script/public-inbox-index

#!perl -w
# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Basic tool to create a Xapian search index for a public-inbox.
# Usage with libeatmydata <https://www.flamingspork.com/projects/libeatmydata/>
# highly recommended: eatmydata public-inbox-index INBOX_DIR

use strict;
use v5.10.1;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
usage: public-inbox-index [options] INBOX_DIR

  Create and update per-inbox search indices

options:

  --no-fsync          speed up indexing, risk corruption on power outage
  -L LEVEL            `basic', `medium', or `full' (default: full)
  -E EXTINDEX         update extindex (default: `all')
  --all               index all configured inboxes
  --compact | -c      run public-inbox-compact(1) after indexing
  --sequential-shard  index Xapian shards sequentially for slow storage
  --jobs=NUM          set or disable parallelization (NUM=0)
  --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
  --reindex           index previously indexed data (if upgrading)
  --since=DATE        limit --reindex to changes after DATE
  --until=DATE        limit --reindex to changes before DATE
  --rethread          regenerate thread IDs (if upgrading, use sparingly)
  --prune             prune git storage on discontiguous history
  --verbose | -v      increase verbosity (may be repeated)

BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
See public-inbox-index(1) man page for full documentation.
EOF
my $opt = {
	quiet => -1, compact => 0, max_size => undef, fsync => 1,
	'update-extindex' => [], # ":s@" optional arg sets '' if no arg given
};
GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
		fsync|sync! xapian_only|xapian-only dangerous
		indexlevel|index-level|L=s max_size|max-size=s
		batch_size|batch-size=s
		since|after=s until|before=s
		sequential-shard|seq-shard
		multi-pack-index!
		no-update-extindex update-extindex|E=s@
		fast-noop|F skip-docdata all C=s@ help|h))
	or die $help;
if ($opt->{help}) { print $help; exit 0 };
die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
if ($opt->{xapian_only} && !$opt->{reindex}) {
	die "--xapian-only requires --reindex\n";
}
if ($opt->{reindex} && delete($opt->{'fast-noop'})) {
	warn "--fast-noop ignored with --reindex\n";
}

# require lazily to speed up --help
require PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-index');
PublicInbox::Admin::do_chdir(delete $opt->{C});

my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
$opt->{-use_cwd} = 1;
my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
PublicInbox::Admin::require_or_die('-index');
unless (@ibxs) { print STDERR $help; exit 1 }
require PublicInbox::InboxWritable;

my (@eidx, %eidx_seen);
my $update_extindex = $opt->{'update-extindex'};
if (!scalar(@$update_extindex) && (my $ALL = $cfg->ALL)) {
	# extindex and normal inboxes may have different owners
	push(@$update_extindex, 'all') if -w $ALL->{topdir};
}
@$update_extindex = () if $opt->{'no-update-extindex'};
if (scalar @$update_extindex) {
	PublicInbox::Admin::require_or_die('-search');
	require PublicInbox::ExtSearchIdx;
}
for my $ei_name (@$update_extindex) {
	my $es = $cfg->lookup_ei($ei_name);
	my $topdir;
	if (!$es && -d $ei_name) { # allow dirname or config section name
		$topdir = $ei_name;
	} elsif ($es) {
		$topdir = $es->{topdir};
	} else {
		die "extindex `$ei_name' not configured or found\n";
	}
	my $o = { %$opt };
	delete $o->{indexlevel} if ($o->{indexlevel}//'') eq 'basic';
	$eidx_seen{$topdir} //=
		push(@eidx, PublicInbox::ExtSearchIdx->new($topdir, $o));
}
my $mods = {};
my @eidx_unconfigured;
foreach my $ibx (@ibxs) {
	$ibx = PublicInbox::InboxWritable->new($ibx);
	# detect_indexlevel may also set $ibx->{-skip_docdata}
	my $detected = $ibx->detect_indexlevel;
	# XXX: users can shoot themselves in the foot, with opt->{indexlevel}
	$ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ?
			'full' : $detected);
	PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
	if (@eidx && $ibx->{-unconfigured}) {
		push @eidx_unconfigured, "  $ibx->{inboxdir}\n";
	}
}
warn <<EOF if @eidx_unconfigured;
The following inboxes are unconfigured and will not be updated in
@$update_extindex:\n@eidx_unconfigured
EOF

$opt->{compact} = 0 if !$mods->{'Xapian'}; # (or old Search::Xapian)

PublicInbox::Admin::require_or_die(keys %$mods);
my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
local %ENV = (%ENV, %$env) if $env;
PublicInbox::Xapcmd::check_compact() if $opt->{compact};
PublicInbox::Admin::progress_prepare($opt);
for my $ibx (@ibxs) {
	if ($opt->{compact} >= 2) {
		PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt});
	}
	$ibx->{-no_fsync} = 1 if !$opt->{fsync};
	$ibx->{-dangerous} = 1 if $opt->{dangerous};
	$ibx->{-skip_docdata} //= $opt->{'skip-docdata'};

	my $ibx_opt = $opt;
	if (defined(my $s = $ibx->{lc('indexSequentialShard')})) {
		defined(my $v = $cfg->git_bool($s)) or die <<EOL;
publicInbox.$ibx->{name}.indexSequentialShard not boolean
EOL
		$ibx_opt = { %$opt, 'sequential-shard' => $v };
	}
	my $nidx = PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
	last if $ibx_opt->{quit};
	if (my $copt = $opt->{compact_opt}) {
		local $copt->{jobs} = 0 if $ibx_opt->{'sequential-shard'};
		PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
	}
	last if $ibx_opt->{quit};
	next if $ibx->{-unconfigured} || !$nidx;
	for my $eidx (@eidx) {
		$eidx->attach_inbox($ibx);
	}
}
my $pr = $opt->{-progress};
for my $eidx (@eidx) {
	$pr->("indexing $eidx->{topdir} ...\n") if $pr;
	$eidx->eidx_sync($opt);
	last if $opt->{quit};
}