Search in sources :

Example 16 with RAMDirectory

use of org.apache.lucene.store.RAMDirectory in project elasticsearch by elastic.

the class SimpleLuceneTests method testBoost.

public void testBoost() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    for (int i = 0; i < 100; i++) {
        // TODO (just setting the boost value does not seem to work...)
        StringBuilder value = new StringBuilder().append("value");
        for (int j = 0; j < i; j++) {
            value.append(" ").append("value");
        }
        Document document = new Document();
        TextField textField = new TextField("_id", Integer.toString(i), Field.Store.YES);
        textField.setBoost(i);
        document.add(textField);
        textField = new TextField("value", value.toString(), Field.Store.YES);
        textField.setBoost(i);
        document.add(textField);
        indexWriter.addDocument(document);
    }
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TermQuery query = new TermQuery(new Term("value", "value"));
    TopDocs topDocs = searcher.search(query, 100);
    assertThat(100, equalTo(topDocs.totalHits));
    for (int i = 0; i < topDocs.scoreDocs.length; i++) {
        Document doc = searcher.doc(topDocs.scoreDocs[i].doc);
        //            System.out.println(doc.get("id") + ": " + searcher.explain(query, topDocs.scoreDocs[i].doc));
        assertThat(doc.get("_id"), equalTo(Integer.toString(100 - i - 1)));
    }
    indexWriter.close();
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) TopDocs(org.apache.lucene.search.TopDocs) IndexWriter(org.apache.lucene.index.IndexWriter) IndexReader(org.apache.lucene.index.IndexReader) TextField(org.apache.lucene.document.TextField) RAMDirectory(org.apache.lucene.store.RAMDirectory) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 17 with RAMDirectory

use of org.apache.lucene.store.RAMDirectory in project elasticsearch by elastic.

the class SimpleLuceneTests method testOrdering.

/**
     * Here, we verify that the order that we add fields to a document counts, and not the lexi order
     * of the field. This means that heavily accessed fields that use field selector should be added
     * first (with load and break).
     */
public void testOrdering() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new TextField("#id", "1", Field.Store.YES));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    final ArrayList<String> fieldsOrder = new ArrayList<>();
    searcher.doc(topDocs.scoreDocs[0].doc, new StoredFieldVisitor() {

        @Override
        public Status needsField(FieldInfo fieldInfo) throws IOException {
            fieldsOrder.add(fieldInfo.name);
            return Status.YES;
        }
    });
    assertThat(fieldsOrder.size(), equalTo(2));
    assertThat(fieldsOrder.get(0), equalTo("_id"));
    assertThat(fieldsOrder.get(1), equalTo("#id"));
    indexWriter.close();
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) ArrayList(java.util.ArrayList) Term(org.apache.lucene.index.Term) IOException(java.io.IOException) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) TopDocs(org.apache.lucene.search.TopDocs) IndexWriter(org.apache.lucene.index.IndexWriter) StoredFieldVisitor(org.apache.lucene.index.StoredFieldVisitor) IndexReader(org.apache.lucene.index.IndexReader) TextField(org.apache.lucene.document.TextField) FieldInfo(org.apache.lucene.index.FieldInfo) RAMDirectory(org.apache.lucene.store.RAMDirectory) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 18 with RAMDirectory

use of org.apache.lucene.store.RAMDirectory in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighterNoTermVector.

public void testVectorHighlighterNoTermVector() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new TextField("content", "the big bad dog", Field.Store.YES));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    assertThat(topDocs.totalHits, equalTo(1));
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) FastVectorHighlighter(org.apache.lucene.search.vectorhighlight.FastVectorHighlighter) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) TopDocs(org.apache.lucene.search.TopDocs) IndexWriter(org.apache.lucene.index.IndexWriter) IndexReader(org.apache.lucene.index.IndexReader) TextField(org.apache.lucene.document.TextField) RAMDirectory(org.apache.lucene.store.RAMDirectory) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 19 with RAMDirectory

use of org.apache.lucene.store.RAMDirectory in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighter.

public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    assertThat(topDocs.totalHits, equalTo(1));
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
    assertThat(fragment, equalTo("the big <b>bad</b> dog"));
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) FastVectorHighlighter(org.apache.lucene.search.vectorhighlight.FastVectorHighlighter) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) FieldType(org.apache.lucene.document.FieldType) TopDocs(org.apache.lucene.search.TopDocs) Field(org.apache.lucene.document.Field) TextField(org.apache.lucene.document.TextField) IndexWriter(org.apache.lucene.index.IndexWriter) IndexReader(org.apache.lucene.index.IndexReader) TextField(org.apache.lucene.document.TextField) RAMDirectory(org.apache.lucene.store.RAMDirectory) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 20 with RAMDirectory

use of org.apache.lucene.store.RAMDirectory in project elasticsearch by elastic.

the class IndexFieldDataServiceTests method testFieldDataCacheListener.

public void testFieldDataCacheListener() throws Exception {
    final IndexService indexService = createIndex("test");
    final IndicesService indicesService = getInstanceFromNode(IndicesService.class);
    // copy the ifdService since we can set the listener only once.
    final IndexFieldDataService ifdService = new IndexFieldDataService(indexService.getIndexSettings(), indicesService.getIndicesFieldDataCache(), indicesService.getCircuitBreakerService(), indexService.mapperService());
    final BuilderContext ctx = new BuilderContext(indexService.getIndexSettings().getSettings(), new ContentPath(1));
    final MappedFieldType mapper1 = new TextFieldMapper.Builder("s").fielddata(true).build(ctx).fieldType();
    final IndexWriter writer = new IndexWriter(new RAMDirectory(), new IndexWriterConfig(new KeywordAnalyzer()));
    Document doc = new Document();
    doc.add(new StringField("s", "thisisastring", Store.NO));
    writer.addDocument(doc);
    DirectoryReader open = DirectoryReader.open(writer);
    final boolean wrap = randomBoolean();
    final IndexReader reader = wrap ? ElasticsearchDirectoryReader.wrap(open, new ShardId("test", "_na_", 1)) : open;
    final AtomicInteger onCacheCalled = new AtomicInteger();
    final AtomicInteger onRemovalCalled = new AtomicInteger();
    ifdService.setListener(new IndexFieldDataCache.Listener() {

        @Override
        public void onCache(ShardId shardId, String fieldName, Accountable ramUsage) {
            if (wrap) {
                assertEquals(new ShardId("test", "_na_", 1), shardId);
            } else {
                assertNull(shardId);
            }
            onCacheCalled.incrementAndGet();
        }

        @Override
        public void onRemoval(ShardId shardId, String fieldName, boolean wasEvicted, long sizeInBytes) {
            if (wrap) {
                assertEquals(new ShardId("test", "_na_", 1), shardId);
            } else {
                assertNull(shardId);
            }
            onRemovalCalled.incrementAndGet();
        }
    });
    IndexFieldData<?> ifd = ifdService.getForField(mapper1);
    LeafReaderContext leafReaderContext = reader.getContext().leaves().get(0);
    AtomicFieldData load = ifd.load(leafReaderContext);
    assertEquals(1, onCacheCalled.get());
    assertEquals(0, onRemovalCalled.get());
    reader.close();
    load.close();
    writer.close();
    assertEquals(1, onCacheCalled.get());
    assertEquals(1, onRemovalCalled.get());
    ifdService.clear();
}
Also used : IndexService(org.elasticsearch.index.IndexService) Matchers.containsString(org.hamcrest.Matchers.containsString) Document(org.apache.lucene.document.Document) ShardId(org.elasticsearch.index.shard.ShardId) MappedFieldType(org.elasticsearch.index.mapper.MappedFieldType) LeafReaderContext(org.apache.lucene.index.LeafReaderContext) KeywordAnalyzer(org.apache.lucene.analysis.core.KeywordAnalyzer) ElasticsearchDirectoryReader(org.elasticsearch.common.lucene.index.ElasticsearchDirectoryReader) DirectoryReader(org.apache.lucene.index.DirectoryReader) Accountable(org.apache.lucene.util.Accountable) IndicesService(org.elasticsearch.indices.IndicesService) ContentPath(org.elasticsearch.index.mapper.ContentPath) RAMDirectory(org.apache.lucene.store.RAMDirectory) IndexWriter(org.apache.lucene.index.IndexWriter) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) StringField(org.apache.lucene.document.StringField) IndexReader(org.apache.lucene.index.IndexReader) BuilderContext(org.elasticsearch.index.mapper.Mapper.BuilderContext) TextFieldMapper(org.elasticsearch.index.mapper.TextFieldMapper) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Aggregations

RAMDirectory (org.apache.lucene.store.RAMDirectory)183 Directory (org.apache.lucene.store.Directory)101 IndexWriter (org.apache.lucene.index.IndexWriter)82 Document (org.apache.lucene.document.Document)75 IndexWriterConfig (org.apache.lucene.index.IndexWriterConfig)73 IndexSearcher (org.apache.lucene.search.IndexSearcher)43 IndexReader (org.apache.lucene.index.IndexReader)41 Test (org.junit.Test)35 TextField (org.apache.lucene.document.TextField)33 Field (org.apache.lucene.document.Field)29 Term (org.apache.lucene.index.Term)25 StandardAnalyzer (org.apache.lucene.analysis.standard.StandardAnalyzer)21 Before (org.junit.Before)21 IOException (java.io.IOException)19 MockAnalyzer (org.apache.lucene.analysis.MockAnalyzer)19 Analyzer (org.apache.lucene.analysis.Analyzer)18 TopDocs (org.apache.lucene.search.TopDocs)16 DirectoryReader (org.apache.lucene.index.DirectoryReader)15 FilterDirectory (org.apache.lucene.store.FilterDirectory)15 FieldType (org.apache.lucene.document.FieldType)13