#!/usr/bin/perl -w
# Copyright (C) 2018-2020 all contributors
# License: AGPL-3.0+
use strict;
use warnings;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
use PublicInbox::InboxWritable;
use PublicInbox::Config;
use PublicInbox::Admin;
use PublicInbox::V2Writable;
use PublicInbox::Git;
use PublicInbox::Spawn qw(spawn);
use Cwd 'abs_path';
use File::Copy 'cp'; # preserves permissions:
my $usage = "Usage: public-inbox-convert OLD NEW\n";
my $jobs;
my $index = 1;
my %opts = (
'--jobs|j=i' => \$jobs,
'--index!' => \$index,
);
GetOptions(%opts) or die "bad command-line args\n$usage";
my $old_dir = shift(@ARGV) or die $usage;
my $new_dir = shift(@ARGV) or die $usage;
die "$new_dir exists\n" if -d $new_dir;
die "$old_dir not a directory\n" unless -d $old_dir;
my $config = eval { PublicInbox::Config->new };
$old_dir = abs_path($old_dir);
my $old;
if ($config) {
$config->each_inbox(sub {
$old = $_[0] if abs_path($_[0]->{inboxdir}) eq $old_dir;
});
}
unless ($old) {
warn "W: $old_dir not configured in " .
PublicInbox::Config::default_file() . "\n";
$old = {
inboxdir => $old_dir,
name => 'ignored',
address => [ 'old@example.com' ],
};
$old = PublicInbox::Inbox->new($old);
}
$old = PublicInbox::InboxWritable->new($old);
if ($old->version >= 2) {
die "Only conversion from v1 inboxes is supported\n";
}
$old->{indexlevel} //= PublicInbox::Admin::detect_indexlevel($old);
if ($index) {
my $mods = {};
PublicInbox::Admin::scan_ibx_modules($mods, $old);
PublicInbox::Admin::require_or_die(keys %$mods);
}
my $new = { %$old };
$new->{inboxdir} = abs_path($new_dir);
$new->{version} = 2;
$new = PublicInbox::InboxWritable->new($new);
my $v2w;
$old->umask_prepare;
sub link_or_copy ($$) {
my ($src, $dst) = @_;
link($src, $dst) and return;
$!{EXDEV} or warn "link $src, $dst failed: $!, trying cp\n";
cp($src, $dst) or die "cp $src, $dst failed: $!\n";
}
$old->with_umask(sub {
my $old_cfg = "$old->{inboxdir}/config";
local $ENV{GIT_CONFIG} = $old_cfg;
my $new_cfg = "$new->{inboxdir}/all.git/config";
$v2w = PublicInbox::V2Writable->new($new, 1);
$v2w->init_inbox($jobs);
unlink $new_cfg;
link_or_copy($old_cfg, $new_cfg);
if (my $alt = $new->{altid}) {
require PublicInbox::AltId;
foreach my $i (0..$#$alt) {
my $src = PublicInbox::AltId->new($old, $alt->[$i], 0);
$src->mm_alt or next;
my $dst = PublicInbox::AltId->new($new, $alt->[$i], 1);
$dst = $dst->{filename};
$src->mm_alt->{dbh}->sqlite_backup_to_file($dst);
}
}
my $desc = "$old->{inboxdir}/description";
link_or_copy($desc, "$new->{inboxdir}/description") if -e $desc;
my $clone = "$old->{inboxdir}/cloneurl";
if (-e $clone) {
warn <<"";
$clone may not be valid after migrating to v2, not copying
}
});
my $state = '';
my $head = $old->{ref_head} || 'HEAD';
my ($rd, $pid) = $old->git->popen(qw(fast-export --use-done-feature), $head);
$v2w->idx_init;
my $im = $v2w->importer;
my ($r, $w) = $im->gfi_start;
my $h = '[0-9a-f]';
my %D;
my $last;
while (<$rd>) {
if ($_ eq "blob\n") {
$state = 'blob';
} elsif (/^commit /) {
$state = 'commit';
} elsif (/^data ([0-9]+)/) {
my $len = $1;
$w->print($_) or $im->wfail;
while ($len) {
my $n = read($rd, my $tmp, $len) or die "read: $!";
warn "$n != $len\n" if $n != $len;
$len -= $n;
$w->print($tmp) or $im->wfail;
}
next;
} elsif ($state eq 'commit') {
if (m{^M 100644 :([0-9]+) (${h}{2}/${h}{38})}o) {
my ($mark, $path) = ($1, $2);
$D{$path} = $mark;
if ($last && $last ne 'm') {
$w->print("D $last\n") or $im->wfail;
}
$w->print("M 100644 :$mark m\n") or $im->wfail;
$last = 'm';
next;
}
if (m{^D (${h}{2}/${h}{38})}o) {
my $mark = delete $D{$1};
defined $mark or die "undeleted path: $1\n";
if ($last && $last ne 'd') {
$w->print("D $last\n") or $im->wfail;
}
$w->print("M 100644 :$mark d\n") or $im->wfail;
$last = 'd';
next;
}
}
last if $_ eq "done\n";
$w->print($_) or $im->wfail;
}
$w = $r = undef;
close $rd or die "close fast-export: $!\n";
waitpid($pid, 0) or die "waitpid failed: $!\n";
$? == 0 or die "fast-export failed: $?\n";
$v2w->done;
if (my $mm = $old->mm) {
$old->cleanup;
$mm->{dbh}->sqlite_backup_to_file("$new_dir/msgmap.sqlite3");
# we want to trigger a reindex, not a from scratch index if
# we're reusing the msgmap from an existing v1 installation.
$v2w->idx_init;
my $epoch0 = PublicInbox::Git->new($v2w->git_init(0));
chop(my $cmt = $epoch0->qx(qw(rev-parse --verify), $head));
$v2w->last_epoch_commit(0, $cmt);
}
$v2w->index_sync({reindex => 1}) if $index;
$v2w->done;