--- cdli/cdliSplitter.py	2007/12/13 19:20:45	1.7.2.9
+++ cdli/cdliSplitter.py	2008/01/14 17:35:26	1.7.2.12
@@ -29,11 +29,11 @@ komma_exceptionex=re.compile(komma_excep
 # grapheme boundaries
 #graphemeBounds="\{|\}|<|>|\(|\)|-|_|\#|,|\||\]|\[|\!|\?"
 graphemeBounds="\{|\}|<|>|-|_|\#|,|\]|\[|\!|\?|\""
-graphemeIgnore="<|>|\#|\||\]|\[|\!|\?"
+graphemeIgnore="<|>|\#|\||\]|\[|\!|\?\*|;"
 # for words 
 #wordBounds="<|>|\(|\)|_|\#|,|\||\]|\[|\!|\?"
 wordBounds="_|,|\""
-wordIgnore="<|>|\#|\||\]|\[|\!|\?"
+wordIgnore="<|>|\#|\||\]|\[|\!|\?\*|;"
            
 class cdliSplitter:
     """base class for splitter. 
@@ -73,7 +73,7 @@ class cdliSplitter:
                         
                     elif not (s[0] in ignoreLines):
                         # regular line
-                        lineparts=s.split(".")
+                        lineparts=s.split(". ",1)
                         if len(lineparts)==1: 
                             # no line number
                             txt=s
@@ -95,7 +95,7 @@ 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