view mercurial/hgweb/request.py @ 35777:0c0689a7565e

subrepo: handle 'C:' style paths on the command line (issue5770) If you think 'C:' and 'C:\' are equivalent paths, see the inline comment before proceeding. The problem here was that several commands that take a URL argument (incoming, outgoing, pull, and push) will use that value to set 'repo._subtoppath' on the repository object after command specific manipulation of it, but before converting it to an absolute path. When an operation is performed on a relative subrepo, subrepo._abssource() will posixpath.join() this value with the relative subrepo path. That adds a '/' after the drive letter, changing how it is evaluated by abspath()/realpath() in vfsmod.vfs(..., realpath=True) as the subrepo is instantiated. I initially tried sanitizing the path in url.localpath(), because url.isabs() only checks that it starts with a drive letter. By the sample behavior, this is clearly not an absolute path. (Though the comment in isabs() is weasely- this style path can't be joined either.) But not everything funnels through there, and it required explicitly calling localpath() in hg.parseurl() and assigning to url.path to fix. But then tests failed with urls like 'a#0'. Next up was sanitizing the path in the url constructor. That caused doctest failures, because there are drive letter tests, so those got expanded in system specific ways. Yuya correctly pointed out that util.url is a parser, and shouldn't be substituting the path too. Rather than fixing every command call site, just convert it in the common subrepo location. I don't see any sanitizing on the path config options, so I fixed those too. Note that while the behavior is fixed here, there are still places where 'comparing with C:' gets printed out, and that's not great for debugging purposes. (Specifically I saw it in `hg incoming -B C:`, without subrepos.) While clone will write out an absolute default path, I wonder what would happen if a user edited that path to be 'C:'. (I don't think supporting relative paths in .hgrc is a sane thing to do, but while we're poking holes in things...) Since this is such an oddball case, it still leaks through in places, and there seems to be a lot of duplicate url parsing, maybe the url parsing should be moved to dispatch, and provide the command with a url object? Then we could convert this to an absolute path once, and not have to worry about it in the rest of the code. I also checked '--cwd C:' on the command line, and it was previously working because os.chdir() will DTRT. Finally, one other note from the url.localpath() experimenting. I don't see any cases where 'self._hostport' can hold a drive letter. So I'm wondering if that is wrong/old code.
author Matt Harbison <matt_harbison@yahoo.com>
date Sun, 21 Jan 2018 13:54:05 -0500
parents 95be8928d6b2
children a0a004b29a51
line wrap: on
line source

# hgweb/request.py - An http request from either CGI or the standalone server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# 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

import cgi
import errno
import socket

from .common import (
    ErrorResponse,
    HTTP_NOT_MODIFIED,
    statusmessage,
)

from .. import (
    pycompat,
    util,
)

shortcuts = {
    'cl': [('cmd', ['changelog']), ('rev', None)],
    'sl': [('cmd', ['shortlog']), ('rev', None)],
    'cs': [('cmd', ['changeset']), ('node', None)],
    'f': [('cmd', ['file']), ('filenode', None)],
    'fl': [('cmd', ['filelog']), ('filenode', None)],
    'fd': [('cmd', ['filediff']), ('node', None)],
    'fa': [('cmd', ['annotate']), ('filenode', None)],
    'mf': [('cmd', ['manifest']), ('manifest', None)],
    'ca': [('cmd', ['archive']), ('node', None)],
    'tags': [('cmd', ['tags'])],
    'tip': [('cmd', ['changeset']), ('node', ['tip'])],
    'static': [('cmd', ['static']), ('file', None)]
}

def normalize(form):
    # first expand the shortcuts
    for k in shortcuts:
        if k in form:
            for name, value in shortcuts[k]:
                if value is None:
                    value = form[k]
                form[name] = value
            del form[k]
    # And strip the values
    for k, v in form.iteritems():
        form[k] = [i.strip() for i in v]
    return form

class wsgirequest(object):
    """Higher-level API for a WSGI request.

    WSGI applications are invoked with 2 arguments. They are used to
    instantiate instances of this class, which provides higher-level APIs
    for obtaining request parameters, writing HTTP output, etc.
    """
    def __init__(self, wsgienv, start_response):
        version = wsgienv[r'wsgi.version']
        if (version < (1, 0)) or (version >= (2, 0)):
            raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                               % version)
        self.inp = wsgienv[r'wsgi.input']
        self.err = wsgienv[r'wsgi.errors']
        self.threaded = wsgienv[r'wsgi.multithread']
        self.multiprocess = wsgienv[r'wsgi.multiprocess']
        self.run_once = wsgienv[r'wsgi.run_once']
        self.env = wsgienv
        self.form = normalize(cgi.parse(self.inp,
                                        self.env,
                                        keep_blank_values=1))
        self._start_response = start_response
        self.server_write = None
        self.headers = []

    def __iter__(self):
        return iter([])

    def read(self, count=-1):
        return self.inp.read(count)

    def drain(self):
        '''need to read all data from request, httplib is half-duplex'''
        length = int(self.env.get('CONTENT_LENGTH') or 0)
        for s in util.filechunkiter(self.inp, limit=length):
            pass

    def respond(self, status, type, filename=None, body=None):
        if not isinstance(type, str):
            type = pycompat.sysstr(type)
        if self._start_response is not None:
            self.headers.append((r'Content-Type', type))
            if filename:
                filename = (filename.rpartition('/')[-1]
                            .replace('\\', '\\\\').replace('"', '\\"'))
                self.headers.append(('Content-Disposition',
                                     'inline; filename="%s"' % filename))
            if body is not None:
                self.headers.append((r'Content-Length', str(len(body))))

            for k, v in self.headers:
                if not isinstance(v, str):
                    raise TypeError('header value must be string: %r' % (v,))

            if isinstance(status, ErrorResponse):
                self.headers.extend(status.headers)
                if status.code == HTTP_NOT_MODIFIED:
                    # RFC 2616 Section 10.3.5: 304 Not Modified has cases where
                    # it MUST NOT include any headers other than these and no
                    # body
                    self.headers = [(k, v) for (k, v) in self.headers if
                                    k in ('Date', 'ETag', 'Expires',
                                          'Cache-Control', 'Vary')]
                status = statusmessage(status.code, str(status))
            elif status == 200:
                status = '200 Script output follows'
            elif isinstance(status, int):
                status = statusmessage(status)

            self.server_write = self._start_response(status, self.headers)
            self._start_response = None
            self.headers = []
        if body is not None:
            self.write(body)
            self.server_write = None

    def write(self, thing):
        if thing:
            try:
                self.server_write(thing)
            except socket.error as inst:
                if inst[0] != errno.ECONNRESET:
                    raise

    def writelines(self, lines):
        for line in lines:
            self.write(line)

    def flush(self):
        return None

    def close(self):
        return None

def wsgiapplication(app_maker):
    '''For compatibility with old CGI scripts. A plain hgweb() or hgwebdir()
    can and should now be used as a WSGI application.'''
    application = app_maker()
    def run_wsgi(env, respond):
        return application(env, respond)
    return run_wsgi