hgweb: parse WSGI request into a data structure
Currently, our WSGI applications (hgweb_mod and hgwebdir_mod) process
the raw WSGI request instance themselves. This means they have to
talk in terms of system strings. And they need to know details
about what's in the WSGI request. And in the case of hgweb_mod, it
is doing some very funky things with URL parsing to impact
dispatching. The code is difficult to read and maintain.
This commit introduces parsing of the WSGI request into a higher-level
and easier-to-reason-about data structure.
To prove it works, we hook it up to hgweb_mod and use it for populating
the relative URL on the request instance.
We hold off on using it in more places because the logic in hgweb_mod
is crazy and I don't want to involve those changes with review of
the parsing code.
The URL construction code has variations that use the HTTP: Host header
(the canonical WSGI way of reconstructing the URL) and with the use
of SERVER_NAME. We need to differentiate because hgweb is currently
using SERVER_NAME for URL construction.
Differential Revision: https://phab.mercurial-scm.org/D2734
"""test line matching with some failing examples and some which warn
run-test.t only checks positive matches and can not see warnings
(both by design)
"""
from __future__ import absolute_import, print_function
import doctest
import os
import re
# this is hack to make sure no escape characters are inserted into the output
if 'TERM' in os.environ:
del os.environ['TERM']
run_tests = __import__('run-tests')
def prn(ex):
m = ex.args[0]
if isinstance(m, str):
print(m)
else:
print(m.decode('utf-8'))
def lm(expected, output):
r"""check if output matches expected
does it generally work?
>>> lm(b'H*e (glob)\n', b'Here\n')
True
fail on bad test data
>>> try: lm(b'a\n',b'a')
... except AssertionError as ex: print(ex)
missing newline
>>> try: lm(b'single backslash\n', b'single \backslash\n')
... except AssertionError as ex: prn(ex)
single backslash or unknown char
"""
assert (expected.endswith(b'\n')
and output.endswith(b'\n')), 'missing newline'
assert not re.search(br'[^ \w\\/\r\n()*?]', expected + output), \
b'single backslash or unknown char'
test = run_tests.TTest(b'test-run-test.t', b'.', b'.')
match = test.linematch(expected, output)
if isinstance(match, str):
return 'special: ' + match
elif isinstance(match, bytes):
return 'special: ' + match.decode('utf-8')
else:
return bool(match) # do not return match object
def wintests():
r"""test matching like running on windows
enable windows matching on any os
>>> _osaltsep = os.altsep
>>> os.altsep = True
>>> _osname = os.name
>>> os.name = 'nt'
valid match on windows
>>> lm(b'g/a*/d (glob)\n', b'g\\abc/d\n')
True
direct matching, glob unnecessary
>>> lm(b'g/b (glob)\n', b'g/b\n')
'special: -glob'
missing glob
>>> lm(b'/g/c/d/fg\n', b'\\g\\c\\d/fg\n')
True
>>> lm(b'/g/c/d/fg\n', b'\\g\\c\\d\\fg\r\n')
True
restore os.altsep
>>> os.altsep = _osaltsep
>>> os.name = _osname
"""
pass
def otherostests():
r"""test matching like running on non-windows os
disable windows matching on any os
>>> _osaltsep = os.altsep
>>> os.altsep = False
>>> _osname = os.name
>>> os.name = 'nt'
backslash does not match slash
>>> lm(b'h/a* (glob)\n', b'h\\ab\n')
False
direct matching glob can not be recognized
>>> lm(b'h/b (glob)\n', b'h/b\n')
True
missing glob can not not be recognized
>>> lm(b'/h/c/df/g/\n', b'\\h/c\\df/g\\\n')
False
restore os.altsep
>>> os.altsep = _osaltsep
>>> os.name = _osname
"""
pass
if __name__ == '__main__':
doctest.testmod()