Merge pull request #1 from ddohler/master

Disable automatic junk detection on Python >=2.7.1
aaronsw · Jan 6, 2013 · f3c99f794a7f83f8e1645d4e58a89948a1939e65 · f3c99f7 · garyrh · Jan 12, 2013
2 parents 8421ee0 + 20e7c28
commit f3c99f794a7f83f8e1645d4e58a89948a1939e65
Unified Split

Showing with 5 additions and 2 deletions.

+5 −2 diff.py
diff --git a/diff.py b/diff.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python2.2
+#!/usr/bin/python
 """HTML Diff: http://www.aaronsw.com/2002/diff
 Rough code, badly documented. Send me comments and patches."""

@@ -15,7 +15,10 @@ def textDiff(a, b):

 	out = []
 	a, b = html2list(a), html2list(b)
-	s = difflib.SequenceMatcher(None, a, b)
+	try: # autojunk can cause malformed HTML, but also speeds up processing.
+		s = difflib.SequenceMatcher(None, a, b, autojunk=False)
+	except TypeError:
+		s = difflib.SequenceMatcher(None, a, b)
 	for e in s.get_opcodes():
 		if e[0] == "replace":
 			# @@ need to do something more complicated here