version 1.7.2.9, 2007/12/13 19:20:45
|
version 1.7.2.10, 2008/01/02 15:52:01
|
Line 29 komma_exceptionex=re.compile(komma_excep
|
Line 29 komma_exceptionex=re.compile(komma_excep
|
# grapheme boundaries |
# grapheme boundaries |
#graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?" |
#graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?" |
graphemeBounds="\{|\}|<|>|-|_|\#|,|\]|\[|\!|\?|\"" |
graphemeBounds="\{|\}|<|>|-|_|\#|,|\]|\[|\!|\?|\"" |
graphemeIgnore="<|>|\#|\||\]|\[|\!|\?" |
graphemeIgnore="<|>|\#|\||\]|\[|\!|\?\*" |
# for words |
# for words |
#wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?" |
#wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?" |
wordBounds="_|,|\"" |
wordBounds="_|,|\"" |
wordIgnore="<|>|\#|\||\]|\[|\!|\?" |
wordIgnore="<|>|\#|\||\]|\[|\!|\?\*" |
|
|
class cdliSplitter: |
class cdliSplitter: |
"""base class for splitter. |
"""base class for splitter. |