transaction: pass the transaction to 'pending' callback

The callback will likely need to perform some operation related to the
transaction (eg: backing files up). So we better pass the current transaction as
the callback argument. Otherwise callback that needs it has to rely on horrible
weak reference trick.

The first foreseen user of this is changelog._writepending. We would like it to
register the temporary file it create for cleanup purpose.

mercurial/changelog.py

@@ -1,378 +1,378
 # changelog.py - changelog class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import weakref
 from node import bin, hex, nullid
 from i18n import _
 import util, error, revlog, encoding
 
 _defaultextra = {'branch': 'default'}
 
 def _string_escape(text):
     """
     >>> d = {'nl': chr(10), 'bs': chr(92), 'cr': chr(13), 'nul': chr(0)}
     >>> s = "ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
     >>> s
     'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n'
     >>> res = _string_escape(s)
     >>> s == res.decode('string_escape')
     True
     """
     # subset of the string_escape codec
     text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
     return text.replace('\0', '\\0')
 
 def decodeextra(text):
     """
     >>> sorted(decodeextra(encodeextra({'foo': 'bar', 'baz': chr(0) + '2'})
     ...                    ).iteritems())
     [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
     >>> sorted(decodeextra(encodeextra({'foo': 'bar',
     ...                                 'baz': chr(92) + chr(0) + '2'})
     ...                    ).iteritems())
     [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
     """
     extra = _defaultextra.copy()
     for l in text.split('\0'):
         if l:
             if '\\0' in l:
                 # fix up \0 without getting into trouble with \\0
                 l = l.replace('\\\\', '\\\\\n')
                 l = l.replace('\\0', '\0')
                 l = l.replace('\n', '')
             k, v = l.decode('string_escape').split(':', 1)
             extra[k] = v
     return extra
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [_string_escape('%s:%s' % (k, d[k])) for k in sorted(d)]
     return "\0".join(items)
 
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')
 
 class appender(object):
     '''the changelog index must be updated last on disk, so we use this class
     to delay writes to it'''
     def __init__(self, vfs, name, mode, buf):
         self.data = buf
         fp = vfs(name, mode)
         self.fp = fp
         self.offset = fp.tell()
         self.size = vfs.fstat(fp).st_size
 
     def end(self):
         return self.size + len("".join(self.data))
     def tell(self):
         return self.offset
     def flush(self):
         pass
     def close(self):
         self.fp.close()
 
     def seek(self, offset, whence=0):
         '''virtual file offset spans real file and data'''
         if whence == 0:
             self.offset = offset
         elif whence == 1:
             self.offset += offset
         elif whence == 2:
             self.offset = self.end() + offset
         if self.offset < self.size:
             self.fp.seek(self.offset)
 
     def read(self, count=-1):
         '''only trick here is reads that span real file and data'''
         ret = ""
         if self.offset < self.size:
             s = self.fp.read(count)
             ret = s
             self.offset += len(s)
             if count > 0:
                 count -= len(s)
         if count != 0:
             doff = self.offset - self.size
             self.data.insert(0, "".join(self.data))
             del self.data[1:]
             s = self.data[0][doff:doff + count]
             self.offset += len(s)
             ret += s
         return ret
 
     def write(self, s):
         self.data.append(str(s))
         self.offset += len(s)
 
 def _divertopener(opener, target):
     """build an opener that writes in 'target.a' instead of 'target'"""
     def _divert(name, mode='r'):
         if name != target:
             return opener(name, mode)
         return opener(name + ".a", mode)
     return _divert
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
     def _delay(name, mode='r'):
         if name != target:
             return opener(name, mode)
         return appender(opener, name, mode, buf)
     return _delay
 
 class changelog(revlog.revlog):
     def __init__(self, opener):
         revlog.revlog.__init__(self, opener, "00changelog.i")
         if self._initempty:
             # changelogs don't benefit from generaldelta
             self.version &= ~revlog.REVLOGGENERALDELTA
             self._generaldelta = False
         self._realopener = opener
         self._delayed = False
         self._delaybuf = None
         self._divert = False
         self.filteredrevs = frozenset()
 
     def tip(self):
         """filtered version of revlog.tip"""
         for i in xrange(len(self) -1, -2, -1):
             if i not in self.filteredrevs:
                 return self.node(i)
 
     def __iter__(self):
         """filtered version of revlog.__iter__"""
         if len(self.filteredrevs) == 0:
             return revlog.revlog.__iter__(self)
 
         def filterediter():
             for i in xrange(len(self)):
                 if i not in self.filteredrevs:
                     yield i
 
         return filterediter()
 
     def revs(self, start=0, stop=None):
         """filtered version of revlog.revs"""
         for i in super(changelog, self).revs(start, stop):
             if i not in self.filteredrevs:
                 yield i
 
     @util.propertycache
     def nodemap(self):
         # XXX need filtering too
         self.rev(self.node(0))
         return self._nodecache
 
     def hasnode(self, node):
         """filtered version of revlog.hasnode"""
         try:
             i = self.rev(node)
             return i not in self.filteredrevs
         except KeyError:
             return False
 
     def headrevs(self):
         if self.filteredrevs:
             try:
                 return self.index.headrevsfiltered(self.filteredrevs)
             # AttributeError covers non-c-extension environments and
             # old c extensions without filter handling.
             except AttributeError:
                 return self._headrevs()
 
         return super(changelog, self).headrevs()
 
     def strip(self, *args, **kwargs):
         # XXX make something better than assert
         # We can't expect proper strip behavior if we are filtered.
         assert not self.filteredrevs
         super(changelog, self).strip(*args, **kwargs)
 
     def rev(self, node):
         """filtered version of revlog.rev"""
         r = super(changelog, self).rev(node)
         if r in self.filteredrevs:
             raise error.FilteredLookupError(hex(node), self.indexfile,
                                             _('filtered node'))
         return r
 
     def node(self, rev):
         """filtered version of revlog.node"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).node(rev)
 
     def linkrev(self, rev):
         """filtered version of revlog.linkrev"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).linkrev(rev)
 
     def parentrevs(self, rev):
         """filtered version of revlog.parentrevs"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).parentrevs(rev)
 
     def flags(self, rev):
         """filtered version of revlog.flags"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).flags(rev)
 
     def delayupdate(self, tr):
         "delay visibility of index updates to other readers"
 
         if not self._delayed:
             if len(self) == 0:
                 self._divert = True
                 if self._realopener.exists(self.indexfile + '.a'):
                     self._realopener.unlink(self.indexfile + '.a')
                 self.opener = _divertopener(self._realopener, self.indexfile)
             else:
                 self._delaybuf = []
                 self.opener = _delayopener(self._realopener, self.indexfile,
                                            self._delaybuf)
         self._delayed = True
         tr.addpending('cl-%i' % id(self), self._writepending)
         trp = weakref.proxy(tr)
         tr.addfinalize('cl-%i' % id(self), lambda: self._finalize(trp))
 
     def _finalize(self, tr):
         "finalize index updates"
         self._delayed = False
         self.opener = self._realopener
         # move redirected index data back into place
         if self._divert:
             assert not self._delaybuf
             tmpname = self.indexfile + ".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, 'a')
             fp.write("".join(self._delaybuf))
             fp.close()
             self._delaybuf = None
         self._divert = False
         # split when we're done
         self.checkinlinesize(tr)
 
     def readpending(self, file):
         r = revlog.revlog(self.opener, file)
         self.index = r.index
         self.nodemap = r.nodemap
         self._nodecache = r._nodecache
         self._chunkcache = r._chunkcache
 
-    def _writepending(self):
+    def _writepending(self, tr):
         "create a file containing the unfinalized state for pretxnchangegroup"
         if self._delaybuf:
             # make a temporary copy of the index
             fp1 = self._realopener(self.indexfile)
             fp2 = self._realopener(self.indexfile + ".a", "w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write("".join(self._delaybuf))
             fp2.close()
             # switch modes so finalize can simply rename
             self._delaybuf = None
             self._divert = True
             self.opener = _divertopener(self._realopener, self.indexfile)
 
         if self._divert:
             return True
 
         return False
 
     def checkinlinesize(self, tr, fp=None):
         if not self._delayed:
             revlog.revlog.checkinlinesize(self, tr, fp)
 
     def read(self, node):
         """
         format used:
         nodeid\n        : manifest node in ascii
         user\n          : user, no \n or \r allowed
         time tz extra\n : date (time is int or float, timezone is int)
                         : extra is metadata, encoded and separated by '\0'
                         : older versions ignore it
         files\n\n       : files modified by the cset, no \n or \r allowed
         (.*)            : comment (free text, ideally utf-8)
 
         changelog v0 doesn't use extra
         """
         text = self.revision(node)
         if not text:
             return (nullid, "", (0, 0), [], "", _defaultextra)
         last = text.index("\n\n")
         desc = encoding.tolocal(text[last + 2:])
         l = text[:last].split('\n')
         manifest = bin(l[0])
         user = encoding.tolocal(l[1])
 
         tdata = l[2].split(' ', 2)
         if len(tdata) != 3:
             time = float(tdata[0])
             try:
                 # various tools did silly things with the time zone field.
                 timezone = int(tdata[1])
             except ValueError:
                 timezone = 0
             extra = _defaultextra
         else:
             time, timezone = float(tdata[0]), int(tdata[1])
             extra = decodeextra(tdata[2])
 
         files = l[3:]
         return (manifest, user, (time, timezone), files, desc, extra)
 
     def add(self, manifest, files, desc, transaction, p1, p2,
                   user, date=None, extra=None):
         # Convert to UTF-8 encoded bytestrings as the very first
         # thing: calling any method on a localstr object will turn it
         # into a str object and the cached UTF-8 string is thus lost.
         user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
 
         user = user.strip()
         # An empty username or a username with a "\n" will make the
         # revision text contain two "\n\n" sequences -> corrupt
         # repository since read cannot unpack the revision.
         if not user:
             raise error.RevlogError(_("empty username"))
         if "\n" in user:
             raise error.RevlogError(_("username %s contains a newline")
                                     % repr(user))
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = "%d %d" % util.parsedate(date)
         else:
             parseddate = "%d %d" % util.makedate()
         if extra:
             branch = extra.get("branch")
             if branch in ("default", ""):
                 del extra["branch"]
             elif branch in (".", "null", "tip"):
                 raise error.RevlogError(_('the name \'%s\' is reserved')
                                         % branch)
         if extra:
             extra = encodeextra(extra)
             parseddate = "%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sorted(files) + ["", desc]
         text = "\n".join(l)
         return self.addrevision(text, transaction, len(self), p1, p2)
 
     def branchinfo(self, rev):
         """return the branch name and open/close state of a revision
 
         This function exists because creating a changectx object
         just to access this is costly."""
         extra = self.read(rev)[5]
         return encoding.tolocal(extra.get("branch")), 'close' in extra

mercurial/transaction.py

@@ -1,429 +1,431
 # transaction.py - simple journaling scheme for mercurial
 #
 # This transaction scheme is intended to gracefully handle program
 # errors and interruptions. More serious failures like system crashes
 # can be recovered with an fsck-like tool. As the whole repository is
 # effectively log-structured, this should amount to simply truncating
 # anything that isn't referenced in the changelog.
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import errno
 import error, util
 
 version = 1
 
 def active(func):
     def _active(self, *args, **kwds):
         if self.count == 0:
             raise error.Abort(_(
                 'cannot use transaction when it is already committed/aborted'))
         return func(self, *args, **kwds)
     return _active
 
 def _playback(journal, report, opener, entries, backupentries, unlink=True):
     for f, o, _ignore in entries:
         if o or not unlink:
             try:
                 fp = opener(f, 'a')
                 fp.truncate(o)
                 fp.close()
             except IOError:
                 report(_("failed to truncate %s\n") % f)
                 raise
         else:
             try:
                 opener.unlink(f)
             except (IOError, OSError), inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
     backupfiles = []
     for f, b in backupentries:
         if b:
             filepath = opener.join(f)
             backuppath = opener.join(b)
             try:
                 util.copyfile(backuppath, filepath)
                 backupfiles.append(b)
             except IOError:
                 report(_("failed to recover %s\n") % f)
                 raise
         else:
             try:
                 opener.unlink(f)
             except (IOError, OSError), inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
     opener.unlink(journal)
     backuppath = "%s.backupfiles" % journal
     if opener.exists(backuppath):
         opener.unlink(backuppath)
     for f in backupfiles:
         opener.unlink(f)
 
 class transaction(object):
     def __init__(self, report, opener, journal, after=None, createmode=None,
             onclose=None, onabort=None):
         """Begin a new transaction
 
         Begins a new transaction that allows rolling back writes in the event of
         an exception.
 
         * `after`: called after the transaction has been committed
         * `createmode`: the mode of the journal file that will be created
         * `onclose`: called as the transaction is closing, but before it is
         closed
         * `onabort`: called as the transaction is aborting, but before any files
         have been truncated
         """
         self.count = 1
         self.usages = 1
         self.report = report
         self.opener = opener
         self.after = after
         self.onclose = onclose
         self.onabort = onabort
         self.entries = []
         self.map = {}
         self.journal = journal
         self._queue = []
         # a dict of arguments to be passed to hooks
         self.hookargs = {}
         self.file = opener.open(self.journal, "w")
 
         # a list of ('path', 'backuppath') entries.
         # if 'backuppath' is empty, no file existed at backup time
         self._backupentries = []
         self._backupmap = {}
         self._backupjournal = "%s.backupfiles" % journal
         self._backupsfile = opener.open(self._backupjournal, 'w')
         self._backupsfile.write('%d\n' % version)
 
         if createmode is not None:
             opener.chmod(self.journal, createmode & 0666)
             opener.chmod(self._backupjournal, createmode & 0666)
 
         # hold file generations to be performed on commit
         self._filegenerators = {}
         # hold callbalk to write pending data for hooks
         self._pendingcallback = {}
         # True is any pending data have been written ever
         self._anypending = False
         # holds callback to call when writing the transaction
         self._finalizecallback = {}
         # hold callbalk for post transaction close
         self._postclosecallback = {}
 
     def __del__(self):
         if self.journal:
             self._abort()
 
     @active
     def startgroup(self):
         """delay registration of file entry
 
         This is used by strip to delay vision of strip offset. The transaction
         sees either none or all of the strip actions to be done."""
         self._queue.append([])
 
     @active
     def endgroup(self):
         """apply delayed registration of file entry.
 
         This is used by strip to delay vision of strip offset. The transaction
         sees either none or all of the strip actions to be done."""
         q = self._queue.pop()
         for f, o, data in q:
             self._addentry(f, o, data)
 
     @active
     def add(self, file, offset, data=None):
         """record the state of an append-only file before update"""
         if file in self.map or file in self._backupmap:
             return
         if self._queue:
             self._queue[-1].append((file, offset, data))
             return
 
         self._addentry(file, offset, data)
 
     def _addentry(self, file, offset, data):
         """add a append-only entry to memory and on-disk state"""
         if file in self.map or file in self._backupmap:
             return
         self.entries.append((file, offset, data))
         self.map[file] = len(self.entries) - 1
         # add enough data to the journal to do the truncate
         self.file.write("%s\0%d\n" % (file, offset))
         self.file.flush()
 
     @active
     def addbackup(self, file, hardlink=True, vfs=None):
         """Adds a backup of the file to the transaction
 
         Calling addbackup() creates a hardlink backup of the specified file
         that is used to recover the file in the event of the transaction
         aborting.
 
         * `file`: the file path, relative to .hg/store
         * `hardlink`: use a hardlink to quickly create the backup
         """
         if self._queue:
             msg = 'cannot use transaction.addbackup inside "group"'
             raise RuntimeError(msg)
 
         if file in self.map or file in self._backupmap:
             return
         backupfile = "%s.backup.%s" % (self.journal, file)
         if vfs is None:
             vfs = self.opener
         if vfs.exists(file):
             filepath = vfs.join(file)
             backuppath = self.opener.join(backupfile)
             util.copyfiles(filepath, backuppath, hardlink=hardlink)
         else:
             backupfile = ''
 
         self._backupentries.append((file, backupfile))
         self._backupmap[file] = len(self._backupentries) - 1
         self._backupsfile.write("%s\0%s\n" % (file, backupfile))
         self._backupsfile.flush()
 
     @active
     def addfilegenerator(self, genid, filenames, genfunc, order=0, vfs=None):
         """add a function to generates some files at transaction commit
 
         The `genfunc` argument is a function capable of generating proper
         content of each entry in the `filename` tuple.
 
         At transaction close time, `genfunc` will be called with one file
         object argument per entries in `filenames`.
 
         The transaction itself is responsible for the backup, creation and
         final write of such file.
 
         The `genid` argument is used to ensure the same set of file is only
         generated once. Call to `addfilegenerator` for a `genid` already
         present will overwrite the old entry.
 
         The `order` argument may be used to control the order in which multiple
         generator will be executed.
         """
         # For now, we are unable to do proper backup and restore of custom vfs
         # but for bookmarks that are handled outside this mechanism.
         assert vfs is None or filenames == ('bookmarks',)
         self._filegenerators[genid] = (order, filenames, genfunc, vfs)
 
     def _generatefiles(self):
         # write files registered for generation
         for entry in sorted(self._filegenerators.values()):
             order, filenames, genfunc, vfs = entry
             if vfs is None:
                 vfs = self.opener
             files = []
             try:
                 for name in filenames:
                     # Some files are already backed up when creating the
                     # localrepo. Until this is properly fixed we disable the
                     # backup for them.
                     if name not in ('phaseroots', 'bookmarks'):
                         self.addbackup(name)
                     files.append(vfs(name, 'w', atomictemp=True))
                 genfunc(*files)
             finally:
                 for f in files:
                     f.close()
 
     @active
     def find(self, file):
         if file in self.map:
             return self.entries[self.map[file]]
         if file in self._backupmap:
             return self._backupentries[self._backupmap[file]]
         return None
 
     @active
     def replace(self, file, offset, data=None):
         '''
         replace can only replace already committed entries
         that are not pending in the queue
         '''
 
         if file not in self.map:
             raise KeyError(file)
         index = self.map[file]
         self.entries[index] = (file, offset, data)
         self.file.write("%s\0%d\n" % (file, offset))
         self.file.flush()
 
     @active
     def nest(self):
         self.count += 1
         self.usages += 1
         return self
 
     def release(self):
         if self.count > 0:
             self.usages -= 1
         # if the transaction scopes are left without being closed, fail
         if self.count > 0 and self.usages == 0:
             self._abort()
 
     def running(self):
         return self.count > 0
 
     def addpending(self, category, callback):
         """add a callback to be called when the transaction is pending
 
+        The transaction will be given as callback's first argument.
+
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._pendingcallback[category] = callback
 
     @active
     def writepending(self):
         '''write pending file to temporary version
 
         This is used to allow hooks to view a transaction before commit'''
         categories = sorted(self._pendingcallback)
         for cat in categories:
             # remove callback since the data will have been flushed
-            any = self._pendingcallback.pop(cat)()
+            any = self._pendingcallback.pop(cat)(self)
             self._anypending = self._anypending or any
         return self._anypending
 
     @active
     def addfinalize(self, category, callback):
         """add a callback to be called when the transaction is closed
 
         Category is a unique identifier to allow overwriting old callbacks with
         newer callbacks.
         """
         self._finalizecallback[category] = callback
 
     @active
     def addpostclose(self, category, callback):
         """add a callback to be called after the transaction is closed
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._postclosecallback[category] = callback
 
     @active
     def close(self):
         '''commit the transaction'''
         if self.count == 1 and self.onclose is not None:
             self._generatefiles()
             categories = sorted(self._finalizecallback)
             for cat in categories:
                 self._finalizecallback[cat]()
             self.onclose()
 
         self.count -= 1
         if self.count != 0:
             return
         self.file.close()
         self._backupsfile.close()
         self.entries = []
         if self.after:
             self.after()
         if self.opener.isfile(self.journal):
             self.opener.unlink(self.journal)
         if self.opener.isfile(self._backupjournal):
             self.opener.unlink(self._backupjournal)
             for _f, b in self._backupentries:
                 if b:
                     self.opener.unlink(b)
         self._backupentries = []
         self.journal = None
         # run post close action
         categories = sorted(self._postclosecallback)
         for cat in categories:
             self._postclosecallback[cat]()
 
     @active
     def abort(self):
         '''abort the transaction (generally called on error, or when the
         transaction is not explicitly committed before going out of
         scope)'''
         self._abort()
 
     def _abort(self):
         self.count = 0
         self.usages = 0
         self.file.close()
         self._backupsfile.close()
 
         if self.onabort is not None:
             self.onabort()
 
         try:
             if not self.entries and not self._backupentries:
                 if self.journal:
                     self.opener.unlink(self.journal)
                 if self._backupjournal:
                     self.opener.unlink(self._backupjournal)
                 return
 
             self.report(_("transaction abort!\n"))
 
             try:
                 _playback(self.journal, self.report, self.opener,
                           self.entries, self._backupentries, False)
                 self.report(_("rollback completed\n"))
             except Exception:
                 self.report(_("rollback failed - please run hg recover\n"))
         finally:
             self.journal = None
 
 
 def rollback(opener, file, report):
     """Rolls back the transaction contained in the given file
 
     Reads the entries in the specified file, and the corresponding
     '*.backupfiles' file, to recover from an incomplete transaction.
 
     * `file`: a file containing a list of entries, specifying where
     to truncate each file.  The file should contain a list of
     file\0offset pairs, delimited by newlines. The corresponding
     '*.backupfiles' file should contain a list of file\0backupfile
     pairs, delimited by \0.
     """
     entries = []
     backupentries = []
 
     fp = opener.open(file)
     lines = fp.readlines()
     fp.close()
     for l in lines:
         try:
             f, o = l.split('\0')
             entries.append((f, int(o), None))
         except ValueError:
             report(_("couldn't read journal entry %r!\n") % l)
 
     backupjournal = "%s.backupfiles" % file
     if opener.exists(backupjournal):
         fp = opener.open(backupjournal)
         lines = fp.readlines()
         if lines:
             ver = lines[0][:-1]
             if ver == str(version):
                 for line in lines[1:]:
                     if line:
                         # Shave off the trailing newline
                         line = line[:-1]
                         f, b = line.split('\0')
                         backupentries.append((f, b))
             else:
                 report(_("journal was created by a newer version of "
                          "Mercurial"))
 
     _playback(file, report, opener, entries, backupentries)