git/git-cvsimport-script

#!/usr/bin/perl -w

# This tool is copyright (c) 2005, Matthias Urlichs.
# It is released under the Gnu Public License, version 2.
#
# The basic idea is to aggregate CVS check-ins into related changes.
# Fortunately, "cvsps" does that for us; all we have to do is to parse
# its output.
#
# Checking out the files is done by a single long-running CVS connection
# / server process.
#
# The head revision is on branch "origin" by default.
# You can change that with the '-o' option.

use strict;
use warnings;
use Getopt::Std;
use File::Path qw(mkpath);
use File::Basename qw(basename dirname);
use Time::Local;
use IO::Socket;
use IO::Pipe;
use POSIX qw(strftime dup2);

$SIG{'PIPE'}="IGNORE";
$ENV{'TZ'}="UTC";

our($opt_h,$opt_o,$opt_v,$opt_d,$opt_p,$opt_C);

sub usage() {
	print STDERR <<END;
Usage: ${\basename $0}     # fetch/update GIT from CVS
	   [ -o branch-for-HEAD ] [ -h ] [ -v ] [ -d CVSROOT ]
       [ -p opts-for-cvsps ] [ -C GIT_repository ]
       [ CVS_module ]
END
	exit(1);
}

getopts("hqvo:d:p:C:") or usage();
usage if $opt_h;

@ARGV <= 1 or usage();

if($opt_d) {
	$ENV{"CVSROOT"} = $opt_d;
} elsif(-f 'CVS/Root') {
	open my $f, '<', 'CVS/Root' or die 'Failed to open CVS/Root';
	$opt_d = <$f>;
	chomp $opt_d;
	close $f;
	$ENV{"CVSROOT"} = $opt_d;
} elsif($ENV{"CVSROOT"}) {
	$opt_d = $ENV{"CVSROOT"};
} else {
	die "CVSROOT needs to be set";
}
$opt_o ||= "origin";
my $git_tree = $opt_C;
$git_tree ||= ".";

my $cvs_tree;
if ($#ARGV == 0) {
	$cvs_tree = $ARGV[0];
} elsif (-f 'CVS/Repository') {
	open my $f, '<', 'CVS/Repository' or 
	    die 'Failed to open CVS/Repository';
	$cvs_tree = <$f>;
	chomp $cvs_tree;
	close $f
} else {
	usage();
}

select(STDERR); $|=1; select(STDOUT);


package CVSconn;
# Basic CVS dialog.
# We're only interested in connecting and downloading, so ...

use File::Spec;
use File::Temp qw(tempfile);
use POSIX qw(strftime dup2);

sub new {
	my($what,$repo,$subdir) = @_;
	$what=ref($what) if ref($what);

	my $self = {};
	$self->{'buffer'} = "";
	bless($self,$what);

	$repo =~ s#/+$##;
	$self->{'fullrep'} = $repo;
	$self->conn();

	$self->{'subdir'} = $subdir;
	$self->{'lines'} = undef;

	return $self;
}

sub conn {
	my $self = shift;
	my $repo = $self->{'fullrep'};
	if($repo =~ s/^:pserver:(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) {
		my($user,$pass,$serv,$port) = ($1,$2,$3,$4);
		$user="anonymous" unless defined $user;
		my $rr2 = "-";
		unless($port) {
			$rr2 = ":pserver:$user\@$serv:$repo";
			$port=2401;
		}
		my $rr = ":pserver:$user\@$serv:$port$repo";

		unless($pass) {
			open(H,$ENV{'HOME'}."/.cvspass") and do {
				# :pserver:cvs@mea.tmt.tele.fi:/cvsroot/zmailer Ah<Z
				while(<H>) {
					chomp;
					s/^\/\d+\s+//;
					my ($w,$p) = split(/\s/,$_,2);
					if($w eq $rr or $w eq $rr2) {
						$pass = $p;
						last;
					}
				}
			};
		}
		$pass="A" unless $pass;

		my $s = IO::Socket::INET->new(PeerHost => $serv, PeerPort => $port);
		die "Socket to $serv: $!\n" unless defined $s;
		$s->write("BEGIN AUTH REQUEST\n$repo\n$user\n$pass\nEND AUTH REQUEST\n")
			or die "Write to $serv: $!\n";
		$s->flush();

		my $rep = <$s>;

		if($rep ne "I LOVE YOU\n") {
			$rep="<unknown>" unless $rep;
			die "AuthReply: $rep\n";
		}
		$self->{'socketo'} = $s;
		$self->{'socketi'} = $s;
	} else { # local or ext: Fork off our own cvs server.
		my $pr = IO::Pipe->new();
		my $pw = IO::Pipe->new();
		my $pid = fork();
		die "Fork: $!\n" unless defined $pid;
		my $cvs = 'cvs';
		$cvs = $ENV{CVS_SERVER} if exists $ENV{CVS_SERVER};
		my $rsh = 'rsh';
		$rsh = $ENV{CVS_RSH} if exists $ENV{CVS_RSH};

		my @cvs = ($cvs, 'server');
		my ($local, $user, $host);
		$local = $repo =~ s/:local://;
		if (!$local) {
		    $repo =~ s/:ext://;
		    $local = !($repo =~ s/^(?:([^\@:]+)\@)?([^:]+)://);
		    ($user, $host) = ($1, $2);
		}
		if (!$local) {
		    if ($user) {
			unshift @cvs, $rsh, '-l', $user, $host;
		    } else {
			unshift @cvs, $rsh, $host;
		    }
		}

		unless($pid) {
			$pr->writer();
			$pw->reader();
			dup2($pw->fileno(),0);
			dup2($pr->fileno(),1);
			$pr->close();
			$pw->close();
			exec(@cvs);
		}
		$pw->writer();
		$pr->reader();
		$self->{'socketo'} = $pw;
		$self->{'socketi'} = $pr;
	}
	$self->{'socketo'}->write("Root $repo\n");

	# Trial and error says that this probably is the minimum set
	$self->{'socketo'}->write("Valid-responses ok error Valid-requests Mode M Mbinary E F Checked-in Created Updated Merged Removed\n");

	$self->{'socketo'}->write("valid-requests\n");
	$self->{'socketo'}->flush();

	chomp(my $rep=$self->readline());
	if($rep !~ s/^Valid-requests\s*//) {
		$rep="<unknown>" unless $rep;
		die "Expected Valid-requests from server, but got: $rep\n";
	}
	chomp(my $res=$self->readline());
	die "validReply: $res\n" if $res ne "ok";

	$self->{'socketo'}->write("UseUnchanged\n") if $rep =~ /\bUseUnchanged\b/;
	$self->{'repo'} = $repo;
}

sub readline {
	my($self) = @_;
	return $self->{'socketi'}->getline();
}

sub _file {
	# Request a file with a given revision.
	# Trial and error says this is a good way to do it. :-/
	my($self,$fn,$rev) = @_;
	$self->{'socketo'}->write("Argument -N\n") or return undef;
	$self->{'socketo'}->write("Argument -P\n") or return undef;
	# $self->{'socketo'}->write("Argument -ko\n") or return undef;
	# -ko: Linus' version doesn't use it
	$self->{'socketo'}->write("Argument -r\n") or return undef;
	$self->{'socketo'}->write("Argument $rev\n") or return undef;
	$self->{'socketo'}->write("Argument --\n") or return undef;
	$self->{'socketo'}->write("Argument $self->{'subdir'}/$fn\n") or return undef;
	$self->{'socketo'}->write("Directory .\n") or return undef;
	$self->{'socketo'}->write("$self->{'repo'}\n") or return undef;
	# $self->{'socketo'}->write("Sticky T1.0\n") or return undef;
	$self->{'socketo'}->write("co\n") or return undef;
	$self->{'socketo'}->flush() or return undef;
	$self->{'lines'} = 0;
	return 1;
}
sub _line {
	# Read a line from the server.
	# ... except that 'line' may be an entire file. ;-)
	my($self, $fh) = @_;
	die "Not in lines" unless defined $self->{'lines'};

	my $line;
	my $res=0;
	while(defined($line = $self->readline())) {
		# M U gnupg-cvs-rep/AUTHORS
		# Updated gnupg-cvs-rep/
		# /daten/src/rsync/gnupg-cvs-rep/AUTHORS
		# /AUTHORS/1.1///T1.1
		# u=rw,g=rw,o=rw
		# 0
		# ok

		if($line =~ s/^(?:Created|Updated) //) {
			$line = $self->readline(); # path
			$line = $self->readline(); # Entries line
			my $mode = $self->readline(); chomp $mode;
			$self->{'mode'} = $mode;
			defined (my $cnt = $self->readline())
				or die "EOF from server after 'Changed'\n";
			chomp $cnt;
			die "Duh: Filesize $cnt" if $cnt !~ /^\d+$/;
			$line="";
			$res=0;
			while($cnt) {
				my $buf;
				my $num = $self->{'socketi'}->read($buf,$cnt);
				die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
				print $fh $buf;
				$res += $num;
				$cnt -= $num;
			}
		} elsif($line =~ s/^ //) {
			print $fh $line;
			$res += length($line);
		} elsif($line =~ /^M\b/) {
			# output, do nothing
		} elsif($line =~ /^Mbinary\b/) {
			my $cnt;
			die "EOF from server after 'Mbinary'" unless defined ($cnt = $self->readline());
			chomp $cnt;
			die "Duh: Mbinary $cnt" if $cnt !~ /^\d+$/ or $cnt<1;
			$line="";
			while($cnt) {
				my $buf;
				my $num = $self->{'socketi'}->read($buf,$cnt);
				die "S: Mbinary $cnt: $num: $!\n" if not defined $num or $num<=0;
				print $fh $buf;
				$res += $num;
				$cnt -= $num;
			}
		} else {
			chomp $line;
			if($line eq "ok") {
				# print STDERR "S: ok (".length($res).")\n";
				return $res;
			} elsif($line =~ s/^E //) {
				# print STDERR "S: $line\n";
			} else {
				die "Unknown: $line\n";
			}
		}
	}
}
sub file {
	my($self,$fn,$rev) = @_;
	my $res;

	my ($fh, $name) = tempfile('gitcvs.XXXXXX', 
		    DIR => File::Spec->tmpdir(), UNLINK => 1);

	$self->_file($fn,$rev) and $res = $self->_line($fh);

	if (!defined $res) {
	    # retry
	    $self->conn();
	    $self->_file($fn,$rev)
		    or die "No file command send\n";
	    $res = $self->_line($fh);
	    die "No input: $fn $rev\n" unless defined $res;
	}

	return ($name, $res);
}


package main;

my $cvs = CVSconn->new($opt_d, $cvs_tree);


sub pdate($) {
	my($d) = @_;
	m#(\d{2,4})/(\d\d)/(\d\d)\s(\d\d):(\d\d)(?::(\d\d))?#
		or die "Unparseable date: $d\n";
	my $y=$1; $y-=1900 if $y>1900;
	return timegm($6||0,$5,$4,$3,$2-1,$y);
}

sub pmode($) {
	my($mode) = @_;
	my $m = 0;
	my $mm = 0;
	my $um = 0;
	for my $x(split(//,$mode)) {
		if($x eq ",") {
			$m |= $mm&$um;
			$mm = 0;
			$um = 0;
		} elsif($x eq "u") { $um |= 0700;
		} elsif($x eq "g") { $um |= 0070;
		} elsif($x eq "o") { $um |= 0007;
		} elsif($x eq "r") { $mm |= 0444;
		} elsif($x eq "w") { $mm |= 0222;
		} elsif($x eq "x") { $mm |= 0111;
		} elsif($x eq "=") { # do nothing
		} else { die "Unknown mode: $mode\n";
		}
	}
	$m |= $mm&$um;
	return $m;
}

my $tmpcv = "/var/cache/cvs";

sub getwd() {
	my $pwd = `pwd`;
	chomp $pwd;
	return $pwd;
}

-d $git_tree
	or mkdir($git_tree,0777)
	or die "Could not create $git_tree: $!";
chdir($git_tree);

my $last_branch = "";
my $orig_branch = "";
my %branch_date;

my $git_dir = $ENV{"GIT_DIR"} || ".git";
$git_dir = getwd()."/".$git_dir unless $git_dir =~ m#^/#;
$ENV{"GIT_DIR"} = $git_dir;
unless(-d $git_dir) {
	system("git-init-db");
	die "Cannot init the GIT db at $git_tree: $?\n" if $?;
	system("git-read-tree");
	die "Cannot init an empty tree: $?\n" if $?;

	$last_branch = $opt_o;
	$orig_branch = "";
} else {
	-f "$git_dir/refs/heads/$opt_o"
		or die "Branch '$opt_o' does not exist.\n".
		       "Either use the correct '-o branch' option,\n".
		       "or import to a new repository.\n";

	$last_branch = basename(readlink("$git_dir/HEAD"));
	unless($last_branch) {
		warn "Cannot read the last branch name: $! -- assuming 'master'\n";
		$last_branch = "master";
	}
	$orig_branch = $last_branch;

	# Get the last import timestamps
	opendir(D,"$git_dir/refs/heads");
	while(defined(my $head = readdir(D))) {
		next if $head =~ /^\./;
		open(F,"$git_dir/refs/heads/$head")
			or die "Bad head branch: $head: $!\n";
		chomp(my $ftag = <F>);
		close(F);
		open(F,"git-cat-file commit $ftag |");
		while(<F>) {
			next unless /^author\s.*\s(\d+)\s[-+]\d{4}$/;
			$branch_date{$head} = $1;
			last;
		}
		close(F);
	}
	closedir(D);
}

-d $git_dir
	or die "Could not create git subdir ($git_dir).\n";

my $pid = open(CVS,"-|");
die "Cannot fork: $!\n" unless defined $pid;
unless($pid) {
	my @opt;
	@opt = split(/,/,$opt_p) if defined $opt_p;
	exec("cvsps",@opt,"-x","-A","--cvs-direct",'--root',$opt_d,$cvs_tree);
	die "Could not start cvsps: $!\n";
}


## cvsps output:
#---------------------
#PatchSet 314
#Date: 1999/09/18 13:03:59
#Author: wkoch
#Branch: STABLE-BRANCH-1-0
#Ancestor branch: HEAD
#Tag: (none)
#Log:
#    See ChangeLog: Sat Sep 18 13:03:28 CEST 1999  Werner Koch
#Members:
#	README:1.57->1.57.2.1
#	VERSION:1.96->1.96.2.1
#
#---------------------

my $state = 0;

my($patchset,$date,$author,$branch,$ancestor,$tag,$logmsg);
my(@old,@new);
my $commit = sub {
	my $pid;
	while(@old) {
		my @o2;
		if(@old > 55) {
			@o2 = splice(@old,0,50);
		} else {
			@o2 = @old;
			@old = ();
		}
		system("git-update-cache","--force-remove","--",@o2);
		die "Cannot remove files: $?\n" if $?;
	}
	while(@new) {
		my @n2;
		if(@new > 12) {
			@n2 = splice(@new,0,10);
		} else {
			@n2 = @new;
			@new = ();
		}
		system("git-update-cache","--add",
			(map { ('--cacheinfo', @$_) } @n2));
		die "Cannot add files: $?\n" if $?;
	}

	$pid = open(C,"-|");
	die "Cannot fork: $!" unless defined $pid;
	unless($pid) {
		exec("git-write-tree");
		die "Cannot exec git-write-tree: $!\n";
	}
	chomp(my $tree = <C>);
	length($tree) == 40
		or die "Cannot get tree id ($tree): $!\n";
	close(C)
		or die "Error running git-write-tree: $?\n";
	print "Tree ID $tree\n" if $opt_v;

	my $parent = "";
	if(open(C,"$git_dir/refs/heads/$last_branch")) {
		chomp($parent = <C>);
		close(C);
		length($parent) == 40
			or die "Cannot get parent id ($parent): $!\n";
		print "Parent ID $parent\n" if $opt_v;
	}

	my $pr = IO::Pipe->new();
	my $pw = IO::Pipe->new();
	$pid = fork();
	die "Fork: $!\n" unless defined $pid;
	unless($pid) {
		$pr->writer();
		$pw->reader();
		dup2($pw->fileno(),0);
		dup2($pr->fileno(),1);
		$pr->close();
		$pw->close();

		my @par = ();
		@par = ("-p",$parent) if $parent;
		exec("env",
			"GIT_AUTHOR_NAME=$author",
			"GIT_AUTHOR_EMAIL=$author",
			"GIT_AUTHOR_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
			"GIT_COMMITTER_NAME=$author",
			"GIT_COMMITTER_EMAIL=$author",
			"GIT_COMMITTER_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
			"git-commit-tree", $tree,@par);
		die "Cannot exec git-commit-tree: $!\n";
	}
	$pw->writer();
	$pr->reader();

	# compatibility with git2cvs
	substr($logmsg,32767) = "" if length($logmsg) > 32767;
	$logmsg =~ s/[\s\n]+\z//;

	print $pw "$logmsg\n"
		or die "Error writing to git-commit-tree: $!\n";
	$pw->close();

	print "Committed patch $patchset ($branch)\n" if $opt_v;
	chomp(my $cid = <$pr>);
	length($cid) == 40
		or die "Cannot get commit id ($cid): $!\n";
	print "Commit ID $cid\n" if $opt_v;
	$pr->close();

	waitpid($pid,0);
	die "Error running git-commit-tree: $?\n" if $?;

	open(C,">$git_dir/refs/heads/$branch")
		or die "Cannot open branch $branch for update: $!\n";
	print C "$cid\n"
		or die "Cannot write branch $branch for update: $!\n";
	close(C)
		or die "Cannot write branch $branch for update: $!\n";

	if($tag) {
		open(C,">$git_dir/refs/tags/$tag")
			or die "Cannot create tag $tag: $!\n";
		print C "$cid\n"
			or die "Cannot write tag $branch: $!\n";
		close(C)
			or die "Cannot write tag $branch: $!\n";
		print "Created tag '$tag' on '$branch'\n" if $opt_v;
	}
};

while(<CVS>) {
	chomp;
	if($state == 0 and /^-+$/) {
		$state = 1;
	} elsif($state == 0) {
		$state = 1;
		redo;
	} elsif(($state==0 or $state==1) and s/^PatchSet\s+//) {
		$patchset = 0+$_;
		$state=2;
	} elsif($state == 2 and s/^Date:\s+//) {
		$date = pdate($_);
		unless($date) {
			print STDERR "Could not parse date: $_\n";
			$state=0;
			next;
		}
		$state=3;
	} elsif($state == 3 and s/^Author:\s+//) {
		s/\s+$//;
		$author = $_;
		$state = 4;
	} elsif($state == 4 and s/^Branch:\s+//) {
		s/\s+$//;
		$branch = $_;
		$state = 5;
	} elsif($state == 5 and s/^Ancestor branch:\s+//) {
		s/\s+$//;
		$ancestor = $_;
		$ancestor = $opt_o if $ancestor eq "HEAD";
		$state = 6;
	} elsif($state == 5) {
		$ancestor = undef;
		$state = 6;
		redo;
	} elsif($state == 6 and s/^Tag:\s+//) {
		s/\s+$//;
		if($_ eq "(none)") {
			$tag = undef;
		} else {
			$tag = $_;
		}
		$state = 7;
	} elsif($state == 7 and /^Log:/) {
		$logmsg = "";
		$state = 8;
	} elsif($state == 8 and /^Members:/) {
		$branch = $opt_o if $branch eq "HEAD";
		if(defined $branch_date{$branch} and $branch_date{$branch} >= $date) {
			# skip
			print "skip patchset $patchset: $date before $branch_date{$branch}\n" if $opt_v;
			$state = 11;
			next;
		}
		if($ancestor) {
			if(-f "$git_dir/refs/heads/$branch") {
				print STDERR "Branch $branch already exists!\n";
				$state=11;
				next;
			}
			unless(open(H,"$git_dir/refs/heads/$ancestor")) {
				print STDERR "Branch $ancestor does not exist!\n";
				$state=11;
				next;
			}
			chomp(my $id = <H>);
			close(H);
			unless(open(H,"> $git_dir/refs/heads/$branch")) {
				print STDERR "Could not create branch $branch: $!\n";
				$state=11;
				next;
			}
			print H "$id\n"
				or die "Could not write branch $branch: $!";
			close(H)
				or die "Could not write branch $branch: $!";
		}
		if(($ancestor || $branch) ne $last_branch) {
			print "Switching from $last_branch to $branch\n" if $opt_v;
			system("git-read-tree","-m","$last_branch","$branch");
			die "read-tree failed: $?\n" if $?;
		}
		if($branch ne $last_branch) {
			unlink("$git_dir/HEAD");
			symlink("refs/heads/$branch","$git_dir/HEAD");
			$last_branch = $branch;
		}
		$state = 9;
	} elsif($state == 8) {
		$logmsg .= "$_\n";
	} elsif($state == 9 and /^\s+(\S+):(INITIAL|\d(?:\.\d+)+)->(\d(?:\.\d+)+)\s*$/) {
#	VERSION:1.96->1.96.2.1
		my $init = ($2 eq "INITIAL");
		my $fn = $1;
		my $rev = $3;
		$fn =~ s#^/+##;
		my ($tmpname, $size) = $cvs->file($fn,$rev);
		print "".($init ? "New" : "Update")." $fn: $size bytes.\n" if $opt_v;
		open my $F, '-|', "git-write-blob $tmpname"
			or die "Cannot create object: $!\n";
		my $sha = <$F>;
		chomp $sha;
		close $F;
		unlink($tmpname);
		my $mode = pmode($cvs->{'mode'});
		push(@new,[$mode, $sha, $fn]); # may be resurrected!
	} elsif($state == 9 and /^\s+(\S+):\d(?:\.\d+)+->(\d(?:\.\d+)+)\(DEAD\)\s*$/) {
		my $fn = $1;
		$fn =~ s#^/+##;
		push(@old,$fn);
	} elsif($state == 9 and /^\s*$/) {
		$state = 10;
	} elsif(($state == 9 or $state == 10) and /^-+$/) {
		&$commit();
		$state = 1;
	} elsif($state == 11 and /^-+$/) {
		$state = 1;
	} elsif(/^-+$/) { # end of unknown-line processing
		$state = 1;
	} elsif($state != 11) { # ignore stuff when skipping
		print "* UNKNOWN LINE * $_\n";
	}
}
&$commit() if $branch and $state != 11;

# Now switch back to the branch we were in before all of this happened
if($orig_branch) {
	print "DONE; switching back to $orig_branch\n" if $opt_v;
} else {
	$orig_branch = "master";
	print "DONE; creating $orig_branch branch\n" if $opt_v;
	system("cp","$git_dir/refs/heads/$opt_o","$git_dir/refs/heads/master")
		unless -f "$git_dir/refs/heads/master";
}

if ($orig_branch) {
	system("git-read-tree",$last_branch);
	die "read-tree failed: $?\n" if $?;
} else {
	system('git-read-tree', $orig_branch);
	die "read-tree failed: $?\n" if $?;
	system('git-checkout-cache', '-a');
	die "checkout-cache failed: $?\n" if $?;
}

unlink("$git_dir/HEAD");
symlink("refs/heads/$orig_branch","$git_dir/HEAD");