pengyuthon/odoo_source
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[MOV] core: move tag_quote() method to ease reading next commit diff

Browse Source 
X-original-commit: b1138e8cc5b8802e5a86315b66387e1576e25bab
Part-of: odoo/odoo#110903
This commit is contained in:
Romain Derie
2023-01-25 05:06:02 +01:00
parent 2be025dfa5
commit 48c7827d6b
1 changed files with 70 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
odoo/tools/mail.py
+70 -69
View File
@@ -76,7 +76,7 @@ class _Cleaner(clean.Cleaner):
def __call__(self, doc):
# perform quote detection before cleaning and class removal
for el in doc.iter(tag=etree.Element):
self.tag_quote(el)
tag_quote(el)
super(_Cleaner, self).__call__(doc)
@@ -90,74 +90,6 @@ class _Cleaner(clean.Cleaner):
for el in doc.iter(tag=etree.Element):
self.parse_style(el)
def tag_quote(self, el):
def _create_new_node(tag, text, tail=None, attrs=None):
new_node = etree.Element(tag)
new_node.text = text
new_node.tail = tail
if attrs:
for key, val in attrs.items():
new_node.set(key, val)
return new_node
def _tag_matching_regex_in_text(regex, node, tag='span', attrs=None):
text = node.text or ''
if not re.search(regex, text):
return
child_node = None
idx, node_idx = 0, 0
for item in re.finditer(regex, text):
new_node = _create_new_node(tag, text[item.start():item.end()], None, attrs)
if child_node is None:
node.text = text[idx:item.start()]
new_node.tail = text[item.end():]
node.insert(node_idx, new_node)
else:
child_node.tail = text[idx:item.start()]
new_node.tail = text[item.end():]
node.insert(node_idx, new_node)
child_node = new_node
idx = item.end()
node_idx = node_idx + 1
el_class = el.get('class', '') or ''
el_id = el.get('id', '') or ''
# gmail or yahoo // # outlook, html // # msoffice
if 'gmail_extra' in el_class or \
'divRplyFwdMsg' in el_id or \
('SkyDrivePlaceholder' in el_class or 'SkyDrivePlaceholder' in el_class):
el.set('data-o-mail-quote', '1')
if el.getparent() is not None:
el.getparent().set('data-o-mail-quote-container', '1')
if (el.tag == 'hr' and ('stopSpelling' in el_class or 'stopSpelling' in el_id)) or \
'yahoo_quoted' in el_class:
# Quote all elements after this one
el.set('data-o-mail-quote', '1')
for sibling in el.itersiblings(preceding=False):
sibling.set('data-o-mail-quote', '1')
# html signature (-- <br />blah)
signature_begin = re.compile(r"((?:(?:^|\n)[-]{2}[\s]?$))")
if el.text and el.find('br') is not None and re.search(signature_begin, el.text):
el.set('data-o-mail-quote', '1')
if el.getparent() is not None:
el.getparent().set('data-o-mail-quote-container', '1')
# text-based quotes (>, >>) and signatures (-- Signature)
text_complete_regex = re.compile(r"((?:\n[>]+[^\n\r]*)+|(?:(?:^|\n)[-]{2}[\s]?[\r\n]{1,2}[\s\S]+))")
if not el.get('data-o-mail-quote'):
_tag_matching_regex_in_text(text_complete_regex, el, 'span', {'data-o-mail-quote': '1'})
if el.tag == 'blockquote':
# remove single node
el.set('data-o-mail-quote-node', '1')
el.set('data-o-mail-quote', '1')
if el.getparent() is not None and (el.getparent().get('data-o-mail-quote') or el.getparent().get('data-o-mail-quote-container')) and not el.getparent().get('data-o-mail-quote-node'):
el.set('data-o-mail-quote', '1')
def strip_class(self, el):
if el.attrib.get('class'):
del el.attrib['class']
@@ -177,6 +109,75 @@ class _Cleaner(clean.Cleaner):
del el.attrib['style']
def tag_quote(el):
def _create_new_node(tag, text, tail=None, attrs=None):
new_node = etree.Element(tag)
new_node.text = text
new_node.tail = tail
if attrs:
for key, val in attrs.items():
new_node.set(key, val)
return new_node
def _tag_matching_regex_in_text(regex, node, tag='span', attrs=None):
text = node.text or ''
if not re.search(regex, text):
return
child_node = None
idx, node_idx = 0, 0
for item in re.finditer(regex, text):
new_node = _create_new_node(tag, text[item.start():item.end()], None, attrs)
if child_node is None:
node.text = text[idx:item.start()]
new_node.tail = text[item.end():]
node.insert(node_idx, new_node)
else:
child_node.tail = text[idx:item.start()]
new_node.tail = text[item.end():]
node.insert(node_idx, new_node)
child_node = new_node
idx = item.end()
node_idx = node_idx + 1
el_class = el.get('class', '') or ''
el_id = el.get('id', '') or ''
# gmail or yahoo // # outlook, html // # msoffice
if 'gmail_extra' in el_class or \
'divRplyFwdMsg' in el_id or \
('SkyDrivePlaceholder' in el_class or 'SkyDrivePlaceholder' in el_class):
el.set('data-o-mail-quote', '1')
if el.getparent() is not None:
el.getparent().set('data-o-mail-quote-container', '1')
if (el.tag == 'hr' and ('stopSpelling' in el_class or 'stopSpelling' in el_id)) or \
'yahoo_quoted' in el_class:
# Quote all elements after this one
el.set('data-o-mail-quote', '1')
for sibling in el.itersiblings(preceding=False):
sibling.set('data-o-mail-quote', '1')
# html signature (-- <br />blah)
signature_begin = re.compile(r"((?:(?:^|\n)[-]{2}[\s]?$))")
if el.text and el.find('br') is not None and re.search(signature_begin, el.text):
el.set('data-o-mail-quote', '1')
if el.getparent() is not None:
el.getparent().set('data-o-mail-quote-container', '1')
# text-based quotes (>, >>) and signatures (-- Signature)
text_complete_regex = re.compile(r"((?:\n[>]+[^\n\r]*)+|(?:(?:^|\n)[-]{2}[\s]?[\r\n]{1,2}[\s\S]+))")
if not el.get('data-o-mail-quote'):
_tag_matching_regex_in_text(text_complete_regex, el, 'span', {'data-o-mail-quote': '1'})
if el.tag == 'blockquote':
# remove single node
el.set('data-o-mail-quote-node', '1')
el.set('data-o-mail-quote', '1')
if el.getparent() is not None and (el.getparent().get('data-o-mail-quote') or el.getparent().get('data-o-mail-quote-container')) and not el.getparent().get('data-o-mail-quote-node'):
el.set('data-o-mail-quote', '1')
def html_sanitize(src, silent=True, sanitize_tags=True, sanitize_attributes=False, sanitize_style=False, sanitize_form=True, strip_style=False, strip_classes=False):
if not src:
return src