mercurial/posix.py

copies: cache the ancestor checking call when tracing copy

A good share of the time spent in this function is spent doing ancestors
checking. To avoid spending time in duplicated call, we cache the result of
calls.

In the slower case, this provide a quite significant performance boost. Below
are the result for a set of selected pairs (many of them pathological):

(And further down is another table that summarize the current state of filelog
based vs changeset base copy tracing)


The benchmark have been configured to be killed after 6 minutes of runtime,
which mean that any detect slower than 2 minutes will be marked as "killed".
This drop some useful information about how much slower these case are… but also
prevent 99% of the benchmark time to be spent on case that can be labelled "very
slow" anyway.


Repo            Case                                  Source-Rev   Dest-Rev         Old-Time      New-Time     Difference   Factor
------------------------------------------------------------------------------------------------------------------------------------
mercurial       x_revs_x_added_0_copies               ad6b123de1c7 39cfcef4f463 :   0.000044 s,   0.000044 s,  +0.000000 s, × 1.0000
mercurial       x_revs_x_added_x_copies               2b1c78674230 0c1d10351869 :   0.000138 s,   0.000138 s,  +0.000000 s, × 1.0000
mercurial       x000_revs_x000_added_x_copies         81f8ff2a9bf2 dd3267698d84 :   0.005067 s,   0.005052 s,  -0.000015 s, × 0.9970
pypy            x_revs_x_added_0_copies               aed021ee8ae8 099ed31b181b :   0.000218 s,   0.000219 s,  +0.000001 s, × 1.0046
pypy            x_revs_x000_added_0_copies            4aa4e1f8e19a 359343b9ac0e :   0.000053 s,   0.000055 s,  +0.000002 s, × 1.0377
pypy            x_revs_x_added_x_copies               ac52eb7bbbb0 72e022663155 :   0.000125 s,   0.000128 s,  +0.000003 s, × 1.0240
pypy            x_revs_x00_added_x_copies             c3b14617fbd7 ace7255d9a26 :   0.001098 s,   0.001089 s,  -0.000009 s, × 0.9918
pypy            x_revs_x000_added_x000_copies         df6f7a526b60 a83dc6a2d56f :   0.017546 s,   0.017407 s,  -0.000139 s, × 0.9921
pypy            x000_revs_xx00_added_0_copies         89a76aede314 2f22446ff07e :   0.096723 s,   0.094175 s,  -0.002548 s, × 0.9737
pypy            x000_revs_x000_added_x_copies         8a3b5bfd266e 2c68e87c3efe :   0.271796 s,   0.238009 s,  -0.033787 s, × 0.8757
pypy            x000_revs_x000_added_x000_copies      89a76aede314 7b3dda341c84 :   0.128602 s,   0.125876 s,  -0.002726 s, × 0.9788
pypy            x0000_revs_x_added_0_copies           d1defd0dc478 c9cb1334cc78 :   7.086742 s,   3.581556 s,  -3.505186 s, × 0.5054
pypy            x0000_revs_xx000_added_0_copies       bf2c629d0071 4ffed77c095c :   0.016634 s,   0.016721 s,  +0.000087 s, × 1.0052
pypy            x0000_revs_xx000_added_x000_copies    08ea3258278e d9fa043f30c0 :   0.254225 s,   0.242367 s,  -0.011858 s, × 0.9534
netbeans        x_revs_x_added_0_copies               fb0955ffcbcd a01e9239f9e7 :   0.000166 s,   0.000165 s,  -0.000001 s, × 0.9940
netbeans        x_revs_x000_added_0_copies            6f360122949f 20eb231cc7d0 :   0.000118 s,   0.000114 s,  -0.000004 s, × 0.9661
netbeans        x_revs_x_added_x_copies               1ada3faf6fb6 5a39d12eecf4 :   0.000296 s,   0.000296 s,  +0.000000 s, × 1.0000
netbeans        x_revs_x00_added_x_copies             35be93ba1e2c 9eec5e90c05f :   0.001137 s,   0.001124 s,  -0.000013 s, × 0.9886
netbeans        x000_revs_xx00_added_0_copies         eac3045b4fdd 51d4ae7f1290 :   0.014133 s,   0.013060 s,  -0.001073 s, × 0.9241
netbeans        x000_revs_x000_added_x_copies         e2063d266acd 6081d72689dc :   0.016988 s,   0.017112 s,  +0.000124 s, × 1.0073
netbeans        x000_revs_x000_added_x000_copies      ff453e9fee32 411350406ec2 :   0.676361 s,   0.660350 s,  -0.016011 s, × 0.9763
netbeans        x0000_revs_xx000_added_x000_copies    588c2d1ced70 1aad62e59ddd :  12.515149 s,  10.032499 s,  -2.482650 s, × 0.8016
mozilla-central x_revs_x_added_0_copies               3697f962bb7b 7015fcdd43a2 :   0.000186 s,   0.000189 s,  +0.000003 s, × 1.0161
mozilla-central x_revs_x000_added_0_copies            dd390860c6c9 40d0c5bed75d :   0.000459 s,   0.000462 s,  +0.000003 s, × 1.0065
mozilla-central x_revs_x_added_x_copies               8d198483ae3b 14207ffc2b2f :   0.000273 s,   0.000270 s,  -0.000003 s, × 0.9890
mozilla-central x_revs_x00_added_x_copies             98cbc58cc6bc 446a150332c3 :   0.001503 s,   0.001474 s,  -0.000029 s, × 0.9807
mozilla-central x_revs_x000_added_x000_copies         3c684b4b8f68 0a5e72d1b479 :   0.004862 s,   0.004806 s,  -0.000056 s, × 0.9885
mozilla-central x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :   0.088291 s,   0.085150 s,  -0.003141 s, × 0.9644
mozilla-central x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :   0.007113 s,   0.007064 s,  -0.000049 s, × 0.9931
mozilla-central x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :   0.004687 s,   0.004741 s,  +0.000054 s, × 1.0115
mozilla-central x000_revs_x000_added_x000_copies      7c97034feb78 4407bd0c6330 :   0.198710 s,   0.190133 s,  -0.008577 s, × 0.9568
mozilla-central x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :   0.036068 s,   0.035651 s,  -0.000417 s, × 0.9884
mozilla-central x0000_revs_xx000_added_x000_copies    f78c615a656c 96a38b690156 :   0.465362 s,   0.440694 s,  -0.024668 s, × 0.9470
mozilla-central x00000_revs_x0000_added_x0000_copies  6832ae71433c 4c222a1d9a00 :  24.519684 s,  18.454163 s,  -6.065521 s, × 0.7526
mozilla-central x00000_revs_x00000_added_x000_copies  76caed42cf7c 1daa622bbe42 :  42.711897 s,  31.562719 s, -11.149178 s, × 0.7390
mozilla-try     x_revs_x_added_0_copies               aaf6dde0deb8 9790f499805a :   0.001201 s,   0.001189 s,  -0.000012 s, × 0.9900
mozilla-try     x_revs_x000_added_0_copies            d8d0222927b4 5bb8ce8c7450 :   0.001216 s,   0.001204 s,  -0.000012 s, × 0.9901
mozilla-try     x_revs_x_added_x_copies               092fcca11bdb 936255a0384a :   0.000595 s,   0.000586 s,  -0.000009 s, × 0.9849
mozilla-try     x_revs_x00_added_x_copies             b53d2fadbdb5 017afae788ec :   0.001856 s,   0.001845 s,  -0.000011 s, × 0.9941
mozilla-try     x_revs_x000_added_x000_copies         20408ad61ce5 6f0ee96e21ad :   0.064936 s,   0.063822 s,  -0.001114 s, × 0.9828
mozilla-try     x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :   0.090601 s,   0.088038 s,  -0.002563 s, × 0.9717
mozilla-try     x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :   0.007510 s,   0.007389 s,  -0.000121 s, × 0.9839
mozilla-try     x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :   0.004911 s,   0.004868 s,  -0.000043 s, × 0.9912
mozilla-try     x000_revs_x000_added_x000_copies      1346fd0130e4 4c65cbdabc1f :   0.233231 s,   0.222450 s,  -0.010781 s, × 0.9538
mozilla-try     x0000_revs_x_added_0_copies           63519bfd42ee a36a2a865d92 :   0.419989 s,   0.370675 s,  -0.049314 s, × 0.8826
mozilla-try     x0000_revs_x_added_x_copies           9fe69ff0762d bcabf2a78927 :   0.401521 s,   0.358020 s,  -0.043501 s, × 0.8917
mozilla-try     x0000_revs_xx000_added_x_copies       156f6e2674f2 4d0f2c178e66 :   0.179555 s,   0.145235 s,  -0.034320 s, × 0.8089
mozilla-try     x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :   0.038004 s,   0.037606 s,  -0.000398 s, × 0.9895
mozilla-try     x0000_revs_xx000_added_x000_copies    89294cd501d9 7ccb2fc7ccb5 :  52.838482 s,   7.382439 s, -45.456043 s, × 0.1397
mozilla-try     x0000_revs_x0000_added_x0000_copies   e928c65095ed e951f4ad123a :   8.705874 s,   7.273506 s,  -1.432368 s, × 0.8355
mozilla-try     x00000_revs_x00000_added_0_copies     dc8a3ca7010e d16fde900c9c :   1.126708 s,   1.074593 s,  -0.052115 s, × 0.9537
mozilla-try     x00000_revs_x0000_added_x0000_copies  8d3fafa80d4b eb884023b810 :  83.854020 s,  27.746195 s, -56.107825 s, × 0.3309


Below is a table comparing the runtime of the current "filelog centric"
algorithm, with the "changeset centric" one, we just modified.

The changeset centric algorithm is a significant win in many scenario, but they
are still various cases where it is quite slower. When many revision  has to be
considered the cost of retrieving the copy information, creating new
dictionaries, merging dictionaries and checking if revision are ancestors of
each other can slow things down.

The rest of this series, will introduce a rust version of the copy tracing code
to deal with most of theses issues.


Repo            Case                                  Source-Rev   Dest-Rev         filelog     sidedata      Difference       Factor
---------------------------------------------------------------------------------------------------------------------------------------
mercurial       x_revs_x_added_0_copies               ad6b123de1c7 39cfcef4f463 :  0.000914 s,  0.000044 s, - 0.000870 s,    × 0.048140
mercurial       x_revs_x_added_x_copies               2b1c78674230 0c1d10351869 :  0.001812 s,  0.000138 s, - 0.001674 s,    × 0.076159
mercurial       x000_revs_x000_added_x_copies         81f8ff2a9bf2 dd3267698d84 :  0.017954 s,  0.005052 s, - 0.012902 s,    × 0.281386
pypy            x_revs_x_added_0_copies               aed021ee8ae8 099ed31b181b :  0.001509 s,  0.000219 s, - 0.001290 s,    × 0.145129
pypy            x_revs_x000_added_0_copies            4aa4e1f8e19a 359343b9ac0e :  0.206881 s,  0.000055 s, - 0.206826 s,    × 0.000266
pypy            x_revs_x_added_x_copies               ac52eb7bbbb0 72e022663155 :  0.016951 s,  0.000128 s, - 0.016823 s,    × 0.007551
pypy            x_revs_x00_added_x_copies             c3b14617fbd7 ace7255d9a26 :  0.019096 s,  0.001089 s, - 0.018007 s,    × 0.057028
pypy            x_revs_x000_added_x000_copies         df6f7a526b60 a83dc6a2d56f :  0.762506 s,  0.017407 s, - 0.745099 s,    × 0.022829
pypy            x000_revs_xx00_added_0_copies         89a76aede314 2f22446ff07e :  1.179211 s,  0.094175 s, - 1.085036 s,    × 0.079863
pypy            x000_revs_x000_added_x_copies         8a3b5bfd266e 2c68e87c3efe :  1.249058 s,  0.238009 s, - 1.011049 s,    × 0.190551
pypy            x000_revs_x000_added_x000_copies      89a76aede314 7b3dda341c84 :  1.614107 s,  0.125876 s, - 1.488231 s,    × 0.077985
pypy            x0000_revs_x_added_0_copies           d1defd0dc478 c9cb1334cc78 :  0.001064 s,  3.581556 s, + 3.580492 s, × 3366.124060
pypy            x0000_revs_xx000_added_0_copies       bf2c629d0071 4ffed77c095c :  1.061275 s,  0.016721 s, - 1.044554 s,    × 0.015756
pypy            x0000_revs_xx000_added_x000_copies    08ea3258278e d9fa043f30c0 :  1.341119 s,  0.242367 s, - 1.098752 s,    × 0.180720
netbeans        x_revs_x_added_0_copies               fb0955ffcbcd a01e9239f9e7 :  0.027803 s,  0.000165 s, - 0.027638 s,    × 0.005935
netbeans        x_revs_x000_added_0_copies            6f360122949f 20eb231cc7d0 :  0.130014 s,  0.000114 s, - 0.129900 s,    × 0.000877
netbeans        x_revs_x_added_x_copies               1ada3faf6fb6 5a39d12eecf4 :  0.024990 s,  0.000296 s, - 0.024694 s,    × 0.011845
netbeans        x_revs_x00_added_x_copies             35be93ba1e2c 9eec5e90c05f :  0.052201 s,  0.001124 s, - 0.051077 s,    × 0.021532
netbeans        x000_revs_xx00_added_0_copies         eac3045b4fdd 51d4ae7f1290 :  0.037642 s,  0.013060 s, - 0.024582 s,    × 0.346953
netbeans        x000_revs_x000_added_x_copies         e2063d266acd 6081d72689dc :  0.197086 s,  0.017112 s, - 0.179974 s,    × 0.086825
netbeans        x000_revs_x000_added_x000_copies      ff453e9fee32 411350406ec2 :  0.935148 s,  0.660350 s, - 0.274798 s,    × 0.706145
netbeans        x0000_revs_xx000_added_x000_copies    588c2d1ced70 1aad62e59ddd :  3.920674 s, 10.032499 s, + 6.111825 s,    × 2.558871
mozilla-central x_revs_x_added_0_copies               3697f962bb7b 7015fcdd43a2 :  0.024232 s,  0.000189 s, - 0.024043 s,    × 0.007800
mozilla-central x_revs_x000_added_0_copies            dd390860c6c9 40d0c5bed75d :  0.141483 s,  0.000462 s, - 0.141021 s,    × 0.003265
mozilla-central x_revs_x_added_x_copies               8d198483ae3b 14207ffc2b2f :  0.025775 s,  0.000270 s, - 0.025505 s,    × 0.010475
mozilla-central x_revs_x00_added_x_copies             98cbc58cc6bc 446a150332c3 :  0.084922 s,  0.001474 s, - 0.083448 s,    × 0.017357
mozilla-central x_revs_x000_added_x000_copies         3c684b4b8f68 0a5e72d1b479 :  0.194784 s,  0.004806 s, - 0.189978 s,    × 0.024673
mozilla-central x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :  2.161103 s,  0.085150 s, - 2.075953 s,    × 0.039401
mozilla-central x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :  0.089347 s,  0.007064 s, - 0.082283 s,    × 0.079063
mozilla-central x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :  0.732171 s,  0.004741 s, - 0.727430 s,    × 0.006475
mozilla-central x000_revs_x000_added_x000_copies      7c97034feb78 4407bd0c6330 :  1.157287 s,  0.190133 s, - 0.967154 s,    × 0.164292
mozilla-central x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :  6.726568 s,  0.035651 s, - 6.690917 s,    × 0.005300
mozilla-central x0000_revs_xx000_added_x000_copies    f78c615a656c 96a38b690156 :  3.266229 s,  0.440694 s, - 2.825535 s,    × 0.134924
mozilla-central x00000_revs_x0000_added_x0000_copies  6832ae71433c 4c222a1d9a00 : 15.860534 s, 18.454163 s, + 2.593629 s,    × 1.163527
mozilla-central x00000_revs_x00000_added_x000_copies  76caed42cf7c 1daa622bbe42 : 20.450475 s, 31.562719 s, +11.112244 s,    × 1.543373
mozilla-try     x_revs_x_added_0_copies               aaf6dde0deb8 9790f499805a :  0.080442 s,  0.001189 s, - 0.079253 s,    × 0.014781
mozilla-try     x_revs_x000_added_0_copies            d8d0222927b4 5bb8ce8c7450 :  0.497672 s,  0.001204 s, - 0.496468 s,    × 0.002419
mozilla-try     x_revs_x_added_x_copies               092fcca11bdb 936255a0384a :  0.021183 s,  0.000586 s, - 0.020597 s,    × 0.027664
mozilla-try     x_revs_x00_added_x_copies             b53d2fadbdb5 017afae788ec :  0.230991 s,  0.001845 s, - 0.229146 s,    × 0.007987
mozilla-try     x_revs_x000_added_x000_copies         20408ad61ce5 6f0ee96e21ad :  1.118461 s,  0.063822 s, - 1.054639 s,    × 0.057062
mozilla-try     x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :  2.206083 s,  0.088038 s, - 2.118045 s,    × 0.039907
mozilla-try     x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :  0.089404 s,  0.007389 s, - 0.082015 s,    × 0.082647
mozilla-try     x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :  0.733043 s,  0.004868 s, - 0.728175 s,    × 0.006641
mozilla-try     x000_revs_x000_added_x000_copies      1346fd0130e4 4c65cbdabc1f :  1.163367 s,  0.222450 s, - 0.940917 s,    × 0.191212
mozilla-try     x0000_revs_x_added_0_copies           63519bfd42ee a36a2a865d92 :  0.085456 s,  0.370675 s, + 0.285219 s,    × 4.337612
mozilla-try     x0000_revs_x_added_x_copies           9fe69ff0762d bcabf2a78927 :  0.083601 s,  0.358020 s, + 0.274419 s,    × 4.282485
mozilla-try     x0000_revs_xx000_added_x_copies       156f6e2674f2 4d0f2c178e66 :  7.366614 s,  0.145235 s, - 7.221379 s,    × 0.019715
mozilla-try     x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :  6.664464 s,  0.037606 s, - 6.626858 s,    × 0.005643
mozilla-try     x0000_revs_xx000_added_x000_copies    89294cd501d9 7ccb2fc7ccb5 :  7.467836 s,  7.382439 s, - 0.085397 s,    × 0.988565
mozilla-try     x0000_revs_x0000_added_x0000_copies   e928c65095ed e951f4ad123a :  9.801294 s,  7.273506 s, - 2.527788 s,    × 0.742097
mozilla-try     x00000_revs_x_added_0_copies          6a320851d377 1ebb79acd503 :  0.091886 s, killed
mozilla-try     x00000_revs_x00000_added_0_copies     dc8a3ca7010e d16fde900c9c : 26.491140 s,  1.074593 s, -25.416547 s,    × 0.040564
mozilla-try     x00000_revs_x_added_x_copies          5173c4b6f97c 95d83ee7242d :  0.092863 s, killed
mozilla-try     x00000_revs_x000_added_x_copies       9126823d0e9c ca82787bb23c :  0.226823 s, killed
mozilla-try     x00000_revs_x0000_added_x0000_copies  8d3fafa80d4b eb884023b810 : 18.914630 s, 27.746195 s, + 8.831565 s,    × 1.466917
mozilla-try     x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 21.198903 s, killed
mozilla-try     x00000_revs_x00000_added_x000_copies  9b2a99adc05e 8e29777b48e6 : 24.952268 s, killed

Differential Revision: https://phab.mercurial-scm.org/D9296

# posix.py - Posix utility function implementations for Mercurial
#
#  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
#
# 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

import errno
import fcntl
import getpass
import grp
import os
import pwd
import re
import select
import stat
import sys
import tempfile
import unicodedata

from .i18n import _
from .pycompat import (
    getattr,
    open,
)
from . import (
    encoding,
    error,
    policy,
    pycompat,
)

osutil = policy.importmod('osutil')

normpath = os.path.normpath
samestat = os.path.samestat
try:
    oslink = os.link
except AttributeError:
    # Some platforms build Python without os.link on systems that are
    # vaguely unix-like but don't have hardlink support. For those
    # poor souls, just say we tried and that it failed so we fall back
    # to copies.
    def oslink(src, dst):
        raise OSError(
            errno.EINVAL, b'hardlinks not supported: %s to %s' % (src, dst)
        )


readlink = os.readlink
unlink = os.unlink
rename = os.rename
removedirs = os.removedirs
expandglobs = False

umask = os.umask(0)
os.umask(umask)

if not pycompat.ispy3:

    def posixfile(name, mode='r', buffering=-1):
        fp = open(name, mode=mode, buffering=buffering)
        # The position when opening in append mode is implementation defined, so
        # make it consistent by always seeking to the end.
        if 'a' in mode:
            fp.seek(0, os.SEEK_END)
        return fp


else:
    # The underlying file object seeks as required in Python 3:
    # https://github.com/python/cpython/blob/v3.7.3/Modules/_io/fileio.c#L474
    posixfile = open


def split(p):
    '''Same as posixpath.split, but faster

    >>> import posixpath
    >>> for f in [b'/absolute/path/to/file',
    ...           b'relative/path/to/file',
    ...           b'file_alone',
    ...           b'path/to/directory/',
    ...           b'/multiple/path//separators',
    ...           b'/file_at_root',
    ...           b'///multiple_leading_separators_at_root',
    ...           b'']:
    ...     assert split(f) == posixpath.split(f), f
    '''
    ht = p.rsplit(b'/', 1)
    if len(ht) == 1:
        return b'', p
    nh = ht[0].rstrip(b'/')
    if nh:
        return nh, ht[1]
    return ht[0] + b'/', ht[1]


def openhardlinks():
    '''return true if it is safe to hold open file handles to hardlinks'''
    return True


def nlinks(name):
    '''return number of hardlinks for the given file'''
    return os.lstat(name).st_nlink


def parsepatchoutput(output_line):
    """parses the output produced by patch and returns the filename"""
    pf = output_line[14:]
    if pycompat.sysplatform == b'OpenVMS':
        if pf[0] == b'`':
            pf = pf[1:-1]  # Remove the quotes
    else:
        if pf.startswith(b"'") and pf.endswith(b"'") and b" " in pf:
            pf = pf[1:-1]  # Remove the quotes
    return pf


def sshargs(sshcmd, host, user, port):
    '''Build argument list for ssh'''
    args = user and (b"%s@%s" % (user, host)) or host
    if b'-' in args[:1]:
        raise error.Abort(
            _(b'illegal ssh hostname or username starting with -: %s') % args
        )
    args = shellquote(args)
    if port:
        args = b'-p %s %s' % (shellquote(port), args)
    return args


def isexec(f):
    """check whether a file is executable"""
    return os.lstat(f).st_mode & 0o100 != 0


def setflags(f, l, x):
    st = os.lstat(f)
    s = st.st_mode
    if l:
        if not stat.S_ISLNK(s):
            # switch file to link
            with open(f, b'rb') as fp:
                data = fp.read()
            unlink(f)
            try:
                os.symlink(data, f)
            except OSError:
                # failed to make a link, rewrite file
                with open(f, b"wb") as fp:
                    fp.write(data)

        # no chmod needed at this point
        return
    if stat.S_ISLNK(s):
        # switch link to file
        data = os.readlink(f)
        unlink(f)
        with open(f, b"wb") as fp:
            fp.write(data)
        s = 0o666 & ~umask  # avoid restatting for chmod

    sx = s & 0o100
    if st.st_nlink > 1 and bool(x) != bool(sx):
        # the file is a hardlink, break it
        with open(f, b"rb") as fp:
            data = fp.read()
        unlink(f)
        with open(f, b"wb") as fp:
            fp.write(data)

    if x and not sx:
        # Turn on +x for every +r bit when making a file executable
        # and obey umask.
        os.chmod(f, s | (s & 0o444) >> 2 & ~umask)
    elif not x and sx:
        # Turn off all +x bits
        os.chmod(f, s & 0o666)


def copymode(src, dst, mode=None, enforcewritable=False):
    '''Copy the file mode from the file at path src to dst.
    If src doesn't exist, we're using mode instead. If mode is None, we're
    using umask.'''
    try:
        st_mode = os.lstat(src).st_mode & 0o777
    except OSError as inst:
        if inst.errno != errno.ENOENT:
            raise
        st_mode = mode
        if st_mode is None:
            st_mode = ~umask
        st_mode &= 0o666

    new_mode = st_mode

    if enforcewritable:
        new_mode |= stat.S_IWUSR

    os.chmod(dst, new_mode)


def checkexec(path):
    """
    Check whether the given path is on a filesystem with UNIX-like exec flags

    Requires a directory (like /foo/.hg)
    """

    # VFAT on some Linux versions can flip mode but it doesn't persist
    # a FS remount. Frequently we can detect it if files are created
    # with exec bit on.

    try:
        EXECFLAGS = stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH
        basedir = os.path.join(path, b'.hg')
        cachedir = os.path.join(basedir, b'wcache')
        storedir = os.path.join(basedir, b'store')
        if not os.path.exists(cachedir):
            try:
                # we want to create the 'cache' directory, not the '.hg' one.
                # Automatically creating '.hg' directory could silently spawn
                # invalid Mercurial repositories. That seems like a bad idea.
                os.mkdir(cachedir)
                if os.path.exists(storedir):
                    copymode(storedir, cachedir)
                else:
                    copymode(basedir, cachedir)
            except (IOError, OSError):
                # we other fallback logic triggers
                pass
        if os.path.isdir(cachedir):
            checkisexec = os.path.join(cachedir, b'checkisexec')
            checknoexec = os.path.join(cachedir, b'checknoexec')

            try:
                m = os.stat(checkisexec).st_mode
            except OSError as e:
                if e.errno != errno.ENOENT:
                    raise
                # checkisexec does not exist - fall through ...
            else:
                # checkisexec exists, check if it actually is exec
                if m & EXECFLAGS != 0:
                    # ensure checkisexec exists, check it isn't exec
                    try:
                        m = os.stat(checknoexec).st_mode
                    except OSError as e:
                        if e.errno != errno.ENOENT:
                            raise
                        open(checknoexec, b'w').close()  # might fail
                        m = os.stat(checknoexec).st_mode
                    if m & EXECFLAGS == 0:
                        # check-exec is exec and check-no-exec is not exec
                        return True
                    # checknoexec exists but is exec - delete it
                    unlink(checknoexec)
                # checkisexec exists but is not exec - delete it
                unlink(checkisexec)

            # check using one file, leave it as checkisexec
            checkdir = cachedir
        else:
            # check directly in path and don't leave checkisexec behind
            checkdir = path
            checkisexec = None
        fh, fn = pycompat.mkstemp(dir=checkdir, prefix=b'hg-checkexec-')
        try:
            os.close(fh)
            m = os.stat(fn).st_mode
            if m & EXECFLAGS == 0:
                os.chmod(fn, m & 0o777 | EXECFLAGS)
                if os.stat(fn).st_mode & EXECFLAGS != 0:
                    if checkisexec is not None:
                        os.rename(fn, checkisexec)
                        fn = None
                    return True
        finally:
            if fn is not None:
                unlink(fn)
    except (IOError, OSError):
        # we don't care, the user probably won't be able to commit anyway
        return False


def checklink(path):
    """check whether the given path is on a symlink-capable filesystem"""
    # mktemp is not racy because symlink creation will fail if the
    # file already exists
    while True:
        cachedir = os.path.join(path, b'.hg', b'wcache')
        checklink = os.path.join(cachedir, b'checklink')
        # try fast path, read only
        if os.path.islink(checklink):
            return True
        if os.path.isdir(cachedir):
            checkdir = cachedir
        else:
            checkdir = path
            cachedir = None
        name = tempfile.mktemp(
            dir=pycompat.fsdecode(checkdir), prefix=r'checklink-'
        )
        name = pycompat.fsencode(name)
        try:
            fd = None
            if cachedir is None:
                fd = pycompat.namedtempfile(
                    dir=checkdir, prefix=b'hg-checklink-'
                )
                target = os.path.basename(fd.name)
            else:
                # create a fixed file to link to; doesn't matter if it
                # already exists.
                target = b'checklink-target'
                try:
                    fullpath = os.path.join(cachedir, target)
                    open(fullpath, b'w').close()
                except IOError as inst:
                    if (
                        inst[0] == errno.EACCES
                    ):  # pytype: disable=unsupported-operands
                        # If we can't write to cachedir, just pretend
                        # that the fs is readonly and by association
                        # that the fs won't support symlinks. This
                        # seems like the least dangerous way to avoid
                        # data loss.
                        return False
                    raise
            try:
                os.symlink(target, name)
                if cachedir is None:
                    unlink(name)
                else:
                    try:
                        os.rename(name, checklink)
                    except OSError:
                        unlink(name)
                return True
            except OSError as inst:
                # link creation might race, try again
                if inst.errno == errno.EEXIST:
                    continue
                raise
            finally:
                if fd is not None:
                    fd.close()
        except AttributeError:
            return False
        except OSError as inst:
            # sshfs might report failure while successfully creating the link
            if inst.errno == errno.EIO and os.path.exists(name):
                unlink(name)
            return False


def checkosfilename(path):
    '''Check that the base-relative path is a valid filename on this platform.
    Returns None if the path is ok, or a UI string describing the problem.'''
    return None  # on posix platforms, every path is ok


def getfsmountpoint(dirpath):
    '''Get the filesystem mount point from a directory (best-effort)

    Returns None if we are unsure. Raises OSError on ENOENT, EPERM, etc.
    '''
    return getattr(osutil, 'getfsmountpoint', lambda x: None)(dirpath)


def getfstype(dirpath):
    '''Get the filesystem type name from a directory (best-effort)

    Returns None if we are unsure. Raises OSError on ENOENT, EPERM, etc.
    '''
    return getattr(osutil, 'getfstype', lambda x: None)(dirpath)


def setbinary(fd):
    pass


def pconvert(path):
    return path


def localpath(path):
    return path


def samefile(fpath1, fpath2):
    """Returns whether path1 and path2 refer to the same file. This is only
    guaranteed to work for files, not directories."""
    return os.path.samefile(fpath1, fpath2)


def samedevice(fpath1, fpath2):
    """Returns whether fpath1 and fpath2 are on the same device. This is only
    guaranteed to work for files, not directories."""
    st1 = os.lstat(fpath1)
    st2 = os.lstat(fpath2)
    return st1.st_dev == st2.st_dev


# os.path.normcase is a no-op, which doesn't help us on non-native filesystems
def normcase(path):
    return path.lower()


# what normcase does to ASCII strings
normcasespec = encoding.normcasespecs.lower
# fallback normcase function for non-ASCII strings
normcasefallback = normcase

if pycompat.isdarwin:

    def normcase(path):
        '''
        Normalize a filename for OS X-compatible comparison:
        - escape-encode invalid characters
        - decompose to NFD
        - lowercase
        - omit ignored characters [200c-200f, 202a-202e, 206a-206f,feff]

        >>> normcase(b'UPPER')
        'upper'
        >>> normcase(b'Caf\\xc3\\xa9')
        'cafe\\xcc\\x81'
        >>> normcase(b'\\xc3\\x89')
        'e\\xcc\\x81'
        >>> normcase(b'\\xb8\\xca\\xc3\\xca\\xbe\\xc8.JPG') # issue3918
        '%b8%ca%c3\\xca\\xbe%c8.jpg'
        '''

        try:
            return encoding.asciilower(path)  # exception for non-ASCII
        except UnicodeDecodeError:
            return normcasefallback(path)

    normcasespec = encoding.normcasespecs.lower

    def normcasefallback(path):
        try:
            u = path.decode('utf-8')
        except UnicodeDecodeError:
            # OS X percent-encodes any bytes that aren't valid utf-8
            s = b''
            pos = 0
            l = len(path)
            while pos < l:
                try:
                    c = encoding.getutf8char(path, pos)
                    pos += len(c)
                except ValueError:
                    c = b'%%%02X' % ord(path[pos : pos + 1])
                    pos += 1
                s += c

            u = s.decode('utf-8')

        # Decompose then lowercase (HFS+ technote specifies lower)
        enc = unicodedata.normalize('NFD', u).lower().encode('utf-8')
        # drop HFS+ ignored characters
        return encoding.hfsignoreclean(enc)


if pycompat.sysplatform == b'cygwin':
    # workaround for cygwin, in which mount point part of path is
    # treated as case sensitive, even though underlying NTFS is case
    # insensitive.

    # default mount points
    cygwinmountpoints = sorted(
        [b"/usr/bin", b"/usr/lib", b"/cygdrive",], reverse=True
    )

    # use upper-ing as normcase as same as NTFS workaround
    def normcase(path):
        pathlen = len(path)
        if (pathlen == 0) or (path[0] != pycompat.ossep):
            # treat as relative
            return encoding.upper(path)

        # to preserve case of mountpoint part
        for mp in cygwinmountpoints:
            if not path.startswith(mp):
                continue

            mplen = len(mp)
            if mplen == pathlen:  # mount point itself
                return mp
            if path[mplen] == pycompat.ossep:
                return mp + encoding.upper(path[mplen:])

        return encoding.upper(path)

    normcasespec = encoding.normcasespecs.other
    normcasefallback = normcase

    # Cygwin translates native ACLs to POSIX permissions,
    # but these translations are not supported by native
    # tools, so the exec bit tends to be set erroneously.
    # Therefore, disable executable bit access on Cygwin.
    def checkexec(path):
        return False

    # Similarly, Cygwin's symlink emulation is likely to create
    # problems when Mercurial is used from both Cygwin and native
    # Windows, with other native tools, or on shared volumes
    def checklink(path):
        return False


_needsshellquote = None


def shellquote(s):
    if pycompat.sysplatform == b'OpenVMS':
        return b'"%s"' % s
    global _needsshellquote
    if _needsshellquote is None:
        _needsshellquote = re.compile(br'[^a-zA-Z0-9._/+-]').search
    if s and not _needsshellquote(s):
        # "s" shouldn't have to be quoted
        return s
    else:
        return b"'%s'" % s.replace(b"'", b"'\\''")


def shellsplit(s):
    """Parse a command string in POSIX shell way (best-effort)"""
    return pycompat.shlexsplit(s, posix=True)


def testpid(pid):
    '''return False if pid dead, True if running or not sure'''
    if pycompat.sysplatform == b'OpenVMS':
        return True
    try:
        os.kill(pid, 0)
        return True
    except OSError as inst:
        return inst.errno != errno.ESRCH


def isowner(st):
    """Return True if the stat object st is from the current user."""
    return st.st_uid == os.getuid()


def findexe(command):
    '''Find executable for command searching like which does.
    If command is a basename then PATH is searched for command.
    PATH isn't searched if command is an absolute or relative path.
    If command isn't found None is returned.'''
    if pycompat.sysplatform == b'OpenVMS':
        return command

    def findexisting(executable):
        b'Will return executable if existing file'
        if os.path.isfile(executable) and os.access(executable, os.X_OK):
            return executable
        return None

    if pycompat.ossep in command:
        return findexisting(command)

    if pycompat.sysplatform == b'plan9':
        return findexisting(os.path.join(b'/bin', command))

    for path in encoding.environ.get(b'PATH', b'').split(pycompat.ospathsep):
        executable = findexisting(os.path.join(path, command))
        if executable is not None:
            return executable
    return None


def setsignalhandler():
    pass


_wantedkinds = {stat.S_IFREG, stat.S_IFLNK}


def statfiles(files):
    '''Stat each file in files. Yield each stat, or None if a file does not
    exist or has a type we don't care about.'''
    lstat = os.lstat
    getkind = stat.S_IFMT
    for nf in files:
        try:
            st = lstat(nf)
            if getkind(st.st_mode) not in _wantedkinds:
                st = None
        except OSError as err:
            if err.errno not in (errno.ENOENT, errno.ENOTDIR):
                raise
            st = None
        yield st


def getuser():
    '''return name of current user'''
    return pycompat.fsencode(getpass.getuser())


def username(uid=None):
    """Return the name of the user with the given uid.

    If uid is None, return the name of the current user."""

    if uid is None:
        uid = os.getuid()
    try:
        return pycompat.fsencode(pwd.getpwuid(uid)[0])
    except KeyError:
        return b'%d' % uid


def groupname(gid=None):
    """Return the name of the group with the given gid.

    If gid is None, return the name of the current group."""

    if gid is None:
        gid = os.getgid()
    try:
        return pycompat.fsencode(grp.getgrgid(gid)[0])
    except KeyError:
        return pycompat.bytestr(gid)


def groupmembers(name):
    """Return the list of members of the group with the given
    name, KeyError if the group does not exist.
    """
    name = pycompat.fsdecode(name)
    return pycompat.rapply(pycompat.fsencode, list(grp.getgrnam(name).gr_mem))


def spawndetached(args):
    return os.spawnvp(os.P_NOWAIT | getattr(os, 'P_DETACH', 0), args[0], args)


def gethgcmd():
    return sys.argv[:1]


def makedir(path, notindexed):
    os.mkdir(path)


def lookupreg(key, name=None, scope=None):
    return None


def hidewindow():
    """Hide current shell window.

    Used to hide the window opened when starting asynchronous
    child process under Windows, unneeded on other systems.
    """
    pass


class cachestat(object):
    def __init__(self, path):
        self.stat = os.stat(path)

    def cacheable(self):
        return bool(self.stat.st_ino)

    __hash__ = object.__hash__

    def __eq__(self, other):
        try:
            # Only dev, ino, size, mtime and atime are likely to change. Out
            # of these, we shouldn't compare atime but should compare the
            # rest. However, one of the other fields changing indicates
            # something fishy going on, so return False if anything but atime
            # changes.
            return (
                self.stat.st_mode == other.stat.st_mode
                and self.stat.st_ino == other.stat.st_ino
                and self.stat.st_dev == other.stat.st_dev
                and self.stat.st_nlink == other.stat.st_nlink
                and self.stat.st_uid == other.stat.st_uid
                and self.stat.st_gid == other.stat.st_gid
                and self.stat.st_size == other.stat.st_size
                and self.stat[stat.ST_MTIME] == other.stat[stat.ST_MTIME]
                and self.stat[stat.ST_CTIME] == other.stat[stat.ST_CTIME]
            )
        except AttributeError:
            return False

    def __ne__(self, other):
        return not self == other


def statislink(st):
    '''check whether a stat result is a symlink'''
    return st and stat.S_ISLNK(st.st_mode)


def statisexec(st):
    '''check whether a stat result is an executable file'''
    return st and (st.st_mode & 0o100 != 0)


def poll(fds):
    """block until something happens on any file descriptor

    This is a generic helper that will check for any activity
    (read, write.  exception) and return the list of touched files.

    In unsupported cases, it will raise a NotImplementedError"""
    try:
        while True:
            try:
                res = select.select(fds, fds, fds)
                break
            except select.error as inst:
                if inst.args[0] == errno.EINTR:
                    continue
                raise
    except ValueError:  # out of range file descriptor
        raise NotImplementedError()
    return sorted(list(set(sum(res, []))))


def readpipe(pipe):
    """Read all available data from a pipe."""
    # We can't fstat() a pipe because Linux will always report 0.
    # So, we set the pipe to non-blocking mode and read everything
    # that's available.
    flags = fcntl.fcntl(pipe, fcntl.F_GETFL)
    flags |= os.O_NONBLOCK
    oldflags = fcntl.fcntl(pipe, fcntl.F_SETFL, flags)

    try:
        chunks = []
        while True:
            try:
                s = pipe.read()
                if not s:
                    break
                chunks.append(s)
            except IOError:
                break

        return b''.join(chunks)
    finally:
        fcntl.fcntl(pipe, fcntl.F_SETFL, oldflags)


def bindunixsocket(sock, path):
    """Bind the UNIX domain socket to the specified path"""
    # use relative path instead of full path at bind() if possible, since
    # AF_UNIX path has very small length limit (107 chars) on common
    # platforms (see sys/un.h)
    dirname, basename = os.path.split(path)
    bakwdfd = None

    try:
        if dirname:
            bakwdfd = os.open(b'.', os.O_DIRECTORY)
            os.chdir(dirname)
        sock.bind(basename)
        if bakwdfd:
            os.fchdir(bakwdfd)
    finally:
        if bakwdfd:
            os.close(bakwdfd)