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 +1,140 @@
|
|
1
|
+
#
|
2
|
+
# Copyright 2007 Penn State University
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
#
|
13
|
+
package CSXUtil::SafeText;
|
14
|
+
##
|
15
|
+
## Methods for stripping bad (XML unsafe) characters
|
16
|
+
## from strings and performing basic HTML entity
|
17
|
+
## translations. Also contains a utility (stripArtifacts)
|
18
|
+
## for getting rid of crazy control characters and
|
19
|
+
## other things that probably aren't proper text.
|
20
|
+
##
|
21
|
+
## Isaac Councill, 12/06/06
|
22
|
+
##
|
23
|
+
#######################################################
|
24
|
+
##
|
25
|
+
use strict;
|
26
|
+
use utf8;
|
27
|
+
require Exporter;
|
28
|
+
|
29
|
+
our ($VERSION, @ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS);
|
30
|
+
|
31
|
+
$VERSION = 1.00;
|
32
|
+
|
33
|
+
@ISA = qw(Exporter);
|
34
|
+
@EXPORT_OK = qw(@badChars %htmlSpecialChars
|
35
|
+
%htmlCharEntities &stripBadChars
|
36
|
+
&encodeHTMLSpecialChars
|
37
|
+
&decodeHTMLSpecialChars
|
38
|
+
&cleanXML &cleanAll &stripArtifacts);
|
39
|
+
|
40
|
+
|
41
|
+
##
|
42
|
+
#######################################################
|
43
|
+
##
|
44
|
+
## Sharable encoding data.
|
45
|
+
##
|
46
|
+
|
47
|
+
## Hex codes for characters that should never be put into
|
48
|
+
## XML - or else parsers will barf.
|
49
|
+
our @badChars = qw(\x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07
|
50
|
+
\x08 \x0B \x0C \x0E \x0F \x10 \x11 \x12
|
51
|
+
\x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1A
|
52
|
+
\x1B \x1C \x1D \x1E \x1F \x7F);
|
53
|
+
|
54
|
+
## Subset of HTML characters that could be problematic
|
55
|
+
## for XML. This is not a complete list of HTML
|
56
|
+
## special characters, but more mappings can be added
|
57
|
+
## as needed.
|
58
|
+
our %htmlSpecialCharEncodings = ("&" => "&",
|
59
|
+
">" => ">",
|
60
|
+
"<" => "<",
|
61
|
+
"\"" => """
|
62
|
+
);
|
63
|
+
|
64
|
+
## The reverse map.
|
65
|
+
our %htmlSpecialCharDecodings;
|
66
|
+
foreach my $key (keys %htmlSpecialCharEncodings) {
|
67
|
+
my $val = $htmlSpecialCharEncodings{$key};
|
68
|
+
$htmlSpecialCharDecodings{$val} = $key;
|
69
|
+
}
|
70
|
+
|
71
|
+
|
72
|
+
##
|
73
|
+
#######################################################
|
74
|
+
##
|
75
|
+
## Subroutines
|
76
|
+
##
|
77
|
+
|
78
|
+
## Delete all occurences of bad characters in text,
|
79
|
+
## returns a new string that is clean.
|
80
|
+
sub stripBadChars {
|
81
|
+
my $rtext = shift;
|
82
|
+
foreach my $char (@badChars) {
|
83
|
+
$$rtext =~ s/$char//g;
|
84
|
+
}
|
85
|
+
}
|
86
|
+
|
87
|
+
|
88
|
+
## Encodes special characters into HTML equivalents
|
89
|
+
## and returns the encoded string.
|
90
|
+
sub encodeHTMLSpecialChars {
|
91
|
+
my $rtext = shift;
|
92
|
+
foreach my $char (keys %htmlSpecialCharEncodings) {
|
93
|
+
my $code = $htmlSpecialCharEncodings{$char};
|
94
|
+
$$rtext =~ s/$char/$code/g;
|
95
|
+
}
|
96
|
+
}
|
97
|
+
|
98
|
+
|
99
|
+
## Decodes a HTML entities in the supplied string
|
100
|
+
## into non-HTML character equivalents and returns
|
101
|
+
## the decoded string.
|
102
|
+
sub decodeHTMLSpecialChars {
|
103
|
+
my $rtext = shift;
|
104
|
+
foreach my $code (keys %htmlSpecialCharDecodings) {
|
105
|
+
my $char = $htmlSpecialCharDecodings{$code};
|
106
|
+
$$rtext =~ s/$code/$char/g;
|
107
|
+
}
|
108
|
+
}
|
109
|
+
|
110
|
+
|
111
|
+
## Strip out any characters that don't look like they
|
112
|
+
## belong in a proper, readable text string.
|
113
|
+
##
|
114
|
+
sub stripArtifacts {
|
115
|
+
my $rtext = shift;
|
116
|
+
$$rtext =~ s/[^\p{IsAlnum}\p{IsPunct}\p{IsSpace}\p{IsS}]//g;
|
117
|
+
}
|
118
|
+
|
119
|
+
|
120
|
+
## Convenience routine for executing both XML safety
|
121
|
+
## routines in a single call.
|
122
|
+
##
|
123
|
+
sub cleanXML {
|
124
|
+
my $rtext = shift;
|
125
|
+
stripBadChars($rtext);
|
126
|
+
encodeHTMLSpecialChars($rtext);
|
127
|
+
}
|
128
|
+
|
129
|
+
|
130
|
+
## Clean for XML and also strip out strange characters.
|
131
|
+
##
|
132
|
+
sub cleanAll {
|
133
|
+
my $rtext = shift;
|
134
|
+
stripBadChars($rtext);
|
135
|
+
stripArtifacts($rtext);
|
136
|
+
encodeHTMLSpecialChars($rtext);
|
137
|
+
}
|
138
|
+
|
139
|
+
|
140
|
+
1;
|