Java CharArraySet类代码示例

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public PatternAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    final CharArraySet defaultStopwords = CharArraySet.EMPTY_SET;
    boolean lowercase =
        settings.getAsBooleanLenientForPreEs6Indices(indexSettings.getIndexVersionCreated(), "lowercase", true, deprecationLogger);
    CharArraySet stopWords = Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, defaultStopwords);

    String sPattern = settings.get("pattern", "\\W+" /*PatternAnalyzer.NON_WORD_PATTERN*/);
    if (sPattern == null) {
        throw new IllegalArgumentException("Analyzer [" + name + "] of type pattern must have a `pattern` set");
    }
    Pattern pattern = Regex.compile(sPattern, settings.get("flags"));

    analyzer = new PatternAnalyzer(pattern, lowercase, stopWords);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public static CharArraySet parseStemExclusion(Settings settings, CharArraySet defaultStemExclusion) {
    String value = settings.get("stem_exclusion");
    if (value != null) {
        if ("_none_".equals(value)) {
            return CharArraySet.EMPTY_SET;
        } else {
            // LUCENE 4 UPGRADE: Should be settings.getAsBoolean("stem_exclusion_case", false)?
            return new CharArraySet(Strings.commaDelimitedListToSet(value), false);
        }
    }
    String[] stemExclusion = settings.getAsArray("stem_exclusion", null);
    if (stemExclusion != null) {
        // LUCENE 4 UPGRADE: Should be settings.getAsBoolean("stem_exclusion_case", false)?
        return new CharArraySet(Arrays.asList(stemExclusion), false);
    } else {
        return defaultStemExclusion;
    }
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public static CharArraySet parseWords(Environment env, Settings settings, String name, CharArraySet defaultWords,
                                      Map<String, Set<?>> namedWords, boolean ignoreCase) {
    String value = settings.get(name);
    if (value != null) {
        if ("_none_".equals(value)) {
            return CharArraySet.EMPTY_SET;
        } else {
            return resolveNamedWords(Strings.commaDelimitedListToSet(value), namedWords, ignoreCase);
        }
    }
    List<String> pathLoadedWords = getWordList(env, settings, name);
    if (pathLoadedWords != null) {
        return resolveNamedWords(pathLoadedWords, namedWords, ignoreCase);
    }
    return defaultWords;
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
@Test
public void testOverlappingAtBeginning() throws Exception {
    final CharArraySet phraseSets = new CharArraySet(Arrays.asList(
            "new york", "new york city", "city of new york"), false);

    final String input = "new york city is great";

    StringReader reader = new StringReader(input);
    final WhitespaceTokenizer in = new WhitespaceTokenizer();
    in.setReader(reader);

    AutoPhrasingTokenFilter aptf = new AutoPhrasingTokenFilter(in, phraseSets, false);
    aptf.setReplaceWhitespaceWith('_');
    CharTermAttribute term = aptf.addAttribute(CharTermAttribute.class);
    aptf.reset();

    assertTrue(aptf.incrementToken());
    assertEquals("new_york_city", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("is", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("great", term.toString());
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
@Test
public void testOverlappingAtEnd() throws Exception {
    final CharArraySet phraseSets = new CharArraySet(Arrays.asList(
            "new york", "new york city", "city of new york"), false);

    final String input = "the great city of new york";

    StringReader reader = new StringReader(input);
    final WhitespaceTokenizer in = new WhitespaceTokenizer();
    in.setReader(reader);

    AutoPhrasingTokenFilter aptf = new AutoPhrasingTokenFilter(in, phraseSets, false);
    aptf.setReplaceWhitespaceWith('_');
    CharTermAttribute term = aptf.addAttribute(CharTermAttribute.class);
    aptf.reset();

    assertTrue(aptf.incrementToken());
    assertEquals("the", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("great", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("city_of_new_york", term.toString());
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
@Test
public void testIncompletePhrase() throws Exception {
    final CharArraySet phraseSets = new CharArraySet(Arrays.asList(
            "big apple", "new york city", "property tax", "three word phrase"), false);

    final String input = "some new york";

    StringReader reader = new StringReader(input);
    final WhitespaceTokenizer in = new WhitespaceTokenizer();
    in.setReader(reader);

    AutoPhrasingTokenFilter aptf = new AutoPhrasingTokenFilter(in, phraseSets, false);
    aptf.setReplaceWhitespaceWith('_');
    CharTermAttribute term = aptf.addAttribute(CharTermAttribute.class);
    aptf.reset();

    assertTrue(aptf.incrementToken());
    assertEquals("some", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("new", term.toString());
    assertTrue(aptf.incrementToken());
    assertEquals("york", term.toString());
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public RomanianAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new RomanianAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, RomanianAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public BasqueAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new BasqueAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, BasqueAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public StandardHtmlStripAnalyzerProvider(IndexSettings indexSettings, Environment env,  String name, Settings settings) {
    super(indexSettings, name, settings);
    final CharArraySet defaultStopwords = CharArraySet.EMPTY_SET;
    CharArraySet stopWords = Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, defaultStopwords);
    analyzer = new StandardHtmlStripAnalyzer(stopWords);
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public IndonesianAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new IndonesianAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, IndonesianAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public ArabicAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    arabicAnalyzer = new ArabicAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, ArabicAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    arabicAnalyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public SnowballAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    String language = settings.get("language", settings.get("name", "English"));
    CharArraySet defaultStopwords = DEFAULT_LANGUAGE_STOPWORDS.getOrDefault(language, CharArraySet.EMPTY_SET);
    CharArraySet stopWords = Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, defaultStopwords);

    analyzer = new SnowballAnalyzer(language, stopWords);
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public StopAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    CharArraySet stopWords = Analysis.parseStopWords(
        env, indexSettings.getIndexVersionCreated(), settings, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
    this.stopAnalyzer = new StopAnalyzer(stopWords);
    this.stopAnalyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public SwedishAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new SwedishAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, SwedishAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    analyzer.setVersion(version);
}
 

import org.apache.lucene.analysis.CharArraySet; //导入依赖的package包/类
public StandardAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    final CharArraySet defaultStopwords = CharArraySet.EMPTY_SET;
    CharArraySet stopWords = Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, defaultStopwords);
    int maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
    standardAnalyzer = new StandardAnalyzer(stopWords);
    standardAnalyzer.setVersion(version);
    standardAnalyzer.setMaxTokenLength(maxTokenLength);
}