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 = <<EOF; # the following should fit w/o scrolling in 80x24 term:
-usage: $usage
+usage: public-inbox-index [options] INBOX_DIR
Create and update search indices
options:
--no-fsync speed up indexing, risk corruption on power outage
- --indexlevel=LEVEL `basic', 'medium', or `full' (default: full)
+ -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)
--rethread regenerate thread IDs (if upgrading, use sparingly)
--prune prune git storage on discontiguous history
--verbose | -v increase verbosity (may be repeated)
- --help | -? show this help
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 $compact_opt;
-my $opt = { quiet => -1, compact => 0, maxsize => undef, fsync => 1 };
+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! xapianonly|xapian-only
- indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s
- sequentialshard|seq-shard|sequential-shard
- help|?))
- or die "bad command-line args\n$usage";
+ 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->{xapianonly} && !$opt->{reindex}) {
+if ($opt->{xapian_only} && !$opt->{reindex}) {
die "--xapian-only requires --reindex\n";
}
require PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-index');
-if ($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);
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
PublicInbox::Admin::require_or_die('-index');
-unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
-
-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";
-}
-
-my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')};
-if (defined $bs) {
- PublicInbox::Admin::parse_unsigned(\$bs) or
- die "`publicInbox.indexBatchSize=$bs' not parsed\n";
-}
-no warnings 'once';
-local $PublicInbox::SearchIdx::BATCH_BYTES = $bs if defined($bs);
-use warnings 'once';
-
-# 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->{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;
-}
+unless (@ibxs) { print STDERR $help; exit 1 }
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->{xapianonly} ?
- 'full' : PublicInbox::Admin::detect_indexlevel($ibx));
- $ibx->{index_max_size} = $max_size;
+ $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ?
+ 'full' : $detected);
PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
}
+# "Search::Xapian" includes SWIG "Xapian", too:
+$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', $compact_opt);
+ PublicInbox::Xapcmd::run($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->{indexsequentialshard})) {
+ 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, sequentialshard => $v };
+ $ibx_opt = { %$opt, sequential_shard => $v };
}
PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
- if ($compact_opt) {
- local $compact_opt->{jobs} = 0 if $ibx_opt->{sequentialshard};
- PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
+ if (my $copt = $opt->{compact_opt}) {
+ local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
+ PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
}
}