List of usage examples for org.apache.lucene.analysis.util AbstractAnalysisFactory LUCENE_MATCH_VERSION_PARAM
String LUCENE_MATCH_VERSION_PARAM
To view the source code for org.apache.lucene.analysis.util AbstractAnalysisFactory LUCENE_MATCH_VERSION_PARAM.
Click Source Link
From source file:edu.cmu.lti.oaqa.annographix.solr.TokenizerParams.java
License:Apache License
/** Specifying which Lucene version we need */ private void addLuceneVersionParam() { mTokClassArgs.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, UtilConst.LUCENE_VERSION); }
From source file:edu.cmu.lti.oaqa.bio.index.medline.annotated.query.TokenizerParams.java
License:Apache License
/** Specifying which Lucene version we need */ private void addLuceneVersionParam() { mTokClassArgs.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, UtilConstMedline.LUCENE_VERSION); }
From source file:jp.co.mixi.rd.lucene.analysis.StandardPlusTokenizerFactoryTest.java
License:Apache License
@Test public void testStandardPlusTokenizer() throws Exception { try (Reader reader = new StringReader("Wha\u0301t's this thing do?")) { Map<String, String> args = new HashMap<String, String>(); args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, BaseTokenStreamTestCase.TEST_VERSION_CURRENT.toString()); StandardPlusTokenizerFactory factory = new StandardPlusTokenizerFactory(args); try (Tokenizer stream = factory.create(reader)) { BaseTokenStreamTestCase.assertTokenStreamContents(stream, new String[] { "Wha\u0301t's", "this", "thing", "do", "?" }); }/* ww w. j a va 2 s. c o m*/ } }
From source file:jp.co.mixi.rd.lucene.analysis.StandardPlusTokenizerFactoryTest.java
License:Apache License
@Test public void testStandardPlusTokenizerMaxTokenLength() throws Exception { StringBuilder builder = new StringBuilder(); for (int i = 0; i < 100; ++i) { builder.append("abcdefg"); // 7 * 100 = 700 char "word" }/*from w w w . j a v a 2s . c o m*/ String longWord = builder.toString(); String content = "one two three " + longWord + " four five six"; try (Reader reader = new StringReader(content)) { Map<String, String> args = new HashMap<String, String>(); args.put("maxTokenLength", "1000"); args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, BaseTokenStreamTestCase.TEST_VERSION_CURRENT.toString()); StandardPlusTokenizerFactory factory = new StandardPlusTokenizerFactory(args); try (Tokenizer stream = factory.create(reader)) { BaseTokenStreamTestCase.assertTokenStreamContents(stream, new String[] { "one", "two", "three", longWord, "four", "five", "six" }); } } }
From source file:jp.co.mixi.rd.lucene.analysis.StandardPlusTokenizerFactoryTest.java
License:Apache License
@Test public void testStandardPlusTokenizerNihongo() throws Exception { try (Reader reader = new StringReader("??? ? ?")) { Map<String, String> args = new HashMap<String, String>(); args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, BaseTokenStreamTestCase.TEST_VERSION_CURRENT.toString()); StandardPlusTokenizerFactory factory = new StandardPlusTokenizerFactory(args); try (Tokenizer stream = factory.create(reader)) { BaseTokenStreamTestCase.assertTokenStreamContents(stream, new String[] { "", "?", "", "", "", "", "", "", "?", "?", "?", "?" }); }/* w w w. j a va 2 s . co m*/ } }
From source file:jp.co.mixi.rd.lucene.analysis.StandardPlusTokenizerFactoryTest.java
License:Apache License
@Test public void testStandardPlusTokenizerSpace() throws Exception { try (Reader reader = new StringReader("?\n?")) { Map<String, String> args = new HashMap<String, String>(); args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, BaseTokenStreamTestCase.TEST_VERSION_CURRENT.toString()); StandardPlusTokenizerFactory factory = new StandardPlusTokenizerFactory(args); try (Tokenizer stream = factory.create(reader)) { BaseTokenStreamTestCase.assertTokenStreamContents(stream, new String[] { "?", "?" }); }/*from w ww. j av a 2 s . c o m*/ } }
From source file:jp.sf.fess.solr.plugin.util.MonitoringUtil.java
License:Apache License
public static String initBaseArgs(final Map<String, String> baseArgs, final String luceneVersion) { final String baseClass = baseArgs.remove(BASE_CLASS); baseArgs.put(CLASS, baseClass);//w w w .ja va 2 s. c om baseArgs.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, luceneVersion); return baseClass; }
From source file:org.aksw.palmetto.corpus.lucene.SimpleAnalyzer.java
License:Open Source License
public SimpleAnalyzer(boolean lowerCase) { Map<String, String> parameters = new HashMap<String, String>(); parameters.put(PatternTokenizerFactory.PATTERN, PATTERN); parameters.put(PatternTokenizerFactory.GROUP, "0"); parameters.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, version.name()); tokenizerFactory = new PatternTokenizerFactory(parameters); if (lowerCase) { parameters = new HashMap<String, String>(); parameters.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, version.name()); lowerCaseFilterFactory = new LowerCaseFilterFactory(parameters); } else {// w w w . j a v a 2 s. com lowerCaseFilterFactory = null; } }