#!/usr/bin/perl -w
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 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 git repository
-# configured for public-inbox.
+# 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 REPO_DIR
+# highly recommended: eatmydata public-inbox-index INBOX_DIR
use strict;
use warnings;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-my $usage = "public-inbox-index REPO_DIR";
-use PublicInbox::Admin qw(resolve_repo_dir);
+my $usage = "public-inbox-index INBOX_DIR";
+use PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-index');
-require PublicInbox::Config;
+use PublicInbox::Xapcmd;
-my $config = eval { PublicInbox::Config->new } || eval {
- warn "public-inbox unconfigured for serving, indexing anyways...\n";
- undef;
-};
+my $compact_opt;
+my $opt = { quiet => -1, compact => 0, maxsize => undef, fsync => 1 };
+GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
+ fsync|sync! xapianonly|xapian-only
+ indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s
+ sequentialshard|seq-shard|sequential-shard))
+ or die "bad command-line args\n$usage";
+die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
-my $reindex;
-my $prune;
-my $jobs = undef;
-my $indexlevel;
-my %opts = (
- '--reindex' => \$reindex,
- '--jobs|j=i' => \$jobs,
- '--prune' => \$prune,
- 'L|indexlevel=s' => \$indexlevel,
-);
-GetOptions(%opts) or die "bad command-line args\n$usage";
-die "--jobs must be positive\n" if defined $jobs && $jobs < 0;
+if ($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 @dirs;
+my $cfg = PublicInbox::Config->new;
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg);
+PublicInbox::Admin::require_or_die('-index');
+unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
-if (@ARGV) {
- @dirs = map { resolve_repo_dir($_) } @ARGV;
-} else {
- @dirs = (resolve_repo_dir());
+my $max_size = $opt->{maxsize} // $cfg->{lc('publicInbox.indexMaxSize')};
+if (defined $max_size) {
+ PublicInbox::Admin::parse_unsigned(\$max_size) or
+ die "`publicInbox.indexMaxSize=$max_size' not parsed\n";
}
-sub usage { print STDERR "Usage: $usage\n"; exit 1 }
-usage() unless @dirs;
+my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')};
+if (defined $bs) {
+ PublicInbox::Admin::parse_unsigned(\$bs) or
+ die "`publicInbox.indexBatchSize=$bs' not parsed\n";
+}
+local $PublicInbox::SearchIdx::BATCH_BYTES = $bs if defined($bs);
-defined($config) and $config->each_inbox(sub {
- my ($ibx) = @_;
+# 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);
- for my $i (0..$#dirs) {
- next if $dirs[$i] ne $ibx->{mainrepo};
- $dirs[$i] = $ibx;
- }
-});
+my $s = $opt->{sequentialshard} //
+ $cfg->{lc('publicInbox.indexSequentialShard')};
+if (defined $s) {
+ my $v = $cfg->git_bool($s);
+ defined($v) or
+ die "`publicInbox.indexSequentialShard=$s' not boolean\n";
+ $opt->{sequentialshard} = $v;
+}
-my @inboxes;
my $mods = {};
-
-foreach my $dir (@dirs) {
- my $ibx = $dir;
- if (!ref($ibx)) {
- unless (-d $dir) {
- die "$dir does not appear to be an inbox repository\n";
- }
- $ibx = PublicInbox::Inbox->new({
- mainrepo => $dir,
- name => 'unnamed',
- indexlevel => $indexlevel,
- version => -f "$dir/inbox.lock" ? 2 : 1,
- });
- } elsif (defined $indexlevel && !defined($ibx->{indexlevel})) {
- # XXX: users can shoot themselves in the foot, with this...
- $ibx->{indexlevel} = $indexlevel;
- }
- push @inboxes, $ibx;
+foreach my $ibx (@ibxs) {
+ # XXX: users can shoot themselves in the foot, with opt->{indexlevel}
+ $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapianonly} ?
+ 'full' : PublicInbox::Admin::detect_indexlevel($ibx));
+ $ibx->{index_max_size} = $max_size;
PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
}
PublicInbox::Admin::require_or_die(keys %$mods);
+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};
-require PublicInbox::SearchIdx;
-index_inbox($_) for @inboxes;
-
-sub index_inbox {
- my ($repo) = @_;
- if (ref($repo) && ($repo->{version} || 1) == 2) {
- eval { require PublicInbox::V2Writable };
- die "v2 requirements not met: $@\n" if $@;
- my $v2w = eval {
- PublicInbox::V2Writable->new($repo, {nproc=>$jobs});
- };
- if (defined $jobs) {
- if ($jobs == 0) {
- $v2w->{parallel} = 0;
- } else {
- my $n = $v2w->{partitions};
- if ($jobs != ($n + 1)) {
- warn
-"Unable to respect --jobs=$jobs, inbox was created with $n partitions\n";
- }
- }
- }
- local $SIG{__WARN__} = sub {
- print STDERR $v2w->{current_info}, ': ', @_;
- };
- $v2w->index_sync({ reindex => $reindex, prune => $prune });
- } else {
- my $s = PublicInbox::SearchIdx->new($repo, 1);
- $s->index_sync({ reindex => $reindex });
+ my $ibx_opt = $opt;
+ if (defined(my $s = $ibx->{indexsequentialshard})) {
+ defined(my $v = $cfg->git_bool($s)) or die <<EOL;
+publicInbox.$ibx->{name}.indexSequentialShard not boolean
+EOL
+ $ibx_opt = { %$opt, sequentialshard => $v };
+ }
+ PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
+ if ($compact_opt) {
+ local $compact_opt->{jobs} = 0 if $ibx_opt->{sequentialshard};
+ PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
}
}