view mercurial/urllibcompat.py @ 42743:8c9a6adec67a

rust-discovery: using the children cache in add_missing

The DAG range computation often needs to get back to very old
revisions, and turns out to be disproportionately long, given
that the end goal is to remove the descendents of the given
missing revisons from the undecided set.

The fast iteration capabilities available in the Rust case make
it possible to avoid the DAG range entirely, at the cost of
precomputing the children cache, and to simply iterate on
children of the given missing revisions.

This is a case where staying on the same side of the interface
between the two languages has clear benefits.

On discoveries with initial undecided sets
small enough to bypass sampling entirely, the total cost of
computing the children cache and the subsequent iteration
becomes better than the Python + C counterpart, which relies on
reachableroots2.

For example, on a repo with more than one million revisions with
an initial undecided set of 11 elements, we get these figures:

Rust version with simple iteration
  addcommons: 57.287us
  first undecided computation: 184.278334ms
  first children cache computation: 131.056us
  addmissings iteration: 42.766us
  first addinfo total: 185.24 ms

Python + C version
  first addcommons: 0.29 ms
  addcommons 0.21 ms
  first undecided computation 191.35 ms
  addmissings 45.75 ms
  first addinfo total: 237.77 ms

On discoveries with large undecided sets, the initial price paid
makes the first addinfo slower than the Python + C version,
but that's more than compensated by the gain in sampling and
subsequent iterations.
Here's an extreme example with an undecided set of a million revisions:

Rust version:
  first undecided computation: 293.842629ms
  first children cache computation: 407.911297ms
  addmissings iteration: 34.312869ms
  first addinfo total: 776.02 ms
  taking initial sample
  query 2: sampling time: 1318.38 ms
  query 2; still undecided: 1005013, sample size is: 200
  addmissings: 143.062us

Python + C version:
  first undecided computation 298.13 ms
  addmissings 80.13 ms
  first addinfo total: 399.62 ms
  taking initial sample
  query 2: sampling time: 3957.23 ms
  query 2; still undecided: 1005013, sample size is: 200
  addmissings 52.88 ms

Differential Revision: https://phab.mercurial-scm.org/D6428

# 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'/'):
        # bytestr has an __iter__ that emits characters. quote_from_bytes()
        # does an iteration and expects ints. We coerce to bytes to appease it.
        if isinstance(s, pycompat.bytestr):
            s = bytes(s)
        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()