From a7a6d956af93a55af86e1461e94dbb4122fff6ca Mon Sep 17 00:00:00 2001
From: Henrik Levkowetz <henrik@levkowetz.com>
Date: Mon, 11 Jun 2007 03:36:08 +0000
Subject: [PATCH] Adding a fix in soup2text for a common pathological case:
 <br><br> used instead of <p /> to indicate paragraph breaks.

This changes the failed diff for /iesg/telechat/detail/354/ to show only three
differences, where two are whitespace differences and one shows a difference
between '@ietf.org. The' and '@ietf.org . The' and is an artifact of the text
extraction.  Will look at fixing that next.
 - Legacy-Id: 300
---
 ietf/utils/soup2text.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ietf/utils/soup2text.py b/ietf/utils/soup2text.py
index bae2bd321..c86484077 100755
--- a/ietf/utils/soup2text.py
+++ b/ietf/utils/soup2text.py
@@ -66,6 +66,8 @@ class TextSoup(BeautifulSoup):
         return str
 
 def soup2text(html):
+    # some preprocessing to handle common pathological cases
+    html = re.sub("<br */?>[ \t\r\n]*(<br */?>)+", "<p/>", html)
     soup = TextSoup(html)
     return str(soup)