public static String tokenFeature()

in opennlp-tools/src/main/java/opennlp/tools/util/featuregen/FeatureGeneratorUtil.java [53:112]

• 57 lines of code
• 16 McCabe index (conditional complexity)

  public static String tokenFeature(String token) {

    StringPattern pattern = StringPattern.recognize(token);

    String feat;
    if (pattern.isAllHiragana()) {
      feat = "jah";
    }
    else if (pattern.isAllKatakana()) {
      feat = "jak";
    }
    else if (pattern.isAllLowerCaseLetter()) {
      feat = "lc";
    }
    else if (pattern.digits() == 2) {
      feat = "2d";
    }
    else if (pattern.digits() == 4) {
      feat = "4d";
    }
    else if (pattern.containsDigit()) {
      if (pattern.containsLetters()) {
        feat = "an";
      }
      else if (pattern.containsHyphen()) {
        feat = "dd";
      }
      else if (pattern.containsSlash()) {
        feat = "ds";
      }
      else if (pattern.containsComma()) {
        feat = "dc";
      }
      else if (pattern.containsPeriod()) {
        feat = "dp";
      }
      else {
        feat = "num";
      }
    }
    else if (pattern.isAllCapitalLetter()) {
      if (token.length() == 1) {
        feat = "sc";
      }
      else {
        feat = "ac";
      }
    }
    else if (capPeriod.matcher(token).find()) {
      feat = "cp";
    }
    else if (pattern.isInitialCapitalLetter()) {
      feat = "ic";
    }
    else {
      feat = "other";
    }

    return (feat);
  }