Mercurial > hg
view hgext/extdiff.py @ 30561:7c0c722d568d
bdiff: early pruning of common prefix before doing expensive computations
It seems quite common that files don't change completely. New lines are often
pretty much appended, and modifications will often only change a small section
of the file which on average will be in the middle.
There can thus be a big win by pruning a common prefix before starting the more
expensive search for longest common substrings.
Worst case, it will scan through a long sequence of similar bytes without
encountering a newline. Splitlines will then have to do the same again ...
twice for each side. If similar lines are found, splitlines will save the
double iteration and hashing of the lines ... plus there will be less lines to
find common substrings in.
This change might in some cases make the algorith pick shorter or less optimal
common substrings. We can't have the cake and eat it.
This make hg --time bundle --base null -r 4.0 go from 14.5 to 15 s - a 3%
increase.
On mozilla-unified:
perfbdiff -m 3041e4d59df2
! wall 0.053088 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) to
! wall 0.024618 comb 0.020000 user 0.020000 sys 0.000000 (best of 116)
perfbdiff 0e9928989e9c --alldata --count 10
! wall 0.702075 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) to
! wall 0.579235 comb 0.580000 user 0.580000 sys 0.000000 (best of 18)
author | Mads Kiilerich <madski@unity3d.com> |
---|---|
date | Wed, 16 Nov 2016 19:45:35 +0100 |
parents | d5883fd055c6 |
children | caf7e1c5efe4 |
line wrap: on
line source
# 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. 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 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 shlex import shutil import tempfile from mercurial.i18n import _ from mercurial.node import ( nullid, short, ) from mercurial import ( archival, cmdutil, commands, error, filemerge, scmutil, util, ) cmdtable = {} command = cmdutil.command(cmdtable) # 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 = '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 == "": dirname = "root" if node is not None: dirname = '%s.%s' % (dirname, short(node)) base = os.path.join(tmproot, dirname) os.mkdir(base) fns_and_mtime = [] if node is not None: ui.note(_('making snapshot of %d files from rev %s\n') % (len(files), short(node))) else: ui.note(_('making snapshot of %d files from working directory\n') % (len(files))) if files: repo.ui.setconfig("ui", "archivemeta", False) archival.archive(repo, base, node, 'files', matchfn=scmutil.matchfiles(repo, files), subrepos=listsubrepos) for fn in sorted(files): wfn = util.pconvert(fn) ui.note(' %s\n' % wfn) if node is None: dest = os.path.join(base, wfn) fns_and_mtime.append((dest, repo.wjoin(fn), os.lstat(dest).st_mtime)) return dirname, fns_and_mtime def dodiff(ui, repo, cmdline, pats, opts): '''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 ''' revs = opts.get('rev') change = opts.get('change') do3way = '$parent2' in cmdline if revs and change: msg = _('cannot specify --rev and --change at the same time') raise error.Abort(msg) elif change: node2 = scmutil.revsingle(repo, change, None).node() node1a, node1b = repo.changelog.parents(node2) else: node1a, node2 = scmutil.revpair(repo, revs) if not revs: node1b = repo.dirstate.p2() else: node1b = nullid # Disable 3-way merge if there is only one parent if do3way: if node1b == nullid: do3way = False subrepos=opts.get('subrepos') matcher = scmutil.match(repo[node2], pats, opts) if opts.get('patch'): if subrepos: raise error.Abort(_('--patch cannot be used with --subrepos')) if node2 is None: raise error.Abort(_('--patch requires two revisions')) else: mod_a, add_a, rem_a = map(set, repo.status(node1a, node2, matcher, listsubrepos=subrepos)[:3]) if do3way: mod_b, add_b, rem_b = map(set, repo.status(node1b, node2, matcher, listsubrepos=subrepos)[:3]) 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 tmproot = tempfile.mkdtemp(prefix='extdiff.') try: if not opts.get('patch'): # Always make a copy of node1a (and node1b, if applicable) dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a) dir1a = snapshot(ui, repo, dir1a_files, node1a, tmproot, subrepos)[0] rev1a = '@%d' % repo[node1a].rev() if do3way: dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b) dir1b = snapshot(ui, repo, dir1b_files, node1b, tmproot, subrepos)[0] rev1b = '@%d' % repo[node1b].rev() else: dir1b = None rev1b = '' fns_and_mtime = [] # If node2 in not the wc or there is >1 change, copy it dir2root = '' rev2 = '' if node2: dir2 = snapshot(ui, repo, modadd, node2, tmproot, subrepos)[0] rev2 = '@%d' % repo[node2].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, fns_and_mtime = snapshot(ui, repo, modadd, None, tmproot, subrepos) else: # This lets the diff tool open the changed file directly dir2 = '' dir2root = repo.root label1a = rev1a label1b = rev1b label2 = rev2 # 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 = os.devnull if do3way: dir1b = os.path.join(tmproot, dir1b, common_file) label1b = common_file + rev1b if not os.path.isfile(dir1b): dir1b = os.devnull dir2 = os.path.join(dir2root, dir2, common_file) label2 = common_file + rev2 else: template = 'hg-%h.patch' cmdutil.export(repo, [repo[node1a].rev(), repo[node2].rev()], template=repo.vfs.reljoin(tmproot, template), match=matcher) label1a = cmdutil.makefilename(repo, template, node1a) label2 = cmdutil.makefilename(repo, template, node2) dir1a = repo.vfs.reljoin(tmproot, label1a) dir2 = repo.vfs.reljoin(tmproot, label2) dir1b = None label1b = None fns_and_mtime = [] # 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 = {'parent': dir1a, 'parent1': dir1a, 'parent2': dir1b, 'plabel1': label1a, 'plabel2': label1b, 'clabel': label2, 'child': dir2, 'root': repo.root} def quote(match): pre = match.group(2) key = match.group(3) if not do3way and key == 'parent2': return pre return pre + util.shellquote(replace[key]) # Match parent2 first, so 'parent1?' will match both parent1 and parent regex = (r'''(['"]?)([^\s'"$]*)''' r'\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)\1') if not do3way and not re.search(regex, cmdline): cmdline += ' $parent1 $child' cmdline = re.sub(regex, quote, cmdline) ui.debug('running %r in %s\n' % (cmdline, tmproot)) ui.system(cmdline, cwd=tmproot) for copy_fn, working_fn, mtime in fns_and_mtime: if os.lstat(copy_fn).st_mtime != mtime: ui.debug('file changed while diffing. ' 'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn)) util.copyfile(copy_fn, working_fn) return 1 finally: ui.note(_('cleaning up temp directory\n')) shutil.rmtree(tmproot) extdiffopts = [ ('o', 'option', [], _('pass option to comparison program'), _('OPT')), ('r', 'rev', [], _('revision'), _('REV')), ('c', 'change', '', _('change made by revision'), _('REV')), ('', 'patch', None, _('compare patches for two revisions')) ] + commands.walkopts + commands.subrepoopts @command('extdiff', [('p', 'program', '', _('comparison program to run'), _('CMD')), ] + extdiffopts, _('hg extdiff [OPT]... [FILE]...'), 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. To pass additional options to the program, use -o/--option. These will be passed before the names of the directories to compare. 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.''' program = opts.get('program') option = opts.get('option') if not program: program = 'diff' option = option or ['-Npru'] cmdline = ' '.join(map(util.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): # We can't pass non-ASCII through docstrings (and path is # in an unknown encoding anyway) docpath = path.encode("string-escape") self.__doc__ = self.__doc__ % {'path': util.uirepr(docpath)} self._cmdline = cmdline def __call__(self, ui, repo, *pats, **opts): options = ' '.join(map(util.shellquote, opts['option'])) if options: options = ' ' + options return dodiff(ui, repo, self._cmdline + options, pats, opts) def uisetup(ui): for cmd, path in ui.configitems('extdiff'): path = util.expandpath(path) if cmd.startswith('cmd.'): cmd = cmd[4:] if not path: path = util.findexe(cmd) if path is None: path = filemerge.findexternaltool(ui, cmd) or cmd diffopts = ui.config('extdiff', 'opts.' + cmd, '') cmdline = util.shellquote(path) if diffopts: cmdline += ' ' + diffopts elif cmd.startswith('opts.'): continue else: if path: # case "cmd = path opts" cmdline = path diffopts = len(shlex.split(cmdline)) > 1 else: # case "cmd =" path = util.findexe(cmd) if path is None: path = filemerge.findexternaltool(ui, cmd) or cmd cmdline = util.shellquote(path) diffopts = False # look for diff arguments in [diff-tools] then [merge-tools] if not diffopts: args = ui.config('diff-tools', cmd+'.diffargs') or \ ui.config('merge-tools', cmd+'.diffargs') if args: cmdline += ' ' + args command(cmd, extdiffopts[:], _('hg %s [OPTION]... [FILE]...') % cmd, inferrepo=True)(savedcmd(path, cmdline)) # tell hggettext to extract docstrings from these functions: i18nfunctions = [savedcmd]