[PATCH 5 of 9] localrepo: changegroupsubset collects shallow changeset, manifest and file nodes

[Faheem Mitha]

On Tue, 06 Jul 2010 16:17:04 +0530, Vishakh H <vsh426 at gmail.com> wrote:
> # HG changeset patch
> # User Vishakh H <vsh426 at gmail.com>
> # Date 1278412035 -19800
> # Branch stable
> # Node ID e9de925ecfaf793340e787d8255f3a4571cfb813
> # Parent  b3c06c23e6b618dc4ad6a94036d49c19432c2441
> localrepo: changegroupsubset collects shallow changeset, manifest and file nodes
>
> while generating groups of revisions, we collect the corresponsing nodes

corresponding

> using the collector functions. it is needed to ensure that we dont miss

don't

> nodes that are referenced by more than one changeset.
>
> this is very slow going through all revisions. otoh doing it in _changegroup
> is a bit redundant.
>
> diff --git a/mercurial/localrepo.py b/mercurial/localrepo.py
> --- a/mercurial/localrepo.py
> +++ b/mercurial/localrepo.py
> @@ -1304,7 +1304,7 @@
>              bases = [nullid]
>          msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
>  
> -        if extranodes is None:
> +        if extranodes is None and shallowroot is None:
>              # can we go through the fast path ?
>              heads.sort()
>              allheads = self.heads()
> @@ -1348,6 +1348,15 @@
>          msng_mnfst_set = {}
>          # Nor do we know which filenodes are missing.
>          msng_filenode_set = {}
> +        # revs needed in shallow clone
> +        if shallowroot is not None:
> +            sh_cl = set([shallowroot])
> +            sh_mnfst = [cl.read(shallowroot)[0]]
> +            sh_filenode = {}
> +        else:
> +            sh_cl = None
> +            sh_mnfst = None
> +            sh_filenode = {}
>  
>          junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
>          junk = None
> @@ -1382,7 +1391,9 @@
>              # the first manifest that references it belongs to.
>              def collect_msng_filenodes(mnfstnode):
>                  r = mnfst.rev(mnfstnode)
> -                if r - 1 in mnfst.parentrevs(r):
> +                if extranodes is None and shallowroot is None:
> +                    return
> +                if r - 1 in mnfst.parentrevs(r) and mnfstnode not in sh_mnfst:
>                      # If the previous rev is one of the parents,
>                      # we only need to see a diff.
>                      deltamf = mnfst.readdelta(mnfstnode)
> @@ -1412,6 +1423,10 @@
>                              clnode = msng_mnfst_set[mnfstnode]
>                              ndset = msng_filenode_set.setdefault(f, {})
>                              ndset.setdefault(fnode, clnode)
> +                    if sh_mnfst is not None and mnfstnode in sh_mnfst:
> +                        # Get all important filenodes
> +                        for f in m:
> +                            sh_filenode.setdefault(f, []).append(m[f])
>              return collect_msng_filenodes
>  
>          # We have a list of filenodes we think we need for a file, lets remove
> @@ -1446,12 +1461,19 @@
>                  if node not in nodes:
>                      nodes[node] = linknode
>  
> +        #find nodes to punch
> +        def prune_shallow(nodes, sh_nodes):
> +            if shallowroot is not None:
> +                return [n for n in nodes if n not in sh_nodes]
> +            return None
> +
>          # Now that we have all theses utility functions to help out and
>          # logically divide up the task, generate the group.
>          def gengroup():
>              # The set of changed files starts empty.
>              changedfiles = {}
> -            collect = changegroup.collector(cl, msng_mnfst_set, changedfiles)
> +            collect = changegroup.collector(cl, msng_mnfst_set, changedfiles,
> +                                sh_cl, sh_mnfst)
>  
>              # Create a changenode group generator that will call our functions
>              # back to lookup the owning changenode and collect information.
> @@ -1480,10 +1502,12 @@
>              msng_mnfst_lst = msng_mnfst_set.keys()
>              # Sort the manifestnodes by revision number.
>              msng_mnfst_lst.sort(key=mnfst.rev)
> +            sh_nodes = prune_shallow(msng_mnfst_lst, sh_mnfst)
>              # Create a generator for the manifestnodes that calls our lookup
>              # and data collection functions back.
>              group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
> -                                filenode_collector(changedfiles))
> +                                filenode_collector(changedfiles),
> +                                shallownodes=sh_nodes)
>              cnt = 0
>              for chnk in group:
>                  yield chnk
> @@ -1523,11 +1547,14 @@
>                      yield fname
>                      # Sort the filenodes by their revision #
>                      msng_filenode_lst.sort(key=filerevlog.rev)
> +                    sh_nodes = prune_shallow(msng_filenode_lst,
> +                                             sh_filenode.get(fname, []))
>                      # Create a group generator and only pass in a changenode
>                      # lookup function as we need to collect no information
>                      # from filenodes.
>                      group = filerevlog.group(msng_filenode_lst,
> -                                             lookup_filenode_link_func(fname))
> +                                             lookup_filenode_link_func(fname),
> +                                             shallownodes=sh_nodes)
>                      for chnk in group:
>                          self.ui.progress(
>                              _('bundling files'), cnt, item=fname, unit=_('chunks'))