Merged revisions 67654,67676-67677,67681,67692,67725,67746,67748,67761,67784-67785,67787-67788,67802,67832,67848-67849,67859,67862-67864,67880,67882,67885,67889-67892,67895 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

................
  r67654 | georg.brandl | 2008-12-07 16:42:09 -0600 (Sun, 07 Dec 2008) | 2 lines

  #4457: rewrite __import__() documentation.
................
  r67676 | benjamin.peterson | 2008-12-08 20:03:03 -0600 (Mon, 08 Dec 2008) | 1 line

  specify how things are copied
................
  r67677 | benjamin.peterson | 2008-12-08 20:05:11 -0600 (Mon, 08 Dec 2008) | 1 line

  revert unrelated change to installer script
................
  r67681 | jeremy.hylton | 2008-12-09 15:03:10 -0600 (Tue, 09 Dec 2008) | 2 lines

  Add simple unittests for Request
................
  r67692 | amaury.forgeotdarc | 2008-12-10 18:03:42 -0600 (Wed, 10 Dec 2008) | 2 lines

  #1030250: correctly pass the dry_run option to the mkpath() function.
................
  r67725 | benjamin.peterson | 2008-12-12 22:02:20 -0600 (Fri, 12 Dec 2008) | 1 line

  fix incorrect example
................
  r67746 | antoine.pitrou | 2008-12-13 17:12:30 -0600 (Sat, 13 Dec 2008) | 3 lines

  Issue #4163: Use unicode-friendly word splitting in the textwrap functions when given an unicode string.
................
  r67748 | benjamin.peterson | 2008-12-13 19:46:11 -0600 (Sat, 13 Dec 2008) | 1 line

  remove has_key usage
................
  r67761 | benjamin.peterson | 2008-12-14 11:26:04 -0600 (Sun, 14 Dec 2008) | 1 line

  fix missing bracket
................
  r67784 | georg.brandl | 2008-12-15 02:33:58 -0600 (Mon, 15 Dec 2008) | 2 lines

  #4446: document "platforms" argument for setup().
................
  r67785 | georg.brandl | 2008-12-15 02:36:11 -0600 (Mon, 15 Dec 2008) | 2 lines

  #4611: fix typo.
................
  r67787 | georg.brandl | 2008-12-15 02:58:59 -0600 (Mon, 15 Dec 2008) | 2 lines

  #4578: fix has_key() usage in compiler package.
................
  r67788 | georg.brandl | 2008-12-15 03:07:39 -0600 (Mon, 15 Dec 2008) | 2 lines

  #4568: remove limitation in varargs callback example.
................
  r67802 | amaury.forgeotdarc | 2008-12-15 16:29:14 -0600 (Mon, 15 Dec 2008) | 4 lines

  #3632: the "pyo" macro from gdbinit can now run when the GIL is released.

  Patch by haypo.
................
  r67832 | antoine.pitrou | 2008-12-17 16:46:54 -0600 (Wed, 17 Dec 2008) | 4 lines

  Issue #2467: gc.DEBUG_STATS reports invalid elapsed times.
  Patch by Neil Schemenauer, very slightly modified.
................
  r67848 | benjamin.peterson | 2008-12-18 20:28:56 -0600 (Thu, 18 Dec 2008) | 1 line

  fix typo
................
  r67849 | benjamin.peterson | 2008-12-18 20:31:35 -0600 (Thu, 18 Dec 2008) | 1 line

  _call_method -> _callmethod and _get_value to _getvalue
................
  r67859 | amaury.forgeotdarc | 2008-12-19 16:56:48 -0600 (Fri, 19 Dec 2008) | 4 lines

  #4700: crtlicense.txt is displayed by the license() command and should be kept ascii-only.

  Will port to 3.0
................
  r67862 | benjamin.peterson | 2008-12-19 20:48:02 -0600 (Fri, 19 Dec 2008) | 1 line

  copy sentence from docstring
................
  r67863 | benjamin.peterson | 2008-12-19 20:51:26 -0600 (Fri, 19 Dec 2008) | 1 line

  add headings
................
  r67864 | benjamin.peterson | 2008-12-19 20:57:19 -0600 (Fri, 19 Dec 2008) | 1 line

  beef up docstring
................
  r67880 | benjamin.peterson | 2008-12-20 16:49:24 -0600 (Sat, 20 Dec 2008) | 1 line

  remove redundant sentence
................
  r67882 | benjamin.peterson | 2008-12-20 16:59:49 -0600 (Sat, 20 Dec 2008) | 1 line

  add some recent releases to the list
................
  r67885 | benjamin.peterson | 2008-12-20 17:48:54 -0600 (Sat, 20 Dec 2008) | 1 line

  silence annoying DeprecationWarning
................
  r67889 | benjamin.peterson | 2008-12-20 19:04:32 -0600 (Sat, 20 Dec 2008) | 1 line

  sphinx.web is long gone
................
  r67890 | benjamin.peterson | 2008-12-20 19:12:26 -0600 (Sat, 20 Dec 2008) | 1 line

  update readme
................
  r67891 | benjamin.peterson | 2008-12-20 19:14:47 -0600 (Sat, 20 Dec 2008) | 1 line

  there are way too many places which need to have the current version added
................
  r67892 | benjamin.peterson | 2008-12-20 19:29:32 -0600 (Sat, 20 Dec 2008) | 9 lines

  Merged revisions 67809 via svnmerge from
  svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3

  ........
    r67809 | benjamin.peterson | 2008-12-15 21:54:45 -0600 (Mon, 15 Dec 2008) | 1 line

    fix logic error
  ........
................
  r67895 | neal.norwitz | 2008-12-21 08:28:32 -0600 (Sun, 21 Dec 2008) | 2 lines

  Add Tarek for work on distutils.
................

1 files changed, 8 insertions, 6 deletions

diff --git a/Lib/textwrap.py b/Lib/textwrap.py
index 53f2f1b..192b43b 100644
--- a/Lib/textwrap.py
+++ b/Lib/textwrap.py
@@ -84,16 +84,16 @@ class TextWrapper:
     # splits into
     #   Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option!
     # (after stripping out empty strings).
-    wordsep_re = re.compile(
+    wordsep_re = (
         r'(\s+|'                                  # any whitespace
-        r'[^\s\w]*\w+[a-zA-Z]-(?=\w+[a-zA-Z])|'   # hyphenated words
+        r'[^\s\w]*\w+[^0-9\W]-(?=\w+[^0-9\W])|'   # hyphenated words
         r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))')   # em-dash
 
     # This less funky little regex just split on recognized spaces. E.g.
     #   "Hello there -- you goof-ball, use the -b option!"
     # splits into
     #   Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/
-    wordsep_simple_re = re.compile(r'(\s+)')
+    wordsep_simple_re = r'(\s+)'
 
     # XXX this is not locale- or charset-aware -- string.lowercase
     # is US-ASCII only (and therefore English-only)
@@ -160,10 +160,12 @@ class TextWrapper:
           'use', ' ', 'the', ' ', '-b', ' ', option!'
         otherwise.
         """
-        if self.break_on_hyphens is True:
-            chunks = self.wordsep_re.split(text)
+        flags = re.UNICODE if isinstance(text, unicode) else 0
+        if self.break_on_hyphens:
+            pat = self.wordsep_re
         else:
-            chunks = self.wordsep_simple_re.split(text)
+            pat = self.wordsep_simple_re
+        chunks = re.compile(pat, flags).split(text)
         chunks = filter(None, chunks)  # remove empty chunks
         return chunks