#!/usr/bin/perl -w
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <http://www.gnu.org/licenses/agpl-3.0.txt>
use strict;
-use warnings;
+use v5.10.1;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-use PublicInbox::MIME;
-use PublicInbox::InboxWritable;
-use PublicInbox::Config;
-use PublicInbox::V2Writable;
-use PublicInbox::Import;
-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";
-GetOptions(%opts) or die "bad command-line args\n$usage";
-my $old_dir = shift or die $usage;
-my $new_dir = shift or die $usage;
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: public-inbox-convert [options] OLD NEW
+
+ convert v1 format inboxes to v2
+
+options:
+
+ --no-index do not index after conversion
+ --jobs=NUM set shards (NUM=0)
+ --verbose | -v increase verbosity (may be repeated)
+
+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)
+ --compact | -c run public-inbox-compact(1) after indexing
+ --sequential-shard index Xapian shards sequentially for slow storage
+ --batch-size=BYTES flush changes to OS after a given number of bytes
+ --max-size=BYTES do not index messages larger than the given size
+
+See public-inbox-convert(1) man page for full documentation.
+EOF
+
+my $opt = {
+ index => 1,
+ # index defaults:
+ quiet => -1, compact => 0, maxsize => undef, fsync => 1,
+ reindex => 1, # we always reindex
+};
+GetOptions($opt, qw(jobs|j=i index! help|h),
+ # 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 $help;
+if ($opt->{help}) { print $help; exit 0 };
+my $old_dir = shift(@ARGV) // '';
+my $new_dir = shift(@ARGV) // '';
+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;
-my $config = PublicInbox::Config->new;
-$old_dir = abs_path($old_dir);
+
+require Cwd;
+Cwd->import('abs_path');
+require PublicInbox::Config;
+require PublicInbox::InboxWritable;
+
+my $abs = abs_path($old_dir);
+die "failed to resolve $old_dir: $!\n" if (!defined($abs));
+
+my $cfg = PublicInbox::Config->new;
my $old;
-$config->each_inbox(sub {
- $old = $_[0] if abs_path($_[0]->{mainrepo}) eq $old_dir;
+$cfg->each_inbox(sub {
+ $old = $_[0] if abs_path($_[0]->{inboxdir}) eq $old_dir;
});
-unless ($old) {
+if ($old) {
+ $old = PublicInbox::InboxWritable->new($old);
+} else {
warn "W: $old_dir not configured in " .
PublicInbox::Config::default_file() . "\n";
- $old = {
- mainrepo => $old_dir,
+ $old = PublicInbox::InboxWritable->new({
+ inboxdir => $old_dir,
name => 'ignored',
+ -primary_address => 'old@example.com',
address => [ 'old@example.com' ],
- };
- $old = PublicInbox::Inbox->new($old);
+ });
}
-$old = PublicInbox::InboxWritable->new($old);
-if (($old->{version} || 1) >= 2) {
- die "Only conversion from v1 inboxes is supported\n";
+die "Only conversion from v1 inboxes is supported\n" if $old->version >= 2;
+
+require File::Spec;
+require PublicInbox::Admin;
+my $detected = PublicInbox::Admin::detect_indexlevel($old);
+$old->{indexlevel} //= $detected;
+my $env;
+if ($opt->{'index'}) {
+ my $mods = {};
+ PublicInbox::Admin::scan_ibx_modules($mods, $old);
+ PublicInbox::Admin::require_or_die(keys %$mods);
+ PublicInbox::Admin::progress_prepare($opt);
+ $env = PublicInbox::Admin::index_prepare($opt, $cfg);
}
+local %ENV = (%$env, %ENV) if $env;
my $new = { %$old };
-$new->{mainrepo} = abs_path($new_dir);
+$new->{inboxdir} = File::Spec->canonpath($new_dir);
$new->{version} = 2;
-$new = PublicInbox::InboxWritable->new($new);
+$new = PublicInbox::InboxWritable->new($new, { nproc => $opt->{jobs} });
+$new->{-no_fsync} = 1 if !$opt->{fsync};
my $v2w;
$old->umask_prepare;
my ($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: $!\n";
+ require File::Copy; # preserves permissions:
+ File::Copy::cp($src, $dst) or die "cp $src, $dst failed: $!\n";
}
$old->with_umask(sub {
- my $old_cfg = "$old->{mainrepo}/config";
+ my $old_cfg = "$old->{inboxdir}/config";
local $ENV{GIT_CONFIG} = $old_cfg;
- my $new_cfg = "$new->{mainrepo}/all.git/config";
- $v2w = PublicInbox::V2Writable->new($new, 1);
- $v2w->init_inbox($jobs);
+ my $new_cfg = "$new->{inboxdir}/all.git/config";
+ $v2w = $new->importer(1);
+ $v2w->init_inbox(delete $opt->{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;
+ $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->{mainrepo}/description";
- link_or_copy($desc, "$new->{mainrepo}/description") if -e $desc;
- my $clone = "$old->{mainrepo}/cloneurl";
+ 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 $state = '';
-my ($prev, $from);
my $head = $old->{ref_head} || 'HEAD';
my ($rd, $pid) = $old->git->popen(qw(fast-export --use-done-feature), $head);
-$v2w->idx_init;
+$v2w->idx_init($opt);
my $im = $v2w->importer;
my ($r, $w) = $im->gfi_start;
my $h = '[0-9a-f]';
$state = 'blob';
} elsif (/^commit /) {
$state = 'commit';
- } elsif (/^data (\d+)/) {
+ } elsif (/^data ([0-9]+)/) {
my $len = $1;
- $w->print($_) or $im->wfail;
+ print $w $_ 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;
+ print $w $tmp or $im->wfail;
}
next;
} elsif ($state eq 'commit') {
- if (m{^M 100644 :(\d+) (${h}{2}/${h}{38})}o) {
+ 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;
+ print $w "D $last\n" or $im->wfail;
}
- $w->print("M 100644 :$mark m\n") or $im->wfail;
+ print $w "M 100644 :$mark m\n" or $im->wfail;
$last = 'm';
next;
}
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;
+ print $w "D $last\n" or $im->wfail;
}
- $w->print("M 100644 :$mark d\n") or $im->wfail;
+ print $w "M 100644 :$mark d\n" or $im->wfail;
$last = 'd';
next;
}
- if (m{^from (:\d+)}) {
- $prev = $from;
- $from = $1;
- # no next
- }
}
last if $_ eq "done\n";
- $w->print($_) or $im->wfail;
+ print $w $_ 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";
-my $mm = $old->mm;
-$mm->{dbh}->sqlite_backup_to_file("$new_dir/msgmap.sqlite3") if $mm;
+$r = $w = undef; # v2w->done does the actual close and error checking
$v2w->done;
-if ($index) {
- $v2w->index_sync;
- $v2w->done;
+if (my $old_mm = $old->mm) {
+ $old->cleanup;
+ $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);
+ $v2w->{mm}->{dbh}->sqlite_backup_from_file($old_mm);
+
+ 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($opt) if delete $opt->{'index'};
+$v2w->done;