Examples of SnowballStemmer

Examples of org.tartarus.snowball.SnowballStemmer

101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
    for (String stemmerLanguage : stemmers) {
      System.out.println(stemmerLanguage);

      Class<?> stemClass = Class.forName("org.tartarus.snowball.ext."
            + stemmerLanguage + "Stemmer");
      SnowballStemmer stemmer = (SnowballStemmer) stemClass
            .newInstance();

      for (String stopWord : stopList) {
        StringBuilder sb = new StringBuilder();

        for (String part : stopWord.split(" ")) {
          if (sb.length() > 0)
            sb.append(" ");
          stemmer.setCurrent(part);
          stemmer.stem();
          sb.append(stemmer.getCurrent());
        }

        stopSet.add(sb.toString());
      }
    }
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer

48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        fields.set(0, fields.get(0) + fields.get(1));
       
        String text = fields.get(3).toLowerCase();
       
        loadStopWords();
      SnowballStemmer stemmer = new org.tartarus.snowball.ext.englishStemmer();
     
      for(int i=0; i < stopWords.size(); i++)
      {
        text = text.replaceAll("[\\s]"+stopWords.get(i)+"[\\s]", " ");
      }
     
      Pattern p = Pattern.compile("[^a-zA-Z]+");
      String [] words = p.split(text);
      text = "";
      for(int i=0; i < words.length; i++)
      {
        if(words[i].length() < 3)
        {
          continue;
        }
       
        stemmer.setCurrent(words[i]);
        stemmer.stem();
        String stemmed = stemmer.getCurrent();
       
        if(!loadedWords.contains(stemmed))
        {
          continue;
        }
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer

39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
   
    int[] wordCounter = new int[loadedWords.size()];
   
    String text = fields.get(3).toLowerCase();
    loadStopWords();
    SnowballStemmer stemmer = new org.tartarus.snowball.ext.englishStemmer();
   
    for(int i=0; i < stopWords.size(); i++)
    {
      text = text.replaceAll("[\\s]"+stopWords.get(i)+"[\\s]", " ");
    }
   
    Pattern p = Pattern.compile("[^a-zA-Z]+");
    String [] words = p.split(text);
   
    for(int i=0; i < words.length; i++)
    {
      if(words[i].length() < 3)
      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
      if(!loadedWords.contains(stemmed))
      {
        continue;
      }
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer

26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
  public Object[] getValues(Vector<String> fields,
      HashMap<String, Boolean> hashMap)
  {
    String text = fields.get(3).toLowerCase();
    loadStopWords();
    SnowballStemmer stemmer = new org.tartarus.snowball.ext.englishStemmer();
   
    for(int i=0; i < stopWords.size(); i++)
    {
      text = text.replaceAll("[\\s]"+stopWords.get(i)+"[\\s]", " ");
    }
   
    Pattern p = Pattern.compile("[^a-zA-Z]+");
    String [] words = p.split(text);
    text = "";
    int no_words = 0;
    for(int i=0; i < words.length; i++)
    {
      if(words[i].length() < 3)
      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
     
      if(text.indexOf(stemmed) >= 0)
      {
        continue;
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer

31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
  public Object[] getValues(Vector<String> fields,
      HashMap<String, Boolean> hashMap)
  {
    String text = fields.get(3).toLowerCase();
    loadStopWords();
    SnowballStemmer stemmer = new org.tartarus.snowball.ext.englishStemmer();
   
    for(int i=0; i < stopWords.size(); i++)
    {
      text = text.replaceAll("[\\s]"+stopWords.get(i)+"[\\s]", " ");
    }
   
    Pattern p = Pattern.compile("[^a-zA-Z]+");
    String [] words = p.split(text);
    text = "";
    for(int i=0; i < words.length; i++)
    {
      if(words[i].length() < 3)
      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
      if(VerifyParents.getParent(fields.get(1)) == null)
      {
        if(stemWordsTotal.containsKey(stemmed))
        {
View Full Code Here

Examples of weka.core.stemmers.SnowballStemmer

64
65
66
67
68
69
70
71
72
73
        private SnowballStemmer snowball;
        private final Pattern nonsensePattern;

        public NoNonsenseStemmer(boolean useSnowball) {
            if (useSnowball) {
                this.snowball = new SnowballStemmer();
            }

            this.nonsensePattern = Pattern.compile("^[\\p{Digit}\\p{Punct}]*$");
        }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.