Mercurial > hg
view hgext/relink.py @ 51871:cfd30df0f8e4
bundlerepo: fix mismatches with repository and revlog classes
Both pytype and PyCharm complained that `write()` and `_write()` in the
bundlephasecache class aren't proper overrides- indeed they seem to be missing
an argument that the base class has.
PyCharm and pytype also complained that the `revlog.revlog` class doesn't have a
`_chunk()` method. That looks like it was moved from revlog to `_InnerRevlog`
back in e8ad6d8de8b8, and wasn't caught because this module wasn't type checked.
However, I couldn't figure out a syntax with `revlog.revlog._inner._chunk(self, rev)`,
as it complained about passing too many args. `bundlerevlog._rawtext()` uses
this `super(...)` style to call the super class, so hopefully that works, even
with the wonky dynamic subclassing. The revlog class needed the `_InnerRevlog`
field typed because it isn't set in the constructor.
Finally, the vfs type hints look broken. This initially failed with:
File "/mnt/c/Users/Matt/hg/mercurial/bundlerepo.py", line 65, in __init__: Function readonlyvfs.__init__ was called with the wrong arguments [wrong-arg-types]
Expected: (self, vfs: mercurial.vfs.vfs)
Actually passed: (self, vfs: Callable)
Called from (traceback):
line 232, in dirlog
line 214, in __init__
I don't see a raw Callable, but I tried changing some of the vfs args to be typed
as `vfsmod.abstractvfs`, but that class doesn't have `options`, so it failed
elsewhere. `readonlyvfs` isn't a subclass of `vfs` (it's a subclass of
`abstractvfs`), so I'm not sure how to handle that. It would be a shame to have
to make a union of vfs subclasses (but not all of them have `options` either).
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Sat, 03 Aug 2024 01:33:13 -0400 |
parents | f4733654f144 |
children |
line wrap: on
line source
# Mercurial extension to provide 'hg relink' command # # Copyright (C) 2007 Brendan Cully <brendan@kublai.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. """recreates hardlinks between repository clones""" from __future__ import annotations import os import stat from mercurial.i18n import _ from mercurial.pycompat import open from mercurial import ( error, hg, registrar, util, ) from mercurial.utils import ( stringutil, urlutil, ) cmdtable = {} command = registrar.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 = b'ships-with-hg-core' @command( b'relink', [], _(b'[ORIGIN]'), helpcategory=command.CATEGORY_MAINTENANCE ) def relink(ui, repo, origin=None, **opts): """recreate hardlinks between two repositories When repositories are cloned locally, their data files will be hardlinked so that they only use the space of a single repository. Unfortunately, subsequent pulls into either repository will break hardlinks for any files touched by the new changesets, even if both repositories end up pulling the same changes. Similarly, passing --rev to "hg clone" will fail to use any hardlinks, falling back to a complete copy of the source repository. This command lets you recreate those hardlinks and reclaim that wasted space. This repository will be relinked to share space with ORIGIN, which must be on the same local disk. If ORIGIN is omitted, looks for "default-relink", then "default", in [paths]. Do not attempt any read operations on this repository while the command is running. (Both repositories will be locked against writes.) """ if not hasattr(util, 'samefile') or not hasattr(util, 'samedevice'): raise error.Abort(_(b'hardlinks are not supported on this system')) if origin is None and b'default-relink' in ui.paths: origin = b'default-relink' path = urlutil.get_unique_pull_path_obj(b'relink', ui, origin) src = hg.repository(repo.baseui, path.loc) ui.status(_(b'relinking %s to %s\n') % (src.store.path, repo.store.path)) if repo.root == src.root: ui.status(_(b'there is nothing to relink\n')) return if not util.samedevice(src.store.path, repo.store.path): # No point in continuing raise error.Abort(_(b'source and destination are on different devices')) with repo.lock(), src.lock(): candidates = sorted(collect(src, ui)) targets = prune(candidates, src.store.path, repo.store.path, ui) do_relink(src.store.path, repo.store.path, targets, ui) def collect(src, ui): seplen = len(os.path.sep) candidates = [] live = len(src[b'tip'].manifest()) # Your average repository has some files which were deleted before # the tip revision. We account for that by assuming that there are # 3 tracked files for every 2 live files as of the tip version of # the repository. # # mozilla-central as of 2010-06-10 had a ratio of just over 7:5. total = live * 3 // 2 src = src.store.path progress = ui.makeprogress(_(b'collecting'), unit=_(b'files'), total=total) pos = 0 ui.status( _(b"tip has %d files, estimated total number of files: %d\n") % (live, total) ) for dirpath, dirnames, filenames in os.walk(src): dirnames.sort() relpath = dirpath[len(src) + seplen :] for filename in sorted(filenames): if filename[-2:] not in (b'.d', b'.i'): continue st = os.stat(os.path.join(dirpath, filename)) if not stat.S_ISREG(st.st_mode): continue pos += 1 candidates.append((os.path.join(relpath, filename), st)) progress.update(pos, item=filename) progress.complete() ui.status(_(b'collected %d candidate storage files\n') % len(candidates)) return candidates def prune(candidates, src, dst, ui): def linkfilter(src, dst, st): try: ts = os.stat(dst) except OSError: # Destination doesn't have this file? return False if util.samefile(src, dst): return False if not util.samedevice(src, dst): # No point in continuing raise error.Abort( _(b'source and destination are on different devices') ) if st.st_size != ts.st_size: return False return st targets = [] progress = ui.makeprogress( _(b'pruning'), unit=_(b'files'), total=len(candidates) ) pos = 0 for fn, st in candidates: pos += 1 srcpath = os.path.join(src, fn) tgt = os.path.join(dst, fn) ts = linkfilter(srcpath, tgt, st) if not ts: ui.debug(b'not linkable: %s\n' % fn) continue targets.append((fn, ts.st_size)) progress.update(pos, item=fn) progress.complete() ui.status( _(b'pruned down to %d probably relinkable files\n') % len(targets) ) return targets def do_relink(src, dst, files, ui): def relinkfile(src, dst): bak = dst + b'.bak' os.rename(dst, bak) try: util.oslink(src, dst) except OSError: os.rename(bak, dst) raise os.remove(bak) CHUNKLEN = 65536 relinked = 0 savedbytes = 0 progress = ui.makeprogress( _(b'relinking'), unit=_(b'files'), total=len(files) ) pos = 0 for f, sz in files: pos += 1 source = os.path.join(src, f) tgt = os.path.join(dst, f) # Binary mode, so that read() works correctly, especially on Windows sfp = open(source, b'rb') dfp = open(tgt, b'rb') sin = sfp.read(CHUNKLEN) while sin: din = dfp.read(CHUNKLEN) if sin != din: break sin = sfp.read(CHUNKLEN) sfp.close() dfp.close() if sin: ui.debug(b'not linkable: %s\n' % f) continue try: relinkfile(source, tgt) progress.update(pos, item=f) relinked += 1 savedbytes += sz except OSError as inst: ui.warn(b'%s: %s\n' % (tgt, stringutil.forcebytestr(inst))) progress.complete() ui.status( _(b'relinked %d files (%s reclaimed)\n') % (relinked, util.bytecount(savedbytes)) )