mirror of
				https://github.com/python/cpython.git
				synced 2025-10-31 05:31:20 +00:00 
			
		
		
		
	Follow-up to r67746 in order to restore backwards-compatibility for
those who (monkey-)patch TextWrapper.wordsep_re with a custom RE.
This commit is contained in:
		
							parent
							
								
									8d5934b25d
								
							
						
					
					
						commit
						3eef441700
					
				
					 1 changed files with 19 additions and 7 deletions
				
			
		|  | @ -84,7 +84,7 @@ class TextWrapper: | ||||||
|     # splits into |     # splits into | ||||||
|     #   Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option! |     #   Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option! | ||||||
|     # (after stripping out empty strings). |     # (after stripping out empty strings). | ||||||
|     wordsep_re = ( |     wordsep_re = re.compile( | ||||||
|         r'(\s+|'                                  # any whitespace |         r'(\s+|'                                  # any whitespace | ||||||
|         r'[^\s\w]*\w+[^0-9\W]-(?=\w+[^0-9\W])|'   # hyphenated words |         r'[^\s\w]*\w+[^0-9\W]-(?=\w+[^0-9\W])|'   # hyphenated words | ||||||
|         r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))')   # em-dash |         r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))')   # em-dash | ||||||
|  | @ -93,7 +93,7 @@ class TextWrapper: | ||||||
|     #   "Hello there -- you goof-ball, use the -b option!" |     #   "Hello there -- you goof-ball, use the -b option!" | ||||||
|     # splits into |     # splits into | ||||||
|     #   Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/ |     #   Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/ | ||||||
|     wordsep_simple_re = r'(\s+)' |     wordsep_simple_re = re.compile(r'(\s+)') | ||||||
| 
 | 
 | ||||||
|     # XXX this is not locale- or charset-aware -- string.lowercase |     # XXX this is not locale- or charset-aware -- string.lowercase | ||||||
|     # is US-ASCII only (and therefore English-only) |     # is US-ASCII only (and therefore English-only) | ||||||
|  | @ -124,6 +124,13 @@ def __init__(self, | ||||||
|         self.drop_whitespace = drop_whitespace |         self.drop_whitespace = drop_whitespace | ||||||
|         self.break_on_hyphens = break_on_hyphens |         self.break_on_hyphens = break_on_hyphens | ||||||
| 
 | 
 | ||||||
|  |         # recompile the regexes for Unicode mode -- done in this clumsy way for | ||||||
|  |         # backwards compatibility because it's rather common to monkey-patch | ||||||
|  |         # the TextWrapper class' wordsep_re attribute. | ||||||
|  |         self.wordsep_re_uni = re.compile(self.wordsep_re.pattern, re.U) | ||||||
|  |         self.wordsep_simple_re_uni = re.compile( | ||||||
|  |             self.wordsep_simple_re.pattern, re.U) | ||||||
|  | 
 | ||||||
| 
 | 
 | ||||||
|     # -- Private methods ----------------------------------------------- |     # -- Private methods ----------------------------------------------- | ||||||
|     # (possibly useful for subclasses to override) |     # (possibly useful for subclasses to override) | ||||||
|  | @ -160,12 +167,17 @@ def _split(self, text): | ||||||
|           'use', ' ', 'the', ' ', '-b', ' ', option!' |           'use', ' ', 'the', ' ', '-b', ' ', option!' | ||||||
|         otherwise. |         otherwise. | ||||||
|         """ |         """ | ||||||
|         flags = re.UNICODE if isinstance(text, unicode) else 0 |         if isinstance(text, unicode): | ||||||
|  |             if self.break_on_hyphens: | ||||||
|  |                 pat = self.wordsep_re_uni | ||||||
|  |             else: | ||||||
|  |                 pat = self.wordsep_simple_re_uni | ||||||
|  |         else: | ||||||
|             if self.break_on_hyphens: |             if self.break_on_hyphens: | ||||||
|                 pat = self.wordsep_re |                 pat = self.wordsep_re | ||||||
|             else: |             else: | ||||||
|                 pat = self.wordsep_simple_re |                 pat = self.wordsep_simple_re | ||||||
|         chunks = re.compile(pat, flags).split(text) |         chunks = pat.split(text) | ||||||
|         chunks = filter(None, chunks)  # remove empty chunks |         chunks = filter(None, chunks)  # remove empty chunks | ||||||
|         return chunks |         return chunks | ||||||
| 
 | 
 | ||||||
|  |  | ||||||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue
	
	 Georg Brandl
						Georg Brandl