backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-15 00:03:28 +01:00
Code Issues Projects Releases Activity

statusandheaders parsing: properly skip multiline bad headers (missing

Browse Source 
header name and ':'), fixes #49
This commit is contained in:
Ilya Kreymer 2014-11-05 20:26:23 -08:00
parent e4bcef1c8b
commit 00121aa165
2 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pywb/utils/statusandheaders.py
View File

@ -169,7 +169,8 @@ class StatusAndHeadersParser(object):
# append continuation lines, if any
while next_line and next_line.startswith((' ', '\t')):
value += next_line
if value is not None:
value += next_line
next_line, total_read = _strip_count(stream.readline(),
total_read)

12
pywb/utils/test/test_statusandheaders.py
View File

@ -32,6 +32,10 @@ False
# empty
>>> st2 = StatusAndHeadersParser(['HTTP/1.0']).parse(BytesIO(status_headers_2)); x = st2.validate_statusline('204 No Content'); st2
StatusAndHeaders(protocol = '', statusline = '204 No Content', headers = [])
>>> StatusAndHeadersParser(['HTTP/1.0']).parse(BytesIO(status_headers_3))
StatusAndHeaders(protocol = 'HTTP/1.0', statusline = '204 Empty', headers = [('Content-Type', 'Value'), ('Content-Length', '0')])
"""
@ -54,6 +58,14 @@ status_headers_2 = """
"""
status_headers_3 = "\
HTTP/1.0 204 Empty\r\n\
Content-Type: Value\r\n\
%Invalid%\r\n\
\tMultiline\r\n\
Content-Length: 0\r\n\
\r\n"
if __name__ == "__main__":
import doctest