From: Greg Ward <gward@python.net>
Date: Wed, 7 May 2003 01:20:58 +0000 (+0000)
Subject: SF #596434: tweak wordsep_re so the definition of an em-dash is
X-Git-Tag: v2.3c1~822
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=a409f7c491647fe0c256c944d6fe4e9593d15760;p=python

SF #596434: tweak wordsep_re so the definition of an em-dash is
stricter: specifically, "--" must be preceded by a limited set of
characters, not by any non-whitespace character.
---

diff --git a/Lib/textwrap.py b/Lib/textwrap.py
index fdb95d7163..b0c7042b54 100644
--- a/Lib/textwrap.py
+++ b/Lib/textwrap.py
@@ -75,7 +75,7 @@ class TextWrapper:
     # (after stripping out empty strings).
     wordsep_re = re.compile(r'(\s+|'                  # any whitespace
                             r'-*\w{2,}-(?=\w{2,})|'   # hyphenated words
-                            r'(?<=\S)-{2,}(?=\w))')   # em-dash
+                            r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))')   # em-dash
 
     # XXX will there be a locale-or-charset-aware version of
     # string.lowercase in 2.3?