view mercurial/repair.py @ 24545:9e0c67e84896

json: implement {tags} template

Tags is pretty easy to implement. Let's start there.

The output is slightly different from `hg tags -Tjson`. For reference,
the CLI has the following output:

  [
   {
    "node": "e2049974f9a23176c2addb61d8f5b86e0d620490",
    "rev": 29880,
    "tag": "tip",
    "type": ""
   },
   ...
  ]

Our output has the format:

  {
    "node": "0aeb19ea57a6d223bacddda3871cb78f24b06510",
    "tags": [
      {
        "node": "e2049974f9a23176c2addb61d8f5b86e0d620490",
        "tag": "tag1",
        "date": [1427775457.0, 25200]
      },
      ...
    ]
  }

"rev" is omitted because it isn't a reliable identifier. We shouldn't
be exposing them in web APIs and giving the impression it remotely
resembles a stable identifier. Perhaps we could one day hide this behind
a config option (it might be useful to expose when running servers
locally).

The "type" of the tag isn't defined because this information isn't yet
exposed to the hgweb templater (it could be in a follow-up) and because
it is questionable whether different types should be exposed at all.
(Should the web interface really be exposing "local" tags?)

We use an object for the outer type instead of Array for a few reasons.
First, it is extensible. If we ever need to throw more global properties
into the output, we can do that without breaking backwards compatibility
(property additions should be backwards compatible). Second, uniformity
in web APIs is nice. Having everything return objects seems much saner than
a mix of array and object. Third, there are security issues with arrays
in older browsers. The JSON web services world almost never uses arrays
as the main type for this reason.

Another possibly controversial part about this patch is how dates are
defined. While JSON has a Date type, it is based on the JavaScript Date
type, which is widely considered a pile of garbage. It is a non-starter
for this reason.

Many of Mercurial's built-in date filters drop seconds resolution. So
that's a non-starter as well, since we want the API to be lossless where
possible. rfc3339date, rfc822date, isodatesec, and date are all lossless.
However, they each require the client to perform string parsing on top of
JSON decoding. While date parsing libraries are pretty ubiquitous, some
languages don't have them out of the box. However, pretty much every
programming language can deal with UNIX timestamps (which are just
integers or floats). So, we choose to use Mercurial's internal date
representation, which in JSON is modeled as float seconds since UNIX
epoch and an integer timezone offset from UTC (keep in mind
JavaScript/JSON models all "Numbers" as double prevision floating point
numbers, so there isn't a difference between ints and floats in JSON).

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <[e-mail]>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial import changegroup, exchange, util, bundle2
from mercurial.node import short, hex
from mercurial.i18n import _
import errno

def _bundle(repo, bases, heads, node, suffix, compress=True):
    """create a bundle with the specified revisions as a backup"""
    usebundle2 = (repo.ui.config('experimental', 'bundle2-exp') and
                  repo.ui.config('experimental', 'strip-bundle2-version'))
    if usebundle2:
        cgversion = repo.ui.config('experimental', 'strip-bundle2-version')
        if cgversion not in changegroup.packermap:
            repo.ui.warn(_('unknown strip-bundle2-version value %r; ' +
                            'should be one of %r\n') %
                         (cgversion, sorted(changegroup.packermap.keys()),))
            cgversion = '01'
            usebundle2 = False
    else:
        cgversion = '01'

    cg = changegroup.changegroupsubset(repo, bases, heads, 'strip',
                                       version=cgversion)
    backupdir = "strip-backup"
    vfs = repo.vfs
    if not vfs.isdir(backupdir):
        vfs.mkdir(backupdir)

    # Include a hash of all the nodes in the filename for uniqueness
    hexbases = (hex(n) for n in bases)
    hexheads = (hex(n) for n in heads)
    allcommits = repo.set('%ls::%ls', hexbases, hexheads)
    allhashes = sorted(c.hex() for c in allcommits)
    totalhash = util.sha1(''.join(allhashes)).hexdigest()
    name = "%s/%s-%s-%s.hg" % (backupdir, short(node), totalhash[:8], suffix)

    if usebundle2:
        bundletype = "HG2Y"
    elif compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"
    return changegroup.writebundle(repo.ui, cg, name, bundletype, vfs)

def _collectfiles(repo, striprev):
    """find out the filelogs affected by the strip"""
    files = set()

    for x in xrange(striprev, len(repo)):
        files.update(repo[x].files())

    return sorted(files)

def _collectbrokencsets(repo, files, striprev):
    """return the changesets which will be broken by the truncation"""
    s = set()
    def collectone(revlog):
        _, brokenset = revlog.getstrippoint(striprev)
        s.update([revlog.linkrev(r) for r in brokenset])

    collectone(repo.manifest)
    for fname in files:
        collectone(repo.file(fname))

    return s

def strip(ui, repo, nodelist, backup=True, topic='backup'):

    # Simple way to maintain backwards compatibility for this
    # argument.
    if backup in ['none', 'strip']:
        backup = False

    repo = repo.unfiltered()
    repo.destroying()

    cl = repo.changelog
    # TODO handle undo of merge sets
    if isinstance(nodelist, str):
        nodelist = [nodelist]
    striplist = [cl.rev(node) for node in nodelist]
    striprev = min(striplist)

    # Some revisions with rev > striprev may not be descendants of striprev.
    # We have to find these revisions and put them in a bundle, so that
    # we can restore them after the truncations.
    # To create the bundle we use repo.changegroupsubset which requires
    # the list of heads and bases of the set of interesting revisions.
    # (head = revision in the set that has no descendant in the set;
    #  base = revision in the set that has no ancestor in the set)
    tostrip = set(striplist)
    for rev in striplist:
        for desc in cl.descendants([rev]):
            tostrip.add(desc)

    files = _collectfiles(repo, striprev)
    saverevs = _collectbrokencsets(repo, files, striprev)

    # compute heads
    saveheads = set(saverevs)
    for r in xrange(striprev + 1, len(cl)):
        if r not in tostrip:
            saverevs.add(r)
            saveheads.difference_update(cl.parentrevs(r))
            saveheads.add(r)
    saveheads = [cl.node(r) for r in saveheads]

    # compute base nodes
    if saverevs:
        descendants = set(cl.descendants(saverevs))
        saverevs.difference_update(descendants)
    savebases = [cl.node(r) for r in saverevs]
    stripbases = [cl.node(r) for r in tostrip]

    # For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
    # is much faster
    newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
    if newbmtarget:
        newbmtarget = repo[newbmtarget.first()].node()
    else:
        newbmtarget = '.'

    bm = repo._bookmarks
    updatebm = []
    for m in bm:
        rev = repo[bm[m]].rev()
        if rev in tostrip:
            updatebm.append(m)

    # create a changegroup for all the branches we need to keep
    backupfile = None
    vfs = repo.vfs
    node = nodelist[-1]
    if backup:
        backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
        repo.ui.status(_("saved backup bundle to %s\n") %
                       vfs.join(backupfile))
        repo.ui.log("backupbundle", "saved backup bundle to %s\n",
                    vfs.join(backupfile))
    if saveheads or savebases:
        # do not compress partial bundle if we remove it from disk later
        chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
                            compress=False)

    mfst = repo.manifest

    tr = repo.transaction("strip")
    offset = len(tr.entries)

    try:
        tr.startgroup()
        cl.strip(striprev, tr)
        mfst.strip(striprev, tr)
        for fn in files:
            repo.file(fn).strip(striprev, tr)
        tr.endgroup()

        try:
            for i in xrange(offset, len(tr.entries)):
                file, troffset, ignore = tr.entries[i]
                repo.svfs(file, 'a').truncate(troffset)
                if troffset == 0:
                    repo.store.markremoved(file)
            tr.close()
        except: # re-raises
            tr.abort()
            raise

        if saveheads or savebases:
            ui.note(_("adding branch\n"))
            f = vfs.open(chgrpfile, "rb")
            gen = exchange.readbundle(ui, f, chgrpfile, vfs)
            if not repo.ui.verbose:
                # silence internal shuffling chatter
                repo.ui.pushbuffer()
            if isinstance(gen, bundle2.unbundle20):
                tr = repo.transaction('strip')
                tr.hookargs = {'source': 'strip',
                               'url': 'bundle:' + vfs.join(chgrpfile)}
                try:
                    bundle2.processbundle(repo, gen, lambda: tr)
                    tr.close()
                finally:
                    tr.release()
            else:
                changegroup.addchangegroup(repo, gen, 'strip',
                                           'bundle:' + vfs.join(chgrpfile),
                                           True)
            if not repo.ui.verbose:
                repo.ui.popbuffer()
            f.close()

        # remove undo files
        for undovfs, undofile in repo.undofiles():
            try:
                undovfs.unlink(undofile)
            except OSError, e:
                if e.errno != errno.ENOENT:
                    ui.warn(_('error removing %s: %s\n') %
                            (undovfs.join(undofile), str(e)))

        for m in updatebm:
            bm[m] = repo[newbmtarget].node()
        bm.write()
    except: # re-raises
        if backupfile:
            ui.warn(_("strip failed, full bundle stored in '%s'\n")
                    % vfs.join(backupfile))
        elif saveheads:
            ui.warn(_("strip failed, partial bundle stored in '%s'\n")
                    % vfs.join(chgrpfile))
        raise
    else:
        if saveheads or savebases:
            # Remove partial backup only if there were no exceptions
            vfs.unlink(chgrpfile)

    repo.destroyed()