Package org.apache.lucene.analysis.hebrew

Examples of org.apache.lucene.analysis.hebrew.StreamLemmasFilter

18
19
20
21
22
23
24
25
26
27
28
29
30
31
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on query - if marked as keyword don't keep origin, else only lemmatized (don't suffix)
        // if word termintates with $ will output word$, else will output all lemmas or word$ if OOV
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setCustomWords(customWords);
        src.setSuffixForExactMatch(originalTermSuffix);
        src.setKeepOriginalWord(true);

        TokenStream tok = new ASCIIFoldingFilter(src);
        tok = new AddSuffixFilter(tok, '$') {
            @Override
            protected void handleCurrentToken() {
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
30
31
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on indexing we should always keep both the stem and marked original word
        // will ignore $ && will always output all lemmas + origin word$
        // basically, if analyzerType == AnalyzerType.INDEXING)
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setCustomWords(customWords);
        src.setKeepOriginalWord(true);

        TokenStream tok = new ASCIIFoldingFilter(src);
        tok = new AddSuffixFilter(tok, '$') {
            @Override
            protected void handleCurrentToken() {
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
30
31
32
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on query - if marked as keyword don't keep origin, else only lemmatized (don't suffix)
        // if word termintates with $ will output word$, else will output all lemmas or word$ if OOV
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setCustomWords(customWords);
        src.setKeepOriginalWord(false);
        src.setSuffixForExactMatch(originalTermSuffix);

        TokenStream tok = new ASCIIFoldingFilter(src);
        //tok = new SuffixKeywordFilter(tok, '$');
        tok = new AddSuffixFilter(tok, '$') {
            @Override
View Full Code Here
18
19
20
21
22
23
24
25
26
27
28
29
30
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on query - if marked as keyword don't keep origin, else only lemmatized (don't suffix)
        // if word termintates with $ will output word$, else will output all lemmas or word$ if OOV
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setSuffixForExactMatch(originalTermSuffix);
        src.setKeepOriginalWord(true);

        TokenStream tok = new ASCIIFoldingFilter(src);
        tok = new AlwaysAddSuffixFilter(tok, '$', true) {
            @Override
            protected boolean possiblySkipFilter() {
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
30
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on indexing we should always keep both the stem and marked original word
        // will ignore $ && will always output all lemmas + origin word$
        // basically, if analyzerType == AnalyzerType.INDEXING)
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setKeepOriginalWord(true);

        TokenStream tok = new ASCIIFoldingFilter(src);
        tok = new AlwaysAddSuffixFilter(tok, '$', true) {
            @Override
            protected boolean possiblySkipFilter() {
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
30
31
    @Override
    protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
        // on query - if marked as keyword don't keep origin, else only lemmatized (don't suffix)
        // if word termintates with $ will output word$, else will output all lemmas or word$ if OOV
        final StreamLemmasFilter src = new StreamLemmasFilter(reader, dictRadix, prefixesTree, SPECIAL_TOKENIZATION_CASES, commonWords, lemmaFilter);
        src.setKeepOriginalWord(false);
        src.setSuffixForExactMatch(originalTermSuffix);

        TokenStream tok = new ASCIIFoldingFilter(src);
        //tok = new SuffixKeywordFilter(tok, '$');
        tok = new AlwaysAddSuffixFilter(tok, '$', true) {
            @Override
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.hebrew.StreamLemmasFilter

  • com.code972.elasticsearch.analysis.HebrewIndexingAnalyzer
  • com.code972.elasticsearch.analysis.HebrewQueryAnalyzer
  • com.code972.elasticsearch.analysis.HebrewQueryLightAnalyzer
  • com.code972.hebmorph.datastructures.DictHebMorph
    • 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.