view hgext/censor.py @ 49442:816236523765

bisect: avoid adding irrelevant revisions to bisect state

When adding new revisions to the bisect state, it only makes sense to add
information about revisions that are under consideration (i.e., those that are
topologically between the known good and bad revisions). However, if the user
passes in a revset (e.g., '!merge()' to exclude merge commits), hg will resolve
the revset first and add all matching revisions to the bisect state (which in
this case would likely be the majority of revisions in the repo). To avoid this,
revisions should only be added to the bisect state if they are between the good
and bad revisions (and therefore relevant to the bisection).

--

Here are the results of some performance tests using the `mozilla-central` repo
(since it is one of the largest freely-available hg repositories in the wild).
These tests compare the performance of a locally-built `hg` before and after
application of this series. Note that `--noupdate` is passed to avoid including
update time (which should not vary across cases).

Setup (run between each test):
  $ hg bisect --reset
  $ hg bisect --noupdate --bad 56c3ad4bde5c70714b784ccf15d099e0df0f5bde
  $ hg bisect --noupdate --good 57426696adaf08298af3027fa77486fee0633b13

Test using a revset that returns a very large number of revisions:
  $ time hg bisect --noupdate --skip '!merge()' > /dev/null

Before:
  real    0m9.398s
  user    0m9.233s
  sys     0m0.120s

After:
  real    0m1.513s
  user    0m1.425s
  sys     0m0.052s

Test using a revset that is expensive to compute:
  $ time hg bisect --noupdate --skip 'desc("Bug")' > /dev/null

Before:
  real    0m49.853s
  user    0m49.580s
  sys     0m0.243s

After:
  real    0m4.120s
  user    0m4.036s
  sys     0m0.048s

# Copyright (C) 2015 - Mike Edgar <[e-mail]>
#
# This extension enables removal of file content at a given revision,
# rewriting the data/metadata of successive revisions to preserve revision log
# integrity.

"""erase file content at a given revision

The censor command instructs Mercurial to erase all content of a file at a given
revision *without updating the changeset hash.* This allows existing history to
remain valid while preventing future clones/pulls from receiving the erased
data.

Typical uses for censor are due to security or legal requirements, including::

 * Passwords, private keys, cryptographic material
 * Licensed data/code/libraries for which the license has expired
 * Personally Identifiable Information or other private data

Censored nodes can interrupt mercurial's typical operation whenever the excised
data needs to be materialized. Some commands, like ``hg cat``/``hg revert``,
simply fail when asked to produce censored data. Others, like ``hg verify`` and
``hg update``, must be capable of tolerating censored data to continue to
function in a meaningful way. Such commands only tolerate censored file
revisions if they are allowed by the "censor.policy=ignore" config option.

A few informative commands such as ``hg grep`` will unconditionally
ignore censored data and merely report that it was encountered.
"""


from mercurial.i18n import _
from mercurial.node import short

from mercurial import (
    error,
    logcmdutil,
    registrar,
    scmutil,
)

cmdtable = {}
command = registrar.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 = b'ships-with-hg-core'


@command(
    b'censor',
    [
        (
            b'r',
            b'rev',
            b'',
            _(b'censor file from specified revision'),
            _(b'REV'),
        ),
        (b't', b'tombstone', b'', _(b'replacement tombstone data'), _(b'TEXT')),
    ],
    _(b'-r REV [-t TEXT] [FILE]'),
    helpcategory=command.CATEGORY_MAINTENANCE,
)
def censor(ui, repo, path, rev=b'', tombstone=b'', **opts):
    with repo.wlock(), repo.lock():
        return _docensor(ui, repo, path, rev, tombstone, **opts)


def _docensor(ui, repo, path, rev=b'', tombstone=b'', **opts):
    if not path:
        raise error.Abort(_(b'must specify file path to censor'))
    if not rev:
        raise error.Abort(_(b'must specify revision to censor'))

    wctx = repo[None]

    m = scmutil.match(wctx, (path,))
    if m.anypats() or len(m.files()) != 1:
        raise error.Abort(_(b'can only specify an explicit filename'))
    path = m.files()[0]
    flog = repo.file(path)
    if not len(flog):
        raise error.Abort(_(b'cannot censor file with no history'))

    rev = logcmdutil.revsingle(repo, rev, rev).rev()
    try:
        ctx = repo[rev]
    except KeyError:
        raise error.Abort(_(b'invalid revision identifier %s') % rev)

    try:
        fctx = ctx.filectx(path)
    except error.LookupError:
        raise error.Abort(_(b'file does not exist at revision %s') % rev)

    fnode = fctx.filenode()
    heads = []
    for headnode in repo.heads():
        hc = repo[headnode]
        if path in hc and hc.filenode(path) == fnode:
            heads.append(hc)
    if heads:
        headlist = b', '.join([short(c.node()) for c in heads])
        raise error.Abort(
            _(b'cannot censor file in heads (%s)') % headlist,
            hint=_(b'clean/delete and commit first'),
        )

    wp = wctx.parents()
    if ctx.node() in [p.node() for p in wp]:
        raise error.Abort(
            _(b'cannot censor working directory'),
            hint=_(b'clean/delete/update first'),
        )

    with repo.transaction(b'censor') as tr:
        flog.censorrevision(tr, fnode, tombstone=tombstone)