Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.CharArraySet$CharArraySetIterator

85
86
87
88
89
90
91
92
93
94
95
      boolean ignoreCase = false;
      String ignoreStr = args.get( KEEP_IGNORE_CASE );
      if ( "true".equalsIgnoreCase( ignoreStr ) ) {
        ignoreCase = true;
      }
      keep = new CharArraySet( 10, ignoreCase );
      while ( st.hasMoreTokens() ) {
        k = st.nextToken().trim();
        keep.add( k.toCharArray() );
      }
    }
View Full Code Here
52
53
54
55
56
57
58
59
      catch ( IOException e ) {
        throw new RuntimeException( e );
      }
    }
    else {
      stopWords = new CharArraySet( StopAnalyzer.ENGLISH_STOP_WORDS_SET, ignoreCase );
    }
  }
View Full Code Here
51
52
53
54
55
56
57
  /**
   * Set the keep word list.
   * NOTE: if ignoreCase==true, the words are expected to be lowercase
   */
  public void setWords(Set<String> words) {
    this.words = new CharArraySet( words, ignoreCase );
  }
View Full Code Here
56
57
58
59
60
61
62
63
64
    this.words = new CharArraySet( words, ignoreCase );
  }

  public void setIgnoreCase(boolean ignoreCase) {
    if ( words != null && this.ignoreCase != ignoreCase ) {
      words = new CharArraySet( words, ignoreCase );
    }
    this.ignoreCase = ignoreCase;
  }
View Full Code Here
40
41
42
43
44
45
46
  /**
   * @deprecated Use {@link #KeepWordFilter(TokenStream, Set, boolean)} instead
   */
  @Deprecated
  public KeepWordFilter(TokenStream in, Set<String> words, boolean ignoreCase) {
    this( in, new CharArraySet( words, ignoreCase ) );
  }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
      try {
        File protectedWordFiles = new File( wordFiles );
        if ( protectedWordFiles.exists() ) {
          List<String> wlist = loader.getLines( wordFiles );
          //This cast is safe in Lucene
          protectedWords = new CharArraySet(
              wlist, false
          );//No need to go through StopFilter as before, since it just uses a List internally
        }
        else {
          List<String> files = StrUtils.splitFileNames( wordFiles );
          for ( String file : files ) {
            List<String> wlist = loader.getLines( file.trim() );
            if ( protectedWords == null ) {
              protectedWords = new CharArraySet( wlist, false );
            }
            else {
              protectedWords.addAll( wlist );
            }
          }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
      try {
        File protectedWordFiles = new File( wordFiles );
        if ( protectedWordFiles.exists() ) {
          List<String> wlist = loader.getLines( wordFiles );
          //This cast is safe in Lucene
          protectedWords = new CharArraySet(
              wlist, false
          );//No need to go through StopFilter as before, since it just uses a List internally
        }
        else {
          List<String> files = StrUtils.splitFileNames( wordFiles );
          for ( String file : files ) {
            List<String> wlist = loader.getLines( file.trim() );
            if ( protectedWords == null ) {
              protectedWords = new CharArraySet( wlist, false );
            }
            else {
              protectedWords.addAll( wlist );
            }
          }
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
  protected CharArraySet getWordSet(ResourceLoader loader,
                    String wordFiles, boolean ignoreCase) throws IOException {
    assureMatchVersion();
    List<String> files = StrUtils.splitFileNames( wordFiles );
    CharArraySet words = null;
    if ( files.size() > 0 ) {
      // default stopwords list has 35 or so words, but maybe don't make it that
      // big to start
      words = new CharArraySet( files.size() * 10, ignoreCase );
      for ( String file : files ) {
        List<String> wlist = loader.getLines( file.trim() );
        words.addAll(
            StopFilter.makeStopSet(
                wlist,
                ignoreCase
            )
        );
View Full Code Here
110
111
112
113
114
115
116
117
118
    super( input );
    if ( commonWords instanceof CharArraySet ) {
      this.commonWords = ( CharArraySet ) commonWords;
    }
    else {
      this.commonWords = new CharArraySet( commonWords.size(), ignoreCase );
      this.commonWords.addAll( commonWords );
    }
  }
View Full Code Here
176
177
178
179
180
181
182
183
184
   *
   * @deprecated create a CharArraySet with CharArraySet instead
   */
  @Deprecated
  public static CharArraySet makeCommonSet(String[] commonWords, boolean ignoreCase) {
    CharArraySet commonSet = new CharArraySet( commonWords.length, ignoreCase );
    commonSet.addAll( Arrays.asList( commonWords ) );
    return commonSet;
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.CharArraySet$CharArraySetIterator

  • com.github.le11.nls.lucene.TypeAwareStopFilter
  • com.github.le11.nls.solr.TypeAwareStopFilterFactory
  • de.jetwick.solrplugin.TWordDelimiterFilterFactory
  • edu.wiki.index.WikipediaAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.TestBulgarianAnalyzer
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.ca.TestCatalanAnalyzer
    • 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.