cdli/cdliSplitter.py - diff

Return to cdliSplitter.py CVS log

Up to [Repository] / cdli

version 1.7.2.9, 2007/12/13 19:20:45	version 1.7.2.12, 2008/01/14 17:35:26
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.
Line 73 class cdliSplitter:	Line 73 class cdliSplitter:

elif not (s[0] in ignoreLines):	elif not (s[0] in ignoreLines):
# regular line	# regular line
lineparts=s.split(".")	lineparts=s.split(". ",1)
if len(lineparts)==1:	if len(lineparts)==1:
# no line number	# no line number
txt=s	txt=s
Line 95 class cdliSplitter:	Line 95 class cdliSplitter:
if not (w==''):	if not (w==''):
result.append(w)	result.append(w)

#logging.debug("split '%s' into %s"%(lst,repr(result)))	logging.debug("split '%s' into %s"%(lst,repr(result)))
return result	return result