| /lucene-3.6.0/lucene/core/src/java/org/apache/lucene/analysis/ |
| H A D | StopwordAnalyzerBase.java | 40 protected final CharArraySet stopwords; field in class:StopwordAnalyzerBase 46 * stopwords 49 * stopwords 52 return stopwords; 60 * @param stopwords 63 protected StopwordAnalyzerBase(final Version version, final Set<?> stopwords) { argument 65 // analyzers should use char array set for stopwords! 66 this.stopwords = stopwords == null ? CharArraySet.EMPTY_SET : CharArraySet 67 .unmodifiableSet(CharArraySet.copy(version, stopwords)); 124 loadStopwordSet(File stopwords, Version matchVersion) argument 148 loadStopwordSet(Reader stopwords, Version matchVersion) argument [all...] |
| H A D | StopAnalyzer.java | 37 * supplementary characters in stopwords 89 * @param stopwords Reader to load stop words from */ 90 public StopAnalyzer(Version matchVersion, Reader stopwords) throws IOException { argument 91 this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion)); 108 source, stopwords));
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ |
| H A D | ArabicAnalyzer.java | 59 * File containing default Arabic stopwords. 64 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 67 * The comment character in the stopwords file. All lines prefixed with this will be ignored 114 * @param stopwords 117 public ArabicAnalyzer(Version matchVersion, Set<?> stopwords){ argument 118 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 128 * @param stopwords 133 public ArabicAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet){ argument 134 super(matchVersion, stopwords); 144 public ArabicAnalyzer( Version matchVersion, String... stopwords ) { [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/el/ |
| H A D | GreekAnalyzer.java | 37 * Supports an external list of stopwords (words 39 * A default set of stopwords is used unless an alternative list is specified. 55 /** File containing default Greek stopwords. */ 56 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 59 * Returns a set of default Greek-stopwords 60 * @return a set of default Greek-stopwords 92 * <b>NOTE:</b> The stopwords set should be pre-processed with the logic of 97 * @param stopwords a stopword set 99 public GreekAnalyzer(Version matchVersion, Set<?> stopwords) { argument 100 super(matchVersion, stopwords); 109 GreekAnalyzer(Version matchVersion, String... stopwords) argument 118 GreekAnalyzer(Version matchVersion, Map<?,?> stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/fa/ |
| H A D | PersianAnalyzer.java | 46 * yeh and keheh) are standardized. "Stemming" is accomplished via stopwords. 52 * File containing default Persian stopwords. 59 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 62 * The comment character in the stopwords file. All lines prefixed with this 106 * @param stopwords 109 public PersianAnalyzer(Version matchVersion, Set<?> stopwords){ argument 110 super(matchVersion, stopwords); 118 public PersianAnalyzer(Version matchVersion, String... stopwords) { argument 119 this(matchVersion, StopFilter.makeStopSet(matchVersion, stopwords)); 127 public PersianAnalyzer(Version matchVersion, Hashtable<?, ?> stopwords) { argument 137 PersianAnalyzer(Version matchVersion, File stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/br/ |
| H A D | BrazilianAnalyzer.java | 46 * Supports an external list of stopwords (words that 57 * List of typical Brazilian Portuguese stopwords. 82 /** File containing default Brazilian Portuguese stopwords. */ 83 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 127 * @param stopwords 130 public BrazilianAnalyzer(Version matchVersion, Set<?> stopwords) { argument 131 super(matchVersion, stopwords); 139 * @param stopwords 142 public BrazilianAnalyzer(Version matchVersion, Set<?> stopwords, argument 144 this(matchVersion, stopwords); 154 BrazilianAnalyzer(Version matchVersion, String... stopwords) argument 163 BrazilianAnalyzer(Version matchVersion, Map<?,?> stopwords) argument 172 BrazilianAnalyzer(Version matchVersion, File stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/de/ |
| H A D | GermanAnalyzer.java | 49 * Supports an external list of stopwords (words that 52 * A default set of stopwords is used unless an alternative list is specified, but the 62 * Snowball stopwords are used by default. 73 * List of typical german stopwords. 92 /** File containing default German stopwords. */ 96 * Returns a set of default German-stopwords 97 * @return a set of default German-stopwords 122 * Contains the stopwords used with the {@link StopFilter}. 146 * @param stopwords 149 public GermanAnalyzer(Version matchVersion, Set<?> stopwords) { argument 163 GermanAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) argument 173 GermanAnalyzer(Version matchVersion, String... stopwords) argument 182 GermanAnalyzer(Version matchVersion, Map<?,?> stopwords) argument 192 GermanAnalyzer(Version matchVersion, File stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/cz/ |
| H A D | CzechAnalyzer.java | 43 * Supports an external list of stopwords (words that will not be indexed at 44 * all). A default set of stopwords is used unless an alternative list is 62 * List of typical stopwords. 87 /** File containing default Czech stopwords. */ 88 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 91 * Returns a set of default Czech-stopwords 93 * @return a set of default Czech-stopwords 116 * Contains the stopwords used with the {@link StopFilter}. 138 * @param stopwords a stopword set 140 public CzechAnalyzer(Version matchVersion, Set<?> stopwords) { argument 153 CzechAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionTable) argument 169 CzechAnalyzer(Version matchVersion, String... stopwords) argument 182 CzechAnalyzer(Version matchVersion, HashSet<?> stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ru/ |
| H A D | RussianAnalyzer.java | 44 * Supports an external list of stopwords (words that 46 * A default set of stopwords is used unless an alternative list is specified. 53 * SnowballFilter, and Snowball stopwords are used by default. 59 * List of typical Russian stopwords. (for backwards compatibility) 76 /** File containing default Russian stopwords. */ 121 public RussianAnalyzer(Version matchVersion, String... stopwords) { argument 122 this(matchVersion, StopFilter.makeStopSet(matchVersion, stopwords)); 130 * @param stopwords 133 public RussianAnalyzer(Version matchVersion, Set<?> stopwords){ argument 134 this(matchVersion, stopwords, CharArraySe 146 RussianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) argument 158 RussianAnalyzer(Version matchVersion, Map<?,?> stopwords) argument [all...] |
| /lucene-3.6.0/lucene/core/src/java/org/apache/lucene/analysis/standard/ |
| H A D | ClassicAnalyzer.java | 44 * supplementary characters in stopwords 94 * @param stopwords File to read stop words from 98 public ClassicAnalyzer(Version matchVersion, File stopwords) throws IOException { argument 99 this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords, 107 * @param stopwords Reader to read stop words from */ 108 public ClassicAnalyzer(Version matchVersion, Reader stopwords) throws IOException { argument 109 this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion)); 136 tok = new StopFilter(matchVersion, tok, stopwords);
|
| H A D | StandardAnalyzer.java | 43 * in stopwords. {@link ClassicTokenizer} and {@link ClassicAnalyzer} 90 * @param stopwords File to read stop words from 94 public StandardAnalyzer(Version matchVersion, File stopwords) throws IOException { argument 95 this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords, 103 * @param stopwords Reader to read stop words from */ 104 public StandardAnalyzer(Version matchVersion, Reader stopwords) throws IOException { argument 105 this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion)); 132 tok = new StopFilter(matchVersion, tok, stopwords);
|
| H A D | UAX29URLEmailAnalyzer.java | 72 * @param stopwords Reader to read stop words from */ 73 public UAX29URLEmailAnalyzer(Version matchVersion, Reader stopwords) throws IOException { argument 74 this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion)); 100 tok = new StopFilter(matchVersion, tok, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/id/ |
| H A D | IndonesianAnalyzer.java | 39 /** File containing default Indonesian stopwords. */ 40 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 82 * @param stopwords 85 public IndonesianAnalyzer(Version matchVersion, Set<?> stopwords){ argument 86 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 96 * @param stopwords 101 public IndonesianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet){ argument 102 super(matchVersion, stopwords); 124 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/cjk/ |
| H A D | CJKAnalyzer.java | 38 * and filters stopwords with {@link StopFilter} 90 * @param stopwords 93 public CJKAnalyzer(Version matchVersion, Set<?> stopwords){ argument 94 super(matchVersion, stopwords); 119 return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords)); 122 return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/nl/ |
| H A D | DutchAnalyzer.java | 50 * Supports an external list of stopwords (words that 54 * A default set of stopwords is used unless an alternative list is specified, but the 67 * stopwords are used by default. 77 * List of typical Dutch stopwords. 83 /** File containing default Dutch stopwords. */ 128 * Contains the stopwords used with the StopFilter. 150 public DutchAnalyzer(Version matchVersion, Set<?> stopwords){ argument 153 this(matchVersion, stopwords, CharArraySet.EMPTY_SET, 159 public DutchAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionTable){ argument 162 this(matchVersion, stopwords, stemExclusionTabl 168 DutchAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionTable, CharArrayMap<String> stemOverrideDict) argument 183 DutchAnalyzer(Version matchVersion, String... stopwords) argument 194 DutchAnalyzer(Version matchVersion, HashSet<?> stopwords) argument 205 DutchAnalyzer(Version matchVersion, File stopwords) argument [all...] |
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/bg/ |
| H A D | BulgarianAnalyzer.java | 49 * File containing default Bulgarian stopwords. 55 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 58 * The comment character in the stopwords file. All lines prefixed with this 106 public BulgarianAnalyzer(Version matchVersion, Set<?> stopwords) { argument 107 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 115 public BulgarianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 116 super(matchVersion, stopwords); 137 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ca/ |
| H A D | CatalanAnalyzer.java | 54 /** File containing default Catalan stopwords. */ 55 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 101 * @param stopwords a stopword set 103 public CatalanAnalyzer(Version matchVersion, Set<?> stopwords) { argument 104 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 113 * @param stopwords a stopword set 116 public CatalanAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 117 super(matchVersion, stopwords); 143 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/da/ |
| H A D | DanishAnalyzer.java | 46 /** File containing default Danish stopwords. */ 87 * @param stopwords a stopword set 89 public DanishAnalyzer(Version matchVersion, Set<?> stopwords) { argument 90 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 99 * @param stopwords a stopword set 102 public DanishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 103 super(matchVersion, stopwords); 126 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/en/ |
| H A D | EnglishAnalyzer.java | 70 * @param stopwords a stopword set 72 public EnglishAnalyzer(Version matchVersion, Set<?> stopwords) { argument 73 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 82 * @param stopwords a stopword set 85 public EnglishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 86 super(matchVersion, stopwords); 112 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/es/ |
| H A D | SpanishAnalyzer.java | 53 /** File containing default Spanish stopwords. */ 94 * @param stopwords a stopword set 96 public SpanishAnalyzer(Version matchVersion, Set<?> stopwords) { argument 97 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 106 * @param stopwords a stopword set 109 public SpanishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 110 super(matchVersion, stopwords); 133 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/eu/ |
| H A D | BasqueAnalyzer.java | 44 /** File containing default Basque stopwords. */ 45 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 85 * @param stopwords a stopword set 87 public BasqueAnalyzer(Version matchVersion, Set<?> stopwords) { argument 88 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 97 * @param stopwords a stopword set 100 public BasqueAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 101 super(matchVersion, stopwords); 124 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/fi/ |
| H A D | FinnishAnalyzer.java | 46 /** File containing default Italian stopwords. */ 87 * @param stopwords a stopword set 89 public FinnishAnalyzer(Version matchVersion, Set<?> stopwords) { argument 90 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 99 * @param stopwords a stopword set 102 public FinnishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 103 super(matchVersion, stopwords); 126 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ga/ |
| H A D | IrishAnalyzer.java | 44 /** File containing default Irish stopwords. */ 45 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 102 * @param stopwords a stopword set 104 public IrishAnalyzer(Version matchVersion, CharArraySet stopwords) { argument 105 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 114 * @param stopwords a stopword set 117 public IrishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) { argument 118 super(matchVersion, stopwords); 145 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/gl/ |
| H A D | GalicianAnalyzer.java | 44 /** File containing default Galician stopwords. */ 45 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 85 * @param stopwords a stopword set 87 public GalicianAnalyzer(Version matchVersion, Set<?> stopwords) { argument 88 this(matchVersion, stopwords, CharArraySet.EMPTY_SET); 97 * @param stopwords a stopword set 100 public GalicianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { argument 101 super(matchVersion, stopwords); 124 result = new StopFilter(matchVersion, result, stopwords);
|
| /lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/hi/ |
| H A D | HindiAnalyzer.java | 50 * File containing default Hindi stopwords. 55 public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; 88 * @param stopwords a stopword set 91 public HindiAnalyzer(Version version, Set<?> stopwords, Set<?> stemExclusionSet) { argument 92 super(version, stopwords); 101 * @param stopwords a stopword set 103 public HindiAnalyzer(Version version, Set<?> stopwords) { argument 104 this(version, stopwords, CharArraySet.EMPTY_SET); 141 result = new StopFilter(matchVersion, result, stopwords);
|