Examples with BytesRef org.apache.lucene.util.BytesRef used on opensource projects

Example 91 with BytesRef

use of org.apache.lucene.util.BytesRef in project elasticsearch by elastic.

the class XMoreLikeThis method addTermFrequencies.

/**
     * Adds terms and frequencies found in vector into the Map termFreqMap
     *
     * @param termFreqMap a Map of terms and their frequencies
     * @param vector List of terms and their frequencies for a doc/field
     * @param fieldName Optional field name of the terms for skip terms
     */
private void addTermFrequencies(Map<String, Int> termFreqMap, Terms vector, @Nullable String fieldName) throws IOException {
    final TermsEnum termsEnum = vector.iterator();
    final CharsRefBuilder spare = new CharsRefBuilder();
    BytesRef text;
    while ((text = termsEnum.next()) != null) {
        spare.copyUTF8Bytes(text);
        final String term = spare.toString();
        if (isNoiseWord(term)) {
            continue;
        }
        if (isSkipTerm(fieldName, term)) {
            continue;
        }
        final PostingsEnum docs = termsEnum.postings(null);
        int freq = 0;
        while (docs != null && docs.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
            freq += docs.freq();
        }
        // increment frequency
        Int cnt = termFreqMap.get(term);
        if (cnt == null) {
            cnt = new Int();
            termFreqMap.put(term, cnt);
            cnt.x = freq;
        } else {
            cnt.x += freq;
        }
    }
}

Example 92 with BytesRef

use of org.apache.lucene.util.BytesRef in project elasticsearch by elastic.

the class Versions method loadPrimaryTerm.

/**
     * Returns the primary term for the given uid term, returning {@code 0} if none is found.
     */
public static long loadPrimaryTerm(IndexReader reader, Term term) throws IOException {
    assert term.field().equals(UidFieldMapper.NAME) : "can only load _primary_term by uid";
    List<LeafReaderContext> leaves = reader.leaves();
    if (leaves.isEmpty()) {
        return 0;
    }
    // which are likely to be in the last segments
    for (int i = leaves.size() - 1; i >= 0; i--) {
        LeafReader leaf = leaves.get(i).reader();
        Bits liveDocs = leaf.getLiveDocs();
        TermsEnum termsEnum = null;
        NumericDocValues dvField = null;
        PostingsEnum docsEnum = null;
        final Fields fields = leaf.fields();
        if (fields != null) {
            Terms terms = fields.terms(UidFieldMapper.NAME);
            if (terms != null) {
                termsEnum = terms.iterator();
                assert termsEnum != null;
                dvField = leaf.getNumericDocValues(SeqNoFieldMapper.PRIMARY_TERM_NAME);
                assert dvField != null;
                final BytesRef id = term.bytes();
                if (termsEnum.seekExact(id)) {
                    // there may be more than one matching docID, in the
                    // case of nested docs, so we want the last one:
                    docsEnum = termsEnum.postings(docsEnum, 0);
                    int docID = DocIdSetIterator.NO_MORE_DOCS;
                    for (int d = docsEnum.nextDoc(); d != DocIdSetIterator.NO_MORE_DOCS; d = docsEnum.nextDoc()) {
                        if (liveDocs != null && liveDocs.get(d) == false) {
                            continue;
                        }
                        docID = d;
                    }
                    if (docID != DocIdSetIterator.NO_MORE_DOCS) {
                        return dvField.get(docID);
                    }
                }
            }
        }
    }
    return 0;
}

Example 93 with BytesRef

use of org.apache.lucene.util.BytesRef in project crate by crate.

the class MatchQueryBuilderTest method testSimpleSingleMatchTwoTerms.

@Test
public void testSimpleSingleMatchTwoTerms() throws Exception {
    Map<String, Object> fields = MapBuilder.<String, Object>newMapBuilder().put("col1", null).map();
    MatchQueryBuilder builder = new MatchQueryBuilder(mockMapperService(), null, Collections.emptyMap());
    Query query = builder.query(fields, new BytesRef("foo bar"));
    assertThat(query, instanceOf(BooleanQuery.class));
}

Example 94 with BytesRef

use of org.apache.lucene.util.BytesRef in project crate by crate.

the class MatchQueryBuilderTest method testTwoFieldsSingleTerm.

@Test
public void testTwoFieldsSingleTerm() throws Exception {
    MatchQueryBuilder builder = new io.crate.lucene.match.MultiMatchQueryBuilder(mockMapperService(), null, Collections.emptyMap());
    Map<String, Object> fields = MapBuilder.<String, Object>newMapBuilder().put("col1", null).put("col2", null).map();
    Query query = builder.query(fields, new BytesRef("foo"));
    assertThat(query, instanceOf(DisjunctionMaxQuery.class));
}

Example 95 with BytesRef

use of org.apache.lucene.util.BytesRef in project crate by crate.

the class MatchQueryBuilderTest method testPhrasePrefix.

@Test
public void testPhrasePrefix() throws Exception {
    MatchQueryBuilder builder = new MatchQueryBuilder(mockMapperService(), new BytesRef("phrase_prefix"), Collections.emptyMap());
    Map<String, Object> fields = MapBuilder.<String, Object>newMapBuilder().put("col1", null).map();
    Query query = builder.query(fields, new BytesRef("foo"));
    assertThat(query, instanceOf(MultiPhrasePrefixQuery.class));
}