hgext/largefiles/localstore.py

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 2009-2010 Gregory P. Ward
# Copyright 2009-2010 Intelerad Medical Systems Incorporated
# Copyright 2010-2011 Fog Creek Software
# Copyright 2010-2011 Unity Technologies
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''store class for local filesystem'''
from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import util

from . import (
    basestore,
    lfutil,
)

class localstore(basestore.basestore):
    '''localstore first attempts to grab files out of the store in the remote
    Mercurial repository.  Failing that, it attempts to grab the files from
    the user cache.'''

    def __init__(self, ui, repo, remote):
        self.remote = remote.local()
        super(localstore, self).__init__(ui, repo, self.remote.url())

    def put(self, source, hash):
        if lfutil.instore(self.remote, hash):
            return
        lfutil.link(source, lfutil.storepath(self.remote, hash))

    def exists(self, hashes):
        retval = {}
        for hash in hashes:
            retval[hash] = lfutil.instore(self.remote, hash)
        return retval

    def _getfile(self, tmpfile, filename, hash):
        path = lfutil.findfile(self.remote, hash)
        if not path:
            raise basestore.StoreError(filename, hash, self.url,
                _("can't get file locally"))
        with open(path, 'rb') as fd:
            return lfutil.copyandhash(
                util.filechunkiter(fd), tmpfile)

    def _verifyfiles(self, contents, filestocheck):
        failed = False
        for cset, filename, expectedhash in filestocheck:
            storepath, exists = lfutil.findstorepath(self.repo, expectedhash)
            if not exists:
                storepath, exists = lfutil.findstorepath(
                    self.remote, expectedhash)
            if not exists:
                self.ui.warn(
                    _('changeset %s: %s references missing %s\n')
                    % (cset, filename, storepath))
                failed = True
            elif contents:
                actualhash = lfutil.hashfile(storepath)
                if actualhash != expectedhash:
                    self.ui.warn(
                        _('changeset %s: %s references corrupted %s\n')
                        % (cset, filename, storepath))
                    failed = True
        return failed