fileset: add a lightweight file filtering language
This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1]. We want a way to specify what
files will be converted to LFS at commit time. And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs. I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.
Yuya suggested farming out to fileset.parse(), which added support for more
symbols. The only fileset element not supported here is 'negate'. (List isn't
supported by filesets either.) I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config. The extension operator was changed from '.'
to '**', to match how recursive path globs are specified. Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher. Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2]. We should
probably revisit that, because it's seriously ugly. But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.
I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.
Sample filter settings:
all() # everything
size(">20MB") # larger than 20MB
!**.txt # except for .txt files
**.zip | **.tar.gz | **.7z # some types of compressed files
"path:bin" # files under "bin" in the project root
[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html
# logexchange.py
#
# Copyright 2017 Augie Fackler <raf@durin42.com>
# Copyright 2017 Sean Farley <sean@farley.io>
#
# 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
from .node import hex
from . import (
vfs as vfsmod,
)
# directory name in .hg/ in which remotenames files will be present
remotenamedir = 'logexchange'
def readremotenamefile(repo, filename):
"""
reads a file from .hg/logexchange/ directory and yields it's content
filename: the file to be read
yield a tuple (node, remotepath, name)
"""
vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
if not vfs.exists(filename):
return
f = vfs(filename)
lineno = 0
for line in f:
line = line.strip()
if not line:
continue
# contains the version number
if lineno == 0:
lineno += 1
try:
node, remote, rname = line.split('\0')
yield node, remote, rname
except ValueError:
pass
f.close()
def readremotenames(repo):
"""
read the details about the remotenames stored in .hg/logexchange/ and
yields a tuple (node, remotepath, name). It does not yields information
about whether an entry yielded is branch or bookmark. To get that
information, call the respective functions.
"""
for bmentry in readremotenamefile(repo, 'bookmarks'):
yield bmentry
for branchentry in readremotenamefile(repo, 'branches'):
yield branchentry
def writeremotenamefile(repo, remotepath, names, nametype):
vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
f = vfs(nametype, 'w', atomictemp=True)
# write the storage version info on top of file
# version '0' represents the very initial version of the storage format
f.write('0\n\n')
olddata = set(readremotenamefile(repo, nametype))
# re-save the data from a different remote than this one.
for node, oldpath, rname in sorted(olddata):
if oldpath != remotepath:
f.write('%s\0%s\0%s\n' % (node, oldpath, rname))
for name, node in sorted(names.iteritems()):
if nametype == "branches":
for n in node:
f.write('%s\0%s\0%s\n' % (n, remotepath, name))
elif nametype == "bookmarks":
if node:
f.write('%s\0%s\0%s\n' % (node, remotepath, name))
f.close()
def saveremotenames(repo, remotepath, branches=None, bookmarks=None):
"""
save remotenames i.e. remotebookmarks and remotebranches in their
respective files under ".hg/logexchange/" directory.
"""
wlock = repo.wlock()
try:
if bookmarks:
writeremotenamefile(repo, remotepath, bookmarks, 'bookmarks')
if branches:
writeremotenamefile(repo, remotepath, branches, 'branches')
finally:
wlock.release()
def pullremotenames(localrepo, remoterepo):
"""
pulls bookmarks and branches information of the remote repo during a
pull or clone operation.
localrepo is our local repository
remoterepo is the peer instance
"""
remotepath = remoterepo.url()
bookmarks = remoterepo.listkeys('bookmarks')
# on a push, we don't want to keep obsolete heads since
# they won't show up as heads on the next pull, so we
# remove them here otherwise we would require the user
# to issue a pull to refresh the storage
bmap = {}
repo = localrepo.unfiltered()
for branch, nodes in remoterepo.branchmap().iteritems():
bmap[branch] = []
for node in nodes:
if node in repo and not repo[node].obsolete():
bmap[branch].append(hex(node))
saveremotenames(localrepo, remotepath, bmap, bookmarks)