view mercurial/unionrepo.py @ 42522:d29db0a0c4eb

update: fix spurious unclean status bug shown by previous commit

The crux of the problem is:
- the dirstate is corrupted (the sizes/dates are assigned to the wrong files)
- because when worker.worker is used with a return value (batchget in
  merge.py here), the return value when worker.worker effectively parallelizes
  is permuted
- this is because worker.worker's partition of input and combination of output
  values are not inverses of one another: it split [1,2,3,4,5,6] into
  [[1,3,5],[2,4,6]], but combines that into [1,3,5,2,4,6].

Given that worker.worker doesn't call its function argument on contiguous
chunks on the input arguments, sticking with lists means we'd need to
know the relation between the inputs of worker.worker function argument
(for instance, requiring that every input element is mapped to exactly
one output element). It seems better to instead switch return values to
dicts, which can combined reliably with a straighforward restriction.

Differential Revision: https://phab.mercurial-scm.org/D6581

# unionrepo.py - repository class for viewing union of repository changesets
#
# Derived from bundlerepo.py
# Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
# Copyright 2013 Unity Technologies, Mads Kiilerich <[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.

"""Repository class for "in-memory pull" of one local repository to another,
allowing operations like diff and log with revsets.
"""

from __future__ import absolute_import

from .i18n import _
from .node import nullid

from . import (
    changelog,
    cmdutil,
    encoding,
    error,
    filelog,
    localrepo,
    manifest,
    mdiff,
    pathutil,
    revlog,
    util,
    vfs as vfsmod,
)

class unionrevlog(revlog.revlog):
    def __init__(self, opener, indexfile, revlog2, linkmapper):
        # How it works:
        # To retrieve a revision, we just need to know the node id so we can
        # look it up in revlog2.
        #
        # To differentiate a rev in the second revlog from a rev in the revlog,
        # we check revision against repotiprev.
        opener = vfsmod.readonlyvfs(opener)
        revlog.revlog.__init__(self, opener, indexfile)
        self.revlog2 = revlog2

        n = len(self)
        self.repotiprev = n - 1
        self.bundlerevs = set() # used by 'bundle()' revset expression
        for rev2 in self.revlog2:
            rev = self.revlog2.index[rev2]
            # rev numbers - in revlog2, very different from self.rev
            _start, _csize, rsize, base, linkrev, p1rev, p2rev, node = rev
            flags = _start & 0xFFFF

            if linkmapper is None: # link is to same revlog
                assert linkrev == rev2 # we never link back
                link = n
            else: # rev must be mapped from repo2 cl to unified cl by linkmapper
                link = linkmapper(linkrev)

            if linkmapper is not None: # link is to same revlog
                base = linkmapper(base)

            if node in self.nodemap:
                # this happens for the common revlog revisions
                self.bundlerevs.add(self.nodemap[node])
                continue

            p1node = self.revlog2.node(p1rev)
            p2node = self.revlog2.node(p2rev)

            # TODO: it's probably wrong to set compressed length to None, but
            # I have no idea if csize is valid in the base revlog context.
            e = (flags, None, rsize, base,
                 link, self.rev(p1node), self.rev(p2node), node)
            self.index.append(e)
            self.nodemap[node] = n
            self.bundlerevs.add(n)
            n += 1

    def _chunk(self, rev):
        if rev <= self.repotiprev:
            return revlog.revlog._chunk(self, rev)
        return self.revlog2._chunk(self.node(rev))

    def revdiff(self, rev1, rev2):
        """return or calculate a delta between two revisions"""
        if rev1 > self.repotiprev and rev2 > self.repotiprev:
            return self.revlog2.revdiff(
                self.revlog2.rev(self.node(rev1)),
                self.revlog2.rev(self.node(rev2)))
        elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
            return self.baserevdiff(rev1, rev2)

        return mdiff.textdiff(self.revision(rev1), self.revision(rev2))

    def revision(self, nodeorrev, _df=None, raw=False):
        """return an uncompressed revision of a given node or revision
        number.
        """
        if isinstance(nodeorrev, int):
            rev = nodeorrev
            node = self.node(rev)
        else:
            node = nodeorrev
            rev = self.rev(node)

        if node == nullid:
            return ""

        if rev > self.repotiprev:
            text = self.revlog2.revision(node)
            self._revisioncache = (node, rev, text)
        else:
            text = self.baserevision(rev)
            # already cached
        return text

    def baserevision(self, nodeorrev):
        # Revlog subclasses may override 'revision' method to modify format of
        # content retrieved from revlog. To use unionrevlog with such class one
        # needs to override 'baserevision' and make more specific call here.
        return revlog.revlog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        # Exists for the same purpose as baserevision.
        return revlog.revlog.revdiff(self, rev1, rev2)

    def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
        raise NotImplementedError
    def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None,
                 maybemissingparents=False):
        raise NotImplementedError
    def strip(self, minlink, transaction):
        raise NotImplementedError
    def checksize(self):
        raise NotImplementedError

class unionchangelog(unionrevlog, changelog.changelog):
    def __init__(self, opener, opener2):
        changelog.changelog.__init__(self, opener)
        linkmapper = None
        changelog2 = changelog.changelog(opener2)
        unionrevlog.__init__(self, opener, self.indexfile, changelog2,
                             linkmapper)

    def baserevision(self, nodeorrev):
        # Although changelog doesn't override 'revision' method, some extensions
        # may replace this class with another that does. Same story with
        # manifest and filelog classes.
        return changelog.changelog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return changelog.changelog.revdiff(self, rev1, rev2)

class unionmanifest(unionrevlog, manifest.manifestrevlog):
    def __init__(self, opener, opener2, linkmapper):
        manifest.manifestrevlog.__init__(self, opener)
        manifest2 = manifest.manifestrevlog(opener2)
        unionrevlog.__init__(self, opener, self.indexfile, manifest2,
                             linkmapper)

    def baserevision(self, nodeorrev):
        return manifest.manifestrevlog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return manifest.manifestrevlog.revdiff(self, rev1, rev2)

class unionfilelog(filelog.filelog):
    def __init__(self, opener, path, opener2, linkmapper, repo):
        filelog.filelog.__init__(self, opener, path)
        filelog2 = filelog.filelog(opener2, path)
        self._revlog = unionrevlog(opener, self.indexfile,
                                   filelog2._revlog, linkmapper)
        self._repo = repo
        self.repotiprev = self._revlog.repotiprev
        self.revlog2 = self._revlog.revlog2

    def baserevision(self, nodeorrev):
        return filelog.filelog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return filelog.filelog.revdiff(self, rev1, rev2)

    def iscensored(self, rev):
        """Check if a revision is censored."""
        if rev <= self.repotiprev:
            return filelog.filelog.iscensored(self, rev)
        node = self.node(rev)
        return self.revlog2.iscensored(self.revlog2.rev(node))

class unionpeer(localrepo.localpeer):
    def canpush(self):
        return False

class unionrepository(object):
    """Represents the union of data in 2 repositories.

    Instances are not usable if constructed directly. Use ``instance()``
    or ``makeunionrepository()`` to create a usable instance.
    """
    def __init__(self, repo2, url):
        self.repo2 = repo2
        self._url = url

        self.ui.setconfig('phases', 'publish', False, 'unionrepo')

    @localrepo.unfilteredpropertycache
    def changelog(self):
        return unionchangelog(self.svfs, self.repo2.svfs)

    @localrepo.unfilteredpropertycache
    def manifestlog(self):
        rootstore = unionmanifest(self.svfs, self.repo2.svfs,
                                  self.unfiltered()._clrev)
        return manifest.manifestlog(self.svfs, self, rootstore,
                                    self.narrowmatch())

    def _clrev(self, rev2):
        """map from repo2 changelog rev to temporary rev in self.changelog"""
        node = self.repo2.changelog.node(rev2)
        return self.changelog.rev(node)

    def url(self):
        return self._url

    def file(self, f):
        return unionfilelog(self.svfs, f, self.repo2.svfs,
                            self.unfiltered()._clrev, self)

    def close(self):
        self.repo2.close()

    def cancopy(self):
        return False

    def peer(self):
        return unionpeer(self)

    def getcwd(self):
        return encoding.getcwd() # always outside the repo

def instance(ui, path, create, intents=None, createopts=None):
    if create:
        raise error.Abort(_('cannot create new union repository'))
    parentpath = ui.config("bundle", "mainreporoot")
    if not parentpath:
        # try to find the correct path to the working directory repo
        parentpath = cmdutil.findrepo(encoding.getcwd())
        if parentpath is None:
            parentpath = ''
    if parentpath:
        # Try to make the full path relative so we get a nice, short URL.
        # In particular, we don't want temp dir names in test outputs.
        cwd = encoding.getcwd()
        if parentpath == cwd:
            parentpath = ''
        else:
            cwd = pathutil.normasprefix(cwd)
            if parentpath.startswith(cwd):
                parentpath = parentpath[len(cwd):]
    if path.startswith('union:'):
        s = path.split(":", 1)[1].split("+", 1)
        if len(s) == 1:
            repopath, repopath2 = parentpath, s[0]
        else:
            repopath, repopath2 = s
    else:
        repopath, repopath2 = parentpath, path

    return makeunionrepository(ui, repopath, repopath2)

def makeunionrepository(ui, repopath1, repopath2):
    """Make a union repository object from 2 local repo paths."""
    repo1 = localrepo.instance(ui, repopath1, create=False)
    repo2 = localrepo.instance(ui, repopath2, create=False)

    url = 'union:%s+%s' % (util.expandpath(repopath1),
                           util.expandpath(repopath2))

    class derivedunionrepository(unionrepository, repo1.__class__):
        pass

    repo = repo1
    repo.__class__ = derivedunionrepository
    unionrepository.__init__(repo1, repo2, url)

    return repo