Package org.apache.lucene.util

Examples of org.apache.lucene.util.CharsRef$UTF16SortedAsUTF8Comparator

80
81
82
83
84
85
86
87
88
89
90
    }
  }
  private CharsRef parseSynonym(String line, CharsRef reuse) throws IOException {
    if (reuse == null) {
      reuse = new CharsRef(8);
    }
   
    int start = line.indexOf('\'')+1;
    int end = line.lastIndexOf('\'');
   
View Full Code Here
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
      }

      final byte[] spare = new byte[5];
     
      Set<CharsRef> keys = workingSet.keySet();
      CharsRef sortedKeys[] = keys.toArray(new CharsRef[keys.size()]);
      Arrays.sort(sortedKeys, CharsRef.getUTF16SortedAsUTF8Comparator());

      final IntsRef scratchIntsRef = new IntsRef();
     
      //System.out.println("fmap.build");
      for (int keyIdx = 0; keyIdx < sortedKeys.length; keyIdx++) {
        CharsRef input = sortedKeys[keyIdx];
        MapEntry output = workingSet.get(input);

        int numEntries = output.ords.size();
        // output size, assume the worst case
        int estimatedSize = 5 + numEntries * 5; // numEntries + one ord for each entry
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
        this.keepOriginalWord = keepOriginalWord;
    }

    public static SynonymMap buildAcronymsMergingMap() throws IOException {
        SynonymMap.Builder synonymMap = new SynonymMap.Builder(true);
        synonymMap.add(new CharsRef("אף על פי כן"), new CharsRef("אעפ\"כ"), false);
        synonymMap.add(new CharsRef("אף על פי"), new CharsRef("אע\"פ"), false);
        synonymMap.add(new CharsRef("כמו כן"), new CharsRef("כמו\"כ"), false);
        synonymMap.add(new CharsRef("על ידי"), new CharsRef("ע\"י"), false);
        synonymMap.add(new CharsRef("על פי"), new CharsRef("ע\"פ"), false);
        synonymMap.add(new CharsRef("כל כך"), new CharsRef("כ\"כ"), false);
        synonymMap.add(new CharsRef("בדרך כלל"), new CharsRef("בד\"כ"), false);
        synonymMap.add(new CharsRef("תל אביב"), new CharsRef("ת\"א"), false);
        return synonymMap.build();
    }
View Full Code Here
701
702
703
704
705
706
707
708
709
710
711
    final BytesRef utf8Key = new BytesRef(key);
    try {

      Automaton lookupAutomaton = toLookupAutomaton(key);

      final CharsRef spare = new CharsRef();

      //System.out.println("  now intersect exactFirst=" + exactFirst);
   
      // Intersect automaton w/ suggest wFST and get all
      // prefix starting nodes & their outputs:
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
      tfit = new UnsortedTermFreqIteratorWrapper(tfit);
    }
    trie = new JaspellTernarySearchTrie();
    trie.setMatchAlmostDiff(editDistance);
    BytesRef spare;
    final CharsRef charsSpare = new CharsRef();

    while ((spare = tfit.next()) != null) {
      final long weight = tfit.weight();
      if (spare.length == 0) {
        continue;
      }
      charsSpare.grow(spare.length);
      UnicodeUtil.UTF8toUTF16(spare.bytes, spare.offset, spare.length, charsSpare);
      trie.put(charsSpare.toString(), Long.valueOf(weight));
    }
  }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
    int maxCnt = Math.min(num, list.size());
    if (onlyMorePopular) {
      LookupPriorityQueue queue = new LookupPriorityQueue(num);
      for (String s : list) {
        long freq = ((Number)trie.get(s)).longValue();
        queue.insertWithOverflow(new LookupResult(new CharsRef(s), freq));
      }
      for (LookupResult lr : queue.getResults()) {
        res.add(lr);
      }
    } else {
      for (int i = 0; i < maxCnt; i++) {
        String s = list.get(i);
        long freq = ((Number)trie.get(s)).longValue();
        res.add(new LookupResult(new CharsRef(s), freq));
      }     
    }
    return res;
  }
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
    if (prefixOutput == null) {
      return Collections.<LookupResult>emptyList();
    }
   
    List<LookupResult> results = new ArrayList<LookupResult>(num);
    CharsRef spare = new CharsRef();
    if (exactFirst && arc.isFinal()) {
      spare.grow(scratch.length);
      UnicodeUtil.UTF8toUTF16(scratch, spare);
      results.add(new LookupResult(spare.toString(), decodeWeight(prefixOutput + arc.nextFinalOutput)));
      if (--num == 0) {
        return results; // that was quick
      }
    }

    // complete top-N
    MinResult<Long> completions[] = null;
    try {
      completions = Util.shortestPaths(fst, arc, prefixOutput, weightComparator, num, !exactFirst);
    } catch (IOException bogus) {
      throw new RuntimeException(bogus);
    }
   
    BytesRef suffix = new BytesRef(8);
    for (MinResult<Long> completion : completions) {
      scratch.length = prefixLength;
      // append suffix
      Util.toBytesRef(completion.input, suffix);
      scratch.append(suffix);
      spare.grow(scratch.length);
      UnicodeUtil.UTF8toUTF16(scratch, spare);
      results.add(new LookupResult(spare.toString(), decodeWeight(completion.output)));
    }
    return results;
  }
View Full Code Here
675
676
677
678
679
680
681
682
683
684
685
    final BytesRef utf8Key = new BytesRef(key);
    try {

      Automaton lookupAutomaton = toLookupAutomaton(key);

      final CharsRef spare = new CharsRef();

      //System.out.println("  now intersect exactFirst=" + exactFirst);
   
      // Intersect automaton w/ suggest wFST and get all
      // prefix starting nodes & their outputs:
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
  @Override
  public Bits readLiveDocs(Directory dir, SegmentInfoPerCommit info, IOContext context) throws IOException {
    assert info.hasDeletions();
    BytesRef scratch = new BytesRef();
    CharsRef scratchUTF16 = new CharsRef();
   
    String fileName = IndexFileNames.fileNameFromGeneration(info.info.name, LIVEDOCS_EXTENSION, info.getDelGen());
    IndexInput in = null;
    boolean success = false;
    try {
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
    if (vector == null) {
      // null snippet
      return;
    }

    final CharsRef spare = new CharsRef();
    final TermsEnum termsEnum = vector.iterator(null);
    DocsAndPositionsEnum dpEnum = null;
    BytesRef text;
   
    int numDocs = reader.maxDoc();
   
    while ((text = termsEnum.next()) != null) {
      UnicodeUtil.UTF8toUTF16(text, spare);
      final String term = spare.toString();
      if (!termSet.contains(term)) {
        continue;
      }
      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      if (dpEnum == null) {
View Full Code Here
TOP

Related Classes of org.apache.lucene.util.CharsRef$UTF16SortedAsUTF8Comparator

  • org.apache.lucene.analysis.charfilter.MappingCharFilter
  • org.apache.lucene.analysis.charfilter.NormalizeCharMap$Builder
  • org.apache.lucene.analysis.hebrew.MorphAnalyzer
  • org.apache.lucene.analysis.hunspell.Dictionary
  • org.apache.lucene.analysis.hunspell.HunspellStemFilter
  • org.apache.lucene.analysis.hunspell.Stemmer
  • org.apache.lucene.analysis.hunspell.TestDictionary
  • org.apache.lucene.analysis.miscellaneous.TestLimitTokenPositionFilter
  • org.apache.lucene.analysis.miscellaneous.TestRemoveDuplicatesTokenFilter
  • org.apache.lucene.analysis.nl.DutchAnalyzer
    • 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.