--- cdli/cdliSplitter.py 2008/01/21 17:19:01 1.8 +++ cdli/cdliSplitter.py 2008/09/25 12:37:55 1.9 @@ -36,9 +36,11 @@ wordBounds="_|,|\"" wordIgnore="<|>|\#|\||\]|\[|\!|\?\*|;" class cdliSplitter: + """base class for splitter. the difference between word and grapheme splitter is the word boundary list.""" + default_encoding = "utf-8" bounds=graphemeBounds