Search in sources :

Example 76 with Document

use of org.apache.lucene.document.Document in project elasticsearch by elastic.

the class XMoreLikeThis method retrieveTerms.

/**
     * Find words for a more-like-this query former.
     *
     * @param docNum the id of the lucene document from which to find terms
     */
private PriorityQueue<ScoreTerm> retrieveTerms(int docNum) throws IOException {
    Map<String, Int> termFreqMap = new HashMap<>();
    for (String fieldName : fieldNames) {
        final Fields vectors = ir.getTermVectors(docNum);
        final Terms vector;
        if (vectors != null) {
            vector = vectors.terms(fieldName);
        } else {
            vector = null;
        }
        // field does not store term vector info
        if (vector == null) {
            Document d = ir.document(docNum);
            IndexableField[] fields = d.getFields(fieldName);
            for (IndexableField field : fields) {
                final String stringValue = field.stringValue();
                if (stringValue != null) {
                    addTermFrequencies(new FastStringReader(stringValue), termFreqMap, fieldName);
                }
            }
        } else {
            addTermFrequencies(termFreqMap, vector, fieldName);
        }
    }
    return createQueue(termFreqMap);
}
Also used : IndexableField(org.apache.lucene.index.IndexableField) Fields(org.apache.lucene.index.Fields) MultiFields(org.apache.lucene.index.MultiFields) FastStringReader(org.elasticsearch.common.io.FastStringReader) HashMap(java.util.HashMap) Terms(org.apache.lucene.index.Terms) Document(org.apache.lucene.document.Document)

Example 77 with Document

use of org.apache.lucene.document.Document in project elasticsearch by elastic.

the class AbstractTermVectorsTestCase method indexDocsWithLucene.

protected DirectoryReader indexDocsWithLucene(TestDoc[] testDocs) throws IOException {
    Map<String, Analyzer> mapping = new HashMap<>();
    for (TestFieldSetting field : testDocs[0].fieldSettings) {
        if (field.storedPayloads) {
            mapping.put(field.name, new Analyzer() {

                @Override
                protected TokenStreamComponents createComponents(String fieldName) {
                    Tokenizer tokenizer = new StandardTokenizer();
                    TokenFilter filter = new LowerCaseFilter(tokenizer);
                    filter = new TypeAsPayloadTokenFilter(filter);
                    return new TokenStreamComponents(tokenizer, filter);
                }
            });
        }
    }
    PerFieldAnalyzerWrapper wrapper = new PerFieldAnalyzerWrapper(new StandardAnalyzer(CharArraySet.EMPTY_SET), mapping);
    Directory dir = new RAMDirectory();
    IndexWriterConfig conf = new IndexWriterConfig(wrapper);
    conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
    IndexWriter writer = new IndexWriter(dir, conf);
    for (TestDoc doc : testDocs) {
        Document d = new Document();
        d.add(new Field("id", doc.id, StringField.TYPE_STORED));
        for (int i = 0; i < doc.fieldContent.length; i++) {
            FieldType type = new FieldType(TextField.TYPE_STORED);
            TestFieldSetting fieldSetting = doc.fieldSettings[i];
            type.setStoreTermVectorOffsets(fieldSetting.storedOffset);
            type.setStoreTermVectorPayloads(fieldSetting.storedPayloads);
            type.setStoreTermVectorPositions(fieldSetting.storedPositions || fieldSetting.storedPayloads || fieldSetting.storedOffset);
            type.setStoreTermVectors(true);
            type.freeze();
            d.add(new Field(fieldSetting.name, doc.fieldContent[i], type));
        }
        writer.updateDocument(new Term("id", doc.id), d);
        writer.commit();
    }
    writer.close();
    return DirectoryReader.open(dir);
}
Also used : HashMap(java.util.HashMap) TypeAsPayloadTokenFilter(org.apache.lucene.analysis.payloads.TypeAsPayloadTokenFilter) Term(org.apache.lucene.index.Term) Analyzer(org.apache.lucene.analysis.Analyzer) StandardAnalyzer(org.apache.lucene.analysis.standard.StandardAnalyzer) Document(org.apache.lucene.document.Document) RAMDirectory(org.apache.lucene.store.RAMDirectory) PerFieldAnalyzerWrapper(org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper) FieldType(org.apache.lucene.document.FieldType) StringField(org.apache.lucene.document.StringField) Field(org.apache.lucene.document.Field) TextField(org.apache.lucene.document.TextField) IndexWriter(org.apache.lucene.index.IndexWriter) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StandardAnalyzer(org.apache.lucene.analysis.standard.StandardAnalyzer) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter) TypeAsPayloadTokenFilter(org.apache.lucene.analysis.payloads.TypeAsPayloadTokenFilter) TokenFilter(org.apache.lucene.analysis.TokenFilter) RAMDirectory(org.apache.lucene.store.RAMDirectory) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 78 with Document

use of org.apache.lucene.document.Document in project elasticsearch by elastic.

the class TermVectorsUnitTests method writeEmptyTermVector.

private void writeEmptyTermVector(TermVectorsResponse outResponse) throws IOException {
    Directory dir = newDirectory();
    IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());
    conf.setOpenMode(OpenMode.CREATE);
    IndexWriter writer = new IndexWriter(dir, conf);
    FieldType type = new FieldType(TextField.TYPE_STORED);
    type.setStoreTermVectorOffsets(true);
    type.setStoreTermVectorPayloads(false);
    type.setStoreTermVectorPositions(true);
    type.setStoreTermVectors(true);
    type.freeze();
    Document d = new Document();
    d.add(new Field("id", "abc", StringField.TYPE_STORED));
    writer.updateDocument(new Term("id", "abc"), d);
    writer.commit();
    writer.close();
    DirectoryReader dr = DirectoryReader.open(dir);
    IndexSearcher s = new IndexSearcher(dr);
    TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
    ScoreDoc[] scoreDocs = search.scoreDocs;
    int doc = scoreDocs[0].doc;
    Fields fields = dr.getTermVectors(doc);
    EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
    outResponse.setFields(fields, null, flags, fields);
    outResponse.setExists(true);
    dr.close();
    dir.close();
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) DirectoryReader(org.apache.lucene.index.DirectoryReader) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) Flag(org.elasticsearch.action.termvectors.TermVectorsRequest.Flag) FieldType(org.apache.lucene.document.FieldType) ScoreDoc(org.apache.lucene.search.ScoreDoc) TopDocs(org.apache.lucene.search.TopDocs) StringField(org.apache.lucene.document.StringField) Field(org.apache.lucene.document.Field) TextField(org.apache.lucene.document.TextField) Fields(org.apache.lucene.index.Fields) IndexWriter(org.apache.lucene.index.IndexWriter) StandardAnalyzer(org.apache.lucene.analysis.standard.StandardAnalyzer) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 79 with Document

use of org.apache.lucene.document.Document in project elasticsearch by elastic.

the class TermVectorsUnitTests method writeStandardTermVector.

private void writeStandardTermVector(TermVectorsResponse outResponse) throws IOException {
    Directory dir = newDirectory();
    IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());
    conf.setOpenMode(OpenMode.CREATE);
    IndexWriter writer = new IndexWriter(dir, conf);
    FieldType type = new FieldType(TextField.TYPE_STORED);
    type.setStoreTermVectorOffsets(true);
    type.setStoreTermVectorPayloads(false);
    type.setStoreTermVectorPositions(true);
    type.setStoreTermVectors(true);
    type.freeze();
    Document d = new Document();
    d.add(new Field("id", "abc", StringField.TYPE_STORED));
    d.add(new Field("title", "the1 quick brown fox jumps over  the1 lazy dog", type));
    d.add(new Field("desc", "the1 quick brown fox jumps over  the1 lazy dog", type));
    writer.updateDocument(new Term("id", "abc"), d);
    writer.commit();
    writer.close();
    DirectoryReader dr = DirectoryReader.open(dir);
    IndexSearcher s = new IndexSearcher(dr);
    TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
    ScoreDoc[] scoreDocs = search.scoreDocs;
    int doc = scoreDocs[0].doc;
    Fields termVectors = dr.getTermVectors(doc);
    EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
    outResponse.setFields(termVectors, null, flags, termVectors);
    dr.close();
    dir.close();
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) TermQuery(org.apache.lucene.search.TermQuery) DirectoryReader(org.apache.lucene.index.DirectoryReader) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) Flag(org.elasticsearch.action.termvectors.TermVectorsRequest.Flag) FieldType(org.apache.lucene.document.FieldType) ScoreDoc(org.apache.lucene.search.ScoreDoc) TopDocs(org.apache.lucene.search.TopDocs) StringField(org.apache.lucene.document.StringField) Field(org.apache.lucene.document.Field) TextField(org.apache.lucene.document.TextField) Fields(org.apache.lucene.index.Fields) IndexWriter(org.apache.lucene.index.IndexWriter) StandardAnalyzer(org.apache.lucene.analysis.standard.StandardAnalyzer) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 80 with Document

use of org.apache.lucene.document.Document in project elasticsearch by elastic.

the class RecoverySourceHandlerTests method testHandleExceptinoOnSendSendFiles.

public void testHandleExceptinoOnSendSendFiles() throws Throwable {
    Settings settings = Settings.builder().put("indices.recovery.concurrent_streams", 1).put("indices.recovery.concurrent_small_file_streams", 1).build();
    final RecoverySettings recoverySettings = new RecoverySettings(settings, service);
    final StartRecoveryRequest request = new StartRecoveryRequest(shardId, new DiscoveryNode("b", buildNewFakeTransportAddress(), emptyMap(), emptySet(), Version.CURRENT), new DiscoveryNode("b", buildNewFakeTransportAddress(), emptyMap(), emptySet(), Version.CURRENT), null, randomBoolean(), randomNonNegativeLong(), randomBoolean() ? SequenceNumbersService.UNASSIGNED_SEQ_NO : 0L);
    Path tempDir = createTempDir();
    Store store = newStore(tempDir, false);
    AtomicBoolean failedEngine = new AtomicBoolean(false);
    RecoverySourceHandler handler = new RecoverySourceHandler(null, null, request, () -> 0L, e -> () -> {
    }, recoverySettings.getChunkSize().bytesAsInt(), Settings.EMPTY) {

        @Override
        protected void failEngine(IOException cause) {
            assertFalse(failedEngine.get());
            failedEngine.set(true);
        }
    };
    Directory dir = store.directory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir, newIndexWriterConfig());
    int numDocs = randomIntBetween(10, 100);
    for (int i = 0; i < numDocs; i++) {
        Document document = new Document();
        document.add(new StringField("id", Integer.toString(i), Field.Store.YES));
        document.add(newField("field", randomUnicodeOfCodepointLengthBetween(1, 10), TextField.TYPE_STORED));
        writer.addDocument(document);
    }
    writer.commit();
    writer.close();
    Store.MetadataSnapshot metadata = store.getMetadata(null);
    List<StoreFileMetaData> metas = new ArrayList<>();
    for (StoreFileMetaData md : metadata) {
        metas.add(md);
    }
    final boolean throwCorruptedIndexException = randomBoolean();
    Store targetStore = newStore(createTempDir(), false);
    try {
        handler.sendFiles(store, metas.toArray(new StoreFileMetaData[0]), (md) -> {
            if (throwCorruptedIndexException) {
                throw new RuntimeException(new CorruptIndexException("foo", "bar"));
            } else {
                throw new RuntimeException("boom");
            }
        });
        fail("exception index");
    } catch (RuntimeException ex) {
        assertNull(ExceptionsHelper.unwrapCorruption(ex));
        if (throwCorruptedIndexException) {
            assertEquals(ex.getMessage(), "[File corruption occurred on recovery but checksums are ok]");
        } else {
            assertEquals(ex.getMessage(), "boom");
        }
    } catch (CorruptIndexException ex) {
        fail("not expected here");
    }
    assertFalse(failedEngine.get());
    IOUtils.close(store, targetStore);
}
Also used : Path(java.nio.file.Path) DiscoveryNode(org.elasticsearch.cluster.node.DiscoveryNode) ArrayList(java.util.ArrayList) Store(org.elasticsearch.index.store.Store) CorruptIndexException(org.apache.lucene.index.CorruptIndexException) IOException(java.io.IOException) Document(org.apache.lucene.document.Document) ParsedDocument(org.elasticsearch.index.mapper.ParsedDocument) AtomicBoolean(java.util.concurrent.atomic.AtomicBoolean) StoreFileMetaData(org.elasticsearch.index.store.StoreFileMetaData) StringField(org.apache.lucene.document.StringField) Settings(org.elasticsearch.common.settings.Settings) IndexSettings(org.elasticsearch.index.IndexSettings) ClusterSettings(org.elasticsearch.common.settings.ClusterSettings) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter) Directory(org.apache.lucene.store.Directory)

Aggregations

Document (org.apache.lucene.document.Document)2344 Directory (org.apache.lucene.store.Directory)1374 MockAnalyzer (org.apache.lucene.analysis.MockAnalyzer)798 RandomIndexWriter (org.apache.lucene.index.RandomIndexWriter)752 IndexReader (org.apache.lucene.index.IndexReader)598 Field (org.apache.lucene.document.Field)480 IndexSearcher (org.apache.lucene.search.IndexSearcher)470 Term (org.apache.lucene.index.Term)456 BytesRef (org.apache.lucene.util.BytesRef)415 StringField (org.apache.lucene.document.StringField)403 TextField (org.apache.lucene.document.TextField)389 NumericDocValuesField (org.apache.lucene.document.NumericDocValuesField)325 IndexWriter (org.apache.lucene.index.IndexWriter)312 IndexWriterConfig (org.apache.lucene.index.IndexWriterConfig)278 TopDocs (org.apache.lucene.search.TopDocs)270 TermQuery (org.apache.lucene.search.TermQuery)237 FieldType (org.apache.lucene.document.FieldType)231 DirectoryReader (org.apache.lucene.index.DirectoryReader)226 Test (org.junit.Test)222 RAMDirectory (org.apache.lucene.store.RAMDirectory)211