Example usage for org.apache.lucene.index Terms hasPayloads

List of usage examples for org.apache.lucene.index Terms hasPayloads

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. Terms
  6. hasPayloads

Introduction

In this page you can find the example usage for org.apache.lucene.index Terms hasPayloads.

Prototype

public abstract boolean hasPayloads();

Source Link

Document

Returns true if documents in this field store payloads.

Usage

From source file:org.apache.blur.lucene.warmup.IndexWarmup.java

License:Apache License

public Map<String, List<IndexTracerResult>> sampleIndex(AtomicReader atomicReader, String context)
        throws IOException {
    Map<String, List<IndexTracerResult>> results = new HashMap<String, List<IndexTracerResult>>();
    if (atomicReader instanceof SegmentReader) {
        SegmentReader segmentReader = (SegmentReader) atomicReader;
        Directory directory = segmentReader.directory();
        if (!(directory instanceof TraceableDirectory)) {
            LOG.info("Context [{1}] cannot warmup directory [{0}] needs to be a TraceableDirectory.", directory,
                    context);//w  w w  .  j av  a 2 s . c o m
            return results;
        }
        IndexTracer tracer = new IndexTracer((TraceableDirectory) directory, _maxSampleSize);
        String fileName = getSampleFileName(segmentReader.getSegmentName());
        List<IndexTracerResult> segmentTraces = new ArrayList<IndexTracerResult>();
        if (directory.fileExists(fileName)) {
            IndexInput input = directory.openInput(fileName, IOContext.READONCE);
            segmentTraces = read(input);
            input.close();
        } else {
            Fields fields = atomicReader.fields();
            for (String field : fields) {
                LOG.debug("Context [{1}] sampling field [{0}].", field, context);
                Terms terms = fields.terms(field);
                boolean hasOffsets = terms.hasOffsets();
                boolean hasPayloads = terms.hasPayloads();
                boolean hasPositions = terms.hasPositions();

                tracer.initTrace(segmentReader, field, hasPositions, hasPayloads, hasOffsets);
                IndexTracerResult result = tracer.runTrace(terms);
                segmentTraces.add(result);
            }
            if (_isClosed.get()) {
                LOG.info("Context [{0}] index closed", context);
                return null;
            }
            IndexOutput output = directory.createOutput(fileName, IOContext.DEFAULT);
            write(segmentTraces, output);
            output.close();
        }
        results.put(segmentReader.getSegmentName(), segmentTraces);
    }
    return results;
}

From source file:org.apache.solr.handler.component.AlfrescoSolrHighlighter.java

License:Open Source License

/**
 * Return a {@link org.apache.lucene.search.highlight.QueryScorer} suitable
 * for this Query and field./*from w  w w. j  a v  a 2  s. c  o  m*/
 * 
 * @param query
 *            The current query
 * @param tokenStream
 *            document text CachingTokenStream
 * @param requestFieldname
 *            The name of the field
 * @param request
 *            The SolrQueryRequest
 */
@Override
protected QueryScorer getSpanQueryScorer(Query query, String requestFieldname, TokenStream tokenStream,
        SolrQueryRequest request) {
    String schemaFieldName = AlfrescoSolrDataModel.getInstance().mapProperty(requestFieldname,
            FieldUse.HIGHLIGHT, request);
    QueryScorer scorer = new QueryScorer(query,
            request.getParams().getFieldBool(requestFieldname, HighlightParams.FIELD_MATCH, false)
                    ? schemaFieldName
                    : null);
    scorer.setExpandMultiTermQuery(request.getParams().getBool(HighlightParams.HIGHLIGHT_MULTI_TERM, true));

    boolean defaultPayloads = true;// overwritten below
    try {
        // It'd be nice to know if payloads are on the tokenStream but the
        // presence of the attribute isn't a good
        // indicator.
        final Terms terms = request.getSearcher().getSlowAtomicReader().fields().terms(schemaFieldName);
        if (terms != null) {
            defaultPayloads = terms.hasPayloads();
        }
    } catch (IOException e) {
        log.error("Couldn't check for existence of payloads", e);
    }
    scorer.setUsePayloads(
            request.getParams().getFieldBool(requestFieldname, HighlightParams.PAYLOADS, defaultPayloads));
    return scorer;
}

From source file:org.codelibs.elasticsearch.common.lucene.all.AllTermQuery.java

License:Apache License

@Override
public Query rewrite(IndexReader reader) throws IOException {
    Query rewritten = super.rewrite(reader);
    if (rewritten != this) {
        return rewritten;
    }/*from  w  ww  . j  a v  a2  s .  com*/
    boolean fieldExists = false;
    boolean hasPayloads = false;
    for (LeafReaderContext context : reader.leaves()) {
        final Terms terms = context.reader().terms(term.field());
        if (terms != null) {
            fieldExists = true;
            if (terms.hasPayloads()) {
                hasPayloads = true;
                break;
            }
        }
    }
    if (fieldExists == false) {
        return new MatchNoDocsQuery();
    }
    if (hasPayloads == false) {
        return new TermQuery(term);
    }
    return this;
}

From source file:org.elasticsearch.action.termvector.TermVectorResponse.java

License:Apache License

private void buildValues(XContentBuilder builder, Terms curTerms, int termFreq) throws IOException {
    if (!(curTerms.hasPayloads() || curTerms.hasOffsets() || curTerms.hasPositions())) {
        return;//from w w  w. j  a  va2s  . c o m
    }

    builder.startArray(FieldStrings.TOKENS);
    for (int i = 0; i < termFreq; i++) {
        builder.startObject();
        if (curTerms.hasPositions()) {
            builder.field(FieldStrings.POS, curentPositions[i]);
        }
        if (curTerms.hasOffsets()) {
            builder.field(FieldStrings.START_OFFSET, currentStartOffset[i]);
            builder.field(FieldStrings.END_OFFSET, currentEndOffset[i]);
        }
        if (curTerms.hasPayloads() && (currentPayloads[i].length() > 0)) {
            builder.field(FieldStrings.PAYLOAD, currentPayloads[i]);
        }
        builder.endObject();
    }
    builder.endArray();

}

From source file:org.elasticsearch.action.termvector.TermVectorResponse.java

License:Apache License

private void initValues(Terms curTerms, DocsAndPositionsEnum posEnum, int termFreq) throws IOException {
    for (int j = 0; j < termFreq; j++) {
        int nextPos = posEnum.nextPosition();
        if (curTerms.hasPositions()) {
            curentPositions[j] = nextPos;
        }//from   w w w. j a  v a2 s .co m
        if (curTerms.hasOffsets()) {
            currentStartOffset[j] = posEnum.startOffset();
            currentEndOffset[j] = posEnum.endOffset();
        }
        if (curTerms.hasPayloads()) {
            BytesRef curPayload = posEnum.getPayload();
            if (curPayload != null) {
                currentPayloads[j] = new BytesArray(curPayload.bytes, 0, curPayload.length);
            } else {
                currentPayloads[j] = null;
            }

        }
    }
}

From source file:org.elasticsearch.action.termvector.TermVectorResponse.java

License:Apache License

private void initMemory(Terms curTerms, int termFreq) {
    // init memory for performance reasons
    if (curTerms.hasPositions()) {
        curentPositions = ArrayUtil.grow(curentPositions, termFreq);
    }/* w  ww . j  av a 2 s . c o m*/
    if (curTerms.hasOffsets()) {
        currentStartOffset = ArrayUtil.grow(currentStartOffset, termFreq);
        currentEndOffset = ArrayUtil.grow(currentEndOffset, termFreq);
    }
    if (curTerms.hasPayloads()) {
        currentPayloads = new BytesArray[termFreq];
    }
}

From source file:org.elasticsearch.action.termvector.TermVectorWriter.java

License:Apache License

void setFields(Fields termVectorsByField, Set<String> selectedFields, EnumSet<Flag> flags,
        Fields topLevelFields) throws IOException {

    int numFieldsWritten = 0;
    TermsEnum iterator = null;//from w  w  w  .j  a  v  a2s . c o m
    DocsAndPositionsEnum docsAndPosEnum = null;
    DocsEnum docsEnum = null;
    TermsEnum topLevelIterator = null;
    for (String field : termVectorsByField) {
        if ((selectedFields != null) && (!selectedFields.contains(field))) {
            continue;
        }

        Terms fieldTermVector = termVectorsByField.terms(field);
        Terms topLevelTerms = topLevelFields.terms(field);

        topLevelIterator = topLevelTerms.iterator(topLevelIterator);
        boolean positions = flags.contains(Flag.Positions) && fieldTermVector.hasPositions();
        boolean offsets = flags.contains(Flag.Offsets) && fieldTermVector.hasOffsets();
        boolean payloads = flags.contains(Flag.Payloads) && fieldTermVector.hasPayloads();
        startField(field, fieldTermVector.size(), positions, offsets, payloads);
        if (flags.contains(Flag.FieldStatistics)) {
            writeFieldStatistics(topLevelTerms);
        }
        iterator = fieldTermVector.iterator(iterator);
        final boolean useDocsAndPos = positions || offsets || payloads;
        while (iterator.next() != null) { // iterate all terms of the
            // current field
            // get the doc frequency
            BytesRef term = iterator.term();
            boolean foundTerm = topLevelIterator.seekExact(term);
            assert (foundTerm);
            startTerm(term);
            if (flags.contains(Flag.TermStatistics)) {
                writeTermStatistics(topLevelIterator);
            }
            if (useDocsAndPos) {
                // given we have pos or offsets
                docsAndPosEnum = writeTermWithDocsAndPos(iterator, docsAndPosEnum, positions, offsets,
                        payloads);
            } else {
                // if we do not have the positions stored, we need to
                // get the frequency from a DocsEnum.
                docsEnum = writeTermWithDocsOnly(iterator, docsEnum);
            }
        }
        numFieldsWritten++;
    }
    response.setTermVectorField(output);
    response.setHeader(writeHeader(numFieldsWritten, flags.contains(Flag.TermStatistics),
            flags.contains(Flag.FieldStatistics)));
}

From source file:org.elasticsearch.action.termvectors.TermVectorsResponse.java

License:Apache License

private void buildValues(XContentBuilder builder, Terms curTerms, int termFreq) throws IOException {
    if (!(curTerms.hasPayloads() || curTerms.hasOffsets() || curTerms.hasPositions())) {
        return;//from  ww  w  .  j a  v a 2s .c  o m
    }

    builder.startArray(FieldStrings.TOKENS);
    for (int i = 0; i < termFreq; i++) {
        builder.startObject();
        if (curTerms.hasPositions()) {
            builder.field(FieldStrings.POS, currentPositions[i]);
        }
        if (curTerms.hasOffsets()) {
            builder.field(FieldStrings.START_OFFSET, currentStartOffset[i]);
            builder.field(FieldStrings.END_OFFSET, currentEndOffset[i]);
        }
        if (curTerms.hasPayloads() && (currentPayloads[i].length() > 0)) {
            builder.field(FieldStrings.PAYLOAD, currentPayloads[i]);
        }
        builder.endObject();
    }
    builder.endArray();
}

From source file:org.elasticsearch.action.termvectors.TermVectorsResponse.java

License:Apache License

private void initValues(Terms curTerms, PostingsEnum posEnum, int termFreq) throws IOException {
    for (int j = 0; j < termFreq; j++) {
        int nextPos = posEnum.nextPosition();
        if (curTerms.hasPositions()) {
            currentPositions[j] = nextPos;
        }/*from   w ww.j  a  v  a  2  s  . c o m*/
        if (curTerms.hasOffsets()) {
            currentStartOffset[j] = posEnum.startOffset();
            currentEndOffset[j] = posEnum.endOffset();
        }
        if (curTerms.hasPayloads()) {
            BytesRef curPayload = posEnum.getPayload();
            if (curPayload != null) {
                currentPayloads[j] = new BytesArray(curPayload.bytes, 0, curPayload.length);
            } else {
                currentPayloads[j] = null;
            }
        }
    }
}

From source file:org.elasticsearch.action.termvectors.TermVectorsResponse.java

License:Apache License

private void initMemory(Terms curTerms, int termFreq) {
    // init memory for performance reasons
    if (curTerms.hasPositions()) {
        currentPositions = ArrayUtil.grow(currentPositions, termFreq);
    }/* w  w  w  . j  a  v  a  2  s .co  m*/
    if (curTerms.hasOffsets()) {
        currentStartOffset = ArrayUtil.grow(currentStartOffset, termFreq);
        currentEndOffset = ArrayUtil.grow(currentEndOffset, termFreq);
    }
    if (curTerms.hasPayloads()) {
        currentPayloads = new BytesArray[termFreq];
    }
}