Class DocumentTokenizer

java.lang.Object
net.ontopia.topicmaps.classify.DocumentTokenizer

public class DocumentTokenizer extends Object
INTERNAL:
  • Constructor Details

    • DocumentTokenizer

      public DocumentTokenizer(TermDatabase tdb)
  • Method Details

    • getTermDatabase

      public TermDatabase getTermDatabase()
    • setTermDatabase

      public void setTermDatabase(TermDatabase tdb)
    • setTokenizer

      public void setTokenizer(TokenizerIF tokenizer)
    • setDelimiterTrimmer

      public void setDelimiterTrimmer(DelimiterTrimmerIF trimmer)
    • addTermNormalizer

      public void addTermNormalizer(TermNormalizerIF normalizer)
    • tokenize

      public void tokenize(Document doc)
    • tokenize

      protected void tokenize(Region region)
    • tokenize

      protected void tokenize(Region parent, TextBlock tb)
    • tokenize

      protected void tokenize(TextBlock tb, String token)