--- cdli/cdliSplitter.py 2007/12/13 19:20:45 1.7.2.9 +++ cdli/cdliSplitter.py 2008/01/09 18:49:07 1.7.2.11 @@ -29,11 +29,11 @@ komma_exceptionex=re.compile(komma_excep # grapheme boundaries #graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?" graphemeBounds="\{|\}|<|>|-|_|\#|,|\]|\[|\!|\?|\"" -graphemeIgnore="<|>|\#|\||\]|\[|\!|\?" +graphemeIgnore="<|>|\#|\||\]|\[|\!|\?\*|;" # for words #wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?" wordBounds="_|,|\"" -wordIgnore="<|>|\#|\||\]|\[|\!|\?" +wordIgnore="<|>|\#|\||\]|\[|\!|\?\*|;" class cdliSplitter: """base class for splitter.