git-remote-mediawiki: get rid of O(N^2) loop

The algorithm to find a path from the local revision to the remote one
was calling "git rev-list" and parsing its output N times. Run rev-list
only once, and fill a hashtable with the result to optimize the body of
the loop.

Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki
index 8e46e4e7c710897444bc19b85a77914f76d634d1..fb1e9e09e48d7e473dc3443a2e7d69a43f036e63 100755 (executable)
--- a/contrib/mw-to-git/git-remote-mediawiki
+++ b/contrib/mw-to-git/git-remote-mediawiki
@@ -1196,16 +1196,26 @@ sub mw_push_revision {
        if ($last_local_revid > 0) {
                my $parsed_sha1 = $remoteorigin_sha1;
                # Find a path from last MediaWiki commit to pushed commit
+               print STDERR "Computing path from local to remote ...\n";
+               my @local_ancestry = split(/\n/, run_git("rev-list --boundary --parents $local ^$parsed_sha1"));
+               my %local_ancestry;
+               foreach my $line (@local_ancestry) {
+                       if (my ($child, $parents) = $line =~ m/^-?([a-f0-9]+) ([a-f0-9 ]+)/) {
+                               foreach my $parent (split(' ', $parents)) {
+                                       $local_ancestry{$parent} = $child;
+                               }
+                       } elsif (!$line =~ m/^([a-f0-9]+)/) {
+                               die "Unexpected output from git rev-list: $line";
+                       }
+               }
                while ($parsed_sha1 ne $HEAD_sha1) {
-                       my @commit_info =  grep(/^$parsed_sha1/, split(/\n/, run_git("rev-list --children $local")));
-                       if (!@commit_info) {
+                       my $child = $local_ancestry{$parsed_sha1};
+                       if (!$child) {
+                               printf STDERR "Cannot find a path in history from remote commit to last commit\n";
                                return error_non_fast_forward($remote);
                        }
-                       my @commit_info_split = split(/ |\n/, $commit_info[0]);
-                       # $commit_info_split[1] is the sha1 of the commit to export
-                       # $commit_info_split[0] is the sha1 of its direct child
-                       push(@commit_pairs, \@commit_info_split);
-                       $parsed_sha1 = $commit_info_split[1];
+                       push(@commit_pairs, [$parsed_sha1, $child]);
+                       $parsed_sha1 = $child;
                }
        } else {
                # No remote mediawiki revision. Export the whole