diff options
Diffstat (limited to 'Lib/textwrap.py')
| -rw-r--r-- | Lib/textwrap.py | 60 |
1 files changed, 11 insertions, 49 deletions
diff --git a/Lib/textwrap.py b/Lib/textwrap.py index 62ea0b4..dfb4005 100644 --- a/Lib/textwrap.py +++ b/Lib/textwrap.py @@ -5,26 +5,8 @@ # Copyright (C) 2002, 2003 Python Software Foundation. # Written by Greg Ward <gward@python.net> -__revision__ = "$Id$" - import string, re -try: - _unicode = unicode -except NameError: - # If Python is built without Unicode support, the unicode type - # will not exist. Fake one. - class _unicode(object): - pass - -# Do the right thing with boolean values for all known Python versions -# (so this module can be copied to projects that don't depend on Python -# 2.3, e.g. Optik and Docutils) by uncommenting the block of code below. -#try: -# True, False -#except NameError: -# (True, False) = (1, 0) - __all__ = ['TextWrapper', 'wrap', 'fill', 'dedent'] # Hardcode the recognized whitespace characters to the US-ASCII @@ -79,12 +61,10 @@ class TextWrapper: Drop leading and trailing whitespace from lines. """ - whitespace_trans = string.maketrans(_whitespace, ' ' * len(_whitespace)) - unicode_whitespace_trans = {} - uspace = ord(u' ') - for x in map(ord, _whitespace): - unicode_whitespace_trans[x] = uspace + uspace = ord(' ') + for x in _whitespace: + unicode_whitespace_trans[ord(x)] = uspace # This funky little regex is just the trick for splitting # text up into word-wrappable chunks. E.g. @@ -105,11 +85,10 @@ class TextWrapper: # XXX this is not locale- or charset-aware -- string.lowercase # is US-ASCII only (and therefore English-only) - sentence_end_re = re.compile(r'[%s]' # lowercase letter + sentence_end_re = re.compile(r'[a-z]' # lowercase letter r'[\.\!\?]' # sentence-ending punct. r'[\"\']?' # optional end-of-quote - r'\Z' # end of chunk - % string.lowercase) + r'\Z') # end of chunk def __init__(self, @@ -132,13 +111,6 @@ class TextWrapper: self.drop_whitespace = drop_whitespace 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 ----------------------------------------------- # (possibly useful for subclasses to override) @@ -153,10 +125,7 @@ class TextWrapper: if self.expand_tabs: text = text.expandtabs() if self.replace_whitespace: - if isinstance(text, str): - text = text.translate(self.whitespace_trans) - elif isinstance(text, _unicode): - text = text.translate(self.unicode_whitespace_trans) + text = text.translate(self.unicode_whitespace_trans) return text @@ -175,18 +144,11 @@ class TextWrapper: 'use', ' ', 'the', ' ', '-b', ' ', option!' otherwise. """ - if isinstance(text, _unicode): - if self.break_on_hyphens: - pat = self.wordsep_re_uni - else: - pat = self.wordsep_simple_re_uni + if self.break_on_hyphens is True: + chunks = self.wordsep_re.split(text) else: - if self.break_on_hyphens: - pat = self.wordsep_re - else: - pat = self.wordsep_simple_re - chunks = pat.split(text) - chunks = filter(None, chunks) # remove empty chunks + chunks = self.wordsep_simple_re.split(text) + chunks = [c for c in chunks if c] return chunks def _fix_sentence_endings(self, chunks): @@ -422,4 +384,4 @@ def dedent(text): if __name__ == "__main__": #print dedent("\tfoo\n\tbar") #print dedent(" \thello there\n \t how are you?") - print dedent("Hello there.\n This is indented.") + print(dedent("Hello there.\n This is indented.")) |