view mercurial/urllibcompat.py @ 37054:40206e227412

wireproto: define and implement protocol for issuing requests

The existing HTTP and SSH wire protocols suffer from a host of flaws
and shortcomings. I've been wanting to rewrite the protocol for a while
now. Supporting partial clone - which will require new wire protocol
commands and capabilities - and other advanced server functionality
will be much easier if we start from a clean slate and don't have
to be constrained by limitations of the existing wire protocol.

This commit starts to introduce a new data exchange format for
use over the wire protocol.

The new protocol is built on top of "frames," which are atomic
units of metadata + data. Frames will make it easier to implement
proxies and other mechanisms that want to inspect data without
having to maintain state. The existing frame metadata is very
minimal and it will evolve heavily. (We will eventually support
things like concurrent requests, out-of-order responses,
compression, side-channels for status updates, etc. Some of
these will require additions to the frame header.)

Another benefit of frames is that all reads are of a fixed size.
A reader works by consuming a frame header, extracting the payload
length, then reading that many bytes. No lookahead, buffering, or
memory reallocations are needed.

The new protocol attempts to be transport agnostic. I want all that's
required to use the new protocol to be a pair of unidirectional,
half-duplex pipes. (Yes, we will eventually make use of full-duplex
pipes, but that's for another commit.) Notably, when the SSH
transport switches to this new protocol, stderr will be unused.
This is by design: the lack of stderr on HTTP harms protocol
behavior there. By shoehorning everything into a pair of pipes,
we can have more consistent behavior across transports.

We currently only define the client side parts of the new protocol,
specifically the bits for requesting that a command run. This keeps
the new code and feature small and somewhat easy to review.

We add support to `hg debugwireproto` for writing frames into
HTTP request bodies. Our tests that issue commands to the new
HTTP endpoint have been updated to transmit frames. The server
bits haven't been touched to consume the frames yet. This will
occur in the next commit...

Astute readers may notice that the command name is transmitted in
both the HTTP request URL and the command request frame. This is
partially a kludge from me initially implementing the frame-based
protocol for SSH first. But it is also a feature: I intend to
eventually support issuing multiple commands per HTTP request. This
will allow us to replace the abomination that is the "batch" wire
protocol command with a protocol-level mechanism for performing
multi-dispatch. Because I want the frame-based protocol to be
as similar as possible across transports, I'd rather we (redundantly)
include the command name in the frame than differ behavior between
transports that have out-of-band routing information (like HTTP)
readily available.

Differential Revision: https://phab.mercurial-scm.org/D2851

# urllibcompat.py - adapters to ease using urllib2 on Py2 and urllib on Py3
#
# Copyright 2017 Google, Inc.
#
# 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

from . import pycompat

_sysstr = pycompat.sysstr

class _pycompatstub(object):
    def __init__(self):
        self._aliases = {}

    def _registeraliases(self, origin, items):
        """Add items that will be populated at the first access"""
        items = map(_sysstr, items)
        self._aliases.update(
            (item.replace(r'_', r'').lower(), (origin, item))
            for item in items)

    def _registeralias(self, origin, attr, name):
        """Alias ``origin``.``attr`` as ``name``"""
        self._aliases[_sysstr(name)] = (origin, _sysstr(attr))

    def __getattr__(self, name):
        try:
            origin, item = self._aliases[name]
        except KeyError:
            raise AttributeError(name)
        self.__dict__[name] = obj = getattr(origin, item)
        return obj

httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()

if pycompat.ispy3:
    import urllib.parse
    urlreq._registeraliases(urllib.parse, (
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "urlparse",
        "urlunparse",
    ))
    urlreq._registeralias(urllib.parse, "parse_qs", "parseqs")
    urlreq._registeralias(urllib.parse, "parse_qsl", "parseqsl")
    urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote")
    import urllib.request
    urlreq._registeraliases(urllib.request, (
        "AbstractHTTPHandler",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "ftpwrapper",
        "HTTPHandler",
        "HTTPSHandler",
        "install_opener",
        "pathname2url",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "HTTPPasswordMgrWithDefaultRealm",
        "ProxyHandler",
        "Request",
        "url2pathname",
        "urlopen",
    ))
    import urllib.response
    urlreq._registeraliases(urllib.response, (
        "addclosehook",
        "addinfourl",
    ))
    import urllib.error
    urlerr._registeraliases(urllib.error, (
        "HTTPError",
        "URLError",
    ))
    import http.server
    httpserver._registeraliases(http.server, (
        "HTTPServer",
        "BaseHTTPRequestHandler",
        "SimpleHTTPRequestHandler",
        "CGIHTTPRequestHandler",
    ))

    # urllib.parse.quote() accepts both str and bytes, decodes bytes
    # (if necessary), and returns str. This is wonky. We provide a custom
    # implementation that only accepts bytes and emits bytes.
    def quote(s, safe=r'/'):
        s = urllib.parse.quote_from_bytes(s, safe=safe)
        return s.encode('ascii', 'strict')

    # urllib.parse.urlencode() returns str. We use this function to make
    # sure we return bytes.
    def urlencode(query, doseq=False):
            s = urllib.parse.urlencode(query, doseq=doseq)
            return s.encode('ascii')

    urlreq.quote = quote
    urlreq.urlencode = urlencode

    def getfullurl(req):
        return req.full_url

    def gethost(req):
        return req.host

    def getselector(req):
        return req.selector

    def getdata(req):
        return req.data

    def hasdata(req):
        return req.data is not None
else:
    import BaseHTTPServer
    import CGIHTTPServer
    import SimpleHTTPServer
    import urllib2
    import urllib
    import urlparse
    urlreq._registeraliases(urllib, (
        "addclosehook",
        "addinfourl",
        "ftpwrapper",
        "pathname2url",
        "quote",
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "unquote",
        "url2pathname",
        "urlencode",
    ))
    urlreq._registeraliases(urllib2, (
        "AbstractHTTPHandler",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "HTTPHandler",
        "HTTPPasswordMgrWithDefaultRealm",
        "HTTPSHandler",
        "install_opener",
        "ProxyHandler",
        "Request",
        "urlopen",
    ))
    urlreq._registeraliases(urlparse, (
        "urlparse",
        "urlunparse",
    ))
    urlreq._registeralias(urlparse, "parse_qs", "parseqs")
    urlreq._registeralias(urlparse, "parse_qsl", "parseqsl")
    urlerr._registeraliases(urllib2, (
        "HTTPError",
        "URLError",
    ))
    httpserver._registeraliases(BaseHTTPServer, (
        "HTTPServer",
        "BaseHTTPRequestHandler",
    ))
    httpserver._registeraliases(SimpleHTTPServer, (
        "SimpleHTTPRequestHandler",
    ))
    httpserver._registeraliases(CGIHTTPServer, (
        "CGIHTTPRequestHandler",
    ))

    def gethost(req):
        return req.get_host()

    def getselector(req):
        return req.get_selector()

    def getfullurl(req):
        return req.get_full_url()

    def getdata(req):
        return req.get_data()

    def hasdata(req):
        return req.has_data()