--- cdli/cdliSplitter.py 2007/10/24 20:36:06 1.7.2.4 +++ cdli/cdliSplitter.py 2007/12/03 21:30:19 1.7.2.6 @@ -26,9 +26,11 @@ separators=[''] # kommas relevant for graphemes will not be deleted komma_exception="([^sStThH])," # grapheme boundaries -graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?" +#graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?" +graphemeBounds="\{|\}|<|>|-|_|\#|,|\]|\[|\!|\?|\"" # for words -wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?" +#wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?" +wordBounds="<|>|_|\#|,|\]|\[|\!|\?|\"" class cdliSplitter: