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

Example 41 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class SolrPluginUtilsTest method testDisjunctionMaxQueryParser.

@Test
public void testDisjunctionMaxQueryParser() throws Exception {
    Query out;
    String t;
    SolrQueryRequest req = req("df", "text");
    QParser qparser = QParser.getParser("hi", "dismax", req);
    DisjunctionMaxQueryParser qp = new SolrPluginUtils.DisjunctionMaxQueryParser(qparser, req.getParams().get("df"));
    qp.addAlias("hoss", 0.01f, SolrPluginUtils.parseFieldBoosts("title^2.0 title_stemmed name^1.2 subject^0.5"));
    qp.addAlias("test", 0.01f, SolrPluginUtils.parseFieldBoosts("text^2.0"));
    qp.addAlias("unused", 1.0f, SolrPluginUtils.parseFieldBoosts("subject^0.5 sind^1.5"));
    /* first some sanity tests that don't use aliasing at all */
    t = "XXXXXXXX";
    out = qp.parse(t);
    assertNotNull(t + " sanity test gave back null", out);
    assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
    assertEquals(t + " sanity test is wrong field", qp.getDefaultField(), ((TermQuery) out).getTerm().field());
    t = "subject:XXXXXXXX";
    out = qp.parse(t);
    assertNotNull(t + " sanity test gave back null", out);
    assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
    assertEquals(t + " sanity test is wrong field", "subject", ((TermQuery) out).getTerm().field());
    /* field has untokenzied type, so this should be a term anyway */
    t = "sind:\"simple phrase\"";
    out = qp.parse(t);
    assertNotNull(t + " sanity test gave back null", out);
    assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
    assertEquals(t + " sanity test is wrong field", "sind", ((TermQuery) out).getTerm().field());
    t = "subject:\"simple phrase\"";
    out = qp.parse(t);
    assertNotNull(t + " sanity test gave back null", out);
    assertTrue(t + " sanity test isn't PhraseQuery: " + out.getClass(), out instanceof PhraseQuery);
    assertEquals(t + " sanity test is wrong field", "subject", ((PhraseQuery) out).getTerms()[0].field());
    /* now some tests that use aliasing */
    /* basic usage of single "term" */
    t = "hoss:XXXXXXXX";
    out = qp.parse(t);
    assertNotNull(t + " was null", out);
    assertTrue(t + " wasn't a DMQ:" + out.getClass(), out instanceof DisjunctionMaxQuery);
    assertEquals(t + " wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) out).iterator()));
    /* odd case, but should still work, DMQ of one clause */
    t = "test:YYYYY";
    out = qp.parse(t);
    assertNotNull(t + " was null", out);
    assertTrue(t + " wasn't a DMQ:" + out.getClass(), out instanceof DisjunctionMaxQuery);
    assertEquals(t + " wrong number of clauses", 1, countItems(((DisjunctionMaxQuery) out).iterator()));
    /* basic usage of multiple "terms" */
    t = "hoss:XXXXXXXX test:YYYYY";
    out = qp.parse(t);
    assertNotNull(t + " was null", out);
    assertTrue(t + " wasn't a boolean:" + out.getClass(), out instanceof BooleanQuery);
    {
        BooleanQuery bq = (BooleanQuery) out;
        List<BooleanClause> clauses = new ArrayList<>(bq.clauses());
        assertEquals(t + " wrong number of clauses", 2, clauses.size());
        Query sub = clauses.get(0).getQuery();
        assertTrue(t + " first wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
        assertEquals(t + " first had wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) sub).iterator()));
        sub = clauses.get(1).getQuery();
        assertTrue(t + " second wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
        assertEquals(t + " second had wrong number of clauses", 1, countItems(((DisjunctionMaxQuery) sub).iterator()));
    }
    /* a phrase, and a term that is a stop word for some fields */
    t = "hoss:\"XXXXXX YYYYY\" hoss:the";
    out = qp.parse(t);
    assertNotNull(t + " was null", out);
    assertTrue(t + " wasn't a boolean:" + out.getClass(), out instanceof BooleanQuery);
    {
        BooleanQuery bq = (BooleanQuery) out;
        List<BooleanClause> clauses = new ArrayList<>(bq.clauses());
        assertEquals(t + " wrong number of clauses", 2, clauses.size());
        Query sub = clauses.get(0).getQuery();
        assertTrue(t + " first wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
        assertEquals(t + " first had wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) sub).iterator()));
        sub = clauses.get(1).getQuery();
        assertTrue(t + " second wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
        assertEquals(t + " second had wrong number of clauses (stop words)", 2, countItems(((DisjunctionMaxQuery) sub).iterator()));
    }
}

Example 42 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project jackrabbit by apache.

the class AbstractExcerpt method getQueryTerms.

private static void getQueryTerms(Query q, Set<Term[]> relevantTerms) {
    if (q instanceof BooleanQuery) {
        final BooleanQuery bq = (BooleanQuery) q;
        for (BooleanClause clause : bq.getClauses()) {
            getQueryTerms(clause.getQuery(), relevantTerms);
        }
        return;
    }
    //need to preserve insertion order
    Set<Term> extractedTerms = new LinkedHashSet<Term>();
    q.extractTerms(extractedTerms);
    Set<Term> filteredTerms = filterRelevantTerms(extractedTerms);
    if (!filteredTerms.isEmpty()) {
        if (q instanceof PhraseQuery) {
            // inline the terms, basically a 'must all' condition
            relevantTerms.add(filteredTerms.toArray(new Term[] {}));
        } else {
            // each possible term gets a new slot
            for (Term t : filteredTerms) {
                relevantTerms.add(new Term[] { t });
            }
        }
    }
}

Example 43 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestAddIndexes method testWithPendingDeletes2.

public void testWithPendingDeletes2() throws IOException {
    // main directory
    Directory dir = newDirectory();
    // auxiliary directory
    Directory aux = newDirectory();
    setUpDirs(dir, aux);
    IndexWriter writer = newWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())).setOpenMode(OpenMode.APPEND));
    // docs, so 10 pending deletes:
    for (int i = 0; i < 20; i++) {
        Document doc = new Document();
        doc.add(newStringField("id", "" + (i % 10), Field.Store.NO));
        doc.add(newTextField("content", "bbb " + i, Field.Store.NO));
        doc.add(new IntPoint("doc", i));
        doc.add(new IntPoint("doc2d", i, i));
        doc.add(new NumericDocValuesField("dv", i));
        writer.updateDocument(new Term("id", "" + (i % 10)), doc);
    }
    writer.addIndexes(aux);
    // Deletes one of the 10 added docs, leaving 9:
    PhraseQuery q = new PhraseQuery("content", "bbb", "14");
    writer.deleteDocuments(q);
    writer.forceMerge(1);
    writer.commit();
    verifyNumDocs(dir, 1039);
    verifyTermDocs(dir, new Term("content", "aaa"), 1030);
    verifyTermDocs(dir, new Term("content", "bbb"), 9);
    writer.close();
    dir.close();
    aux.close();
}

Example 44 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestAddIndexes method testWithPendingDeletes.

public void testWithPendingDeletes() throws IOException {
    // main directory
    Directory dir = newDirectory();
    // auxiliary directory
    Directory aux = newDirectory();
    setUpDirs(dir, aux);
    IndexWriter writer = newWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())).setOpenMode(OpenMode.APPEND));
    writer.addIndexes(aux);
    // docs, so 10 pending deletes:
    for (int i = 0; i < 20; i++) {
        Document doc = new Document();
        doc.add(newStringField("id", "" + (i % 10), Field.Store.NO));
        doc.add(newTextField("content", "bbb " + i, Field.Store.NO));
        doc.add(new IntPoint("doc", i));
        doc.add(new IntPoint("doc2d", i, i));
        doc.add(new NumericDocValuesField("dv", i));
        writer.updateDocument(new Term("id", "" + (i % 10)), doc);
    }
    // Deletes one of the 10 added docs, leaving 9:
    PhraseQuery q = new PhraseQuery("content", "bbb", "14");
    writer.deleteDocuments(q);
    writer.forceMerge(1);
    writer.commit();
    verifyNumDocs(dir, 1039);
    verifyTermDocs(dir, new Term("content", "aaa"), 1030);
    verifyTermDocs(dir, new Term("content", "bbb"), 9);
    writer.close();
    dir.close();
    aux.close();
}

Example 45 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestIndexWriterExceptions method testAddDocsNonAbortingException.

public void testAddDocsNonAbortingException() throws Exception {
    final Directory dir = newDirectory();
    final RandomIndexWriter w = new RandomIndexWriter(random(), dir);
    final int numDocs1 = random().nextInt(25);
    for (int docCount = 0; docCount < numDocs1; docCount++) {
        Document doc = new Document();
        doc.add(newTextField("content", "good content", Field.Store.NO));
        w.addDocument(doc);
    }
    final List<Document> docs = new ArrayList<>();
    for (int docCount = 0; docCount < 7; docCount++) {
        Document doc = new Document();
        docs.add(doc);
        doc.add(newStringField("id", docCount + "", Field.Store.NO));
        doc.add(newTextField("content", "silly content " + docCount, Field.Store.NO));
        if (docCount == 4) {
            Field f = newTextField("crash", "", Field.Store.NO);
            doc.add(f);
            MockTokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
            tokenizer.setReader(new StringReader("crash me on the 4th token"));
            // disable workflow checking as we forcefully close() in exceptional cases.
            tokenizer.setEnableChecks(false);
            f.setTokenStream(new CrashingFilter("crash", tokenizer));
        }
    }
    IOException expected = expectThrows(IOException.class, () -> {
        w.addDocuments(docs);
    });
    assertEquals(CRASH_FAIL_MESSAGE, expected.getMessage());
    final int numDocs2 = random().nextInt(25);
    for (int docCount = 0; docCount < numDocs2; docCount++) {
        Document doc = new Document();
        doc.add(newTextField("content", "good content", Field.Store.NO));
        w.addDocument(doc);
    }
    final IndexReader r = w.getReader();
    w.close();
    final IndexSearcher s = newSearcher(r);
    PhraseQuery pq = new PhraseQuery("content", "silly", "good");
    assertEquals(0, s.search(pq, 1).totalHits);
    pq = new PhraseQuery("content", "good", "content");
    assertEquals(numDocs1 + numDocs2, s.search(pq, 1).totalHits);
    r.close();
    dir.close();
}