[PATCH 9 of 9 v2] bundlerepo: add support for treemanifests in cg3 bundles

[Martin von Zweigbergk]

On Fri, Aug 5, 2016 at 10:23 AM, Augie Fackler <raf at durin42.com> wrote:
> # HG changeset patch
> # User Augie Fackler <augie at google.com>
> # Date 1470416891 14400
> #      Fri Aug 05 13:08:11 2016 -0400
> # Node ID 9fd3a481214d424286e3c1b52dc16a3a894665a4
> # Parent  bf05e3655cb4239fa34e0b7e263aa33a7a2143bd
> bundlerepo: add support for treemanifests in cg3 bundles
>
> This is a little messier than I'd like, and I'll probably come back
> and do some more refactoring later, but as it is this unblocks
> narrowhg. An alternative approach (which I may do as part of the
> mentioned refactoring) would be to construct *all* dirlog instances up
> front, so that we don't have to keep track of the linkmapper
> method. This would avoid a reference cycle between the bundlemanifest
> and the bundlerepository, but I was hesitant to do all the work up
> front like that.
>
> diff --git a/mercurial/bundlerepo.py b/mercurial/bundlerepo.py
> --- a/mercurial/bundlerepo.py
> +++ b/mercurial/bundlerepo.py
> @@ -187,10 +187,12 @@ class bundlechangelog(bundlerevlog, chan
>              self.filteredrevs = oldfilter
>
>  class bundlemanifest(bundlerevlog, manifest.manifest):
> -    def __init__(self, opener, bundle, linkmapper):
> -        manifest.manifest.__init__(self, opener)
> +    def __init__(self, opener, bundle, linkmapper, dirlogstarts, dir=''):
> +        manifest.manifest.__init__(self, opener, dir=dir)
>          bundlerevlog.__init__(self, opener, self.indexfile, bundle,
>                                linkmapper)
> +        self._dirlogstarts = dirlogstarts
> +        self.linkmapper = linkmapper
>
>      def baserevision(self, nodeorrev):
>          node = nodeorrev
> @@ -203,6 +205,14 @@ class bundlemanifest(bundlerevlog, manif
>              result = manifest.manifest.revision(self, nodeorrev)
>          return result
>
> +    def dirlog(self, d):
> +        if d in self._dirlogstarts:
> +            self.bundle.seek(self._dirlogstarts[d])
> +            return bundlemanifest(
> +                self.opener, self.bundle, self.linkmapper,
> +                self._dirlogstarts, dir=d)
> +        return super(bundlemanifest, self).dirlog(d)
> +
>  class bundlefilelog(bundlerevlog, filelog.filelog):
>      def __init__(self, opener, path, bundle, linkmapper):
>          filelog.filelog.__init__(self, opener, path)
> @@ -304,6 +314,8 @@ class bundlerepository(localrepo.localre
>                                                                  bundlename,
>                                                                  self.vfs)
>
> +        # map dirlog name to position in the bundle
> +        self.bundledirstarts = {} # type: Dict[bytes, int]
>          # dict with the mapping 'filename' -> position in the bundle
>          self.bundlefilespos = {}
>
> @@ -329,11 +341,16 @@ class bundlerepository(localrepo.localre
>          # consume the header if it exists
>          self.bundle.manifestheader()
>          linkmapper = self.unfiltered().changelog.rev
> -        m = bundlemanifest(self.svfs, self.bundle, linkmapper)
> -        # XXX: hack to work with changegroup3, but we still don't handle
> -        # tree manifests correctly
> +        dirlogstarts = {}
> +        # Note slight spooky action here: we pass in the dirlogstarts
> +        # dict and fill it in *after* running the constructor. This is
> +        # horrible.
> +        m = bundlemanifest(self.svfs, self.bundle, linkmapper, dirlogstarts)

Can the stuff below be moved into bundlemanifest to avoid the spookiness?

>          if self.bundle.version == "03":
> -            self.bundle.filelogheader()
> +            for dirheader in iter(self.bundle.filelogheader, {}):
> +                d = dirheader["filename"]
> +                dirlogstarts[d] = self.bundle.tell()
> +                _discarddeltachunks(self.bundle)
>          self.filestart = self.bundle.tell()
>          return m
>
> diff --git a/mercurial/manifest.py b/mercurial/manifest.py
> --- a/mercurial/manifest.py
> +++ b/mercurial/manifest.py
> @@ -913,7 +913,7 @@ class manifest(revlog.revlog):
>          self._usemanifestv2 = usemanifestv2
>          indexfile = "00manifest.i"
>          if dir:
> -            assert self._treeondisk
> +            assert self._treeondisk, 'opts is %r' % opts
>              if not dir.endswith('/'):
>                  dir = dir + '/'
>              indexfile = "meta/" + dir + "00manifest.i"
> diff --git a/tests/test-treemanifest.t b/tests/test-treemanifest.t
> --- a/tests/test-treemanifest.t
> +++ b/tests/test-treemanifest.t
> @@ -326,6 +326,25 @@ Stripping and recovering changes should
>       rev    offset  length  delta linkrev nodeid       p1           p2
>         0         0     127     -1       4 064927a0648a 000000000000 000000000000
>         1       127     111      0       5 25ecb8cb8618 000000000000 000000000000
> +  $ hg incoming --traceback .hg/strip-backup/*

Drop --traceback?

> +  comparing with .hg/strip-backup/*-backup.hg (glob)
> +  searching for changes
> +  changeset:   6:51cfd7b1e13b
> +  tag:         tip
> +  user:        test
> +  date:        Thu Jan 01 00:00:00 1970 +0000
> +  summary:     modify dir1/a
> +
> +  $ hg pull .hg/strip-backup/*
> +  pulling from .hg/strip-backup/51cfd7b1e13b-78a2f3ed-backup.hg
> +  searching for changes
> +  adding changesets
> +  adding manifests
> +  adding file changes
> +  added 1 changesets with 1 changes to 1 files
> +  (run 'hg update' to get a working copy)
> +  $ hg --config extensions.strip= strip tip
> +  saved backup bundle to $TESTTMP/repo-mixed/.hg/strip-backup/*-backup.hg (glob)
>    $ hg unbundle -q .hg/strip-backup/*
>    $ hg debugindex --dir dir1
>       rev    offset  length  delta linkrev nodeid       p1           p2
> _______________________________________________
> Mercurial-devel mailing list
> Mercurial-devel at mercurial-scm.org
> https://www.mercurial-scm.org/mailman/listinfo/mercurial-devel