X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-convert;h=42955a482ed378bcfaea9d2f1df4909bca6a11a2;hp=56a810eb054ffc1ea41585eab1052dabb0b7bc12;hb=refs%2Fheads%2Fmaster;hpb=227a1d886672767e37cc86a3432952c14eb8a143 diff --git a/script/public-inbox-convert b/script/public-inbox-convert index 56a810eb..42955a48 100755 --- a/script/public-inbox-convert +++ b/script/public-inbox-convert @@ -1,79 +1,110 @@ #!/usr/bin/perl -w -# Copyright (C) 2018-2019 all contributors +# Copyright (C) 2018-2021 all contributors # License: AGPL-3.0+ use strict; -use warnings; +use v5.10.1; use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev); -use PublicInbox::InboxWritable; -use PublicInbox::Config; -use PublicInbox::V2Writable; -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 or die $usage; -my $new_dir = shift or die $usage; +my $help = < 1, + # index defaults: + quiet => -1, compact => 0, maxsize => undef, fsync => 1, + reindex => 1, # we always reindex +}; +GetOptions($opt, qw(jobs|j=i index! help|h 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|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 $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 $config = eval { PublicInbox::Config->new }; -$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) { + +require PublicInbox::Config; +require PublicInbox::InboxWritable; + +my $cfg = PublicInbox::Config->new; +my @old = PublicInbox::Admin::resolve_inboxes([$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 = { - 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"; +die "Only conversion from v1 inboxes is supported\n" if $old->version >= 2; + +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 }; -$new->{inboxdir} = abs_path($new_dir); +$new->{inboxdir} = $cfg->rel2abs_collapsed($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; 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: $!\n"; + require File::Copy; # preserves permissions: + File::Copy::cp($src, $dst) or die "cp $src, $dst failed: $!\n"; } $old->with_umask(sub { my $old_cfg = "$old->{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); + $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->{inboxdir}/description"; @@ -86,10 +117,9 @@ $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 $h = '[0-9a-f]'; @@ -102,12 +132,12 @@ while (<$rd>) { $state = 'commit'; } 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') { @@ -115,9 +145,9 @@ while (<$rd>) { my ($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; $last = 'm'; next; } @@ -125,29 +155,33 @@ while (<$rd>) { 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 (:[0-9]+)}) { - $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->{mg}->add_epoch(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;