public class WikipediaArticleReader extends WikipediaPageReader
PARAM_ONLY_FIRST_PARAGRAPH
currentArticleIndex, nrOfArticles, outputPlainText, pageBuffer, pageIdFile, pageIdParamArray, pageIter, pageNameFile, pageNameParamArray, PARAM_OUTPUT_PLAIN_TEXT, PARAM_PAGE_BUFFER, PARAM_PAGE_ID_LIST, PARAM_PAGE_TITLE_LIST, PARAM_PATH_TO_PAGE_ID_LIST, PARAM_PATH_TO_PAGE_TITLE_LIST, parser
dbconfig, PARAM_CREATE_DATABASE_CONFIG_ANNOTATION, PARAM_DB, PARAM_HOST, PARAM_LANGUAGE, PARAM_PASSWORD, PARAM_USER, wiki
Constructor and Description |
---|
WikipediaArticleReader() |
Modifier and Type | Method and Description |
---|---|
protected boolean |
isValidPage(de.tudarmstadt.ukp.wikipedia.api.Page page) |
getPlainDocumentText, initialize
getDocumentText, getNext, getPage, getProgress, hasNext
close, getLogger, getNext, initialize
destroy, getCasInitializer, getProcessingResourceMetaData, initialize, isConsuming, reconfigure, setCasInitializer, typeSystemInit
getConfigParameterValue, getConfigParameterValue, setConfigParameterValue, setConfigParameterValue
getCasManager, getMetaData, getRelativePathResolver, getResourceManager, getUimaContext, getUimaContextAdmin, setLogger, setMetaData
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
protected boolean isValidPage(de.tudarmstadt.ukp.wikipedia.api.Page page) throws de.tudarmstadt.ukp.wikipedia.api.exception.WikiTitleParsingException
isValidPage
in class WikipediaPageReader
de.tudarmstadt.ukp.wikipedia.api.exception.WikiTitleParsingException
Copyright © 2007–2018 Ubiquitous Knowledge Processing (UKP) Lab, Technische Universität Darmstadt. All rights reserved.