Package org.apache.lucene.util

Examples of org.apache.lucene.util.IntsRef

251
252
253
254
255
256
257
258
259
260
261
    meta.writeVInt(field.number);
    meta.writeByte(FST);
    meta.writeLong(data.getFilePointer());
    PositiveIntOutputs outputs = PositiveIntOutputs.getSingleton();
    Builder<Long> builder = new Builder<Long>(INPUT_TYPE.BYTE1, outputs);
    IntsRef scratch = new IntsRef();
    long ord = 0;
    for (BytesRef v : values) {
      builder.add(Util.toIntsRef(v, scratch), ord);
      ord++;
    }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
   
    System.out.println("  encode...");

    PositiveIntOutputs fstOutput = PositiveIntOutputs.getSingleton();
    Builder<Long> fstBuilder = new Builder<Long>(FST.INPUT_TYPE.BYTE2, 0, 0, true, true, Integer.MAX_VALUE, fstOutput, null, true, PackedInts.DEFAULT, true, 15);
    IntsRef scratch = new IntsRef();
    long ord = -1; // first ord will be 0
    String lastValue = null;

    // build tokeninfo dictionary
    for (String[] entry : lines) {
      int next = dictionary.put(entry);
       
      if(next == offset){
        System.out.println("Failed to process line: " + Arrays.toString(entry));
        continue;
      }
     
      String token = entry[0];
      if (!token.equals(lastValue)) {
        // new word to add to fst
        ord++;
        lastValue = token;
        scratch.grow(token.length());
        scratch.length = token.length();
        for (int i = 0; i < token.length(); i++) {
          scratch.ints[i] = (int) token.charAt(i);
        }
        fstBuilder.add(scratch, ord);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
      int[] ords = new int[maxDoc]; // let's assume one ordinal per-document as an initial size

      // this aggregator is limited to Integer.MAX_VALUE total ordinals.
      int totOrds = 0;
      final IntDecoder decoder = clp.createEncoder().createMatchingDecoder();
      final IntsRef values = new IntsRef(32);
      for (int docID = 0; docID < maxDoc; docID++) {
        offsets[docID] = totOrds;
        dv.get(docID, buf);
        if (buf.length > 0) {
          // this document has facets
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
   *
   * @return true iff the current candidate document has a non excluded required
   * node.
   */
  private boolean toNonExcludedNode() throws IOException {
    IntsRef reqNode = reqScorer.node(); // may be excluded
    IntsRef exclNode = exclScorer.node();

    int comparison;
    while ((comparison = NodeUtils.compare(reqNode, exclNode)) >= 0) {
      // if node equal, advance to next node in reqScorer
      if (comparison == 0 && !reqScorer.nextNode()) {
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
  @Test
  public void testIncompleteFrame() throws IOException {
    final BlockCompressor compressor = new AForBlockCompressor();

    final IntsRef input = new IntsRef(64);
    final BytesRef output = new BytesRef(compressor.maxCompressedSize(64));

    // fill first part with 1
    for (int i = 0; i < 33; i++) {
      input.ints[i] = 1;
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
    BytesRef docCompressedBuffer;
    BytesRef nodFreqCompressedBuffer;

    public DocsFreqBlockWriter() {
      // ensure that the input buffers has the minimum size required
      docBuffer = new IntsRef(this.getMinimumBufferSize(maxBlockSize, docCompressor.getWindowSize()));
      nodFreqBuffer = new IntsRef(this.getMinimumBufferSize(maxBlockSize, freqCompressor.getWindowSize()));

      // determine max size of compressed buffer to avoid overflow
      int size = docCompressor.maxCompressedSize(maxBlockSize);
      docCompressedBuffer = new BytesRef(size);
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
    return scorer.doc();
  }

  @Override
  public IntsRef node() {
    final IntsRef node = scorer.node();
    // resize node array only if node is not a sentinel value
    if (node.length > ancestorLevel &&
        node.ints[node.offset] != -1 &&
        node != DocsAndNodesIterator.NO_MORE_NOD) {
      node.length = ancestorLevel;
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
    BytesRef termFreqCompressedBuffer;

    public NodBlockWriter() {
      // ensure that the input buffers has the minimum size required
      // maxBlockSize is just use as a minimum initial capacity for the buffers
      nodLenBuffer = new IntsRef(this.getMinimumBufferSize(maxBlockSize, nodCompressor.getWindowSize()));
      nodBuffer = new IntsRef(this.getMinimumBufferSize(maxBlockSize, nodCompressor.getWindowSize()));
      termFreqBuffer = new IntsRef(this.getMinimumBufferSize(maxBlockSize, nodCompressor.getWindowSize()));

      // init of the compressed buffers
      nodLenCompressedBuffer = new BytesRef();
      nodCompressedBuffer = new BytesRef();
      termFreqCompressedBuffer = new BytesRef();
View Full Code Here
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
    // we always receive node ids in the payload
    assert payload != null;

    // decode payload
    sirenPayload.decode(payload);
    final IntsRef node = sirenPayload.getNode();

    // check if we received the same node
    // TODO: we pay the cost of decoding the node before testing the equality
    // we could instead directly compute the node hash based on the byte array
    final int nodeHash = node.hashCode();
    if (lastNodeHash != nodeHash) { // if different node
      // add term freq for previous node if not first payload.
      if (lastNodeHash != Long.MAX_VALUE) {
        this.addTermFreqInNode();
      }
View Full Code Here
462
463
464
465
466
467
468
469
470
471
472
      final int nodeFreq = postingsEnum.nodeFreqInDoc();
      docWriter.writeNodeFreq(nodeFreq);

      while (postingsEnum.nextNode()) {
        final IntsRef node = postingsEnum.node();
        nodWriter.write(node);

        final int termFreqInNode = postingsEnum.termFreqInNode();
        nodWriter.writeTermFreq(termFreqInNode);
View Full Code Here
TOP

Related Classes of org.apache.lucene.util.IntsRef

  • org.apache.lucene.analysis.charfilter.NormalizeCharMap$Builder
  • org.apache.lucene.analysis.hunspell.Dictionary
  • org.apache.lucene.analysis.hunspell.Stemmer
  • org.apache.lucene.analysis.hunspell.TestDictionary
  • org.apache.lucene.analysis.ja.dict.TestTokenInfoDictionary
  • org.apache.lucene.analysis.ja.dict.UserDictionary
  • org.apache.lucene.analysis.ja.util.TokenInfoDictionaryBuilder
  • org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter$Builder
  • org.apache.lucene.analysis.synonym.SynonymMap$Builder
  • org.apache.lucene.codecs.blockterms.VariableGapTermsIndexReader$FieldIndexData
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.