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 +1,968 @@
|
|
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 HeaderParse::API::AssembleXMLMetadata;
|
14
|
+
|
15
|
+
# example input:
|
16
|
+
#<DID> 5 </DID>
|
17
|
+
#<note>Third ILOG International Users Meeting , 9 10 July 1997 , Paris , France</note>
|
18
|
+
#<title>Daily management of an earth observation satellite :</title>
|
19
|
+
#<title>comparison of ILOG Solver with dedicated algorithms</title>
|
20
|
+
#<title>for Valued Constraint Satisfaction Problems</title>
|
21
|
+
#<author>Michel Lemaitre</author>
|
22
|
+
#<author>G'erard Verfaillie</author>
|
23
|
+
#<abstract>ONERA/CERT</abstract>
|
24
|
+
#<abstract>2 , avenue</abstract>
|
25
|
+
#<address>Edouard Belin -- BP 4025 --</address>
|
26
|
+
#<address>31055 Toulouse cedex 4 -- France</address>
|
27
|
+
#<email>fMichel.Lemaitre,Gerard.Verfaillieg@cert.fr</email>
|
28
|
+
|
29
|
+
################Function Description########################
|
30
|
+
# Find the name and its affiliation/address mapping
|
31
|
+
#Assumption:
|
32
|
+
#(1) It is valid to split the header by authors into chunks; each resulting chunk has complete informaiton of the authors in that chunk
|
33
|
+
#(2) Use edit-distance to find the mapping between authors and emails.
|
34
|
+
|
35
|
+
#For each author chunk with N authors.
|
36
|
+
#case 1: N = 1;
|
37
|
+
# (a) if (exists following affi. and addr.) {
|
38
|
+
# combine the following affi. and addrs.
|
39
|
+
# }
|
40
|
+
# (b) else
|
41
|
+
# warning
|
42
|
+
|
43
|
+
#case 2: N > 1;
|
44
|
+
# (a) if the following affi. and addrs == 1
|
45
|
+
# these N people share the affi. and addr.
|
46
|
+
# (b) if the following affi. and addrs == N
|
47
|
+
# map 1-1
|
48
|
+
# (c) otherwise
|
49
|
+
# warning
|
50
|
+
|
51
|
+
#package finalize_metata_extraction_v4;
|
52
|
+
use utf8;
|
53
|
+
use HeaderParse::Config::API_Config;
|
54
|
+
use Data::Dumper;
|
55
|
+
use String::Approx 'adist';
|
56
|
+
use HeaderParse::API::Function qw(&weired_author);
|
57
|
+
use CSXUtil::SafeText qw(&cleanXML &cleanAll);
|
58
|
+
|
59
|
+
|
60
|
+
sub assemble(){
|
61
|
+
my $rstr = shift;
|
62
|
+
|
63
|
+
$$rstr =~ s/^\s+//g;
|
64
|
+
$$rstr =~ s/\s+$//g;
|
65
|
+
|
66
|
+
my @xml_arr = split(/<DID>\s*(\d+)\s*<\/DID>/, $$rstr);
|
67
|
+
|
68
|
+
$did=1;
|
69
|
+
$xml_hash{$did} = $$rstr;
|
70
|
+
|
71
|
+
#turn arr into hash;
|
72
|
+
splice(@xml_arr,0,1);
|
73
|
+
|
74
|
+
my %xml_hash_parsed;
|
75
|
+
|
76
|
+
#start parsing authors and all their attributes
|
77
|
+
($xml_hash_parsed{$did}, $uncertain) = &parse_xml($did, $xml_hash{$did},$uncertain_addr);
|
78
|
+
|
79
|
+
$xml_hash_parsed{$did}{raw} = $xml_hash{$did};
|
80
|
+
delete($xml_hash{$did});
|
81
|
+
|
82
|
+
if ($uncertain) {
|
83
|
+
print STDERR "\n\n$did has mismatched address parsing \n";
|
84
|
+
$uncertain_addr++;
|
85
|
+
}
|
86
|
+
|
87
|
+
my $handle = Data::Dumper->new([\%xml_hash_parsed]);
|
88
|
+
$$rstr = $handle->Dump;
|
89
|
+
|
90
|
+
my $rFinalStr = &output_xml(\%xml_hash_parsed);
|
91
|
+
return $rFinalStr;
|
92
|
+
}
|
93
|
+
|
94
|
+
|
95
|
+
|
96
|
+
#cluster needs initialization --the first cluster!
|
97
|
+
sub parse_xml () {
|
98
|
+
my $did = shift;
|
99
|
+
my $str = shift;
|
100
|
+
my $uncertain_addr = shift;
|
101
|
+
my %xml_hash = ();
|
102
|
+
|
103
|
+
my @lines = split(/\s*\n\s*/, $str);
|
104
|
+
my $pre_stat = "";
|
105
|
+
my %pre_email = ();
|
106
|
+
#pre address/affiliation info.
|
107
|
+
my $pre_cluster_id = "";
|
108
|
+
my $pre_add_cluster_id = "";
|
109
|
+
|
110
|
+
my $cluster_affi_exist = 0; # may not be useful
|
111
|
+
my $cluster_addr_exist = 0; #may not be useful
|
112
|
+
|
113
|
+
my $abstractComplete = 0;
|
114
|
+
|
115
|
+
my $line_count = 0;
|
116
|
+
for my $i(0 .. $#lines) {
|
117
|
+
my $line = $lines[$i];
|
118
|
+
$line = &string_clean($line);
|
119
|
+
if ($line =~ /^\s*$/) {next;}
|
120
|
+
if ($line =~ /\<(\w+)\>(.*)\<\/\w+\>/) {
|
121
|
+
my $tag = $1;
|
122
|
+
my $content = $2;
|
123
|
+
#$content = &lclean($content);
|
124
|
+
$line_count++;
|
125
|
+
$content = &string_clean($content);
|
126
|
+
if ($pre_stat ne $tag) { #different tags
|
127
|
+
if ($tag =~ /abstract/) {
|
128
|
+
if (!defined $xml_hash{$tag}) {
|
129
|
+
$xml_hash{$tag} .= "$content";
|
130
|
+
} else {
|
131
|
+
$abstractComplete = 1;
|
132
|
+
}
|
133
|
+
} elsif ($tag =~ /author/) {
|
134
|
+
$content =~ s/\s*(\,|\;)\s*/ /g;
|
135
|
+
$content = &string_clean($content);
|
136
|
+
$xml_hash{cluster_num}++;
|
137
|
+
my $cluster_id = $xml_hash{cluster_num};
|
138
|
+
$xml_hash{cluster}{$cluster_id}{start} = $line_count;
|
139
|
+
$xml_hash{cluster}{$cluster_id}{end} = $line_count;
|
140
|
+
|
141
|
+
#heuristically judge the correctness of name parsing, and clean names
|
142
|
+
my @multi_names = split(/\s+and\s+/i, $content);
|
143
|
+
for my $i(0 .. $#multi_names) {
|
144
|
+
my $name = $multi_names[$i];
|
145
|
+
my ($weireness, $clean_name) = &weired_author($name);
|
146
|
+
if ($weireness) {next;}
|
147
|
+
$xml_hash{cluster}{$cluster_id}{author_num}++;
|
148
|
+
my $author_id = $xml_hash{cluster}{$cluster_id}{author_num};
|
149
|
+
$xml_hash{cluster}{$cluster_id}{author}{$author_id}{name} = $clean_name;
|
150
|
+
}
|
151
|
+
|
152
|
+
#within cluster parameters update
|
153
|
+
$cluster_affi_exist = 0;
|
154
|
+
$cluster_addr_exist = 0;
|
155
|
+
}elsif ($tag =~ /affiliation/) {
|
156
|
+
my $cluster_id = $xml_hash{cluster_num};
|
157
|
+
if ($cluster_id <0) {
|
158
|
+
print STDERR "warning $did has affiliations ahead of authors \n";
|
159
|
+
}else{
|
160
|
+
#start a new add_cluster regardless what different tags the previous line has
|
161
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster_num}++;
|
162
|
+
my $add_cluster_id = $xml_hash{cluster}{$cluster_id}{add_cluster_num};
|
163
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi_num}++;
|
164
|
+
my $affi_id = $xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi_num};
|
165
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi}{$affi_id} = $content;
|
166
|
+
#not good
|
167
|
+
if ($pre_stat eq "email") {
|
168
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{pre_email} = %pre_email;
|
169
|
+
}
|
170
|
+
}
|
171
|
+
$cluster_affi_exist =1;
|
172
|
+
}elsif ($tag =~ /address/) {
|
173
|
+
my $cluster_id = $xml_hash{cluster_num};
|
174
|
+
if ($cluster_id <0) {
|
175
|
+
#print "warning $did has affiliations ahead of authors \n";
|
176
|
+
}else{
|
177
|
+
if ($pre_stat !~ /affiliation/) {
|
178
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster_num}++;
|
179
|
+
}
|
180
|
+
my $add_cluster_id = $xml_hash{cluster}{$cluster_id}{add_cluster_num};
|
181
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr_num}++;
|
182
|
+
my $addr_id = $xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr_num};
|
183
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr}{$addr_id} = $content;
|
184
|
+
#not good
|
185
|
+
if ($pre_stat eq "email") {
|
186
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{pre_email} = %pre_email;
|
187
|
+
}
|
188
|
+
}
|
189
|
+
$cluster_addr_exist =1;
|
190
|
+
}elsif ($tag =~ /email/) { # other tags
|
191
|
+
if ($content =~ /\@/) {
|
192
|
+
$parsed_emails = &parse_email($content);
|
193
|
+
#concatenate these emails to the new one
|
194
|
+
for my $i(0 .. $#$parsed_emails) {
|
195
|
+
$$parsed_emails[$i] = &string_clean($$parsed_emails[$i]);
|
196
|
+
$xml_hash{email_num}++;
|
197
|
+
my $email_id = $xml_hash{email_num};
|
198
|
+
$xml_hash{email}{$email_id} = $$parsed_emails[$i];
|
199
|
+
$pre_email{$$parsed_emails[$i]}++;
|
200
|
+
#if previous taf is affi/addr. point the pre-affi/addr down to email
|
201
|
+
if (($pre_stat eq "affiliation") || ($pre_stat eq "address")) {
|
202
|
+
$xml_hash{cluster}{$pre_cluster_id}{add_cluster}{$pre_add_cluster_id}{next_email}{$$parsed_emails[$i]} = 1;
|
203
|
+
}
|
204
|
+
}
|
205
|
+
}
|
206
|
+
}else {
|
207
|
+
$xml_hash{$tag}= $content;
|
208
|
+
}
|
209
|
+
}else { #same tags with the previous line
|
210
|
+
my $cluster_id = $xml_hash{cluster_num};
|
211
|
+
if ($tag =~ /author/) {
|
212
|
+
$content =~ s/\s*(\,|\;)\s*/ /g;
|
213
|
+
$content = &string_clean($content);
|
214
|
+
if ($xml_hash{cluster}{$cluster_id}{end} != ($line_count-1)) {
|
215
|
+
die "SVMHeaderParse: $did cluster assignment inappropriate";
|
216
|
+
}else {
|
217
|
+
$xml_hash{cluster}{$cluster_id}{end} = $line_count;
|
218
|
+
#heuristically judge the correctness of name parsing, and clean names
|
219
|
+
my @multi_names = split(/\s+and\s+/i, $content);
|
220
|
+
for my $i(0 .. $#multi_names) {
|
221
|
+
my $name = $multi_names[$i];
|
222
|
+
my ($weireness, $clean_name) = &weired_author($name);
|
223
|
+
if ($weireness) {next;}
|
224
|
+
$xml_hash{cluster}{$cluster_id}{author_num}++;
|
225
|
+
my $author_id = $xml_hash{cluster}{$cluster_id}{author_num};
|
226
|
+
$xml_hash{cluster}{$cluster_id}{author}{$author_id}{name} = $clean_name;
|
227
|
+
}
|
228
|
+
}
|
229
|
+
}elsif ($tag =~ /affiliation/) {
|
230
|
+
my $add_cluster_id = $xml_hash{cluster}{$cluster_id}{add_cluster_num};
|
231
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi_num}++;
|
232
|
+
my $affi_id = $xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi_num};
|
233
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{affi}{$affi_id} = $content;
|
234
|
+
$cluster_affi_exist =1;
|
235
|
+
}elsif ($tag =~ /address/) {
|
236
|
+
my $add_cluster_id = $xml_hash{cluster}{$cluster_id}{add_cluster_num};
|
237
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr_num}++;
|
238
|
+
my $addr_id = $xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr_num};
|
239
|
+
$xml_hash{cluster}{$cluster_id}{add_cluster}{$add_cluster_id}{addr}{$addr_id} = $content;
|
240
|
+
$cluster_addr_exist =1;
|
241
|
+
}elsif ($tag =~ /email/) {# other tags
|
242
|
+
if ($content =~ /\@/) {
|
243
|
+
$parsed_emails = &parse_email($content);
|
244
|
+
#concatenate these emails to the new one
|
245
|
+
for my $i(0 .. $#$parsed_emails) {
|
246
|
+
$$parsed_emails[$i] = &string_clean($$parsed_emails[$i]);
|
247
|
+
$xml_hash{email_num}++;
|
248
|
+
my $email_id = $xml_hash{email_num};
|
249
|
+
$xml_hash{email}{$email_id} = $$parsed_emails[$i];
|
250
|
+
$pre_email{$$parsed_emails[$i]}++;
|
251
|
+
}
|
252
|
+
}
|
253
|
+
} elsif ($tag =~ /abstract/) {
|
254
|
+
if ($abstractComplete <= 0) {
|
255
|
+
$xml_hash{$tag} .= "\n$content";
|
256
|
+
}
|
257
|
+
}else {
|
258
|
+
$xml_hash{$tag} .= " $content";
|
259
|
+
}
|
260
|
+
}
|
261
|
+
#parameters update
|
262
|
+
if (($tag eq "affiliation") || ($tag eq "address")) {
|
263
|
+
$pre_cluster_id = $xml_hash{cluster_num};
|
264
|
+
$pre_add_cluster_id = $xml_hash{cluster}{$pre_cluster_id}{add_cluster_num};
|
265
|
+
%pre_email = ();
|
266
|
+
}elsif ($tag ne "email") {
|
267
|
+
%pre_email = ();
|
268
|
+
$pre_cluster_id = "";
|
269
|
+
$pre_add_cluster_id = "";
|
270
|
+
}
|
271
|
+
$pre_stat = $tag;
|
272
|
+
}
|
273
|
+
}
|
274
|
+
|
275
|
+
$xml_hash{'abstractEnded'} = $abstractComplete;
|
276
|
+
|
277
|
+
#the order of adjusting email and address is non changable
|
278
|
+
$xml_hash = &adjust_email(\%xml_hash);
|
279
|
+
($xml_hash, $uncertain) = &adjust_addr($xml_hash, $uncertain_addr);
|
280
|
+
|
281
|
+
return($xml_hash,$uncertain);
|
282
|
+
}
|
283
|
+
|
284
|
+
|
285
|
+
sub parse_email(){
|
286
|
+
my $content = shift;
|
287
|
+
|
288
|
+
#parse email; email could be separated by only author names, or the whole email addresses
|
289
|
+
my @all_emails = ();
|
290
|
+
$content =~ s/(email|e-mail|e mail)(s)*(\s*\:\s*)*//gi;
|
291
|
+
my @email_parts = split(/\@/, $content);
|
292
|
+
if ($#email_parts < 2) { #only one @
|
293
|
+
if ($content =~ /\,|;|\{|\}|\[|\]/) { #multiple people with the same email root
|
294
|
+
$content =~ s/\{|\}|\[|\]//g;
|
295
|
+
my ($pre, $last) = split(/\@/, $content);
|
296
|
+
my @authors = split(/\,/, $pre);
|
297
|
+
for my $k(0 .. $#authors) {
|
298
|
+
my $tmp_email = "$authors[$k]"."\@"."$last";
|
299
|
+
$tmp_email =~ s/^\s+//g;
|
300
|
+
$tmp_email =~ s/\s+$//g;
|
301
|
+
push @all_emails, $tmp_email;
|
302
|
+
}
|
303
|
+
}else {
|
304
|
+
push @all_emails, $content;
|
305
|
+
}
|
306
|
+
}else { # do not consider the case that some @ string has 1+ people (if exists; extend the function)
|
307
|
+
my @emails = ();
|
308
|
+
if ($content =~ /\,|\;/) {
|
309
|
+
@emails = split(/\,|\;/, $content);
|
310
|
+
}else {
|
311
|
+
@emails = split(/\s+/, $content);
|
312
|
+
}
|
313
|
+
|
314
|
+
for my $k(0 .. $#emails) {
|
315
|
+
push @all_emails, $emails[$k];
|
316
|
+
}
|
317
|
+
}
|
318
|
+
for (my $i=0; $i<=$#all_emails; $i++) {
|
319
|
+
my $email = $all_emails[$i];
|
320
|
+
$email =~ s/^[\(\[\s\<]+//;
|
321
|
+
$email =~ s/[\]\)\s\>]+$//;
|
322
|
+
$all_emails[$i] = $email;
|
323
|
+
}
|
324
|
+
return(\@all_emails);
|
325
|
+
}
|
326
|
+
|
327
|
+
sub adjust_email () {
|
328
|
+
my $adjust_hash= shift;
|
329
|
+
|
330
|
+
my %author_email = ();
|
331
|
+
my %email_author = ();
|
332
|
+
foreach my $cluster_id (sort {$a<=>$b} keys %{$$adjust_hash{cluster}}) {
|
333
|
+
foreach my $author_id (sort {$a<=>$b} keys %{$$adjust_hash{cluster}{$cluster_id}{author}}) {
|
334
|
+
my $name = $$adjust_hash{cluster}{$cluster_id}{author}{$author_id}{name};
|
335
|
+
my $name_id = "$cluster_id"."_"."$author_id";
|
336
|
+
if ($name !~ /\w/) {next;}
|
337
|
+
foreach my $email_id(sort {$a<=>$b} keys %{$$adjust_hash{email}}) {
|
338
|
+
my $email = $$adjust_hash{email}{$email_id};
|
339
|
+
my ($email_name, $email_root) = split(/\@/,$email);
|
340
|
+
if ($email_name !~ /\w/) {next;}
|
341
|
+
$dist = adist(lc($email_name), lc($name));
|
342
|
+
$author_email{$name_id}{$email} = abs($dist);
|
343
|
+
$email_author{$email}{$name_id} = abs($dist);
|
344
|
+
}
|
345
|
+
}
|
346
|
+
}
|
347
|
+
|
348
|
+
foreach my $author_id (keys %author_email) {
|
349
|
+
my $counter = keys %{$author_email{$author_id}};
|
350
|
+
foreach my $email_id (sort {$author_email{$author_id}{$b}<=>$author_email{$author_id}{$a}} keys %{$author_email{$author_id}}) {
|
351
|
+
$author_email{$author_id}{$email_id}{rank} = $counter;
|
352
|
+
$author_email{$author_id}{$email_id}{score} = $author_email{$author_id}{$email_id};
|
353
|
+
$counter--;
|
354
|
+
}
|
355
|
+
}
|
356
|
+
|
357
|
+
foreach my $email_id (keys %email_author) {
|
358
|
+
my $counter = keys %{$email_author{$email_id}};
|
359
|
+
foreach my $author_id (sort {$email_author{$email_id}{$b}<=>$email_author{$email_id}{$a}} keys %{$email_author{$email_id}}) {
|
360
|
+
$email_author{$email_id}{$author_id}{rank} = $counter;
|
361
|
+
$email_author{$email_id}{$author_id}{score} = $email_author{$email_id}{$author_id};
|
362
|
+
$counter--;
|
363
|
+
}
|
364
|
+
}
|
365
|
+
|
366
|
+
my %picked_author;
|
367
|
+
my %picked_email;
|
368
|
+
my %final_map = ();
|
369
|
+
my %sum_hash = (); #rank
|
370
|
+
|
371
|
+
#add the ranks from two sides -> all combinations
|
372
|
+
foreach my $author_id (sort {$a<=>$b} keys %author_email) {
|
373
|
+
foreach my $email_id (keys %{$author_email{$author_id}}) {
|
374
|
+
my $macro = "$author_id"."<>"."$email_id";
|
375
|
+
my ($cluster_id, $author_id2) = split(/\_/, $author_id);
|
376
|
+
#my $macro = "$$adjust_hash{cluster}{$cluster_id}{author}{$author_id2}"."<>"."$email_id";;
|
377
|
+
$sum_hash{$macro}{score} = $author_email{$author_id}{$email_id}{score} + $email_author{$email_id}{$author_id}{score};
|
378
|
+
}
|
379
|
+
}
|
380
|
+
|
381
|
+
foreach my $macro (sort {$sum_hash{$a}{score} <=> $sum_hash{$b}{score}} keys %sum_hash) {
|
382
|
+
my ($author_id1, $email_id) = split(/<>/,$macro);
|
383
|
+
if ($picked_author{$author_id1} || $picked_email{$email_id}) {next;}
|
384
|
+
$picked_author{$author_id1} = 1;
|
385
|
+
$picked_email{$email_id} = 1;
|
386
|
+
$final_map{$author_id1} = $email_id;
|
387
|
+
my ($cluster_id, $author_id2) = split(/\_/, $author_id1);
|
388
|
+
$$adjust_hash{cluster}{$cluster_id}{author}{$author_id2}{email}=$email_id;
|
389
|
+
}
|
390
|
+
|
391
|
+
return($adjust_hash);
|
392
|
+
}
|
393
|
+
|
394
|
+
sub adjust_addr() {
|
395
|
+
my $H= shift;
|
396
|
+
|
397
|
+
#address/affiliation assignment is unreasonable
|
398
|
+
my $uncertain = 0;
|
399
|
+
|
400
|
+
foreach my $cluster_id (sort {$a<=>$b} keys %{$$H{cluster}}) {
|
401
|
+
if ($$H{cluster}{$cluster_id}{author_num} eq 1) {
|
402
|
+
if ($$H{cluster}{$cluster_id}{add_cluster_num} > 1) {
|
403
|
+
#for one author - multiple address case; combine all
|
404
|
+
my ($affi, $addr) = &combine_all_addr_set($$H{cluster}{$cluster_id});
|
405
|
+
if ($affi ne "") {
|
406
|
+
$$H{cluster}{$cluster_id}{author}{1}{affi}=$affi;
|
407
|
+
}
|
408
|
+
if ($addr ne "") {
|
409
|
+
$$H{cluster}{$cluster_id}{author}{1}{addr}=$addr;
|
410
|
+
}
|
411
|
+
}elsif ($$H{cluster}{$cluster_id}{add_cluster_num} eq 1) {
|
412
|
+
my ($affi, $addr) = &combine_first_addr_set($$H{cluster}{$cluster_id});
|
413
|
+
#print "affi is $affi and addr is $addr \n";
|
414
|
+
if ($affi ne "") {
|
415
|
+
$$H{cluster}{$cluster_id}{author}{1}{affi}=$affi;
|
416
|
+
}
|
417
|
+
if ($addr ne "") {
|
418
|
+
$$H{cluster}{$cluster_id}{author}{1}{addr}=$addr;
|
419
|
+
}
|
420
|
+
}else {
|
421
|
+
#print "warning: No address and affiliations\n";
|
422
|
+
}
|
423
|
+
}elsif ($$H{cluster}{$cluster_id}{author_num} > 1) {
|
424
|
+
if ($$H{cluster}{$cluster_id}{add_cluster_num} > 1) {
|
425
|
+
if ($$H{cluster}{$cluster_id}{add_cluster_num} eq $$H{cluster}{$cluster_id}{author_num}) {
|
426
|
+
my $addr_cluster = &combine_addr_set($$H{cluster}{$cluster_id});
|
427
|
+
#equally assign
|
428
|
+
for my $author_id (1 .. $$H{cluster}{$cluster_id}{author_num}) {
|
429
|
+
$$H{cluster}{$cluster_id}{author}{$author_id}{affi}=$$addr_cluster{$cluster_id}{affi};
|
430
|
+
$$H{cluster}{$cluster_id}{author}{$author_id}{addr}=$$addr_cluster{$cluster_id}{addr};
|
431
|
+
}
|
432
|
+
}else {
|
433
|
+
#check if existing emails as separators.
|
434
|
+
my $consonence = &check_email_as_address_separator($$H{cluster}{$cluster_id}{add_cluster});
|
435
|
+
#emails ahead of each address cluster is the separator for author's address
|
436
|
+
if (($consonence eq "pre") || ($consonence eq "next")) {
|
437
|
+
$$H{cluster}{$cluster_id} = &adjust_cluster_by_email_separator($consonence, $$H{cluster}{$cluster_id});
|
438
|
+
}else {
|
439
|
+
$uncertain =1;
|
440
|
+
}
|
441
|
+
#another strategies:
|
442
|
+
#first name has first address; last name has last address
|
443
|
+
$$H{cluster}{$cluster_id} = &assign_edge_address($$H{cluster}{$cluster_id});
|
444
|
+
#other stategies???
|
445
|
+
|
446
|
+
}
|
447
|
+
}elsif ($$H{cluster}{$cluster_id}{add_cluster_num} eq 1) {
|
448
|
+
my ($affi, $addr) = &combine_first_addr_set($$H{cluster}{$cluster_id});
|
449
|
+
#print "affi is $affi and addr is $addr \n";
|
450
|
+
for my $author_id (1 .. $$H{cluster}{$cluster_id}{author_num}) {
|
451
|
+
$$H{cluster}{$cluster_id}{author}{$author_id}{affi}=$affi;
|
452
|
+
$$H{cluster}{$cluster_id}{author}{$author_id}{addr}=$addr;
|
453
|
+
}
|
454
|
+
}else {
|
455
|
+
#print "warning: No address and affiliations\n";
|
456
|
+
}
|
457
|
+
}
|
458
|
+
}
|
459
|
+
|
460
|
+
return($H, $uncertain);
|
461
|
+
}
|
462
|
+
|
463
|
+
sub combine_first_addr_set() {
|
464
|
+
my $H = shift;
|
465
|
+
|
466
|
+
my $affi = "";
|
467
|
+
my $addr = "";
|
468
|
+
|
469
|
+
foreach my $affi_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{1}{affi}}) {
|
470
|
+
$affi .= "\; $$H{'add_cluster'}{1}{affi}{$affi_id}";
|
471
|
+
}
|
472
|
+
$affi =~ s/^\s*\;\s*//g;
|
473
|
+
foreach my $addr_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{1}{addr}}) {
|
474
|
+
$addr .= "\; $$H{'add_cluster'}{1}{addr}{$addr_id}";
|
475
|
+
}
|
476
|
+
$addr =~ s/^\s*\;\s*//g;
|
477
|
+
delete($$H{'add_cluster'}{1}{affi});
|
478
|
+
delete($$H{'add_cluster'}{1}{addr});
|
479
|
+
|
480
|
+
return($affi,$addr);
|
481
|
+
}
|
482
|
+
|
483
|
+
sub combine_addr_set() {
|
484
|
+
my $H = shift;
|
485
|
+
|
486
|
+
my %add_cluster = ();
|
487
|
+
|
488
|
+
foreach my $cluster_id (sort {$a <=> $b} keys %{$$H{'add_cluster'}}) {
|
489
|
+
my $affi = "";
|
490
|
+
my $addr = "";
|
491
|
+
foreach my $affi_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{$cluster_id}{affi}}) {
|
492
|
+
$affi .= "\; $$H{'add_cluster'}{$cluster_id}{affi}{$affi_id}";
|
493
|
+
}
|
494
|
+
$affi =~ s/^\s*\;\s*//g;
|
495
|
+
foreach my $addr_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{$cluster_id}{addr}}) {
|
496
|
+
$addr .= "\; $$H{'add_cluster'}{$cluster_id}{addr}{$addr_id}";
|
497
|
+
}
|
498
|
+
$addr =~ s/^\s*\;\s*//g;
|
499
|
+
if ($affi ne "") {
|
500
|
+
$add_cluster{$cluster_id}{affi} = $affi;
|
501
|
+
}
|
502
|
+
|
503
|
+
if ($addr ne "") {
|
504
|
+
$add_cluster{$cluster_id}{addr} = $addr;
|
505
|
+
}
|
506
|
+
|
507
|
+
delete($$H{'add_cluster'}{$cluster_id}{affi});
|
508
|
+
delete($$H{'add_cluster'}{$cluster_id}{addr});
|
509
|
+
}
|
510
|
+
|
511
|
+
return(\%add_cluster);
|
512
|
+
}
|
513
|
+
|
514
|
+
|
515
|
+
sub combine_all_addr_set() {
|
516
|
+
my $H = shift;
|
517
|
+
|
518
|
+
my $affi = "";
|
519
|
+
my $addr = "";
|
520
|
+
my %add_cluster = ();
|
521
|
+
|
522
|
+
foreach my $cluster_id (sort {$a <=> $b} keys %{$$H{'add_cluster'}}) {
|
523
|
+
foreach my $affi_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{$cluster_id}{affi}}) {
|
524
|
+
$affi .= "\; $$H{'add_cluster'}{$cluster_id}{affi}{$affi_id}";
|
525
|
+
}
|
526
|
+
foreach my $addr_id(sort {$a <=> $b} keys %{$$H{'add_cluster'}{$cluster_id}{addr}}) {
|
527
|
+
$addr .= "\; $$H{'add_cluster'}{$cluster_id}{addr}{$addr_id}";
|
528
|
+
}
|
529
|
+
delete($$H{'add_cluster'}{$cluster_id}{affi});
|
530
|
+
delete($$H{'add_cluster'}{$cluster_id}{addr});
|
531
|
+
}
|
532
|
+
|
533
|
+
return($affi,$addr);
|
534
|
+
}
|
535
|
+
|
536
|
+
sub combine_affi() {
|
537
|
+
my $H = shift;
|
538
|
+
|
539
|
+
my $affi = "";
|
540
|
+
foreach my $affi_id (sort {$a <=> $b} keys %{$$H{affi}}) {
|
541
|
+
$affi .= "\; $$H{affi}{$affi_id}";
|
542
|
+
}
|
543
|
+
$affi =~ s/^\s*\;\s*//g;
|
544
|
+
return($affi);
|
545
|
+
}
|
546
|
+
|
547
|
+
sub combine_addr() {
|
548
|
+
my $H = shift;
|
549
|
+
|
550
|
+
my $addr = "";
|
551
|
+
foreach my $addr_id (sort {$a <=> $b} keys %{$$H{addr}}) {
|
552
|
+
$addr .= "\; $$H{addr}{$addr_id}";
|
553
|
+
}
|
554
|
+
$addr =~ s/^\s*\;\s*//g;
|
555
|
+
|
556
|
+
return($addr);
|
557
|
+
}
|
558
|
+
|
559
|
+
sub check_email_as_address_separator(){
|
560
|
+
my $H = shift;
|
561
|
+
|
562
|
+
my $consonence = 0; #0 is null state; -1 is conflict
|
563
|
+
foreach my $add_cluster_id (sort {$a<=>$b} keys %{$H}) {
|
564
|
+
if ($consonence eq "-1") {last;}
|
565
|
+
my $pre_email = $$H{$add_cluster_id}{'pre_email'};
|
566
|
+
my $next_email = $$H{$add_cluster_id}{'next_email'};
|
567
|
+
###################here
|
568
|
+
foreach my $email_key (sort %{$pre_email}) {
|
569
|
+
if ($email_key =~ /\w/) {
|
570
|
+
if (($consonence eq "0") || ($consonence eq "pre")) {
|
571
|
+
$consonence = "pre";
|
572
|
+
}elsif ($consonence ne "next") {
|
573
|
+
$consonence = -1;
|
574
|
+
}
|
575
|
+
last;
|
576
|
+
}
|
577
|
+
}
|
578
|
+
|
579
|
+
foreach my $email_key (sort %{$next_email}) {
|
580
|
+
if ($email_key =~ /\w/) {
|
581
|
+
if (($consonence eq "0") || ($consonence eq "next")) {
|
582
|
+
$consonence = "next";
|
583
|
+
}elsif ($consonence ne "pre") {
|
584
|
+
$consonence = -1;
|
585
|
+
}
|
586
|
+
last;
|
587
|
+
}
|
588
|
+
}
|
589
|
+
} #end of checking emails as the address separators
|
590
|
+
|
591
|
+
return($consonence);
|
592
|
+
}
|
593
|
+
|
594
|
+
|
595
|
+
|
596
|
+
sub adjust_cluster_by_email_separator() {
|
597
|
+
my $consonence =shift;
|
598
|
+
#$$H{cluster}{$cluster_id})
|
599
|
+
my $H = shift;
|
600
|
+
|
601
|
+
if ($consonence eq "pre") {
|
602
|
+
foreach my $add_cluster_id (sort {$a<=>$b} keys %{$$H{add_cluster}}) {
|
603
|
+
my $pre_email_hash = $$H{add_cluster}{$add_cluster_id}{'pre_email'};
|
604
|
+
#check each email and assign to respective author
|
605
|
+
foreach my $pre_email (keys %{$pre_email_hash}) {
|
606
|
+
foreach my $author_id (keys %{$$H{author}}) {
|
607
|
+
if ($pre_email eq $$H{author}{$author_id}{email}) {
|
608
|
+
#need to combine them first.
|
609
|
+
my $combine_affi = &combine_affi($$H{add_cluster}{$add_cluster_id});
|
610
|
+
my $combine_addr = &combine_addr($$H{add_cluster}{$add_cluster_id});
|
611
|
+
$$H{author}{$author_id}{affi} = $combine_affi;
|
612
|
+
$$H{author}{$author_id}{addr} = $combine_addr;
|
613
|
+
}
|
614
|
+
}
|
615
|
+
}
|
616
|
+
}
|
617
|
+
}elsif ($consonence eq "next") {
|
618
|
+
foreach my $add_cluster_id (sort {$a<=>$b} keys %{$$H{add_cluster}}) {
|
619
|
+
my $next_email_hash = $$H{add_cluster}{$add_cluster_id}{'next_email'};
|
620
|
+
#check each email and assign to respective author
|
621
|
+
foreach my $next_email (keys %{$next_email_hash}) {
|
622
|
+
foreach my $author_id (keys %{$$H{author}}) {
|
623
|
+
if ($next_email eq $$H{author}{$author_id}{email}) {
|
624
|
+
#need to combine them first.
|
625
|
+
my $combine_affi = &combine_affi($$H{add_cluster}{$add_cluster_id});
|
626
|
+
my $combine_addr = &combine_addr($$H{add_cluster}{$add_cluster_id});
|
627
|
+
$$H{author}{$author_id}{affi} = $combine_affi;
|
628
|
+
$$H{author}{$author_id}{addr} = $combine_addr;
|
629
|
+
}
|
630
|
+
}
|
631
|
+
}
|
632
|
+
}
|
633
|
+
}
|
634
|
+
|
635
|
+
return($H);
|
636
|
+
}
|
637
|
+
|
638
|
+
|
639
|
+
#assign first name first address and last name last address
|
640
|
+
sub assign_edge_address () {
|
641
|
+
my $H = shift;
|
642
|
+
|
643
|
+
my $first_name_addr = $$H{author}{1}{addr};
|
644
|
+
my $first_name_affi = $$H{author}{1}{affi};
|
645
|
+
my $last_name_addr = $$H{author}{$$H{author_num}}{addr};
|
646
|
+
my $last_name_affi = $$H{author}{$$H{author_num}}{affi};
|
647
|
+
|
648
|
+
#needs to combine add and affi
|
649
|
+
if (($first_name_addr eq "" ) && ($first_name_affi eq "")) {
|
650
|
+
my $combine_affi = &combine_affi($$H{add_cluster}{1});
|
651
|
+
my $combine_addr = &combine_addr($$H{add_cluster}{1});
|
652
|
+
|
653
|
+
$$H{author}{1}{affi} = $combine_affi;
|
654
|
+
$$H{author}{1}{addr} = $combine_addr;
|
655
|
+
}
|
656
|
+
|
657
|
+
if (($last_name_addr eq "" ) && ($last_name_affi eq "")) {
|
658
|
+
my $combine_affi = &combine_affi($$H{add_cluster}{$$H{add_cluster_num}});
|
659
|
+
my $combine_addr = &combine_addr($$H{add_cluster}{$$H{add_cluster_num}});
|
660
|
+
$$H{author}{$$H{author_num}}{affi} = $combine_affi;
|
661
|
+
$$H{author}{$$H{author_num}}{addr} = $combine_addr;
|
662
|
+
}
|
663
|
+
|
664
|
+
return($H);
|
665
|
+
}
|
666
|
+
|
667
|
+
sub output_xml(){
|
668
|
+
my $parsed_hash = shift;
|
669
|
+
my $author_found = 0;
|
670
|
+
|
671
|
+
my $l_algName = $algName;
|
672
|
+
my $l_algVersion = $algVersion;
|
673
|
+
cleanXML(\$l_algName);
|
674
|
+
cleanXML(\$l_algVersion);
|
675
|
+
|
676
|
+
my $str = "<algorithm name=\"$l_algName\" version=\"$l_algVersion\">\n";
|
677
|
+
|
678
|
+
foreach my $did (sort {$a <=> $b} keys %{$parsed_hash}) {
|
679
|
+
my $title = $$parsed_hash{$did}{title};
|
680
|
+
$title = repairPunctuation($title);
|
681
|
+
cleanAll(\$title);
|
682
|
+
|
683
|
+
$str.="<title>$title</title>\n";
|
684
|
+
$str.="<authors>\n";
|
685
|
+
foreach my $cluster_id (sort {$a <=> $b} keys %{$$parsed_hash{$did}{cluster}}) {
|
686
|
+
if ($cluster_id =~ /\d+/) {
|
687
|
+
foreach my $author_id ( sort {$a <=> $b} keys %{$$parsed_hash{$did}{cluster}{$cluster_id}{author}}) {
|
688
|
+
$author_found = 1;
|
689
|
+
|
690
|
+
my $name = $$parsed_hash{$did}{cluster}{$cluster_id}{author}{$author_id}{name};
|
691
|
+
cleanAll(\$name);
|
692
|
+
$name = normalizeName($name);
|
693
|
+
my $affi = $$parsed_hash{$did}{cluster}{$cluster_id}{author}{$author_id}{affi};
|
694
|
+
$affi = repairPunctuation($affi);
|
695
|
+
cleanAll(\$affi);
|
696
|
+
|
697
|
+
my $addr = $$parsed_hash{$did}{cluster}{$cluster_id}{author}{$author_id}{addr};
|
698
|
+
$addr = repairPunctuation($addr);
|
699
|
+
cleanAll(\$addr);
|
700
|
+
|
701
|
+
my $email = $$parsed_hash{$did}{cluster}{$cluster_id}{author}{$author_id}{email};
|
702
|
+
cleanAll(\$email);
|
703
|
+
|
704
|
+
if ($name =~ /\w/) {
|
705
|
+
$str.="<author>\n";
|
706
|
+
$str.="<name>$name</name>\n";
|
707
|
+
if ($affi =~ /\w/) {
|
708
|
+
$str.="<affiliation>$affi</affiliation>\n";
|
709
|
+
}
|
710
|
+
if ($addr =~ /\w/) {
|
711
|
+
$str.="<address>$addr</address>\n";
|
712
|
+
}
|
713
|
+
if ($email =~ /\w/) {
|
714
|
+
$str.="<email>$email</email>\n";
|
715
|
+
}
|
716
|
+
$str.="</author>\n";
|
717
|
+
}
|
718
|
+
}
|
719
|
+
}
|
720
|
+
}
|
721
|
+
$str.="</authors>\n";
|
722
|
+
|
723
|
+
my $keywords = $$parsed_hash{$did}{keyword};
|
724
|
+
if ($keywords =~ /\w/) {
|
725
|
+
$keywords = repairPunctuation($keywords);
|
726
|
+
my @keywords = normalizeKeywords($keywords);
|
727
|
+
$str .= "<keywords>\n";
|
728
|
+
foreach my $keyword (@keywords) {
|
729
|
+
cleanAll(\$keyword);
|
730
|
+
$str .= "<keyword>$keyword</keyword>\n";
|
731
|
+
}
|
732
|
+
$str .= "</keywords>\n";
|
733
|
+
}
|
734
|
+
|
735
|
+
my $abstract = $$parsed_hash{$did}{abstract};
|
736
|
+
if ($abstract =~ /\w/) {
|
737
|
+
$abstract = repairPunctuation($abstract);
|
738
|
+
$abstract = normalizeAbstract($abstract, $$parsed_hash{$did}{abstractEnded});
|
739
|
+
cleanAll(\$abstract);
|
740
|
+
$str .= "<abstract>$abstract</abstract>\n";
|
741
|
+
}
|
742
|
+
|
743
|
+
my $date = $$parsed_hash{$did}{date};
|
744
|
+
if ($date =~ /\d/) {
|
745
|
+
$date = repairPunctuation($date);
|
746
|
+
cleanAll(\$date);
|
747
|
+
$date = normalizeDate($date);
|
748
|
+
if (defined $date) {
|
749
|
+
$str .= "<date>$date</date>\n";
|
750
|
+
}
|
751
|
+
}
|
752
|
+
}
|
753
|
+
|
754
|
+
my $titlelength = length($$parsed_hash{$did}{title});
|
755
|
+
my $authorcount = scalar keys %{$$parsed_hash{$did}{cluster}{$cluster_id}{author}};
|
756
|
+
|
757
|
+
my $validHeader;
|
758
|
+
|
759
|
+
if(length($$parsed_hash{$did}{title}) > 0 && $author_found) {
|
760
|
+
$validHeader = "<validHeader>1</validHeader>";
|
761
|
+
}
|
762
|
+
else {
|
763
|
+
$validHeader = "<validHeader>0</validHeader>";
|
764
|
+
}
|
765
|
+
|
766
|
+
$str.="$validHeader\n";
|
767
|
+
$str.="</algorithm>\n";
|
768
|
+
|
769
|
+
return \$str;
|
770
|
+
}
|
771
|
+
|
772
|
+
|
773
|
+
sub normalizeName {
|
774
|
+
my $name = shift;
|
775
|
+
my @tokens = split " ", $name;
|
776
|
+
my @newTokens = ();
|
777
|
+
foreach my $token (@tokens) {
|
778
|
+
if ($token =~ m/^and$/i) {
|
779
|
+
next;
|
780
|
+
}
|
781
|
+
push @newTokens, $token;
|
782
|
+
}
|
783
|
+
return join " ", @newTokens;
|
784
|
+
}
|
785
|
+
|
786
|
+
|
787
|
+
sub normalizeKeywords {
|
788
|
+
my $text = shift;
|
789
|
+
my @tokens = split '\s*[\:\;\,]\s*', $text;
|
790
|
+
for (my $i=0; $i<=$#tokens; $i++) {
|
791
|
+
$tokens[$i] = trimPunctuation($tokens[$i]);
|
792
|
+
}
|
793
|
+
if ($tokens[0] =~ m/keyword|keyphrase/i) {
|
794
|
+
return @tokens[1..$#tokens];
|
795
|
+
}
|
796
|
+
return @tokens;
|
797
|
+
}
|
798
|
+
|
799
|
+
sub normalizeAbstract {
|
800
|
+
my ($text, $abstractEnded) = @_;
|
801
|
+
|
802
|
+
my @lines = split '\n', $text;
|
803
|
+
if ($#lines < 0) {
|
804
|
+
return "";
|
805
|
+
}
|
806
|
+
|
807
|
+
if ($abstractEnded<=0) {
|
808
|
+
my $minLines = 5;
|
809
|
+
my $maxLines = 15;
|
810
|
+
my $lineCount = 0;
|
811
|
+
for (my $i=0; $i<$#lines; $i++) {
|
812
|
+
$lineCount++;
|
813
|
+
if (($lineCount >= $minLines) && $line =~ m/\.\s*$/) {
|
814
|
+
last;
|
815
|
+
}
|
816
|
+
if ($lineCount >= $maxLines) {
|
817
|
+
last;
|
818
|
+
}
|
819
|
+
}
|
820
|
+
@lines = @lines[0..($lineCount-1)];
|
821
|
+
}
|
822
|
+
|
823
|
+
my $abstract = "";
|
824
|
+
foreach my $line (@lines) {
|
825
|
+
if ($line =~ m/\b(?:Abstract|ABSTRACT|abstract|Introduction|INTRODUCTION)\:?\s*$/ ||
|
826
|
+
$line =~ m/^\s*$/) {
|
827
|
+
next;
|
828
|
+
}
|
829
|
+
if ($abstract =~ m/\-$/ || $abstract =~ m/^\s*$/s) {
|
830
|
+
$abstract .= $line;
|
831
|
+
} else {
|
832
|
+
$abstract .= " $line";
|
833
|
+
}
|
834
|
+
}
|
835
|
+
return $abstract;
|
836
|
+
}
|
837
|
+
|
838
|
+
sub normalizeDate {
|
839
|
+
my $date = shift;
|
840
|
+
if ($date =~ m/(\b\d{4}\b)/) {
|
841
|
+
my $year = $1;
|
842
|
+
my @timeData = localtime(time);
|
843
|
+
my $currentYear = $timeData[5]+1900;
|
844
|
+
if ($year <= $currentYear+3) {
|
845
|
+
return $year;
|
846
|
+
}
|
847
|
+
}
|
848
|
+
return undef;
|
849
|
+
}
|
850
|
+
|
851
|
+
sub trimPunctuation {
|
852
|
+
my $text = shift;
|
853
|
+
$text =~ s/[\.\,\<\>\?\/\:\;\"\'\{\[\}\]\+\=\_\-\(\)\*\&\^\%\$\#\@\!\~\`\\\|]+\s*$//;
|
854
|
+
$text =~ s/^\s*[\.\,\<\>\?\/\:\;\"\'\{\[\}\]\+\=\_\-\(\)\*\&\^\%\$\#\@\!\~\`\\\|]+//;
|
855
|
+
return $text;
|
856
|
+
}
|
857
|
+
|
858
|
+
|
859
|
+
sub string_clean() {
|
860
|
+
my $str = shift;
|
861
|
+
$str =~ s/^\s+//g;
|
862
|
+
$str =~ s/\s+$//g;
|
863
|
+
|
864
|
+
return($str);
|
865
|
+
}
|
866
|
+
|
867
|
+
|
868
|
+
sub new
|
869
|
+
{
|
870
|
+
my $classname = shift;
|
871
|
+
|
872
|
+
my $self = { XMLindent => ' ' };
|
873
|
+
|
874
|
+
my @upperentities = qw (nbsp iexcl cent pound curren yen brvbar sect
|
875
|
+
uml copy ordf laquo not 173 reg macr deg plusmn
|
876
|
+
sup2 sup3 acute micro para middot cedil supl
|
877
|
+
ordm raquo frac14 half frac34 iquest Agrave
|
878
|
+
Aacute Acirc Atilde Auml Aring AElig Ccedil
|
879
|
+
Egrave Eacute Ecirc Euml Igrave Iacute Icirc
|
880
|
+
Iuml ETH Ntilde Ograve Oacute Ocirc Otilde Ouml
|
881
|
+
times Oslash Ugrave Uacute Ucirc Uuml Yacute
|
882
|
+
THORN szlig agrave aacute acirc atilde auml
|
883
|
+
aring aelig ccedil egrave eacute ecirc euml
|
884
|
+
igrave iacute icirc iuml eth ntilde ograve
|
885
|
+
oacute ocirc otilde ouml divide oslash ugrave
|
886
|
+
uacute ucirc uuml yacute thorn yuml);
|
887
|
+
$upperentities[12] = '#173';
|
888
|
+
|
889
|
+
$self->{'hashentity'} = {};
|
890
|
+
for ( my $i=0; $i<=$#upperentities; $i++ )
|
891
|
+
{
|
892
|
+
my $key = '&'.$upperentities[$i].';';
|
893
|
+
$self->{'hashentity'}->{$key}=$i+160;
|
894
|
+
}
|
895
|
+
|
896
|
+
$self->{'hashstr'} = (join (';|', @upperentities)).';';
|
897
|
+
|
898
|
+
bless $self, $classname;
|
899
|
+
return $self;
|
900
|
+
}
|
901
|
+
|
902
|
+
sub char_converter()
|
903
|
+
{
|
904
|
+
|
905
|
+
my $H = { XMLindent => ' ' };
|
906
|
+
|
907
|
+
my @upperentities = qw (nbsp iexcl cent pound curren yen brvbar sect
|
908
|
+
uml copy ordf laquo not 173 reg macr deg plusmn
|
909
|
+
sup2 sup3 acute micro para middot cedil supl
|
910
|
+
ordm raquo frac14 half frac34 iquest Agrave
|
911
|
+
Aacute Acirc Atilde Auml Aring AElig Ccedil
|
912
|
+
Egrave Eacute Ecirc Euml Igrave Iacute Icirc
|
913
|
+
Iuml ETH Ntilde Ograve Oacute Ocirc Otilde Ouml
|
914
|
+
times Oslash Ugrave Uacute Ucirc Uuml Yacute
|
915
|
+
THORN szlig agrave aacute acirc atilde auml
|
916
|
+
aring aelig ccedil egrave eacute ecirc euml
|
917
|
+
igrave iacute icirc iuml eth ntilde ograve
|
918
|
+
oacute ocirc otilde ouml divide oslash ugrave
|
919
|
+
uacute ucirc uuml yacute thorn yuml);
|
920
|
+
$upperentities[12] = '#173';
|
921
|
+
|
922
|
+
$H->{'hashentity'} = {};
|
923
|
+
for ( my $i=0; $i<=$#upperentities; $i++ )
|
924
|
+
{
|
925
|
+
my $key = '&'.$upperentities[$i].';';
|
926
|
+
$H->{'hashentity'}->{$key}=$i+160;
|
927
|
+
}
|
928
|
+
|
929
|
+
$H->{'hashstr'} = (join (';|', @upperentities)).';';
|
930
|
+
|
931
|
+
return $H;
|
932
|
+
}
|
933
|
+
|
934
|
+
sub repairPunctuation {
|
935
|
+
my $text = shift;
|
936
|
+
$text =~ s/ / /gs;
|
937
|
+
$text =~ s/\s([\.\,\;\]\)\:\}\!\?\>\-])/$1/gs;
|
938
|
+
$text =~ s/^\s+//;
|
939
|
+
$text =~ s/\s+$//;
|
940
|
+
return $text;
|
941
|
+
}
|
942
|
+
|
943
|
+
# clean XML version two - for single-line streams
|
944
|
+
sub lclean
|
945
|
+
{
|
946
|
+
my $t = shift;
|
947
|
+
return undef if (! defined $t );
|
948
|
+
|
949
|
+
$H = &char_converter;
|
950
|
+
# make ISOlat1 entities into Unicode character entities
|
951
|
+
$t =~ s/&($H->{'hashstr'})/sprintf ("&#x%04X;", $H->{'hashentity'}->{$&})/geo;
|
952
|
+
# escape non-XML-encoded ampersands (including from other characters sets)
|
953
|
+
$t =~ s/&(?!((\#[0-9]*)|(\#x[0-9]*)|(amp)|(lt)|(gt)|(apos)|(quot));)/&/go;
|
954
|
+
# convert extended ascii into Unicode character entities
|
955
|
+
$t =~ s/[\xa0-\xff]/'&#'.ord ($&).';'/geo;
|
956
|
+
# remove extended ascii that doesnt translate into ISO8859/1
|
957
|
+
$t =~ s/[\x00-\x08\x0B\x0C\x0E-\x1f\x80-\x9f]//go;
|
958
|
+
# make tags delimiters into entities
|
959
|
+
$t =~ s/</</go;
|
960
|
+
$t =~ s/>/>/go;
|
961
|
+
# flatten whitespace
|
962
|
+
$t =~ s/[\s\t\r\n]+/ /go;
|
963
|
+
# kill leading and terminating spaces
|
964
|
+
$t =~ s/^[ ]+(.+)[ ]+$/$1/;
|
965
|
+
return $t;
|
966
|
+
}
|
967
|
+
|
968
|
+
1;
|