tags: write tag overwriting history also into tag cache file (issue3911)

Before this patch, tag overwriting history is not written into tag
cache file ".hg/cache/tags".

This may give higher priority to local tag than global one, even if
the former is overwritten by the latter, because tag overwriting
history is used to compare priorities of them (as "rank").

In such cases, "hg tags" invocations using tag cache file shows
incorrect tag information.

This patch writes tag overwriting history also into tag cache file.

mercurial/tags.py

@@ -1,298 +1,300 b''
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Matt Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[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.
 
 # Currently this module only deals with reading and caching tags.
 # Eventually, it could take care of updating (adding/removing/moving)
 # tags too.
 
 from node import nullid, bin, hex, short
 from i18n import _
 import encoding
 import error
 import errno
 
 def findglobaltags(ui, repo, alltags, tagtypes):
     '''Find global tags in repo by reading .hgtags from every head that
     has a distinct version of it, using a cache to avoid excess work.
     Updates the dicts alltags, tagtypes in place: alltags maps tag name
     to (node, hist) pair (see _readtags() below), and tagtypes maps tag
     name to tag type ("global" in this case).'''
     # This is so we can be lazy and assume alltags contains only global
     # tags when we pass it to _writetagcache().
     assert len(alltags) == len(tagtypes) == 0, \
            "findglobaltags() should be called first"
 
     (heads, tagfnode, cachetags, shouldwrite) = _readtagcache(ui, repo)
     if cachetags is not None:
         assert not shouldwrite
         # XXX is this really 100% correct?  are there oddball special
         # cases where a global tag should outrank a local tag but won't,
         # because cachetags does not contain rank info?
         _updatetags(cachetags, 'global', alltags, tagtypes)
         return
 
     seen = set()                    # set of fnode
     fctx = None
     for head in reversed(heads):        # oldest to newest
         assert head in repo.changelog.nodemap, \
                "tag cache returned bogus head %s" % short(head)
 
         fnode = tagfnode.get(head)
         if fnode and fnode not in seen:
             seen.add(fnode)
             if not fctx:
                 fctx = repo.filectx('.hgtags', fileid=fnode)
             else:
                 fctx = fctx.filectx(fnode)
 
             filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
             _updatetags(filetags, 'global', alltags, tagtypes)
 
     # and update the cache (if necessary)
     if shouldwrite:
         _writetagcache(ui, repo, heads, tagfnode, alltags)
 
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo.  Update alltags and tagtypes.'''
     try:
         data = repo.opener.read("localtags")
     except IOError, inst:
         if inst.errno != errno.ENOENT:
             raise
         return
 
     # localtags is in the local encoding; re-encode to UTF-8 on
     # input for consistency with the rest of this module.
     filetags = _readtags(
         ui, repo, data.splitlines(), "localtags",
         recode=encoding.fromlocal)
     _updatetags(filetags, "local", alltags, tagtypes)
 
 def _readtags(ui, repo, lines, fn, recode=None):
     '''Read tag definitions from a file (or any source of lines).
     Return a mapping from tag name to (node, hist): node is the node id
     from the last line read for that name, and hist is the list of node
     ids previously associated with it (in file order).  All node ids are
     binary, not hex.'''
 
     filetags = {}               # map tag name to (node, hist)
     count = 0
 
     def warn(msg):
         ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
     for line in lines:
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(" ", 1)
         except ValueError:
             warn(_("cannot parse entry"))
             continue
         name = name.strip()
         if recode:
             name = recode(name)
         try:
             nodebin = bin(nodehex)
         except TypeError:
             warn(_("node '%s' is not well formed") % nodehex)
             continue
 
         # update filetags
         hist = []
         if name in filetags:
             n, hist = filetags[name]
             hist.append(n)
         filetags[name] = (nodebin, hist)
     return filetags
 
 def _updatetags(filetags, tagtype, alltags, tagtypes):
     '''Incorporate the tag info read from one file into the two
     dictionaries, alltags and tagtypes, that contain all tag
     info (global across all heads plus local).'''
 
     for name, nodehist in filetags.iteritems():
         if name not in alltags:
             alltags[name] = nodehist
             tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supersedes us OR
         #  mutual supersedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (bnode != anode and anode in bhist and
             (bnode not in ahist or len(bhist) > len(ahist))):
             anode = bnode
         else:
             tagtypes[name] = tagtype
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
 
 
 # The tag cache only stores info about heads, not the tag contents
 # from each head.  I.e. it doesn't try to squeeze out the maximum
 # performance, but is simpler has a better chance of actually
 # working correctly.  And this gives the biggest performance win: it
 # avoids looking up .hgtags in the manifest for every head, and it
 # can avoid calling heads() at all if there have been no changes to
 # the repo.
 
 def _readtagcache(ui, repo):
     '''Read the tag cache and return a tuple (heads, fnodes, cachetags,
     shouldwrite).  If the cache is completely up-to-date, cachetags is a
     dict of the form returned by _readtags(); otherwise, it is None and
     heads and fnodes are set.  In that case, heads is the list of all
     heads currently in the repository (ordered from tip to oldest) and
     fnodes is a mapping from head to .hgtags filenode.  If those two are
     set, caller is responsible for reading tag info from each head.'''
 
     try:
         cachefile = repo.opener('cache/tags', 'r')
         # force reading the file for static-http
         cachelines = iter(cachefile)
     except IOError:
         cachefile = None
 
     # The cache file consists of lines like
     #   <headrev> <headnode> [<tagnode>]
     # where <headrev> and <headnode> redundantly identify a repository
     # head from the time the cache was written, and <tagnode> is the
     # filenode of .hgtags on that head.  Heads with no .hgtags file will
     # have no <tagnode>.  The cache is ordered from tip to oldest (which
     # is part of why <headrev> is there: a quick visual check is all
     # that's required to ensure correct order).
     #
     # This information is enough to let us avoid the most expensive part
     # of finding global tags, which is looking up <tagnode> in the
     # manifest for each head.
     cacherevs = []                      # list of headrev
     cacheheads = []                     # list of headnode
     cachefnode = {}                     # map headnode to filenode
     if cachefile:
         try:
             for line in cachelines:
                 if line == "\n":
                     break
                 line = line.split()
                 cacherevs.append(int(line[0]))
                 headnode = bin(line[1])
                 cacheheads.append(headnode)
                 if len(line) == 3:
                     fnode = bin(line[2])
                     cachefnode[headnode] = fnode
         except Exception:
             # corruption of the tags cache, just recompute it
             ui.warn(_('.hg/cache/tags is corrupt, rebuilding it\n'))
             cacheheads = []
             cacherevs = []
             cachefnode = {}
 
     tipnode = repo.changelog.tip()
     tiprev = len(repo.changelog) - 1
 
     # Case 1 (common): tip is the same, so nothing has changed.
     # (Unchanged tip trivially means no changesets have been added.
     # But, thanks to localrepository.destroyed(), it also means none
     # have been destroyed by strip or rollback.)
     if cacheheads and cacheheads[0] == tipnode and cacherevs[0] == tiprev:
         tags = _readtags(ui, repo, cachelines, cachefile.name)
         cachefile.close()
         return (None, None, tags, False)
     if cachefile:
         cachefile.close()               # ignore rest of file
 
     repoheads = repo.heads()
     # Case 2 (uncommon): empty repo; get out quickly and don't bother
     # writing an empty cache.
     if repoheads == [nullid]:
         return ([], {}, {}, False)
 
     # Case 3 (uncommon): cache file missing or empty.
 
     # Case 4 (uncommon): tip rev decreased.  This should only happen
     # when we're called from localrepository.destroyed().  Refresh the
     # cache so future invocations will not see disappeared heads in the
     # cache.
 
     # Case 5 (common): tip has changed, so we've added/replaced heads.
 
     # As it happens, the code to handle cases 3, 4, 5 is the same.
 
     # N.B. in case 4 (nodes destroyed), "new head" really means "newly
     # exposed".
     if not len(repo.file('.hgtags')):
         # No tags have ever been committed, so we can avoid a
         # potentially expensive search.
         return (repoheads, cachefnode, None, True)
 
     newheads = [head
                 for head in repoheads
                 if head not in set(cacheheads)]
 
     # Now we have to lookup the .hgtags filenode for every new head.
     # This is the most expensive part of finding tags, so performance
     # depends primarily on the size of newheads.  Worst case: no cache
     # file, so newheads == repoheads.
     for head in reversed(newheads):
         cctx = repo[head]
         try:
             fnode = cctx.filenode('.hgtags')
             cachefnode[head] = fnode
         except error.LookupError:
             # no .hgtags file on this head
             pass
 
     # Caller has to iterate over all heads, but can use the filenodes in
     # cachefnode to get to each .hgtags revision quickly.
     return (repoheads, cachefnode, None, True)
 
 def _writetagcache(ui, repo, heads, tagfnode, cachetags):
 
     try:
         cachefile = repo.opener('cache/tags', 'w', atomictemp=True)
     except (OSError, IOError):
         return
 
     realheads = repo.heads()            # for sanity checks below
     for head in heads:
         # temporary sanity checks; these can probably be removed
         # once this code has been in crew for a few weeks
         assert head in repo.changelog.nodemap, \
                'trying to write non-existent node %s to tag cache' % short(head)
         assert head in realheads, \
                'trying to write non-head %s to tag cache' % short(head)
         assert head != nullid, \
                'trying to write nullid to tag cache'
 
         # This can't fail because of the first assert above.  When/if we
         # remove that assert, we might want to catch LookupError here
         # and downgrade it to a warning.
         rev = repo.changelog.rev(head)
 
         fnode = tagfnode.get(head)
         if fnode:
             cachefile.write('%d %s %s\n' % (rev, hex(head), hex(fnode)))
         else:
             cachefile.write('%d %s\n' % (rev, hex(head)))
 
     # Tag names in the cache are in UTF-8 -- which is the whole reason
     # we keep them in UTF-8 throughout this module.  If we converted
     # them local encoding on input, we would lose info writing them to
     # the cache.
     cachefile.write('\n')
     for (name, (node, hist)) in cachetags.iteritems():
+        for n in hist:
+            cachefile.write("%s %s\n" % (hex(n), name))
         cachefile.write("%s %s\n" % (hex(node), name))
 
     try:
         cachefile.close()
     except (OSError, IOError):
         pass

tests/test-tags.t

@@ -1,406 +1,419 b''
 Helper functions:
 
   $ cacheexists() {
   >   [ -f .hg/cache/tags ] && echo "tag cache exists" || echo "no tag cache"
   > }
 
   $ dumptags() {
   >     rev=$1
   >     echo "rev $rev: .hgtags:"
   >     hg cat -r$rev .hgtags
   > }
 
 # XXX need to test that the tag cache works when we strip an old head
 # and add a new one rooted off non-tip: i.e. node and rev of tip are the
 # same, but stuff has changed behind tip.
 
 Setup:
 
   $ hg init t
   $ cd t
   $ cacheexists
   no tag cache
   $ hg id
   000000000000 tip
   $ cacheexists
   no tag cache
   $ echo a > a
   $ hg add a
   $ hg commit -m "test"
   $ hg co
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg identify
   acb14030fe0a tip
   $ cacheexists
   tag cache exists
 
 Try corrupting the cache
 
   $ printf 'a b' > .hg/cache/tags
   $ hg identify
   .hg/cache/tags is corrupt, rebuilding it
   acb14030fe0a tip
   $ cacheexists
   tag cache exists
   $ hg identify
   acb14030fe0a tip
 
 Create local tag with long name:
 
   $ T=`hg identify --debug --id`
   $ hg tag -l "This is a local tag with a really long name!"
   $ hg tags
   tip                                0:acb14030fe0a
   This is a local tag with a really long name!     0:acb14030fe0a
   $ rm .hg/localtags
 
 Create a tag behind hg's back:
 
   $ echo "$T first" > .hgtags
   $ cat .hgtags
   acb14030fe0a21b60322c440ad2d20cf7685a376 first
   $ hg add .hgtags
   $ hg commit -m "add tags"
   $ hg tags
   tip                                1:b9154636be93
   first                              0:acb14030fe0a
   $ hg identify
   b9154636be93 tip
 
 Repeat with cold tag cache:
 
   $ rm -f .hg/cache/tags
   $ hg identify
   b9154636be93 tip
 
 And again, but now unable to write tag cache:
 
 #if unix-permissions
   $ rm -f .hg/cache/tags
   $ chmod 555 .hg
   $ hg identify
   b9154636be93 tip
   $ chmod 755 .hg
 #endif
 
 Create a branch:
 
   $ echo bb > a
   $ hg status
   M a
   $ hg identify
   b9154636be93+ tip
   $ hg co first
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg id
   acb14030fe0a+ first
   $ hg -v id
   acb14030fe0a+ first
   $ hg status
   M a
   $ echo 1 > b
   $ hg add b
   $ hg commit -m "branch"
   created new head
   $ hg id
   c8edf04160c7 tip
 
 Merge the two heads:
 
   $ hg merge 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg id
   c8edf04160c7+b9154636be93+ tip
   $ hg status
   M .hgtags
   $ hg commit -m "merge"
 
 Create a fake head, make sure tag not visible afterwards:
 
   $ cp .hgtags tags
   $ hg tag last
   $ hg rm .hgtags
   $ hg commit -m "remove"
 
   $ mv tags .hgtags
   $ hg add .hgtags
   $ hg commit -m "readd"
   $ 
   $ hg tags
   tip                                6:35ff301afafe
   first                              0:acb14030fe0a
 
 Add invalid tags:
 
   $ echo "spam" >> .hgtags
   $ echo >> .hgtags
   $ echo "foo bar" >> .hgtags
   $ echo "a5a5 invalid" >> .hg/localtags
   $ cat .hgtags
   acb14030fe0a21b60322c440ad2d20cf7685a376 first
   spam
   
   foo bar
   $ hg commit -m "tags"
 
 Report tag parse error on other head:
 
   $ hg up 3
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 'x y' >> .hgtags
   $ hg commit -m "head"
   created new head
 
   $ hg tags
   .hgtags@75d9f02dfe28, line 2: cannot parse entry
   .hgtags@75d9f02dfe28, line 4: node 'foo' is not well formed
   .hgtags@c4be69a18c11, line 2: node 'x' is not well formed
   tip                                8:c4be69a18c11
   first                              0:acb14030fe0a
   $ hg tip
   changeset:   8:c4be69a18c11
   tag:         tip
   parent:      3:ac5e980c4dc0
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     head
   
 
 Test tag precedence rules:
 
   $ cd ..
   $ hg init t2
   $ cd t2
   $ echo foo > foo
   $ hg add foo
   $ hg ci -m 'add foo'      # rev 0
   $ hg tag bar              # rev 1
   $ echo >> foo
   $ hg ci -m 'change foo 1' # rev 2
   $ hg up -C 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg tag -r 1 -f bar      # rev 3
   $ hg up -C 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo >> foo
   $ hg ci -m 'change foo 2' # rev 4
   created new head
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Repeat in case of cache effects:
 
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Detailed dump of tag info:
 
   $ hg heads -q             # expect 4, 3, 2
   4:0c192d7d5e6b
   3:6fa450212aeb
   2:7a94127795a3
   $ dumptags 2
   rev 2: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   $ dumptags 3
   rev 3: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   78391a272241d70354aa14c874552cad6b51bb42 bar
   $ dumptags 4
   rev 4: .hgtags:
   bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 
 Dump cache:
 
   $ cat .hg/cache/tags
   4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   3 6fa450212aeb2a21ed616a54aea39a4a27894cd7 7d3b718c964ef37b89e550ebdafd5789e76ce1b0
   2 7a94127795a33c10a370c93f731fd9fea0b79af6 0c04f2a8af31de17fab7422878ee5a2dadbc943d
   
+  bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
+  bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   78391a272241d70354aa14c874552cad6b51bb42 bar
 
 Test tag removal:
 
   $ hg tag --remove bar     # rev 5
   $ hg tip -vp
   changeset:   5:5f6e8655b1c7
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   files:       .hgtags
   description:
   Removed tag bar
   
   
   diff -r 0c192d7d5e6b -r 5f6e8655b1c7 .hgtags
   --- a/.hgtags	Thu Jan 01 00:00:00 1970 +0000
   +++ b/.hgtags	Thu Jan 01 00:00:00 1970 +0000
   @@ -1,1 +1,3 @@
    bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
   +78391a272241d70354aa14c874552cad6b51bb42 bar
   +0000000000000000000000000000000000000000 bar
   
   $ hg tags
   tip                                5:5f6e8655b1c7
   $ hg tags                 # again, try to expose cache bugs
   tip                                5:5f6e8655b1c7
 
 Remove nonexistent tag:
 
   $ hg tag --remove foobar
   abort: tag 'foobar' does not exist
   [255]
   $ hg tip
   changeset:   5:5f6e8655b1c7
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     Removed tag bar
   
 
 Undo a tag with rollback:
 
   $ hg rollback             # destroy rev 5 (restore bar)
   repository tip rolled back to revision 4 (undo commit)
   working directory now based on revision 4
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
   $ hg tags
   tip                                4:0c192d7d5e6b
   bar                                1:78391a272241
 
 Test tag rank:
 
   $ cd ..
   $ hg init t3
   $ cd t3
   $ echo foo > foo
   $ hg add foo
   $ hg ci -m 'add foo'       # rev 0
   $ hg tag -f bar            # rev 1 bar -> 0
   $ hg tag -f bar            # rev 2 bar -> 1
   $ hg tag -fr 0 bar         # rev 3 bar -> 0
   $ hg tag -fr 1 bar         # rev 4 bar -> 1
   $ hg tag -fr 0 bar         # rev 5 bar -> 0
   $ hg tags
   tip                                5:85f05169d91d
   bar                                0:bbd179dfa0a7
   $ hg co 3
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo barbar > foo
   $ hg ci -m 'change foo'    # rev 6
   created new head
   $ hg tags
   tip                                6:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Don't allow moving tag without -f:
 
   $ hg tag -r 3 bar
   abort: tag 'bar' already exists (use -f to force)
   [255]
   $ hg tags
   tip                                6:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Strip 1: expose an old head:
 
   $ hg --config extensions.mq= strip 5
   saved backup bundle to $TESTTMP/t3/.hg/strip-backup/*-backup.hg (glob)
   $ hg tags                  # partly stale cache
   tip                                5:735c3ca72986
   bar                                1:78391a272241
   $ hg tags                  # up-to-date cache
   tip                                5:735c3ca72986
   bar                                1:78391a272241
 
 Strip 2: destroy whole branch, no old head exposed
 
   $ hg --config extensions.mq= strip 4
   saved backup bundle to $TESTTMP/t3/.hg/strip-backup/*-backup.hg (glob)
   $ hg tags                  # partly stale
   tip                                4:735c3ca72986
   bar                                0:bbd179dfa0a7
   $ rm -f .hg/cache/tags
   $ hg tags                  # cold cache
   tip                                4:735c3ca72986
   bar                                0:bbd179dfa0a7
 
 Test tag rank with 3 heads:
 
   $ cd ..
   $ hg init t4
   $ cd t4
   $ echo foo > foo
   $ hg add
   adding foo
   $ hg ci -m 'add foo'                 # rev 0
   $ hg tag bar                         # rev 1 bar -> 0
   $ hg tag -f bar                      # rev 2 bar -> 1
   $ hg up -qC 0
   $ hg tag -fr 2 bar                   # rev 3 bar -> 2
   $ hg tags
   tip                                3:197c21bbbf2c
   bar                                2:6fa450212aeb
   $ hg up -qC 0
   $ hg tag -m 'retag rev 0' -fr 0 bar  # rev 4 bar -> 0, but bar stays at 2
 
 Bar should still point to rev 2:
 
   $ hg tags
   tip                                4:3b4b14ed0202
   bar                                2:6fa450212aeb
 
 Test that removing global/local tags does not get confused when trying
 to remove a tag of type X which actually only exists as a type Y:
 
   $ cd ..
   $ hg init t5
   $ cd t5
   $ echo foo > foo
   $ hg add
   adding foo
   $ hg ci -m 'add foo'                 # rev 0
 
   $ hg tag -r 0 -l localtag
   $ hg tag --remove localtag
   abort: tag 'localtag' is not a global tag
   [255]
   $ 
   $ hg tag -r 0 globaltag
   $ hg tag --remove -l globaltag
   abort: tag 'globaltag' is not a local tag
   [255]
   $ hg tags -v
   tip                                1:a0b6fe111088
   localtag                           0:bbd179dfa0a7 local
   globaltag                          0:bbd179dfa0a7
 
 Test for issue3911
 
   $ hg tag -r 0 -l localtag2
   $ hg tag -l --remove localtag2
   $ hg tags -v
   tip                                1:a0b6fe111088
   localtag                           0:bbd179dfa0a7 local
   globaltag                          0:bbd179dfa0a7
 
   $ hg tag -r 1 -f localtag
   $ hg tags -v
   tip                                2:5c70a037bb37
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
+  $ hg tags -v
+  tip                                2:5c70a037bb37
+  localtag                           1:a0b6fe111088
+  globaltag                          0:bbd179dfa0a7
+
   $ hg tag -r 1 localtag2
   $ hg tags -v
   tip                                3:bbfb8cd42be2
   localtag2                          1:a0b6fe111088
   localtag                           1:a0b6fe111088
   globaltag                          0:bbd179dfa0a7
 
+  $ hg tags -v
+  tip                                3:bbfb8cd42be2
+  localtag2                          1:a0b6fe111088
+  localtag                           1:a0b6fe111088
+  globaltag                          0:bbd179dfa0a7
+
   $ cd ..