No ext_urls

[public-inbox.git] / script / public-inbox-convert

diff --git a/script/public-inbox-convert b/script/public-inbox-convert
index 275857fad4c8864c74ff95f69bbeb6d620eb2e5a..42955a482ed378bcfaea9d2f1df4909bca6a11a2 100755 (executable)
--- a/script/public-inbox-convert
+++ b/script/public-inbox-convert
@@ -1,12 +1,11 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <http://www.gnu.org/licenses/agpl-3.0.txt>
 use strict;
 use v5.10.1;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-my $usage = 'Usage: public-inbox-convert [options] OLD NEW';
 my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
-usage: $usage
+usage: public-inbox-convert [options] OLD NEW
 
   convert v1 format inboxes to v2
 
@@ -15,9 +14,8 @@ options:
   --no-index          do not index after conversion
   --jobs=NUM          set shards (NUM=0)
   --verbose | -v      increase verbosity (may be repeated)
-  --help | -?         show this help
 
-index options (see public-inbox-index(1) manpage for full description):
+index options (see public-inbox-index(1) man page for full description):
 
   --no-fsync          speed up indexing, risk corruption on power outage
   -L LEVEL            `basic', `medium', or `full' (default: full)
@@ -35,49 +33,38 @@ my $opt = {
        quiet => -1, compact => 0, maxsize => undef, fsync => 1,
        reindex => 1, # we always reindex
 };
-GetOptions($opt, qw(jobs|j=i index! help|?),
+GetOptions($opt, qw(jobs|j=i index! help|h C=s@),
                # index options
                qw(verbose|v+ rethread compact|c+ fsync|sync!
                indexlevel|index-level|L=s max_size|max-size=s
                batch_size|batch-size=s
-               sequential_shard|sequential-shard|seq-shard
-               )) or die <<EOF;
-bad command-line args\n$usage
-EOF
+               sequential-shard|seq-shard
+               )) or die $help;
 if ($opt->{help}) { print $help; exit 0 };
+require PublicInbox::Admin;
+PublicInbox::Admin::do_chdir(delete $opt->{C});
 my $old_dir = shift(@ARGV) // '';
 my $new_dir = shift(@ARGV) // '';
-die $usage if (scalar(@ARGV) || $new_dir eq '' || $old_dir eq '');
+die $help if (scalar(@ARGV) || $new_dir eq '' || $old_dir eq '');
 die "$new_dir exists\n" if -d $new_dir;
 die "$old_dir not a directory\n" unless -d $old_dir;
 
-require Cwd;
-Cwd->import('abs_path');
 require PublicInbox::Config;
 require PublicInbox::InboxWritable;
 
-$old_dir = abs_path($old_dir);
 my $cfg = PublicInbox::Config->new;
-my $old;
-$cfg->each_inbox(sub {
-       $old = $_[0] if abs_path($_[0]->{inboxdir}) eq $old_dir;
-});
-if ($old) {
-       $old = PublicInbox::InboxWritable->new($old);
-} else {
+my @old = PublicInbox::Admin::resolve_inboxes([$old_dir], undef, $cfg);
+@old > 1 and die "BUG: resolved several inboxes from $old_dir:\n",
+               map { "\t$_->{inboxdir}\n" } @old;
+my $old = PublicInbox::InboxWritable->new($old[0]);
+if (delete $old->{-unconfigured}) {
        warn "W: $old_dir not configured in " .
                PublicInbox::Config::default_file() . "\n";
-       $old = PublicInbox::InboxWritable->new({
-               inboxdir => $old_dir,
-               name => 'ignored',
-               -primary_address => 'old@example.com',
-               address => [ 'old@example.com' ],
-       });
 }
 die "Only conversion from v1 inboxes is supported\n" if $old->version >= 2;
 
-require PublicInbox::Admin;
-$old->{indexlevel} //= PublicInbox::Admin::detect_indexlevel($old);
+my $detected = PublicInbox::Admin::detect_indexlevel($old);
+$old->{indexlevel} //= $detected;
 my $env;
 if ($opt->{'index'}) {
        my $mods = {};
@@ -88,12 +75,11 @@ if ($opt->{'index'}) {
 }
 local %ENV = (%$env, %ENV) if $env;
 my $new = { %$old };
-$new->{inboxdir} = abs_path($new_dir);
+$new->{inboxdir} = $cfg->rel2abs_collapsed($new_dir);
 $new->{version} = 2;
 $new = PublicInbox::InboxWritable->new($new, { nproc => $opt->{jobs} });
 $new->{-no_fsync} = 1 if !$opt->{fsync};
 my $v2w;
-$old->umask_prepare;
 
 sub link_or_copy ($$) {
        my ($src, $dst) = @_;
@@ -115,10 +101,10 @@ $old->with_umask(sub {
                require PublicInbox::AltId;
                foreach my $i (0..$#$alt) {
                        my $src = PublicInbox::AltId->new($old, $alt->[$i], 0);
-                       $src->mm_alt or next;
+                       $src = $src->mm_alt or next;
+                       $src = $src->{dbh}->sqlite_db_filename;
                        my $dst = PublicInbox::AltId->new($new, $alt->[$i], 1);
-                       $dst = $dst->{filename};
-                       $src->mm_alt->{dbh}->sqlite_backup_to_file($dst);
+                       $dst->mm_alt->{dbh}->sqlite_backup_from_file($src);
                }
        }
        my $desc = "$old->{inboxdir}/description";
@@ -184,14 +170,16 @@ waitpid($pid, 0) or die "waitpid failed: $!\n";
 $? == 0 or die "fast-export failed: $?\n";
 $r = $w = undef; # v2w->done does the actual close and error checking
 $v2w->done;
-if (my $mm = $old->mm) {
+if (my $old_mm = $old->mm) {
        $old->cleanup;
-       $mm->{dbh}->sqlite_backup_to_file("$new_dir/msgmap.sqlite3");
+       $old_mm = $old_mm->{dbh}->sqlite_db_filename;
 
        # we want to trigger a reindex, not a from scratch index if
        # we're reusing the msgmap from an existing v1 installation.
        $v2w->idx_init($opt);
-       my $epoch0 = PublicInbox::Git->new($v2w->git_init(0));
+       $v2w->{mm}->{dbh}->sqlite_backup_from_file($old_mm);
+
+       my $epoch0 = PublicInbox::Git->new($v2w->{mg}->add_epoch(0));
        chop(my $cmt = $epoch0->qx(qw(rev-parse --verify), $head));
        $v2w->last_epoch_commit(0, $cmt);
 }