hgext/lfs/pointer.py

fncache: avoid loading the filename cache when not actually modifying it

With time, fncache can become very large. The mozilla-central repo for example,
has a 31M and growing fncache file. Loading this file takes time (280ms for the
mozilla-central repository).

In many scenarios, we don't need to load fncache at all. For example, when
committing changes to existing files, or pushing such commits to another clone.
This patch detects when a name is added via store.vfs(), and only loads the
cache if a) the data metadata file doesn't already exist, or b) when opening
for appending, the data or metadata file exists but has size  (a transaction
rollback leaves behind such files).

Benchmarks (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz
and flash drive), each test without and with patch run 5 times:

* committing to an existing file, against the mozilla-central repository.
  Baseline real time average 2.3736, with patch 1.9884.

* unbundling a large changeset consisting *only* of existing-file modifications
  (159 revisions, 1050 modifications, mozilla-central
  4a250a0e4f29:beea9ac7d823), into a clone limited to the ancestor revision of
  that revset). Baseline real time average 1.5048, with patch 1.3108.

# pointer.py - Git-LFS pointer serialization
#
# Copyright 2017 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 re

from mercurial.i18n import _

from mercurial import (
    error,
    pycompat,
)
from mercurial.utils import (
    stringutil,
)

class InvalidPointer(error.RevlogError):
    pass

class gitlfspointer(dict):
    VERSION = 'https://git-lfs.github.com/spec/v1'

    def __init__(self, *args, **kwargs):
        self['version'] = self.VERSION
        super(gitlfspointer, self).__init__(*args)
        self.update(pycompat.byteskwargs(kwargs))

    @classmethod
    def deserialize(cls, text):
        try:
            return cls(l.split(' ', 1) for l in text.splitlines()).validate()
        except ValueError: # l.split returns 1 item instead of 2
            raise InvalidPointer(_('cannot parse git-lfs text: %s')
                                 % stringutil.pprint(text))

    def serialize(self):
        sortkeyfunc = lambda x: (x[0] != 'version', x)
        items = sorted(self.validate().iteritems(), key=sortkeyfunc)
        return ''.join('%s %s\n' % (k, v) for k, v in items)

    def oid(self):
        return self['oid'].split(':')[-1]

    def size(self):
        return int(self['size'])

    # regular expressions used by _validate
    # see https://github.com/git-lfs/git-lfs/blob/master/docs/spec.md
    _keyre = re.compile(br'\A[a-z0-9.-]+\Z')
    _valuere = re.compile(br'\A[^\n]*\Z')
    _requiredre = {
        'size': re.compile(br'\A[0-9]+\Z'),
        'oid': re.compile(br'\Asha256:[0-9a-f]{64}\Z'),
        'version': re.compile(br'\A%s\Z' % stringutil.reescape(VERSION)),
    }

    def validate(self):
        """raise InvalidPointer on error. return self if there is no error"""
        requiredcount = 0
        for k, v in self.iteritems():
            if k in self._requiredre:
                if not self._requiredre[k].match(v):
                    raise InvalidPointer(
                        _('unexpected lfs pointer value: %s=%s')
                        % (k, stringutil.pprint(v)))
                requiredcount += 1
            elif not self._keyre.match(k):
                raise InvalidPointer(_('unexpected lfs pointer key: %s') % k)
            if not self._valuere.match(v):
                raise InvalidPointer(_('unexpected lfs pointer value: %s=%s')
                                     % (k, stringutil.pprint(v)))
        if len(self._requiredre) != requiredcount:
            miss = sorted(set(self._requiredre.keys()).difference(self.keys()))
            raise InvalidPointer(_('missing lfs pointer keys: %s')
                                 % ', '.join(miss))
        return self

deserialize = gitlfspointer.deserialize