# HG changeset patch
# User Pulkit Goyal <pulkit@yandex-team.ru>
# Date 2018-09-17 12:55:18
# Node ID c73c7653dfb9a2da91442304529fb3998f7cfb0f
# Parent  322aaf80acf38c9d77fa5b38f1a0ecb650f20959

narrow: use diffmatcher to send only new filelogs in non-ellipses widening

Before this patch, when we widen a non-ellipses narrow clone, we downloads all
the filelogs matching the resulting new matcher. This is same as the ellipses
case but can be improved because, we don't pull new csets in non-ellipses cases,
we can only download the new added files instead of downloading all the files
which matches the new matcher.

So, we only download files which matches the new matcher but does not matches
the old matcher. There exists a match.differencematcher() which is used here.

This will lead to significant amount of speedup in extending a non-ellipses
narrow copy on large repos because we will download and process only the new
required filelogs.

The tests changes demonstrate that we are downloading now less files.

Thanks to Augie for pointing that functionality of differencematcher exists in
core.

Differential Revision: https://phab.mercurial-scm.org/D4614

diff --git a/hgext/narrow/narrowbundle2.py b/hgext/narrow/narrowbundle2.py
--- a/hgext/narrow/narrowbundle2.py
+++ b/hgext/narrow/narrowbundle2.py
@@ -21,6 +21,7 @@ from mercurial import (
     error,
     exchange,
     extensions,
+    match as matchmod,
     narrowspec,
     repair,
     repository,
@@ -72,6 +73,9 @@ def getbundlechangegrouppart_widen(bundl
     newmatch = narrowspec.match(repo.root, include=include, exclude=exclude)
     oldinclude = sorted(filter(bool, kwargs.get(r'oldincludepats', [])))
     oldexclude = sorted(filter(bool, kwargs.get(r'oldexcludepats', [])))
+    oldmatch = narrowspec.match(repo.root, include=oldinclude,
+                                exclude=oldexclude)
+    diffmatch = matchmod.differencematcher(newmatch, oldmatch)
     common = set(common or [nullid])
 
     if (oldinclude != include or oldexclude != exclude):
@@ -84,7 +88,7 @@ def getbundlechangegrouppart_widen(bundl
             # XXX: we should only send the filelogs (and treemanifest). user
             # already has the changelog and manifest
             packer = changegroup.getbundler(version, repo,
-                                            filematcher=newmatch,
+                                            filematcher=diffmatch,
                                             fullnodes=commonnodes)
             cgdata = packer.generate(set([nullid]), list(commonnodes), False,
                     source)
diff --git a/tests/test-narrow-widen-no-ellipsis.t b/tests/test-narrow-widen-no-ellipsis.t
--- a/tests/test-narrow-widen-no-ellipsis.t
+++ b/tests/test-narrow-widen-no-ellipsis.t
@@ -95,7 +95,7 @@ added upstream revisions.
   adding changesets
   adding manifests
   adding file changes
-  added 0 changesets with 1 changes to 2 files
+  added 0 changesets with 1 changes to 1 files
   3 local changesets published
   $ hg tracked
   I path:inside
@@ -154,7 +154,7 @@ widen the narrow spec to include the wid
   adding changesets
   adding manifests
   adding file changes
-  added 0 changesets with 1 changes to 3 files
+  added 0 changesets with 1 changes to 1 files
   5 local changesets published
   $ hg tracked
   I path:inside
@@ -259,7 +259,7 @@ make narrow clone with every third node.
   adding changesets
   adding manifests
   adding file changes
-  added 0 changesets with 1 changes to 5 files
+  added 0 changesets with 1 changes to 1 files
   11 local changesets published
   $ hg tracked
   I path:d0
@@ -351,7 +351,7 @@ Widening that fails can be recovered fro
   adding changesets
   adding manifests
   adding file changes
-  added 0 changesets with 1 changes to 2 files
+  added 0 changesets with 1 changes to 1 files
   11 local changesets published
   $ hg log -T "{if(ellipsis, '...')}{rev}: {desc}\n"
   11: local