# html encode email tags
part = re.compile(r"(<(([^a<>]|a[^<>\s])[^<>]*)@[^<>]+>)", re.IGNORECASE | re.DOTALL)
src = part.sub(lambda m: cgi.escape(m.group(1)), src)
+ # html encode mako tags <% ... %> to decode them later and keep them alive, otherwise they are stripped by the cleaner
+ src = src.replace('<%', cgi.escape('<%'))
+ src = src.replace('%>', cgi.escape('%>'))
kwargs = {
'page_structure': True,
'remove_unknown_tags': False,
'allow_tags': allowed_tags,
'comments': False,
- 'processing_instructions' : False
+ 'processing_instructions': False
}
if etree.LXML_VERSION >= (2, 3, 1):
# kill_tags attribute has been added in version 2.3.1
cleaned = cleaned.replace('%20', ' ')
cleaned = cleaned.replace('%5B', '[')
cleaned = cleaned.replace('%5D', ']')
+ cleaned = cleaned.replace('<%', '<%')
+ cleaned = cleaned.replace('%>', '%>')
except etree.ParserError, e:
if 'empty' in str(e):
return ""
node.set('in_quote', '1')
node.set('tail_remove', '1')
if node.tag == 'blockquote' or node.get('text_quote') or node.get('text_signature'):
+ # here no quote_begin because we want to be able to remove some quoted
+ # text without removing all the remaining context
+ node.set('in_quote', '1')
+ if node.getparent() is not None and node.getparent().get('in_quote'):
+ # inside a block of removed text but not in quote_begin (see above)
node.set('in_quote', '1')
# shorten:
html = html.replace(' ' * 2, ' ')
html = html.replace('>', '>')
html = html.replace('<', '<')
+ html = html.replace('&', '&')
# strip all lines
html = '\n'.join([x.strip() for x in html.splitlines()])
# group(1) = the record ID ; group(2) = the model (if any) ; group(3) = the domain
reference_re = re.compile("<.*-open(?:object|erp)-(\\d+)(?:-([\w.]+))?.*@(.*)>", re.UNICODE)
-# Bounce regex
-# Typical form of bounce is bounce-128-crm.lead-34@domain
-# group(1) = the mail ID; group(2) = the model (if any); group(3) = the record ID
-bounce_re = re.compile("[\w]+-(\d+)-?([\w.]+)?-?(\d+)?", re.UNICODE)
def generate_tracking_message_id(res_id):
"""Returns a string that can be used in the Message-ID RFC822 header field
# sometimes returns emails without at least '@'. The '@'
# is strictly required in RFC2822's `addr-spec`.
if addr[1]
- if '@' in addr[1]]
\ No newline at end of file
+ if '@' in addr[1]]