├── 2005_wiki_stop_categories.txt ├── README ├── addAnchors.py ├── addRedirects.py ├── directScan.py ├── esa-lucene ├── .classpath ├── .project ├── .settings │ └── org.eclipse.jdt.core.prefs ├── lib │ └── servlet-api.jar ├── src │ ├── config │ │ ├── db.conf │ │ ├── stopwords.txt │ │ └── wordsim353-combined.tab │ ├── edu │ │ └── wiki │ │ │ ├── api │ │ │ └── concept │ │ │ │ ├── IConceptIterator.java │ │ │ │ ├── IConceptVector.java │ │ │ │ ├── IConceptVectorData.java │ │ │ │ ├── scorer │ │ │ │ └── CosineScorer.java │ │ │ │ └── search │ │ │ │ └── IScorer.java │ │ │ ├── concept │ │ │ ├── ConceptVectorSimilarity.java │ │ │ ├── TroveConceptVector.java │ │ │ └── TroveConceptVectorOrderedIterator.java │ │ │ ├── demo │ │ │ ├── TestCombinedESAVectors.java │ │ │ ├── TestESAVectors.java │ │ │ ├── TestGeneralESAVectors.java │ │ │ ├── TestSimilarity.java │ │ │ └── TestWordsim353.java │ │ │ ├── index │ │ │ ├── ESASimilarity.java │ │ │ ├── ESAWikipediaIndexer.java │ │ │ └── WikipediaAnalyzer.java │ │ │ ├── modify │ │ │ ├── IndexModifier.java │ │ │ ├── IndexPruner.java │ │ │ └── MemIndexModifier.java │ │ │ ├── search │ │ │ ├── ESASearcher.java │ │ │ ├── NormalizedWikipediaDistance.java │ │ │ └── WikipediaNormalSearcher.java │ │ │ ├── service │ │ │ ├── ESAServlet.java │ │ │ └── UTF8Filter.java │ │ │ └── util │ │ │ └── HeapSort.java │ └── org │ │ └── apache │ │ └── lucene │ │ └── analysis │ │ ├── CustomFilter.java │ │ └── CustomTokenizer.java └── web │ └── WEB-INF │ ├── lib │ ├── esa-web.jar │ ├── lucene-analyzers-3.0.0.jar │ ├── lucene-core-3.0.0.jar │ ├── mysql-connector-java-5.1.12-bin.jar │ └── trove-2.1.0.jar │ └── web.xml ├── lewis_smart_sorted_uniq.txt ├── readCatHier.py ├── scanCatHier.py ├── scanData.py ├── scanLinks.py ├── selected.txt ├── wiki_stop_categories.txt └── xmlwikiprep.py /2005_wiki_stop_categories.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/2005_wiki_stop_categories.txt -------------------------------------------------------------------------------- /README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/README -------------------------------------------------------------------------------- /addAnchors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/addAnchors.py -------------------------------------------------------------------------------- /addRedirects.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/addRedirects.py -------------------------------------------------------------------------------- /directScan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/directScan.py -------------------------------------------------------------------------------- /esa-lucene/.classpath: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/.classpath -------------------------------------------------------------------------------- /esa-lucene/.project: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/.project -------------------------------------------------------------------------------- /esa-lucene/.settings/org.eclipse.jdt.core.prefs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/.settings/org.eclipse.jdt.core.prefs -------------------------------------------------------------------------------- /esa-lucene/lib/servlet-api.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/lib/servlet-api.jar -------------------------------------------------------------------------------- /esa-lucene/src/config/db.conf: -------------------------------------------------------------------------------- 1 | localhost 2 | wiki 3 | root 4 | 123456 -------------------------------------------------------------------------------- /esa-lucene/src/config/stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/config/stopwords.txt -------------------------------------------------------------------------------- /esa-lucene/src/config/wordsim353-combined.tab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/config/wordsim353-combined.tab -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/api/concept/IConceptIterator.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/api/concept/IConceptIterator.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/api/concept/IConceptVector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/api/concept/IConceptVector.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/api/concept/IConceptVectorData.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/api/concept/IConceptVectorData.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/api/concept/scorer/CosineScorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/api/concept/scorer/CosineScorer.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/api/concept/search/IScorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/api/concept/search/IScorer.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/concept/ConceptVectorSimilarity.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/concept/ConceptVectorSimilarity.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/concept/TroveConceptVector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/concept/TroveConceptVector.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/concept/TroveConceptVectorOrderedIterator.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/concept/TroveConceptVectorOrderedIterator.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/demo/TestCombinedESAVectors.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/demo/TestCombinedESAVectors.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/demo/TestESAVectors.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/demo/TestESAVectors.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/demo/TestGeneralESAVectors.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/demo/TestGeneralESAVectors.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/demo/TestSimilarity.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/demo/TestSimilarity.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/demo/TestWordsim353.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/demo/TestWordsim353.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/index/ESASimilarity.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/index/ESASimilarity.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/index/ESAWikipediaIndexer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/index/ESAWikipediaIndexer.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/index/WikipediaAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/index/WikipediaAnalyzer.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/modify/IndexModifier.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/modify/IndexModifier.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/modify/IndexPruner.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/modify/IndexPruner.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/modify/MemIndexModifier.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/modify/MemIndexModifier.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/search/ESASearcher.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/search/ESASearcher.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/search/NormalizedWikipediaDistance.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/search/NormalizedWikipediaDistance.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/search/WikipediaNormalSearcher.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/search/WikipediaNormalSearcher.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/service/ESAServlet.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/service/ESAServlet.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/service/UTF8Filter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/service/UTF8Filter.java -------------------------------------------------------------------------------- /esa-lucene/src/edu/wiki/util/HeapSort.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/edu/wiki/util/HeapSort.java -------------------------------------------------------------------------------- /esa-lucene/src/org/apache/lucene/analysis/CustomFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/org/apache/lucene/analysis/CustomFilter.java -------------------------------------------------------------------------------- /esa-lucene/src/org/apache/lucene/analysis/CustomTokenizer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/src/org/apache/lucene/analysis/CustomTokenizer.java -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/lib/esa-web.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/lib/esa-web.jar -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/lib/lucene-analyzers-3.0.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/lib/lucene-analyzers-3.0.0.jar -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/lib/lucene-core-3.0.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/lib/lucene-core-3.0.0.jar -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/lib/mysql-connector-java-5.1.12-bin.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/lib/mysql-connector-java-5.1.12-bin.jar -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/lib/trove-2.1.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/lib/trove-2.1.0.jar -------------------------------------------------------------------------------- /esa-lucene/web/WEB-INF/web.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/esa-lucene/web/WEB-INF/web.xml -------------------------------------------------------------------------------- /lewis_smart_sorted_uniq.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/lewis_smart_sorted_uniq.txt -------------------------------------------------------------------------------- /readCatHier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/readCatHier.py -------------------------------------------------------------------------------- /scanCatHier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/scanCatHier.py -------------------------------------------------------------------------------- /scanData.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/scanData.py -------------------------------------------------------------------------------- /scanLinks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/scanLinks.py -------------------------------------------------------------------------------- /selected.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/selected.txt -------------------------------------------------------------------------------- /wiki_stop_categories.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/wiki_stop_categories.txt -------------------------------------------------------------------------------- /xmlwikiprep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/faraday/wikiprep-esa/HEAD/xmlwikiprep.py --------------------------------------------------------------------------------