hgext/extdiff.py
| author |
Pierre-Yves David <pierre-yves.david@octobus.net> |
|
Mon, 14 Dec 2020 11:32:24 +0100 |
| changeset 46149 |
294d5aca4ff5 |
| parent 46134 |
0a4d47f4337b
|
| child 46843 |
728d89f6f9b1 |
| permissions |
-rw-r--r-- |
copies: iterate over children directly (instead of parents)
Before this change we would gather all parent → child edges and iterate on
all parent, gathering copy information for children and aggregating them from
there.
They are not strict requirement for edges to be processed in that specific
order. We could also simply iterate over all "children" revision and aggregate
data from both parents at the same time. This patch does that.
It make various things simpler:
* since both parents are processed at the same time, we no longer need to
cache data for merge (see next changeset for details),
* we no longer need nested loop to process data,
* we no longer need to store partial merge data for a rev from distinct loop
interaction to another when processing merges,
* we no longer need to build a full parent -> children mapping (we only rely on
a simpler "parent -> number of children" map (for memory efficiency),
* the data access pattern is now simpler (from lower revisions to higher
revisions) and entirely predicable. That predictability open the way to
prefetching and parallel processing.
So that new iterations order requires simpler code and open the way to
interesting optimisation.
The effect on performance is quite good. In the worse case, we don't see any
significant negative impact. And in the best case, the reduction of roundtrip
to Python provide us with a significant speed. Some example below:
Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev
# full comparison between the previous changeset and this one
Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000048 s, 0.000041 s, -0.000007 s, × 0.8542, 41 µs/rev
mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000153 s, 0.000102 s, -0.000051 s, × 0.6667, 17 µs/rev
mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004209 s, 0.004254 s, +0.000045 s, × 1.0107, 4 µs/rev
pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000203 s, 0.000282 s, +0.000079 s, × 1.3892, 31 µs/rev
pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000059 s, 0.000048 s, -0.000011 s, × 0.8136, 48 µs/rev
pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000194 s, 0.000211 s, +0.000017 s, × 1.0876, 30 µs/rev
pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000380 s, 0.000375 s, -0.000005 s, × 0.9868, 375 µs/rev
pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010588 s, 0.010574 s, -0.000014 s, × 0.9987, 1762 µs/rev
pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.048961 s, 0.049974 s, +0.001013 s, × 1.0207, 10 µs/rev
pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.083612 s, 0.084300 s, +0.000688 s, × 1.0082, 12 µs/rev
pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.058579 s, 0.060128 s, +0.001549 s, × 1.0264, 11 µs/rev
pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.736783 s, 0.686542 s, -0.050241 s, × 0.9318, 15 µs/rev
pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.022050 s, 0.009277 s, -0.012773 s, × 0.4207, 4638 µs/rev
pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120800 s, 0.114733 s, -0.006067 s, × 0.9498, 10 µs/rev
netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000140 s, 0.000081 s, -0.000059 s, × 0.5786, 40 µs/rev
netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000114 s, 0.000107 s, -0.000007 s, × 0.9386, 53 µs/rev
netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000224 s, 0.000173 s, -0.000051 s, × 0.7723, 57 µs/rev
netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000723 s, 0.000698 s, -0.000025 s, × 0.9654, 77 µs/rev
netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009665 s, 0.009248 s, -0.000417 s, × 0.9569, 6 µs/rev
netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.014820 s, 0.015446 s, +0.000626 s, × 1.0422, 10 µs/rev
netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.076049 s, 0.074373 s, -0.001676 s, × 0.9780, 12 µs/rev
netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.683603 s, 0.639870 s, -0.043733 s, × 0.9360, 9 µs/rev
mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000161 s, 0.000088 s, -0.000073 s, × 0.5466, 44 µs/rev
mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000234 s, 0.000199 s, -0.000035 s, × 0.8504, 24 µs/rev
mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000247 s, 0.000171 s, -0.000076 s, × 0.6923, 19 µs/rev
mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000630 s, 0.000592 s, -0.000038 s, × 0.9397, 84 µs/rev
mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003286 s, 0.003151 s, -0.000135 s, × 0.9589, 1050 µs/rev
mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062441 s, 0.061612 s, -0.000829 s, × 0.9867, 10268 µs/rev
mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005423 s, 0.005381 s, -0.000042 s, × 0.9923, 3 µs/rev
mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005919 s, 0.003742 s, -0.002177 s, × 0.6322, 91 µs/rev
mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.062597 s, 0.061983 s, -0.000614 s, × 0.9902, 7 µs/rev
mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.043551 s, 0.019861 s, -0.023690 s, × 0.4560, 32 µs/rev
mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.192475 s, 0.188101 s, -0.004374 s, × 0.9773, 6 µs/rev
mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.955575 s, 1.806696 s, -0.148879 s, × 0.9239, 11 µs/rev
mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.886501 s, 2.682987 s, -0.203514 s, × 0.9295, 13 µs/rev
mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.001181 s, 0.000852 s, -0.000329 s, × 0.7214, 426 µs/rev
mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.001189 s, 0.000859 s, -0.000330 s, × 0.7225, 429 µs/rev
mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000563 s, 0.000150 s, -0.000413 s, × 0.2664, 37 µs/rev
mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001548 s, 0.001158 s, -0.000390 s, × 0.7481, 579 µs/rev
mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027782 s, 0.027240 s, -0.000542 s, × 0.9805, 27240 µs/rev
mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062781 s, 0.062824 s, +0.000043 s, × 1.0007, 10470 µs/rev
mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005778 s, 0.005463 s, -0.000315 s, × 0.9455, 3 µs/rev
mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.006192 s, 0.004238 s, -0.001954 s, × 0.6844, 103 µs/rev
mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065391 s, 0.064113 s, -0.001278 s, × 0.9805, 9 µs/rev
mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.317216 s, 0.294063 s, -0.023153 s, × 0.9270, 7 µs/rev
mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.303119 s, 0.281493 s, -0.021626 s, × 0.9287, 7 µs/rev
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev
mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.045739 s, 0.020390 s, -0.025349 s, × 0.4458, 33 µs/rev
mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.098021 s, 3.023879 s, -0.074142 s, × 0.9761, 31 µs/rev
mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.771480 s, 0.735549 s, -0.035931 s, × 0.9534, 14 µs/rev
mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.813422 s, 18.568900 s, -0.244522 s, × 0.9870, 51 µs/rev
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev
mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.684923 s, 18.356645 s, -0.328278 s, × 0.9824, 50 µs/rev
mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.296305 s, 18.250393 s, -0.045912 s, × 0.9975, 50 µs/rev
mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 3.061887 s, 2.792459 s, -0.269428 s, × 0.9120, 14 µs/rev
mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s, +3.827623 s, × 1.0369, 470 µs/rev
mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 64.262957 s, 63.961040 s, -0.301917 s, × 0.9953, 167 µs/rev
Differential Revision: https://phab.mercurial-scm.org/D9422
# extdiff.py - external diff program support for mercurial
#
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
'''command to allow external programs to compare revisions
The extdiff Mercurial extension allows you to use external programs
to compare revisions, or revision with working directory. The external
diff programs are called with a configurable set of options and two
non-option arguments: paths to directories containing snapshots of
files to compare.
If there is more than one file being compared and the "child" revision
is the working directory, any modifications made in the external diff
program will be copied back to the working directory from the temporary
directory.
The extdiff extension also allows you to configure new diff commands, so
you do not need to type :hg:`extdiff -p kdiff3` always. ::
[extdiff]
# add new command that runs GNU diff(1) in 'context diff' mode
cdiff = gdiff -Nprc5
## or the old way:
#cmd.cdiff = gdiff
#opts.cdiff = -Nprc5
# add new command called meld, runs meld (no need to name twice). If
# the meld executable is not available, the meld tool in [merge-tools]
# will be used, if available
meld =
# add new command called vimdiff, runs gvimdiff with DirDiff plugin
# (see http://www.vim.org/scripts/script.php?script_id=102) Non
# English user, be sure to put "let g:DirDiffDynamicDiffText = 1" in
# your .vimrc
vimdiff = gvim -f "+next" \\
"+execute 'DirDiff' fnameescape(argv(0)) fnameescape(argv(1))"
Tool arguments can include variables that are expanded at runtime::
$parent1, $plabel1 - filename, descriptive label of first parent
$child, $clabel - filename, descriptive label of child revision
$parent2, $plabel2 - filename, descriptive label of second parent
$root - repository root
$parent is an alias for $parent1.
The extdiff extension will look in your [diff-tools] and [merge-tools]
sections for diff tool arguments, when none are specified in [extdiff].
::
[extdiff]
kdiff3 =
[diff-tools]
kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
If a program has a graphical interface, it might be interesting to tell
Mercurial about it. It will prevent the program from being mistakenly
used in a terminal-only environment (such as an SSH terminal session),
and will make :hg:`extdiff --per-file` open multiple file diffs at once
instead of one by one (if you still want to open file diffs one by one,
you can use the --confirm option).
Declaring that a tool has a graphical interface can be done with the
``gui`` flag next to where ``diffargs`` are specified:
::
[diff-tools]
kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
kdiff3.gui = true
You can use -I/-X and list of file or directory names like normal
:hg:`diff` command. The extdiff extension makes snapshots of only
needed files, so running the external diff program will actually be
pretty fast (at least faster than having to compare the entire tree).
'''
from __future__ import absolute_import
import os
import re
import shutil
import stat
import subprocess
from mercurial.i18n import _
from mercurial.node import (
nullid,
short,
)
from mercurial import (
archival,
cmdutil,
encoding,
error,
filemerge,
formatter,
pycompat,
registrar,
scmutil,
util,
)
from mercurial.utils import (
procutil,
stringutil,
)
cmdtable = {}
command = registrar.command(cmdtable)
configtable = {}
configitem = registrar.configitem(configtable)
configitem(
b'extdiff',
br'opts\..*',
default=b'',
generic=True,
)
configitem(
b'extdiff',
br'gui\..*',
generic=True,
)
configitem(
b'diff-tools',
br'.*\.diffargs$',
default=None,
generic=True,
)
configitem(
b'diff-tools',
br'.*\.gui$',
generic=True,
)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'
def snapshot(ui, repo, files, node, tmproot, listsubrepos):
"""snapshot files as of some revision
if not using snapshot, -I/-X does not work and recursive diff
in tools like kdiff3 and meld displays too many files."""
dirname = os.path.basename(repo.root)
if dirname == b"":
dirname = b"root"
if node is not None:
dirname = b'%s.%s' % (dirname, short(node))
base = os.path.join(tmproot, dirname)
os.mkdir(base)
fnsandstat = []
if node is not None:
ui.note(
_(b'making snapshot of %d files from rev %s\n')
% (len(files), short(node))
)
else:
ui.note(
_(b'making snapshot of %d files from working directory\n')
% (len(files))
)
if files:
repo.ui.setconfig(b"ui", b"archivemeta", False)
archival.archive(
repo,
base,
node,
b'files',
match=scmutil.matchfiles(repo, files),
subrepos=listsubrepos,
)
for fn in sorted(files):
wfn = util.pconvert(fn)
ui.note(b' %s\n' % wfn)
if node is None:
dest = os.path.join(base, wfn)
fnsandstat.append((dest, repo.wjoin(fn), os.lstat(dest)))
return dirname, fnsandstat
def formatcmdline(
cmdline,
repo_root,
do3way,
parent1,
plabel1,
parent2,
plabel2,
child,
clabel,
):
# Function to quote file/dir names in the argument string.
# When not operating in 3-way mode, an empty string is
# returned for parent2
replace = {
b'parent': parent1,
b'parent1': parent1,
b'parent2': parent2,
b'plabel1': plabel1,
b'plabel2': plabel2,
b'child': child,
b'clabel': clabel,
b'root': repo_root,
}
def quote(match):
pre = match.group(2)
key = match.group(3)
if not do3way and key == b'parent2':
return pre
return pre + procutil.shellquote(replace[key])
# Match parent2 first, so 'parent1?' will match both parent1 and parent
regex = (
br'''(['"]?)([^\s'"$]*)'''
br'\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)\1'
)
if not do3way and not re.search(regex, cmdline):
cmdline += b' $parent1 $child'
return re.sub(regex, quote, cmdline)
def _systembackground(cmd, environ=None, cwd=None):
"""like 'procutil.system', but returns the Popen object directly
so we don't have to wait on it.
"""
env = procutil.shellenviron(environ)
proc = subprocess.Popen(
procutil.tonativestr(cmd),
shell=True,
close_fds=procutil.closefds,
env=procutil.tonativeenv(env),
cwd=pycompat.rapply(procutil.tonativestr, cwd),
)
return proc
def _runperfilediff(
cmdline,
repo_root,
ui,
guitool,
do3way,
confirm,
commonfiles,
tmproot,
dir1a,
dir1b,
dir2,
rev1a,
rev1b,
rev2,
):
# Note that we need to sort the list of files because it was
# built in an "unstable" way and it's annoying to get files in a
# random order, especially when "confirm" mode is enabled.
waitprocs = []
totalfiles = len(commonfiles)
for idx, commonfile in enumerate(sorted(commonfiles)):
path1a = os.path.join(dir1a, commonfile)
label1a = commonfile + rev1a
if not os.path.isfile(path1a):
path1a = pycompat.osdevnull
path1b = b''
label1b = b''
if do3way:
path1b = os.path.join(dir1b, commonfile)
label1b = commonfile + rev1b
if not os.path.isfile(path1b):
path1b = pycompat.osdevnull
path2 = os.path.join(dir2, commonfile)
label2 = commonfile + rev2
if confirm:
# Prompt before showing this diff
difffiles = _(b'diff %s (%d of %d)') % (
commonfile,
idx + 1,
totalfiles,
)
responses = _(
b'[Yns?]'
b'$$ &Yes, show diff'
b'$$ &No, skip this diff'
b'$$ &Skip remaining diffs'
b'$$ &? (display help)'
)
r = ui.promptchoice(b'%s %s' % (difffiles, responses))
if r == 3: # ?
while r == 3:
for c, t in ui.extractchoices(responses)[1]:
ui.write(b'%s - %s\n' % (c, encoding.lower(t)))
r = ui.promptchoice(b'%s %s' % (difffiles, responses))
if r == 0: # yes
pass
elif r == 1: # no
continue
elif r == 2: # skip
break
curcmdline = formatcmdline(
cmdline,
repo_root,
do3way=do3way,
parent1=path1a,
plabel1=label1a,
parent2=path1b,
plabel2=label1b,
child=path2,
clabel=label2,
)
if confirm or not guitool:
# Run the comparison program and wait for it to exit
# before we show the next file.
# This is because either we need to wait for confirmation
# from the user between each invocation, or because, as far
# as we know, the tool doesn't have a GUI, in which case
# we can't run multiple CLI programs at the same time.
ui.debug(
b'running %r in %s\n' % (pycompat.bytestr(curcmdline), tmproot)
)
ui.system(curcmdline, cwd=tmproot, blockedtag=b'extdiff')
else:
# Run the comparison program but don't wait, as we're
# going to rapid-fire each file diff and then wait on
# the whole group.
ui.debug(
b'running %r in %s (backgrounded)\n'
% (pycompat.bytestr(curcmdline), tmproot)
)
proc = _systembackground(curcmdline, cwd=tmproot)
waitprocs.append(proc)
if waitprocs:
with ui.timeblockedsection(b'extdiff'):
for proc in waitprocs:
proc.wait()
def diffpatch(ui, repo, node1, node2, tmproot, matcher, cmdline):
template = b'hg-%h.patch'
# write patches to temporary files
with formatter.nullformatter(ui, b'extdiff', {}) as fm:
cmdutil.export(
repo,
[repo[node1].rev(), repo[node2].rev()],
fm,
fntemplate=repo.vfs.reljoin(tmproot, template),
match=matcher,
)
label1 = cmdutil.makefilename(repo[node1], template)
label2 = cmdutil.makefilename(repo[node2], template)
file1 = repo.vfs.reljoin(tmproot, label1)
file2 = repo.vfs.reljoin(tmproot, label2)
cmdline = formatcmdline(
cmdline,
repo.root,
# no 3way while comparing patches
do3way=False,
parent1=file1,
plabel1=label1,
# while comparing patches, there is no second parent
parent2=None,
plabel2=None,
child=file2,
clabel=label2,
)
ui.debug(b'running %r in %s\n' % (pycompat.bytestr(cmdline), tmproot))
ui.system(cmdline, cwd=tmproot, blockedtag=b'extdiff')
return 1
def diffrevs(
ui,
repo,
ctx1a,
ctx1b,
ctx2,
matcher,
tmproot,
cmdline,
do3way,
guitool,
opts,
):
subrepos = opts.get(b'subrepos')
# calculate list of files changed between both revs
st = ctx1a.status(ctx2, matcher, listsubrepos=subrepos)
mod_a, add_a, rem_a = set(st.modified), set(st.added), set(st.removed)
if do3way:
stb = ctx1b.status(ctx2, matcher, listsubrepos=subrepos)
mod_b, add_b, rem_b = (
set(stb.modified),
set(stb.added),
set(stb.removed),
)
else:
mod_b, add_b, rem_b = set(), set(), set()
modadd = mod_a | add_a | mod_b | add_b
common = modadd | rem_a | rem_b
if not common:
return 0
# Always make a copy of ctx1a (and ctx1b, if applicable)
# dir1a should contain files which are:
# * modified or removed from ctx1a to ctx2
# * modified or added from ctx1b to ctx2
# (except file added from ctx1a to ctx2 as they were not present in
# ctx1a)
dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a)
dir1a = snapshot(ui, repo, dir1a_files, ctx1a.node(), tmproot, subrepos)[0]
rev1a = b'' if ctx1a.rev() is None else b'@%d' % ctx1a.rev()
if do3way:
# file calculation criteria same as dir1a
dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b)
dir1b = snapshot(
ui, repo, dir1b_files, ctx1b.node(), tmproot, subrepos
)[0]
rev1b = b'@%d' % ctx1b.rev()
else:
dir1b = None
rev1b = b''
fnsandstat = []
# If ctx2 is not the wc or there is >1 change, copy it
dir2root = b''
rev2 = b''
if ctx2.node() is not None:
dir2 = snapshot(ui, repo, modadd, ctx2.node(), tmproot, subrepos)[0]
rev2 = b'@%d' % ctx2.rev()
elif len(common) > 1:
# we only actually need to get the files to copy back to
# the working dir in this case (because the other cases
# are: diffing 2 revisions or single file -- in which case
# the file is already directly passed to the diff tool).
dir2, fnsandstat = snapshot(ui, repo, modadd, None, tmproot, subrepos)
else:
# This lets the diff tool open the changed file directly
dir2 = b''
dir2root = repo.root
label1a = rev1a
label1b = rev1b
label2 = rev2
if not opts.get(b'per_file'):
# If only one change, diff the files instead of the directories
# Handle bogus modifies correctly by checking if the files exist
if len(common) == 1:
common_file = util.localpath(common.pop())
dir1a = os.path.join(tmproot, dir1a, common_file)
label1a = common_file + rev1a
if not os.path.isfile(dir1a):
dir1a = pycompat.osdevnull
if do3way:
dir1b = os.path.join(tmproot, dir1b, common_file)
label1b = common_file + rev1b
if not os.path.isfile(dir1b):
dir1b = pycompat.osdevnull
dir2 = os.path.join(dir2root, dir2, common_file)
label2 = common_file + rev2
# Run the external tool on the 2 temp directories or the patches
cmdline = formatcmdline(
cmdline,
repo.root,
do3way=do3way,
parent1=dir1a,
plabel1=label1a,
parent2=dir1b,
plabel2=label1b,
child=dir2,
clabel=label2,
)
ui.debug(b'running %r in %s\n' % (pycompat.bytestr(cmdline), tmproot))
ui.system(cmdline, cwd=tmproot, blockedtag=b'extdiff')
else:
# Run the external tool once for each pair of files
_runperfilediff(
cmdline,
repo.root,
ui,
guitool=guitool,
do3way=do3way,
confirm=opts.get(b'confirm'),
commonfiles=common,
tmproot=tmproot,
dir1a=os.path.join(tmproot, dir1a),
dir1b=os.path.join(tmproot, dir1b) if do3way else None,
dir2=os.path.join(dir2root, dir2),
rev1a=rev1a,
rev1b=rev1b,
rev2=rev2,
)
for copy_fn, working_fn, st in fnsandstat:
cpstat = os.lstat(copy_fn)
# Some tools copy the file and attributes, so mtime may not detect
# all changes. A size check will detect more cases, but not all.
# The only certain way to detect every case is to diff all files,
# which could be expensive.
# copyfile() carries over the permission, so the mode check could
# be in an 'elif' branch, but for the case where the file has
# changed without affecting mtime or size.
if (
cpstat[stat.ST_MTIME] != st[stat.ST_MTIME]
or cpstat.st_size != st.st_size
or (cpstat.st_mode & 0o100) != (st.st_mode & 0o100)
):
ui.debug(
b'file changed while diffing. '
b'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn)
)
util.copyfile(copy_fn, working_fn)
return 1
def dodiff(ui, repo, cmdline, pats, opts, guitool=False):
"""Do the actual diff:
- copy to a temp structure if diffing 2 internal revisions
- copy to a temp structure if diffing working revision with
another one and more than 1 file is changed
- just invoke the diff for a single file in the working dir
"""
cmdutil.check_at_most_one_arg(opts, b'rev', b'change')
revs = opts.get(b'rev')
from_rev = opts.get(b'from')
to_rev = opts.get(b'to')
change = opts.get(b'change')
do3way = b'$parent2' in cmdline
if change:
ctx2 = scmutil.revsingle(repo, change, None)
ctx1a, ctx1b = ctx2.p1(), ctx2.p2()
elif from_rev or to_rev:
repo = scmutil.unhidehashlikerevs(
repo, [from_rev] + [to_rev], b'nowarn'
)
ctx1a = scmutil.revsingle(repo, from_rev, None)
ctx1b = repo[nullid]
ctx2 = scmutil.revsingle(repo, to_rev, None)
else:
ctx1a, ctx2 = scmutil.revpair(repo, revs)
if not revs:
ctx1b = repo[None].p2()
else:
ctx1b = repo[nullid]
# Disable 3-way merge if there is only one parent
if do3way:
if ctx1b.node() == nullid:
do3way = False
matcher = scmutil.match(ctx2, pats, opts)
if opts.get(b'patch'):
if opts.get(b'subrepos'):
raise error.Abort(_(b'--patch cannot be used with --subrepos'))
if opts.get(b'per_file'):
raise error.Abort(_(b'--patch cannot be used with --per-file'))
if ctx2.node() is None:
raise error.Abort(_(b'--patch requires two revisions'))
tmproot = pycompat.mkdtemp(prefix=b'extdiff.')
try:
if opts.get(b'patch'):
return diffpatch(
ui, repo, ctx1a.node(), ctx2.node(), tmproot, matcher, cmdline
)
return diffrevs(
ui,
repo,
ctx1a,
ctx1b,
ctx2,
matcher,
tmproot,
cmdline,
do3way,
guitool,
opts,
)
finally:
ui.note(_(b'cleaning up temp directory\n'))
shutil.rmtree(tmproot)
extdiffopts = (
[
(
b'o',
b'option',
[],
_(b'pass option to comparison program'),
_(b'OPT'),
),
(b'r', b'rev', [], _(b'revision (DEPRECATED)'), _(b'REV')),
(b'', b'from', b'', _(b'revision to diff from'), _(b'REV1')),
(b'', b'to', b'', _(b'revision to diff to'), _(b'REV2')),
(b'c', b'change', b'', _(b'change made by revision'), _(b'REV')),
(
b'',
b'per-file',
False,
_(b'compare each file instead of revision snapshots'),
),
(
b'',
b'confirm',
False,
_(b'prompt user before each external program invocation'),
),
(b'', b'patch', None, _(b'compare patches for two revisions')),
]
+ cmdutil.walkopts
+ cmdutil.subrepoopts
)
@command(
b'extdiff',
[
(b'p', b'program', b'', _(b'comparison program to run'), _(b'CMD')),
]
+ extdiffopts,
_(b'hg extdiff [OPT]... [FILE]...'),
helpcategory=command.CATEGORY_FILE_CONTENTS,
inferrepo=True,
)
def extdiff(ui, repo, *pats, **opts):
"""use external program to diff repository (or selected files)
Show differences between revisions for the specified files, using
an external program. The default program used is diff, with
default options "-Npru".
To select a different program, use the -p/--program option. The
program will be passed the names of two directories to compare,
unless the --per-file option is specified (see below). To pass
additional options to the program, use -o/--option. These will be
passed before the names of the directories or files to compare.
The --from, --to, and --change options work the same way they do for
:hg:`diff`.
The --per-file option runs the external program repeatedly on each
file to diff, instead of once on two directories. By default,
this happens one by one, where the next file diff is open in the
external program only once the previous external program (for the
previous file diff) has exited. If the external program has a
graphical interface, it can open all the file diffs at once instead
of one by one. See :hg:`help -e extdiff` for information about how
to tell Mercurial that a given program has a graphical interface.
The --confirm option will prompt the user before each invocation of
the external program. It is ignored if --per-file isn't specified.
"""
opts = pycompat.byteskwargs(opts)
program = opts.get(b'program')
option = opts.get(b'option')
if not program:
program = b'diff'
option = option or [b'-Npru']
cmdline = b' '.join(map(procutil.shellquote, [program] + option))
return dodiff(ui, repo, cmdline, pats, opts)
class savedcmd(object):
"""use external program to diff repository (or selected files)
Show differences between revisions for the specified files, using
the following program::
%(path)s
When two revision arguments are given, then changes are shown
between those revisions. If only one revision is specified then
that revision is compared to the working directory, and, when no
revisions are specified, the working directory files are compared
to its parent.
"""
def __init__(self, path, cmdline, isgui):
# We can't pass non-ASCII through docstrings (and path is
# in an unknown encoding anyway), but avoid double separators on
# Windows
docpath = stringutil.escapestr(path).replace(b'\\\\', b'\\')
self.__doc__ %= {'path': pycompat.sysstr(stringutil.uirepr(docpath))}
self._cmdline = cmdline
self._isgui = isgui
def __call__(self, ui, repo, *pats, **opts):
opts = pycompat.byteskwargs(opts)
options = b' '.join(map(procutil.shellquote, opts[b'option']))
if options:
options = b' ' + options
return dodiff(
ui, repo, self._cmdline + options, pats, opts, guitool=self._isgui
)
def _gettooldetails(ui, cmd, path):
"""
returns following things for a
```
[extdiff]
<cmd> = <path>
```
entry:
cmd: command/tool name
path: path to the tool
cmdline: the command which should be run
isgui: whether the tool uses GUI or not
Reads all external tools related configs, whether it be extdiff section,
diff-tools or merge-tools section, or its specified in an old format or
the latest format.
"""
path = util.expandpath(path)
if cmd.startswith(b'cmd.'):
cmd = cmd[4:]
if not path:
path = procutil.findexe(cmd)
if path is None:
path = filemerge.findexternaltool(ui, cmd) or cmd
diffopts = ui.config(b'extdiff', b'opts.' + cmd)
cmdline = procutil.shellquote(path)
if diffopts:
cmdline += b' ' + diffopts
isgui = ui.configbool(b'extdiff', b'gui.' + cmd)
else:
if path:
# case "cmd = path opts"
cmdline = path
diffopts = len(pycompat.shlexsplit(cmdline)) > 1
else:
# case "cmd ="
path = procutil.findexe(cmd)
if path is None:
path = filemerge.findexternaltool(ui, cmd) or cmd
cmdline = procutil.shellquote(path)
diffopts = False
isgui = ui.configbool(b'extdiff', b'gui.' + cmd)
# look for diff arguments in [diff-tools] then [merge-tools]
if not diffopts:
key = cmd + b'.diffargs'
for section in (b'diff-tools', b'merge-tools'):
args = ui.config(section, key)
if args:
cmdline += b' ' + args
if isgui is None:
isgui = ui.configbool(section, cmd + b'.gui') or False
break
return cmd, path, cmdline, isgui
def uisetup(ui):
for cmd, path in ui.configitems(b'extdiff'):
if cmd.startswith(b'opts.') or cmd.startswith(b'gui.'):
continue
cmd, path, cmdline, isgui = _gettooldetails(ui, cmd, path)
command(
cmd,
extdiffopts[:],
_(b'hg %s [OPTION]... [FILE]...') % cmd,
helpcategory=command.CATEGORY_FILE_CONTENTS,
inferrepo=True,
)(savedcmd(path, cmdline, isgui))
# tell hggettext to extract docstrings from these functions:
i18nfunctions = [savedcmd]