From: Greg Ward <gward@python.net>
Date: Fri, 7 Jun 2002 22:04:15 +0000 (+0000)
Subject: Convert _fix_sentence_endings() to use a regex, and augment it to
X-Git-Tag: v2.3c1~5414
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=9b4864e40af38eee803b65e9a336a1590b0f633e;p=thirdparty%2FPython%2Fcpython.git

Convert _fix_sentence_endings() to use a regex, and augment it to
handle sentences like this:
  And she said, "Go to hell!"  Can you believe that?
---

diff --git a/Lib/textwrap.py b/Lib/textwrap.py
index ef6c372ce513..3f4442a7f00d 100644
--- a/Lib/textwrap.py
+++ b/Lib/textwrap.py
@@ -54,8 +54,12 @@ class TextWrapper:
                             r'\w{2,}-(?=\w{2,})|'     # hyphenated words
                             r'(?<=\w)-{2,}(?=\w))')   # em-dash
 
-    # Punctuation characters found at the end of a sentence.
-    sentence_end = ".?!"
+    # XXX will there be a locale-or-charset-aware version of
+    # string.lowercase in 2.3?
+    sentence_end_re = re.compile(r'[%s]'              # lowercase letter
+                                 r'[\.\!\?]'          # sentence-ending punct.
+                                 r'[\"\']?'           # optional end-of-quote
+                                 % string.lowercase)
 
 
     def __init__ (self):
@@ -107,13 +111,9 @@ class TextWrapper:
         space to two.
         """
         i = 0
-        punct = self.sentence_end
+        pat = self.sentence_end_re
         while i < len(chunks)-1:
-            # chunks[i] looks like the last word of a sentence,
-            # and it's followed by a single space.
-            if (chunks[i][-1] in punct and
-                  chunks[i+1] == " " and
-                  islower(chunks[i][-2])):
+            if chunks[i+1] == " " and pat.search(chunks[i]):
                 chunks[i+1] = "  "
                 i += 2
             else: