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

Example 66 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project lucene-solr by apache.

the class TestOrdsBlockTree method testThreeBlocks.

public void testThreeBlocks() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir);
    List<String> terms = new ArrayList<>();
    for (int i = 0; i < 36; i++) {
        Document doc = new Document();
        String term = "" + (char) (97 + i);
        terms.add(term);
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term);
        }
        doc.add(newTextField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    for (int i = 0; i < 36; i++) {
        Document doc = new Document();
        String term = "m" + (char) (97 + i);
        terms.add(term);
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term);
        }
        doc.add(newTextField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    for (int i = 0; i < 36; i++) {
        Document doc = new Document();
        String term = "mo" + (char) (97 + i);
        terms.add(term);
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term);
        }
        doc.add(newTextField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    w.forceMerge(1);
    IndexReader r = w.getReader();
    TermsEnum te = MultiFields.getTerms(r, "field").iterator();
    if (VERBOSE) {
        while (te.next() != null) {
            System.out.println("TERM: " + te.ord() + " " + te.term().utf8ToString());
        }
    }
    assertTrue(te.seekExact(new BytesRef("mo")));
    assertEquals(27, te.ord());
    te.seekExact(90);
    assertEquals(new BytesRef("s"), te.term());
    testEnum(te, terms);
    r.close();
    w.close();
    dir.close();
}

Example 67 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project lucene-solr by apache.

the class TestOrdsBlockTree method testFloorBlocks.

public void testFloorBlocks() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
    IndexWriter w = new IndexWriter(dir, iwc);
    for (int i = 0; i < 128; i++) {
        Document doc = new Document();
        String term = "" + (char) i;
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term + " bytes=" + new BytesRef(term));
        }
        doc.add(newStringField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    w.forceMerge(1);
    IndexReader r = DirectoryReader.open(w);
    TermsEnum te = MultiFields.getTerms(r, "field").iterator();
    if (VERBOSE) {
        BytesRef term;
        while ((term = te.next()) != null) {
            System.out.println("  " + te.ord() + ": " + term.utf8ToString());
        }
    }
    assertTrue(te.seekExact(new BytesRef("a")));
    assertEquals(97, te.ord());
    te.seekExact(98);
    assertEquals(new BytesRef("b"), te.term());
    assertTrue(te.seekExact(new BytesRef("z")));
    assertEquals(122, te.ord());
    r.close();
    w.close();
    dir.close();
}

Example 68 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project lucene-solr by apache.

the class TestOrdsBlockTree method testSeveralNonRootBlocks.

public void testSeveralNonRootBlocks() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
    IndexWriter w = new IndexWriter(dir, iwc);
    List<String> terms = new ArrayList<>();
    for (int i = 0; i < 30; i++) {
        for (int j = 0; j < 30; j++) {
            Document doc = new Document();
            String term = "" + (char) (97 + i) + (char) (97 + j);
            terms.add(term);
            if (VERBOSE) {
                System.out.println("term=" + term);
            }
            doc.add(newTextField("body", term, Field.Store.NO));
            w.addDocument(doc);
        }
    }
    w.forceMerge(1);
    IndexReader r = DirectoryReader.open(w);
    TermsEnum te = MultiFields.getTerms(r, "body").iterator();
    for (int i = 0; i < 30; i++) {
        for (int j = 0; j < 30; j++) {
            String term = "" + (char) (97 + i) + (char) (97 + j);
            if (VERBOSE) {
                System.out.println("TEST: check term=" + term);
            }
            assertEquals(term, te.next().utf8ToString());
            assertEquals(30 * i + j, te.ord());
        }
    }
    testEnum(te, terms);
    te.seekExact(0);
    assertEquals("aa", te.term().utf8ToString());
    r.close();
    w.close();
    dir.close();
}

Example 69 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project lucene-solr by apache.

the class TestOrdsBlockTree method testTwoBlocks.

public void testTwoBlocks() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir);
    List<String> terms = new ArrayList<>();
    for (int i = 0; i < 36; i++) {
        Document doc = new Document();
        String term = "" + (char) (97 + i);
        terms.add(term);
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term);
        }
        doc.add(newTextField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    for (int i = 0; i < 36; i++) {
        Document doc = new Document();
        String term = "m" + (char) (97 + i);
        terms.add(term);
        if (VERBOSE) {
            System.out.println("i=" + i + " term=" + term);
        }
        doc.add(newTextField("field", term, Field.Store.NO));
        w.addDocument(doc);
    }
    if (VERBOSE) {
        System.out.println("TEST: now forceMerge");
    }
    w.forceMerge(1);
    IndexReader r = w.getReader();
    TermsEnum te = MultiFields.getTerms(r, "field").iterator();
    assertTrue(te.seekExact(new BytesRef("mo")));
    assertEquals(27, te.ord());
    te.seekExact(54);
    assertEquals(new BytesRef("s"), te.term());
    Collections.sort(terms);
    for (int i = terms.size() - 1; i >= 0; i--) {
        te.seekExact(i);
        assertEquals(i, te.ord());
        assertEquals(terms.get(i), te.term().utf8ToString());
    }
    int iters = atLeast(1000);
    for (int iter = 0; iter < iters; iter++) {
        int ord = random().nextInt(terms.size());
        BytesRef term = new BytesRef(terms.get(ord));
        if (random().nextBoolean()) {
            if (VERBOSE) {
                System.out.println("TEST: iter=" + iter + " seek to ord=" + ord + " of " + terms.size());
            }
            te.seekExact(ord);
        } else {
            if (VERBOSE) {
                System.out.println("TEST: iter=" + iter + " seek to term=" + terms.get(ord) + " ord=" + ord + " of " + terms.size());
            }
            te.seekExact(term);
        }
        assertEquals(ord, te.ord());
        assertEquals(term, te.term());
    }
    r.close();
    w.close();
    dir.close();
}

Example 70 with TermsEnum

use of org.apache.lucene.index.TermsEnum in project lucene-solr by apache.

the class TestOrdsBlockTree method testSeekCeilNotFound.

public void testSeekCeilNotFound() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    // Get empty string in there!
    doc.add(newStringField("field", "", Field.Store.NO));
    w.addDocument(doc);
    for (int i = 0; i < 36; i++) {
        doc = new Document();
        String term = "" + (char) (97 + i);
        String term2 = "a" + (char) (97 + i);
        doc.add(newTextField("field", term + " " + term2, Field.Store.NO));
        w.addDocument(doc);
    }
    w.forceMerge(1);
    IndexReader r = w.getReader();
    TermsEnum te = MultiFields.getTerms(r, "field").iterator();
    assertEquals(TermsEnum.SeekStatus.NOT_FOUND, te.seekCeil(new BytesRef(new byte[] { 0x22 })));
    assertEquals("a", te.term().utf8ToString());
    assertEquals(1L, te.ord());
    r.close();
    w.close();
    dir.close();
}