view hgext/share.py @ 30745:c1b7b2285522

revlog: flag processor

Add the ability for revlog objects to process revision flags and apply
registered transforms on read/write operations.

This patch introduces:
- the 'revlog._processflags()' method that looks at revision flags and applies
  flag processors registered on them. Due to the need to handle non-commutative
  operations, flag transforms are applied in stable order but the order in which
  the transforms are applied is reversed between read and write operations.
- the 'addflagprocessor()' method allowing to register processors on flags.
  Flag processors are defined as a 3-tuple of (read, write, raw) functions to be
  applied depending on the operation being performed.
- an update on 'revlog.addrevision()' behavior. The current flagprocessor design
  relies on extensions to wrap around 'addrevision()' to set flags on revision
  data, and on the flagprocessor to perform the actual transformation of its
  contents. In the lfs case, this means we need to process flags before we meet
  the 2GB size check, leading to performing some operations before it happens:
  - if flags are set on the revision data, we assume some extensions might be
    modifying the contents using the flag processor next, and we compute the
    node for the original revision data (still allowing extension to override
    the node by wrapping around 'addrevision()').
  - we then invoke the flag processor to apply registered transforms (in lfs's
    case, drastically reducing the size of large blobs).
  - finally, we proceed with the 2GB size check.

Note: In the case a cachedelta is passed to 'addrevision()' and we detect the
flag processor modified the revision data, we chose to trust the flag processor
and drop the cachedelta.

# Copyright 2006, 2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''share a common history between several working directories

Automatic Pooled Storage for Clones
-----------------------------------

When this extension is active, :hg:`clone` can be configured to
automatically share/pool storage across multiple clones. This
mode effectively converts :hg:`clone` to :hg:`clone` + :hg:`share`.
The benefit of using this mode is the automatic management of
store paths and intelligent pooling of related repositories.

The following ``share.`` config options influence this feature:

``share.pool``
    Filesystem path where shared repository data will be stored. When
    defined, :hg:`clone` will automatically use shared repository
    storage instead of creating a store inside each clone.

``share.poolnaming``
    How directory names in ``share.pool`` are constructed.

    "identity" means the name is derived from the first changeset in the
    repository. In this mode, different remotes share storage if their
    root/initial changeset is identical. In this mode, the local shared
    repository is an aggregate of all encountered remote repositories.

    "remote" means the name is derived from the source repository's
    path or URL. In this mode, storage is only shared if the path or URL
    requested in the :hg:`clone` command matches exactly to a repository
    that was cloned before.

    The default naming mode is "identity."
'''

from __future__ import absolute_import

import errno
from mercurial.i18n import _
from mercurial import (
    bookmarks,
    cmdutil,
    commands,
    error,
    extensions,
    hg,
    util,
)

repository = hg.repository
parseurl = hg.parseurl

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('share',
    [('U', 'noupdate', None, _('do not create a working directory')),
     ('B', 'bookmarks', None, _('also share bookmarks'))],
    _('[-U] [-B] SOURCE [DEST]'),
    norepo=True)
def share(ui, source, dest=None, noupdate=False, bookmarks=False):
    """create a new shared repository

    Initialize a new repository and working directory that shares its
    history (and optionally bookmarks) with another repository.

    .. note::

       using rollback or extensions that destroy/modify history (mq,
       rebase, etc.) can cause considerable confusion with shared
       clones. In particular, if two shared clones are both updated to
       the same changeset, and one of them destroys that changeset
       with rollback, the other clone will suddenly stop working: all
       operations will fail with "abort: working directory has unknown
       parent". The only known workaround is to use debugsetparents on
       the broken clone to reset it to a changeset that still exists.
    """

    return hg.share(ui, source, dest=dest, update=not noupdate,
                    bookmarks=bookmarks)

@command('unshare', [], '')
def unshare(ui, repo):
    """convert a shared repository to a normal one

    Copy the store data to the repo and remove the sharedpath data.
    """

    if not repo.shared():
        raise error.Abort(_("this is not a shared repo"))

    destlock = lock = None
    lock = repo.lock()
    try:
        # we use locks here because if we race with commit, we
        # can end up with extra data in the cloned revlogs that's
        # not pointed to by changesets, thus causing verify to
        # fail

        destlock = hg.copystore(ui, repo, repo.path)

        sharefile = repo.join('sharedpath')
        util.rename(sharefile, sharefile + '.old')

        repo.requirements.discard('sharedpath')
        repo._writerequirements()
    finally:
        destlock and destlock.release()
        lock and lock.release()

    # update store, spath, svfs and sjoin of repo
    repo.unfiltered().__init__(repo.baseui, repo.root)

# Wrap clone command to pass auto share options.
def clone(orig, ui, source, *args, **opts):
    pool = ui.config('share', 'pool', None)
    if pool:
        pool = util.expandpath(pool)

    opts['shareopts'] = dict(
        pool=pool,
        mode=ui.config('share', 'poolnaming', 'identity'),
    )

    return orig(ui, source, *args, **opts)

def extsetup(ui):
    extensions.wrapfunction(bookmarks, '_getbkfile', getbkfile)
    extensions.wrapfunction(bookmarks.bmstore, 'recordchange', recordchange)
    extensions.wrapfunction(bookmarks.bmstore, '_writerepo', writerepo)
    extensions.wrapcommand(commands.table, 'clone', clone)

def _hassharedbookmarks(repo):
    """Returns whether this repo has shared bookmarks"""
    try:
        shared = repo.vfs.read('shared').splitlines()
    except IOError as inst:
        if inst.errno != errno.ENOENT:
            raise
        return False
    return hg.sharedbookmarks in shared

def _getsrcrepo(repo):
    """
    Returns the source repository object for a given shared repository.
    If repo is not a shared repository, return None.
    """
    if repo.sharedpath == repo.path:
        return None

    if util.safehasattr(repo, 'srcrepo') and repo.srcrepo:
        return repo.srcrepo

    # the sharedpath always ends in the .hg; we want the path to the repo
    source = repo.vfs.split(repo.sharedpath)[0]
    srcurl, branches = parseurl(source)
    srcrepo = repository(repo.ui, srcurl)
    repo.srcrepo = srcrepo
    return srcrepo

def getbkfile(orig, repo):
    if _hassharedbookmarks(repo):
        srcrepo = _getsrcrepo(repo)
        if srcrepo is not None:
            repo = srcrepo
    return orig(repo)

def recordchange(orig, self, tr):
    # Continue with write to local bookmarks file as usual
    orig(self, tr)

    if _hassharedbookmarks(self._repo):
        srcrepo = _getsrcrepo(self._repo)
        if srcrepo is not None:
            category = 'share-bookmarks'
            tr.addpostclose(category, lambda tr: self._writerepo(srcrepo))

def writerepo(orig, self, repo):
    # First write local bookmarks file in case we ever unshare
    orig(self, repo)

    if _hassharedbookmarks(self._repo):
        srcrepo = _getsrcrepo(self._repo)
        if srcrepo is not None:
            orig(self, srcrepo)