www: drop --subject from "git send-email" instructions

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

diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex
old mode 100644 (file)
new mode 100755 (executable)
index f4ffda4..bee824b
--- a/script/public-inbox-extindex
+++ b/script/public-inbox-extindex
@@ -1,12 +1,11 @@
 #!perl -w
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 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.
 use strict;
 use v5.10.1;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
 my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
-usage: public-inbox-extindex [options] EXTINDEX_DIR [INBOX_DIR]
+usage: public-inbox-extindex [options] [EXTINDEX_DIR] [INBOX_DIR...]
 
   Create and update external (detached) search indices
 
@@ -18,37 +17,55 @@ usage: public-inbox-extindex [options] EXTINDEX_DIR [INBOX_DIR]
   --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
   --gc                perform garbage collection instead of indexing
+  --dedupe[=MSGID]    fix prior deduplication errors (may be repeated)
+  --reindex           index previously indexed inboxes
+  --fast              only reindex unseen/stale messages
   --verbose | -v      increase verbosity (may be repeated)
+  --dry-run | -n      dry-run on --dedupe
 
 BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
 See public-inbox-extindex(1) man page for full documentation.
 EOF
 my $opt = { quiet => -1, compact => 0, fsync => 1, scan => 1 };
 GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i
-               fsync|sync!
+               fsync|sync! fast dangerous
                indexlevel|index-level|L=s max_size|max-size=s
                batch_size|batch-size=s
-               gc commit-interval=i watch scan!
-               all help|h))
+               dedupe:s@ gc commit-interval=i watch scan! dry-run|n
+               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;
 require IO::Handle;
 STDOUT->autoflush(1);
 STDERR->autoflush(1);
-# require lazily to speed up --help
-my $eidx_dir = shift(@ARGV) // die "E: $help";
 local $SIG{USR1} = 'IGNORE'; # to be overridden in eidx_sync
+# require lazily to speed up --help
 require PublicInbox::Admin;
+PublicInbox::Admin::do_chdir(delete $opt->{C});
 my $cfg = PublicInbox::Config->new;
+my $eidx_dir = shift(@ARGV);
+unless (defined $eidx_dir) {
+       if ($opt->{all} && $cfg->ALL) {
+               $eidx_dir = $cfg->ALL->{topdir};
+       } else {
+               die "E: $help";
+       }
+}
 my @ibxs;
 if ($opt->{gc}) {
        die "E: inbox paths must not be specified with --gc\n" if @ARGV;
-       die "E: --all not compatible with --gc\n" if $opt->{all};
-       die "E: --watch is not compatible with --gc\n" if $opt->{watch};
+       for my $sw (qw(all watch dry-run dedupe)) {
+               die "E: --$sw is not compatible with --gc\n" if $opt->{$sw};
+       }
 } else {
        @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
 }
+$opt->{'dry-run'} && !$opt->{dedupe} and
+       die "E: --dry-run only affects --dedupe\n";
+$opt->{fast} && !$opt->{reindex} and
+       die "E: --fast only affects --reindex\n";
+
 PublicInbox::Admin::require_or_die(qw(-search));
 PublicInbox::Config::json() or die "Cpanel::JSON::XS or similar missing\n";
 PublicInbox::Admin::progress_prepare($opt);
@@ -63,7 +80,7 @@ if ($opt->{gc}) {
        if ($opt->{all}) {
                $eidx->attach_config($cfg);
        } else {
-               $eidx->attach_inbox($_) for @ibxs;
+               $eidx->attach_config($cfg, \@ibxs);
        }
        if ($opt->{watch}) {
                $cfg = undef; # save memory only after SIGHUP