[Lxml-checkins] r43963 - in lxml/branch/html/src/lxml/html: . tests

Fri Jun 1 07:12:30 CEST 2007

Author: ianb
Date: Fri Jun  1 07:12:30 2007
New Revision: 43963

Modified:
   lxml/branch/html/src/lxml/html/clean.py
   lxml/branch/html/src/lxml/html/tests/test_clean.txt
Log:
Handle <image> in clean

Modified: lxml/branch/html/src/lxml/html/clean.py
==============================================================================

--- lxml/branch/html/src/lxml/html/clean.py	(original)
+++ lxml/branch/html/src/lxml/html/clean.py	Fri Jun  1 07:12:30 2007
@@ -11,7 +11,6 @@
 # Other on* attributes that aren't standard?
 # Try these tests: http://feedparser.org/tests/wellformed/sanitize/
 # Also http://code.sixapart.com/trac/livejournal/browser/trunk/cgi-bin/cleanhtml.pl
-# IE treats <image> like <img>
 # <layer>...?
 # <head> and <title> is fishy in a fragment
 # max width for words

Modified: lxml/branch/html/src/lxml/html/tests/test_clean.txt
==============================================================================
--- lxml/branch/html/src/lxml/html/tests/test_clean.txt	(original)
+++ lxml/branch/html/src/lxml/html/tests/test_clean.txt	Fri Jun  1 07:12:30 2007
@@ -19,6 +19,7 @@
 ...    </form>
 ...    <blink>annoying EVIL!</blink>
 ...    <a href="evil-site">spam spam SPAM!</a>
+...    <image src="evil!">
 ...  </body>
 ... </html>'''
 >>> print doc
@@ -40,6 +41,7 @@
     </form>
     <blink>annoying EVIL!</blink>
     <a href="evil-site">spam spam SPAM!</a>
+    <image src="evil!">
   </body>
 </html>
 >>> print tostring(HTML(doc))
@@ -61,6 +63,7 @@
     </form>
     <blink>annoying EVIL!</blink>
     <a href="evil-site">spam spam SPAM!</a>
+    <image src="evil!">
   </body>
 </html>
 >>> print clean_html(doc)
@@ -76,6 +79,7 @@
     Password:
     <blink>annoying EVIL!</blink>
     <a href="evil-site">spam spam SPAM!</a>
+    <img src="evil!">
   </body>
 </html>
 >>> print clean_html(doc, style=True, links=True, add_nofollow=True)
@@ -90,5 +94,6 @@
     Password:
     <blink>annoying EVIL!</blink>
     <a href="evil-site" rel="nofollow">spam spam SPAM!</a>
+    <img src="evil!">
   </body>
 </html>
