Examples with TermsEnum org.apache.lucene.index.TermsEnum used on opensource projects

Example 1 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project elasticsearch by elastic.

the class SimpleLuceneTests method testNRTSearchOnClosedWriter.

public void testNRTSearchOnClosedWriter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    DirectoryReader reader = DirectoryReader.open(indexWriter);
    for (int i = 0; i < 100; i++) {
        Document document = new Document();
        TextField field = new TextField("_id", Integer.toString(i), Field.Store.YES);
        field.setBoost(i);
        document.add(field);
        indexWriter.addDocument(document);
    }
    reader = refreshReader(reader);
    indexWriter.close();
    TermsEnum termDocs = SlowCompositeReaderWrapper.wrap(reader).terms("_id").iterator();
    termDocs.next();
}

Example 2 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project elasticsearch by elastic.

the class TextFieldMapperTests method testDefaultPositionIncrementGap.

public void testDefaultPositionIncrementGap() throws IOException {
    String mapping = XContentFactory.jsonBuilder().startObject().startObject("type").startObject("properties").startObject("field").field("type", "text").endObject().endObject().endObject().endObject().string();
    DocumentMapper mapper = indexService.mapperService().merge("type", new CompressedXContent(mapping), MergeReason.MAPPING_UPDATE, false);
    assertEquals(mapping, mapper.mappingSource().toString());
    ParsedDocument doc = mapper.parse("test", "type", "1", XContentFactory.jsonBuilder().startObject().array("field", new String[] { "a", "b" }).endObject().bytes());
    IndexableField[] fields = doc.rootDoc().getFields("field");
    assertEquals(2, fields.length);
    assertEquals("a", fields[0].stringValue());
    assertEquals("b", fields[1].stringValue());
    IndexShard shard = indexService.getShard(0);
    shard.index(new Engine.Index(new Term("_uid", doc.uid()), doc));
    shard.refresh("test");
    try (Engine.Searcher searcher = shard.acquireSearcher("test")) {
        LeafReader leaf = searcher.getDirectoryReader().leaves().get(0).reader();
        TermsEnum terms = leaf.terms("field").iterator();
        assertTrue(terms.seekExact(new BytesRef("b")));
        PostingsEnum postings = terms.postings(null, PostingsEnum.POSITIONS);
        assertEquals(0, postings.nextDoc());
        assertEquals(TextFieldMapper.Defaults.POSITION_INCREMENT_GAP + 1, postings.nextPosition());
    }
}

Example 3 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project elasticsearch by elastic.

the class TermVectorsResponse method buildField.

private void buildField(XContentBuilder builder, final CharsRefBuilder spare, Fields theFields, Iterator<String> fieldIter) throws IOException {
    String fieldName = fieldIter.next();
    builder.startObject(fieldName);
    Terms curTerms = theFields.terms(fieldName);
    // write field statistics
    buildFieldStatistics(builder, curTerms);
    builder.startObject(FieldStrings.TERMS);
    TermsEnum termIter = curTerms.iterator();
    BoostAttribute boostAtt = termIter.attributes().addAttribute(BoostAttribute.class);
    for (int i = 0; i < curTerms.size(); i++) {
        buildTerm(builder, spare, curTerms, termIter, boostAtt);
    }
    builder.endObject();
    builder.endObject();
}

Example 4 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project elasticsearch by elastic.

the class MoreLikeThisQuery method handleUnlike.

private void handleUnlike(XMoreLikeThis mlt, String[] unlikeText, Fields[] unlikeFields) throws IOException {
    Set<Term> skipTerms = new HashSet<>();
    // handle like text
    if (unlikeText != null) {
        for (String text : unlikeText) {
            // only use the first field to be consistent
            String fieldName = moreLikeFields[0];
            try (TokenStream ts = analyzer.tokenStream(fieldName, text)) {
                CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
                ts.reset();
                while (ts.incrementToken()) {
                    skipTerms.add(new Term(fieldName, termAtt.toString()));
                }
                ts.end();
            }
        }
    }
    // handle like fields
    if (unlikeFields != null) {
        for (Fields fields : unlikeFields) {
            for (String fieldName : fields) {
                Terms terms = fields.terms(fieldName);
                final TermsEnum termsEnum = terms.iterator();
                BytesRef text;
                while ((text = termsEnum.next()) != null) {
                    skipTerms.add(new Term(fieldName, text.utf8ToString()));
                }
            }
        }
    }
    if (!skipTerms.isEmpty()) {
        mlt.setSkipTerms(skipTerms);
    }
}

Example 5 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project elasticsearch by elastic.

the class MultiPhrasePrefixQuery method getPrefixTerms.

private void getPrefixTerms(ObjectHashSet<Term> terms, final Term prefix, final IndexReader reader) throws IOException {
    // SlowCompositeReaderWrapper could be used... but this would merge all terms from each segment into one terms
    // instance, which is very expensive. Therefore I think it is better to iterate over each leaf individually.
    List<LeafReaderContext> leaves = reader.leaves();
    for (LeafReaderContext leaf : leaves) {
        Terms _terms = leaf.reader().terms(field);
        if (_terms == null) {
            continue;
        }
        TermsEnum termsEnum = _terms.iterator();
        TermsEnum.SeekStatus seekStatus = termsEnum.seekCeil(prefix.bytes());
        if (TermsEnum.SeekStatus.END == seekStatus) {
            continue;
        }
        for (BytesRef term = termsEnum.term(); term != null; term = termsEnum.next()) {
            if (!StringHelper.startsWith(term, prefix.bytes())) {
                break;
            }
            terms.add(new Term(field, BytesRef.deepCopyOf(term)));
            if (terms.size() >= maxExpansions) {
                return;
            }
        }
    }
}