tests/autodiff.py

log: speed up single file log with hidden revs (issue4747)

On repos with lots of heads, the filelog() code could spend several
minutes decompressing manifests. This change instead tries to
efficiently scan the changelog for candidates and decompress as few
manifests as possible. This is a regression introduced in 3.3 by the
linkrev adjustment code. Prior to that, filelog was nearly instant.

For the repo in the bug report, this improves time of a simple log
command from ~3 minutes to ~.5 seconds, a 360x speedup.

For the main Mercurial repo, a log of commands.py slows down from
1.14s to 1.45s, a 27% slowdown. This is still faster than the file()
revset, which takes 2.1 seconds.

# Extension dedicated to test patch.diff() upgrade modes

from __future__ import absolute_import

from mercurial import (
    cmdutil,
    error,
    patch,
    scmutil,
)

cmdtable = {}
command = cmdutil.command(cmdtable)

@command('autodiff',
    [('', 'git', '', 'git upgrade mode (yes/no/auto/warn/abort)')],
    '[OPTION]... [FILE]...')
def autodiff(ui, repo, *pats, **opts):
    diffopts = patch.difffeatureopts(ui, opts)
    git = opts.get('git', 'no')
    brokenfiles = set()
    losedatafn = None
    if git in ('yes', 'no'):
        diffopts.git = git == 'yes'
        diffopts.upgrade = False
    elif git == 'auto':
        diffopts.git = False
        diffopts.upgrade = True
    elif git == 'warn':
        diffopts.git = False
        diffopts.upgrade = True
        def losedatafn(fn=None, **kwargs):
            brokenfiles.add(fn)
            return True
    elif git == 'abort':
        diffopts.git = False
        diffopts.upgrade = True
        def losedatafn(fn=None, **kwargs):
            raise error.Abort('losing data for %s' % fn)
    else:
        raise error.Abort('--git must be yes, no or auto')

    node1, node2 = scmutil.revpair(repo, [])
    m = scmutil.match(repo[node2], pats, opts)
    it = patch.diff(repo, node1, node2, match=m, opts=diffopts,
                    losedatafn=losedatafn)
    for chunk in it:
        ui.write(chunk)
    for fn in sorted(brokenfiles):
        ui.write(('data lost for: %s\n' % fn))