Hopiu/wagtail
1
0
Fork 0
mirror of https://github.com/Hopiu/wagtail.git synced 2026-05-14 10:13:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Refactor handle_starttag/handle_endtag to keep track of the original handler

Browse source
This commit is contained in:
Matt Westcott 2017-12-06 20:51:02 +00:00 committed by Thibaud Colas
parent 5660bb85f4
commit dd2bd5b161
1 changed files with 9 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
wagtail/admin/rich_text/converters/html_to_contentstate.py
View file

@ -227,7 +227,10 @@ class HtmlToContentStateHandler(HTMLParser):
def reset(self):
self.state = HandlerState()
self.contentstate = ContentState()
self.element_depth = 0 # number of unclosed start tags encountered, including the one currently being handled
# stack of (name, handler) tuples for the elements we're currently inside
self.open_elements = []
super().reset()
def add_block(self, block):
@ -236,36 +239,27 @@ class HtmlToContentStateHandler(HTMLParser):
self.state.leading_whitespace = 'strip'
def handle_starttag(self, name, attrs):
self.element_depth += 1
try:
element_handler = self.element_handlers[name]
except KeyError:
if self.element_depth == 1:
if not self.open_elements:
# treat unrecognised top-level elements as paragraphs
element_handler = self.element_handlers['p']
else:
# ignore unrecognised elements below the top-level
element_handler = None
self.open_elements.append((name, element_handler))
if element_handler:
element_handler.handle_starttag(name, attrs, self.state, self.contentstate)
def handle_endtag(self, name):
try:
element_handler = self.element_handlers[name]
except KeyError:
if self.element_depth == 1:
# treat unrecognised top-level elements as paragraphs
element_handler = self.element_handlers['p']
else:
# ignore unrecognised elements below the top-level
element_handler = None
expected_name, element_handler = self.open_elements.pop()
assert name == expected_name, "Unmatched tags: expected %s, got %s" % (expected_name, name)
if element_handler:
element_handler.handle_endtag(name, self.state, self.contentstate)
self.element_depth -= 1
def handle_data(self, content):
# normalise whitespace sequences to a single space
content = re.sub(r'\s+', ' ', content)