biblicit 1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +3 -0
- data/.rspec +1 -0
- data/Gemfile +6 -0
- data/LICENSE.TXT +176 -0
- data/README.md +120 -0
- data/Rakefile +8 -0
- data/biblicit.gemspec +33 -0
- data/lib/biblicit/cb2bib.rb +83 -0
- data/lib/biblicit/citeseer.rb +53 -0
- data/lib/biblicit/extractor.rb +37 -0
- data/lib/biblicit.rb +6 -0
- data/perl/DocFilter/lib/CSXUtil/SafeText.pm +140 -0
- data/perl/DocFilter/lib/DocFilter/Config.pm +35 -0
- data/perl/DocFilter/lib/DocFilter/Filter.pm +51 -0
- data/perl/FileConversionService/README.TXT +11 -0
- data/perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar +0 -0
- data/perl/FileConversionService/lib/CSXUtil/SafeText.pm +140 -0
- data/perl/FileConversionService/lib/FileConverter/CheckSum.pm +77 -0
- data/perl/FileConversionService/lib/FileConverter/Compression.pm +137 -0
- data/perl/FileConversionService/lib/FileConverter/Config.pm +57 -0
- data/perl/FileConversionService/lib/FileConverter/Controller.pm +191 -0
- data/perl/FileConversionService/lib/FileConverter/JODConverter.pm +61 -0
- data/perl/FileConversionService/lib/FileConverter/PDFBox.pm +69 -0
- data/perl/FileConversionService/lib/FileConverter/PSConverter.pm +69 -0
- data/perl/FileConversionService/lib/FileConverter/PSToText.pm +88 -0
- data/perl/FileConversionService/lib/FileConverter/Prescript.pm +68 -0
- data/perl/FileConversionService/lib/FileConverter/TET.pm +75 -0
- data/perl/FileConversionService/lib/FileConverter/Utils.pm +130 -0
- data/perl/HeaderParseService/README.TXT +80 -0
- data/perl/HeaderParseService/lib/CSXUtil/SafeText.pm +140 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm +968 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/Function.pm +2016 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm +444 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm +409 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm +537 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/Parser.pm +68 -0
- data/perl/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm +1880 -0
- data/perl/HeaderParseService/lib/HeaderParse/Config/API_Config.pm +46 -0
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt +24330 -0
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed +27506 -0
- data/perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old +26495 -0
- data/perl/HeaderParseService/resources/data/tagged_headers.txt +40668 -0
- data/perl/HeaderParseService/resources/data/test_header.txt +31 -0
- data/perl/HeaderParseService/resources/data/test_header.txt.parsed +31 -0
- data/perl/HeaderParseService/resources/database/50states +60 -0
- data/perl/HeaderParseService/resources/database/AddrTopWords.txt +17 -0
- data/perl/HeaderParseService/resources/database/AffiTopWords.txt +35 -0
- data/perl/HeaderParseService/resources/database/AffiTopWordsAll.txt +533 -0
- data/perl/HeaderParseService/resources/database/ChineseSurNames.txt +276 -0
- data/perl/HeaderParseService/resources/database/Csurnames.bin +0 -0
- data/perl/HeaderParseService/resources/database/Csurnames_spec.bin +0 -0
- data/perl/HeaderParseService/resources/database/DomainSuffixes.txt +242 -0
- data/perl/HeaderParseService/resources/database/LabeledHeader +18 -0
- data/perl/HeaderParseService/resources/database/README +2 -0
- data/perl/HeaderParseService/resources/database/TrainMulClassLines +254 -0
- data/perl/HeaderParseService/resources/database/TrainMulClassLines1 +510 -0
- data/perl/HeaderParseService/resources/database/abstract.txt +1 -0
- data/perl/HeaderParseService/resources/database/abstractTopWords +9 -0
- data/perl/HeaderParseService/resources/database/addr.txt +28 -0
- data/perl/HeaderParseService/resources/database/affi.txt +34 -0
- data/perl/HeaderParseService/resources/database/affis.bin +0 -0
- data/perl/HeaderParseService/resources/database/all_namewords_spec.bin +0 -0
- data/perl/HeaderParseService/resources/database/allnamewords.bin +0 -0
- data/perl/HeaderParseService/resources/database/cities_US.txt +4512 -0
- data/perl/HeaderParseService/resources/database/cities_world.txt +4463 -0
- data/perl/HeaderParseService/resources/database/city.txt +3150 -0
- data/perl/HeaderParseService/resources/database/cityname.txt +3151 -0
- data/perl/HeaderParseService/resources/database/country_abbr.txt +243 -0
- data/perl/HeaderParseService/resources/database/countryname.txt +262 -0
- data/perl/HeaderParseService/resources/database/dateTopWords +30 -0
- data/perl/HeaderParseService/resources/database/degree.txt +67 -0
- data/perl/HeaderParseService/resources/database/email.txt +3 -0
- data/perl/HeaderParseService/resources/database/excludeWords.txt +40 -0
- data/perl/HeaderParseService/resources/database/female-names +4960 -0
- data/perl/HeaderParseService/resources/database/firstNames.txt +8448 -0
- data/perl/HeaderParseService/resources/database/firstnames.bin +0 -0
- data/perl/HeaderParseService/resources/database/firstnames_spec.bin +0 -0
- data/perl/HeaderParseService/resources/database/intro.txt +2 -0
- data/perl/HeaderParseService/resources/database/keyword.txt +5 -0
- data/perl/HeaderParseService/resources/database/keywordTopWords +7 -0
- data/perl/HeaderParseService/resources/database/male-names +3906 -0
- data/perl/HeaderParseService/resources/database/middleNames.txt +2 -0
- data/perl/HeaderParseService/resources/database/month.txt +35 -0
- data/perl/HeaderParseService/resources/database/mul +868 -0
- data/perl/HeaderParseService/resources/database/mul.label +869 -0
- data/perl/HeaderParseService/resources/database/mul.label.old +869 -0
- data/perl/HeaderParseService/resources/database/mul.processed +762 -0
- data/perl/HeaderParseService/resources/database/mulAuthor +619 -0
- data/perl/HeaderParseService/resources/database/mulClassStat +45 -0
- data/perl/HeaderParseService/resources/database/nickname.txt +58 -0
- data/perl/HeaderParseService/resources/database/nicknames.bin +0 -0
- data/perl/HeaderParseService/resources/database/note.txt +121 -0
- data/perl/HeaderParseService/resources/database/page.txt +1 -0
- data/perl/HeaderParseService/resources/database/phone.txt +9 -0
- data/perl/HeaderParseService/resources/database/postcode.txt +54 -0
- data/perl/HeaderParseService/resources/database/pubnum.txt +45 -0
- data/perl/HeaderParseService/resources/database/statename.bin +0 -0
- data/perl/HeaderParseService/resources/database/statename.txt +73 -0
- data/perl/HeaderParseService/resources/database/states_and_abbreviations.txt +118 -0
- data/perl/HeaderParseService/resources/database/stopwords +438 -0
- data/perl/HeaderParseService/resources/database/stopwords.bin +0 -0
- data/perl/HeaderParseService/resources/database/surNames.txt +19613 -0
- data/perl/HeaderParseService/resources/database/surnames.bin +0 -0
- data/perl/HeaderParseService/resources/database/surnames_spec.bin +0 -0
- data/perl/HeaderParseService/resources/database/university_list/A.html +167 -0
- data/perl/HeaderParseService/resources/database/university_list/B.html +161 -0
- data/perl/HeaderParseService/resources/database/university_list/C.html +288 -0
- data/perl/HeaderParseService/resources/database/university_list/D.html +115 -0
- data/perl/HeaderParseService/resources/database/university_list/E.html +147 -0
- data/perl/HeaderParseService/resources/database/university_list/F.html +112 -0
- data/perl/HeaderParseService/resources/database/university_list/G.html +115 -0
- data/perl/HeaderParseService/resources/database/university_list/H.html +140 -0
- data/perl/HeaderParseService/resources/database/university_list/I.html +138 -0
- data/perl/HeaderParseService/resources/database/university_list/J.html +82 -0
- data/perl/HeaderParseService/resources/database/university_list/K.html +115 -0
- data/perl/HeaderParseService/resources/database/university_list/L.html +131 -0
- data/perl/HeaderParseService/resources/database/university_list/M.html +201 -0
- data/perl/HeaderParseService/resources/database/university_list/N.html +204 -0
- data/perl/HeaderParseService/resources/database/university_list/O.html +89 -0
- data/perl/HeaderParseService/resources/database/university_list/P.html +125 -0
- data/perl/HeaderParseService/resources/database/university_list/Q.html +49 -0
- data/perl/HeaderParseService/resources/database/university_list/R.html +126 -0
- data/perl/HeaderParseService/resources/database/university_list/S.html +296 -0
- data/perl/HeaderParseService/resources/database/university_list/T.html +156 -0
- data/perl/HeaderParseService/resources/database/university_list/U.html +800 -0
- data/perl/HeaderParseService/resources/database/university_list/V.html +75 -0
- data/perl/HeaderParseService/resources/database/university_list/W.html +144 -0
- data/perl/HeaderParseService/resources/database/university_list/WCSelect.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/X.html +44 -0
- data/perl/HeaderParseService/resources/database/university_list/Y.html +53 -0
- data/perl/HeaderParseService/resources/database/university_list/Z.html +43 -0
- data/perl/HeaderParseService/resources/database/university_list/ae.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/am.html +30 -0
- data/perl/HeaderParseService/resources/database/university_list/ar.html +35 -0
- data/perl/HeaderParseService/resources/database/university_list/at.html +43 -0
- data/perl/HeaderParseService/resources/database/university_list/au.html +82 -0
- data/perl/HeaderParseService/resources/database/university_list/bd.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/be.html +41 -0
- data/perl/HeaderParseService/resources/database/university_list/bg.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/bh.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/blueribbon.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/bm.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/bn.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/br.html +66 -0
- data/perl/HeaderParseService/resources/database/university_list/ca.html +174 -0
- data/perl/HeaderParseService/resources/database/university_list/ch.html +52 -0
- data/perl/HeaderParseService/resources/database/university_list/cl.html +40 -0
- data/perl/HeaderParseService/resources/database/university_list/cn.html +87 -0
- data/perl/HeaderParseService/resources/database/university_list/co.html +39 -0
- data/perl/HeaderParseService/resources/database/university_list/cr.html +34 -0
- data/perl/HeaderParseService/resources/database/university_list/cy.html +34 -0
- data/perl/HeaderParseService/resources/database/university_list/cz.html +44 -0
- data/perl/HeaderParseService/resources/database/university_list/de.html +128 -0
- data/perl/HeaderParseService/resources/database/university_list/dean-mainlink.jpg +0 -0
- data/perl/HeaderParseService/resources/database/university_list/dk.html +42 -0
- data/perl/HeaderParseService/resources/database/university_list/ec.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/ee.html +30 -0
- data/perl/HeaderParseService/resources/database/university_list/eg.html +29 -0
- data/perl/HeaderParseService/resources/database/university_list/es.html +68 -0
- data/perl/HeaderParseService/resources/database/university_list/et.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/faq.html +147 -0
- data/perl/HeaderParseService/resources/database/university_list/fi.html +49 -0
- data/perl/HeaderParseService/resources/database/university_list/fj.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/fo.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/fr.html +106 -0
- data/perl/HeaderParseService/resources/database/university_list/geog.html +150 -0
- data/perl/HeaderParseService/resources/database/university_list/gr.html +38 -0
- data/perl/HeaderParseService/resources/database/university_list/gu.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/hk.html +34 -0
- data/perl/HeaderParseService/resources/database/university_list/hr.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/hu.html +46 -0
- data/perl/HeaderParseService/resources/database/university_list/id.html +29 -0
- data/perl/HeaderParseService/resources/database/university_list/ie.html +49 -0
- data/perl/HeaderParseService/resources/database/university_list/il.html +35 -0
- data/perl/HeaderParseService/resources/database/university_list/in.html +109 -0
- data/perl/HeaderParseService/resources/database/university_list/is.html +32 -0
- data/perl/HeaderParseService/resources/database/university_list/it.html +75 -0
- data/perl/HeaderParseService/resources/database/university_list/jm.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/jo.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/jp.html +155 -0
- data/perl/HeaderParseService/resources/database/university_list/kaplan.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/kr.html +65 -0
- data/perl/HeaderParseService/resources/database/university_list/kw.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/lb.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/linkbw2.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/lk.html +30 -0
- data/perl/HeaderParseService/resources/database/university_list/lt.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/lu.html +34 -0
- data/perl/HeaderParseService/resources/database/university_list/lv.html +30 -0
- data/perl/HeaderParseService/resources/database/university_list/ma.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/maczynski.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/mirror.tar +0 -0
- data/perl/HeaderParseService/resources/database/university_list/mk.html +29 -0
- data/perl/HeaderParseService/resources/database/university_list/mo.html +29 -0
- data/perl/HeaderParseService/resources/database/university_list/mseawdm.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/mt.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/mx.html +68 -0
- data/perl/HeaderParseService/resources/database/university_list/my.html +39 -0
- data/perl/HeaderParseService/resources/database/university_list/ni.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/nl.html +51 -0
- data/perl/HeaderParseService/resources/database/university_list/no.html +56 -0
- data/perl/HeaderParseService/resources/database/university_list/nz.html +41 -0
- data/perl/HeaderParseService/resources/database/university_list/pa.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/pe.html +40 -0
- data/perl/HeaderParseService/resources/database/university_list/ph.html +41 -0
- data/perl/HeaderParseService/resources/database/university_list/pl.html +51 -0
- data/perl/HeaderParseService/resources/database/university_list/pointcom.gif +0 -0
- data/perl/HeaderParseService/resources/database/university_list/pr.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/ps.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/pt.html +45 -0
- data/perl/HeaderParseService/resources/database/university_list/recognition.html +69 -0
- data/perl/HeaderParseService/resources/database/university_list/results.html +71 -0
- data/perl/HeaderParseService/resources/database/university_list/ro.html +38 -0
- data/perl/HeaderParseService/resources/database/university_list/ru.html +48 -0
- data/perl/HeaderParseService/resources/database/university_list/sd.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/se.html +57 -0
- data/perl/HeaderParseService/resources/database/university_list/sg.html +33 -0
- data/perl/HeaderParseService/resources/database/university_list/si.html +30 -0
- data/perl/HeaderParseService/resources/database/university_list/sk.html +35 -0
- data/perl/HeaderParseService/resources/database/university_list/th.html +45 -0
- data/perl/HeaderParseService/resources/database/university_list/tr.html +44 -0
- data/perl/HeaderParseService/resources/database/university_list/tw.html +76 -0
- data/perl/HeaderParseService/resources/database/university_list/ua.html +29 -0
- data/perl/HeaderParseService/resources/database/university_list/uk.html +168 -0
- data/perl/HeaderParseService/resources/database/university_list/univ-full.html +3166 -0
- data/perl/HeaderParseService/resources/database/university_list/univ.html +122 -0
- data/perl/HeaderParseService/resources/database/university_list/uy.html +31 -0
- data/perl/HeaderParseService/resources/database/university_list/ve.html +34 -0
- data/perl/HeaderParseService/resources/database/university_list/yu.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list/za.html +46 -0
- data/perl/HeaderParseService/resources/database/university_list/zm.html +28 -0
- data/perl/HeaderParseService/resources/database/university_list.txt +3025 -0
- data/perl/HeaderParseService/resources/database/url.txt +1 -0
- data/perl/HeaderParseService/resources/database/webTopWords +225 -0
- data/perl/HeaderParseService/resources/database/words +45402 -0
- data/perl/HeaderParseService/resources/models/10ContextModelfold1 +369 -0
- data/perl/HeaderParseService/resources/models/10Modelfold1 +376 -0
- data/perl/HeaderParseService/resources/models/11ContextModelfold1 +400 -0
- data/perl/HeaderParseService/resources/models/11Modelfold1 +526 -0
- data/perl/HeaderParseService/resources/models/12ContextModelfold1 +510 -0
- data/perl/HeaderParseService/resources/models/12Modelfold1 +423 -0
- data/perl/HeaderParseService/resources/models/13ContextModelfold1 +364 -0
- data/perl/HeaderParseService/resources/models/13Modelfold1 +677 -0
- data/perl/HeaderParseService/resources/models/14ContextModelfold1 +459 -0
- data/perl/HeaderParseService/resources/models/14Modelfold1 +325 -0
- data/perl/HeaderParseService/resources/models/15ContextModelfold1 +340 -0
- data/perl/HeaderParseService/resources/models/15Modelfold1 +390 -0
- data/perl/HeaderParseService/resources/models/1ContextModelfold1 +668 -0
- data/perl/HeaderParseService/resources/models/1Modelfold1 +1147 -0
- data/perl/HeaderParseService/resources/models/2ContextModelfold1 +755 -0
- data/perl/HeaderParseService/resources/models/2Modelfold1 +796 -0
- data/perl/HeaderParseService/resources/models/3ContextModelfold1 +1299 -0
- data/perl/HeaderParseService/resources/models/3Modelfold1 +1360 -0
- data/perl/HeaderParseService/resources/models/4ContextModelfold1 +1062 -0
- data/perl/HeaderParseService/resources/models/4Modelfold1 +993 -0
- data/perl/HeaderParseService/resources/models/5ContextModelfold1 +1339 -0
- data/perl/HeaderParseService/resources/models/5Modelfold1 +2098 -0
- data/perl/HeaderParseService/resources/models/6ContextModelfold1 +888 -0
- data/perl/HeaderParseService/resources/models/6Modelfold1 +620 -0
- data/perl/HeaderParseService/resources/models/7ContextModelfold1 +257 -0
- data/perl/HeaderParseService/resources/models/7Modelfold1 +228 -0
- data/perl/HeaderParseService/resources/models/8ContextModelfold1 +677 -0
- data/perl/HeaderParseService/resources/models/8Modelfold1 +1871 -0
- data/perl/HeaderParseService/resources/models/9ContextModelfold1 +198 -0
- data/perl/HeaderParseService/resources/models/9Modelfold1 +170 -0
- data/perl/HeaderParseService/resources/models/NameSpaceModel +181 -0
- data/perl/HeaderParseService/resources/models/NameSpaceTrainF +347 -0
- data/perl/HeaderParseService/resources/models/WrapperBaseFeaDict +13460 -0
- data/perl/HeaderParseService/resources/models/WrapperContextFeaDict +14045 -0
- data/perl/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict +510 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8 +23 -0
- data/perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9 +23 -0
- data/perl/ParsCit/README.TXT +82 -0
- data/perl/ParsCit/crfpp/traindata/parsCit.template +60 -0
- data/perl/ParsCit/crfpp/traindata/parsCit.train.data +12104 -0
- data/perl/ParsCit/crfpp/traindata/tagged_references.txt +500 -0
- data/perl/ParsCit/lib/CSXUtil/SafeText.pm +140 -0
- data/perl/ParsCit/lib/ParsCit/Citation.pm +462 -0
- data/perl/ParsCit/lib/ParsCit/CitationContext.pm +132 -0
- data/perl/ParsCit/lib/ParsCit/Config.pm +46 -0
- data/perl/ParsCit/lib/ParsCit/Controller.pm +306 -0
- data/perl/ParsCit/lib/ParsCit/PostProcess.pm +367 -0
- data/perl/ParsCit/lib/ParsCit/PreProcess.pm +333 -0
- data/perl/ParsCit/lib/ParsCit/Tr2crfpp.pm +331 -0
- data/perl/ParsCit/resources/parsCit.model +0 -0
- data/perl/ParsCit/resources/parsCitDict.txt +148783 -0
- data/perl/extract.pl +199 -0
- data/spec/biblicit/cb2bib_spec.rb +48 -0
- data/spec/biblicit/citeseer_spec.rb +40 -0
- data/spec/fixtures/pdf/10.1.1.109.4049.pdf +0 -0
- data/spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf +0 -0
- data/spec/fixtures/pdf/ICINCO_2010.pdf +0 -0
- data/spec/spec_helper.rb +3 -0
- metadata +474 -0
@@ -0,0 +1,438 @@
|
|
1
|
+
a
|
2
|
+
about
|
3
|
+
above
|
4
|
+
according
|
5
|
+
across
|
6
|
+
after
|
7
|
+
after
|
8
|
+
afterwards
|
9
|
+
again
|
10
|
+
against
|
11
|
+
albeit
|
12
|
+
all
|
13
|
+
almost
|
14
|
+
alone
|
15
|
+
along
|
16
|
+
already
|
17
|
+
also
|
18
|
+
although
|
19
|
+
always
|
20
|
+
am
|
21
|
+
among
|
22
|
+
amongst
|
23
|
+
an
|
24
|
+
and
|
25
|
+
another
|
26
|
+
any
|
27
|
+
anybody
|
28
|
+
anyhow
|
29
|
+
anyone
|
30
|
+
anything
|
31
|
+
anyway
|
32
|
+
anywhere
|
33
|
+
apart
|
34
|
+
are
|
35
|
+
around
|
36
|
+
as
|
37
|
+
as
|
38
|
+
at
|
39
|
+
back
|
40
|
+
be
|
41
|
+
became
|
42
|
+
because
|
43
|
+
become
|
44
|
+
becomes
|
45
|
+
becoming
|
46
|
+
been
|
47
|
+
before
|
48
|
+
before
|
49
|
+
beforehand
|
50
|
+
behind
|
51
|
+
being
|
52
|
+
below
|
53
|
+
beside
|
54
|
+
besides
|
55
|
+
between
|
56
|
+
beyond
|
57
|
+
both
|
58
|
+
but
|
59
|
+
but
|
60
|
+
by
|
61
|
+
can
|
62
|
+
cannot
|
63
|
+
canst
|
64
|
+
certain
|
65
|
+
cf
|
66
|
+
choose
|
67
|
+
contrariwise
|
68
|
+
cos
|
69
|
+
could
|
70
|
+
day
|
71
|
+
do
|
72
|
+
dost
|
73
|
+
doth
|
74
|
+
double
|
75
|
+
down
|
76
|
+
dual
|
77
|
+
during
|
78
|
+
each
|
79
|
+
eg
|
80
|
+
either
|
81
|
+
either
|
82
|
+
else
|
83
|
+
elsewhere
|
84
|
+
enough
|
85
|
+
et
|
86
|
+
etc
|
87
|
+
even
|
88
|
+
ever
|
89
|
+
every
|
90
|
+
everybody
|
91
|
+
everyone
|
92
|
+
everything
|
93
|
+
everywhere
|
94
|
+
except
|
95
|
+
excepted
|
96
|
+
excepting
|
97
|
+
exclude
|
98
|
+
excluding
|
99
|
+
exclusive
|
100
|
+
far
|
101
|
+
farther
|
102
|
+
farthest
|
103
|
+
few
|
104
|
+
ff
|
105
|
+
first
|
106
|
+
for
|
107
|
+
former
|
108
|
+
formerly
|
109
|
+
forth
|
110
|
+
forward
|
111
|
+
from
|
112
|
+
front
|
113
|
+
further
|
114
|
+
furthermore
|
115
|
+
furthest
|
116
|
+
get
|
117
|
+
go
|
118
|
+
had
|
119
|
+
halves
|
120
|
+
hardly
|
121
|
+
has
|
122
|
+
hast
|
123
|
+
hath
|
124
|
+
hatless
|
125
|
+
have
|
126
|
+
he
|
127
|
+
hence
|
128
|
+
henceforth
|
129
|
+
her
|
130
|
+
here
|
131
|
+
hereabouts
|
132
|
+
hereafter
|
133
|
+
hereby
|
134
|
+
herein
|
135
|
+
hereto
|
136
|
+
hereupon
|
137
|
+
hers
|
138
|
+
herself
|
139
|
+
him
|
140
|
+
himself
|
141
|
+
hindmost
|
142
|
+
his
|
143
|
+
hither
|
144
|
+
hitherto
|
145
|
+
how
|
146
|
+
however
|
147
|
+
however
|
148
|
+
howsoever
|
149
|
+
i
|
150
|
+
ie
|
151
|
+
if
|
152
|
+
in
|
153
|
+
inasmuch
|
154
|
+
inc
|
155
|
+
include
|
156
|
+
included
|
157
|
+
including
|
158
|
+
indeed
|
159
|
+
indoors
|
160
|
+
inside
|
161
|
+
insomuch
|
162
|
+
instead
|
163
|
+
into
|
164
|
+
inward
|
165
|
+
inwards
|
166
|
+
is
|
167
|
+
it
|
168
|
+
it
|
169
|
+
its
|
170
|
+
itself
|
171
|
+
just
|
172
|
+
kind
|
173
|
+
kg
|
174
|
+
km
|
175
|
+
last
|
176
|
+
latter
|
177
|
+
latterly
|
178
|
+
less
|
179
|
+
less
|
180
|
+
lest
|
181
|
+
let
|
182
|
+
like
|
183
|
+
little
|
184
|
+
ltd
|
185
|
+
many
|
186
|
+
may
|
187
|
+
maybe
|
188
|
+
me
|
189
|
+
meantime
|
190
|
+
meanwhile
|
191
|
+
might
|
192
|
+
moreover
|
193
|
+
most
|
194
|
+
mostly
|
195
|
+
more
|
196
|
+
mr
|
197
|
+
mrs
|
198
|
+
ms
|
199
|
+
much
|
200
|
+
much
|
201
|
+
must
|
202
|
+
my
|
203
|
+
myself
|
204
|
+
namely
|
205
|
+
need
|
206
|
+
neither
|
207
|
+
neither
|
208
|
+
never
|
209
|
+
nevertheless
|
210
|
+
next
|
211
|
+
no
|
212
|
+
no
|
213
|
+
nobody
|
214
|
+
none
|
215
|
+
nonetheless
|
216
|
+
noone
|
217
|
+
nope
|
218
|
+
nor
|
219
|
+
not
|
220
|
+
nothing
|
221
|
+
notwithstanding
|
222
|
+
now
|
223
|
+
nowadays
|
224
|
+
nowhere
|
225
|
+
of
|
226
|
+
off
|
227
|
+
often
|
228
|
+
ok
|
229
|
+
on
|
230
|
+
once
|
231
|
+
once
|
232
|
+
one
|
233
|
+
only
|
234
|
+
onto
|
235
|
+
or
|
236
|
+
other
|
237
|
+
others
|
238
|
+
otherwise
|
239
|
+
ought
|
240
|
+
our
|
241
|
+
ours
|
242
|
+
ourselves
|
243
|
+
out
|
244
|
+
outside
|
245
|
+
over
|
246
|
+
own
|
247
|
+
per
|
248
|
+
perhaps
|
249
|
+
plenty
|
250
|
+
provide
|
251
|
+
quite
|
252
|
+
rather
|
253
|
+
really
|
254
|
+
right
|
255
|
+
round
|
256
|
+
said
|
257
|
+
sake
|
258
|
+
same
|
259
|
+
sang
|
260
|
+
save
|
261
|
+
saw
|
262
|
+
see
|
263
|
+
seeing
|
264
|
+
seem
|
265
|
+
seemed
|
266
|
+
seeming
|
267
|
+
seems
|
268
|
+
seen
|
269
|
+
seldom
|
270
|
+
selves
|
271
|
+
sent
|
272
|
+
several
|
273
|
+
shalt
|
274
|
+
she
|
275
|
+
should
|
276
|
+
shown
|
277
|
+
sideways
|
278
|
+
since
|
279
|
+
slept
|
280
|
+
slew
|
281
|
+
slung
|
282
|
+
slunk
|
283
|
+
smote
|
284
|
+
so
|
285
|
+
so
|
286
|
+
some
|
287
|
+
somebody
|
288
|
+
somehow
|
289
|
+
someone
|
290
|
+
something
|
291
|
+
sometime
|
292
|
+
sometimes
|
293
|
+
somewhat
|
294
|
+
somewhere
|
295
|
+
spake
|
296
|
+
spat
|
297
|
+
spoke
|
298
|
+
spoken
|
299
|
+
sprang
|
300
|
+
sprung
|
301
|
+
stave
|
302
|
+
staves
|
303
|
+
still
|
304
|
+
such
|
305
|
+
supposing
|
306
|
+
than
|
307
|
+
that
|
308
|
+
that
|
309
|
+
that
|
310
|
+
that
|
311
|
+
the
|
312
|
+
thee
|
313
|
+
their
|
314
|
+
them
|
315
|
+
themselves
|
316
|
+
then
|
317
|
+
then
|
318
|
+
thence
|
319
|
+
thenceforth
|
320
|
+
there
|
321
|
+
there
|
322
|
+
thereabout
|
323
|
+
thereabouts
|
324
|
+
thereafter
|
325
|
+
thereby
|
326
|
+
therefore
|
327
|
+
therein
|
328
|
+
thereof
|
329
|
+
thereon
|
330
|
+
thereto
|
331
|
+
thereupon
|
332
|
+
these
|
333
|
+
they
|
334
|
+
this
|
335
|
+
those
|
336
|
+
thou
|
337
|
+
though
|
338
|
+
though
|
339
|
+
thrice
|
340
|
+
through
|
341
|
+
throughout
|
342
|
+
thru
|
343
|
+
thus
|
344
|
+
thy
|
345
|
+
thyself
|
346
|
+
till
|
347
|
+
time
|
348
|
+
to
|
349
|
+
to
|
350
|
+
together
|
351
|
+
too
|
352
|
+
toward
|
353
|
+
towards
|
354
|
+
ugh
|
355
|
+
unable
|
356
|
+
under
|
357
|
+
underneath
|
358
|
+
unless
|
359
|
+
unlike
|
360
|
+
until
|
361
|
+
up
|
362
|
+
upon
|
363
|
+
upward
|
364
|
+
upwards
|
365
|
+
us
|
366
|
+
very
|
367
|
+
via
|
368
|
+
vs
|
369
|
+
want
|
370
|
+
was
|
371
|
+
we
|
372
|
+
week
|
373
|
+
well
|
374
|
+
were
|
375
|
+
what
|
376
|
+
whatever
|
377
|
+
whatsoever
|
378
|
+
when
|
379
|
+
whence
|
380
|
+
whenever
|
381
|
+
whensoever
|
382
|
+
where
|
383
|
+
whereabouts
|
384
|
+
whereafter
|
385
|
+
whereas
|
386
|
+
whereat
|
387
|
+
whereby
|
388
|
+
wherefore
|
389
|
+
wherefrom
|
390
|
+
wherein
|
391
|
+
whereinto
|
392
|
+
whereof
|
393
|
+
whereon
|
394
|
+
wheresoever
|
395
|
+
whereto
|
396
|
+
whereunto
|
397
|
+
whereupon
|
398
|
+
wherever
|
399
|
+
wherewith
|
400
|
+
whether
|
401
|
+
whew
|
402
|
+
which
|
403
|
+
whichever
|
404
|
+
whichsoever
|
405
|
+
while
|
406
|
+
while
|
407
|
+
whilst
|
408
|
+
whither
|
409
|
+
who
|
410
|
+
whoa
|
411
|
+
whoever
|
412
|
+
whole
|
413
|
+
whom
|
414
|
+
whomever
|
415
|
+
whomsoever
|
416
|
+
whose
|
417
|
+
whosoever
|
418
|
+
why
|
419
|
+
will
|
420
|
+
wilt
|
421
|
+
with
|
422
|
+
within
|
423
|
+
without
|
424
|
+
worse
|
425
|
+
worst
|
426
|
+
would
|
427
|
+
wow
|
428
|
+
ye
|
429
|
+
yet
|
430
|
+
year
|
431
|
+
yippee
|
432
|
+
you
|
433
|
+
you
|
434
|
+
your
|
435
|
+
yours
|
436
|
+
yourself
|
437
|
+
yourselves
|
438
|
+
|
Binary file
|