view tests/flagprocessorext.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

# coding=UTF-8

from __future__ import absolute_import

import base64
import zlib

from mercurial import (
    changegroup,
    exchange,
    extensions,
    revlog,
    util,
)

# Test only: These flags are defined here only in the context of testing the
# behavior of the flag processor. The canonical way to add flags is to get in
# touch with the community and make them known in revlog.
REVIDX_NOOP = (1 << 3)
REVIDX_BASE64 = (1 << 2)
REVIDX_GZIP = (1 << 1)
REVIDX_FAIL = 1

def validatehash(self, text):
    return True

def bypass(self, text):
    return False

def noopdonothing(self, text):
    return (text, True)

def b64encode(self, text):
    return (base64.b64encode(text), False)

def b64decode(self, text):
    return (base64.b64decode(text), True)

def gzipcompress(self, text):
    return (zlib.compress(text), False)

def gzipdecompress(self, text):
    return (zlib.decompress(text), True)

def supportedoutgoingversions(orig, repo):
    versions = orig(repo)
    versions.discard(b'01')
    versions.discard(b'02')
    versions.add(b'03')
    return versions

def allsupportedversions(orig, ui):
    versions = orig(ui)
    versions.add(b'03')
    return versions

def makewrappedfile(obj):
    class wrappedfile(obj.__class__):
        def addrevision(self, text, transaction, link, p1, p2,
                        cachedelta=None, node=None,
                        flags=revlog.REVIDX_DEFAULT_FLAGS):
            if b'[NOOP]' in text:
                flags |= REVIDX_NOOP

            if b'[BASE64]' in text:
                flags |= REVIDX_BASE64

            if b'[GZIP]' in text:
                flags |= REVIDX_GZIP

            # This addrevision wrapper is meant to add a flag we will not have
            # transforms registered for, ensuring we handle this error case.
            if b'[FAIL]' in text:
                flags |= REVIDX_FAIL

            return super(wrappedfile, self).addrevision(text, transaction, link,
                                                        p1, p2,
                                                        cachedelta=cachedelta,
                                                        node=node,
                                                        flags=flags)

    obj.__class__ = wrappedfile

def reposetup(ui, repo):
    class wrappingflagprocessorrepo(repo.__class__):
        def file(self, f):
            orig = super(wrappingflagprocessorrepo, self).file(f)
            makewrappedfile(orig)
            return orig

    repo.__class__ = wrappingflagprocessorrepo

def extsetup(ui):
    # Enable changegroup3 for flags to be sent over the wire
    wrapfunction = extensions.wrapfunction
    wrapfunction(changegroup,
                 'supportedoutgoingversions',
                 supportedoutgoingversions)
    wrapfunction(changegroup,
                 'allsupportedversions',
                 allsupportedversions)

    # Teach revlog about our test flags
    flags = [REVIDX_NOOP, REVIDX_BASE64, REVIDX_GZIP, REVIDX_FAIL]
    revlog.REVIDX_KNOWN_FLAGS |= util.bitsfrom(flags)
    revlog.REVIDX_FLAGS_ORDER.extend(flags)

    # Teach exchange to use changegroup 3
    for k in exchange._bundlespeccontentopts.keys():
        exchange._bundlespeccontentopts[k][b"cg.version"] = b"03"

    # Register flag processors for each extension
    revlog.addflagprocessor(
        REVIDX_NOOP,
        (
            noopdonothing,
            noopdonothing,
            validatehash,
        )
    )
    revlog.addflagprocessor(
        REVIDX_BASE64,
        (
            b64decode,
            b64encode,
            bypass,
        ),
    )
    revlog.addflagprocessor(
        REVIDX_GZIP,
        (
            gzipdecompress,
            gzipcompress,
            bypass
        )
    )