Examples with SortedSetDocValuesField org.apache.lucene.document.SortedSetDocValuesField used on opensource projects

Example 76 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestSortedSetSortField method testReverse.

public void testReverse() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("foo")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("bar")));
    doc.add(newStringField("id", "1", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("baz")));
    doc.add(newStringField("id", "2", Field.Store.YES));
    writer.addDocument(doc);
    IndexReader ir = writer.getReader();
    writer.close();
    IndexSearcher searcher = newSearcher(ir);
    Sort sort = new Sort(new SortedSetSortField("value", true));
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(2, td.totalHits);
    // 'bar' comes before 'baz'
    assertEquals("2", searcher.doc(td.scoreDocs[0].doc).get("id"));
    assertEquals("1", searcher.doc(td.scoreDocs[1].doc).get("id"));
    ir.close();
    dir.close();
}

Example 77 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestIndexSorting method testMissingMultiValuedStringFirst.

public void testMissingMultiValuedStringFirst() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
    SortField sortField = new SortedSetSortField("foo", false);
    sortField.setMissingValue(SortField.STRING_FIRST);
    Sort indexSort = new Sort(sortField);
    iwc.setIndexSort(indexSort);
    IndexWriter w = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new NumericDocValuesField("id", 3));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("zzz")));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("zzza")));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("zzzd")));
    w.addDocument(doc);
    // so we get more than one segment, so that forceMerge actually does merge, since we only get a sorted segment by merging:
    w.commit();
    // missing
    doc = new Document();
    doc.add(new NumericDocValuesField("id", 1));
    w.addDocument(doc);
    w.commit();
    doc = new Document();
    doc.add(new NumericDocValuesField("id", 2));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("mmm")));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("nnnn")));
    w.addDocument(doc);
    w.forceMerge(1);
    DirectoryReader r = DirectoryReader.open(w);
    LeafReader leaf = getOnlyLeafReader(r);
    assertEquals(3, leaf.maxDoc());
    NumericDocValues values = leaf.getNumericDocValues("id");
    assertEquals(0, values.nextDoc());
    assertEquals(1l, values.longValue());
    assertEquals(1, values.nextDoc());
    assertEquals(2l, values.longValue());
    assertEquals(2, values.nextDoc());
    assertEquals(3l, values.longValue());
    r.close();
    w.close();
    dir.close();
}

Example 78 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestIndexSorting method testMultiValuedStringAlreadySorted.

public void testMultiValuedStringAlreadySorted() throws Exception {
    assertNeedsIndexSortMerge(new SortedSetSortField("foo", false), (doc) -> {
        doc.add(new SortedSetDocValuesField("foo", new BytesRef("")));
        int num = random().nextInt(5);
        for (int j = 0; j < num; j++) {
            doc.add(new SortedSetDocValuesField("foo", TestUtil.randomBinaryTerm(random())));
        }
    }, (doc) -> {
        int num = random().nextInt(5);
        for (int j = 0; j < num; j++) {
            doc.add(new SortedSetDocValuesField("foo", TestUtil.randomBinaryTerm(random())));
        }
    });
}

Example 79 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestIndexSorting method testMissingMultiValuedStringLast.

public void testMissingMultiValuedStringLast() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(new MockAnalyzer(random()));
    SortField sortField = new SortedSetSortField("foo", false);
    sortField.setMissingValue(SortField.STRING_LAST);
    Sort indexSort = new Sort(sortField);
    iwc.setIndexSort(indexSort);
    IndexWriter w = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new NumericDocValuesField("id", 2));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("zzz")));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("zzzd")));
    w.addDocument(doc);
    // so we get more than one segment, so that forceMerge actually does merge, since we only get a sorted segment by merging:
    w.commit();
    // missing
    doc = new Document();
    doc.add(new NumericDocValuesField("id", 3));
    w.addDocument(doc);
    w.commit();
    doc = new Document();
    doc.add(new NumericDocValuesField("id", 1));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("mmm")));
    doc.add(new SortedSetDocValuesField("foo", new BytesRef("ppp")));
    w.addDocument(doc);
    w.forceMerge(1);
    DirectoryReader r = DirectoryReader.open(w);
    LeafReader leaf = getOnlyLeafReader(r);
    assertEquals(3, leaf.maxDoc());
    NumericDocValues values = leaf.getNumericDocValues("id");
    assertEquals(0, values.nextDoc());
    assertEquals(1l, values.longValue());
    assertEquals(1, values.nextDoc());
    assertEquals(2l, values.longValue());
    assertEquals(2, values.nextDoc());
    assertEquals(3l, values.longValue());
    r.close();
    w.close();
    dir.close();
}

Example 80 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestJoinUtil method testEquals.

public void testEquals() throws Exception {
    final int numDocs = atLeast(random(), 50);
    try (final Directory dir = newDirectory()) {
        try (final RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()))) {
            boolean multiValued = random().nextBoolean();
            String joinField = multiValued ? "mvField" : "svField";
            for (int id = 0; id < numDocs; id++) {
                Document doc = new Document();
                doc.add(new TextField("id", "" + id, Field.Store.NO));
                doc.add(new TextField("name", "name" + (id % 7), Field.Store.NO));
                if (multiValued) {
                    int numValues = 1 + random().nextInt(2);
                    for (int i = 0; i < numValues; i++) {
                        doc.add(new SortedSetDocValuesField(joinField, new BytesRef("" + random().nextInt(13))));
                    }
                } else {
                    doc.add(new SortedDocValuesField(joinField, new BytesRef("" + random().nextInt(13))));
                }
                w.addDocument(doc);
            }
            Set<ScoreMode> scoreModes = EnumSet.allOf(ScoreMode.class);
            ScoreMode scoreMode1 = RandomPicks.randomFrom(random(), scoreModes);
            scoreModes.remove(scoreMode1);
            ScoreMode scoreMode2 = RandomPicks.randomFrom(random(), scoreModes);
            final Query x;
            try (IndexReader r = w.getReader()) {
                IndexSearcher indexSearcher = new IndexSearcher(r);
                x = JoinUtil.createJoinQuery(joinField, multiValued, joinField, new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode1);
                assertEquals("identical calls to createJoinQuery", x, JoinUtil.createJoinQuery(joinField, multiValued, joinField, new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode1));
                assertFalse("score mode (" + scoreMode1 + " != " + scoreMode2 + "), but queries are equal", x.equals(JoinUtil.createJoinQuery(joinField, multiValued, joinField, new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode2)));
                assertFalse("from fields (joinField != \"other_field\") but queries equals", x.equals(JoinUtil.createJoinQuery(joinField, multiValued, "other_field", new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode1)));
                assertFalse("from fields (\"other_field\" != joinField) but queries equals", x.equals(JoinUtil.createJoinQuery("other_field", multiValued, joinField, new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode1)));
                assertFalse("fromQuery (name:name5 != name:name6) but queries equals", x.equals(JoinUtil.createJoinQuery("other_field", multiValued, joinField, new TermQuery(new Term("name", "name6")), indexSearcher, scoreMode1)));
            }
            for (int i = 0; i < 13; i++) {
                Document doc = new Document();
                doc.add(new TextField("id", "new_id", Field.Store.NO));
                doc.add(new TextField("name", "name5", Field.Store.NO));
                if (multiValued) {
                    int numValues = 1 + random().nextInt(2);
                    for (int j = 0; j < numValues; j++) {
                        doc.add(new SortedSetDocValuesField(joinField, new BytesRef("" + i)));
                    }
                } else {
                    doc.add(new SortedDocValuesField(joinField, new BytesRef("" + i)));
                }
                w.addDocument(doc);
            }
            try (IndexReader r = w.getReader()) {
                IndexSearcher indexSearcher = new IndexSearcher(r);
                assertFalse("Query shouldn't be equal, because different index readers ", x.equals(JoinUtil.createJoinQuery(joinField, multiValued, joinField, new TermQuery(new Term("name", "name5")), indexSearcher, scoreMode1)));
            }
        }
    }
}