--- cdli/cdliSplitter.py 2007/10/26 22:45:12 1.7.2.5 +++ 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: @@ -86,7 +88,7 @@ class cdliSplitter: if not (w==''): result.append(w) - #logging.debug("split '%s' into %s"%(lst,repr(result))) + logging.debug("split '%s' into %s"%(lst,repr(result))) return result