Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.Token$TokenAttributeFactory

286
287
288
289
290
291
292
293
294
295
296
297
298
    BooleanQuery allFieldsQuery = new BooleanQuery();
    String value = String.valueOf(condition.getValue());

    LowercaseWhitespaceAnalyzer analyzer = new LowercaseWhitespaceAnalyzer();
    TokenStream tokenStream = analyzer.tokenStream(String.valueOf(IEntity.ALL_FIELDS), new StringReader(value));
    Token token = null;
    while ((token = tokenStream.next()) != null) {
      String termText = token.termText();

      /* Contained in Title */
      WildcardQuery titleQuery = new WildcardQuery(new Term(String.valueOf(INews.TITLE), termText));
      allFieldsQuery.add(new BooleanClause(titleQuery, Occur.SHOULD));

View Full Code Here
458
459
460
461
462
463
464
465
466
467
468
469
470
      case SIMILIAR_TO: {
        BooleanQuery similarityQuery = new BooleanQuery();

        LowercaseWhitespaceAnalyzer analyzer = new LowercaseWhitespaceAnalyzer();
        TokenStream tokenStream = analyzer.tokenStream(String.valueOf(IEntity.ALL_FIELDS), new StringReader(value));
        Token token = null;
        while ((token = tokenStream.next()) != null) {
          Term term = new Term(fieldname, token.termText());
          similarityQuery.add(new BooleanClause(new FuzzyQuery(term), Occur.MUST));
        }

        return similarityQuery;
      }
View Full Code Here
622
623
624
625
626
627
628
629
630
631
632
633
634
      case SIMILIAR_TO: {
        BooleanQuery similarityQuery = new BooleanQuery();

        LowercaseWhitespaceAnalyzer similarAnalyzer = new LowercaseWhitespaceAnalyzer();
        TokenStream tokenStream = similarAnalyzer.tokenStream(String.valueOf(IEntity.ALL_FIELDS), new StringReader(value));
        Token token = null;
        while ((token = tokenStream.next()) != null) {
          String termText = new String(token.termBuffer(), 0, token.termLength());
          Term term = new Term(fieldname, termText);
          similarityQuery.add(new BooleanClause(new FuzzyQuery(term), Occur.MUST));
        }

        return similarityQuery;
View Full Code Here
189
190
191
192
193
194
195
196
197
198
199
    return stream;           
  }
 
  private List getTokens(TokenStream stream) throws IOException {
    ArrayList tokens = new ArrayList();
    Token token;
    while ((token = stream.next()) != null) {
      tokens.add(token);
    }
    return tokens;
  }
View Full Code Here
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
  private void assertEquals(List tokens1, List tokens2) {
    int size = Math.min(tokens1.size(), tokens2.size());
    int i=0;
    try {
      for (; i < size; i++) {
        Token t1 = (Token) tokens1.get(i);
        Token t2 = (Token) tokens2.get(i);
        if (!(t1.termText().equals(t2.termText()))) throw new IllegalStateException("termText");
        if (t1.startOffset() != t2.startOffset()) throw new IllegalStateException("startOffset");
        if (t1.endOffset() != t2.endOffset()) throw new IllegalStateException("endOffset");
        if (!(t1.type().equals(t2.type()))) throw new IllegalStateException("type");
      }
      if (tokens1.size() != tokens2.size())   throw new IllegalStateException("size1=" + tokens1.size() + ", size2=" + tokens2.size());
    }

    catch (IllegalStateException e) {
View Full Code Here
225
226
227
228
229
230
231
232
233
234
 
  private String toString(List tokens) {
    if (tokens == null) return "null";
    String str = "[";
    for (int i=0; i < tokens.size(); i++) {
      Token t1 = (Token) tokens.get(i);
      str = str + "'" + t1.termText() + "', ";
    }
    return str + "]";
  }
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
159
            TokenStream includeStream =
                    new StandardAnalyzer().tokenStream(null, new StringReader(escape(terms).toLowerCase()));

            while (true) {
                Token t = includeStream.next();
                if (t == null) break;
                query.add( new Term(fieldName, t.termText()) );
            }

            return query.getTerms().length > 0 ? query : null;
        } catch (Exception ex) {
            throw new RuntimeException(ex);
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
    long b2 = System.currentTimeMillis();// (b2 - b1)Ϊװ�شʵ�ʱ��
    Reader r = new StringReader(testString);
    XTokenizer ts = (XTokenizer) analyzer.tokenStream("", r);

    Token t;
    while ((t = ts.next()) != null) {
       //System.out.println(t);
    }

    long b3 = System.currentTimeMillis();
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
   
    long b2 = System.currentTimeMillis();// (b2 - b1)Ϊװ�شʵ�ʱ��
    Reader r = new StringReader(testString);
    XTokenizer ts = (XTokenizer) analyzer.tokenStream("", r);

    Token t;
    while ((t = ts.next()) != null) {
       //System.out.println(t);
    }

    long b3 = System.currentTimeMillis();
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
    this.tokens = new LinkedList<Token>();
    return iter;
  }

  public void collect(String word, int offset, int end) {
    Token c = candidate != null ? candidate : last;
    if (c == null) {
      candidate = new Token(word, offset, end);
    } else if (offset == c.startOffset()) {
      if (end > c.endOffset()) {
        candidate = new Token(word, offset, end);
      }
    } else if (offset > c.startOffset()) {
      if (candidate != null) {
        select(candidate);
      }
      if (end > c.endOffset()) {
        candidate = new Token(word, offset, end);
      } else {
        candidate = null;
      }
    } else if (end >= c.endOffset()) {
      if (last != null && last.startOffset() >= offset
          && last.endOffset() <= end) {
        for (Iterator iter = tokens.iterator(); iter.hasNext();) {
          last = (Token) iter.next();
          if (last.startOffset() >= offset && last.endOffset() <= end) {
            iter.remove();
          }
        }
      }
      last = null;
      candidate = new Token(word, offset, end);
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.Token$TokenAttributeFactory

  • com.chenlb.mmseg4j.analysis.CutLetterDigitFilter
  • com.flaptor.hounder.classifier.util.TupleTokenizer
  • com.stimulus.archiva.search.EmailFilter
  • com.stimulus.archiva.search.FileNameFilter
  • net.nutch.analysis.CommonGrams
  • net.nutch.analysis.CommonGrams$Filter
  • net.nutch.analysis.NutchDocumentTokenizer
  • org.apache.cocoon.bean.query.SimpleLuceneCriterionBean
  • org.apache.jackrabbit.core.query.lucene.AbstractExcerpt
  • org.apache.jackrabbit.core.query.lucene.SearchIndex
    • 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.