cis-kuldeep/PyBitmessage-2021-04-27
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Html parser fixes

Browse Source 
Raw mode improved, avoid HTML parser entirely and just replaces some
strings.
This commit is contained in:
mailchuck 2015-12-16 14:20:51 +01:00
parent 9c0fe3c3c0
commit 30ab5006be
Signed by untrusted user who does not match committer: PeterSurda
GPG Key ID: 0C5F50C0B5F37D87
1 changed files with 14 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
src/bitmessageqt/safehtmlparser.py
View File

@ -17,6 +17,14 @@ class SafeHTMLParser(HTMLParser):
'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong', 'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video'] 'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
replaces = [["&", "&amp;"], ["\"", "&quot;"], ["<", "&lt;"], [">", "&gt;"], ["\n", "<br/>"]]
@staticmethod
def multi_replace(text):
for a in SafeHTMLParser.replaces:
text = text.replace(a[0], a[1])
return text
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
HTMLParser.__init__(self, *args, **kwargs) HTMLParser.__init__(self, *args, **kwargs)
self.elements = set() self.elements = set()
@ -48,51 +56,33 @@ class SafeHTMLParser(HTMLParser):
self.sanitised += "/" self.sanitised += "/"
self.sanitised += ">" self.sanitised += ">"
def add_raw(self, tag, attrs = None):
self.raw += "&lt;"
if inspect.stack()[1][3] == "handle_endtag":
self.raw += "/"
self.raw += tag
if not attrs is None:
for attr in attrs:
if tag == "img" and attr[0] == "src" and not self.allow_picture:
attr[1] = ""
self.raw += " " + attr[0]
if not (attr[1] is None):
self.raw += "=&quot;" + attr[1] + "&quot;"
if inspect.stack()[1][3] == "handle_startendtag":
self.raw += "/"
self.raw += "&gt;"
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if tag in self.acceptable_elements: if tag in self.acceptable_elements:
self.has_html = True self.has_html = True
self.add_if_acceptable(tag, attrs) self.add_if_acceptable(tag, attrs)
self.add_raw(tag, attrs)
def handle_endtag(self, tag): def handle_endtag(self, tag):
self.add_if_acceptable(tag) self.add_if_acceptable(tag)
self.add_raw(tag)
def handle_startendtag(self, tag, attrs): def handle_startendtag(self, tag, attrs):
if tag in self.acceptable_elements: if tag in self.acceptable_elements:
self.has_html = True self.has_html = True
self.add_if_acceptable(tag, attrs) self.add_if_acceptable(tag, attrs)
self.add_raw(tag, attrs)
def handle_data(self, data): def handle_data(self, data):
self.sanitised += unicode(data, 'utf-8', 'replace') self.sanitised += unicode(data, 'utf-8', 'replace')
tmp = data.replace("\n", "<br/>")
self.raw += unicode(tmp, 'utf-8', 'replace')
def handle_charref(self, name): def handle_charref(self, name):
self.sanitised += "&#" + name + ";" self.sanitised += "&#" + name + ";"
self.raw += quote("&#" + name + ";")
def handle_entityref(self, name): def handle_entityref(self, name):
self.sanitised += "&" + name + ";" self.sanitised += "&" + name + ";"
self.raw += quote("&" + name + ";")
def feed(self, data):
HTMLParser.feed(self, data)
tmp = SafeHTMLParser.multi_replace(data)
self.raw += unicode(tmp, 'utf-8', 'replace')
def is_html(self, text = None, allow_picture = False): def is_html(self, text = None, allow_picture = False):
if text: if text:
self.reset() self.reset()