Example usage for org.apache.lucene.index DocValuesType BINARY

List of usage examples for org.apache.lucene.index DocValuesType BINARY

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. DocValuesType
  6. BINARY

Introduction

In this page you can find the example usage for org.apache.lucene.index DocValuesType BINARY.

Prototype

DocValuesType BINARY

To view the source code for org.apache.lucene.index DocValuesType BINARY.

Click Source Link

Document

A per-document byte[].

Usage

From source file:com.tuplejump.stargate.lucene.LuceneUtils.java

License:Apache License

public static FieldType docValueTypeFrom(FieldType fieldType) {
    FieldType docValType = new FieldType(fieldType);
    if (fieldType.numericType() != null)
        docValType.setDocValueType(FieldInfo.DocValuesType.NUMERIC);
    else//  www.j a va  2s  . c  o  m
        docValType.setDocValueType(FieldInfo.DocValuesType.BINARY);
    return docValType;
}

From source file:com.vmware.xenon.services.common.Lucene60FieldInfosFormatWithCache.java

License:Open Source License

private static DocValuesType getDocValuesType(IndexInput input, byte b) throws IOException {
    switch (b) {//  w w w .j  a  v a 2 s  .co m
    case 0:
        return DocValuesType.NONE;
    case 1:
        return DocValuesType.NUMERIC;
    case 2:
        return DocValuesType.BINARY;
    case 3:
        return DocValuesType.SORTED;
    case 4:
        return DocValuesType.SORTED_SET;
    case 5:
        return DocValuesType.SORTED_NUMERIC;
    default:
        throw new CorruptIndexException("invalid docvalues byte: " + b, input);
    }
}

From source file:net.semanticmetadata.lire.solr.LireValueSource.java

License:Open Source License

@Override
/**/*from  w w w.  ja v a 2 s.co m*/
 * Check also {@link org.apache.lucene.queries.function.valuesource.BytesRefFieldSource}
 */
public FunctionValues getValues(Map context, LeafReaderContext readerContext) throws IOException {
    final FieldInfo fieldInfo = readerContext.reader().getFieldInfos().fieldInfo(field);
    if (fieldInfo != null && fieldInfo.getDocValuesType() == DocValuesType.BINARY) {
        final BinaryDocValues binaryValues = DocValues.getBinary(readerContext.reader(), field);
        final Bits docsWithField = DocValues.getDocsWithField(readerContext.reader(), field);

        return new FunctionValues() {
            @Override
            public boolean exists(int doc) {
                return docsWithField.get(doc);
            }

            @Override
            public boolean bytesVal(int doc, BytesRefBuilder target) {
                target.copyBytes(binaryValues.get(doc));
                return target.length() > 0;
            }

            @Override
            public float floatVal(int doc) {
                return (float) doubleVal(doc);
            }

            public String strVal(int doc) {
                final BytesRefBuilder bytes = new BytesRefBuilder();
                return bytesVal(doc, bytes) ? bytes.get().utf8ToString() : null;
            }

            /**
             * This method basically decides which type is delivered on request. It can be a String,
             * in this case it is the double form the distance function.
             * @param doc
             * @return the distance as Double, mapping to {@link FunctionValues#doubleVal(int)}
             */
            @Override
            public Object objectVal(int doc) {
                return doubleVal(doc);
            }

            @Override
            public String toString(int doc) {
                return description() + '=' + strVal(doc);
            }

            @Override
            /**
             * This method has to be implemented to support sorting!
             */
            public double doubleVal(int doc) {
                if (binaryValues.get(doc).length > 0) {
                    tmpFeature.setByteArrayRepresentation(binaryValues.get(doc).bytes,
                            binaryValues.get(doc).offset, binaryValues.get(doc).length);
                    return tmpFeature.getDistance(feature);
                } else
                    return maxDistance; // make sure max distance is returned for those without value
            }
        };
    } else {
        // there is no DocVal to sort by. Therefore we need to set the function value to -1 and everything without DocVal gets ranked first?
        return new DocTermsIndexDocValues(this, readerContext, field) {
            @Override
            protected String toTerm(String readableValue) {
                return Double.toString(maxDistance);
            }

            @Override
            public Object objectVal(int doc) {
                return maxDistance;
            }

            @Override
            public String toString(int doc) {
                return description() + '=' + strVal(doc);
            }

            public double doubleVal(int doc) {
                return maxDistance;
            }
        };
    }
}

From source file:org.apache.solr.uninverting.UninvertingReader.java

License:Apache License

/** 
 * Create a new UninvertingReader with the specified mapping 
 * <p>/*from  w ww  .  j ava  2 s  .c o m*/
 * Expert: This should almost never be used. Use {@link #wrap(DirectoryReader, Map)}
 * instead.
 *  
 * @lucene.internal
 */
public UninvertingReader(LeafReader in, Map<String, Type> mapping) {
    super(in);
    this.mapping = mapping;
    ArrayList<FieldInfo> filteredInfos = new ArrayList<>();
    for (FieldInfo fi : in.getFieldInfos()) {
        DocValuesType type = fi.getDocValuesType();
        if (type == DocValuesType.NONE) {
            Type t = mapping.get(fi.name);
            if (t != null) {
                if (t == Type.INTEGER_POINT || t == Type.LONG_POINT || t == Type.FLOAT_POINT
                        || t == Type.DOUBLE_POINT) {
                    // type uses points
                    if (fi.getPointDimensionCount() == 0) {
                        continue;
                    }
                } else {
                    // type uses inverted index
                    if (fi.getIndexOptions() == IndexOptions.NONE) {
                        continue;
                    }
                }
                switch (t) {
                case INTEGER_POINT:
                case LONG_POINT:
                case FLOAT_POINT:
                case DOUBLE_POINT:
                case LEGACY_INTEGER:
                case LEGACY_LONG:
                case LEGACY_FLOAT:
                case LEGACY_DOUBLE:
                    type = DocValuesType.NUMERIC;
                    break;
                case BINARY:
                    type = DocValuesType.BINARY;
                    break;
                case SORTED:
                    type = DocValuesType.SORTED;
                    break;
                case SORTED_SET_BINARY:
                case SORTED_SET_INTEGER:
                case SORTED_SET_FLOAT:
                case SORTED_SET_LONG:
                case SORTED_SET_DOUBLE:
                    type = DocValuesType.SORTED_SET;
                    break;
                default:
                    throw new AssertionError();
                }
            }
        }
        filteredInfos.add(new FieldInfo(fi.name, fi.number, fi.hasVectors(), fi.omitsNorms(), fi.hasPayloads(),
                fi.getIndexOptions(), type, fi.getDocValuesGen(), fi.attributes(), fi.getPointDimensionCount(),
                fi.getPointNumBytes()));
    }
    fieldInfos = new FieldInfos(filteredInfos.toArray(new FieldInfo[filteredInfos.size()]));
}

From source file:org.elasticsearch.index.mapper.IpRangeFieldMapperTests.java

License:Apache License

public void testStoreCidr() throws Exception {
    XContentBuilder mapping = XContentFactory.jsonBuilder().startObject().startObject("type")
            .startObject("properties").startObject("field").field("type", "ip_range").field("store", true);
    mapping = mapping.endObject().endObject().endObject().endObject();
    DocumentMapper mapper = parser.parse("type", new CompressedXContent(Strings.toString(mapping)));
    assertEquals(Strings.toString(mapping), mapper.mappingSource().toString());
    final Map<String, String> cases = new HashMap<>();
    cases.put("192.168.0.0/15", "192.169.255.255");
    cases.put("192.168.0.0/16", "192.168.255.255");
    cases.put("192.168.0.0/17", "192.168.127.255");
    for (final Map.Entry<String, String> entry : cases.entrySet()) {
        ParsedDocument doc = mapper.parse(SourceToParse.source("test", "type", "1",
                BytesReference.bytes(//from  w w w. j  av a2s .c  o  m
                        XContentFactory.jsonBuilder().startObject().field("field", entry.getKey()).endObject()),
                XContentType.JSON));
        IndexableField[] fields = doc.rootDoc().getFields("field");
        assertEquals(3, fields.length);
        IndexableField dvField = fields[0];
        assertEquals(DocValuesType.BINARY, dvField.fieldType().docValuesType());
        IndexableField pointField = fields[1];
        assertEquals(2, pointField.fieldType().pointDimensionCount());
        IndexableField storedField = fields[2];
        assertTrue(storedField.fieldType().stored());
        String strVal = InetAddresses.toAddrString(InetAddresses.forString("192.168.0.0")) + " : "
                + InetAddresses.toAddrString(InetAddresses.forString(entry.getValue()));
        assertThat(storedField.stringValue(), containsString(strVal));
    }
}

From source file:org.elasticsearch.search.suggest.completion.CompletionPostingsFormatTest.java

License:Apache License

@Test
public void testNoDocs() throws IOException {
    AnalyzingCompletionLookupProvider provider = new AnalyzingCompletionLookupProvider(true, false, true, true);
    RAMDirectory dir = new RAMDirectory();
    IndexOutput output = dir.createOutput("foo.txt", IOContext.DEFAULT);
    FieldsConsumer consumer = provider.consumer(output);
    FieldInfo fieldInfo = new FieldInfo("foo", true, 1, false, true, true,
            IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, DocValuesType.SORTED, DocValuesType.BINARY,
            new HashMap<String, String>());
    TermsConsumer addField = consumer.addField(fieldInfo);
    addField.finish(0, 0, 0);//from   w  w w  .j a  v  a  2 s  . c o m
    consumer.close();
    output.close();

    IndexInput input = dir.openInput("foo.txt", IOContext.DEFAULT);
    LookupFactory load = provider.load(input);
    PostingsFormatProvider format = new PreBuiltPostingsFormatProvider(new Elasticsearch090PostingsFormat());
    NamedAnalyzer analyzer = new NamedAnalyzer("foo", new StandardAnalyzer(TEST_VERSION_CURRENT));
    assertNull(load.getLookup(
            new CompletionFieldMapper(new Names("foo"), analyzer, analyzer, format, null, true, true, true,
                    Integer.MAX_VALUE, AbstractFieldMapper.MultiFields.empty(), null),
            new CompletionSuggestionContext(null)));
    dir.close();
}

From source file:org.elasticsearch.search.suggest.completion.CompletionPostingsFormatTest.java

License:Apache License

private void writeData(Directory dir, Completion090PostingsFormat.CompletionLookupProvider provider)
        throws IOException {
    IndexOutput output = dir.createOutput("foo.txt", IOContext.DEFAULT);
    FieldsConsumer consumer = provider.consumer(output);
    FieldInfo fieldInfo = new FieldInfo("foo", true, 1, false, true, true,
            IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, DocValuesType.SORTED, DocValuesType.BINARY,
            new HashMap<String, String>());
    TermsConsumer addField = consumer.addField(fieldInfo);

    PostingsConsumer postingsConsumer = addField.startTerm(new BytesRef("foofightersgenerator"));
    postingsConsumer.startDoc(0, 1);//from ww  w. java2 s  .  com
    postingsConsumer.addPosition(256 - 2,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("foofightersgenerator"), new TermStats(1, 1));
    addField.startTerm(new BytesRef("generator"));
    postingsConsumer.startDoc(0, 1);
    postingsConsumer.addPosition(256 - 1,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("generator"), new TermStats(1, 1));
    addField.finish(1, 1, 1);
    consumer.close();
    output.close();

}

From source file:org.elasticsearch.search.suggest.CompletionPostingsFormatTest.java

License:Apache License

@Test
public void testCompletionPostingsFormat() throws IOException {
    AnalyzingCompletionLookupProvider provider = new AnalyzingCompletionLookupProvider(true, false, true, true);
    RAMDirectory dir = new RAMDirectory();
    IndexOutput output = dir.createOutput("foo.txt", IOContext.DEFAULT);
    FieldsConsumer consumer = provider.consumer(output);
    FieldInfo fieldInfo = new FieldInfo("foo", true, 1, false, true, true,
            IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, DocValuesType.SORTED, DocValuesType.BINARY,
            new HashMap<String, String>());
    TermsConsumer addField = consumer.addField(fieldInfo);

    PostingsConsumer postingsConsumer = addField.startTerm(new BytesRef("foofightersgenerator"));
    postingsConsumer.startDoc(0, 1);/*w w w  .j  a va 2 s.com*/
    postingsConsumer.addPosition(256 - 2,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("foofightersgenerator"), new TermStats(1, 1));
    addField.startTerm(new BytesRef("generator"));
    postingsConsumer.startDoc(0, 1);
    postingsConsumer.addPosition(256 - 1,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("generator"), new TermStats(1, 1));
    addField.finish(1, 1, 1);
    consumer.close();
    output.close();

    IndexInput input = dir.openInput("foo.txt", IOContext.DEFAULT);
    LookupFactory load = provider.load(input);
    PostingsFormatProvider format = new PreBuiltPostingsFormatProvider(new ElasticSearch090PostingsFormat());
    NamedAnalyzer analyzer = new NamedAnalyzer("foo", new StandardAnalyzer(TEST_VERSION_CURRENT));
    Lookup lookup = load.getLookup(new CompletionFieldMapper(new Names("foo"), analyzer, analyzer, format, null,
            true, true, true, Integer.MAX_VALUE), new CompletionSuggestionContext(null));
    List<LookupResult> result = lookup.lookup("ge", false, 10);
    assertThat(result.get(0).key.toString(), equalTo("Generator - Foo Fighters"));
    assertThat(result.get(0).payload.utf8ToString(), equalTo("id:10"));
    dir.close();
}

From source file:org.elasticsearch.search.suggest.CompletionPostingsFormatTest.java

License:Apache License

@Test
public void testNoDocs() throws IOException {
    AnalyzingCompletionLookupProvider provider = new AnalyzingCompletionLookupProvider(true, false, true, true);
    RAMDirectory dir = new RAMDirectory();
    IndexOutput output = dir.createOutput("foo.txt", IOContext.DEFAULT);
    FieldsConsumer consumer = provider.consumer(output);
    FieldInfo fieldInfo = new FieldInfo("foo", true, 1, false, true, true,
            IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, DocValuesType.SORTED, DocValuesType.BINARY,
            new HashMap<String, String>());
    TermsConsumer addField = consumer.addField(fieldInfo);
    addField.finish(0, 0, 0);/*from w w  w.  j  ava  2 s . c  o  m*/
    consumer.close();
    output.close();

    IndexInput input = dir.openInput("foo.txt", IOContext.DEFAULT);
    LookupFactory load = provider.load(input);
    PostingsFormatProvider format = new PreBuiltPostingsFormatProvider(new ElasticSearch090PostingsFormat());
    NamedAnalyzer analyzer = new NamedAnalyzer("foo", new StandardAnalyzer(TEST_VERSION_CURRENT));
    assertNull(load.getLookup(new CompletionFieldMapper(new Names("foo"), analyzer, analyzer, format, null,
            true, true, true, Integer.MAX_VALUE), new CompletionSuggestionContext(null)));
    dir.close();
}

From source file:org.elasticsearch.test.integration.search.suggest.CompletionPostingsFormatTest.java

License:Apache License

@Test
public void testCompletionPostingsFormat() throws IOException {
    AnalyzingCompletionLookupProvider provider = new AnalyzingCompletionLookupProvider(true, false, true, true);
    RAMDirectory dir = new RAMDirectory();
    IndexOutput output = dir.createOutput("foo.txt", IOContext.DEFAULT);
    FieldsConsumer consumer = provider.consumer(output);
    FieldInfo fieldInfo = new FieldInfo("foo", true, 1, false, true, true,
            IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, DocValuesType.SORTED, DocValuesType.BINARY,
            new HashMap<String, String>());
    TermsConsumer addField = consumer.addField(fieldInfo);

    PostingsConsumer postingsConsumer = addField.startTerm(new BytesRef("foofightersgenerator"));
    postingsConsumer.startDoc(0, 1);// w  w  w  .  j av a2s .  c  o m
    postingsConsumer.addPosition(256 - 2,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("foofightersgenerator"), new TermStats(1, 1));
    addField.startTerm(new BytesRef("generator"));
    postingsConsumer.startDoc(0, 1);
    postingsConsumer.addPosition(256 - 1,
            provider.buildPayload(new BytesRef("Generator - Foo Fighters"), 9, new BytesRef("id:10")), 0, 1);
    postingsConsumer.finishDoc();
    addField.finishTerm(new BytesRef("generator"), new TermStats(1, 1));
    addField.finish(1, 1, 1);
    consumer.close();
    output.close();

    IndexInput input = dir.openInput("foo.txt", IOContext.DEFAULT);
    LookupFactory load = provider.load(input);
    PostingsFormatProvider format = new PreBuiltPostingsFormatProvider(new ElasticSearch090PostingsFormat());
    NamedAnalyzer analyzer = new NamedAnalyzer("foo", new StandardAnalyzer(TEST_VERSION_CURRENT));
    Lookup lookup = load.getLookup(
            new CompletionFieldMapper(new Names("foo"), analyzer, analyzer, format, null, true, true, true),
            false);
    List<LookupResult> result = lookup.lookup("ge", false, 10);
    assertThat(result.get(0).key.toString(), equalTo("Generator - Foo Fighters"));
    assertThat(result.get(0).payload.utf8ToString(), equalTo("id:10"));
    dir.close();
}