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

HTML parser fix

Browse Source 
- URLs followed with space were broken
This commit is contained in:
Peter Šurda 2017-02-28 22:47:56 +01:00
parent b7e75b9bc5
commit 171bc83ec0
Signed by untrusted user: PeterSurda
GPG Key ID: 0C5F50C0B5F37D87
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/bitmessageqt/safehtmlparser.py
View File

@ -19,15 +19,22 @@ 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/>"], ["\t", "&nbsp;&nbsp;&nbsp;&nbsp;"], [" ", "&nbsp; "], [" ", "&nbsp; "], ["<br/> ", "<br/>&nbsp;"]] replaces_pre = [["&", "&amp;"], ["\"", "&quot;"], ["<", "&lt;"], [">", "&gt;"]]
replaces_post = [["\n", "<br/>"], ["\t", "&nbsp;&nbsp;&nbsp;&nbsp;"], [" ", "&nbsp; "], [" ", "&nbsp; "], ["<br/> ", "<br/>&nbsp;"]]
src_schemes = [ "data" ] src_schemes = [ "data" ]
uriregex1 = re.compile(r'(?i)\b((?:(https?|ftp|bitcoin):(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>?]))') uriregex1 = re.compile(r'(?i)\b((?:(https?|ftp|bitcoin):(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>?]))')
uriregex2 = re.compile(r'<a href="([^"]+)&amp;') uriregex2 = re.compile(r'<a href="([^"]+)&amp;')
emailregex = re.compile(r'\b([A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,})\b') emailregex = re.compile(r'\b([A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,})\b')
@staticmethod @staticmethod
def multi_replace(text): def replace_pre(text):
for a in SafeHTMLParser.replaces: for a in SafeHTMLParser.replaces_pre:
text = text.replace(a[0], a[1])
return text
@staticmethod
def replace_post(text):
for a in SafeHTMLParser.replaces_post:
text = text.replace(a[0], a[1]) text = text.replace(a[0], a[1])
if len(text) > 1 and text[0] == " ": if len(text) > 1 and text[0] == " ":
text = "&nbsp;" + text[1:] text = "&nbsp;" + text[1:]
@ -95,12 +102,13 @@ class SafeHTMLParser(HTMLParser):
except UnicodeDecodeError: except UnicodeDecodeError:
data = unicode(data, 'utf-8', errors='replace') data = unicode(data, 'utf-8', errors='replace')
HTMLParser.feed(self, data) HTMLParser.feed(self, data)
tmp = SafeHTMLParser.multi_replace(data) tmp = SafeHTMLParser.replace_pre(data)
tmp = SafeHTMLParser.uriregex1.sub( tmp = SafeHTMLParser.uriregex1.sub(
r'<a href="\1">\1</a>', r'<a href="\1">\1</a>',
tmp) tmp)
tmp = SafeHTMLParser.uriregex2.sub(r'<a href="\1&', tmp) tmp = SafeHTMLParser.uriregex2.sub(r'<a href="\1&', tmp)
tmp = SafeHTMLParser.emailregex.sub(r'<a href="mailto:\1">\1</a>', tmp) tmp = SafeHTMLParser.emailregex.sub(r'<a href="mailto:\1">\1</a>', tmp)
tmp = SafeHTMLParser.replace_post(tmp)
self.raw += tmp self.raw += tmp
def is_html(self, text = None, allow_picture = False): def is_html(self, text = None, allow_picture = False):