Package org.apache.solr.analysis

Examples of org.apache.solr.analysis.TokenizerChain

938
939
940
941
942
943
944
945
        return null; // used for map registration
      }
    };
    filterLoader.load( loader, (NodeList)xpath.evaluate("./filter", node, XPathConstants.NODESET) );

    return new TokenizerChain(charFilters.toArray(new CharFilterFactory[charFilters.size()]),
        tokenizers.get(0), filters.toArray(new TokenFilterFactory[filters.size()]));
  };
View Full Code Here
95
96
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
      NamedList<List<NamedList>> namedList = new NamedList<List<NamedList>>();
      namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(analyzeTokenStream(tokenStream), context));
      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
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
  private static SimpleOrderedMap<Object> getAnalyzerInfo(Analyzer analyzer) {
    SimpleOrderedMap<Object> aninfo = new SimpleOrderedMap<Object>();
    aninfo.add("className", analyzer.getClass().getName());
    if (analyzer instanceof TokenizerChain) {

      TokenizerChain tchain = (TokenizerChain)analyzer;

      CharFilterFactory[] cfiltfacs = tchain.getCharFilterFactories();
      SimpleOrderedMap<Map<String, Object>> cfilters = new SimpleOrderedMap<Map<String, Object>>();
      for (CharFilterFactory cfiltfac : cfiltfacs) {
        Map<String, Object> tok = new HashMap<String, Object>();
        String className = cfiltfac.getClass().getName();
        tok.put("className", className);
        tok.put("args", cfiltfac.getArgs());
        cfilters.add(className.substring(className.lastIndexOf('.')+1), tok);
      }
      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) {
        Map<String, Object> tok = new HashMap<String, Object>();
        String className = filtfac.getClass().getName();
        tok.put("className", className);
View Full Code Here
229
230
231
232
233
234
235
236
        return null; // used for map registration
      }
    };
    filterLoader.load(loader, tokenFilterNodes);

    return new TokenizerChain(charFilters.toArray(new CharFilterFactory[charFilters.size()]),
        tokenizers.get(0), filters.toArray(new TokenFilterFactory[filters.size()]));
  }
View Full Code Here
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
    if (!(analyzer instanceof TokenizerChain)) {
      throw new SolrException(SolrException.ErrorCode.SERVER_ERROR,
        "Invalid index analyzer '" + analyzer.getClass() + "' received");
    }

    final TokenizerChain chain = (TokenizerChain) analyzer;
    // copy the existing list of token filters
    final TokenFilterFactory[] old = chain.getTokenFilterFactories();
    final TokenFilterFactory[] filterFactories = new TokenFilterFactory[old.length + 3];
    System.arraycopy(old, 0, filterFactories, 0, old.length);
    // append the datatype analyzer filter factory
    final DatatypeAnalyzerFilterFactory datatypeFactory = new DatatypeAnalyzerFilterFactory(luceneDefaultVersion);
    datatypeFactory.register(datatypes);
    filterFactories[old.length] = datatypeFactory;
    // append the position attribute filter factory
    filterFactories[old.length + 1] = new PositionAttributeFilterFactory();
    // append the siren payload filter factory
    filterFactories[old.length + 2] = new SirenPayloadFilterFactory();
    // create a new tokenizer chain with the updated list of filter factories
    return new TokenizerChain(chain.getCharFilterFactories(),
      chain.getTokenizerFactory(), filterFactories);
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
    final IndexSchema schema = h.getCore().getSchema();
    final SchemaField ntriple = schema.getField(JSON_FIELD);
    final FieldType tmp = ntriple.getType();

    assertTrue(tmp.getAnalyzer() instanceof TokenizerChain);
    final TokenizerChain ts = (TokenizerChain) tmp.getAnalyzer();
    assertNotNull(ts.getTokenizerFactory());
    assertTrue(ts.getTokenizerFactory() instanceof JsonTokenizerFactory);

    // 3 filters for index analyzer
    assertNotNull(ts.getTokenFilterFactories());
    assertEquals(3, ts.getTokenFilterFactories().length);
    assertTrue(ts.getTokenFilterFactories()[0] instanceof DatatypeAnalyzerFilterFactory);
    assertTrue(ts.getTokenFilterFactories()[1] instanceof PositionAttributeFilterFactory);
    assertTrue(ts.getTokenFilterFactories()[2] instanceof SirenPayloadFilterFactory);

    // no query analyzer
    assertNull(tmp.getQueryAnalyzer());
  }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
  public void testSirenFieldDatatypeAnalyzer() throws Exception {
    final IndexSchema schema = h.getCore().getSchema();
    final SchemaField ntriple = schema.getField(JSON_FIELD);
    final FieldType tmp = ntriple.getType();

    TokenizerChain ts = (TokenizerChain) tmp.getAnalyzer();

    assertTrue(ts.getTokenFilterFactories()[0] instanceof DatatypeAnalyzerFilterFactory);
    final DatatypeAnalyzerFilterFactory f = (DatatypeAnalyzerFilterFactory) ts.getTokenFilterFactories()[0];
    assertNotNull(f.getDatatypeAnalyzers());
    assertEquals(9, f.getDatatypeAnalyzers().size());

    assertNotNull(f.getDatatypeAnalyzers().get("http://json.org/field"));
    ts = (TokenizerChain) f.getDatatypeAnalyzers().get("http://json.org/field");
    assertNotNull(ts.getTokenizerFactory());
    assertTrue(ts.getTokenizerFactory() instanceof WhitespaceTokenizerFactory);

    assertNotNull(f.getDatatypeAnalyzers().get("http://www.w3.org/2001/XMLSchema#string"));
    ts = (TokenizerChain) f.getDatatypeAnalyzers().get("http://www.w3.org/2001/XMLSchema#string");
    assertNotNull(ts.getTokenizerFactory());
    assertTrue(ts.getTokenizerFactory() instanceof UAX29URLEmailTokenizerFactory);

    assertNotNull(f.getDatatypeAnalyzers().get("http://www.w3.org/2001/XMLSchema#int"));
    assertTrue(f.getDatatypeAnalyzers().get("http://www.w3.org/2001/XMLSchema#int") instanceof IntNumericAnalyzer);
    final IntNumericAnalyzer a = (IntNumericAnalyzer) f.getDatatypeAnalyzers().get("http://www.w3.org/2001/XMLSchema#int");
    assertEquals(8, a.getPrecisionStep());
View Full Code Here
93
94
95
96
97
98
99
          charFilterDef.params(), luceneMatchVersion
      );
      charFilters[index].init( mapOfParameters );
      injectResourceLoader( charFilters[index], defaultResourceLoader, mapOfParameters );
    }
    return new TokenizerChain( charFilters, tokenFactory, filters );
  }
View Full Code Here
93
94
95
96
97
98
99
          charFilterDef.params(), luceneMatchVersion
      );
      charFilters[index].init( mapOfParameters );
      injectResourceLoader( charFilters[index], defaultResourceLoader, mapOfParameters );
    }
    return new TokenizerChain( charFilters, tokenFactory, filters );
  }
View Full Code Here
94
95
96
97
98
99
100
          charFilterDef.params(), luceneMatchVersion
      );
      charFilters[index].init( mapOfParameters );
      injectResourceLoader( charFilters[index], defaultResourceLoader, mapOfParameters );
    }
    return new TokenizerChain( charFilters, tokenFactory, filters );
  }
View Full Code Here
TOP

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

  • com.chenlb.mmseg4j.solr.MMSegTokenizerFactoryTest
  • org.apache.lucene.analysis.CharStream
  • org.apache.lucene.analysis.Tokenizer
  • org.apache.lucene.analysis.TokenStream
  • org.apache.solr.handler.admin.LukeRequestHandler
  • org.apache.solr.handler.AnalysisRequestHandlerBase
  • org.apache.solr.schema.IndexSchema
  • org.apache.solr.schema.TrieDateField
  • org.apache.solr.search.SolrQueryParser
  • org.hibernate.search.impl.InitContext
    • 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.