X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=9855c67d31012ed734f3ff2c499bc14597a574a8;hb=29c5f2a6fc3b86306a5dbeadfae061d06f2bc6dd;hp=e4a7be1979ae88915d0ef689ed99c5ccdf51d347;hpb=4f814ff418e334a9b7b9bd96cd5450c2823de2f6;p=public-inbox.git
diff --git a/script/public-inbox-index b/script/public-inbox-index
index e4a7be19..9855c67d 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,37 +1,94 @@
-#!/usr/bin/perl -w
-# Copyright (C) 2015-2019 all contributors
+#!perl -w
+# Copyright (C) 2015-2020 all contributors
# License: AGPL-3.0+
-# 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
# 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);
-my $usage = "public-inbox-index INBOX_DIR";
-use PublicInbox::Admin;
-PublicInbox::Admin::require_or_die('-index');
+my $usage = 'public-inbox-index [options] INBOX_DIR';
+my $help = < -1 };
-GetOptions($opt, qw(verbose|v+ reindex jobs|j=i prune indexlevel|L=s))
+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|?))
or die "bad command-line args\n$usage";
-die "--jobs must be positive\n" if defined $opt->{jobs} && $opt->{jobs} <= 0;
+if ($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 }
+# require lazily to speed up --help
+require PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-index');
-my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV);
+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');
-usage() unless @ibxs;
+unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
+
my $mods = {};
foreach my $ibx (@ibxs) {
- if (defined $opt->{indexlevel} && !defined($ibx->{indexlevel})) {
- # XXX: users can shoot themselves in the foot, with this...
- $ibx->{indexlevel} = $opt->{indexlevel};
- }
+ # 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, $ibx);
}
PublicInbox::Admin::require_or_die(keys %$mods);
+my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
+local %ENV = (%ENV, %$env) if $env;
+require PublicInbox::InboxWritable;
PublicInbox::Admin::progress_prepare($opt);
-PublicInbox::Admin::index_inbox($_, $opt) for @ibxs;
+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 <{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);
+ }
+}