view hgext/fsmonitor/state.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.

# state.py - fsmonitor persistent state
#
# Copyright 2013-2016 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import errno
import os
import socket
import struct

from mercurial.i18n import _
from mercurial import pathutil

_version = 4
_versionformat = ">I"

class state(object):
    def __init__(self, repo):
        self._opener = repo.opener
        self._ui = repo.ui
        self._rootdir = pathutil.normasprefix(repo.root)
        self._lastclock = None

        self.mode = self._ui.config('fsmonitor', 'mode', default='on')
        self.walk_on_invalidate = self._ui.configbool(
            'fsmonitor', 'walk_on_invalidate', False)
        self.timeout = float(self._ui.config(
            'fsmonitor', 'timeout', default='2'))

    def get(self):
        try:
            file = self._opener('fsmonitor.state', 'rb')
        except IOError as inst:
            if inst.errno != errno.ENOENT:
                raise
            return None, None, None

        versionbytes = file.read(4)
        if len(versionbytes) < 4:
            self._ui.log(
                'fsmonitor', 'fsmonitor: state file only has %d bytes, '
                'nuking state\n' % len(versionbytes))
            self.invalidate()
            return None, None, None
        try:
            diskversion = struct.unpack(_versionformat, versionbytes)[0]
            if diskversion != _version:
                # different version, nuke state and start over
                self._ui.log(
                    'fsmonitor', 'fsmonitor: version switch from %d to '
                    '%d, nuking state\n' % (diskversion, _version))
                self.invalidate()
                return None, None, None

            state = file.read().split('\0')
            # state = hostname\0clock\0ignorehash\0 + list of files, each
            # followed by a \0
            if len(state) < 3:
                self._ui.log(
                    'fsmonitor', 'fsmonitor: state file truncated (expected '
                    '3 chunks, found %d), nuking state\n', len(state))
                self.invalidate()
                return None, None, None
            diskhostname = state[0]
            hostname = socket.gethostname()
            if diskhostname != hostname:
                # file got moved to a different host
                self._ui.log('fsmonitor', 'fsmonitor: stored hostname "%s" '
                             'different from current "%s", nuking state\n' %
                             (diskhostname, hostname))
                self.invalidate()
                return None, None, None

            clock = state[1]
            ignorehash = state[2]
            # discard the value after the last \0
            notefiles = state[3:-1]

        finally:
            file.close()

        return clock, ignorehash, notefiles

    def set(self, clock, ignorehash, notefiles):
        if clock is None:
            self.invalidate()
            return

        try:
            file = self._opener('fsmonitor.state', 'wb', atomictemp=True)
        except (IOError, OSError):
            self._ui.warn(_("warning: unable to write out fsmonitor state\n"))
            return

        with file:
            file.write(struct.pack(_versionformat, _version))
            file.write(socket.gethostname() + '\0')
            file.write(clock + '\0')
            file.write(ignorehash + '\0')
            if notefiles:
                file.write('\0'.join(notefiles))
                file.write('\0')

    def invalidate(self):
        try:
            os.unlink(os.path.join(self._rootdir, '.hg', 'fsmonitor.state'))
        except OSError as inst:
            if inst.errno != errno.ENOENT:
                raise

    def setlastclock(self, clock):
        self._lastclock = clock

    def getlastclock(self):
        return self._lastclock