Examples of TokenizerFactory

Examples of org.apache.lucene.analysis.util.TokenizerFactory

31
32
33
34
35
36
37
38
39
40
41
42
public class TestHMMChineseTokenizerFactory extends BaseTokenStreamTestCase {
 
  /** Test showing the behavior */
  public void testSimple() throws Exception {
    Reader reader = new StringReader("我购买了道具和服装。");
    TokenizerFactory factory = new HMMChineseTokenizerFactory(new HashMap<String,String>());
    Tokenizer tokenizer = factory.create(reader);
    tokenizer.setReader(reader);
    // TODO: fix smart chinese to not emit punctuation tokens
    // at the moment: you have to clean up with WDF, or use the stoplist, etc
    assertTokenStreamContents(tokenizer,
       new String[] { "我", "购买", "了", "道具", "和", "服装", "," });
View Full Code Here

Examples of org.apache.lucene.analysis.util.TokenizerFactory

60
61
62
63
64
65
66
67
68
69
70
    }
  }
 
  private void doTestTokenizer(String tokenizer) throws IOException {
    Class<? extends TokenizerFactory> factoryClazz = TokenizerFactory.lookupClass(tokenizer);
    TokenizerFactory factory = (TokenizerFactory) initialize(factoryClazz);
    if (factory != null) {
      // we managed to fully create an instance. check a few more things:
     
      // if it implements MultiTermAware, sanity check its impl
      if (factory instanceof MultiTermAwareComponent) {
View Full Code Here

Examples of org.apache.lucene.analysis.util.TokenizerFactory

250
251
252
253
254
255
256
257
258
259
260
    // prepare bi-gram tokenizer factory
    Map<String, String> args = new HashMap<>();
    args.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM, "4.4");
    args.put("minGramSize","2");
    args.put("maxGramSize","2");
    TokenizerFactory tf = new NGramTokenizerFactory(args);
   
    // (ab)->(bc)->(cd)->[ef][fg][gh]
    List<String> rules = new ArrayList<>();
    rules.add( "abcd=>efgh" );
    synMap = new SlowSynonymMap( true );
View Full Code Here

Examples of org.apache.lucene.analysis.util.TokenizerFactory

142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
      if (Tokenizer.class.isAssignableFrom(c)) {
        String clazzName = c.getSimpleName();
        assertTrue(clazzName.endsWith("Tokenizer"));
        String simpleName = clazzName.substring(0, clazzName.length() - 9);
        assertNotNull(TokenizerFactory.lookupClass(simpleName));
        TokenizerFactory instance = null;
        try {
          instance = TokenizerFactory.forName(simpleName, args);
          assertNotNull(instance);
          if (instance instanceof ResourceLoaderAware) {
            ((ResourceLoaderAware) instance).inform(loader);
          }
          assertSame(c, instance.create(new StringReader("")).getClass());
        } catch (IllegalArgumentException e) {
          if (e.getCause() instanceof NoSuchMethodException) {
            // there is no corresponding ctor available
            throw e;
          }
          // TODO: For now pass because some factories have not yet a default config that always works
        }
      } else if (TokenFilter.class.isAssignableFrom(c)) {
        String clazzName = c.getSimpleName();
        assertTrue(clazzName.endsWith("Filter"));
        String simpleName = clazzName.substring(0, clazzName.length() - (clazzName.endsWith("TokenFilter") ? 11 : 6));
        assertNotNull(TokenFilterFactory.lookupClass(simpleName));
        TokenFilterFactory instance = null;
        try {
          instance = TokenFilterFactory.forName(simpleName, args);
          assertNotNull(instance);
          if (instance instanceof ResourceLoaderAware) {
            ((ResourceLoaderAware) instance).inform(loader);
          }
          Class<? extends TokenStream> createdClazz = instance.create(new KeywordTokenizer(new StringReader(""))).getClass();
          // only check instance if factory have wrapped at all!
          if (KeywordTokenizer.class != createdClazz) {
            assertSame(c, createdClazz);
          }
        } catch (IllegalArgumentException e) {
          if (e.getCause() instanceof NoSuchMethodException) {
            // there is no corresponding ctor available
            throw e;
          }
          // TODO: For now pass because some factories have not yet a default config that always works
        }
      } else if (CharFilter.class.isAssignableFrom(c)) {
        String clazzName = c.getSimpleName();
        assertTrue(clazzName.endsWith("CharFilter"));
        String simpleName = clazzName.substring(0, clazzName.length() - 10);
        assertNotNull(CharFilterFactory.lookupClass(simpleName));
        CharFilterFactory instance = null;
        try {
          instance = CharFilterFactory.forName(simpleName, args);
          assertNotNull(instance);
          if (instance instanceof ResourceLoaderAware) {
            ((ResourceLoaderAware) instance).inform(loader);
          }
          Class<? extends Reader> createdClazz = instance.create(new StringReader("")).getClass();
          // only check instance if factory have wrapped at all!
          if (StringReader.class != createdClazz) {
            assertSame(c, createdClazz);
          }
        } catch (IllegalArgumentException e) {
View Full Code Here

Examples of org.apache.lucene.analysis.util.TokenizerFactory

65
66
67
68
69
70
71
72
73
74
75
   */
  public static Analyzer buildAnalyzer(AnalyzerDef analyzerDef, Version luceneMatchVersion) throws IOException {
    ResourceLoader defaultResourceLoader = new HibernateSearchResourceLoader();
    TokenizerDef token = analyzerDef.tokenizer();
    final Map<String, String> tokenMapsOfParameters = getMapOfParameters( token.params(), luceneMatchVersion );
    TokenizerFactory tokenFactory = instanceFromClass( TokenizerFactory.class, token.factory(), "Tokenizer factory", 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

Examples of org.apache.lucene.analysis.util.TokenizerFactory

37
38
39
40
41
42
43
44
45
46
47
48
    FieldType ft = h.getCore().getLatestSchema().getFieldTypeByName(fieldTypeName);
    Analyzer a = ft.getAnalyzer();
    Assert.assertEquals(a.getClass(), TokenizerChain.class);
   
    TokenizerChain tc = (TokenizerChain) a;
    TokenizerFactory tf = tc.getTokenizerFactory();
    Assert.assertEquals(tf.getClass(), MMSegTokenizerFactory.class);
   
    MMSegTokenizerFactory mtf = (MMSegTokenizerFactory) tf;
   
    Assert.assertNotNull(mtf.dic);
    return mtf.dic;
View Full Code Here

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

Examples of org.apache.solr.analysis.TokenizerFactory

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

Examples of org.apache.solr.analysis.TokenizerFactory

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

Examples of org.apache.solr.analysis.TokenizerFactory

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
TOP
Copyright © 2018 www.massapi.com. 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.