hgext/commitextras.py

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

# commitextras.py
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''adds a new flag extras to commit (ADVANCED)'''

from __future__ import absolute_import

import re

from mercurial.i18n import _
from mercurial import (
    commands,
    error,
    extensions,
    registrar,
)

cmdtable = {}
command = registrar.command(cmdtable)
testedwith = 'ships-with-hg-core'

usedinternally = {
    'amend_source',
    'branch',
    'close',
    'histedit_source',
    'topic',
    'rebase_source',
    'intermediate-source',
    '__touch-noise__',
    'source',
    'transplant_source',
}

def extsetup(ui):
    entry = extensions.wrapcommand(commands.table, 'commit', _commit)
    options = entry[1]
    options.append(('', 'extra', [],
        _('set a changeset\'s extra values'), _("KEY=VALUE")))

def _commit(orig, ui, repo, *pats, **opts):
    origcommit = repo.commit
    try:
        def _wrappedcommit(*innerpats, **inneropts):
            extras = opts.get(r'extra')
            if extras:
                for raw in extras:
                    if '=' not in raw:
                        msg = _("unable to parse '%s', should follow "
                                "KEY=VALUE format")
                        raise error.Abort(msg % raw)
                    k, v = raw.split('=', 1)
                    if not k:
                        msg = _("unable to parse '%s', keys can't be empty")
                        raise error.Abort(msg % raw)
                    if re.search('[^\w-]', k):
                        msg = _("keys can only contain ascii letters, digits,"
                                " '_' and '-'")
                        raise error.Abort(msg)
                    if k in usedinternally:
                        msg = _("key '%s' is used internally, can't be set "
                                "manually")
                        raise error.Abort(msg % k)
                    inneropts[r'extra'][k] = v
            return origcommit(*innerpats, **inneropts)

        # This __dict__ logic is needed because the normal
        # extension.wrapfunction doesn't seem to work.
        repo.__dict__[r'commit'] = _wrappedcommit
        return orig(ui, repo, *pats, **opts)
    finally:
        del repo.__dict__[r'commit']