outgoing: rework the handling of the `missingroots` case to be faster
The previous implementation was slow, to the point it was taking a significant
amount of `hg bundle --type none-streamv2` call. We rework the code to compute
the same value much faster, making the operation disappear from the `hg bundle
--type none-streamv2` profile. Someone would remark that producing a streamclone
does not requires an `outgoing` object. However that is a matter for another
day. There is other user of `missingroots` (non stream `hg bundle` call for
example), and they will also benefit from this rework.
We implement an old TODO in the process, directly computing the missing and
common attribute as we have most element at hand already.
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 7.750458
after: 6.665565 (-14.00%, -1.08)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 0.700229
after: 0.496050 (-29.16%, -0.20)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 346.508952
after: 316.749699 (-8.59%, -29.76)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 3.401700
after: 2.915810 (-14.28%, -0.49)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 1.870798
after: 1.461583 (-21.87%, -0.41)
note: this whole `missingroots` of outgoing has a limited number of callers and
could likely be replace by something simpler (like taking an explicit
"missing_revs" set for example). However this is a wider change and we focus on
a small impact, quick rework that does not change the API for now.
# 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 . 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