git-commit-vandalism/git-cvsimport-script
2005-06-28 16:48:40 +02:00

585 lines
14 KiB
Perl
Executable File

#!/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 POSIX qw(strftime);
$SIG{'PIPE'}="IGNORE";
$ENV{'TZ'}="UTC";
our($opt_h,$opt_o,$opt_v);
sub usage() {
print STDERR <<END;
Usage: ${\basename $0} -- fetch/update GIT from CVS
[ -h (help) ]
[ -v (verbose) ] [ -o name-of-HEAD ]
CVS_archive GIT_dest
END
exit(1);
}
getopts("hqvo:") or usage();
usage if $opt_h;
@ARGV == 2 or usage();
$opt_o ||= "origin";
my($cvs_tree, $git_tree) = @ARGV;
select(STDERR); $|=1; select(STDOUT);
package CVSconn;
# Basic CVS dialog.
# We're only interested in downloading files.
sub new {
my($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;
use IO::Socket;
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: Fork off our own cvs server.
use IO::Pipe;
my $pr = IO::Pipe->new();
my $pw = IO::Pipe->new();
my $pid = fork();
die "Fork: $!\n" unless defined $pid;
unless($pid) {
$pr->writer();
$pw->reader();
use POSIX qw(dup2);
dup2($pw->fileno(),0);
dup2($pr->fileno(),1);
$pr->close();
$pw->close();
exec("cvs","server");
}
$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 T1.1\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) = @_;
die "Not in lines" unless defined $self->{'lines'};
my $line;
my $res="";
while(defined($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="";
$res="";
while($cnt) {
my $buf;
my $num = $self->{'socketi'}->read($buf,$cnt);
die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
$res .= $buf;
$cnt -= $num;
}
} elsif($line =~ s/^ //) {
$res .= $line;
} elsif($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;
$res .= $buf;
$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 $res;
if ($self->_file($fn,$rev)) {
$res = $self->_line();
return $res if defined $res;
}
# retry
$self->conn();
$self->_file($fn,$rev)
or die "No file command send\n";
$res = $self->_line();
die "No input: $fn $rev\n" unless defined $res;
return $res;
}
package main;
my $cvs = CVSconn->new(dirname($cvs_tree), basename($cvs_tree));
sub pdate($) {
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 %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;
} else {
$last_branch = basename(readlink("$git_dir/HEAD"));
die "Cannot read the last branch name: $!\n" unless $last_branch;
# Get the last import timestamps
opendir(D,"$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) {
exec("cvsps","-A","--cvs-direct",$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;
system("git-update-cache","--force-remove","--",@old) if @old;
die "Cannot remove files: $?\n" if $?;
system("git-update-cache","--add","--",@new) if @new;
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;
}
pipe(I,O)
or die "No pipe: $!\n";
$pid = open(C,"|-");
die "Cannot fork: $!" unless defined $pid;
unless($pid) {
close(I);
open(STDOUT,">&O");
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";
}
close(O);
print C $logmsg
or die "Error writing to git-commit-tree: $!\n";
close(C)
or die "Error running git-commit-tree: $?\n";
print "Committed patch $patchset ($branch)\n" if $opt_v;
chomp(my $cid = <I>);
length($cid) == 40
or die "Cannot get commit id ($cid): $!\n";
print "Commit ID $cid\n" if $opt_v;
close(I);
open(C,">$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 $opt_v;
}
@old = ();
@new = ();
};
while(<CVS>) {
chomp;
if($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 == "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";
$state = 11;
next;
}
if($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) {
system("git-read-tree -m -u $last_branch $branch");
die "read-tree $branch failed at $branch: $?\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 $fn = $1;
my $data = $cvs->file($fn,$2);
print "Update $fn: ".length($data)." bytes.\n";
mkpath(dirname($fn),$opt_v);
open(F,"> ./$fn")
or die "Cannot create '$fn': $!\n";
print F $data
or die "Cannot write to '$fn': $!\n";
close(F)
or die "Cannot write to '$fn': $!\n";
chmod(pmode($cvs->{'mode'}), $fn);
push(@new,$fn); # may be resurrected!
} elsif($state == 9 and /^\s+(\S+):\d(?:\.\d+)+->(\d(?:\.\d+)+)\(DEAD\)\s*$/) {
push(@old,$1);
} elsif($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;
print "DONE\n" if $opt_v;