use warnings;
use Getopt::Std;
use File::Spec;
-use File::Temp qw(tempfile);
+use File::Temp qw(tempfile tmpnam);
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);
+use POSIX qw(strftime dup2 ENOENT);
use IPC::Open2;
$SIG{'PIPE'}="IGNORE";
$ENV{'TZ'}="UTC";
-our($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S);
+our ($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L, $opt_a);
my (%conv_author_name, %conv_author_email);
-sub usage() {
+sub usage(;$) {
+ my $msg = shift;
+ print(STDERR "Error: $msg\n") if $msg;
print STDERR <<END;
Usage: ${\basename $0} # fetch/update GIT from CVS
[-o branch-for-HEAD] [-h] [-v] [-d CVSROOT] [-A author-conv-file]
- [-p opts-for-cvsps] [-C GIT_repository] [-z fuzz] [-i] [-k] [-u]
- [-s subst] [-m] [-M regex] [-S regex] [CVS_module]
+ [-p opts-for-cvsps] [-P file] [-C GIT_repository] [-z fuzz] [-i] [-k]
+ [-u] [-s subst] [-a] [-m] [-M regex] [-S regex] [-L commitlimit]
+ [CVS_module]
END
exit(1);
}
close ($f);
}
-getopts("hivmkuo:d:p:C:z:s:M:P:A:S:") or usage();
+# convert getopts specs for use by git-repo-config
+sub read_repo_config {
+ # Split the string between characters, unless there is a ':'
+ # So "abc:de" becomes ["a", "b", "c:", "d", "e"]
+ my @opts = split(/ *(?!:)/, shift);
+ foreach my $o (@opts) {
+ my $key = $o;
+ $key =~ s/://g;
+ my $arg = 'git-repo-config';
+ $arg .= ' --bool' if ($o !~ /:$/);
+
+ chomp(my $tmp = `$arg --get cvsimport.$key`);
+ if ($tmp && !($arg =~ /--bool/ && $tmp eq 'false')) {
+ no strict 'refs';
+ my $opt_name = "opt_" . $key;
+ if (!$$opt_name) {
+ $$opt_name = $tmp;
+ }
+ }
+ }
+ if (@ARGV == 0) {
+ chomp(my $module = `git-repo-config --get cvsimport.module`);
+ push(@ARGV, $module);
+ }
+}
+
+my $opts = "haivmkuo:d:p:C:z:s:M:P:A:S:L:";
+read_repo_config($opts);
+getopts($opts) or usage();
usage if $opt_h;
-@ARGV <= 1 or usage();
+@ARGV <= 1 or usage("You can't specify more than one CVS module");
-if($opt_d) {
+if ($opt_d) {
$ENV{"CVSROOT"} = $opt_d;
-} elsif(-f 'CVS/Root') {
+} 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"}) {
+} elsif ($ENV{"CVSROOT"}) {
$opt_d = $ENV{"CVSROOT"};
} else {
- die "CVSROOT needs to be set";
+ usage("CVSROOT needs to be set");
}
$opt_o ||= "origin";
$opt_s ||= "-";
+$opt_a ||= 0;
+
my $git_tree = $opt_C;
$git_tree ||= ".";
if ($#ARGV == 0) {
$cvs_tree = $ARGV[0];
} elsif (-f 'CVS/Repository') {
- open my $f, '<', 'CVS/Repository' or
+ open my $f, '<', 'CVS/Repository' or
die 'Failed to open CVS/Repository';
$cvs_tree = <$f>;
chomp $cvs_tree;
close $f;
} else {
- usage();
+ usage("CVS module has to be specified");
}
our @mergerx = ();
push (@mergerx, qr/$opt_M/);
}
+# Remember UTC of our starting time
+# we'll want to avoid importing commits
+# that are too recent
+our $starttime = time();
+
select(STDERR); $|=1; select(STDOUT);
use POSIX qw(strftime dup2);
sub new {
- my($what,$repo,$subdir) = @_;
+ my ($what,$repo,$subdir) = @_;
$what=ref($what) if ref($what);
my $self = {};
sub conn {
my $self = shift;
my $repo = $self->{'fullrep'};
- if($repo =~ s/^:pserver:(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) {
- my($user,$pass,$serv,$port) = ($1,$2,$3,$4);
+ if ($repo =~ s/^:pserver(?:([^:]*)):(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) {
+ my ($param,$user,$pass,$serv,$port) = ($1,$2,$3,$4,$5);
+
+ my ($proxyhost,$proxyport);
+ if ($param && ($param =~ m/proxy=([^;]+)/)) {
+ $proxyhost = $1;
+ # Default proxyport, if not specified, is 8080.
+ $proxyport = 8080;
+ if ($ENV{"CVS_PROXY_PORT"}) {
+ $proxyport = $ENV{"CVS_PROXY_PORT"};
+ }
+ if ($param =~ m/proxyport=([^;]+)/) {
+ $proxyport = $1;
+ }
+ }
+
$user="anonymous" unless defined $user;
my $rr2 = "-";
- unless($port) {
+ unless ($port) {
$rr2 = ":pserver:$user\@$serv:$repo";
$port=2401;
}
my $rr = ":pserver:$user\@$serv:$port$repo";
- unless($pass) {
+ unless ($pass) {
open(H,$ENV{'HOME'}."/.cvspass") and do {
# :pserver:cvs@mea.tmt.tele.fi:/cvsroot/zmailer Ah<Z
- while(<H>) {
+ while (<H>) {
chomp;
s/^\/\d+\s+//;
my ($w,$p) = split(/\s/,$_,2);
- if($w eq $rr or $w eq $rr2) {
+ if ($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 $s;
+ my ($s, $rep);
+ if ($proxyhost) {
+
+ # Use a HTTP Proxy. Only works for HTTP proxies that
+ # don't require user authentication
+ #
+ # See: http://www.ietf.org/rfc/rfc2817.txt
+
+ $s = IO::Socket::INET->new(PeerHost => $proxyhost, PeerPort => $proxyport);
+ die "Socket to $proxyhost: $!\n" unless defined $s;
+ $s->write("CONNECT $serv:$port HTTP/1.1\r\nHost: $serv:$port\r\n\r\n")
+ or die "Write to $proxyhost: $!\n";
+ $s->flush();
+
+ $rep = <$s>;
+
+ # The answer should look like 'HTTP/1.x 2yy ....'
+ if (!($rep =~ m#^HTTP/1\.. 2[0-9][0-9]#)) {
+ die "Proxy connect: $rep\n";
+ }
+ # Skip up to the empty line of the proxy server output
+ # including the response headers.
+ while ($rep = <$s>) {
+ last if (!defined $rep ||
+ $rep eq "\n" ||
+ $rep eq "\r\n");
+ }
+ } else {
+ $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>;
+ $rep = <$s>;
- if($rep ne "I LOVE YOU\n") {
+ if ($rep ne "I LOVE YOU\n") {
$rep="<unknown>" unless $rep;
die "AuthReply: $rep\n";
}
}
}
- unless($pid) {
+ unless ($pid) {
$pr->writer();
$pw->reader();
dup2($pw->fileno(),0);
$self->{'socketo'}->flush();
chomp(my $rep=$self->readline());
- if($rep !~ s/^Valid-requests\s*//) {
+ if ($rep !~ s/^Valid-requests\s*//) {
$rep="<unknown>" unless $rep;
die "Expected Valid-requests from server, but got: $rep\n";
}
}
sub readline {
- my($self) = @_;
+ 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) = @_;
+ my ($self,$fn,$rev) = @_;
$self->{'socketo'}->write("Argument -N\n") or return undef;
$self->{'socketo'}->write("Argument -P\n") or return undef;
# -kk: Linus' version doesn't use it - defaults to off
sub _line {
# Read a line from the server.
# ... except that 'line' may be an entire file. ;-)
- my($self, $fh) = @_;
+ my ($self, $fh) = @_;
die "Not in lines" unless defined $self->{'lines'};
my $line;
my $res=0;
- while(defined($line = $self->readline())) {
+ while (defined($line = $self->readline())) {
# M U gnupg-cvs-rep/AUTHORS
# Updated gnupg-cvs-rep/
# /daten/src/rsync/gnupg-cvs-rep/AUTHORS
# 0
# ok
- if($line =~ s/^(?:Created|Updated) //) {
+ if ($line =~ s/^(?:Created|Updated) //) {
$line = $self->readline(); # path
$line = $self->readline(); # Entries line
my $mode = $self->readline(); chomp $mode;
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/^ //) {
+ $res = $self->_fetchfile($fh, $cnt);
+ } elsif ($line =~ s/^ //) {
print $fh $line;
$res += length($line);
- } elsif($line =~ /^M\b/) {
+ } elsif ($line =~ /^M\b/) {
# output, do nothing
- } elsif($line =~ /^Mbinary\b/) {
+ } elsif ($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;
- }
+ $res += $self->_fetchfile($fh, $cnt);
} else {
chomp $line;
- if($line eq "ok") {
+ if ($line eq "ok") {
# print STDERR "S: ok (".length($res).")\n";
return $res;
- } elsif($line =~ s/^E //) {
+ } elsif ($line =~ s/^E //) {
# print STDERR "S: $line\n";
- } elsif($line =~ /^(Remove-entry|Removed) /i) {
+ } elsif ($line =~ /^(Remove-entry|Removed) /i) {
$line = $self->readline(); # filename
$line = $self->readline(); # OK
chomp $line;
return undef;
}
sub file {
- my($self,$fn,$rev) = @_;
+ my ($self,$fn,$rev) = @_;
my $res;
- my ($fh, $name) = tempfile('gitcvs.XXXXXX',
+ my ($fh, $name) = tempfile('gitcvs.XXXXXX',
DIR => File::Spec->tmpdir(), UNLINK => 1);
$self->_file($fn,$rev) and $res = $self->_line($fh);
return ($name, $res);
}
+sub _fetchfile {
+ my ($self, $fh, $cnt) = @_;
+ my $res = 0;
+ my $bufsize = 1024 * 1024;
+ while ($cnt) {
+ if ($bufsize > $cnt) {
+ $bufsize = $cnt;
+ }
+ my $buf;
+ my $num = $self->{'socketi'}->read($buf,$bufsize);
+ die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
+ print $fh $buf;
+ $res += $num;
+ $cnt -= $num;
+ }
+ return $res;
+}
package main;
sub pdate($) {
- my($d) = @_;
+ my ($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 $y>1900;
}
sub pmode($) {
- my($mode) = @_;
+ my ($mode) = @_;
my $m = 0;
my $mm = 0;
my $um = 0;
for my $x(split(//,$mode)) {
- if($x eq ",") {
+ if ($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
+ } 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";
}
}
return $pwd;
}
+sub is_sha1 {
+ my $s = shift;
+ return $s =~ /^[a-f0-9]{40}$/;
+}
-sub get_headref($$) {
+sub get_headref ($$) {
my $name = shift;
- my $git_dir = shift;
- my $sha;
-
- if (open(C,"$git_dir/refs/heads/$name")) {
- chomp($sha = <C>);
- close(C);
- length($sha) == 40
- or die "Cannot get head id for $name ($sha): $!\n";
+ my $git_dir = shift;
+
+ my $f = "$git_dir/refs/heads/$name";
+ if (open(my $fh, $f)) {
+ chomp(my $r = <$fh>);
+ is_sha1($r) or die "Cannot get head id for $name ($r): $!";
+ return $r;
}
- return $sha;
+ die "unable to open $f: $!" unless $! == POSIX::ENOENT;
+ return undef;
}
-
-d $git_tree
or mkdir($git_tree,0777)
or die "Could not create $git_tree: $!";
$ENV{"GIT_DIR"} = $git_dir;
my $orig_git_index;
$orig_git_index = $ENV{GIT_INDEX_FILE} if exists $ENV{GIT_INDEX_FILE};
-my ($git_ih, $git_index) = tempfile('gitXXXXXX', SUFFIX => '.idx',
- DIR => File::Spec->tmpdir());
-close ($git_ih);
-$ENV{GIT_INDEX_FILE} = $git_index;
-unless(-d $git_dir) {
- system("git-init-db");
+
+my %index; # holds filenames of one index per branch
+
+unless (-d $git_dir) {
+ system("git-init");
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";
-
open(F, "git-symbolic-ref HEAD |") or
die "Cannot run git-symbolic-ref: $!\n";
chomp ($last_branch = <F>);
$last_branch = basename($last_branch);
close(F);
- unless($last_branch) {
+ unless ($last_branch) {
warn "Cannot read the last branch name: $! -- assuming 'master'\n";
$last_branch = "master";
}
$orig_branch = $last_branch;
$tip_at_start = `git-rev-parse --verify HEAD`;
- # populate index
- system('git-read-tree', $last_branch);
- die "read-tree failed: $?\n" if $?;
-
# Get the last import timestamps
- opendir(D,"$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);
+ my $fmt = '($ref, $author) = (%(refname), %(author));';
+ open(H, "git-for-each-ref --perl --format='$fmt' refs/heads |") or
+ die "Cannot run git-for-each-ref: $!\n";
+ while (defined(my $entry = <H>)) {
+ my ($ref, $author);
+ eval($entry) || die "cannot eval refs list: $@";
+ my ($head) = ($ref =~ m|^refs/heads/(.*)|);
+ $author =~ /^.*\s(\d+)\s[-+]\d{4}$/;
+ $branch_date{$head} = $1;
}
- closedir(D);
+ close(H);
+ if (!exists $branch_date{$opt_o}) {
+ die "Branch '$opt_o' does not exist.\n".
+ "Either use the correct '-o branch' option,\n".
+ "or import to a new repository.\n";
+ }
}
-d $git_dir
write_author_info("$git_dir/cvs-authors");
}
-my $pid = open(CVS,"-|");
-die "Cannot fork: $!\n" unless defined $pid;
-unless($pid) {
- my @opt;
- @opt = split(/,/,$opt_p) if defined $opt_p;
- unshift @opt, '-z', $opt_z if defined $opt_z;
- unshift @opt, '-q' unless defined $opt_v;
- unless (defined($opt_p) && $opt_p =~ m/--no-cvs-direct/) {
- push @opt, '--cvs-direct';
+
+#
+# run cvsps into a file unless we are getting
+# it passed as a file via $opt_P
+#
+my $cvspsfile;
+unless ($opt_P) {
+ print "Running cvsps...\n" if $opt_v;
+ my $pid = open(CVSPS,"-|");
+ my $cvspsfh;
+ die "Cannot fork: $!\n" unless defined $pid;
+ unless ($pid) {
+ my @opt;
+ @opt = split(/,/,$opt_p) if defined $opt_p;
+ unshift @opt, '-z', $opt_z if defined $opt_z;
+ unshift @opt, '-q' unless defined $opt_v;
+ unless (defined($opt_p) && $opt_p =~ m/--no-cvs-direct/) {
+ push @opt, '--cvs-direct';
+ }
+ exec("cvsps","--norc",@opt,"-u","-A",'--root',$opt_d,$cvs_tree);
+ die "Could not start cvsps: $!\n";
}
- if ($opt_P) {
- exec("cat", $opt_P);
- } else {
- exec("cvsps","--norc",@opt,"-u","-A",'--root',$opt_d,$cvs_tree);
- die "Could not start cvsps: $!\n";
+ ($cvspsfh, $cvspsfile) = tempfile('gitXXXXXX', SUFFIX => '.cvsps',
+ DIR => File::Spec->tmpdir());
+ while (<CVSPS>) {
+ print $cvspsfh $_;
}
+ close CVSPS;
+ close $cvspsfh;
+} else {
+ $cvspsfile = $opt_P;
}
+open(CVS, "<$cvspsfile") or die $!;
## cvsps output:
#---------------------
my $state = 0;
-my($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg);
-my(@old,@new,@skipped);
-sub commit {
- my $pid;
- while(@old) {
- my @o2;
- if(@old > 55) {
- @o2 = splice(@old,0,50);
- } else {
- @o2 = @old;
- @old = ();
- }
- system("git-update-index","--force-remove","--",@o2);
- die "Cannot remove files: $?\n" if $?;
- }
- while(@new) {
- my @n2;
- if(@new > 12) {
- @n2 = splice(@new,0,10);
- } else {
- @n2 = @new;
- @new = ();
- }
- system("git-update-index","--add",
- (map { ('--cacheinfo', @$_) } @n2));
- die "Cannot add files: $?\n" if $?;
- }
+sub update_index (\@\@) {
+ my $old = shift;
+ my $new = shift;
+ open(my $fh, '|-', qw(git-update-index -z --index-info))
+ or die "unable to open git-update-index: $!";
+ print $fh
+ (map { "0 0000000000000000000000000000000000000000\t$_\0" }
+ @$old),
+ (map { '100' . sprintf('%o', $_->[0]) . " $_->[1]\t$_->[2]\0" }
+ @$new)
+ or die "unable to write to git-update-index: $!";
+ close $fh
+ or die "unable to write to git-update-index: $!";
+ $? and die "git-update-index reported error: $?";
+}
- $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)
+sub write_tree () {
+ open(my $fh, '-|', qw(git-write-tree))
+ or die "unable to open git-write-tree: $!";
+ chomp(my $tree = <$fh>);
+ is_sha1($tree)
+ or die "Cannot get tree id ($tree): $!";
+ close($fh)
or die "Error running git-write-tree: $?\n";
print "Tree ID $tree\n" if $opt_v;
+ return $tree;
+}
- 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 $opt_v;
- }
+my ($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg);
+my (@old,@new,@skipped,%ignorebranch);
- my $pr = IO::Pipe->new() or die "Cannot open pipe: $!\n";
- my $pw = IO::Pipe->new() or die "Cannot open pipe: $!\n";
- $pid = fork();
- die "Fork: $!\n" unless defined $pid;
- unless($pid) {
- $pr->writer();
- $pw->reader();
- open(OUT,">&STDOUT");
- dup2($pw->fileno(),0);
- dup2($pr->fileno(),1);
- $pr->close();
- $pw->close();
-
- my @par = ();
- @par = ("-p",$parent) if $parent;
-
- # loose detection of merges
- # based on the commit msg
- foreach my $rx (@mergerx) {
- if ($logmsg =~ $rx) {
- my $mparent = $1;
- if ($mparent eq 'HEAD') { $mparent = $opt_o };
- if ( -e "$git_dir/refs/heads/$mparent") {
- $mparent = get_headref($mparent, $git_dir);
- push @par, '-p', $mparent;
- print OUT "Merge parent branch: $mparent\n" if $opt_v;
- }
- }
- }
+# commits that cvsps cannot place anywhere...
+$ignorebranch{'#CVSPS_NO_BRANCH'} = 1;
- exec("env",
- "GIT_AUTHOR_NAME=$author_name",
- "GIT_AUTHOR_EMAIL=$author_email",
- "GIT_AUTHOR_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
- "GIT_COMMITTER_NAME=$author_name",
- "GIT_COMMITTER_EMAIL=$author_email",
- "GIT_COMMITTER_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
- "git-commit-tree", $tree,@par);
- die "Cannot exec git-commit-tree: $!\n";
-
- close OUT;
+sub commit {
+ if ($branch eq $opt_o && !$index{branch} && !get_headref($branch, $git_dir)) {
+ # looks like an initial commit
+ # use the index primed by git-init
+ $ENV{GIT_INDEX_FILE} = "$git_dir/index";
+ $index{$branch} = "$git_dir/index";
+ } else {
+ # use an index per branch to speed up
+ # imports of projects with many branches
+ unless ($index{$branch}) {
+ $index{$branch} = tmpnam();
+ $ENV{GIT_INDEX_FILE} = $index{$branch};
+ if ($ancestor) {
+ system("git-read-tree", $ancestor);
+ } else {
+ system("git-read-tree", $branch);
+ }
+ die "read-tree failed: $?\n" if $?;
+ }
+ }
+ $ENV{GIT_INDEX_FILE} = $index{$branch};
+
+ update_index(@old, @new);
+ @old = @new = ();
+ my $tree = write_tree();
+ my $parent = get_headref($last_branch, $git_dir);
+ print "Parent ID " . ($parent ? $parent : "(empty)") . "\n" if $opt_v;
+
+ my @commit_args;
+ push @commit_args, ("-p", $parent) if $parent;
+
+ # loose detection of merges
+ # based on the commit msg
+ foreach my $rx (@mergerx) {
+ next unless $logmsg =~ $rx && $1;
+ my $mparent = $1 eq 'HEAD' ? $opt_o : $1;
+ if (my $sha1 = get_headref($mparent, $git_dir)) {
+ push @commit_args, '-p', $mparent;
+ print "Merge parent branch: $mparent\n" if $opt_v;
+ }
}
- $pw->writer();
- $pr->reader();
+
+ my $commit_date = strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date));
+ $ENV{GIT_AUTHOR_NAME} = $author_name;
+ $ENV{GIT_AUTHOR_EMAIL} = $author_email;
+ $ENV{GIT_AUTHOR_DATE} = $commit_date;
+ $ENV{GIT_COMMITTER_NAME} = $author_name;
+ $ENV{GIT_COMMITTER_EMAIL} = $author_email;
+ $ENV{GIT_COMMITTER_DATE} = $commit_date;
+ my $pid = open2(my $commit_read, my $commit_write,
+ 'git-commit-tree', $tree, @commit_args);
# compatibility with git2cvs
substr($logmsg,32767) = "" if length($logmsg) > 32767;
@skipped = ();
}
- print $pw "$logmsg\n"
+ print($commit_write "$logmsg\n") && close($commit_write)
or die "Error writing to git-commit-tree: $!\n";
- $pw->close();
- print "Committed patch $patchset ($branch ".strftime("%Y-%m-%d %H:%M:%S",gmtime($date)).")\n" if $opt_v;
- chomp(my $cid = <$pr>);
- length($cid) == 40
- or die "Cannot get commit id ($cid): $!\n";
+ print "Committed patch $patchset ($branch $commit_date)\n" if $opt_v;
+ chomp(my $cid = <$commit_read>);
+ is_sha1($cid) or die "Cannot get commit id ($cid): $!\n";
print "Commit ID $cid\n" if $opt_v;
- $pr->close();
+ close($commit_read);
waitpid($pid,0);
die "Error running git-commit-tree: $?\n" if $?;
system("git-update-ref refs/heads/$branch $cid") == 0
or die "Cannot write branch $branch for update: $!\n";
- if($tag) {
- my($in, $out) = ('','');
- my($xtag) = $tag;
+ if ($tag) {
+ my ($in, $out) = ('','');
+ my ($xtag) = $tag;
$xtag =~ s/\s+\*\*.*$//; # Remove stuff like ** INVALID ** and ** FUNKY **
$xtag =~ tr/_/\./ if ( $opt_u );
$xtag =~ s/[\/]/$opt_s/g;
-
+
my $pid = open2($in, $out, 'git-mktag');
print $out "object $cid\n".
"type commit\n".
$? != 0 or $tagobj !~ /^[0123456789abcdef]{40}$/ ) {
die "Cannot create tag object $xtag: $!\n";
}
-
+
open(C,">$git_dir/refs/tags/$xtag")
or die "Cannot create tag $xtag: $!\n";
}
};
-while(<CVS>) {
+my $commitcount = 1;
+while (<CVS>) {
chomp;
- if($state == 0 and /^-+$/) {
+ if ($state == 0 and /^-+$/) {
$state = 1;
- } elsif($state == 0) {
+ } elsif ($state == 0) {
$state = 1;
redo;
- } elsif(($state==0 or $state==1) and s/^PatchSet\s+//) {
+ } elsif (($state==0 or $state==1) and s/^PatchSet\s+//) {
$patchset = 0+$_;
$state=2;
- } elsif($state == 2 and s/^Date:\s+//) {
+ } elsif ($state == 2 and s/^Date:\s+//) {
$date = pdate($_);
- unless($date) {
+ unless ($date) {
print STDERR "Could not parse date: $_\n";
$state=0;
next;
}
$state=3;
- } elsif($state == 3 and s/^Author:\s+//) {
+ } elsif ($state == 3 and s/^Author:\s+//) {
s/\s+$//;
if (/^(.*?)\s+<(.*)>/) {
($author_name, $author_email) = ($1, $2);
$author_name = $author_email = $_;
}
$state = 4;
- } elsif($state == 4 and s/^Branch:\s+//) {
+ } elsif ($state == 4 and s/^Branch:\s+//) {
s/\s+$//;
s/[\/]/$opt_s/g;
$branch = $_;
$state = 5;
- } elsif($state == 5 and s/^Ancestor branch:\s+//) {
+ } elsif ($state == 5 and s/^Ancestor branch:\s+//) {
s/\s+$//;
$ancestor = $_;
$ancestor = $opt_o if $ancestor eq "HEAD";
$state = 6;
- } elsif($state == 5) {
+ } elsif ($state == 5) {
$ancestor = undef;
$state = 6;
redo;
- } elsif($state == 6 and s/^Tag:\s+//) {
+ } elsif ($state == 6 and s/^Tag:\s+//) {
s/\s+$//;
- if($_ eq "(none)") {
+ if ($_ eq "(none)") {
$tag = undef;
} else {
$tag = $_;
}
$state = 7;
- } elsif($state == 7 and /^Log:/) {
+ } elsif ($state == 7 and /^Log:/) {
$logmsg = "";
$state = 8;
- } elsif($state == 8 and /^Members:/) {
+ } elsif ($state == 8 and /^Members:/) {
$branch = $opt_o if $branch eq "HEAD";
- if(defined $branch_date{$branch} and $branch_date{$branch} >= $date) {
+ 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") {
+ if (!$opt_a && $starttime - 300 - (defined $opt_z ? $opt_z : 300) <= $date) {
+ # skip if the commit is too recent
+ # that the cvsps default fuzz is 300s, we give ourselves another
+ # 300s just in case -- this also prevents skipping commits
+ # due to server clock drift
+ print "skip patchset $patchset: $date too recent\n" if $opt_v;
+ $state = 11;
+ next;
+ }
+ if (exists $ignorebranch{$branch}) {
+ print STDERR "Skipping $branch\n";
+ $state = 11;
+ next;
+ }
+ if ($ancestor) {
+ if ($ancestor eq $branch) {
+ print STDERR "Branch $branch erroneously stems from itself -- changed ancestor to $opt_o\n";
+ $ancestor = $opt_o;
+ }
+ if (-f "$git_dir/refs/heads/$branch") {
print STDERR "Branch $branch already exists!\n";
$state=11;
next;
}
- unless(open(H,"$git_dir/refs/heads/$ancestor")) {
+ unless (open(H,"$git_dir/refs/heads/$ancestor")) {
print STDERR "Branch $ancestor does not exist!\n";
+ $ignorebranch{$branch} = 1;
$state=11;
next;
}
chomp(my $id = <H>);
close(H);
- unless(open(H,"> $git_dir/refs/heads/$branch")) {
+ unless (open(H,"> $git_dir/refs/heads/$branch")) {
print STDERR "Could not create branch $branch: $!\n";
+ $ignorebranch{$branch} = 1;
$state=11;
next;
}
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", $branch);
- die "read-tree failed: $?\n" if $?;
- }
$last_branch = $branch if $branch ne $last_branch;
$state = 9;
- } elsif($state == 8) {
+ } elsif ($state == 8) {
$logmsg .= "$_\n";
- } elsif($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) {
+ } elsif ($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) {
# VERSION:1.96->1.96.2.1
my $init = ($2 eq "INITIAL");
my $fn = $1;
}
print "Fetching $fn v $rev\n" if $opt_v;
my ($tmpname, $size) = $cvs->file($fn,$rev);
- if($size == -1) {
+ if ($size == -1) {
push(@old,$fn);
print "Drop $fn\n" if $opt_v;
} else {
push(@new,[$mode, $sha, $fn]); # may be resurrected!
}
unlink($tmpname);
- } elsif($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) {
+ } elsif ($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) {
my $fn = $1;
$fn =~ s#^/+##;
push(@old,$fn);
print "Delete $fn\n" if $opt_v;
- } elsif($state == 9 and /^\s*$/) {
+ } elsif ($state == 9 and /^\s*$/) {
$state = 10;
- } elsif(($state == 9 or $state == 10) and /^-+$/) {
+ } elsif (($state == 9 or $state == 10) and /^-+$/) {
+ $commitcount++;
+ if ($opt_L && $commitcount > $opt_L) {
+ last;
+ }
commit();
+ if (($commitcount & 1023) == 0) {
+ system("git repack -a -d");
+ }
$state = 1;
- } elsif($state == 11 and /^-+$/) {
+ } elsif ($state == 11 and /^-+$/) {
$state = 1;
- } elsif(/^-+$/) { # end of unknown-line processing
+ } elsif (/^-+$/) { # end of unknown-line processing
$state = 1;
- } elsif($state != 11) { # ignore stuff when skipping
+ } elsif ($state != 11) { # ignore stuff when skipping
print "* UNKNOWN LINE * $_\n";
}
}
commit() if $branch and $state != 11;
-unlink($git_index);
+unless ($opt_P) {
+ unlink($cvspsfile);
+}
+
+# The heuristic of repacking every 1024 commits can leave a
+# lot of unpacked data. If there is more than 1MB worth of
+# not-packed objects, repack once more.
+my $line = `git-count-objects`;
+if ($line =~ /^(\d+) objects, (\d+) kilobytes$/) {
+ my ($n_objects, $kb) = ($1, $2);
+ 1024 < $kb
+ and system("git repack -a -d");
+}
+
+foreach my $git_index (values %index) {
+ if ($git_index ne "$git_dir/index") {
+ unlink($git_index);
+ }
+}
if (defined $orig_git_index) {
$ENV{GIT_INDEX_FILE} = $orig_git_index;
}
# Now switch back to the branch we were in before all of this happened
-if($orig_branch) {
+if ($orig_branch) {
print "DONE.\n" if $opt_v;
if ($opt_i) {
exit 0;