view mercurial/tags.py @ 23923:ab6fd3205dad stable

largefiles: fix commit of a directory with no largefile changes (issue4330)

When a directory is named in the commit file list, the previous behavior was to
walk the list, and if no normal files in the directory were also named, add the
corresponding standin for each largefile in that directory.  The directory is
then dropped from the list, so that committing a directory with no normal file
changes works.  It then added the corresponding standin directory for the first
largefile seen, by prefixing it with '.hglf/'.

The latter is unnecessary since each affected largefile is explicitly referenced
by its standin in the list.  It also caused an abort if there were no changed
largefiles in the directory, because none of its standins changed:

    abort: .hglf/foo/bar: no match under directory!

This list of files is used to tweak a matcher in lfutil.updatestandinsbymatch(),
which is what is passed to commit().

The status() call that is ultimately done in the commit code with this matcher
seems to have some OS specific differences.  It is not necessary to append '.'
for Windows to run the largefiles tests cleanly.  But if '.' is not added to the
list, the match function isn't called on Linux, so status() would miss any
normal files that were also in a named directory.  The commit then proceeds
without those normal files, or says "nothing changed" if there were no changed
largefiles in the directory.  This is not filesystem specific, as VFAT on Linux
had the same behavior as when run on ext4.  It is also not an issue with
lfilesrepo.status(), since that only calls the overridden implementation when
paths are passed to commit.  I dont have access to an OS X machine ATM to test
there.

Maybe there's a better way to do this.  But since the standin directory for the
first largefile was previously being added, and that caused the same walk in
status(), there's no preformance change to this.  There is no danger of
erroneously committing files in '.', because the original match function is
called, and if it fails, the lfutil.updatestandinsbymatch() tweaked matcher only
indicates a match if the file is in the list of standins- and '.' never is.  The
added tests confirm this.

# 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 util
import encoding
import error
import errno
import time

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.vfs.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)

    # remove tags pointing to invalid nodes
    cl = repo.changelog
    for t in filetags.keys():
        try:
            cl.rev(filetags[t][0])
        except (LookupError, ValueError):
            del filetags[t]

    _updatetags(filetags, "local", alltags, tagtypes)

def _readtaghist(ui, repo, lines, fn, recode=None, calcnodelines=False):
    '''Read tag definitions from a file (or any source of lines).
    This function returns two sortdicts with similar information:
    - the first dict, bintaghist, contains the tag information as expected by
      the _readtags function, i.e. a mapping from tag name to (node, hist):
        - node is the node id from the last line read for that name,
        - hist is the list of node ids previously associated with it (in file
          order).  All node ids are binary, not hex.
    - the second dict, hextaglines, is a mapping from tag name to a list of
      [hexnode, line number] pairs, ordered from the oldest to the newest node.
    When calcnodelines is False the hextaglines dict is not calculated (an
    empty dict is returned). This is done to improve this function's
    performance in cases where the line numbers are not needed.
    '''

    bintaghist = util.sortdict()
    hextaglines = util.sortdict()
    count = 0

    def warn(msg):
        ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))

    for nline, line in enumerate(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
        if calcnodelines:
            # map tag name to a list of line numbers
            if name not in hextaglines:
                hextaglines[name] = []
            hextaglines[name].append([nodehex, nline])
            continue
        # map tag name to (node, hist)
        if name not in bintaghist:
            bintaghist[name] = []
        bintaghist[name].append(nodebin)
    return bintaghist, hextaglines

def _readtags(ui, repo, lines, fn, recode=None, calcnodelines=False):
    '''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, nodelines = _readtaghist(ui, repo, lines, fn, recode=recode,
                                       calcnodelines=calcnodelines)
    for tag, taghist in filetags.items():
        filetags[tag] = (taghist[-1], taghist[:-1])
    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.vfs('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)

    starttime = time.time()

    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

    duration = time.time() - starttime
    ui.log('tagscache',
           'resolved %d tags cache entries from %d manifests in %0.4f '
           'seconds\n',
           len(cachefnode), len(newheads), duration)

    # 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.vfs('cache/tags', 'w', atomictemp=True)
    except (OSError, IOError):
        return

    ui.log('tagscache', 'writing tags cache file with %d heads and %d tags\n',
            len(heads), len(cachetags))

    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