Package org.apache.solr.analysis

Examples of org.apache.solr.analysis.TokenizerFactory

68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
    final boolean ignoreCase = getBoolean("ignoreCase", false);
    this.ignoreCase = ignoreCase;

    String tf = args.get("tokenizerFactory");

    final TokenizerFactory factory = tf == null ? null : loadTokenizerFactory(loader, tf, args);

    Analyzer analyzer = new ReusableAnalyzerBase() {
      @Override
      protected ReusableAnalyzerBase.TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_31, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_31, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };
View Full Code Here
156
157
158
159
160
161
162
163
164
    }
    return parser.build();
  }

  private static TokenizerFactory loadTokenizerFactory(ResourceLoader loader, String cname, Map<String, String> args) {
    TokenizerFactory tokFactory = (TokenizerFactory) loader.newInstance(cname);
    tokFactory.init(args);
    return tokFactory;
  }
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
      return namedList;
    }

    TokenizerChain tokenizerChain = (TokenizerChain) analyzer;
    CharFilterFactory[] cfiltfacs = tokenizerChain.getCharFilterFactories();
    TokenizerFactory tfac = tokenizerChain.getTokenizerFactory();
    TokenFilterFactory[] filtfacs = tokenizerChain.getTokenFilterFactories();

    NamedList<List<NamedList>> namedList = new NamedList<List<NamedList>>();

    if( cfiltfacs != null ){
      String source = value;
      for(CharFilterFactory cfiltfac : cfiltfacs ){
        CharStream reader = CharReader.get(new StringReader(source));
        reader = cfiltfac.create(reader);
        source = writeCharStream(namedList, reader);
      }
    }

    TokenStream tokenStream = tfac.create(tokenizerChain.charStream(new StringReader(value)));
    List<AttributeSource> tokens = analyzeTokenStream(tokenStream);

    namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokens, context));

    ListBasedTokenStream listBasedTokenStream = new ListBasedTokenStream(tokens);
View Full Code Here
406
407
408
409
410
411
412
413
414
415
416
417
418
      if (cfilters.size() > 0) {
        aninfo.add("charFilters", cfilters);
      }
     
      SimpleOrderedMap<Object> tokenizer = new SimpleOrderedMap<Object>();
      TokenizerFactory tfac = tchain.getTokenizerFactory();
      tokenizer.add("className", tfac.getClass().getName());
      tokenizer.add("args", tfac.getArgs());
      aninfo.add("tokenizer", tokenizer);

      TokenFilterFactory[] filtfacs = tchain.getTokenFilterFactories();
      SimpleOrderedMap<Map<String, Object>> filters = new SimpleOrderedMap<Map<String, Object>>();
      for (TokenFilterFactory filtfac : filtfacs) {
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
   * @return a Lucene <code>Analyzer</code>
   */
  public static Analyzer buildAnalyzer(AnalyzerDef analyzerDef, Version luceneMatchVersion) {
    ResourceLoader defaultResourceLoader = new HibernateSearchResourceLoader();
    TokenizerDef token = analyzerDef.tokenizer();
    TokenizerFactory tokenFactory = ( TokenizerFactory ) instantiate( token.factory() );
    final Map<String, String> tokenMapsOfParameters = getMapOfParameters( token.params(), luceneMatchVersion );
    tokenFactory.init( tokenMapsOfParameters );
    injectResourceLoader( tokenFactory, defaultResourceLoader, tokenMapsOfParameters );

    final int length = analyzerDef.filters().length;
    final int charLength = analyzerDef.charFilters().length;
    TokenFilterFactory[] filters = new TokenFilterFactory[length];
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
   * @return a Lucene <code>Analyzer</code>
   */
  public static Analyzer buildAnalyzer(AnalyzerDef analyzerDef, Version luceneMatchVersion) {
    ResourceLoader defaultResourceLoader = new HibernateSearchResourceLoader();
    TokenizerDef token = analyzerDef.tokenizer();
    TokenizerFactory tokenFactory = instanceFromClass( TokenizerFactory.class, token.factory(), "Tokenizer factory" );
    final Map<String, String> tokenMapsOfParameters = getMapOfParameters( token.params(), luceneMatchVersion );
    tokenFactory.init( tokenMapsOfParameters );
    injectResourceLoader( tokenFactory, defaultResourceLoader, tokenMapsOfParameters );

    final int length = analyzerDef.filters().length;
    final int charLength = analyzerDef.charFilters().length;
    TokenFilterFactory[] filters = new TokenFilterFactory[length];
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
   * @return a Lucene <code>Analyzer</code>
   */
  public static Analyzer buildAnalyzer(AnalyzerDef analyzerDef, Version luceneMatchVersion) {
    ResourceLoader defaultResourceLoader = new HibernateSearchResourceLoader();
    TokenizerDef token = analyzerDef.tokenizer();
    TokenizerFactory tokenFactory = instanceFromClass( TokenizerFactory.class, token.factory(), "Tokenizer factory" );
    final Map<String, String> tokenMapsOfParameters = getMapOfParameters( token.params(), luceneMatchVersion );
    tokenFactory.init( tokenMapsOfParameters );
    injectResourceLoader( tokenFactory, defaultResourceLoader, tokenMapsOfParameters );

    final int length = analyzerDef.filters().length;
    final int charLength = analyzerDef.charFilters().length;
    TokenFilterFactory[] filters = new TokenFilterFactory[length];
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
      return namedList;
    }

    TokenizerChain tokenizerChain = (TokenizerChain) analyzer;
    CharFilterFactory[] cfiltfacs = tokenizerChain.getCharFilterFactories();
    TokenizerFactory tfac = tokenizerChain.getTokenizerFactory();
    TokenFilterFactory[] filtfacs = tokenizerChain.getTokenFilterFactories();

    NamedList<List<NamedList>> namedList = new NamedList<List<NamedList>>();

    if( cfiltfacs != null ){
      String source = value;
      for(CharFilterFactory cfiltfac : cfiltfacs ){
        CharStream reader = CharReader.get(new StringReader(source));
        reader = cfiltfac.create(reader);
        source = writeCharStream(namedList, reader);
      }
    }

    TokenStream tokenStream = tfac.create(tokenizerChain.charStream(new StringReader(value)));
    List<AttributeSource> tokens = analyzeTokenStream(tokenStream);

    namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokens, context));

    ListBasedTokenStream listBasedTokenStream = new ListBasedTokenStream(tokens);
View Full Code Here
404
405
406
407
408
409
410
411
412
413
414
415
416
      if (cfilters.size() > 0) {
        aninfo.add("charFilters", cfilters);
      }
     
      SimpleOrderedMap<Object> tokenizer = new SimpleOrderedMap<Object>();
      TokenizerFactory tfac = tchain.getTokenizerFactory();
      tokenizer.add("className", tfac.getClass().getName());
      tokenizer.add("args", tfac.getArgs());
      aninfo.add("tokenizer", tokenizer);

      TokenFilterFactory[] filtfacs = tchain.getTokenFilterFactories();
      SimpleOrderedMap<Map<String, Object>> filters = new SimpleOrderedMap<Map<String, Object>>();
      for (TokenFilterFactory filtfac : filtfacs) {
View Full Code Here
386
387
388
389
390
391
392
393
394
395
396
397
398
    SimpleOrderedMap<Object> aninfo = new SimpleOrderedMap<Object>();
    aninfo.add("className", analyzer.getClass().getName());
    if (analyzer instanceof TokenizerChain) {
       SimpleOrderedMap<Object> tokenizer = new SimpleOrderedMap<Object>();
         TokenizerChain tchain = (TokenizerChain)analyzer;
         TokenizerFactory tfac = tchain.getTokenizerFactory();
         tokenizer.add("className", tfac.getClass().getName());
         tokenizer.add("args", tfac.getArgs());
         aninfo.add("tokenizer", tokenizer);
         TokenFilterFactory[] filtfacs = tchain.getTokenFilterFactories();
        
        SimpleOrderedMap<Map<String, Object>> filters = new SimpleOrderedMap<Map<String, Object>>();
        for (TokenFilterFactory filtfac : filtfacs) {
View Full Code Here
TOP

Related Classes of org.apache.solr.analysis.TokenizerFactory

  • com.github.le11.nls.solr.TypeAwareSynonymFilterFactory
  • org.apache.solr.handler.admin.LukeRequestHandler
  • org.apache.solr.handler.AnalysisRequestHandlerBase
  • org.apache.solr.schema.IndexSchema
  • org.hibernate.search.impl.InitContext
  • org.hibernate.search.impl.SolrAnalyzerBuilder
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.