hgext/censor.py
author Manuel Jacob <me@manueljacob.de>
Mon, 30 May 2022 16:18:12 +0200
changeset 49248 63fd0282ad40
parent 48875 6000f5b25c9b
child 51266 51056bedbe0d
permissions -rw-r--r--
node: stop converting binascii.Error to TypeError in bin() Changeset f574cc00831a introduced the wrapper, to make bin() behave like on Python 2, where it raised TypeError in many cases. Another previous approach, changing callers to catch binascii.Error in addition to TypeError, was backed out after negative review feedback [1]. However, I think it’s worth reconsidering the approach. Now that we’re on Python 3 only, callers have to catch only binascii.Error instead of both. Catching binascii.Error instead of TypeError has the advantage that it’s less likely to cover a programming error (e.g. passing an int to bin() raises TypeError). Also, raising TypeError never made sense semantically when bin() got an argument of valid type. As a side-effect, this fixed an exception in test-http-bad-server.t. The TODO was outdated: it was not an uncaught ValueError in batch.results() but uncaught TypeError from the now removed wrapper. Now that bin() raises binascii.Error instead of TypeError, it gets converted to a proper error in wirepeer.heads.<locals>.decode() that catches ValueError (superclass of binascii.Error). This is a good example of why this changeset is a good idea. Catching TypeError instead of ValueError there would not make much sense. [1] https://phab.mercurial-scm.org/D2244

# Copyright (C) 2015 - Mike Edgar <adgar@google.com>
#
# 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)