Examples of net.paoding.analysis.dictionary.HashBinaryDictionary

net.paoding.analysis.dictionary.HashBinaryDictionary
Dictionary的散列+二叉查找实现。
用于对大数量的，且头字符相同的字符串较多的情况，e.g汉字词语字典。在这种情况下，检索速度将比二叉字典更快。
HashBinaryDictionary以一组已经排序的词语为输入，所有头字符相同的词语划为一个集合作为分字典(使用BinaryDictionary实现)。查找词语时，先根据第一个字符找得分词典(BinaryDictionary实现)，再从该分词典中定位该词语。
@author Zhiliang Wang [qieqie.wang@gmail.com] @see BinaryDictionary @since 1.0

   * @return
   */
  public synchronized Dictionary getVocabularyDictionary() {
    if (vocabularyDictionary == null) {
      // 大概有5639个字有词语，故取0x2fff=x^13>8000>8000*0.75=6000>5639
      vocabularyDictionary = new HashBinaryDictionary(
          getVocabularyWords(), 0x2fff, 0.75f);
      Dictionary noiseWordsDic = getNoiseWordsDictionary();
      for (int i = 0; i < noiseWordsDic.size(); i++) {
        Hit hit = vocabularyDictionary.search(noiseWordsDic.get(i), 0, noiseWordsDic.get(i).length());
        if (hit.isHit()) {

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getNoiseCharactorsDictionary() {
    if (noiseCharactorsDictionary == null) {
      noiseCharactorsDictionary = new HashBinaryDictionary(
          getNoiseCharactors(), 256, 0.75f);
    }
    return noiseCharactorsDictionary;
  }

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getUnitsDictionary() {
    if (unitsDictionary == null) {
      unitsDictionary = new HashBinaryDictionary(getUnits(), 1024, 0.75f);
    }
    return unitsDictionary;
  }

View Full Code Here

   * @return
   */
  public synchronized Dictionary getVocabularyDictionary() {
    if (vocabularyDictionary == null) {
      // 大概有5639个字有词语，故取0x2fff=x^13>8000>8000*0.75=6000>5639
      vocabularyDictionary = new HashBinaryDictionary(
          getVocabularyWords(), 0x2fff, 0.75f);
    }
    return vocabularyDictionary;
  }

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getNoiseCharactorsDictionary() {
    if (noiseCharactorsDictionary == null) {
      noiseCharactorsDictionary = new HashBinaryDictionary(
          getNoiseCharactors(), 256, 0.75f);
    }
    return noiseCharactorsDictionary;
  }

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getUnitsDictionary() {
    if (unitsDictionary == null) {
      unitsDictionary = new HashBinaryDictionary(getUnits(), 1024, 0.75f);
    }
    return unitsDictionary;
  }

View Full Code Here

   * @return
   */
  public synchronized Dictionary getVocabularyDictionary() {
    if (vocabularyDictionary == null) {
      // 大概有5639个字有词语，故取0x2fff=x^13>8000>8000*0.75=6000>5639
      vocabularyDictionary = new HashBinaryDictionary(
          getVocabularyWords(), 0x2fff, 0.75f);
    }
    return vocabularyDictionary;
  }

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getNoiseCharactorsDictionary() {
    if (noiseCharactorsDictionary == null) {
      noiseCharactorsDictionary = new HashBinaryDictionary(
          getNoiseCharactors(), 256, 0.75f);
    }
    return noiseCharactorsDictionary;
  }

View Full Code Here

   * 
   * @return
   */
  public synchronized Dictionary getUnitsDictionary() {
    if (unitsDictionary == null) {
      unitsDictionary = new HashBinaryDictionary(getUnits(), 1024, 0.75f);
    }
    return unitsDictionary;
  }

View Full Code Here

   * @return
   */
  public synchronized Dictionary getVocabularyDictionary() {
    if (vocabularyDictionary == null) {
      // 大概有5639个字有词语，故取0x2fff=x^13>8000>8000*0.75=6000>5639
      vocabularyDictionary = new HashBinaryDictionary(
          getVocabularyWords(), 0x2fff, 0.75f);
      Dictionary noiseWordsDic = getNoiseWordsDictionary();
      for (int i = 0; i < noiseWordsDic.size(); i++) {
        Hit hit = vocabularyDictionary.search(noiseWordsDic.get(i), 0, noiseWordsDic.get(i).length());
        if (hit.isHit()) {

View Full Code Here

0 1

TOP

Related Classes of net.paoding.analysis.dictionary.HashBinaryDictionary

net.paoding.analysis.analyzer.impl.CompiledFileDictionaries

net.paoding.analysis.knife.FileDictionaries

java.util.HashMap

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.