-#!/usr/bin/perl -w
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (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.
+#!perl -w
+# 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 public-inbox.
# Usage with libeatmydata <https://www.flamingspork.com/projects/libeatmydata/>
-# highly recommended: eatmydata public-inbox-index GIT_DIR
+# highly recommended: eatmydata public-inbox-index INBOX_DIR
use strict;
-use warnings;
+use v5.10.1;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-use Cwd 'abs_path';
-my $usage = "public-inbox-index GIT_DIR";
-use PublicInbox::Config;
-my $config = PublicInbox::Config->new;
-eval { require PublicInbox::SearchIdx };
-if ($@) {
- print STDERR "Search::Xapian required for $0\n";
- exit 1;
-}
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: public-inbox-index [options] INBOX_DIR
-my $reindex;
-my %opts = ( '--reindex' => \$reindex );
-GetOptions(%opts) or die "bad command-line args\n$usage";
+ Create and update search indices
-my @dirs;
+options:
-sub resolve_git_dir {
- my ($cd) = @_;
- my @cmd = qw(git rev-parse --git-dir);
- my $cmd = join(' ', @cmd);
- my $pid = open my $fh, '-|';
- defined $pid or die "forking $cmd failed: $!\n";
- if ($pid == 0) {
- if (defined $cd) {
- chdir $cd or die "chdir $cd failed: $!\n";
- }
- exec @cmd;
- die "Failed to exec $cmd: $!\n";
- } else {
- my $dir = eval {
- local $/;
- <$fh>;
- };
- close $fh or die "error in $cmd: $!\n";
- chomp $dir;
- return abs_path($cd) if ($dir eq '.' && defined $cd);
- abs_path($dir);
- }
-}
+ --no-fsync speed up indexing, risk corruption on power outage
+ -L LEVEL `basic', `medium', or `full' (default: full)
+ --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)
+ --rethread regenerate thread IDs (if upgrading, use sparingly)
+ --prune prune git storage on discontiguous history
+ --verbose | -v increase verbosity (may be repeated)
-if (@ARGV) {
- @dirs = map { resolve_git_dir($_) } @ARGV;
-} else {
- @dirs = (resolve_git_dir());
+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 $opt = { quiet => -1, compact => 0, max_size => undef, fsync => 1 };
+GetOptions($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
+ skip-docdata all 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";
}
-sub usage { print STDERR "Usage: $usage\n"; exit 1 }
-usage() unless @dirs;
+# require lazily to speed up --help
+require PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-index');
-foreach my $k (keys %$config) {
- $k =~ /\Apublicinbox\.([^\.]+)\.mainrepo\z/ or next;
- my $name = $1;
- my $v = $config->{$k};
- for my $i (0..$#dirs) {
- next if $dirs[$i] ne $v;
- my $ibx = $config->lookup_name($name);
- $dirs[$i] = $ibx if $ibx;
- }
-}
+my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
+PublicInbox::Admin::require_or_die('-index');
+unless (@ibxs) { print STDERR $help; exit 1 }
-foreach my $dir (@dirs) {
- index_dir($dir);
+my $mods = {};
+foreach my $ibx (@ibxs) {
+ # detect_indexlevel may also set $ibx->{-skip_docdata}
+ my $detected = PublicInbox::Admin::detect_indexlevel($ibx);
+ # 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, $ibx);
}
-sub index_dir {
- my ($git_dir) = @_;
- if (!ref $git_dir && ! -d $git_dir) {
- die "$git_dir does not appear to be a git repository\n";
+# "Search::Xapian" includes SWIG "Xapian", too:
+$opt->{compact} = 0 if !$mods->{'Search::Xapian'};
+
+PublicInbox::Admin::require_or_die(keys %$mods);
+my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
+local %ENV = (%ENV, %$env) if $env;
+require PublicInbox::InboxWritable;
+PublicInbox::Xapcmd::check_compact() if $opt->{compact};
+PublicInbox::Admin::progress_prepare($opt);
+for my $ibx (@ibxs) {
+ $ibx = PublicInbox::InboxWritable->new($ibx);
+ if ($opt->{compact} >= 2) {
+ PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt});
+ }
+ $ibx->{-no_fsync} = 1 if !$opt->{fsync};
+ $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 => $v };
+ }
+ PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
+ if (my $copt = $opt->{compact_opt}) {
+ local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
+ PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
}
- my $s = PublicInbox::SearchIdx->new($git_dir, 1);
- $s->index_sync({ reindex => $reindex });
}