D4011: changegroup: move file matcher from narrow extension

[indygreg (Gregory Szorc)]

indygreg created this revision.
Herald added a reviewer: durin42.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.

REVISION SUMMARY
  Sparse changegroup generation requires the use of a matcher to
  filter which files are relevant.
  
  This commit moves the file matcher from the narrow extension to core
  and updates the narrow extension to use it.
  
  I'm not sure why the narrow extension was storing the matcher as
  a callable that resolved to a matcher. So I changed it to be a
  simple matcher instance.
  
  In addition, code from narrow to intersect the matcher with the local
  narrow spec is now performed automatically when the changegroup
  packer is created.
  
  If a matcher is not passed into getbundler() an alwaysmatcher() is
  assumed. This ensures that a matcher is always defined for all
  operations.

REPOSITORY
  rHG Mercurial

REVISION DETAIL
  https://phab.mercurial-scm.org/D4011

AFFECTED FILES
  hgext/narrow/narrowbundle2.py
  hgext/narrow/narrowchangegroup.py
  mercurial/changegroup.py

CHANGE DETAILS

diff --git a/mercurial/changegroup.py b/mercurial/changegroup.py
--- a/mercurial/changegroup.py
+++ b/mercurial/changegroup.py
@@ -21,6 +21,7 @@
 from . import (
     dagutil,
     error,
+    match as matchmod,
     mdiff,
     phases,
     pycompat,
@@ -496,14 +497,20 @@
 class cg1packer(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     version = '01'
-    def __init__(self, repo, bundlecaps=None):
+    def __init__(self, repo, filematcher, bundlecaps=None):
         """Given a source repo, construct a bundler.
 
+        filematcher is a matcher that matches on files to include in the
+        changegroup. Used to facilitate sparse changegroups.
+
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle. While bundlecaps is
         unused in core Mercurial, extensions rely on this feature to communicate
         capabilities to customize the changegroup packer.
         """
+        assert filematcher
+        self._filematcher = filematcher
+
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
@@ -813,8 +820,10 @@
     version = '02'
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
 
-    def __init__(self, repo, bundlecaps=None):
-        super(cg2packer, self).__init__(repo, bundlecaps)
+    def __init__(self, repo, filematcher, bundlecaps=None):
+        super(cg2packer, self).__init__(repo, filematcher,
+                                        bundlecaps=bundlecaps)
+
         if self._reorder is None:
             # Since generaldelta is directly supported by cg2, reordering
             # generally doesn't help, so we disable it by default (treating
@@ -927,9 +936,23 @@
     assert versions
     return min(versions)
 
-def getbundler(version, repo, bundlecaps=None):
+def getbundler(version, repo, bundlecaps=None, filematcher=None):
     assert version in supportedoutgoingversions(repo)
-    return _packermap[version][0](repo, bundlecaps)
+
+    if filematcher is None:
+        filematcher = matchmod.alwaysmatcher(repo.root, '')
+
+    if version == '01' and not filematcher.always():
+        raise error.ProgrammingError('version 01 changegroups do not support '
+                                     'sparse file matchers')
+
+    # Requested files could include files not in the local store. So
+    # filter those out.
+    filematcher = matchmod.intersectmatchers(repo.narrowmatch(),
+                                             filematcher)
+
+    return _packermap[version][0](repo, filematcher=filematcher,
+                                  bundlecaps=bundlecaps)
 
 def getunbundler(version, fh, alg, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
@@ -950,8 +973,9 @@
                         {'clcount': len(outgoing.missing) })
 
 def makestream(repo, outgoing, version, source, fastpath=False,
-               bundlecaps=None):
-    bundler = getbundler(version, repo, bundlecaps=bundlecaps)
+               bundlecaps=None, filematcher=None):
+    bundler = getbundler(version, repo, bundlecaps=bundlecaps,
+                         filematcher=filematcher)
 
     repo = repo.unfiltered()
     commonrevs = outgoing.common
diff --git a/hgext/narrow/narrowchangegroup.py b/hgext/narrow/narrowchangegroup.py
--- a/hgext/narrow/narrowchangegroup.py
+++ b/hgext/narrow/narrowchangegroup.py
@@ -13,38 +13,26 @@
     error,
     extensions,
     manifest,
-    match as matchmod,
     mdiff,
     node,
     revlog,
     util,
 )
 
 def setup():
-
-    def _cgmatcher(cgpacker):
-        localmatcher = cgpacker._repo.narrowmatch()
-        remotematcher = getattr(cgpacker, '_narrow_matcher', lambda: None)()
-        if remotematcher:
-            return matchmod.intersectmatchers(localmatcher, remotematcher)
-        else:
-            return localmatcher
-
     def prune(orig, self, revlog, missing, commonrevs):
         if isinstance(revlog, manifest.manifestrevlog):
-            matcher = _cgmatcher(self)
-            if (matcher and
-                not matcher.visitdir(revlog._dir[:-1] or '.')):
+            if not self._filematcher.visitdir(revlog._dir[:-1] or '.'):
                 return []
+
         return orig(self, revlog, missing, commonrevs)
 
     extensions.wrapfunction(changegroup.cg1packer, 'prune', prune)
 
     def generatefiles(orig, self, changedfiles, linknodes, commonrevs,
                       source):
-        matcher = _cgmatcher(self)
-        if matcher:
-            changedfiles = list(filter(matcher, changedfiles))
+        changedfiles = list(filter(self._filematcher, changedfiles))
+
         if getattr(self, 'is_shallow', False):
             # See comment in generate() for why this sadness is a thing.
             mfdicts = self._mfdicts
diff --git a/hgext/narrow/narrowbundle2.py b/hgext/narrow/narrowbundle2.py
--- a/hgext/narrow/narrowbundle2.py
+++ b/hgext/narrow/narrowbundle2.py
@@ -60,10 +60,8 @@
     # set, we know we have an ellipsis node and we should defer
     # sending that node's data. We override close() to detect
     # pending ellipsis nodes and flush them.
-    packer = changegroup.getbundler(version, repo)
-    # Let the packer have access to the narrow matcher so it can
-    # omit filelogs and dirlogs as needed
-    packer._narrow_matcher = lambda : match
+    packer = changegroup.getbundler(version, repo,
+                                    filematcher=match)
     # Give the packer the list of nodes which should not be
     # ellipsis nodes. We store this rather than the set of nodes
     # that should be an ellipsis because for very large histories
@@ -107,13 +105,9 @@
         outgoing = exchange._computeoutgoing(repo, heads, common)
         if not outgoing.missing:
             return
-        def wrappedgetbundler(orig, *args, **kwargs):
-            bundler = orig(*args, **kwargs)
-            bundler._narrow_matcher = lambda : newmatch
-            return bundler
-        with extensions.wrappedfunction(changegroup, 'getbundler',
-                                        wrappedgetbundler):
-            cg = changegroup.makestream(repo, outgoing, version, source)
+
+        cg = changegroup.makestream(repo, outgoing, version, source,
+                                    filematcher=newmatch)
         part = bundler.newpart('changegroup', data=cg)
         part.addparam('version', version)
         if 'treemanifest' in repo.requirements:



To: indygreg, durin42, #hg-reviewers
Cc: mercurial-devel