sapling/eden/scm/edenscm/hgext/journal.py
Durham Goode a6353c55f5 py3: fix sparse
Reviewed By: quark-zju

Differential Revision: D19800699

fbshipit-source-id: 7cf86d0ab9a0efc96966ac3747f56b229251fb0d
2020-02-17 14:52:38 -08:00

592 lines
20 KiB
Python

# Copyright (c) Facebook, Inc. and its affiliates.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2.
"""track previous positions of bookmarks (EXPERIMENTAL)
This extension adds a new command: `hg journal`, which shows you where
bookmarks were previously located.
"""
from __future__ import absolute_import
import collections
import errno
import os
import weakref
from typing import NamedTuple, Tuple
from edenscm.mercurial import (
bookmarks,
cmdutil,
dispatch,
error,
extensions,
hg,
localrepo,
lock,
node,
pycompat,
registrar,
util,
)
from edenscm.mercurial.i18n import _
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 = "ships-with-hg-core"
# storage format version; increment when the format changes
storageversion = 0
# namespaces
bookmarktype = "bookmark"
wdirparenttype = "wdirparent"
# In a shared repository, what shared feature name is used
# to indicate this namespace is shared with the source?
sharednamespaces = {bookmarktype: hg.sharedbookmarks}
# Journal recording, register hooks and storage object
def extsetup(ui):
extensions.wrapfunction(dispatch, "runcommand", runcommand)
extensions.wrapfunction(bookmarks.bmstore, "_write", recordbookmarks)
extensions.wrapfilecache(localrepo.localrepository, "dirstate", wrapdirstate)
extensions.wrapfunction(hg, "postshare", wrappostshare)
extensions.wrapfunction(hg, "copystore", unsharejournal)
def reposetup(ui, repo):
if repo.local():
repo.journal = journalstorage(repo)
repo._wlockfreeprefix.add("namejournal")
dirstate, cached = localrepo.isfilecached(repo, "dirstate")
if cached:
# already instantiated dirstate isn't yet marked as
# "journal"-ing, even though repo.dirstate() was already
# wrapped by own wrapdirstate()
_setupdirstate(repo, dirstate)
def runcommand(orig, lui, repo, cmd, fullargs, *args):
"""Track the command line options for recording in the journal"""
journalstorage.recordcommand(*fullargs)
return orig(lui, repo, cmd, fullargs, *args)
def _setupdirstate(repo, dirstate):
dirstate.journalstorage = repo.journal
dirstate.addparentchangecallback("journal", recorddirstateparents)
# hooks to record dirstate changes
def wrapdirstate(orig, repo):
"""Make journal storage available to the dirstate object"""
dirstate = orig(repo)
if util.safehasattr(repo, "journal"):
_setupdirstate(repo, dirstate)
return dirstate
def recorddirstateparents(dirstate, old, new):
"""Records all dirstate parent changes in the journal."""
old = list(old)
new = list(new)
if util.safehasattr(dirstate, "journalstorage"):
# only record two hashes if there was a merge
oldhashes = old[:1] if old[1] == node.nullid else old
newhashes = new[:1] if new[1] == node.nullid else new
dirstate.journalstorage.record(wdirparenttype, ".", oldhashes, newhashes)
# hooks to record bookmark changes (both local and remote)
def recordbookmarks(orig, store, fp):
"""Records all bookmark changes in the journal."""
repo = store._repo
if util.safehasattr(repo, "journal"):
oldmarks = bookmarks.bmstore(repo)
for mark, value in pycompat.iteritems(store):
oldvalue = oldmarks.get(mark, node.nullid)
if value != oldvalue:
repo.journal.record(bookmarktype, mark, oldvalue, value)
return orig(store, fp)
def _mergeentriesiter(*iterables, **kwargs):
"""Given a set of sorted iterables, yield the next entry in merged order
Note that by default entries go from most recent to oldest.
"""
order = kwargs.pop(r"order", max)
iterables = [iter(it) for it in iterables]
# this tracks still active iterables; iterables are deleted as they are
# exhausted, which is why this is a dictionary and why each entry also
# stores the key. Entries are mutable so we can store the next value each
# time.
iterable_map = {}
for key, it in enumerate(iterables):
try:
iterable_map[key] = [next(it), key, it]
except StopIteration:
# empty entry, can be ignored
pass
while iterable_map:
value, key, it = order(pycompat.itervalues(iterable_map))
yield value
try:
iterable_map[key][0] = next(it)
except StopIteration:
# this iterable is empty, remove it from consideration
del iterable_map[key]
def wrappostshare(orig, sourcerepo, destrepo, **kwargs):
"""Mark this shared working copy as sharing journal information"""
with destrepo.wlock():
orig(sourcerepo, destrepo, **kwargs)
with destrepo.localvfs("shared", "ab") as fp:
fp.write(b"journal\n")
def unsharejournal(orig, ui, repo, repopath):
"""Copy shared journal entries into this repo when unsharing"""
if repo.path == repopath and repo.shared() and util.safehasattr(repo, "journal"):
if repo.shared() and "journal" in repo.sharedfeatures:
# there is a shared repository and there are shared journal entries
# to copy. move shared data over from source to destination but
# rename the local file first
if repo.localvfs.exists("namejournal"):
journalpath = repo.localvfs.join("namejournal")
util.rename(journalpath, journalpath + ".bak")
storage = repo.journal
local = storage._open(
repo.localvfs, filename="namejournal.bak", _newestfirst=False
)
shared = (
e
for e in storage._open(repo.sharedvfs, _newestfirst=False)
if sharednamespaces.get(e.namespace) in repo.sharedfeatures
)
for entry in _mergeentriesiter(local, shared, order=min):
storage._write(repo.localvfs, [entry])
return orig(ui, repo, repopath)
# TODO: Once we fully convert to Python 3 we can change this to the much nicer Python 3
# style attribute annotations for these NamedTuple members. For now we are stuck with
# this uglier legacy syntax.
class journalentry(
NamedTuple(
"journalentry",
[
("timestamp", Tuple[float, int]),
("user", str),
("command", str),
("namespace", str),
("name", str),
("oldhashes", Tuple[bytes, ...]),
("newhashes", Tuple[bytes, ...]),
],
)
):
"""Individual journal entry
* timestamp: a mercurial (time, timezone) tuple
* user: the username that ran the command
* command: the hg command that triggered this record
* namespace: the entry namespace, an opaque string
* name: the name of the changed item, opaque string with meaning in the
namespace
* oldhashes: a tuple of one or more binary hashes for the old location
* newhashes: a tuple of one or more binary hashes for the new location
Handles serialisation from and to the storage format. Fields are
separated by newlines, hashes are written out in hex separated by commas,
timestamp and timezone are separated by a space.
"""
@classmethod
def fromstorage(cls, line):
# type: (bytes) -> journalentry
(
time,
user,
command,
namespace,
name,
oldhashes,
newhashes,
) = pycompat.decodeutf8(line).split("\n")
timestamp, tz = time.split()
timestamp, tz = float(timestamp), int(tz)
oldhashes = tuple(node.bin(hash) for hash in oldhashes.split(","))
newhashes = tuple(node.bin(hash) for hash in newhashes.split(","))
return cls(
(timestamp, tz), user, command, namespace, name, oldhashes, newhashes
)
def serialize(self):
# type: () -> bytes
"""String representation for storage"""
time = " ".join(map(str, self.timestamp))
oldhashes = ",".join([node.hex(hash) for hash in self.oldhashes])
newhashes = ",".join([node.hex(hash) for hash in self.newhashes])
return pycompat.encodeutf8(
"\n".join(
(
time,
self.user,
self.command,
self.namespace,
self.name,
oldhashes,
newhashes,
)
)
)
class journalstorage(object):
"""Storage for journal entries
Entries are divided over two files; one with entries that pertain to the
local working copy *only*, and one with entries that are shared across
multiple working copies when shared using the share extension.
Entries are stored with NUL bytes as separators. See the journalentry
class for the per-entry structure.
The file format starts with an integer version, delimited by a NUL.
This storage uses a dedicated lock; this makes it easier to avoid issues
with adding entries that added when the regular wlock is unlocked (e.g.
the dirstate).
"""
_currentcommand = ()
_lockref = None
def __init__(self, repo):
self.user = util.getuser()
self.ui = repo.ui
self.localvfs = repo.localvfs
self.sharedfeatures = repo.sharedfeatures
if repo.shared() and "journal" in self.sharedfeatures:
self.sharedvfs = repo.sharedvfs
else:
self.sharedvfs = None
# track the current command for recording in journal entries
@property
def command(self):
commandstr = " ".join(map(util.shellquote, journalstorage._currentcommand))
if "\n" in commandstr:
# truncate multi-line commands
commandstr = commandstr.partition("\n")[0] + " ..."
return commandstr
@classmethod
def recordcommand(cls, *fullargs):
"""Set the current hg arguments, stored with recorded entries"""
# Set the current command on the class because we may have started
# with a non-local repo (cloning for example).
cls._currentcommand = fullargs
def _currentlock(self, lockref):
"""Returns the lock if it's held, or None if it's not.
(This is copied from the localrepo class)
"""
if lockref is None:
return None
l = lockref()
if l is None or not l.held:
return None
return l
def jlock(self, vfs):
"""Create a lock for the journal file"""
if self._currentlock(self._lockref) is not None:
raise error.Abort(_("journal lock does not support nesting"))
desc = _("journal of %s") % vfs.base
try:
l = lock.lock(vfs, "namejournal.lock", 0, desc=desc)
except error.LockHeld as inst:
self.ui.warn(
_("waiting for lock on %s held by %r\n") % (desc, inst.lockinfo)
)
# default to 600 seconds timeout
l = lock.lock(
vfs, "namejournal.lock", self.ui.configint("ui", "timeout"), desc=desc
)
self.ui.warn(_("got lock after %s seconds\n") % l.delay)
self._lockref = weakref.ref(l)
return l
def record(self, namespace, name, oldhashes, newhashes):
"""Record a new journal entry
* namespace: an opaque string; this can be used to filter on the type
of recorded entries.
* name: the name defining this entry; for bookmarks, this is the
bookmark name. Can be filtered on when retrieving entries.
* oldhashes and newhashes: each a single binary hash, or a list of
binary hashes. These represent the old and new position of the named
item.
"""
entry = self._buildjournalentry(namespace, name, oldhashes, newhashes)
vfs = self._getvfs(namespace)
self._write(vfs, [entry])
def recordmany(self, namespace, entrydata):
"""Batch version of `record()`
Records a lot of entries at once. namespace is the same as in `record()`
`entrydata` is an iterable of `(name, oldhashes, newhashes)`
"""
vfs = self._getvfs(namespace)
entries = []
for name, oldhashes, newhashes in entrydata:
entry = self._buildjournalentry(namespace, name, oldhashes, newhashes)
entries.append(entry)
self._write(vfs, entries)
def _getvfs(self, namespace):
# write to the shared repository if this feature is being
# shared between working copies.
if (
self.sharedvfs is not None
and sharednamespaces.get(namespace) in self.sharedfeatures
):
return self.sharedvfs
else:
return self.localvfs
def _buildjournalentry(self, namespace, name, oldhashes, newhashes):
if not isinstance(oldhashes, list):
oldhashes = [oldhashes]
if not isinstance(newhashes, list):
newhashes = [newhashes]
return journalentry(
util.makedate(),
self.user,
self.command,
namespace,
name,
oldhashes,
newhashes,
)
def _write(self, vfs, entries):
with self.jlock(vfs):
version = None
# open file in amend mode to ensure it is created if missing
with vfs("namejournal", mode="a+b") as f:
f.seek(0, os.SEEK_SET)
# Read just enough bytes to get a version number (up to 2
# digits plus separator)
version = pycompat.decodeutf8(f.read(3).partition(b"\0")[0])
if version and version != str(storageversion):
# different version of the storage. Exit early (and not
# write anything) if this is not a version we can handle or
# the file is corrupt. In future, perhaps rotate the file
# instead?
self.ui.warn(_("unsupported journal file version '%s'\n") % version)
return
if not version:
# empty file, write version first
f.write(pycompat.encodeutf8(str(storageversion) + "\0"))
f.seek(0, os.SEEK_END)
for entry in entries:
f.write(entry.serialize() + b"\0")
def filtered(self, namespace=None, name=None):
"""Yield all journal entries with the given namespace or name
Both the namespace and the name are optional; if neither is given all
entries in the journal are produced.
Matching supports regular expressions by using the `re:` prefix
(use `literal:` to match names or namespaces that start with `re:`)
"""
if namespace is not None:
namespace = util.stringmatcher(namespace)[-1]
if name is not None:
name = util.stringmatcher(name)[-1]
for entry in self:
if namespace is not None and not namespace(entry.namespace):
continue
if name is not None and not name(entry.name):
continue
yield entry
def __iter__(self):
"""Iterate over the storage
Yields journalentry instances for each contained journal record.
"""
local = self._open(self.localvfs)
if self.sharedvfs is None:
return local
# iterate over both local and shared entries, but only those
# shared entries that are among the currently shared features
shared = (
e
for e in self._open(self.sharedvfs)
if sharednamespaces.get(e.namespace) in self.sharedfeatures
)
return _mergeentriesiter(local, shared)
def _open(self, vfs, filename="namejournal", _newestfirst=True):
if not vfs.exists(filename):
return
with vfs(filename) as f:
raw = f.read()
lines = raw.split(b"\0")
version = lines and pycompat.decodeutf8(lines[0])
if version != str(storageversion):
version = version or _("not available")
raise error.Abort(_("unknown journal file version '%s'") % version)
# Skip the first line, it's a version number. Normally we iterate over
# these in reverse order to list newest first; only when copying across
# a shared storage do we forgo reversing.
lines = lines[1:]
if _newestfirst:
lines = reversed(lines)
for line in lines:
if not line:
continue
yield journalentry.fromstorage(line)
# journal reading
# log options that don't make sense for journal
_ignoreopts = ("no-merges", "graph")
@command(
"journal|j|jo|jou|jour|journ|journa",
[
("", "all", None, "show history for all names"),
("c", "commits", None, "show commit metadata"),
]
+ [opt for opt in cmdutil.logopts if opt[1] not in _ignoreopts],
"[OPTION]... [BOOKMARKNAME]",
)
def journal(ui, repo, *args, **opts):
"""show history of the checked out commit or a bookmark
Show the history of all the commits that were once the current commit. In
other words, shows a list of your previously checked out commits.
:hg:`journal` can be used to find older versions of commits (for example,
when you want to revert to a previous state). It can also be used to
discover commits that were previously hidden.
By default, :hg:`journal` displays the history of the current commit. To
display a list of commits pointed to by a bookmark, specify a bookmark
name.
Specify --all to show the history of both the current commit and all
bookmarks. In the output for --all, bookmarks are listed by name, and '.'
indicates the current commit.
Specify -Tjson to produce machine-readable output.
.. container:: verbose
By default, :hg:`journal` only shows the commit hash and the
corresponding command. Specify --verbose to also include the previous
commit hash, user, and timestamp.
Use -c/--commits to output log information about each commit hash. To
customize the log output, you can also specify switches like '--patch',
'--git', '--stat', and '--template'.
If a bookmark name starts with 're:', the remainder of the name is
treated as a regular expression. To match a name that actually starts
with 're:', use the prefix 'literal:'.
"""
name = "."
if opts.get("all"):
if args:
raise error.Abort(_("You can't combine --all and filtering on a name"))
name = None
if args:
name = args[0]
fm = ui.formatter("journal", opts)
ui.pager("journal")
if not opts.get("template"):
if name is None:
displayname = _("the working copy and bookmarks")
else:
displayname = "'%s'" % name
ui.status(_("previous locations of %s:\n") % displayname)
limit = cmdutil.loglimit(opts)
entry = None
for count, entry in enumerate(repo.journal.filtered(name=name)):
if count == limit:
break
newhashesstr = fm.formatlist(
list(map(fm.hexfunc, entry.newhashes)), name="node", sep=","
)
oldhashesstr = fm.formatlist(
list(map(fm.hexfunc, entry.oldhashes)), name="node", sep=","
)
fm.startitem()
fm.condwrite(ui.verbose, "oldhashes", "%s -> ", oldhashesstr)
fm.write("newhashes", "%s", newhashesstr)
fm.condwrite(ui.verbose, "user", " %-8s", entry.user)
fm.condwrite(
opts.get("all") or name.startswith("re:"), "name", " %-8s", entry.name
)
timestring = fm.formatdate(entry.timestamp, "%Y-%m-%d %H:%M %1%2")
fm.condwrite(ui.verbose, "date", " %s", timestring)
fm.write("command", " %s\n", entry.command)
if opts.get("commits"):
displayer = cmdutil.show_changeset(ui, repo, opts, buffered=False)
for hash in entry.newhashes:
try:
ctx = repo[hash]
displayer.show(ctx)
except error.RepoLookupError as e:
fm.write("repolookuperror", "%s\n\n", str(e))
displayer.close()
fm.end()
if entry is None and not opts.get("template"):
ui.status(_("no recorded locations\n"))