view contrib/check-config.py @ 36858:01f6bba64424

hgweb: remove support for POST form data (BC)

Previously, we called out to cgi.parse(), which for POST requests
parsed multipart/form-data and application/x-www-form-urlencoded
Content-Type requests for form data, combined it with query string
parameters, returned a union of the values.

As far as I know, nothing in Mercurial actually uses this mechanism
to submit data to the HTTP server. The wire protocol has its own
mechanism for passing parameters. And the web interface only does
GET requests. Removing support for parsing POST data doesn't break
any tests.

Another reason to not like this feature is that cgi.parse() may
modify the QUERY_STRING environment variable as a side-effect.
In addition, it merges both POST data and the query string into
one data structure. This prevents consumers from knowing whether
a variable came from the query string or POST data. That can matter
for some operations.

I suspect we use cgi.parse() because back when this code was
initially implemented, it was the function that was readily
available. In other words, I don't think there was conscious
choice to support POST data: we just got it because cgi.parse()
supported it.

Since nothing uses the feature and it is untested, let's remove
support for parsing POST form data. We can add it back in easily
enough if we need it in the future.

.. bc::

   Hgweb no longer reads form data in POST requests from
   multipart/form-data and application/x-www-form-urlencoded
   requests. Arguments should be specified as URL path components
   or in the query string in the URL instead.

Differential Revision: https://phab.mercurial-scm.org/D2774

#!/usr/bin/env python
#
# check-config - a config flag documentation checker for Mercurial
#
# Copyright 2015 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function
import re
import sys

foundopts = {}
documented = {}
allowinconsistent = set()

configre = re.compile(br'''
    # Function call
    ui\.config(?P<ctype>|int|bool|list)\(
        # First argument.
        ['"](?P<section>\S+)['"],\s*
        # Second argument
        ['"](?P<option>\S+)['"](,\s+
        (?:default=)?(?P<default>\S+?))?
    \)''', re.VERBOSE | re.MULTILINE)

configwithre = re.compile(b'''
    ui\.config(?P<ctype>with)\(
        # First argument is callback function. This doesn't parse robustly
        # if it is e.g. a function call.
        [^,]+,\s*
        ['"](?P<section>\S+)['"],\s*
        ['"](?P<option>\S+)['"](,\s+
        (?:default=)?(?P<default>\S+?))?
    \)''', re.VERBOSE | re.MULTILINE)

configpartialre = (br"""ui\.config""")

ignorere = re.compile(br'''
    \#\s(?P<reason>internal|experimental|deprecated|developer|inconsistent)\s
    config:\s(?P<config>\S+\.\S+)$
    ''', re.VERBOSE | re.MULTILINE)

def main(args):
    for f in args:
        sect = b''
        prevname = b''
        confsect = b''
        carryover = b''
        linenum = 0
        for l in open(f, 'rb'):
            linenum += 1

            # check topic-like bits
            m = re.match(b'\s*``(\S+)``', l)
            if m:
                prevname = m.group(1)
            if re.match(b'^\s*-+$', l):
                sect = prevname
                prevname = b''

            if sect and prevname:
                name = sect + b'.' + prevname
                documented[name] = 1

            # check docstring bits
            m = re.match(br'^\s+\[(\S+)\]', l)
            if m:
                confsect = m.group(1)
                continue
            m = re.match(br'^\s+(?:#\s*)?(\S+) = ', l)
            if m:
                name = confsect + b'.' + m.group(1)
                documented[name] = 1

            # like the bugzilla extension
            m = re.match(br'^\s*(\S+\.\S+)$', l)
            if m:
                documented[m.group(1)] = 1

            # like convert
            m = re.match(br'^\s*:(\S+\.\S+):\s+', l)
            if m:
                documented[m.group(1)] = 1

            # quoted in help or docstrings
            m = re.match(br'.*?``(\S+\.\S+)``', l)
            if m:
                documented[m.group(1)] = 1

            # look for ignore markers
            m = ignorere.search(l)
            if m:
                if m.group('reason') == 'inconsistent':
                    allowinconsistent.add(m.group('config'))
                else:
                    documented[m.group('config')] = 1

            # look for code-like bits
            line = carryover + l
            m = configre.search(line) or configwithre.search(line)
            if m:
                ctype = m.group('ctype')
                if not ctype:
                    ctype = 'str'
                name = m.group('section') + "." + m.group('option')
                default = m.group('default')
                if default in (None, 'False', 'None', '0', '[]', '""', "''"):
                    default = ''
                if re.match(b'[a-z.]+$', default):
                    default = '<variable>'
                if (name in foundopts and (ctype, default) != foundopts[name]
                    and name not in allowinconsistent):
                    print(l.rstrip())
                    print("conflict on %s: %r != %r" % (name, (ctype, default),
                                                        foundopts[name]))
                    print("at %s:%d:" % (f, linenum))
                foundopts[name] = (ctype, default)
                carryover = ''
            else:
                m = re.search(configpartialre, line)
                if m:
                    carryover = line
                else:
                    carryover = ''

    for name in sorted(foundopts):
        if name not in documented:
            if not (name.startswith("devel.") or
                    name.startswith("experimental.") or
                    name.startswith("debug.")):
                ctype, default = foundopts[name]
                if default:
                    default = ' [%s]' % default
                print("undocumented: %s (%s)%s" % (name, ctype, default))

if __name__ == "__main__":
    if len(sys.argv) > 1:
        sys.exit(main(sys.argv[1:]))
    else:
        sys.exit(main([l.rstrip() for l in sys.stdin]))