[MERGE] tools mail: Return the initial variable if is false or if is not an instance of basestring. Remove encoding attribute in html tags.

bzr revid: chm@openerp.com-20121221083527-py3wr2syz5d8igv8

openerp/tests/test_mail.py

@@ -177,6 +177,10 @@ class TestCleaner(unittest2.TestCase):
         new_html = html_email_clean(False)
         self.assertEqual(new_html, False, 'html_email_cleaner did change a False in an other value.')
 
+        # Test6: Message with xml and doctype tags don't crash
+        new_html = html_email_clean(u'<?xml version="1.0" encoding="iso-8859-1"?>\n<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\n         "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">\n<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">\n <head>\n  <title>404 - Not Found</title>\n </head>\n <body>\n  <h1>404 - Not Found</h1>\n </body>\n</html>\n')
+        self.assertNotIn('encoding', new_html, 'html_email_cleaner did not remove correctly encoding attributes')
+
 class TestHtmlTools(unittest2.TestCase):
     """ Test some of our generic utility functions about html """
 

openerp/tools/mail.py

@@ -130,11 +130,15 @@ def html_email_clean(html):
         dest += source[idx:]
         return dest
 
-    if not html:
+    if not html or not isinstance(html, basestring):
         return html
 
     html = ustr(html)
 
+    # 0. remove encoding attribute inside tags
+    doctype = re.compile(r'(<[^>]*\s)(encoding=(["\'][^"\']*?["\']|[^\s\n\r>]+)(\s[^>]*|/)?>)', re.IGNORECASE | re.DOTALL)
+    html = doctype.sub(r"", html)
+
     # 1. <br[ /]> -> \n, because otherwise the tree is obfuscated
     br_tags = re.compile(r'([<]\s*[bB][rR]\s*\/?[>])')
     html = _replace_matching_regex(br_tags, html, '__BR_TAG__')