Examples with TermQuery org.apache.lucene.search.TermQuery used on opensource projects

Example 66 with TermQuery

use of org.apache.lucene.search.TermQuery in project elasticsearch by elastic.

the class XMoreLikeThis method addToQuery.

/**
     * Add to an existing boolean query the More Like This query from this PriorityQueue
     */
private void addToQuery(PriorityQueue<ScoreTerm> q, BooleanQuery.Builder query) {
    ScoreTerm scoreTerm;
    float bestScore = -1;
    while ((scoreTerm = q.pop()) != null) {
        Query tq = new TermQuery(new Term(scoreTerm.topField, scoreTerm.word));
        if (boost) {
            if (bestScore == -1) {
                bestScore = (scoreTerm.score);
            }
            float myScore = (scoreTerm.score);
            tq = new BoostQuery(tq, boostFactor * myScore / bestScore);
        }
        try {
            query.add(tq, BooleanClause.Occur.SHOULD);
        } catch (BooleanQuery.TooManyClauses ignore) {
            break;
        }
    }
}

Example 67 with TermQuery

use of org.apache.lucene.search.TermQuery in project elasticsearch by elastic.

the class AllTermQuery method rewrite.

@Override
public Query rewrite(IndexReader reader) throws IOException {
    Query rewritten = super.rewrite(reader);
    if (rewritten != this) {
        return rewritten;
    }
    boolean hasPayloads = false;
    for (LeafReaderContext context : reader.leaves()) {
        final Terms terms = context.reader().terms(term.field());
        if (terms != null) {
            if (terms.hasPayloads()) {
                hasPayloads = true;
                break;
            }
        }
    }
    // which rewrites query with an empty reader.
    if (hasPayloads == false) {
        return new TermQuery(term);
    }
    return this;
}

Example 68 with TermQuery

use of org.apache.lucene.search.TermQuery in project elasticsearch by elastic.

the class XMoreLikeThisTests method testTopN.

public void testTopN() throws Exception {
    int numDocs = 100;
    int topN = 25;
    // add series of docs with terms of decreasing df
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    for (int i = 0; i < numDocs; i++) {
        addDoc(writer, generateStrSeq(0, i + 1));
    }
    IndexReader reader = writer.getReader();
    writer.close();
    // setup MLT query
    MoreLikeThis mlt = new MoreLikeThis(reader);
    mlt.setAnalyzer(new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false));
    mlt.setMaxQueryTerms(topN);
    mlt.setMinDocFreq(1);
    mlt.setMinTermFreq(1);
    mlt.setMinWordLen(1);
    mlt.setFieldNames(new String[] { "text" });
    // perform MLT query
    String likeText = "";
    for (String text : generateStrSeq(0, numDocs)) {
        likeText += text + " ";
    }
    BooleanQuery query = (BooleanQuery) mlt.like("text", new StringReader(likeText));
    // check best terms are topN of highest idf
    List<BooleanClause> clauses = query.clauses();
    assertEquals("Expected" + topN + "clauses only!", topN, clauses.size());
    Term[] expectedTerms = new Term[topN];
    int idx = 0;
    for (String text : generateStrSeq(numDocs - topN, topN)) {
        expectedTerms[idx++] = new Term("text", text);
    }
    for (BooleanClause clause : clauses) {
        Term term = ((TermQuery) clause.getQuery()).getTerm();
        assertTrue(Arrays.asList(expectedTerms).contains(term));
    }
    // clean up
    reader.close();
    dir.close();
}

Example 69 with TermQuery

use of org.apache.lucene.search.TermQuery in project OpenGrok by OpenGrok.

the class HistoryContextTest method testGetContext_3args.

@Test
public void testGetContext_3args() throws Exception {
    String path = "/mercurial/Makefile";
    String filename = repositories.getSourceRoot() + path;
    // Construct a query equivalent to hist:dummy
    TermQuery q1 = new TermQuery(new Term("hist", "dummy"));
    ArrayList<Hit> hits = new ArrayList<>();
    assertTrue(new HistoryContext(q1).getContext(filename, path, hits));
    assertEquals(1, hits.size());
    assertTrue(hits.get(0).getLine().contains("Created a small <b>dummy</b> program"));
    // Construct a query equivalent to hist:"dummy program"        
    PhraseQuery.Builder q2 = new PhraseQuery.Builder();
    q2.add(new Term("hist", "dummy"));
    q2.add(new Term("hist", "program"));
    hits.clear();
    assertTrue(new HistoryContext(q2.build()).getContext(filename, path, hits));
    assertEquals(1, hits.size());
    assertTrue(hits.get(0).getLine().contains("Created a small <b>dummy program</b>"));
    // Search for a term that doesn't exist
    TermQuery q3 = new TermQuery(new Term("hist", "term_does_not_exist"));
    hits.clear();
    assertFalse(new HistoryContext(q3).getContext(filename, path, hits));
    assertEquals(0, hits.size());
    // Search for term with multiple hits - hist:small OR hist:target
    BooleanQuery.Builder q4 = new BooleanQuery.Builder();
    q4.add(new TermQuery(new Term("hist", "small")), Occur.SHOULD);
    q4.add(new TermQuery(new Term("hist", "target")), Occur.SHOULD);
    hits.clear();
    assertTrue(new HistoryContext(q4.build()).getContext(filename, path, hits));
    assertEquals(2, hits.size());
    assertTrue(hits.get(0).getLine().contains("Add lint make <b>target</b> and fix lint warnings"));
    assertTrue(hits.get(1).getLine().contains("Created a <b>small</b> dummy program"));
}

Example 70 with TermQuery

use of org.apache.lucene.search.TermQuery in project ansj_seg by NLPchina.

the class PhraseTest method main.

public static void main(String[] args) throws IOException, ParseException {
    DicLibrary.insert(DicLibrary.DEFAULT, "上网人");
    DicLibrary.insert(DicLibrary.DEFAULT, "网人");
    AnsjAnalyzer ansjAnalyzer = new AnsjAnalyzer(AnsjAnalyzer.TYPE.index_ansj);
    TokenStream tokenStream = ansjAnalyzer.tokenStream("上网人员测试", "test");
    while (tokenStream.incrementToken()) {
        System.out.println(tokenStream.getAttribute(CharTermAttribute.class));
    }
    IndexWriterConfig config = new IndexWriterConfig(ansjAnalyzer);
    IndexWriter writer = new IndexWriter(new RAMDirectory(), config);
    Document doc = new Document();
    doc.add(new TextField("test", "上网人员测试", Field.Store.YES));
    writer.addDocument(doc);
    writer.commit();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(writer));
    System.out.println(searcher.count(new TermQuery(new Term("test", "网人"))));
    Query q = new QueryParser("test", new AnsjAnalyzer(AnsjAnalyzer.TYPE.index_ansj)).parse("\"上网人\"");
    System.out.println(q);
    System.out.println(searcher.count(q));
}