Package net.paoding.analysis.dictionary

Examples of net.paoding.analysis.dictionary.Dictionary

203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
  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()) {
          hit.getWord().setNoiseWord();
        }
      }
      Dictionary noiseCharactorsDic = getNoiseCharactorsDictionary();
      for (int i = 0; i < noiseCharactorsDic.size(); i++) {
        Hit hit = vocabularyDictionary.search(noiseCharactorsDic.get(i), 0, noiseCharactorsDic.get(i).length());
        if (hit.isHit()) {
          hit.getWord().setNoiseCharactor();
        }
      }
     
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
   
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/most-words-mode");
    compiledDicHomeFile.mkdirs();
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    compileVocabulary(vocabularyDictionary, knife, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);
   
    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/most-words-mode/.metadata");
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/sorting");
    compiledDicHomeFile.mkdirs();
   
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    sortCompile(vocabularyDictionary, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);

    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/sorting/.metadata");
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
   
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/most-words-mode");
    compiledDicHomeFile.mkdirs();
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    compileVocabulary(vocabularyDictionary, knife, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);
   
    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/most-words-mode/.metadata");
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/sorting");
    compiledDicHomeFile.mkdirs();
   
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    sortCompile(vocabularyDictionary, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);

    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/sorting/.metadata");
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
  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()) {
          hit.getWord().setNoiseWord();
        }
      }
      Dictionary noiseCharactorsDic = getNoiseCharactorsDictionary();
      for (int i = 0; i < noiseCharactorsDic.size(); i++) {
        Hit hit = vocabularyDictionary.search(noiseCharactorsDic.get(i), 0, noiseCharactorsDic.get(i).length());
        if (hit.isHit()) {
          hit.getWord().setNoiseCharactor();
        }
      }
     
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
  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()) {
          hit.getWord().setNoiseWord();
        }
      }
      Dictionary noiseCharactorsDic = getNoiseCharactorsDictionary();
      for (int i = 0; i < noiseCharactorsDic.size(); i++) {
        Hit hit = vocabularyDictionary.search(noiseCharactorsDic.get(i), 0, noiseCharactorsDic.get(i).length());
        if (hit.isHit()) {
          hit.getWord().setNoiseCharactor();
        }
      }
     
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
   
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/most-words-mode");
    compiledDicHomeFile.mkdirs();
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    compileVocabulary(vocabularyDictionary, knife, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);
   
    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/most-words-mode/.metadata");
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    File dicHomeFile = new File(dicHome);
    File compiledDicHomeFile = new File(dicHomeFile, ".compiled/sorting");
    compiledDicHomeFile.mkdirs();
   
    //
    Dictionary vocabularyDictionary = dictionaries.getVocabularyDictionary();
    File vocabularyFile = new File(compiledDicHomeFile, "vocabulary.dic.compiled");
    sortCompile(vocabularyDictionary, vocabularyFile, charsetName);

    //
    Dictionary noiseCharactorsDictionary = dictionaries.getNoiseCharactorsDictionary();
    File noiseCharactorsDictionaryFile = new File(compiledDicHomeFile, noiseCharactor + ".dic.compiled");
    sortCompile(noiseCharactorsDictionary, noiseCharactorsDictionaryFile, charsetName);
    //
    Dictionary noiseWordsDictionary = dictionaries.getNoiseWordsDictionary();
    File noiseWordsDictionaryFile = new File(compiledDicHomeFile, noiseWord + ".dic.compiled");
    sortCompile(noiseWordsDictionary, noiseWordsDictionaryFile, charsetName);
    //
    Dictionary unitsDictionary = dictionaries.getUnitsDictionary();
    File unitsDictionaryFile = new File(compiledDicHomeFile, unit + ".dic.compiled");
    sortCompile(unitsDictionary, unitsDictionaryFile, charsetName);
    //
    Dictionary confucianFamilyDictionary = dictionaries.getConfucianFamilyNamesDictionary();
    File confucianFamilyDictionaryFile = new File(compiledDicHomeFile, confucianFamilyName + ".dic.compiled");
    sortCompile(confucianFamilyDictionary, confucianFamilyDictionaryFile, charsetName);
    //
    Dictionary combinatoricsDictionary = dictionaries.getCombinatoricsDictionary();
    File combinatoricsDictionaryFile = new File(compiledDicHomeFile, combinatorics + ".dic.compiled");
    sortCompile(combinatoricsDictionary, combinatoricsDictionaryFile, charsetName);

    //
    File compliedMetadataFile = new File(dicHomeFile, ".compiled/sorting/.metadata");
View Full Code Here
TOP

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

  • net.paoding.analysis.analyzer.impl.MostWordsModeDictionariesCompiler
  • net.paoding.analysis.analyzer.impl.SortingDictionariesCompiler
  • net.paoding.analysis.knife.FileDictionaries
    • 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.