org.apache.lucene.analysis.pattern.PatternTokenizer Java Examples

The following examples show how to use org.apache.lucene.analysis.pattern.PatternTokenizer. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example #1

Source File: CommonAnalysisPlugin.java From crate with Apache License 2.0

6 votes

@Override
public List<PreConfiguredTokenizer> getPreConfiguredTokenizers() {
    List<PreConfiguredTokenizer> tokenizers = new ArrayList<>();
    tokenizers.add(PreConfiguredTokenizer.singleton("keyword", KeywordTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("classic", ClassicTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("uax_url_email", UAX29URLEmailTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("path_hierarchy", PathHierarchyTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("letter", LetterTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("whitespace", WhitespaceTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("ngram", NGramTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("edge_ngram",
        () -> new EdgeNGramTokenizer(EdgeNGramTokenizer.DEFAULT_MIN_GRAM_SIZE, EdgeNGramTokenizer.DEFAULT_MAX_GRAM_SIZE), null));
    tokenizers.add(PreConfiguredTokenizer.singleton("pattern", () -> new PatternTokenizer(Regex.compile("\\W+", null), -1), null));
    tokenizers.add(PreConfiguredTokenizer.singleton("thai", ThaiTokenizer::new, null));
    tokenizers.add(PreConfiguredTokenizer.singleton("lowercase", XLowerCaseTokenizer::new, () -> new TokenFilterFactory() {
        @Override
        public String name() {
            return "lowercase";
        }

        @Override
        public TokenStream create(TokenStream tokenStream) {
            return new LowerCaseFilter(tokenStream);
        }
    }));

    // Temporary shim for aliases. TODO deprecate after they are moved
    tokenizers.add(PreConfiguredTokenizer.singleton("PathHierarchy", PathHierarchyTokenizer::new, null));

    return tokenizers;
}

Example #2

Source File: URLTokenizer.java From elasticsearch-analysis-url with Apache License 2.0

5 votes

private List<Token> getQueryTokens(String url, String partStringRaw, String partString) throws IOException {
    int start = getStartIndex(url, partStringRaw);
    if (!tokenizeQuery) {
        int end = getEndIndex(start, partStringRaw);
        return Collections.singletonList(new Token(partString, URLPart.QUERY, start, end));
    }
    return tokenize(URLPart.QUERY, addReader(new PatternTokenizer(QUERY_SEPARATOR, -1), new StringReader(partString)), start);
}

Example #3

Source File: NeedsConfiguringAnalyzerFactory.java From database with GNU General Public License v2.0

5 votes

/**
 * The second phase of the life-cycle, used for sanity checking.
 */
public void validate() {
	if (pattern != null ) {
		if ( className != null && className != PatternTokenizer.class.getName()) {
			throw new RuntimeException("Bad Option: Language range "+languageRange + " with pattern propety for class "+ className);
		}
		className = PatternTokenizer.class.getName();
	}
	if (this.wordBoundary != null  ) {
		if ( className != null && className != TermCompletionAnalyzer.class.getName()) {
			throw new RuntimeException("Bad Option: Language range "+languageRange + " with pattern propety for class "+ className);
		}
		className = TermCompletionAnalyzer.class.getName();
		
		if ( subWordBoundary == null ) {
			subWordBoundary = AnalyzerOptions.DEFAULT_SUB_WORD_BOUNDARY;
		}
		if ( alwaysRemoveSoftHyphens != null && softHyphens == null ) {
			throw new RuntimeException("Bad option: Language range "+languageRange + ": must specify softHypens when setting alwaysRemoveSoftHyphens");		
		}
		if (softHyphens != null && alwaysRemoveSoftHyphens == null) {
			alwaysRemoveSoftHyphens = AnalyzerOptions.DEFAULT_ALWAYS_REMOVE_SOFT_HYPHENS;
		}
		
	} else if ( subWordBoundary != null || softHyphens != null || alwaysRemoveSoftHyphens != null ||
			TermCompletionAnalyzer.class.getName().equals(className) ) {
		throw new RuntimeException("Bad option: Language range "+languageRange + ": must specify wordBoundary for TermCompletionAnalyzer");
	}
	
	if (PatternTokenizer.class.getName().equals(className) && pattern == null ) {
		throw new RuntimeException("Bad Option: Language range "+languageRange + " must specify pattern for PatternTokenizer.");
	}
	if ( (like != null) == (className != null) ) {
		throw new RuntimeException("Bad Option: Language range "+languageRange + " must specify exactly one of implementation class or like.");
	}
	if (stopwords != null && like != null) {
		throw new RuntimeException("Bad Option: Language range "+languageRange + " must not specify stopwords with like.");
	}
	
}

Example #4

Source File: PatternAnalyzerImpl.java From database with GNU General Public License v2.0

5 votes

@Override
protected TokenStreamComponents createComponents(final String field) {
	//Use default grouping
	final Tokenizer tokenizer = new PatternTokenizer(pattern,-1);
	final TokenStream filter = new LowerCaseFilter(tokenizer);
	return new TokenStreamComponents(tokenizer, filter);
}

Example #5

Source File: PatternTokenizerFactory.java From Elasticsearch with Apache License 2.0

4 votes

@Override
public Tokenizer create() {
    return new PatternTokenizer(pattern, group);
}

Example #6

Source File: PatternTokenizerFactory.java From crate with Apache License 2.0

4 votes

@Override
public Tokenizer create() {
    return new PatternTokenizer(pattern, group);
}