[RFC] Applying a graft to a tree and "rippling" the changes through the history

I've written a tool that will take a single commit, add it as a parent of another commit, and recreate the history above that second commit in a fully compatible manner.

This is mostly useful for creating a fully merged-up repository of the Linux Historical tree, and the current working tree.

I run this with /graft-ripple.pl linux-history.tmp/ linus origin

Where "origin" is the branch the historical repository is on, and "linus" is the branch the current repository is on.

Note: This does not end up fixing up HEAD or any branches, it just pulls
all the objects together and recreates the full history.

GPLv2, but I'll redo with a proper patch, signed-off-by, command line options and help and docs if anyone else feels this is useful as a general tool.

========= cut here =============

#!/usr/bin/perl

use strict; use warnings;

use Data::Dumper; use IPC::Open2;

sub git_commit_tree {
        my ($tree,$comments,@parents) = @_;

        my @cparents;
        foreach my $p (@parents) {
                push @cparents,"-p",$p;
        }

        my $pid = open2(*Reader, *Writer,
		"git-commit-tree",$tree,@cparents);
        print Writer $comments;
        close(Writer);
        my $commit = <Reader>;

        waitpid $pid, 0;
        close(Reader);

        chomp $commit;

        return $commit;
}

chdir($ARGV[0]);
open(GRL,"-|","git-rev-list","--parents",$ARGV[1])
	or die "Failed to run git-rev-list: " . $!;

my %csets;
my @revs;
while(<GRL>) {
	chomp;
	my ($commit,@parents) = split /\s+/;
	$csets{$commit}{parents} = \@parents;
	push @revs, $commit;

	open(GCF,"-|","git-cat-file","commit",$commit)
		or die "Failed to open git-cat-file: " . $!;

	my $in_comments = 0;
	while(<GCF>) {
		chomp;
		if ($in_comments) {
			$csets{$commit}{comments} .= $_ . "\n";

		} elsif (m/^tree (.+)$/) {
			$csets{$commit}{tree} = $1;
			#printf("tree = %s\n",$1);

		} elsif (m/^parent (.+)$/) {
			# Do nothing, we already got
			# the parents from rev-list.

		} elsif (m/^(author|committer) (.*) <(.*)> (.*)$/) {
			#printf("%s = %s <%s> at %s\n",$1, $2,$3,$4);
			@{$csets{$commit}{$1}}{qw(name email datetime)}
				= ($2,$3,$4);

		} elsif (length == 0) {
			$in_comments = 1;
			$csets{$commit}{comments} = "";
			next;
		}
	}
	close(GCF);

} close(GRL);

@revs = reverse @revs; push @{$csets{$revs[0]}{parents}},$ARGV[2];

my %newcsets;
foreach my $old (@revs) {
	printf("Processing commit %s\n",$old);
        $ENV{GIT_AUTHOR_EMAIL} = $csets{$old}{author}{email};
        $ENV{GIT_AUTHOR_NAME} = $csets{$old}{author}{name};
        $ENV{GIT_AUTHOR_DATE} = $csets{$old}{author}{datetime};
        $ENV{GIT_COMMITTER_DATE} = $csets{$old}{committer}{datetime};
        $ENV{GIT_COMMITTER_EMAIL} = $csets{$old}{committer}{email};
        $ENV{GIT_COMMITTER_NAME} = $csets{$old}{committer}{name};

	my @parents = @{$csets{$old}{parents}};
	foreach my $p (@{$csets{$old}{parents}}) {
		if (exists $newcsets{$p}) {
			push @parents, $newcsets{$p}
				if exists $newcsets{$p};
			printf("Found new csetid %s for %s\n",
				$newcsets{$p},$p);
		}
	}
        my $commit = git_commit_tree($csets{$old}{tree},
		$csets{$old}{comments},@parents);
	$newcsets{$old} = $commit;
        printf("Commit for version %s is %s\n",$old,$newcsets{$old});
}