コード例 #1
0
      protected void processPayload(Similarity similarity) throws IOException {
        if (positions.isPayloadAvailable()) {
          payload = positions.getPayload(payload, 0);
          payloadScore =
              function.currentScore(
                  doc,
                  term.field(),
                  spans.start(),
                  spans.end(),
                  payloadsSeen,
                  payloadScore,
                  similarity.scorePayload(
                      doc,
                      term.field(),
                      spans.start(),
                      spans.end(),
                      payload,
                      0,
                      positions.getPayloadLength()));
          payloadsSeen++;

        } else {
          // zero out the payload?
        }
      }
コード例 #2
0
  @Override
  public boolean reload(String collectionName, int docNum) {
    if (collectionName == null) return false;

    CrescentCollectionHandler collectionHandler =
        SpringApplicationContext.getBean(
            "crescentCollectionHandler", CrescentCollectionHandler.class);
    CrescentCollection collection =
        collectionHandler.getCrescentCollections().getCrescentCollection(collectionName);

    if (collection == null) {
      logger.debug("doesn't Collection Info => {}", collectionName);
      return false;
    }

    List<String> fieldName = new ArrayList<String>();
    List<String> flag = new ArrayList<String>();
    List<String> norm = new ArrayList<String>();
    List<String> value = new ArrayList<String>();

    try {
      Directory directory = FSDirectory.open(new File(collection.getIndexingDirectory()));
      IndexReader reader = IndexReader.open(directory);

      Document document = null;
      try {
        document = reader.document(docNum);
      } catch (IllegalArgumentException e) {
        e.printStackTrace();
        return false;
      }

      String fName = null;
      for (Fieldable field : document.getFields()) {
        fName = field.name();
        fieldName.add(fName);
        flag.add(fieldFlag(field));
        if (reader.hasNorms(fName)) {
          norm.add(String.valueOf(Similarity.decodeNorm(reader.norms(fName)[docNum])));
        } else {
          norm.add("---");
        }
        value.add(field.stringValue());
      }

    } catch (IOException e) {
      e.printStackTrace();
      return false;
    }

    result.put("collection", collectionName);
    result.put("docNum", docNum);
    result.put("fieldName", fieldName);
    result.put("flag", flag);
    result.put("norm", norm);
    result.put("value", value);

    return true;
  }
コード例 #3
0
      @Override
      protected boolean setFreqCurrentDoc() throws IOException {
        if (!more) {
          return false;
        }
        doc = spans.doc();
        freq = 0.0f;
        payloadScore = 0;
        payloadsSeen = 0;
        Similarity similarity1 = getSimilarity();
        while (more && doc == spans.doc()) {
          int matchLength = spans.end() - spans.start();

          freq += similarity1.sloppyFreq(matchLength);
          processPayload(similarity1);

          more = spans.next(); // this moves positions to the next match in this document
        }
        return more || (freq != 0);
      }
コード例 #4
0
  /**
   * This method is no longer an official member of {@link Scorer}, but it is needed by SpanWeight
   * to build an explanation.
   */
  protected Explanation explain(final int doc) throws IOException {
    Explanation tfExplanation = new Explanation();

    int expDoc = advance(doc);

    float phraseFreq = (expDoc == doc) ? freq : 0.0f;
    tfExplanation.setValue(similarity.tf(phraseFreq));
    tfExplanation.setDescription("tf(phraseFreq=" + phraseFreq + ")");

    return tfExplanation;
  }
コード例 #5
0
 protected boolean setFreqCurrentDoc() throws IOException {
   if (!more) {
     return false;
   }
   doc = spans.doc();
   freq = 0.0f;
   do {
     int matchLength = spans.end() - spans.start();
     freq += similarity.sloppyFreq(matchLength);
     more = spans.next();
   } while (more && (doc == spans.doc()));
   return true;
 }
コード例 #6
0
    public Explanation explain(IndexReader reader, int doc) throws IOException {
      ComplexExplanation result = new ComplexExplanation();
      result.setDescription("weight(" + getQuery() + " in " + doc + "), product of:");

      Explanation idfExpl = new Explanation(idf, "idf(docFreq=" + reader.docFreq(term) + ")");

      // explain query weight
      Explanation queryExpl = new Explanation();
      queryExpl.setDescription("queryWeight(" + getQuery() + "), product of:");

      Explanation boostExpl = new Explanation(getBoost(), "boost");
      if (getBoost() != 1.0f) queryExpl.addDetail(boostExpl);
      queryExpl.addDetail(idfExpl);

      Explanation queryNormExpl = new Explanation(queryNorm, "queryNorm");
      queryExpl.addDetail(queryNormExpl);

      queryExpl.setValue(boostExpl.getValue() * idfExpl.getValue() * queryNormExpl.getValue());

      result.addDetail(queryExpl);

      // explain field weight
      String field = term.field();
      ComplexExplanation fieldExpl = new ComplexExplanation();
      fieldExpl.setDescription("fieldWeight(" + term + " in " + doc + "), product of:");

      Explanation tfExpl = scorer(reader).explain(doc);
      fieldExpl.addDetail(tfExpl);
      fieldExpl.addDetail(idfExpl);

      Explanation fieldNormExpl = new Explanation();
      byte[] fieldNorms = reader.norms(field);
      float fieldNorm = fieldNorms != null ? Similarity.decodeNorm(fieldNorms[doc]) : 0.0f;
      fieldNormExpl.setValue(fieldNorm);
      fieldNormExpl.setDescription("fieldNorm(field=" + field + ", doc=" + doc + ")");
      fieldExpl.addDetail(fieldNormExpl);

      fieldExpl.setMatch(Boolean.valueOf(tfExpl.isMatch()));
      fieldExpl.setValue(tfExpl.getValue() * idfExpl.getValue() * fieldNormExpl.getValue());

      result.addDetail(fieldExpl);
      result.setMatch(fieldExpl.getMatch());

      // combine them
      result.setValue(queryExpl.getValue() * fieldExpl.getValue());

      if (queryExpl.getValue() == 1.0f) return fieldExpl;

      return result;
    }
コード例 #7
0
 @Override
 public synchronized void norms(String field, byte[] result, int offset) throws IOException {
   ensureOpen();
   byte[] bytes = normsCache.get(field);
   if (bytes == null && !hasNorms(field)) {
     Arrays.fill(result, offset, result.length, Similarity.getDefault().encodeNormValue(1.0f));
   } else if (bytes != null) { // cache hit
     System.arraycopy(bytes, 0, result, offset, maxDoc());
   } else {
     for (int i = 0; i < subReaders.length; i++) { // read from segments
       subReaders[i].norms(field, result, offset + starts[i]);
     }
   }
 }
コード例 #8
0
 @Override
 public float score() throws IOException {
   float raw = similarity.tf(freq) * value; // raw score
   return norms == null ? raw : raw * similarity.decodeNormValue(norms[doc]); // normalize
 }
コード例 #9
0
 public MyWeight(Searcher searcher) throws IOException {
   this.similarity = getSimilarity(searcher);
   idf = similarity.idf(term, searcher);
 }
コード例 #10
0
ファイル: TFIDF.java プロジェクト: sparklezzz/BaiduContest
 @Override
 public double calculate(int tf, int df, int length, int numDocs) {
   // ignore length
   return sim.tf(tf) * sim.idf(df, numDocs);
 }