From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 3E2D32009A
	for <meta@public-inbox.org>; Tue, 27 Oct 2020 07:55:00 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 40/52] script: add preliminary eindex implementation
Date: Tue, 27 Oct 2020 07:54:41 +0000
Message-Id: <20201027075453.19163-41-e@80x24.org>
In-Reply-To: <20201027075453.19163-1-e@80x24.org>
References: <20201027075453.19163-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

Not documented, yet, but it runs...
---
 MANIFEST                   |  1 +
 script/public-inbox-eindex | 43 ++++++++++++++++++++++++++++++++++++++
 t/extsearch.t              | 26 +++++++++++++++++++++++
 3 files changed, 70 insertions(+)
 create mode 100644 script/public-inbox-eindex

diff --git a/MANIFEST b/MANIFEST
index 418a2f17..10561cd2 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -225,6 +225,7 @@ sa_config/user/.spamassassin/user_prefs
 script/public-inbox-compact
 script/public-inbox-convert
 script/public-inbox-edit
+script/public-inbox-eindex
 script/public-inbox-httpd
 script/public-inbox-imapd
 script/public-inbox-index
diff --git a/script/public-inbox-eindex b/script/public-inbox-eindex
new file mode 100644
index 00000000..c26edb93
--- /dev/null
+++ b/script/public-inbox-eindex
@@ -0,0 +1,43 @@
+#!perl -w
+# Copyright (C) 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.
+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-eindex [options] EINDEX_DIR [INBOX_DIR]
+
+  Create and update external (detached) search indices
+
+  --no-fsync          speed up indexing, risk corruption on power outage
+  -L LEVEL            `medium', or `full' (default: full)
+  --all               index all configured inboxes
+  --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
+  --verbose | -v      increase verbosity (may be repeated)
+
+BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
+See public-inbox-eindex(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
+		fsync|sync!
+		indexlevel|index-level|L=s max_size|max-size=s
+		batch_size|batch-size=s
+		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;
+
+# require lazily to speed up --help
+my $eidx_dir = shift(@ARGV) // die "E: $help";
+require PublicInbox::Admin;
+my $cfg = PublicInbox::Config->new;
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
+PublicInbox::Admin::require_or_die(qw(-search));
+require PublicInbox::ExtSearchIdx;
+my $eidx = PublicInbox::ExtSearchIdx->new($eidx_dir, $opt);
+$eidx->attach_inbox($_) for @ibxs;
+$eidx->eidx_sync($opt);
diff --git a/t/extsearch.t b/t/extsearch.t
index 54927c50..dfec6b6f 100644
--- a/t/extsearch.t
+++ b/t/extsearch.t
@@ -4,9 +4,35 @@
 use strict;
 use Test::More;
 use PublicInbox::TestCommon;
+use Fcntl qw(:seek);
 require_git(2.6);
 require_mods(qw(DBD::SQLite Search::Xapian));
 use_ok 'PublicInbox::ExtSearch';
 use_ok 'PublicInbox::ExtSearchIdx';
+my ($home, $for_destroy) = tmpdir();
+local $ENV{HOME} = $home;
+mkdir "$home/.public-inbox" or BAIL_OUT $!;
+open my $fh, '>', "$home/.public-inbox/config" or BAIL_OUT $!;
+print $fh <<EOF or BAIL_OUT $!;
+[publicinboxMda]
+	spamcheck = none
+EOF
+close $fh or BAIL_OUT $!;
+my $v2addr = 'v2test@example.com';
+my $v1addr = 'v1test@example.com';
+ok(run_script([qw(-init -V2 v2test), "$home/v2test",
+	'http://example.com/v2test', $v2addr ]), 'v2test init');
+my $env = { ORIGINAL_RECIPIENT => $v2addr };
+open($fh, '<', 't/utf8.eml') or BAIL_OUT("open t/utf8.eml: $!");
+run_script(['-mda', '--no-precheck'], $env, { 0 => $fh }) or BAIL_OUT '-mda';
+
+ok(run_script([qw(-init -V1 v1test), "$home/v1test",
+	'http://example.com/v1test', $v1addr ]), 'v1test init');
+$env = { ORIGINAL_RECIPIENT => $v1addr };
+seek($fh, 0, SEEK_SET) or BAIL_OUT $!;
+run_script(['-mda', '--no-precheck'], $env, { 0 => $fh }) or BAIL_OUT '-mda';
+run_script(['-index', "$home/v1test"]) or BAIL_OUT "index $?";
+
+ok(run_script([qw(-eindex --all), "$home/eindex"]), 'eindex init');
 
 done_testing;