transactions: fix hg recover with fncache backups

The transaction backupfiles logic was broken for 'hg recover'.  The file format
is XXX\0XXX\0YYY\0YYY\0 but the parser did a couple things wrong. 1) It went one
step beyond the final \0 and tried to read past the end of the array. 2)
array[i:i+1] returns a single item, instead of two items as intended.

Added a test to catch it, which turns out to be the first actual 'hg recover'
test.

mercurial/transaction.py

@@ -1,356 +1,357 b''
 # 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
 
 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, _ignore in backupentries:
         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
 
     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.backupentries = []
         self.map = {}
         self.backupmap = {}
         self.journal = journal
         self._queue = []
         # a dict of arguments to be passed to hooks
         self.hookargs = {}
 
         self.backupjournal = "%s.backupfiles" % journal
         self.file = opener.open(self.journal, "w")
         self.backupsfile = opener.open(self.backupjournal, 'w')
         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 = {}
 
     def __del__(self):
         if self.journal:
             self._abort()
 
     @active
     def startgroup(self):
         self._queue.append(([], []))
 
     @active
     def endgroup(self):
         q = self._queue.pop()
         self.entries.extend(q[0])
         self.backupentries.extend(q[1])
 
         offsets = []
         backups = []
         for f, o, _data in q[0]:
             offsets.append((f, o))
 
         for f, b, _data in q[1]:
             backups.append((f, b))
 
         d = ''.join(['%s\0%d\n' % (f, o) for f, o in offsets])
         self.file.write(d)
         self.file.flush()
 
         d = ''.join(['%s\0%s\0' % (f, b) for f, b in backups])
         self.backupsfile.write(d)
         self.backupsfile.flush()
 
     @active
     def add(self, file, offset, data=None):
         if file in self.map or file in self.backupmap:
             return
         if self._queue:
             self._queue[-1][0].append((file, offset, data))
             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 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:
             self.add(file, 0)
             return
 
         if self._queue:
             self._queue[-1][1].append((file, backupfile))
             return
 
         self.backupentries.append((file, backupfile, None))
         self.backupmap[file] = len(self.backupentries) - 1
         self.backupsfile.write("%s\0%s\0" % (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)
 
     @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
 
     @active
     def close(self):
         '''commit the transaction'''
         # 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()
 
         if self.count == 1 and self.onclose is not None:
             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, _ignore in self.backupentries:
                 self.opener.unlink(b)
         self.backupentries = []
         self.journal = None
 
     @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)
         data = fp.read()
         if len(data) > 0:
             parts = data.split('\0')
-            for i in xrange(0, len(parts), 2):
-                f, b = parts[i:i + 1]
+            # Skip the final part, since it's just a trailing empty space
+            for i in xrange(0, len(parts) - 1, 2):
+                f, b = parts[i:i + 2]
                 backupentries.append((f, b, None))
 
     _playback(file, report, opener, entries, backupentries)

tests/test-fncache.t

@@ -1,238 +1,281 b''
 Init repo1:
 
   $ hg init repo1
   $ cd repo1
   $ echo "some text" > a
   $ hg add
   adding a
   $ hg ci -m first
   $ cat .hg/store/fncache | sort
   data/a.i
 
 Testing a.i/b:
 
   $ mkdir a.i
   $ echo "some other text" > a.i/b
   $ hg add
   adding a.i/b (glob)
   $ hg ci -m second
   $ cat .hg/store/fncache | sort
   data/a.i
   data/a.i.hg/b.i
 
 Testing a.i.hg/c:
 
   $ mkdir a.i.hg
   $ echo "yet another text" > a.i.hg/c
   $ hg add
   adding a.i.hg/c (glob)
   $ hg ci -m third
   $ cat .hg/store/fncache | sort
   data/a.i
   data/a.i.hg.hg/c.i
   data/a.i.hg/b.i
 
 Testing verify:
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   3 files, 3 changesets, 3 total revisions
 
   $ rm .hg/store/fncache
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    data/a.i@0: missing revlog!
    data/a.i.hg/c.i@2: missing revlog!
    data/a.i/b.i@1: missing revlog!
   3 files, 3 changesets, 3 total revisions
   3 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cd ..
 
 Non store repo:
 
   $ hg --config format.usestore=False init foo
   $ cd foo
   $ mkdir tst.d
   $ echo foo > tst.d/foo
   $ hg ci -Amfoo
   adding tst.d/foo
   $ find .hg | sort
   .hg
   .hg/00changelog.i
   .hg/00manifest.i
   .hg/cache
   .hg/cache/branch2-served
   .hg/data
   .hg/data/tst.d.hg
   .hg/data/tst.d.hg/foo.i
   .hg/dirstate
   .hg/last-message.txt
   .hg/phaseroots
   .hg/requires
   .hg/undo
   .hg/undo.bookmarks
   .hg/undo.branch
   .hg/undo.desc
   .hg/undo.dirstate
   .hg/undo.phaseroots
   $ cd ..
 
 Non fncache repo:
 
   $ hg --config format.usefncache=False init bar
   $ cd bar
   $ mkdir tst.d
   $ echo foo > tst.d/Foo
   $ hg ci -Amfoo
   adding tst.d/Foo
   $ find .hg | sort
   .hg
   .hg/00changelog.i
   .hg/cache
   .hg/cache/branch2-served
   .hg/dirstate
   .hg/last-message.txt
   .hg/requires
   .hg/store
   .hg/store/00changelog.i
   .hg/store/00manifest.i
   .hg/store/data
   .hg/store/data/tst.d.hg
   .hg/store/data/tst.d.hg/_foo.i
   .hg/store/phaseroots
   .hg/store/undo
   .hg/store/undo.phaseroots
   .hg/undo.bookmarks
   .hg/undo.branch
   .hg/undo.desc
   .hg/undo.dirstate
   $ cd ..
 
 Encoding of reserved / long paths in the store
 
   $ hg init r2
   $ cd r2
   $ cat <<EOF > .hg/hgrc
   > [ui]
   > portablefilenames = ignore
   > EOF
 
   $ hg import -q --bypass - <<EOF
   > # HG changeset patch
   > # User test
   > # Date 0 0
   > # Node ID 1c7a2f7cb77be1a0def34e4c7cabc562ad98fbd7
   > # Parent  0000000000000000000000000000000000000000
   > 1
   > 
   > diff --git a/12345678/12345678/12345678/12345678/12345678/12345678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-123456789-12.3456789-12345-ABCDEFGHIJKLMNOPRSTUVWXYZ-abcdefghjiklmnopqrstuvwxyz b/12345678/12345678/12345678/12345678/12345678/12345678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-123456789-12.3456789-12345-ABCDEFGHIJKLMNOPRSTUVWXYZ-abcdefghjiklmnopqrstuvwxyz
   > new file mode 100644
   > --- /dev/null
   > +++ b/12345678/12345678/12345678/12345678/12345678/12345678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-123456789-12.3456789-12345-ABCDEFGHIJKLMNOPRSTUVWXYZ-abcdefghjiklmnopqrstuvwxyz
   > @@ -0,0 +1,1 @@
   > +foo
   > diff --git a/AUX/SECOND/X.PRN/FOURTH/FI:FTH/SIXTH/SEVENTH/EIGHTH/NINETH/TENTH/ELEVENTH/LOREMIPSUM.TXT b/AUX/SECOND/X.PRN/FOURTH/FI:FTH/SIXTH/SEVENTH/EIGHTH/NINETH/TENTH/ELEVENTH/LOREMIPSUM.TXT
   > new file mode 100644
   > --- /dev/null
   > +++ b/AUX/SECOND/X.PRN/FOURTH/FI:FTH/SIXTH/SEVENTH/EIGHTH/NINETH/TENTH/ELEVENTH/LOREMIPSUM.TXT
   > @@ -0,0 +1,1 @@
   > +foo
   > diff --git a/Project Planning/Resources/AnotherLongDirectoryName/Followedbyanother/AndAnother/AndThenAnExtremelyLongFileName.txt b/Project Planning/Resources/AnotherLongDirectoryName/Followedbyanother/AndAnother/AndThenAnExtremelyLongFileName.txt
   > new file mode 100644
   > --- /dev/null
   > +++ b/Project Planning/Resources/AnotherLongDirectoryName/Followedbyanother/AndAnother/AndThenAnExtremelyLongFileName.txt	
   > @@ -0,0 +1,1 @@
   > +foo
   > diff --git a/bla.aux/prn/PRN/lpt/com3/nul/coma/foo.NUL/normal.c b/bla.aux/prn/PRN/lpt/com3/nul/coma/foo.NUL/normal.c
   > new file mode 100644
   > --- /dev/null
   > +++ b/bla.aux/prn/PRN/lpt/com3/nul/coma/foo.NUL/normal.c
   > @@ -0,0 +1,1 @@
   > +foo
   > diff --git a/enterprise/openesbaddons/contrib-imola/corba-bc/netbeansplugin/wsdlExtension/src/main/java/META-INF/services/org.netbeans.modules.xml.wsdl.bindingsupport.spi.ExtensibilityElementTemplateProvider b/enterprise/openesbaddons/contrib-imola/corba-bc/netbeansplugin/wsdlExtension/src/main/java/META-INF/services/org.netbeans.modules.xml.wsdl.bindingsupport.spi.ExtensibilityElementTemplateProvider
   > new file mode 100644
   > --- /dev/null
   > +++ b/enterprise/openesbaddons/contrib-imola/corba-bc/netbeansplugin/wsdlExtension/src/main/java/META-INF/services/org.netbeans.modules.xml.wsdl.bindingsupport.spi.ExtensibilityElementTemplateProvider
   > @@ -0,0 +1,1 @@
   > +foo
   > EOF
 
   $ find .hg/store -name *.i  | sort
   .hg/store/00changelog.i
   .hg/store/00manifest.i
   .hg/store/data/bla.aux/pr~6e/_p_r_n/lpt/co~6d3/nu~6c/coma/foo._n_u_l/normal.c.i
   .hg/store/dh/12345678/12345678/12345678/12345678/12345678/12345678/12345678/12345/xxxxxx168e07b38e65eff86ab579afaaa8e30bfbe0f35f.i
   .hg/store/dh/au~78/second/x.prn/fourth/fi~3afth/sixth/seventh/eighth/nineth/tenth/loremia20419e358ddff1bf8751e38288aff1d7c32ec05.i
   .hg/store/dh/enterpri/openesba/contrib-/corba-bc/netbeans/wsdlexte/src/main/java/org.net7018f27961fdf338a598a40c4683429e7ffb9743.i
   .hg/store/dh/project_/resource/anotherl/followed/andanoth/andthenanextremelylongfilename0d8e1f4187c650e2f1fdca9fd90f786bc0976b6b.i
 
   $ cd ..
 
 Aborting lock does not prevent fncache writes
 
   $ cat > exceptionext.py <<EOF
   > import os
   > from mercurial import commands, util
   > from mercurial.extensions import wrapfunction
   > 
   > def lockexception(orig, vfs, lockname, wait, releasefn, acquirefn, desc):
   >     def releasewrap():
   >         raise util.Abort("forced lock failure")
   >     return orig(vfs, lockname, wait, releasewrap, acquirefn, desc)
   > 
   > def reposetup(ui, repo):
   >     wrapfunction(repo, '_lock', lockexception)
   > 
   > cmdtable = {}
   > 
   > EOF
   $ extpath=`pwd`/exceptionext.py
   $ hg init fncachetxn
   $ cd fncachetxn
   $ printf "[extensions]\nexceptionext=$extpath\n" >> .hg/hgrc
   $ touch y
   $ hg ci -qAm y
   abort: forced lock failure
   [255]
   $ cat .hg/store/fncache
   data/y.i
 
 Aborting transaction prevents fncache change
 
   $ cat > ../exceptionext.py <<EOF
   > import os
   > from mercurial import commands, util, transaction
   > from mercurial.extensions import wrapfunction
   > 
   > def wrapper(orig, self, *args, **kwargs):
   >     origonclose = self.onclose
   >     def onclose():
   >         origonclose()
   >         raise util.Abort("forced transaction failure")
   >     self.onclose = onclose
   >     return orig(self, *args, **kwargs)
   > 
   > def uisetup(ui):
   >     wrapfunction(transaction.transaction, 'close', wrapper)
   > 
   > cmdtable = {}
   > 
   > EOF
   $ rm -f "${extpath}c"
   $ touch z
   $ hg ci -qAm z
   transaction abort!
   rollback completed
   abort: forced transaction failure
   [255]
   $ cat .hg/store/fncache
   data/y.i
+
+Aborted transactions can be recovered later
+
+  $ cat > ../exceptionext.py <<EOF
+  > import os
+  > from mercurial import commands, util, transaction
+  > from mercurial.extensions import wrapfunction
+  > 
+  > def closewrapper(orig, self, *args, **kwargs):
+  >     origonclose = self.onclose
+  >     def onclose():
+  >         origonclose()
+  >         raise util.Abort("forced transaction failure")
+  >     self.onclose = onclose
+  >     return orig(self, *args, **kwargs)
+  > 
+  > def abortwrapper(orig, self, *args, **kwargs):
+  >     raise util.Abort("forced transaction failure")
+  > 
+  > def uisetup(ui):
+  >     wrapfunction(transaction.transaction, 'close', closewrapper)
+  >     wrapfunction(transaction.transaction, '_abort', abortwrapper)
+  > 
+  > cmdtable = {}
+  > 
+  > EOF
+  $ rm -f "${extpath}c"
+  $ hg up -q 1
+  $ touch z
+  $ hg ci -qAm z 2>/dev/null
+  [255]
+  $ cat .hg/store/fncache | sort
+  data/y.i
+  data/z.i
+  $ hg recover
+  rolling back interrupted transaction
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+  1 files, 1 changesets, 1 total revisions
+  $ cat .hg/store/fncache
+  data/y.i