Package org.apache.lucene.analysis.util

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<String, String>();
    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<String>();
    rules.add( "abcd=>efgh" );
    synMap = new SlowSynonymMap( true );
View Full Code Here
140
141
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
     
      if (Tokenizer.class.isAssignableFrom(c)) {
        String clazzName = c.getSimpleName();
        assertTrue(clazzName.endsWith("Tokenizer"));
        String simpleName = clazzName.substring(0, clazzName.length() - 9);
        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.getMessage().contains("SPI")) {
            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));
        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.getMessage().contains("SPI")) {
            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);
        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
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
51
52
53
54
55
56
57
58
59
60
61
      Version luceneMatchVersion,
      ServiceManager serviceManager) throws IOException {
    ResourceLoader defaultResourceLoader = new HibernateSearchResourceLoader( serviceManager );
    TokenizerDef token = analyzerDef.tokenizer();
    final Map<String, String> tokenMapsOfParameters = getMapOfParameters( token.params(), luceneMatchVersion );
    TokenizerFactory tokenFactory = instanceFromClass(
        TokenizerFactory.class,
        token.factory(),
        "Tokenizer factory",
        tokenMapsOfParameters
    );
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
 
  public void testBigramTokenizer() throws Exception {
    SlowSynonymMap synMap;

    // prepare bi-gram tokenizer factory
    TokenizerFactory tf = new NGramTokenizerFactory();
    Map<String, String> args = new HashMap<String, String>();
    args.put("minGramSize","2");
    args.put("maxGramSize","2");
    tf.init( args );

    // (ab)->(bc)->(cd)->[ef][fg][gh]
    List<String> rules = new ArrayList<String>();
    rules.add( "abcd=>efgh" );
    synMap = new SlowSynonymMap( true );
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
      doTestCharFilter(charFilter);
    }
  }
 
  private void doTestTokenizer(String tokenizer) throws IOException {
    TokenizerFactory factory = TokenizerFactory.forName(tokenizer);
    if (initialize(factory)) {
      // 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
131
132
133
134
135
136
137
138
139
140
141
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
     
      if (Tokenizer.class.isAssignableFrom(c)) {
        String clazzName = c.getSimpleName();
        assertTrue(clazzName.endsWith("Tokenizer"));
        String simpleName = clazzName.substring(0, clazzName.length() - 9);
        TokenizerFactory instance = TokenizerFactory.forName(simpleName);
        assertNotNull(instance);
        try {
          instance.setLuceneMatchVersion(TEST_VERSION_CURRENT);
          instance.init(Collections.<String,String>emptyMap());
          if (instance instanceof ResourceLoaderAware) {
            ((ResourceLoaderAware) instance).inform(loader);
          }
          assertSame(c, instance.create(new StringReader("")).getClass());
        } catch (IllegalArgumentException 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));
        TokenFilterFactory instance = TokenFilterFactory.forName(simpleName);
        assertNotNull(instance);
        try {
          instance.setLuceneMatchVersion(TEST_VERSION_CURRENT);
          instance.init(Collections.<String,String>emptyMap());
          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) {
          // 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);
        CharFilterFactory instance = CharFilterFactory.forName(simpleName);
        assertNotNull(instance);
        try {
          instance.setLuceneMatchVersion(TEST_VERSION_CURRENT);
          instance.init(Collections.<String,String>emptyMap());
          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
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(newAttributeFactory(), 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
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
204
205
      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
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
TOP

Related Classes of org.apache.lucene.analysis.util.TokenizerFactory

  • com.chenlb.mmseg4j.solr.MMSegTokenizerFactoryTest
  • org.apache.lucene.analysis.cn.smart.TestHMMChineseTokenizerFactory
  • org.apache.lucene.analysis.core.TestAllAnalyzersHaveFactories
  • org.apache.lucene.analysis.core.TestFactories
  • org.apache.lucene.analysis.synonym.TestSynonymMap
  • 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.