use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/;
use File::Spec qw//;
use POSIX qw/strftime/;
+use IPC::Open3;
use Memoize;
memoize('revisions_eq');
+memoize('cmt_metadata');
+memoize('get_commit_time');
my ($SVN_PATH, $SVN, $SVN_LOG, $_use_lib);
$_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB};
my $sha1 = qr/[a-f\d]{40}/;
my $sha1_short = qr/[a-f\d]{4,40}/;
my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit,
- $_find_copies_harder, $_l, $_cp_similarity,
+ $_find_copies_harder, $_l, $_cp_similarity, $_cp_remote,
$_repack, $_repack_nr, $_repack_flags,
$_template, $_shared, $_no_default_regex, $_no_graft_copy,
$_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit,
{ 'revision|r=i' => \$_revision } ],
rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)",
{ 'no-ignore-externals' => \$_no_ignore_ext,
+ 'copy-remote|remote=s' => \$_cp_remote,
'upgrade' => \$_upgrade } ],
'graft-branches' => [ \&graft_branches,
'Detect merges/branches from already imported history',
{ 'merge-rx|m' => \@_opt_m,
+ 'branch|b=s' => \@_branch_from,
+ 'branch-all-refs|B' => \$_branch_all_refs,
'no-default-regex' => \$_no_default_regex,
'no-graft-copy' => \$_no_graft_copy } ],
'multi-init' => [ \&multi_init,
init_vars();
load_authors() if $_authors;
load_all_refs() if $_branch_all_refs;
-svn_compat_check();
-migration_check() unless $cmd =~ /^(?:init|multi-init)$/;
+svn_compat_check() unless $_use_lib;
+migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init)$/;
$cmd{$cmd}->[0]->(@ARGV);
exit 0;
}
sub rebuild {
+ if (quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0")) {
+ copy_remote_ref();
+ }
$SVN_URL = shift or undef;
my $newest_rev = 0;
if ($_upgrade) {
# performance sucks with it enabled, so it's much
# faster to fetch revision ranges instead of relying
# on the limiter.
- $SVN_LOG->get_log( '/'.$SVN_PATH, $min, $max, 0, 1, 1,
+ libsvn_get_log($SVN_LOG, '/'.$SVN_PATH,
+ $min, $max, 0, 1, 1,
sub {
my $log_msg;
if ($last_commit) {
my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$";
+ if (defined $LC_ALL) {
+ $ENV{LC_ALL} = $LC_ALL;
+ } else {
+ delete $ENV{LC_ALL};
+ }
foreach my $c (@revs) {
+ my $log_msg = get_commit_message($c, $commit_msg);
+
# fork for each commit because there's a memory leak I
# can't track down... (it's probably in the SVN code)
defined(my $pid = open my $fh, '-|') or croak $!;
if (!$pid) {
- if (defined $LC_ALL) {
- $ENV{LC_ALL} = $LC_ALL;
- } else {
- delete $ENV{LC_ALL};
- }
- my $log_msg = get_commit_message($c, $commit_msg);
my $ed = SVN::Git::Editor->new(
{ r => $r_last,
ra => $SVN,
($r_last, $cmt_last) = ($r_new, $cmt_new);
}
}
+ $ENV{LC_ALL} = 'C';
unlink $commit_msg;
}
my $l_map = read_url_paths();
my @re = map { qr/$_/is } @_opt_m if @_opt_m;
unless ($_no_default_regex) {
- push @re, ( qr/\b(?:merge|merging|merged)\s+(\S.+)/is,
- qr/\b(?:from|of)\s+(\S.+)/is );
+ push @re, (qr/\b(?:merge|merging|merged)\s+with\s+([\w\.\-]+)/i,
+ qr/\b(?:merge|merging|merged)\s+([\w\.\-]+)/i,
+ qr/\b(?:from|of)\s+([\w\.\-]+)/i );
}
foreach my $u (keys %$l_map) {
if (@re) {
foreach my $p (keys %{$l_map->{$u}}) {
- graft_merge_msg($grafts,$l_map,$u,$p);
+ graft_merge_msg($grafts,$l_map,$u,$p,@re);
}
}
unless ($_no_graft_copy) {
}
}
}
+ graft_tree_joins($grafts);
write_grafts($grafts, $comments, $gr_file);
unlink "$gr_file~$gr_sha1" if $gr_sha1;
my $pid = open(my $log,'-|');
defined $pid or croak $!;
if (!$pid) {
- my @rl = (qw/git-log --abbrev-commit --pretty=raw
- --default/, "remotes/$GIT_SVN");
- push @rl, '--raw' if $_verbose;
- exec(@rl, @args) or croak $!;
+ exec(git_svn_log_cmd($r_min,$r_max), @args) or croak $!;
}
setup_pager();
my (@k, $c, $d);
+
while (<$log>) {
if (/^commit ($sha1_short)/o) {
my $cmt = $1;
- if ($c && defined $c->{r} && $c->{r} != $r_last) {
+ if ($c && cmt_showable($c) && $c->{r} != $r_last) {
$r_last = $c->{r};
process_commit($c, $r_min, $r_max, \@k) or
goto out;
} elsif ($d) {
push @{$c->{diff}}, $_;
} elsif (/^ (git-svn-id:.+)$/) {
- my ($url, $rev, $uuid) = extract_metadata($1);
- $c->{r} = $rev;
+ (undef, $c->{r}, undef) = extract_metadata($1);
} elsif (s/^ //) {
push @{$c->{l}}, $_;
}
########################### utility functions #########################
+sub cmt_showable {
+ my ($c) = @_;
+ return 1 if defined $c->{r};
+ if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
+ $c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
+ my @msg = safe_qx(qw/git-cat-file commit/, $c->{c});
+ shift @msg while ($msg[0] ne "\n");
+ shift @msg;
+ @{$c->{l}} = grep !/^git-svn-id: /, @msg;
+
+ (undef, $c->{r}, undef) = extract_metadata(
+ (grep(/^git-svn-id: /, @msg))[-1]);
+ }
+ return defined $c->{r};
+}
+
+sub git_svn_log_cmd {
+ my ($r_min, $r_max) = @_;
+ my @cmd = (qw/git-log --abbrev-commit --pretty=raw
+ --default/, "refs/remotes/$GIT_SVN");
+ push @cmd, '--summary' if $_verbose;
+ return @cmd unless defined $r_max;
+ if ($r_max == $r_min) {
+ push @cmd, '--max-count=1';
+ if (my $c = revdb_get($REVDB, $r_max)) {
+ push @cmd, $c;
+ }
+ } else {
+ my ($c_min, $c_max);
+ $c_max = revdb_get($REVDB, $r_max);
+ $c_min = revdb_get($REVDB, $r_min);
+ if ($c_min && $c_max) {
+ if ($r_max > $r_max) {
+ push @cmd, "$c_min..$c_max";
+ } else {
+ push @cmd, "$c_max..$c_min";
+ }
+ } elsif ($r_max > $r_min) {
+ push @cmd, $c_max;
+ } else {
+ push @cmd, $c_min;
+ }
+ }
+ return @cmd;
+}
+
sub fetch_child_id {
my $id = shift;
print "Fetching $id\n";
return '';
}
+# grafts set here are 'stronger' in that they're based on actual tree
+# matches, and won't be deleted from merge-base checking in write_grafts()
+sub graft_tree_joins {
+ my $grafts = shift;
+ map_tree_joins() if (@_branch_from && !%tree_map);
+ return unless %tree_map;
+
+ git_svn_each(sub {
+ my $i = shift;
+ defined(my $pid = open my $fh, '-|') or croak $!;
+ if (!$pid) {
+ exec qw/git-rev-list --pretty=raw/,
+ "refs/remotes/$i" or croak $!;
+ }
+ while (<$fh>) {
+ next unless /^commit ($sha1)$/o;
+ my $c = $1;
+ my ($t) = (<$fh> =~ /^tree ($sha1)$/o);
+ next unless $tree_map{$t};
+
+ my $l;
+ do {
+ $l = readline $fh;
+ } until ($l =~ /^committer (?:.+) (\d+) ([\-\+]?\d+)$/);
+
+ my ($s, $tz) = ($1, $2);
+ if ($tz =~ s/^\+//) {
+ $s += tz_to_s_offset($tz);
+ } elsif ($tz =~ s/^\-//) {
+ $s -= tz_to_s_offset($tz);
+ }
+
+ my ($url_a, $r_a, $uuid_a) = cmt_metadata($c);
+
+ foreach my $p (@{$tree_map{$t}}) {
+ next if $p eq $c;
+ my $mb = eval {
+ safe_qx('git-merge-base', $c, $p)
+ };
+ next unless ($@ || $?);
+ if (defined $r_a) {
+ # see if SVN says it's a relative
+ my ($url_b, $r_b, $uuid_b) =
+ cmt_metadata($p);
+ next if (defined $url_b &&
+ defined $url_a &&
+ ($url_a eq $url_b) &&
+ ($uuid_a eq $uuid_b));
+ if ($uuid_a eq $uuid_b) {
+ if ($r_b < $r_a) {
+ $grafts->{$c}->{$p} = 2;
+ next;
+ } elsif ($r_b > $r_a) {
+ $grafts->{$p}->{$c} = 2;
+ next;
+ }
+ }
+ }
+ my $ct = get_commit_time($p);
+ if ($ct < $s) {
+ $grafts->{$c}->{$p} = 2;
+ } elsif ($ct > $s) {
+ $grafts->{$p}->{$c} = 2;
+ }
+ # what should we do when $ct == $s ?
+ }
+ }
+ close $fh or croak $?;
+ });
+}
+
# this isn't funky-filename safe, but good enough for now...
sub graft_file_copy_cmd {
my ($grafts, $l_map, $u) = @_;
$SVN::Error::handler = \&libsvn_skip_unknown_revs;
while (1) {
my $pool = SVN::Pool->new;
- $SVN_LOG->get_log( "/$path", $min, $max, 0, 1, 1,
+ libsvn_get_log($SVN_LOG, "/$path", $min, $max, 0, 1, 1,
sub {
libsvn_graft_file_copies($grafts, $tree_paths,
$path, @_);
my $re = qr/\Q$w\E/i;
foreach (keys %{$l_map->{$u}}) {
if (/$re/) {
- push @strong, $_;
+ push @strong, $l_map->{$u}->{$_};
last;
}
}
$re = qr/\Q$w\E/i;
foreach (keys %{$l_map->{$u}}) {
if (/$re/) {
- push @strong, $_;
+ push @strong, $l_map->{$u}->{$_};
last;
}
}
return unless defined $rev;
}
foreach my $m (@strong) {
- my ($r0, $s0) = find_rev_before($rev, $m);
+ my ($r0, $s0) = find_rev_before($rev, $m, 1);
$grafts->{$c->{c}}->{$s0} = 1 if defined $s0;
}
}
} elsif ($m->{chg} eq 'T') {
sys(qw(svn rm --force),$m->{file_b});
apply_mod_line_blob($m);
- sys(qw(svn add --force), $m->{file_b});
+ sys(qw(svn add), $m->{file_b});
svn_check_prop_executable($m);
} elsif ($m->{chg} eq 'A') {
svn_ensure_parent_path( $m->{file_b} );
apply_mod_line_blob($m);
- sys(qw(svn add --force), $m->{file_b});
+ sys(qw(svn add), $m->{file_b});
svn_check_prop_executable($m);
} else {
croak "Invalid chg: $m->{chg}\n";
restore_index($index);
}
if (exists $tree_map{$tree}) {
- push @tmp_parents, @{$tree_map{$tree}};
+ foreach my $p (@{$tree_map{$tree}}) {
+ my $skip;
+ foreach (@tmp_parents) {
+ # see if a common parent is found
+ my $mb = eval {
+ safe_qx('git-merge-base', $_, $p)
+ };
+ next if ($@ || $?);
+ $skip = 1;
+ last;
+ }
+ next if $skip;
+ my ($url_p, $r_p, $uuid_p) = cmt_metadata($p);
+ next if (($SVN_UUID eq $uuid_p) &&
+ ($log_msg->{revision} > $r_p));
+ next if (defined $url_p && defined $SVN_URL &&
+ ($SVN_UUID eq $uuid_p) &&
+ ($url_p eq $SVN_URL));
+ push @tmp_parents, $p;
+ }
}
foreach (@tmp_parents) {
next if $seen_parent{$_};
sub check_upgrade_needed {
if (!-r $REVDB) {
+ -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
open my $fh, '>>',$REVDB or croak $!;
close $fh;
}
init_vars();
exit 0 if -r $REVDB;
print "Upgrading svn => git mapping...\n";
+ -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
open my $fh, '>>',$REVDB or croak $!;
close $fh;
rebuild();
$GIT_SVN_INDEX = "$GIT_SVN_DIR/index";
$SVN_URL = undef;
$SVN_WC = "$GIT_SVN_DIR/tree";
+ %tree_map = ();
}
# convert GetOpt::Long specs for use by git-repo-config
print $fh $_ foreach @{$comments->{$c}};
}
my $p = $grafts->{$c};
+ my %x; # real parents
delete $p->{$c}; # commits are not self-reproducing...
my $pid = open my $ch, '-|';
defined $pid or croak $!;
exec(qw/git-cat-file commit/, $c) or croak $!;
}
while (<$ch>) {
- if (/^parent ([a-f\d]{40})/) {
- $p->{$1} = 1;
+ if (/^parent ($sha1)/) {
+ $x{$1} = $p->{$1} = 1;
} else {
- last unless /^\S/i;
+ last unless /^\S/;
}
}
close $ch; # breaking the pipe
+
+ # if real parents are the only ones in the grafts, drop it
+ next if join(' ',sort keys %$p) eq join(' ',sort keys %x);
+
+ my (@ip, @jp, $mb);
+ my %del = %x;
+ @ip = @jp = keys %$p;
+ foreach my $i (@ip) {
+ next if $del{$i} || $p->{$i} == 2;
+ foreach my $j (@jp) {
+ next if $i eq $j || $del{$j} || $p->{$j} == 2;
+ $mb = eval { safe_qx('git-merge-base',$i,$j) };
+ next unless $mb;
+ chomp $mb;
+ next if $x{$mb};
+ if ($mb eq $j) {
+ delete $p->{$i};
+ $del{$i} = 1;
+ } elsif ($mb eq $i) {
+ delete $p->{$j};
+ $del{$j} = 1;
+ }
+ }
+ }
+
+ # if real parents are the only ones in the grafts, drop it
+ next if join(' ',sort keys %$p) eq join(' ',sort keys %x);
+
print $fh $c, ' ', join(' ', sort keys %$p),"\n";
}
if ($comments->{'END'}) {
}
sub extract_metadata {
- my $id = shift;
+ my $id = shift or return (undef, undef, undef);
my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
\s([a-f\d\-]+)$/x);
if (!$rev || !$uuid || !$url) {
return ($url, $rev, $uuid);
}
+sub cmt_metadata {
+ return extract_metadata((grep(/^git-svn-id: /,
+ safe_qx(qw/git-cat-file commit/, shift)))[-1]);
+}
+
+sub get_commit_time {
+ my $cmt = shift;
+ defined(my $pid = open my $fh, '-|') or croak $!;
+ if (!$pid) {
+ exec qw/git-rev-list --pretty=raw -n1/, $cmt or croak $!;
+ }
+ while (<$fh>) {
+ /^committer\s(?:.+) (\d+) ([\-\+]?\d+)$/ or next;
+ my ($s, $tz) = ($1, $2);
+ if ($tz =~ s/^\+//) {
+ $s += tz_to_s_offset($tz);
+ } elsif ($tz =~ s/^\-//) {
+ $s -= tz_to_s_offset($tz);
+ }
+ close $fh;
+ return $s;
+ }
+ die "Can't get commit time for commit: $cmt\n";
+}
+
sub tz_to_s_offset {
my ($tz) = @_;
$tz =~ s/(\d\d)$//;
sub get_author_info {
my ($dest, $author, $t, $tz) = @_;
$author =~ s/(?:^\s*|\s*$)//g;
+ $dest->{a_raw} = $author;
my $_a;
if ($_authors) {
$_a = $rusers{$author} || undef;
return unless $_use_lib;
$_use_lib = eval {
require SVN::Core;
- if ($SVN::Core::VERSION lt '1.2.1') {
- die "Need SVN::Core 1.2.1 or better ",
+ if ($SVN::Core::VERSION lt '1.1.0') {
+ die "Need SVN::Core 1.1.0 or better ",
"(got $SVN::Core::VERSION) ",
"Falling back to command-line svn\n";
}
my $p = $f;
return unless ($p =~ s#^\Q$SVN_PATH\E/?##);
- my $fd = IO::File->new_tmpfile or croak $!;
+ my ($hash, $pid, $in, $out);
my $pool = SVN::Pool->new;
- my ($r, $props) = $SVN->get_file($f, $rev, $fd, $pool);
+ defined($pid = open3($in, $out, '>&STDERR',
+ qw/git-hash-object -w --stdin/)) or croak $!;
+ # redirect STDOUT for SVN 1.1.x compatibility
+ open my $stdout, '>&', \*STDOUT or croak $!;
+ open STDOUT, '>&', $in or croak $!;
+ $| = 1; # not sure if this is necessary, better safe than sorry...
+ my ($r, $props) = $SVN->get_file($f, $rev, \*STDOUT, $pool);
+ $in->flush == 0 or croak $!;
+ open STDOUT, '>&', $stdout or croak $!;
+ close $in or croak $!;
+ close $stdout or croak $!;
$pool->clear;
- $fd->flush == 0 or croak $!;
- seek $fd, 0, 0 or croak $!;
- if (my $es = $props->{'svn:eol-style'}) {
- my $new_fd = IO::File->new_tmpfile or croak $!;
- eol_cp_fd($fd, $new_fd, $es);
- close $fd or croak $!;
- $fd = $new_fd;
- seek $fd, 0, 0 or croak $!;
- $fd->flush == 0 or croak $!;
- }
- my $mode = '100644';
- if (exists $props->{'svn:executable'}) {
- $mode = '100755';
- }
+ chomp($hash = do { local $/; <$out> });
+ close $out or croak $!;
+ waitpid $pid, 0;
+ $hash =~ /^$sha1$/o or die "not a sha1: $hash\n";
+
+ my $mode = exists $props->{'svn:executable'} ? '100755' : '100644';
if (exists $props->{'svn:special'}) {
$mode = '120000';
- local $/;
- my $link = <$fd>;
+ my $link = `git-cat-file blob $hash`;
$link =~ s/^link // or die "svn:special file with contents: <",
$link, "> is not understood\n";
- seek $fd, 0, 0 or croak $!;
- truncate $fd, 0 or croak $!;
- print $fd $link or croak $!;
- seek $fd, 0, 0 or croak $!;
- $fd->flush == 0 or croak $!;
- }
- my $pid = open my $ho, '-|';
- defined $pid or croak $!;
- if (!$pid) {
- open STDIN, '<&', $fd or croak $!;
- exec qw/git-hash-object -w --stdin/ or croak $!;
+ defined($pid = open3($in, $out, '>&STDERR',
+ qw/git-hash-object -w --stdin/)) or croak $!;
+ print $in $link;
+ $in->flush == 0 or croak $!;
+ close $in or croak $!;
+ chomp($hash = do { local $/; <$out> });
+ close $out or croak $!;
+ waitpid $pid, 0;
+ $hash =~ /^$sha1$/o or die "not a sha1: $hash\n";
}
- chomp(my $hash = do { local $/; <$ho> });
- close $ho or croak $?;
- $hash =~ /^$sha1$/o or die "not a sha1: $hash\n";
print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!;
- close $fd or croak $?;
}
sub libsvn_log_entry {
chomp(my $c = do { local $/; <$fh> });
close $fh;
if (defined $c && length $c) {
- my ($url, $rev, $uuid) = extract_metadata((grep(/^git-svn-id: /,
- safe_qx(qw/git-cat-file commit/, $c)))[0]);
+ my ($url, $rev, $uuid) = cmt_metadata($c);
return ($rev, $c);
}
return (undef, undef);
if ($_use_lib) {
# should be OK to use Pool here (r1 - r0) should be small
my $pool = SVN::Pool->new;
- $SVN->get_log("/$path", $r0, $r1, 0, 1, 1, sub {$nr++},$pool);
+ libsvn_get_log($SVN, "/$path", $r0, $r1,
+ 0, 1, 1, sub {$nr++}, $pool);
$pool->clear;
} else {
my ($url, undef) = repo_path_split($SVN_URL);
return undef;
}
+sub libsvn_get_log {
+ my ($ra, @args) = @_;
+ if ($SVN::Core::VERSION le '1.2.0') {
+ splice(@args, 3, 1);
+ }
+ $ra->get_log(@args);
+}
+
sub libsvn_new_tree {
if (my $log_entry = libsvn_find_parent_branch(@_)) {
return $log_entry;
my $i = $tree_paths->{$x};
my ($r, $parent) = find_rev_before($r0, $i, 1);
if (defined $r && defined $parent && revisions_eq($x,$r,$r0)) {
+ my ($url_b, undef, $uuid_b) = cmt_metadata($c);
+ my ($url_a, undef, $uuid_a) = cmt_metadata($parent);
+ next if ($url_a && $url_b && $url_a eq $url_b &&
+ $uuid_b eq $uuid_a);
$grafts->{$c}->{$parent} = 1;
}
}
return $ret;
}
+sub copy_remote_ref {
+ my $origin = $_cp_remote ? $_cp_remote : 'origin';
+ my $ref = "refs/remotes/$GIT_SVN";
+ if (safe_qx('git-ls-remote', $origin, $ref)) {
+ sys(qw/git fetch/, $origin, "$ref:$ref");
+ } else {
+ die "Unable to find remote reference: ",
+ "refs/remotes/$GIT_SVN on $origin\n";
+ }
+}
+
package SVN::Git::Editor;
use vars qw/@ISA/;
use strict;
exec qw/git-ls-tree --name-only -r -z/, $self->{c} or croak $!;
}
local $/ = "\0";
+ my @svn_path = split m#/#, $self->{svn_path};
while (<$fh>) {
chomp;
- $_ = $self->{svn_path} . '/' . $_;
- my ($dn) = ($_ =~ m#^(.*?)/?(?:[^/]+)$#);
- delete $rm->{$dn};
- last unless %$rm;
+ my @dn = (@svn_path, (split m#/#, $_));
+ while (pop @dn) {
+ delete $rm->{join '/', @dn};
+ }
+ unless (%$rm) {
+ close $fh;
+ return;
+ }
}
+ close $fh;
+
my ($r, $p, $bat) = ($self->{r}, $self->{pool}, $self->{bat});
foreach my $d (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$rm) {
$self->close_directory($bat->{$d}, $p);