Package morfologik.stemming

Examples of morfologik.stemming.IStemmer.lookup()

141
142
143
144
145
146
147
148
149
150
151
    //Adjectiu femení singular o participi femení singular + -ment
    if (word.endsWith("ment")){
      final String lowerWord = word.toLowerCase(conversionLocale);
      final String possibleAdj = lowerWord.replaceAll("^(.+)ment$", "$1");
      List<AnalyzedToken> taggerTokens;
      taggerTokens = asAnalyzedTokenList(possibleAdj, dictLookup.lookup(possibleAdj));
      for (AnalyzedToken taggerToken : taggerTokens ) {
        final String posTag = taggerToken.getPOSTag();
        if (posTag != null) {
          final Matcher m = ADJ_PART_FS.matcher(posTag);
          if (m.matches()) {
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
    //Any well-formed verb with prefixes is tagged as a verb copying the original tags
    Matcher matcher=PREFIXES_FOR_VERBS.matcher(word);
    if (matcher.matches()) {
      final String possibleVerb = matcher.group(2).toLowerCase();
      List<AnalyzedToken> taggerTokens;
      taggerTokens = asAnalyzedTokenList(possibleVerb, dictLookup.lookup(possibleVerb));
      for (AnalyzedToken taggerToken : taggerTokens ) {
        final String posTag = taggerToken.getPOSTag();
        if (posTag != null) {
          final Matcher m = VERB.matcher(posTag);
          if (m.matches()) {
View Full Code Here
195
196
197
198
199
200
201
202
203
204
205
    // U+013F LATIN CAPITAL LETTER L WITH MIDDLE DOT
    // U+0140 LATIN SMALL LETTER L WITH MIDDLE DOT
    if (word.contains("\u0140") || word.contains("\u013f")) {
      final String lowerWord = word.toLowerCase(conversionLocale);
      final String possibleWord = lowerWord.replaceAll("\u0140", "l·");
      List<AnalyzedToken> taggerTokens = asAnalyzedTokenList(word,dictLookup.lookup(possibleWord));
      return taggerTokens;
    }
    return null;
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
    final IStemmer morfologik = new DictionaryLookup(getDictionary());

    for (String word : sentenceTokens) {
      final List<AnalyzedToken> l = new ArrayList<>();
      final String lowerWord = word.toLowerCase(plLocale);
      taggerTokens = asAnalyzedTokenList(word, morfologik.lookup(word));
      lowerTaggerTokens = asAnalyzedTokenList(word, morfologik.lookup(lowerWord));      
      final boolean isLowercase = word.equals(lowerWord);

      //normal case
      addTokens(taggerTokens, l);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    for (String word : sentenceTokens) {
      final List<AnalyzedToken> l = new ArrayList<>();
      final String lowerWord = word.toLowerCase(plLocale);
      taggerTokens = asAnalyzedTokenList(word, morfologik.lookup(word));
      lowerTaggerTokens = asAnalyzedTokenList(word, morfologik.lookup(lowerWord));      
      final boolean isLowercase = word.equals(lowerWord);

      //normal case
      addTokens(taggerTokens, l);
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
      }

      //uppercase
      if (lowerTaggerTokens.isEmpty() && taggerTokens.isEmpty()) {
        if (isLowercase) {
          upperTaggerTokens = asAnalyzedTokenList(word, morfologik.lookup(StringTools
              .uppercaseFirstChar(word)));
          if (!upperTaggerTokens.isEmpty()) {
            addTokens(upperTaggerTokens, l);
          } else {
            l.add(new AnalyzedToken(word, null, null));
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.