#!perl -w
# Copyright (C) 2015-2020 all contributors
# License: AGPL-3.0+
# Basic tool to create a Xapian search index for a public-inbox.
# Usage with 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 $usage = 'public-inbox-index [options] INBOX_DIR';
my $help = < -1, compact => 0, max_size => undef, fsync => 1 };
GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
fsync|sync! xapian_only|xapian-only
indexlevel|index-level|L=s max_size|max-size=s
batch_size|batch-size=s
sequential_shard|seq-shard|sequential-shard
help|?))
or die "bad command-line args\n$usage";
if ($opt->{help}) { print $help; exit 0 };
die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
if ($opt->{xapian_only} && !$opt->{reindex}) {
die "--xapian-only requires --reindex\n";
}
# require lazily to speed up --help
require PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-index');
if ($opt->{compact}) {
require PublicInbox::Xapcmd;
PublicInbox::Xapcmd::check_compact();
$compact_opt = { -coarse_lock => 1, compact => 1 };
if (defined(my $jobs = $opt->{jobs})) {
$compact_opt->{jobs} = $jobs;
}
}
my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg);
PublicInbox::Admin::require_or_die('-index');
unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
my $max_size = $opt->{max_size} // $cfg->{lc('publicInbox.indexMaxSize')};
if (defined $max_size) {
PublicInbox::Admin::parse_unsigned(\$max_size) or
die "`publicInbox.indexMaxSize=$max_size' not parsed\n";
$opt->{max_size} = $max_size;
}
my $bs = $opt->{batch_size} // $cfg->{lc('publicInbox.indexBatchSize')};
if (defined $bs) {
PublicInbox::Admin::parse_unsigned(\$bs) or
die "`publicInbox.indexBatchSize=$bs' not parsed\n";
$opt->{batch_size} = $bs;
}
# out-of-the-box builds of Xapian 1.4.x are still limited to 32-bit
# https://getting-started-with-xapian.readthedocs.io/en/latest/concepts/indexing/limitations.html
local $ENV{XAPIAN_FLUSH_THRESHOLD} ||= '4294967295' if defined($bs);
my $s = $opt->{sequential_shard} //
$cfg->{lc('publicInbox.indexSequentialShard')};
if (defined $s) {
my $v = $cfg->git_bool($s);
defined($v) or
die "`publicInbox.indexSequentialShard=$s' not boolean\n";
$opt->{sequential_shard} = $v;
}
my $mods = {};
foreach my $ibx (@ibxs) {
# XXX: users can shoot themselves in the foot, with opt->{indexlevel}
$ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ?
'full' : PublicInbox::Admin::detect_indexlevel($ibx));
PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
}
PublicInbox::Admin::require_or_die(keys %$mods);
require PublicInbox::InboxWritable;
PublicInbox::Admin::progress_prepare($opt);
for my $ibx (@ibxs) {
$ibx = PublicInbox::InboxWritable->new($ibx);
if ($opt->{compact} >= 2) {
PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
}
$ibx->{-no_fsync} = 1 if !$opt->{fsync};
my $ibx_opt = $opt;
if (defined(my $s = $ibx->{lc('indexSequentialShard')})) {
defined(my $v = $cfg->git_bool($s)) or die <{name}.indexSequentialShard not boolean
EOL
$ibx_opt = { %$opt, sequential_shard => $v };
}
PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
if ($compact_opt) {
local $compact_opt->{jobs} = 0 if $ibx_opt->{sequential_shard};
PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
}
}