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
metadata
ADDED
@@ -0,0 +1,474 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: biblicit
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '1.0'
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- David Judd
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-01-24 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: activesupport
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: nokogiri
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rake
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: rspec
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: pry
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ! '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: pry-debugger
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
type: :development
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
description: Extract citations from PDFs.
|
111
|
+
email:
|
112
|
+
- david@academia.edu
|
113
|
+
executables: []
|
114
|
+
extensions: []
|
115
|
+
extra_rdoc_files: []
|
116
|
+
files:
|
117
|
+
- .gitignore
|
118
|
+
- .rspec
|
119
|
+
- Gemfile
|
120
|
+
- LICENSE.TXT
|
121
|
+
- README.md
|
122
|
+
- Rakefile
|
123
|
+
- biblicit.gemspec
|
124
|
+
- lib/biblicit.rb
|
125
|
+
- lib/biblicit/cb2bib.rb
|
126
|
+
- lib/biblicit/citeseer.rb
|
127
|
+
- lib/biblicit/extractor.rb
|
128
|
+
- perl/DocFilter/lib/CSXUtil/SafeText.pm
|
129
|
+
- perl/DocFilter/lib/DocFilter/Config.pm
|
130
|
+
- perl/DocFilter/lib/DocFilter/Filter.pm
|
131
|
+
- perl/FileConversionService/README.TXT
|
132
|
+
- perl/FileConversionService/converters/PDFBox/pdfbox-app-1.7.1.jar
|
133
|
+
- perl/FileConversionService/lib/CSXUtil/SafeText.pm
|
134
|
+
- perl/FileConversionService/lib/FileConverter/CheckSum.pm
|
135
|
+
- perl/FileConversionService/lib/FileConverter/Compression.pm
|
136
|
+
- perl/FileConversionService/lib/FileConverter/Config.pm
|
137
|
+
- perl/FileConversionService/lib/FileConverter/Controller.pm
|
138
|
+
- perl/FileConversionService/lib/FileConverter/JODConverter.pm
|
139
|
+
- perl/FileConversionService/lib/FileConverter/PDFBox.pm
|
140
|
+
- perl/FileConversionService/lib/FileConverter/PSConverter.pm
|
141
|
+
- perl/FileConversionService/lib/FileConverter/PSToText.pm
|
142
|
+
- perl/FileConversionService/lib/FileConverter/Prescript.pm
|
143
|
+
- perl/FileConversionService/lib/FileConverter/TET.pm
|
144
|
+
- perl/FileConversionService/lib/FileConverter/Utils.pm
|
145
|
+
- perl/HeaderParseService/README.TXT
|
146
|
+
- perl/HeaderParseService/lib/CSXUtil/SafeText.pm
|
147
|
+
- perl/HeaderParseService/lib/HeaderParse/API/AssembleXMLMetadata.pm
|
148
|
+
- perl/HeaderParseService/lib/HeaderParse/API/Function.pm
|
149
|
+
- perl/HeaderParseService/lib/HeaderParse/API/LoadInformation.pm
|
150
|
+
- perl/HeaderParseService/lib/HeaderParse/API/MultiClassChunking.pm
|
151
|
+
- perl/HeaderParseService/lib/HeaderParse/API/NamePatternMatch.pm
|
152
|
+
- perl/HeaderParseService/lib/HeaderParse/API/Parser.pm
|
153
|
+
- perl/HeaderParseService/lib/HeaderParse/API/ParserMethods.pm
|
154
|
+
- perl/HeaderParseService/lib/HeaderParse/Config/API_Config.pm
|
155
|
+
- perl/HeaderParseService/resources/data/EbizHeaders.txt
|
156
|
+
- perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed
|
157
|
+
- perl/HeaderParseService/resources/data/EbizHeaders.txt.parsed.old
|
158
|
+
- perl/HeaderParseService/resources/data/tagged_headers.txt
|
159
|
+
- perl/HeaderParseService/resources/data/test_header.txt
|
160
|
+
- perl/HeaderParseService/resources/data/test_header.txt.parsed
|
161
|
+
- perl/HeaderParseService/resources/database/50states
|
162
|
+
- perl/HeaderParseService/resources/database/AddrTopWords.txt
|
163
|
+
- perl/HeaderParseService/resources/database/AffiTopWords.txt
|
164
|
+
- perl/HeaderParseService/resources/database/AffiTopWordsAll.txt
|
165
|
+
- perl/HeaderParseService/resources/database/ChineseSurNames.txt
|
166
|
+
- perl/HeaderParseService/resources/database/Csurnames.bin
|
167
|
+
- perl/HeaderParseService/resources/database/Csurnames_spec.bin
|
168
|
+
- perl/HeaderParseService/resources/database/DomainSuffixes.txt
|
169
|
+
- perl/HeaderParseService/resources/database/LabeledHeader
|
170
|
+
- perl/HeaderParseService/resources/database/README
|
171
|
+
- perl/HeaderParseService/resources/database/TrainMulClassLines
|
172
|
+
- perl/HeaderParseService/resources/database/TrainMulClassLines1
|
173
|
+
- perl/HeaderParseService/resources/database/abstract.txt
|
174
|
+
- perl/HeaderParseService/resources/database/abstractTopWords
|
175
|
+
- perl/HeaderParseService/resources/database/addr.txt
|
176
|
+
- perl/HeaderParseService/resources/database/affi.txt
|
177
|
+
- perl/HeaderParseService/resources/database/affis.bin
|
178
|
+
- perl/HeaderParseService/resources/database/all_namewords_spec.bin
|
179
|
+
- perl/HeaderParseService/resources/database/allnamewords.bin
|
180
|
+
- perl/HeaderParseService/resources/database/cities_US.txt
|
181
|
+
- perl/HeaderParseService/resources/database/cities_world.txt
|
182
|
+
- perl/HeaderParseService/resources/database/city.txt
|
183
|
+
- perl/HeaderParseService/resources/database/cityname.txt
|
184
|
+
- perl/HeaderParseService/resources/database/country_abbr.txt
|
185
|
+
- perl/HeaderParseService/resources/database/countryname.txt
|
186
|
+
- perl/HeaderParseService/resources/database/dateTopWords
|
187
|
+
- perl/HeaderParseService/resources/database/degree.txt
|
188
|
+
- perl/HeaderParseService/resources/database/email.txt
|
189
|
+
- perl/HeaderParseService/resources/database/excludeWords.txt
|
190
|
+
- perl/HeaderParseService/resources/database/female-names
|
191
|
+
- perl/HeaderParseService/resources/database/firstNames.txt
|
192
|
+
- perl/HeaderParseService/resources/database/firstnames.bin
|
193
|
+
- perl/HeaderParseService/resources/database/firstnames_spec.bin
|
194
|
+
- perl/HeaderParseService/resources/database/intro.txt
|
195
|
+
- perl/HeaderParseService/resources/database/keyword.txt
|
196
|
+
- perl/HeaderParseService/resources/database/keywordTopWords
|
197
|
+
- perl/HeaderParseService/resources/database/male-names
|
198
|
+
- perl/HeaderParseService/resources/database/middleNames.txt
|
199
|
+
- perl/HeaderParseService/resources/database/month.txt
|
200
|
+
- perl/HeaderParseService/resources/database/mul
|
201
|
+
- perl/HeaderParseService/resources/database/mul.label
|
202
|
+
- perl/HeaderParseService/resources/database/mul.label.old
|
203
|
+
- perl/HeaderParseService/resources/database/mul.processed
|
204
|
+
- perl/HeaderParseService/resources/database/mulAuthor
|
205
|
+
- perl/HeaderParseService/resources/database/mulClassStat
|
206
|
+
- perl/HeaderParseService/resources/database/nickname.txt
|
207
|
+
- perl/HeaderParseService/resources/database/nicknames.bin
|
208
|
+
- perl/HeaderParseService/resources/database/note.txt
|
209
|
+
- perl/HeaderParseService/resources/database/page.txt
|
210
|
+
- perl/HeaderParseService/resources/database/phone.txt
|
211
|
+
- perl/HeaderParseService/resources/database/postcode.txt
|
212
|
+
- perl/HeaderParseService/resources/database/pubnum.txt
|
213
|
+
- perl/HeaderParseService/resources/database/statename.bin
|
214
|
+
- perl/HeaderParseService/resources/database/statename.txt
|
215
|
+
- perl/HeaderParseService/resources/database/states_and_abbreviations.txt
|
216
|
+
- perl/HeaderParseService/resources/database/stopwords
|
217
|
+
- perl/HeaderParseService/resources/database/stopwords.bin
|
218
|
+
- perl/HeaderParseService/resources/database/surNames.txt
|
219
|
+
- perl/HeaderParseService/resources/database/surnames.bin
|
220
|
+
- perl/HeaderParseService/resources/database/surnames_spec.bin
|
221
|
+
- perl/HeaderParseService/resources/database/university_list.txt
|
222
|
+
- perl/HeaderParseService/resources/database/university_list/A.html
|
223
|
+
- perl/HeaderParseService/resources/database/university_list/B.html
|
224
|
+
- perl/HeaderParseService/resources/database/university_list/C.html
|
225
|
+
- perl/HeaderParseService/resources/database/university_list/D.html
|
226
|
+
- perl/HeaderParseService/resources/database/university_list/E.html
|
227
|
+
- perl/HeaderParseService/resources/database/university_list/F.html
|
228
|
+
- perl/HeaderParseService/resources/database/university_list/G.html
|
229
|
+
- perl/HeaderParseService/resources/database/university_list/H.html
|
230
|
+
- perl/HeaderParseService/resources/database/university_list/I.html
|
231
|
+
- perl/HeaderParseService/resources/database/university_list/J.html
|
232
|
+
- perl/HeaderParseService/resources/database/university_list/K.html
|
233
|
+
- perl/HeaderParseService/resources/database/university_list/L.html
|
234
|
+
- perl/HeaderParseService/resources/database/university_list/M.html
|
235
|
+
- perl/HeaderParseService/resources/database/university_list/N.html
|
236
|
+
- perl/HeaderParseService/resources/database/university_list/O.html
|
237
|
+
- perl/HeaderParseService/resources/database/university_list/P.html
|
238
|
+
- perl/HeaderParseService/resources/database/university_list/Q.html
|
239
|
+
- perl/HeaderParseService/resources/database/university_list/R.html
|
240
|
+
- perl/HeaderParseService/resources/database/university_list/S.html
|
241
|
+
- perl/HeaderParseService/resources/database/university_list/T.html
|
242
|
+
- perl/HeaderParseService/resources/database/university_list/U.html
|
243
|
+
- perl/HeaderParseService/resources/database/university_list/V.html
|
244
|
+
- perl/HeaderParseService/resources/database/university_list/W.html
|
245
|
+
- perl/HeaderParseService/resources/database/university_list/WCSelect.gif
|
246
|
+
- perl/HeaderParseService/resources/database/university_list/X.html
|
247
|
+
- perl/HeaderParseService/resources/database/university_list/Y.html
|
248
|
+
- perl/HeaderParseService/resources/database/university_list/Z.html
|
249
|
+
- perl/HeaderParseService/resources/database/university_list/ae.html
|
250
|
+
- perl/HeaderParseService/resources/database/university_list/am.html
|
251
|
+
- perl/HeaderParseService/resources/database/university_list/ar.html
|
252
|
+
- perl/HeaderParseService/resources/database/university_list/at.html
|
253
|
+
- perl/HeaderParseService/resources/database/university_list/au.html
|
254
|
+
- perl/HeaderParseService/resources/database/university_list/bd.html
|
255
|
+
- perl/HeaderParseService/resources/database/university_list/be.html
|
256
|
+
- perl/HeaderParseService/resources/database/university_list/bg.html
|
257
|
+
- perl/HeaderParseService/resources/database/university_list/bh.html
|
258
|
+
- perl/HeaderParseService/resources/database/university_list/blueribbon.gif
|
259
|
+
- perl/HeaderParseService/resources/database/university_list/bm.html
|
260
|
+
- perl/HeaderParseService/resources/database/university_list/bn.html
|
261
|
+
- perl/HeaderParseService/resources/database/university_list/br.html
|
262
|
+
- perl/HeaderParseService/resources/database/university_list/ca.html
|
263
|
+
- perl/HeaderParseService/resources/database/university_list/ch.html
|
264
|
+
- perl/HeaderParseService/resources/database/university_list/cl.html
|
265
|
+
- perl/HeaderParseService/resources/database/university_list/cn.html
|
266
|
+
- perl/HeaderParseService/resources/database/university_list/co.html
|
267
|
+
- perl/HeaderParseService/resources/database/university_list/cr.html
|
268
|
+
- perl/HeaderParseService/resources/database/university_list/cy.html
|
269
|
+
- perl/HeaderParseService/resources/database/university_list/cz.html
|
270
|
+
- perl/HeaderParseService/resources/database/university_list/de.html
|
271
|
+
- perl/HeaderParseService/resources/database/university_list/dean-mainlink.jpg
|
272
|
+
- perl/HeaderParseService/resources/database/university_list/dk.html
|
273
|
+
- perl/HeaderParseService/resources/database/university_list/ec.html
|
274
|
+
- perl/HeaderParseService/resources/database/university_list/ee.html
|
275
|
+
- perl/HeaderParseService/resources/database/university_list/eg.html
|
276
|
+
- perl/HeaderParseService/resources/database/university_list/es.html
|
277
|
+
- perl/HeaderParseService/resources/database/university_list/et.html
|
278
|
+
- perl/HeaderParseService/resources/database/university_list/faq.html
|
279
|
+
- perl/HeaderParseService/resources/database/university_list/fi.html
|
280
|
+
- perl/HeaderParseService/resources/database/university_list/fj.html
|
281
|
+
- perl/HeaderParseService/resources/database/university_list/fo.html
|
282
|
+
- perl/HeaderParseService/resources/database/university_list/fr.html
|
283
|
+
- perl/HeaderParseService/resources/database/university_list/geog.html
|
284
|
+
- perl/HeaderParseService/resources/database/university_list/gr.html
|
285
|
+
- perl/HeaderParseService/resources/database/university_list/gu.html
|
286
|
+
- perl/HeaderParseService/resources/database/university_list/hk.html
|
287
|
+
- perl/HeaderParseService/resources/database/university_list/hr.html
|
288
|
+
- perl/HeaderParseService/resources/database/university_list/hu.html
|
289
|
+
- perl/HeaderParseService/resources/database/university_list/id.html
|
290
|
+
- perl/HeaderParseService/resources/database/university_list/ie.html
|
291
|
+
- perl/HeaderParseService/resources/database/university_list/il.html
|
292
|
+
- perl/HeaderParseService/resources/database/university_list/in.html
|
293
|
+
- perl/HeaderParseService/resources/database/university_list/is.html
|
294
|
+
- perl/HeaderParseService/resources/database/university_list/it.html
|
295
|
+
- perl/HeaderParseService/resources/database/university_list/jm.html
|
296
|
+
- perl/HeaderParseService/resources/database/university_list/jo.html
|
297
|
+
- perl/HeaderParseService/resources/database/university_list/jp.html
|
298
|
+
- perl/HeaderParseService/resources/database/university_list/kaplan.gif
|
299
|
+
- perl/HeaderParseService/resources/database/university_list/kr.html
|
300
|
+
- perl/HeaderParseService/resources/database/university_list/kw.html
|
301
|
+
- perl/HeaderParseService/resources/database/university_list/lb.html
|
302
|
+
- perl/HeaderParseService/resources/database/university_list/linkbw2.gif
|
303
|
+
- perl/HeaderParseService/resources/database/university_list/lk.html
|
304
|
+
- perl/HeaderParseService/resources/database/university_list/lt.html
|
305
|
+
- perl/HeaderParseService/resources/database/university_list/lu.html
|
306
|
+
- perl/HeaderParseService/resources/database/university_list/lv.html
|
307
|
+
- perl/HeaderParseService/resources/database/university_list/ma.html
|
308
|
+
- perl/HeaderParseService/resources/database/university_list/maczynski.gif
|
309
|
+
- perl/HeaderParseService/resources/database/university_list/mirror.tar
|
310
|
+
- perl/HeaderParseService/resources/database/university_list/mk.html
|
311
|
+
- perl/HeaderParseService/resources/database/university_list/mo.html
|
312
|
+
- perl/HeaderParseService/resources/database/university_list/mseawdm.gif
|
313
|
+
- perl/HeaderParseService/resources/database/university_list/mt.html
|
314
|
+
- perl/HeaderParseService/resources/database/university_list/mx.html
|
315
|
+
- perl/HeaderParseService/resources/database/university_list/my.html
|
316
|
+
- perl/HeaderParseService/resources/database/university_list/ni.html
|
317
|
+
- perl/HeaderParseService/resources/database/university_list/nl.html
|
318
|
+
- perl/HeaderParseService/resources/database/university_list/no.html
|
319
|
+
- perl/HeaderParseService/resources/database/university_list/nz.html
|
320
|
+
- perl/HeaderParseService/resources/database/university_list/pa.html
|
321
|
+
- perl/HeaderParseService/resources/database/university_list/pe.html
|
322
|
+
- perl/HeaderParseService/resources/database/university_list/ph.html
|
323
|
+
- perl/HeaderParseService/resources/database/university_list/pl.html
|
324
|
+
- perl/HeaderParseService/resources/database/university_list/pointcom.gif
|
325
|
+
- perl/HeaderParseService/resources/database/university_list/pr.html
|
326
|
+
- perl/HeaderParseService/resources/database/university_list/ps.html
|
327
|
+
- perl/HeaderParseService/resources/database/university_list/pt.html
|
328
|
+
- perl/HeaderParseService/resources/database/university_list/recognition.html
|
329
|
+
- perl/HeaderParseService/resources/database/university_list/results.html
|
330
|
+
- perl/HeaderParseService/resources/database/university_list/ro.html
|
331
|
+
- perl/HeaderParseService/resources/database/university_list/ru.html
|
332
|
+
- perl/HeaderParseService/resources/database/university_list/sd.html
|
333
|
+
- perl/HeaderParseService/resources/database/university_list/se.html
|
334
|
+
- perl/HeaderParseService/resources/database/university_list/sg.html
|
335
|
+
- perl/HeaderParseService/resources/database/university_list/si.html
|
336
|
+
- perl/HeaderParseService/resources/database/university_list/sk.html
|
337
|
+
- perl/HeaderParseService/resources/database/university_list/th.html
|
338
|
+
- perl/HeaderParseService/resources/database/university_list/tr.html
|
339
|
+
- perl/HeaderParseService/resources/database/university_list/tw.html
|
340
|
+
- perl/HeaderParseService/resources/database/university_list/ua.html
|
341
|
+
- perl/HeaderParseService/resources/database/university_list/uk.html
|
342
|
+
- perl/HeaderParseService/resources/database/university_list/univ-full.html
|
343
|
+
- perl/HeaderParseService/resources/database/university_list/univ.html
|
344
|
+
- perl/HeaderParseService/resources/database/university_list/uy.html
|
345
|
+
- perl/HeaderParseService/resources/database/university_list/ve.html
|
346
|
+
- perl/HeaderParseService/resources/database/university_list/yu.html
|
347
|
+
- perl/HeaderParseService/resources/database/university_list/za.html
|
348
|
+
- perl/HeaderParseService/resources/database/university_list/zm.html
|
349
|
+
- perl/HeaderParseService/resources/database/url.txt
|
350
|
+
- perl/HeaderParseService/resources/database/webTopWords
|
351
|
+
- perl/HeaderParseService/resources/database/words
|
352
|
+
- perl/HeaderParseService/resources/models/10ContextModelfold1
|
353
|
+
- perl/HeaderParseService/resources/models/10Modelfold1
|
354
|
+
- perl/HeaderParseService/resources/models/11ContextModelfold1
|
355
|
+
- perl/HeaderParseService/resources/models/11Modelfold1
|
356
|
+
- perl/HeaderParseService/resources/models/12ContextModelfold1
|
357
|
+
- perl/HeaderParseService/resources/models/12Modelfold1
|
358
|
+
- perl/HeaderParseService/resources/models/13ContextModelfold1
|
359
|
+
- perl/HeaderParseService/resources/models/13Modelfold1
|
360
|
+
- perl/HeaderParseService/resources/models/14ContextModelfold1
|
361
|
+
- perl/HeaderParseService/resources/models/14Modelfold1
|
362
|
+
- perl/HeaderParseService/resources/models/15ContextModelfold1
|
363
|
+
- perl/HeaderParseService/resources/models/15Modelfold1
|
364
|
+
- perl/HeaderParseService/resources/models/1ContextModelfold1
|
365
|
+
- perl/HeaderParseService/resources/models/1Modelfold1
|
366
|
+
- perl/HeaderParseService/resources/models/2ContextModelfold1
|
367
|
+
- perl/HeaderParseService/resources/models/2Modelfold1
|
368
|
+
- perl/HeaderParseService/resources/models/3ContextModelfold1
|
369
|
+
- perl/HeaderParseService/resources/models/3Modelfold1
|
370
|
+
- perl/HeaderParseService/resources/models/4ContextModelfold1
|
371
|
+
- perl/HeaderParseService/resources/models/4Modelfold1
|
372
|
+
- perl/HeaderParseService/resources/models/5ContextModelfold1
|
373
|
+
- perl/HeaderParseService/resources/models/5Modelfold1
|
374
|
+
- perl/HeaderParseService/resources/models/6ContextModelfold1
|
375
|
+
- perl/HeaderParseService/resources/models/6Modelfold1
|
376
|
+
- perl/HeaderParseService/resources/models/7ContextModelfold1
|
377
|
+
- perl/HeaderParseService/resources/models/7Modelfold1
|
378
|
+
- perl/HeaderParseService/resources/models/8ContextModelfold1
|
379
|
+
- perl/HeaderParseService/resources/models/8Modelfold1
|
380
|
+
- perl/HeaderParseService/resources/models/9ContextModelfold1
|
381
|
+
- perl/HeaderParseService/resources/models/9Modelfold1
|
382
|
+
- perl/HeaderParseService/resources/models/NameSpaceModel
|
383
|
+
- perl/HeaderParseService/resources/models/NameSpaceTrainF
|
384
|
+
- perl/HeaderParseService/resources/models/WrapperBaseFeaDict
|
385
|
+
- perl/HeaderParseService/resources/models/WrapperContextFeaDict
|
386
|
+
- perl/HeaderParseService/resources/models/WrapperSpaceAuthorFeaDict
|
387
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test1
|
388
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test10
|
389
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test11
|
390
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test12
|
391
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test13
|
392
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test14
|
393
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test15
|
394
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test2
|
395
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test3
|
396
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test4
|
397
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test5
|
398
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test6
|
399
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test7
|
400
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test8
|
401
|
+
- perl/HeaderParseService/tmp/tmpVec_1156237246.08016_test9
|
402
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test1
|
403
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test10
|
404
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test11
|
405
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test12
|
406
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test13
|
407
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test14
|
408
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test15
|
409
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test2
|
410
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test3
|
411
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test4
|
412
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test5
|
413
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test6
|
414
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test7
|
415
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test8
|
416
|
+
- perl/HeaderParseService/tmp/tmpVec_914027525.276114_test9
|
417
|
+
- perl/ParsCit/README.TXT
|
418
|
+
- perl/ParsCit/crfpp/traindata/parsCit.template
|
419
|
+
- perl/ParsCit/crfpp/traindata/parsCit.train.data
|
420
|
+
- perl/ParsCit/crfpp/traindata/tagged_references.txt
|
421
|
+
- perl/ParsCit/lib/CSXUtil/SafeText.pm
|
422
|
+
- perl/ParsCit/lib/ParsCit/Citation.pm
|
423
|
+
- perl/ParsCit/lib/ParsCit/CitationContext.pm
|
424
|
+
- perl/ParsCit/lib/ParsCit/Config.pm
|
425
|
+
- perl/ParsCit/lib/ParsCit/Controller.pm
|
426
|
+
- perl/ParsCit/lib/ParsCit/PostProcess.pm
|
427
|
+
- perl/ParsCit/lib/ParsCit/PreProcess.pm
|
428
|
+
- perl/ParsCit/lib/ParsCit/Tr2crfpp.pm
|
429
|
+
- perl/ParsCit/resources/parsCit.model
|
430
|
+
- perl/ParsCit/resources/parsCitDict.txt
|
431
|
+
- perl/extract.pl
|
432
|
+
- spec/biblicit/cb2bib_spec.rb
|
433
|
+
- spec/biblicit/citeseer_spec.rb
|
434
|
+
- spec/fixtures/pdf/10.1.1.109.4049.pdf
|
435
|
+
- spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf
|
436
|
+
- spec/fixtures/pdf/ICINCO_2010.pdf
|
437
|
+
- spec/spec_helper.rb
|
438
|
+
homepage: http://github.com/academia-edu/biblicit
|
439
|
+
licenses: []
|
440
|
+
post_install_message:
|
441
|
+
rdoc_options: []
|
442
|
+
require_paths:
|
443
|
+
- lib
|
444
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
445
|
+
none: false
|
446
|
+
requirements:
|
447
|
+
- - ! '>='
|
448
|
+
- !ruby/object:Gem::Version
|
449
|
+
version: '0'
|
450
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
451
|
+
none: false
|
452
|
+
requirements:
|
453
|
+
- - ! '>='
|
454
|
+
- !ruby/object:Gem::Version
|
455
|
+
version: '0'
|
456
|
+
requirements:
|
457
|
+
- java
|
458
|
+
- perl
|
459
|
+
- for the :citeseer algorithm, the CRF++ Conditional Random Fields library (try "which
|
460
|
+
crf_test")
|
461
|
+
- for the :cb2bib algorithm, the cb2bib citation extraction tool
|
462
|
+
rubyforge_project:
|
463
|
+
rubygems_version: 1.8.23
|
464
|
+
signing_key:
|
465
|
+
specification_version: 3
|
466
|
+
summary: Extract citations from PDFs.
|
467
|
+
test_files:
|
468
|
+
- spec/biblicit/cb2bib_spec.rb
|
469
|
+
- spec/biblicit/citeseer_spec.rb
|
470
|
+
- spec/fixtures/pdf/10.1.1.109.4049.pdf
|
471
|
+
- spec/fixtures/pdf/Bagnoli Watts TAR 2010.pdf
|
472
|
+
- spec/fixtures/pdf/ICINCO_2010.pdf
|
473
|
+
- spec/spec_helper.rb
|
474
|
+
has_rdoc:
|