view mercurial/urllibcompat.py @ 50338:81c7d04f4722 stable

match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sat, 01 Apr 2023 05:58:59 +0200
parents 642e31cb55f0
children 18c8c18993f0
line wrap: on
line source

# 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.

import http.server
import urllib.error
import urllib.parse
import urllib.request
import urllib.response

from .pycompat import getattr
from . import pycompat

_sysstr = pycompat.sysstr


class _pycompatstub:
    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('_', '').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()

urlreq._registeraliases(
    urllib.parse,
    (
        b"splitattr",
        b"splitpasswd",
        b"splitport",
        b"splituser",
        b"urlparse",
        b"urlunparse",
    ),
)
urlreq._registeralias(urllib.parse, b"parse_qs", b"parseqs")
urlreq._registeralias(urllib.parse, b"parse_qsl", b"parseqsl")
urlreq._registeralias(urllib.parse, b"unquote_to_bytes", b"unquote")

urlreq._registeraliases(
    urllib.request,
    (
        b"AbstractHTTPHandler",
        b"BaseHandler",
        b"build_opener",
        b"FileHandler",
        b"FTPHandler",
        b"ftpwrapper",
        b"HTTPHandler",
        b"HTTPSHandler",
        b"install_opener",
        b"pathname2url",
        b"HTTPBasicAuthHandler",
        b"HTTPDigestAuthHandler",
        b"HTTPPasswordMgrWithDefaultRealm",
        b"ProxyHandler",
        b"Request",
        b"url2pathname",
        b"urlopen",
    ),
)


urlreq._registeraliases(
    urllib.response,
    (
        b"addclosehook",
        b"addinfourl",
    ),
)

urlerr._registeraliases(
    urllib.error,
    (
        b"HTTPError",
        b"URLError",
    ),
)

httpserver._registeraliases(
    http.server,
    (
        b"HTTPServer",
        b"BaseHTTPRequestHandler",
        b"SimpleHTTPRequestHandler",
        b"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='/'):
    # 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