author Gregory Szorc <gregory.szorc@gmail.com>
Wed, 01 Aug 2018 13:00:45 -0700
changeset 47112 e7aa113b14f77959ad4039d873b57100a4d56b31
parent 46674 e219e355e0889f6f91b2266a49b3593f71de89c9
child 50000 a658f97c1ce4e26a4642c192dd524da6c3720329
permissions -rw-r--r--
global: use pycompat.xrange() On Python 3, our module importer automatically rewrites xrange() to pycompat.xrange(). We want to move away from the custom importer on Python 3. This commit converts all instances of xrange() to use pycompat.xrange(). Differential Revision: https://phab.mercurial-scm.org/D4032

# 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

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.

from __future__ import absolute_import

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

from mercurial import (

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 = 'ships-with-hg-core'

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

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

    wctx = repo[None]

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

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

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

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

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

    flogv = flog.version & 0xFFFF
    if flogv != revlog.REVLOGV1:
        raise error.Abort(
            _('censor does not support revlog version %d') % (flogv,))

    tombstone = revlog.packmeta({"censored": tombstone}, "")

    crev = fctx.filerev()

    if len(tombstone) > flog.rawsize(crev):
        raise error.Abort(_(
            'censor tombstone must be no longer than censored data'))

    # Using two files instead of one makes it easy to rewrite entry-by-entry
    idxread = repo.svfs(flog.indexfile, 'r')
    idxwrite = repo.svfs(flog.indexfile, 'wb', atomictemp=True)
    if flog.version & revlog.FLAG_INLINE_DATA:
        dataread, datawrite = idxread, idxwrite
        dataread = repo.svfs(flog.datafile, 'r')
        datawrite = repo.svfs(flog.datafile, 'wb', atomictemp=True)

    # Copy all revlog data up to the entry to be censored.
    rio = revlog.revlogio()
    offset = flog.start(crev)

    for chunk in util.filechunkiter(idxread, limit=crev * rio.size):
    for chunk in util.filechunkiter(dataread, limit=offset):

    def rewriteindex(r, newoffs, newdata=None):
        """Rewrite the index entry with a new data offset and optional new data.

        The newdata argument, if given, is a tuple of three positive integers:
        (new compressed, new uncompressed, added flag bits).
        offlags, comp, uncomp, base, link, p1, p2, nodeid = flog.index[r]
        flags = revlog.gettype(offlags)
        if newdata:
            comp, uncomp, nflags = newdata
            flags |= nflags
        offlags = revlog.offset_type(newoffs, flags)
        e = (offlags, comp, uncomp, r, link, p1, p2, nodeid)
        idxwrite.write(rio.packentry(e, None, flog.version, r))
        idxread.seek(rio.size, 1)

    def rewrite(r, offs, data, nflags=revlog.REVIDX_DEFAULT_FLAGS):
        """Write the given full text to the filelog with the given data offset.

            The integer number of data bytes written, for tracking data offsets.
        flag, compdata = flog.compress(data)
        newcomp = len(flag) + len(compdata)
        rewriteindex(r, offs, (newcomp, len(data), nflags))
        dataread.seek(flog.length(r), 1)
        return newcomp

    # Rewrite censored revlog entry with (padded) tombstone data.
    pad = ' ' * (flog.rawsize(crev) - len(tombstone))
    offset += rewrite(crev, offset, tombstone + pad, revlog.REVIDX_ISCENSORED)

    # Rewrite all following filelog revisions fixing up offsets and deltas.
    for srev in pycompat.xrange(crev + 1, len(flog)):
        if crev in flog.parentrevs(srev):
            # Immediate children of censored node must be re-added as fulltext.
                revdata = flog.revision(srev)
            except error.CensoredNodeError as e:
                revdata = e.tombstone
            dlen = rewrite(srev, offset, revdata)
            # Copy any other revision data verbatim after fixing up the offset.
            rewriteindex(srev, offset)
            dlen = flog.length(srev)
            for chunk in util.filechunkiter(dataread, limit=dlen):
        offset += dlen

    if dataread is not idxread: