view hgext/censor.py @ 30817:2b279126b8f5

revlog: use compression engine APIs for decompression

Now that compression engines declare their header in revlog chunks
and can decompress revlog chunks, we refactor revlog.decompress()
to use them.

Making full use of the property that revlog compressor objects are
reusable, revlog instances now maintain a dict mapping an engine's
revlog header to a compressor object. This is not only a performance
optimization for engines where compressor object reuse can result in
better performance, but it also serves as a cache of header values
so we don't need to perform redundant lookups against the compression
engine manager. (Yes, I measured and the overhead of a function call
versus a dict lookup was observed.)

Replacing the previous inline lookup table with a dict lookup was
measured to make chunk reading ~2.5% slower on changelogs and ~4.5%
slower on manifests. So, the inline lookup table has been mostly
preserved so we don't lose performance. This is unfortunate. But
many decompression operations complete in microseconds, so Python
attribute lookup, dict lookup, and function calls do matter.

The impact of this change on mozilla-unified is as follows:

$ hg perfrevlogchunks -c
! chunk
! wall 1.953663 comb 1.950000 user 1.920000 sys 0.030000 (best of 6)
! wall 1.946000 comb 1.940000 user 1.910000 sys 0.030000 (best of 6)
! chunk batch
! wall 1.791075 comb 1.800000 user 1.760000 sys 0.040000 (best of 6)
! wall 1.785690 comb 1.770000 user 1.750000 sys 0.020000 (best of 6)

$ hg perfrevlogchunks -m
! chunk
! wall 2.587262 comb 2.580000 user 2.550000 sys 0.030000 (best of 4)
! wall 2.616330 comb 2.610000 user 2.560000 sys 0.050000 (best of 4)
! chunk batch
! wall 2.427092 comb 2.420000 user 2.400000 sys 0.020000 (best of 5)
! wall 2.462061 comb 2.460000 user 2.400000 sys 0.060000 (best of 4)

Changelog chunk reading is slightly faster but manifest reading is
slower. What gives?

On this repo, 99.85% of changelog entries are zlib compressed (the 'x'
header). On the manifest, 67.5% are zlib and 32.4% are '\0'. This patch
swapped the test order of 'x' and '\0' so now 'x' is tested first. This
makes changelogs faster since they almost always hit the first branch.
This makes a significant percentage of manifest '\0' chunks slower
because that code path now performs an extra test. Yes, I too can't
believe we're able to measure the impact of an if..elif with simple
string compares. I reckon this code would benefit from being written
in C...

# 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.
"""

from __future__ import absolute_import

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

from mercurial import (
    cmdutil,
    error,
    filelog,
    lock as lockmod,
    revlog,
    scmutil,
    util,
)

cmdtable = {}
command = cmdutil.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'

@command('censor',
    [('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):
    wlock = lock = None
    try:
        wlock = repo.wlock()
        lock = repo.lock()
        return _docensor(ui, repo, path, rev, tombstone, **opts)
    finally:
        lockmod.release(lock, wlock)

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

    try:
        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.REVLOGNG:
        raise error.Abort(
            _('censor does not support revlog version %d') % (flogv,))

    tombstone = filelog.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.REVLOGNGINLINEDATA:
        dataread, datawrite = idxread, idxwrite
    else:
        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):
        idxwrite.write(chunk)
    for chunk in util.filechunkiter(dataread, limit=offset):
        datawrite.write(chunk)

    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.

        Returns:
            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))
        datawrite.write(flag)
        datawrite.write(compdata)
        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 xrange(crev + 1, len(flog)):
        if crev in flog.parentrevs(srev):
            # Immediate children of censored node must be re-added as fulltext.
            try:
                revdata = flog.revision(srev)
            except error.CensoredNodeError as e:
                revdata = e.tombstone
            dlen = rewrite(srev, offset, revdata)
        else:
            # 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):
                datawrite.write(chunk)
        offset += dlen

    idxread.close()
    idxwrite.close()
    if dataread is not idxread:
        dataread.close()
        datawrite.close()