view mercurial/urllibcompat.py @ 36426:23d12524a202

http: drop custom http client logic

Eight and a half years ago, as my starter bug on code.google.com, I
investigated a mysterious "broken pipe" error from seemingly random
clients[0]. That investigation revealed a tragic story: the Python
standard library's httplib was (and remains) barely functional. During
large POSTs, if a server responds early with an error (even a
permission denied error!) the client only notices that the server
closed the connection and everything breaks. Such server behavior is
implicitly legal under RFC 2616 (the latest HTTP RFC as of when I was
last working on this), and my understanding is that later RFCs have
made it explicitly legal to respond early with any status code outside
the 2xx range.

I embarked, probably foolishly, on a journey to write a new http
library with better overall behavior. The http library appears to work
well in most cases, but it can get confused in the presence of
proxies, and it depends on select(2) which limits its utility if a lot
of file descriptors are open. I haven't touched the http library in
almost two years, and in the interim the Python community has
discovered a better way[1] of writing network code. In theory some day
urllib3 will have its own home-grown http library built on h11[2], or
we could do that. Either way, it's time to declare our current
confusingly-named "http2" client logic and move on. I do hope to
revisit this some day: it's still garbage that we can't even respond
with a 401 or 403 without reading the entire POST body from the
client, but the goalposts on writing a new http client library have
moved substantially. We're almost certainly better off just switching
to requests and eventually picking up their http fixes than trying to
live with something that realistically only we'll ever use. Another
approach would be to write an adapter so that Mercurial can use pycurl
if it's installed. Neither of those approaches seem like they should
be investigated prior to a release of Mercurial that works on Python
3: that's where the mindshare is going to be for any improvements to
the state of the http client art.

0: http://web.archive.org/web/20130501031801/http://code.google.com/p/support/issues/detail?id=2716
1: http://sans-io.readthedocs.io/
2: https://github.com/njsmith/h11

Differential Revision: https://phab.mercurial-scm.org/D2444

# 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(_sysstr('_'), _sysstr('')).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, "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")
    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()