No ext_urls

[public-inbox.git] / script / public-inbox-index

diff --git a/script/public-inbox-index b/script/public-inbox-index
index c68f922447293bb0b43782e7795d57e9c7387ba0..a04be9fcb4f18456777f3eb0e0295c9cd283ce96 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,5 +1,5 @@
 #!perl -w
-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 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/>
@@ -25,6 +25,8 @@ options:
   --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)
+  --since=DATE        limit --reindex to changes after DATE
+  --until=DATE        limit --reindex to changes before DATE
   --rethread          regenerate thread IDs (if upgrading, use sparingly)
   --prune             prune git storage on discontiguous history
   --verbose | -v      increase verbosity (may be repeated)
@@ -37,12 +39,13 @@ my $opt = {
        'update-extindex' => [], # ":s@" optional arg sets '' if no arg given
 };
 GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
-               fsync|sync! xapian_only|xapian-only
+               fsync|sync! xapian_only|xapian-only dangerous
                indexlevel|index-level|L=s max_size|max-size=s
                batch_size|batch-size=s
-               sequential_shard|seq-shard|sequential-shard
+               since|after=s until|before=s
+               sequential-shard|seq-shard
                no-update-extindex update-extindex|E=s@
-               fast-noop|F skip-docdata all help|h))
+               fast-noop|F skip-docdata all C=s@ help|h))
        or die $help;
 if ($opt->{help}) { print $help; exit 0 };
 die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
@@ -56,6 +59,7 @@ if ($opt->{reindex} && delete($opt->{'fast-noop'})) {
 # require lazily to speed up --help
 require PublicInbox::Admin;
 PublicInbox::Admin::require_or_die('-index');
+PublicInbox::Admin::do_chdir(delete $opt->{C});
 
 my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
 $opt->{-use_cwd} = 1;
@@ -84,8 +88,10 @@ for my $ei_name (@$update_extindex) {
        } else {
                die "extindex `$ei_name' not configured or found\n";
        }
+       my $o = { %$opt };
+       delete $o->{indexlevel} if ($o->{indexlevel}//'') eq 'basic';
        $eidx_seen{$topdir} //=
-               push(@eidx, PublicInbox::ExtSearchIdx->new($topdir, $opt));
+               push(@eidx, PublicInbox::ExtSearchIdx->new($topdir, $o));
 }
 my $mods = {};
 my @eidx_unconfigured;
@@ -120,6 +126,7 @@ for my $ibx (@ibxs) {
                PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt});
        }
        $ibx->{-no_fsync} = 1 if !$opt->{fsync};
+       $ibx->{-dangerous} = 1 if $opt->{dangerous};
        $ibx->{-skip_docdata} //= $opt->{'skip-docdata'};
 
        my $ibx_opt = $opt;
@@ -127,12 +134,12 @@ for my $ibx (@ibxs) {
                defined(my $v = $cfg->git_bool($s)) or die <<EOL;
 publicInbox.$ibx->{name}.indexSequentialShard not boolean
 EOL
-               $ibx_opt = { %$opt, sequential_shard => $v };
+               $ibx_opt = { %$opt, 'sequential-shard' => $v };
        }
        my $nidx = PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
        last if $ibx_opt->{quit};
        if (my $copt = $opt->{compact_opt}) {
-               local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
+               local $copt->{jobs} = 0 if $ibx_opt->{'sequential-shard'};
                PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
        }
        last if $ibx_opt->{quit};