Package net.ontopia.topicmaps.classify
Class DocumentTokenizer
- java.lang.Object
-
- net.ontopia.topicmaps.classify.DocumentTokenizer
-
public class DocumentTokenizer extends Object
INTERNAL:
-
-
Constructor Summary
Constructors Constructor Description DocumentTokenizer(TermDatabase tdb)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description void
addTermNormalizer(TermNormalizerIF normalizer)
TermDatabase
getTermDatabase()
void
setDelimiterTrimmer(DelimiterTrimmerIF trimmer)
void
setTermDatabase(TermDatabase tdb)
void
setTokenizer(TokenizerIF tokenizer)
void
tokenize(Document doc)
protected void
tokenize(Region region)
protected void
tokenize(Region parent, TextBlock tb)
protected void
tokenize(TextBlock tb, String token)
-
-
-
Constructor Detail
-
DocumentTokenizer
public DocumentTokenizer(TermDatabase tdb)
-
-
Method Detail
-
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)
-
-