rnhmjoj/qutebrowser
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Replaced quote-printable with own function

Browse Source 
The original one had some inconsistencies that lead to bugs.

The content-type of the root document now also contains the charset.
This commit is contained in:
Daniel 2015-09-20 16:05:36 +02:00
parent 930871be01
commit 024ae52366
1 changed files with 29 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
qutebrowser/misc/mhtml.py
View File

@ -53,12 +53,33 @@ def _chunked_base64(data, maxlen=76, linesep=b"\r\n"):
def _rn_quopri(data): def _rn_quopri(data):
"""Return a quoted-printable representation of data.""" """Return a quoted-printable representation of data."""
orig_funcs = (quopri.b2a_qp, quopri.a2b_qp) # See RFC 2045 https://tools.ietf.org/html/rfc2045#section-6.7
# Workaround for quopri mixing \n and \r\n # The stdlib version in the quopri module has inconsistencies with line
quopri.b2a_qp = quopri.a2b_qp = None # endings and breaks up character escapes over multiple lines, which isn't
encoded = quopri.encodestring(data) # understood by qute and leads to jumbled text
quopri.b2a_qp, quopri.a2b_qp = orig_funcs MAXLEN = 76
return encoded.replace(b"\n", b"\r\n") WHITESPACE = {ord(b"\t"), ord(b" ")}
output = []
current_line = b""
for byte in data:
# Literal representation according to (2) and (3)
if (ord(b"!") <= byte <= ord(b"<") or
ord(b">") <= byte <= ord(b"~") or
byte in WHITESPACE):
current_line += bytes([byte])
else:
current_line += b"=" + "{:02X}".format(byte).encode("ascii")
if len(current_line) >= MAXLEN:
# We need to account for the = character
split = [current_line[:MAXLEN-1], current_line[MAXLEN-1:]]
quoted_pos = split[0].rfind(b"=")
if quoted_pos + 2 >= MAXLEN - 1:
split[0], token = split[0][:quoted_pos], split[0][quoted_pos:]
split[1] = token + split[1]
current_line = split[1]
output.append(split[0] + b"=")
output.append(current_line)
return b"\r\n".join(output)
E_NONE = (None, lambda x: x) E_NONE = (None, lambda x: x)
@ -86,7 +107,7 @@ class MHTMLWriter(object):
self._files = {} self._files = {}
def add_file(self, location, content, content_type=None, def add_file(self, location, content, content_type=None,
transfer_encoding=E_BASE64): transfer_encoding=E_QUOPRI):
"""Add a file to the given MHTML collection. """Add a file to the given MHTML collection.
Args: Args:
@ -178,7 +199,7 @@ def start_download(dest):
# I've found no way of getting the content type of a QWebView, but since # I've found no way of getting the content type of a QWebView, but since
# we're using .toHtml, it's probably safe to say that the content-type is # we're using .toHtml, it's probably safe to say that the content-type is
# HTML # HTML
writer.content_type = "text/html" writer.content_type = 'text/html; charset="UTF-8"'
# Currently only downloading <link> (stylesheets), <script> (javascript) and # Currently only downloading <link> (stylesheets), <script> (javascript) and
# <img> (image) elements. # <img> (image) elements.
elements = (web_frame.findAllElements("link") + elements = (web_frame.findAllElements("link") +