Bitmessage/PyBitmessage-2024-12-03
Archived
2
0
Fork 0
Code Issues 168 Pull Requests 53 Actions Packages Projects Releases 5 Wiki Activity

flake8 for bitmessageqt.safehtmlparser (with docstrings from #1368)

Browse Source
This commit is contained in:
Dmitri Bogomolov 2018-11-16 16:58:12 +02:00
parent 97366ede73
commit e8bd427b9f
Signed by untrusted user: g1itch
GPG Key ID: 720A756F18DEED13
1 changed files with 62 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
src/bitmessageqt/safehtmlparser.py
View File

@ -1,12 +1,18 @@
from HTMLParser import HTMLParser
"""Subclass of HTMLParser.HTMLParser for MessageView widget"""
import inspect
import re
from urllib import quote, quote_plus
from HTMLParser import HTMLParser
from urllib import quote_plus
from urlparse import urlparse
class SafeHTMLParser(HTMLParser):
"""HTML parser with sanitisation"""
# from html5lib.sanitiser
acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area',
acceptable_elements = (
'a', 'abbr', 'acronym', 'address', 'area',
'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
@ -18,34 +24,50 @@ class SafeHTMLParser(HTMLParser):
'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
replaces_pre = [["&", "&amp;"], ["\"", "&quot;"], ["<", "&lt;"], [">", "&gt;"]]
replaces_post = [["\n", "<br/>"], ["\t", "&nbsp;&nbsp;&nbsp;&nbsp;"], [" ", "&nbsp; "], [" ", "&nbsp; "], ["<br/> ", "<br/>&nbsp;"]]
'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video'
)
replaces_pre = (
("&", "&amp;"), ("\"", "&quot;"), ("<", "&lt;"), (">", "&gt;"))
replaces_post = (
("\n", "<br/>"), ("\t", "&nbsp;&nbsp;&nbsp;&nbsp;"),
(" ", "&nbsp; "), (" ", "&nbsp; "), ("<br/> ", "<br/>&nbsp;"))
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'((https?|ftp|bitcoin):(?:/{1,3}|[a-z0-9%])(?:[a-zA-Z]|[0-9]|[$-_@.&+#]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+)')
# uriregex1 = re.compile(
# r'(?i)\b((?:(https?|ftp|bitcoin):(?:/{1,3}|[a-z0-9%])'
# r'|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)'
# r'(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))'
# r'+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>?]))')
uriregex1 = re.compile(
r'((https?|ftp|bitcoin):(?:/{1,3}|[a-z0-9%])'
r'(?:[a-zA-Z]|[0-9]|[$-_@.&+#]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+)'
)
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
def replace_pre(text):
"""Perform substring replacement before regex replacements"""
for a in SafeHTMLParser.replaces_pre:
text = text.replace(a[0], a[1])
text = text.replace(*a)
return text
@staticmethod
def replace_post(text):
"""Perform substring replacement after regex replacements"""
for a in SafeHTMLParser.replaces_post:
text = text.replace(a[0], a[1])
text = text.replace(*a)
if len(text) > 1 and text[0] == " ":
text = "&nbsp;" + text[1:]
return text
def __init__(self, *args, **kwargs):
HTMLParser.__init__(self, *args, **kwargs)
self.reset()
self.reset_safe()
def reset_safe(self):
"""Reset runtime variables specific to this class"""
self.elements = set()
self.raw = u""
self.sanitised = u""
@ -54,7 +76,8 @@ class SafeHTMLParser(HTMLParser):
self.allow_external_src = False
def add_if_acceptable(self, tag, attrs=None):
if tag not in SafeHTMLParser.acceptable_elements:
"""Add tag if it passes sanitisation"""
if tag not in self.acceptable_elements:
return
self.sanitised += "<"
if inspect.stack()[1][3] == "handle_endtag":
@ -66,7 +89,7 @@ class SafeHTMLParser(HTMLParser):
val = ""
elif attr == "src" and not self.allow_external_src:
url = urlparse(val)
if url.scheme not in SafeHTMLParser.src_schemes:
if url.scheme not in self.src_schemes:
val = ""
self.sanitised += " " + quote_plus(attr)
if not (val is None):
@ -76,7 +99,7 @@ class SafeHTMLParser(HTMLParser):
self.sanitised += ">"
def handle_starttag(self, tag, attrs):
if tag in SafeHTMLParser.acceptable_elements:
if tag in self.acceptable_elements:
self.has_html = True
self.add_if_acceptable(tag, attrs)
@ -84,7 +107,7 @@ class SafeHTMLParser(HTMLParser):
self.add_if_acceptable(tag)
def handle_startendtag(self, tag, attrs):
if tag in SafeHTMLParser.acceptable_elements:
if tag in self.acceptable_elements:
self.has_html = True
self.add_if_acceptable(tag, attrs)
@ -104,15 +127,14 @@ class SafeHTMLParser(HTMLParser):
data = unicode(data, 'utf-8', errors='replace')
HTMLParser.feed(self, data)
tmp = SafeHTMLParser.replace_pre(data)
tmp = SafeHTMLParser.uriregex1.sub(
r'<a href="\1">\1</a>',
tmp)
tmp = SafeHTMLParser.uriregex2.sub(r'<a href="\1&', tmp)
tmp = SafeHTMLParser.emailregex.sub(r'<a href="mailto:\1">\1</a>', tmp)
tmp = self.uriregex1.sub(r'<a href="\1">\1</a>', tmp)
tmp = self.uriregex2.sub(r'<a href="\1&', tmp)
tmp = self.emailregex.sub(r'<a href="mailto:\1">\1</a>', tmp)
tmp = SafeHTMLParser.replace_post(tmp)
self.raw += tmp
def is_html(self, text=None, allow_picture=False):
"""Detect if string contains HTML tags"""
if text:
self.reset()
self.reset_safe()