be used to
|
76
|
+
# uniquely identify a citation. If too much data is missing,
|
77
|
+
# returns 0; otherwise, returns 1.
|
78
|
+
###
|
79
|
+
sub isValid
|
80
|
+
{
|
81
|
+
my ($self) = @_;
|
82
|
+
|
83
|
+
my @authors = $self->getAuthors();
|
84
|
+
my $title = $self->getTitle();
|
85
|
+
my $venue = $self->getJournal();
|
86
|
+
my $date = $self->getDate();
|
87
|
+
|
88
|
+
###
|
89
|
+
# Modified by Artemy Kolchinsky (v090625)
|
90
|
+
# added extra checks to subroutine 'isValid' in lib/ParsCit/Citation.pm.
|
91
|
+
# It helps to eliminate a lot of mis-parsed citations
|
92
|
+
###
|
93
|
+
my $rawString = $self->getString();
|
94
|
+
|
95
|
+
# Date not found in citation
|
96
|
+
if (!defined $date) { return 0; }
|
97
|
+
|
98
|
+
# Citation string over 400 characters --- probably a mistake in parsing somewhere
|
99
|
+
if (length($rawString) > 400) { return 0; }
|
100
|
+
###
|
101
|
+
# End modified by Artemy Kolchinsky (v090625)
|
102
|
+
###
|
103
|
+
|
104
|
+
if (!defined $venue) { $venue = $self->getBooktitle(); }
|
105
|
+
|
106
|
+
if ($#authors>=0 && (defined $title || defined $date)) { return 1; }
|
107
|
+
|
108
|
+
if (defined $venue && defined $date) { return 1; }
|
109
|
+
|
110
|
+
if (defined $title) { return 1; }
|
111
|
+
|
112
|
+
# Not a valid citation
|
113
|
+
return 0;
|
114
|
+
}
|
115
|
+
|
116
|
+
###
|
117
|
+
# Utility for loading in a datum based on a tag from Tr2crfpp output.
|
118
|
+
###
|
119
|
+
sub loadDataItem
|
120
|
+
{
|
121
|
+
my ($self, $tag, $data) = @_;
|
122
|
+
|
123
|
+
if ($tag eq "authors")
|
124
|
+
{
|
125
|
+
my @authors = @$data;
|
126
|
+
foreach my $auth (@authors)
|
127
|
+
{
|
128
|
+
$self->addAuthor($auth);
|
129
|
+
}
|
130
|
+
}
|
131
|
+
|
132
|
+
if ($tag eq "contexts")
|
133
|
+
{
|
134
|
+
my @contexts = @$data;
|
135
|
+
foreach my $context (@contexts)
|
136
|
+
{
|
137
|
+
$self->addContext($context);
|
138
|
+
}
|
139
|
+
}
|
140
|
+
|
141
|
+
if ($tag eq "title")
|
142
|
+
{
|
143
|
+
$self->setTitle($data);
|
144
|
+
}
|
145
|
+
|
146
|
+
if ($tag eq "date")
|
147
|
+
{
|
148
|
+
$self->setDate($data);
|
149
|
+
}
|
150
|
+
|
151
|
+
if ($tag eq "journal")
|
152
|
+
{
|
153
|
+
$self->setJournal($data);
|
154
|
+
}
|
155
|
+
|
156
|
+
if ($tag eq "booktitle")
|
157
|
+
{
|
158
|
+
$self->setBooktitle($data);
|
159
|
+
}
|
160
|
+
|
161
|
+
if ($tag eq "tech")
|
162
|
+
{
|
163
|
+
$self->setTech($data);
|
164
|
+
}
|
165
|
+
|
166
|
+
if ($tag eq "location")
|
167
|
+
{
|
168
|
+
$self->setLocation($data);
|
169
|
+
}
|
170
|
+
|
171
|
+
if ($tag eq "volume")
|
172
|
+
{
|
173
|
+
my @volumes = @$data;
|
174
|
+
foreach my $vol (@volumes)
|
175
|
+
{
|
176
|
+
$self->addVolume($vol);
|
177
|
+
}
|
178
|
+
}
|
179
|
+
|
180
|
+
if ($tag eq "note")
|
181
|
+
{
|
182
|
+
$self->setNote($data);
|
183
|
+
}
|
184
|
+
|
185
|
+
if ($tag eq "editor")
|
186
|
+
{
|
187
|
+
$self->setEditor($data);
|
188
|
+
}
|
189
|
+
|
190
|
+
if ($tag eq "publisher")
|
191
|
+
{
|
192
|
+
$self->setPublisher($data);
|
193
|
+
}
|
194
|
+
|
195
|
+
if ($tag eq "pages")
|
196
|
+
{
|
197
|
+
$self->setPages($data);
|
198
|
+
}
|
199
|
+
|
200
|
+
if ($tag eq "institution")
|
201
|
+
{
|
202
|
+
$self->setInstitution($data);
|
203
|
+
}
|
204
|
+
|
205
|
+
if ($tag eq "marker")
|
206
|
+
{
|
207
|
+
$self->setMarker($data);
|
208
|
+
}
|
209
|
+
}
|
210
|
+
|
211
|
+
##
|
212
|
+
# Returns a well-formed XML snippet containing all the data
|
213
|
+
# in a citation object.
|
214
|
+
##
|
215
|
+
sub toXML
|
216
|
+
{
|
217
|
+
my $self = shift;
|
218
|
+
|
219
|
+
my $valid = $self->isValid();
|
220
|
+
|
221
|
+
if ($valid>0)
|
222
|
+
{
|
223
|
+
$valid = "true";
|
224
|
+
}
|
225
|
+
else
|
226
|
+
{
|
227
|
+
$valid = "false";
|
228
|
+
}
|
229
|
+
|
230
|
+
# Begin citation tag
|
231
|
+
my $xml = "<citation valid=\"$valid\">\n";
|
232
|
+
|
233
|
+
my @authors = $self->getAuthors();
|
234
|
+
map { $_ =~ s/_/ /g } @authors;
|
235
|
+
|
236
|
+
# Authors
|
237
|
+
if ($#authors >= 0)
|
238
|
+
{
|
239
|
+
$xml .= "<authors>\n";
|
240
|
+
|
241
|
+
foreach my $auth (@authors)
|
242
|
+
{
|
243
|
+
cleanAll(\$auth);
|
244
|
+
$xml .= "<author>" . $auth . "</author>\n";
|
245
|
+
}
|
246
|
+
|
247
|
+
$xml .= "</authors>\n";
|
248
|
+
}
|
249
|
+
|
250
|
+
# Title
|
251
|
+
my $title = $self->getTitle();
|
252
|
+
if (defined $title)
|
253
|
+
{
|
254
|
+
cleanAll(\$title);
|
255
|
+
$xml .= "<title>" . $title . "</title>\n";
|
256
|
+
}
|
257
|
+
|
258
|
+
# Date
|
259
|
+
my $date = $self->getDate();
|
260
|
+
if (defined $date)
|
261
|
+
{
|
262
|
+
cleanAll(\$date);
|
263
|
+
$xml .= "<date>" . $date . "</date>\n";
|
264
|
+
}
|
265
|
+
|
266
|
+
# Journal name
|
267
|
+
my $journal = $self->getJournal();
|
268
|
+
if (defined $journal)
|
269
|
+
{
|
270
|
+
cleanAll(\$journal);
|
271
|
+
$xml .= "<journal>" . $journal . "</journal>\n";
|
272
|
+
}
|
273
|
+
|
274
|
+
# Book title
|
275
|
+
my $booktitle = $self->getBooktitle();
|
276
|
+
if (defined $booktitle)
|
277
|
+
{
|
278
|
+
cleanAll(\$booktitle);
|
279
|
+
$xml .= "<booktitle>" . $booktitle . "</booktitle>\n";
|
280
|
+
}
|
281
|
+
|
282
|
+
# What' title is it?
|
283
|
+
my $tech = $self->getTech();
|
284
|
+
if (defined $tech)
|
285
|
+
{
|
286
|
+
cleanAll(\$tech);
|
287
|
+
$xml .= "<tech>" . $tech . "</tech>\n";
|
288
|
+
}
|
289
|
+
|
290
|
+
my @volumes = $self->getVolumes();
|
291
|
+
if (scalar(@volumes) > 0)
|
292
|
+
{
|
293
|
+
# Main volume
|
294
|
+
cleanAll(\$volumes[ 0 ]);
|
295
|
+
$xml .= "<volume>" . $volumes[ 0 ] . "</volume>\n";
|
296
|
+
|
297
|
+
# Sub-volume, issue
|
298
|
+
for (my $i = 1; $i < scalar(@volumes); $i++)
|
299
|
+
{
|
300
|
+
cleanAll(\$volumes[ $i ]);
|
301
|
+
$xml .= "<issue>" . $volumes[ $i ] . "</issue>\n";
|
302
|
+
}
|
303
|
+
}
|
304
|
+
|
305
|
+
my $pages = $self->getPages();
|
306
|
+
if (defined $pages)
|
307
|
+
{
|
308
|
+
cleanAll(\$pages);
|
309
|
+
$xml .= "<pages>" . $pages . "</pages>\n";
|
310
|
+
}
|
311
|
+
|
312
|
+
my $editor = $self->getEditor();
|
313
|
+
if (defined $editor)
|
314
|
+
{
|
315
|
+
cleanAll(\$editor);
|
316
|
+
$xml .= "<editor>" . $editor . "</editor>\n";
|
317
|
+
}
|
318
|
+
|
319
|
+
my $publisher = $self->getPublisher();
|
320
|
+
if (defined $publisher)
|
321
|
+
{
|
322
|
+
cleanAll(\$publisher);
|
323
|
+
$xml .= "<publisher>" . $publisher . "</publisher>\n";
|
324
|
+
}
|
325
|
+
|
326
|
+
my $institution = $self->getInstitution();
|
327
|
+
if (defined $institution)
|
328
|
+
{
|
329
|
+
cleanAll(\$institution);
|
330
|
+
$xml .= "<institution>" . $institution . "</institution>\n";
|
331
|
+
}
|
332
|
+
|
333
|
+
my $location = $self->getLocation();
|
334
|
+
if (defined $location)
|
335
|
+
{
|
336
|
+
cleanAll(\$location);
|
337
|
+
$xml .= "<location>" . $location . "</location>\n";
|
338
|
+
}
|
339
|
+
|
340
|
+
my $note = $self->getNote();
|
341
|
+
if (defined $note)
|
342
|
+
{
|
343
|
+
cleanAll(\$note);
|
344
|
+
$xml .= "<note>" . $note . "</note>\n";
|
345
|
+
}
|
346
|
+
|
347
|
+
###
|
348
|
+
# Modified by Nick Friedrich (v081201)
|
349
|
+
# the xml-element "context" contains now an attribute "position"
|
350
|
+
####
|
351
|
+
my @contexts = $self->getContexts();
|
352
|
+
my @positions = $self->getPositions();
|
353
|
+
# Thang Nov 09
|
354
|
+
my @cit_strs = $self->getCitStrs();
|
355
|
+
|
356
|
+
# Thang May 10
|
357
|
+
my @start_wd_positions = $self->getStartWordPositions();
|
358
|
+
my @end_wd_positions = $self->getEndWordPositions();
|
359
|
+
|
360
|
+
if ($#contexts >= 0)
|
361
|
+
{
|
362
|
+
$xml .= "<contexts>\n";
|
363
|
+
|
364
|
+
# Print out citation's context
|
365
|
+
foreach my $context (@contexts)
|
366
|
+
{
|
367
|
+
cleanAll(\$context);
|
368
|
+
|
369
|
+
my $pos = shift(@positions);
|
370
|
+
# Thang Nov 09
|
371
|
+
my $cit_str = shift(@cit_strs);
|
372
|
+
cleanAll(\$cit_str);
|
373
|
+
|
374
|
+
# Thang May 10
|
375
|
+
my $start_wd_position = shift(@start_wd_positions);
|
376
|
+
my $end_wd_position = shift(@end_wd_positions);
|
377
|
+
|
378
|
+
$xml .= "<context";
|
379
|
+
$xml .= " position=\"" . $pos . "\"";
|
380
|
+
# Thang Nov 09
|
381
|
+
$xml .= " citStr=\"" . $cit_str . "\"";
|
382
|
+
|
383
|
+
# Thang May 10
|
384
|
+
$xml .= " startWordPosition=\"" . $start_wd_position . "\"";
|
385
|
+
$xml .= " endWordPosition=\"" . $end_wd_position . "\"";
|
386
|
+
|
387
|
+
$xml .= ">" . $context . "</context>\n";
|
388
|
+
}
|
389
|
+
|
390
|
+
$xml .= "</contexts>\n";
|
391
|
+
}
|
392
|
+
###
|
393
|
+
# End modified by Nick Friedrich (v081201)
|
394
|
+
###
|
395
|
+
|
396
|
+
my $marker = $self->getMarker();
|
397
|
+
if (defined $marker)
|
398
|
+
{
|
399
|
+
cleanAll(\$marker);
|
400
|
+
$xml .= "<marker>" . $marker . "</marker>\n";
|
401
|
+
}
|
402
|
+
|
403
|
+
my $rawString = $self->getString();
|
404
|
+
if (defined $rawString)
|
405
|
+
{
|
406
|
+
cleanXML(\$rawString);
|
407
|
+
$xml .= "<rawString>" . $rawString . "</rawString>\n";
|
408
|
+
}
|
409
|
+
|
410
|
+
$xml .= "</citation>\n";
|
411
|
+
# Our work here is done
|
412
|
+
return $xml;
|
413
|
+
|
414
|
+
} # toXML
|
415
|
+
|
416
|
+
|
417
|
+
sub getPositions
|
418
|
+
{
|
419
|
+
my ($self) = @_;
|
420
|
+
return @{$self->{'_positions'}};
|
421
|
+
}
|
422
|
+
|
423
|
+
sub addPosition
|
424
|
+
{
|
425
|
+
my ($self, $position) = @_;
|
426
|
+
my @positions = @{$self->{'_positions'}};
|
427
|
+
push @positions, $position;
|
428
|
+
$self->{'_positions'} = \@positions;
|
429
|
+
}
|
430
|
+
|
431
|
+
###
|
432
|
+
# Thang Nov 09 add in-text citation strings
|
433
|
+
###
|
434
|
+
sub getCitStrs
|
435
|
+
{
|
436
|
+
my ($self) = @_;
|
437
|
+
return @{$self->{'_citStrs'}};
|
438
|
+
}
|
439
|
+
|
440
|
+
sub addCitStr
|
441
|
+
{
|
442
|
+
my ($self, $cit_str) = @_;
|
443
|
+
my @cit_strs = @{$self->{'_citStrs'}};
|
444
|
+
push @cit_strs, $cit_str;
|
445
|
+
$self->{ '_citStrs' } = \@cit_strs;
|
446
|
+
}
|
447
|
+
###
|
448
|
+
# End Thang Nov 09 add in-text citation strings
|
449
|
+
###
|
450
|
+
|
451
|
+
###
|
452
|
+
# Thang May 10 add positions (in word unit, 0-based) for in-text citation strings
|
453
|
+
###
|
454
|
+
sub getStartWordPositions
|
455
|
+
{
|
456
|
+
my ($self) = @_;
|
457
|
+
return @{$self->{'_startWordPositions'}};
|
458
|
+
}
|
459
|
+
|
460
|
+
sub addStartWordPosition
|
461
|
+
{
|
462
|
+
my ($self, $start_wd_position) = @_;
|
463
|
+
my @start_wd_positions = @{ $self->{ '_startWordPositions' } };
|
464
|
+
push @start_wd_positions, $start_wd_position;
|
465
|
+
$self->{ '_startWordPositions' } = \@start_wd_positions;
|
466
|
+
}
|
467
|
+
|
468
|
+
sub getEndWordPositions
|
469
|
+
{
|
470
|
+
my ($self) = @_;
|
471
|
+
return @{ $self->{ '_endWordPositions' } };
|
472
|
+
}
|
473
|
+
|
474
|
+
sub addEndWordPosition
|
475
|
+
{
|
476
|
+
my ($self, $end_wd_position) = @_;
|
477
|
+
my @end_wd_positions = @{ $self->{ '_endWordPositions' } };
|
478
|
+
push @end_wd_positions, $end_wd_position;
|
479
|
+
$self->{ '_endWordPositions' } = \@end_wd_positions;
|
480
|
+
}
|
481
|
+
###
|
482
|
+
# End Thang May 10 add positions (in word unit) for in-text citation strings
|
483
|
+
###
|
484
|
+
|
485
|
+
sub getString
|
486
|
+
{
|
487
|
+
my ($self) = @_;
|
488
|
+
return $self->{ '_rawString' };
|
489
|
+
}
|
490
|
+
|
491
|
+
sub setString
|
492
|
+
{
|
493
|
+
my ($self, $str) = @_;
|
494
|
+
$self->{ '_rawString' } = $str;
|
495
|
+
}
|
496
|
+
|
497
|
+
sub getMarkerType
|
498
|
+
{
|
499
|
+
my ($self) = @_;
|
500
|
+
return $self->{ '_markerType' };
|
501
|
+
}
|
502
|
+
|
503
|
+
sub setMarkerType
|
504
|
+
{
|
505
|
+
my ($self, $marker_type) = @_;
|
506
|
+
$self->{ '_markerType' } = $marker_type;
|
507
|
+
}
|
508
|
+
|
509
|
+
sub getMarker
|
510
|
+
{
|
511
|
+
my ($self) = @_;
|
512
|
+
return $self->{ '_marker' };
|
513
|
+
}
|
514
|
+
|
515
|
+
sub setMarker
|
516
|
+
{
|
517
|
+
my ($self, $marker) = @_;
|
518
|
+
$self->{ '_marker' } = $marker;
|
519
|
+
}
|
520
|
+
|
521
|
+
sub addAuthor
|
522
|
+
{
|
523
|
+
my ($self, $author) = @_;
|
524
|
+
my @authors = @{ $self->{ '_authors' } };
|
525
|
+
push @authors, $author;
|
526
|
+
$self->{ '_authors' } = \@authors;
|
527
|
+
}
|
528
|
+
|
529
|
+
sub getAuthors
|
530
|
+
{
|
531
|
+
my ($self) = @_;
|
532
|
+
return @{ $self->{ '_authors' } };
|
533
|
+
}
|
534
|
+
|
535
|
+
sub addContext
|
536
|
+
{
|
537
|
+
my ($self, $context) = @_;
|
538
|
+
my @contexts = @{ $self->{ '_contexts' } };
|
539
|
+
push @contexts, $context;
|
540
|
+
$self->{ '_contexts' } = \@contexts;
|
541
|
+
}
|
542
|
+
|
543
|
+
sub getContexts
|
544
|
+
{
|
545
|
+
my ($self) = @_;
|
546
|
+
return @{ $self->{ '_contexts' } };
|
547
|
+
}
|
548
|
+
|
549
|
+
sub getTitle
|
550
|
+
{
|
551
|
+
my ($self) = @_;
|
552
|
+
return $self->{ '_title' };
|
553
|
+
}
|
554
|
+
|
555
|
+
sub setTitle
|
556
|
+
{
|
557
|
+
my ($self, $title) = @_;
|
558
|
+
$self->{ '_title' } = $title;
|
559
|
+
}
|
560
|
+
|
561
|
+
sub getDate
|
562
|
+
{
|
563
|
+
my $self = shift;
|
564
|
+
return $self->{ '_year' };
|
565
|
+
}
|
566
|
+
|
567
|
+
sub setDate
|
568
|
+
{
|
569
|
+
my ($self, $year) = @_;
|
570
|
+
$self->{ '_year' } = $year;
|
571
|
+
}
|
572
|
+
|
573
|
+
sub getPublisher
|
574
|
+
{
|
575
|
+
my $self = shift;
|
576
|
+
return $self->{ '_publisher' };
|
577
|
+
}
|
578
|
+
|
579
|
+
sub setPublisher
|
580
|
+
{
|
581
|
+
my ($self, $publisher) = @_;
|
582
|
+
$self->{ '_publisher' } = $publisher;
|
583
|
+
}
|
584
|
+
|
585
|
+
sub getLocation
|
586
|
+
{
|
587
|
+
my $self = shift;
|
588
|
+
return $self->{ '_location' };
|
589
|
+
}
|
590
|
+
|
591
|
+
sub setLocation
|
592
|
+
{
|
593
|
+
my ($self, $location) = @_;
|
594
|
+
$self->{ '_location' } = $location;
|
595
|
+
}
|
596
|
+
|
597
|
+
sub getBooktitle
|
598
|
+
{
|
599
|
+
my $self = shift;
|
600
|
+
return $self->{ '_booktitle' };
|
601
|
+
}
|
602
|
+
|
603
|
+
sub setBooktitle
|
604
|
+
{
|
605
|
+
my ($self, $booktitle) = @_;
|
606
|
+
$self->{ '_booktitle' } = $booktitle;
|
607
|
+
}
|
608
|
+
|
609
|
+
sub getJournal
|
610
|
+
{
|
611
|
+
my $self = shift;
|
612
|
+
return $self->{ '_journal' };
|
613
|
+
}
|
614
|
+
|
615
|
+
sub setJournal
|
616
|
+
{
|
617
|
+
my ($self, $journal) = @_;
|
618
|
+
$self->{ '_journal' } = $journal;
|
619
|
+
}
|
620
|
+
|
621
|
+
sub getPages
|
622
|
+
{
|
623
|
+
my $self = shift;
|
624
|
+
return $self->{ '_pages' };
|
625
|
+
}
|
626
|
+
|
627
|
+
sub setPages
|
628
|
+
{
|
629
|
+
my ($self, $pages) = @_;
|
630
|
+
$self->{ '_pages' } = $pages;
|
631
|
+
}
|
632
|
+
|
633
|
+
sub addVolume
|
634
|
+
{
|
635
|
+
my ($self, $volume) = @_;
|
636
|
+
my @volumes = @{ $self->{ '_volume' } };
|
637
|
+
push @volumes, $volume;
|
638
|
+
$self->{ '_volume' } = \@volumes;
|
639
|
+
}
|
640
|
+
|
641
|
+
sub getVolumes
|
642
|
+
{
|
643
|
+
my $self = shift;
|
644
|
+
###
|
645
|
+
# Huydhn: volume is now an array of sub-volume
|
646
|
+
# 18 Jan 2011
|
647
|
+
###
|
648
|
+
return @{ $self->{ '_volume' } };
|
649
|
+
}
|
650
|
+
|
651
|
+
###
|
652
|
+
# Huydhn: remove because volume is now an array of sub-volumes
|
653
|
+
###
|
654
|
+
#sub setVolume
|
655
|
+
#{
|
656
|
+
# my ($self, $volume) = @_;
|
657
|
+
# $self->{'_volume'} = $volume;
|
658
|
+
#}
|
659
|
+
#
|
660
|
+
#sub getVolume {
|
661
|
+
# my $self = shift;
|
662
|
+
# return $self->{'_volume'};
|
663
|
+
#}
|
664
|
+
|
665
|
+
sub getTech
|
666
|
+
{
|
667
|
+
my $self = shift;
|
668
|
+
return $self->{ '_tech' };
|
669
|
+
}
|
670
|
+
|
671
|
+
sub setTech
|
672
|
+
{
|
673
|
+
my ($self, $tech) = @_;
|
674
|
+
$self->{ '_tech' } = $tech;
|
675
|
+
}
|
676
|
+
|
677
|
+
sub getInstitution
|
678
|
+
{
|
679
|
+
my $self = shift;
|
680
|
+
return $self->{ '_institution' };
|
681
|
+
}
|
682
|
+
|
683
|
+
sub setInstitution
|
684
|
+
{
|
685
|
+
my ($self, $institution) = @_;
|
686
|
+
$self->{ '_institution' } = $institution;
|
687
|
+
}
|
688
|
+
|
689
|
+
sub getEditor
|
690
|
+
{
|
691
|
+
my $self = shift;
|
692
|
+
return $self->{ '_editor' };
|
693
|
+
}
|
694
|
+
|
695
|
+
sub setEditor
|
696
|
+
{
|
697
|
+
my ($self, $editor) = @_;
|
698
|
+
$self->{ '_editor' } = $editor;
|
699
|
+
}
|
700
|
+
|
701
|
+
sub getNote
|
702
|
+
{
|
703
|
+
my $self = shift;
|
704
|
+
return $self->{ '_note' };
|
705
|
+
}
|
706
|
+
|
707
|
+
sub setNote
|
708
|
+
{
|
709
|
+
my ($self, $note) = @_;
|
710
|
+
$self->{ '_note' } = $note;
|
711
|
+
}
|
712
|
+
|
713
|
+
|
714
|
+
###
|
715
|
+
# Build a marker based on the author list and publication year.
|
716
|
+
# This should be used when no marker was found during citation
|
717
|
+
# segmentation.
|
718
|
+
###
|
719
|
+
sub buildAuthYearMarker
|
720
|
+
{
|
721
|
+
my $self = shift;
|
722
|
+
|
723
|
+
my @authors = $self->getAuthors();
|
724
|
+
my @last_names = ();
|
725
|
+
|
726
|
+
foreach my $auth (@authors)
|
727
|
+
{
|
728
|
+
my @toks = split " +", $auth;
|
729
|
+
push @last_names, $toks[ $#toks ];
|
730
|
+
}
|
731
|
+
|
732
|
+
my $year = $self->getDate();
|
733
|
+
map { $_ =~ s/_/ /g } @last_names;
|
734
|
+
return join ", ", @last_names, $year;
|
735
|
+
}
|
736
|
+
|
737
|
+
1;
|