tests/autodiff.py

copies: filter out copies from non-existent source later in _chain()

_changesetforwardcopies() repeatedly calls _chain(). That is very
expensive because _chain() does lookups in the manifest. I hope to
split up the function in two parts: 1) simple chaining, not
considering end points, and 2) filter out files that don't exist in
the end points (and ping-pong copies/renames).

This patches gets us closer to that by moving the check for
non-existent source later in the function. Now there are no more
checks for "src" and "dst" in the first loop; all the filtering of
invalid copies is done in the second loop. The code also looks much
more consistent now.

No measureable impact on `hg debugpathcopies 4.0 4.8`. That shouldn't
be surprising since the only case we're doing more checks now is in
case of chained copies/renames, which are quire rare in practice.

Differential Revision: https://phab.mercurial-scm.org/D6277

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

from __future__ import absolute_import

from mercurial import (
    error,
    patch,
    pycompat,
    registrar,
    scmutil,
)

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

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

    ctx1, ctx2 = scmutil.revpair(repo, [])
    m = scmutil.match(ctx2, pats, opts)
    it = patch.diff(repo, ctx1.node(), ctx2.node(), match=m, opts=diffopts,
                    losedatafn=losedatafn)
    for chunk in it:
        ui.write(chunk)
    for fn in sorted(brokenfiles):
        ui.write((b'data lost for: %s\n' % fn))