Java SpanQuery.getSpans方法代码示例

import org.apache.lucene.search.spans.SpanQuery; //导入方法依赖的package包/类
private void getPayloads(Collection<byte []> payloads, SpanQuery query)
    throws IOException {
  Map<Term,TermContext> termContexts = new HashMap<>();
  TreeSet<Term> terms = new TreeSet<>();
  query.extractTerms(terms);
  for (Term term : terms) {
    termContexts.put(term, TermContext.build(context, term));
  }
  for (AtomicReaderContext atomicReaderContext : context.leaves()) {
    final Spans spans = query.getSpans(atomicReaderContext, atomicReaderContext.reader().getLiveDocs(), termContexts);
    while (spans.next() == true) {
      if (spans.isPayloadAvailable()) {
        Collection<byte[]> payload = spans.getPayload();
        for (byte [] bytes : payload) {
          payloads.add(bytes);
        }
      }
    }
  }
}
 

import org.apache.lucene.search.spans.SpanQuery; //导入方法依赖的package包/类
public SimpleSpans (SimpleSpanQuery simpleSpanQuery,
                    LeafReaderContext context, Bits acceptDocs,
                    Map<Term, TermContext> termContexts)
        throws IOException {
    this();
    query = simpleSpanQuery;
    collectPayloads = query.isCollectPayloads();
    // Get the enumeration of the two spans to match
    SpanQuery sq;
    if ((sq = simpleSpanQuery.getFirstClause()) != null)
        firstSpans = sq.getSpans(context, acceptDocs, termContexts);

    if ((sq = simpleSpanQuery.getSecondClause()) != null)
        secondSpans = sq.getSpans(context, acceptDocs, termContexts);

}
 

import org.apache.lucene.search.spans.SpanQuery; //导入方法依赖的package包/类
/**
 * Construct a new ClassSpans object.
 * 
 * @param operand
 *            An arbitrary nested {@link SpanQuery}.
 * @param context
 *            The {@link LeafReaderContext}.
 * @param acceptDocs
 *            Bit vector representing the documents
 *            to be searched in.
 * @param termContexts
 *            A map managing {@link TermState TermStates}.
 * @param number
 *            The identifying class number.
 */
public ClassSpans (SpanQuery operand, LeafReaderContext context,
                   Bits acceptDocs, Map<Term, TermContext> termContexts,
                   byte number)
        throws IOException {
    spans = operand.getSpans(context, acceptDocs, termContexts);

    // The number of the class
    this.number = number;

    // The current operand
    this.operand = operand;

    // The highlighted payload
    this.classedPayload = new ArrayList<byte[]>(3);

}
 

import org.apache.lucene.search.spans.SpanQuery; //导入方法依赖的package包/类
public static List<String> getSpanInfo (IndexReader reader, SpanQuery query)
        throws IOException {
    Map<Term, TermContext> termContexts = new HashMap<>();
    List<String> spanArray = new ArrayList<>();

    for (LeafReaderContext atomic : reader.leaves()) {
        Bits bitset = atomic.reader().getLiveDocs();
        // Spans spans = NearSpansOrdered();
        Spans spans = query.getSpans(atomic, bitset, termContexts);

        while (spans.next()) {
            StringBuffer payloadString = new StringBuffer();
            int docid = atomic.docBase + spans.doc();
            if (spans.isPayloadAvailable()) {
                for (byte[] payload : spans.getPayload()) {
                    /* retrieve payload for current matching span */

                    payloadString.append(byte2int(payload)).append(",");
                    payloadString.append(byte2int(payload, 2));
                    //			payloadString.append(byte2int(payload, 1));
                    payloadString.append(" (" + payload.length + ")");
                    payloadString.append(" | ");
                };
            };
            spanArray.add("Doc: " + docid + " with " + spans.start() + "-"
                    + spans.end() + " || " + payloadString.toString());
        };
    };
    return spanArray;
}