#!perl -w
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
use strict;
use Test::More;
use PublicInbox::TestCommon;
use PublicInbox::Config;
+use PublicInbox::InboxWritable;
use Fcntl qw(:seek);
-my $json = PublicInbox::Config::json() or plan skip_all => 'JSON missing';
require_git(2.6);
-require_mods(qw(DBD::SQLite Search::Xapian));
+require_mods(qw(json DBD::SQLite Search::Xapian));
+require PublicInbox::Search;
use_ok 'PublicInbox::ExtSearch';
use_ok 'PublicInbox::ExtSearchIdx';
+use_ok 'PublicInbox::OverIdx';
my $sock = tcp_server();
-my $host_port = $sock->sockhost . ':' . $sock->sockport;
+my $host_port = tcp_host_port($sock);
my ($home, $for_destroy) = tmpdir();
local $ENV{HOME} = $home;
mkdir "$home/.public-inbox" or BAIL_OUT $!;
ok($es->has_threadid, '->has_threadid');
}
+if ('with boost') {
+ xsys([qw(git config publicinbox.v1test.boost), 10],
+ { GIT_CONFIG => $cfg_path });
+ ok(run_script([qw(-extindex --all), "$home/extindex-b"]),
+ 'extindex init with boost');
+ my $es = PublicInbox::ExtSearch->new("$home/extindex-b");
+ my $smsg = $es->over->get_art(1);
+ ok($smsg, 'got first article');
+ my $xref3 = $es->over->get_xref3($smsg->{num});
+ my @v1 = grep(/\Av1/, @$xref3);
+ my @v2 = grep(/\Av2/, @$xref3);
+ like($v1[0], qr/\Av1\.example.*?\b\Q$smsg->{blob}\E\b/,
+ 'smsg->{blob} respected boost');
+ is(scalar(@$xref3), 2, 'only to entries');
+ undef $es;
+
+ xsys([qw(git config publicinbox.v2test.boost), 20],
+ { GIT_CONFIG => $cfg_path });
+ ok(run_script([qw(-extindex --all --reindex), "$home/extindex-b"]),
+ 'extindex --reindex with altered boost');
+
+ $es = PublicInbox::ExtSearch->new("$home/extindex-b");
+ $smsg = $es->over->get_art(1);
+ like($v2[0], qr/\Av2\.example.*?\b\Q$smsg->{blob}\E\b/,
+ 'smsg->{blob} respects boost after reindex');
+
+ xsys([qw(git config --unset publicinbox.v1test.boost)],
+ { GIT_CONFIG => $cfg_path });
+ xsys([qw(git config --unset publicinbox.v2test.boost)],
+ { GIT_CONFIG => $cfg_path });
+}
+
{ # TODO: -extindex should write this to config
open $fh, '>>', $cfg_path or BAIL_OUT $!;
print $fh <<EOF or BAIL_OUT $!;
is(scalar(@$xref3), 2, 'only to entries');
}
-{
+if ('inbox edited') {
my ($in, $out, $err);
$in = $out = $err = '';
my $opt = { 0 => \$in, 1 => \$out, 2 => \$err };
like($it[0]->get_document->get_data, qr/v2test/, 'docdata matched v2');
like($it[1]->get_document->get_data, qr/v1test/, 'docdata matched v1');
+my $cfg = PublicInbox::Config->new;
+my $schema_version = PublicInbox::Search::SCHEMA_VERSION();
+my $f = "$home/extindex/ei$schema_version/over.sqlite3";
+my $oidx = PublicInbox::OverIdx->new($f);
if ('inject w/o indexing') {
use PublicInbox::Import;
- use PublicInbox::Search;
- my $schema_version = PublicInbox::Search::SCHEMA_VERSION();
- my $v1ibx = PublicInbox::Config->new->lookup_name('v1test');
+ my $v1ibx = $cfg->lookup_name('v1test');
my $last_v1_commit = $v1ibx->mm->last_commit;
- my $v2ibx = PublicInbox::Config->new->lookup_name('v2test');
+ my $v2ibx = $cfg->lookup_name('v2test');
my $last_v2_commit = $v2ibx->mm->last_commit_xap($schema_version, 0);
my $git0 = PublicInbox::Git->new("$v2ibx->{inboxdir}/git/0.git");
chomp(my $cmt = $git0->qx(qw(rev-parse HEAD^0)));
is($mset->size, 1, 'got v2 message');
}
+if ('reindex catches missed messages') {
+ my $v2ibx = $cfg->lookup_name('v2test');
+ $v2ibx->{-no_fsync} = 1;
+ my $im = PublicInbox::InboxWritable->new($v2ibx)->importer(0);
+ my $cmt_a = $v2ibx->mm->last_commit_xap($schema_version, 0);
+ my $eml = eml_load('t/data/0001.patch');
+ $im->add($eml);
+ $im->done;
+ my $cmt_b = $v2ibx->mm->last_commit_xap($schema_version, 0);
+ isnt($cmt_a, $cmt_b, 'v2 0.git HEAD updated');
+ $oidx->dbh;
+ my $uv = $v2ibx->uidvalidity;
+ my $lc_key = "lc-v2:v2.example//$uv;0";
+ is($oidx->eidx_meta($lc_key, $cmt_b), $cmt_a,
+ 'update lc-v2 meta, old is as expected');
+ my $max = $oidx->max;
+ $oidx->dbh_close;
+ ok(run_script([qw(-extindex), "$home/extindex", $v2ibx->{inboxdir}]),
+ '-extindex noop');
+ is($oidx->max, $max, '->max unchanged');
+ is($oidx->eidx_meta($lc_key), $cmt_b, 'lc-v2 unchanged');
+ $oidx->dbh_close;
+ my $opt = { 2 => \(my $err = '') };
+ ok(run_script([qw(-extindex --reindex), "$home/extindex",
+ $v2ibx->{inboxdir}], undef, $opt),
+ '--reindex for unseen');
+ is($oidx->max, $max + 1, '->max bumped');
+ is($oidx->eidx_meta($lc_key), $cmt_b, 'lc-v2 stays unchanged');
+ my @err = split(/^/, $err);
+ is(scalar(@err), 1, 'only one warning') or diag "err=$err";
+ like($err[0], qr/I: reindex_unseen/, 'got reindex_unseen message');
+ my $new = $oidx->get_art($max + 1);
+ is($new->{subject}, $eml->header('Subject'), 'new message added');
+
+ $es->{xdb}->reopen;
+ my $mset = $es->mset("mid:$new->{mid}");
+ is($mset->size, 1, 'previously unseen, now indexed in Xapian');
+
+ ok($im->remove($eml), 'remove new message from v2 inbox');
+ $im->done;
+ my $cmt_c = $v2ibx->mm->last_commit_xap($schema_version, 0);
+ is($oidx->eidx_meta($lc_key, $cmt_c), $cmt_b,
+ 'bump lc-v2 meta again to skip v2 remove');
+ $err = '';
+ $oidx->dbh_close;
+ ok(run_script([qw(-extindex --reindex), "$home/extindex",
+ $v2ibx->{inboxdir}], undef, $opt),
+ '--reindex for stale');
+ @err = split(/^/, $err);
+ is(scalar(@err), 1, 'only one warning') or diag "err=$err";
+ like($err[0], qr/\(#$new->{num}\): stale/, 'got stale message warning');
+ is($oidx->get_art($new->{num}), undef,
+ 'stale message gone from over');
+ is_deeply($oidx->get_xref3($new->{num}), [],
+ 'stale message has no xref3');
+ $es->{xdb}->reopen;
+ $mset = $es->mset("mid:$new->{mid}");
+ is($mset->size, 0, 'stale mid gone Xapian');
+}
+
+if ('reindex catches content bifurcation') {
+ use PublicInbox::MID qw(mids);
+ my $v2ibx = $cfg->lookup_name('v2test');
+ $v2ibx->{-no_fsync} = 1;
+ my $im = PublicInbox::InboxWritable->new($v2ibx)->importer(0);
+ my $eml = eml_load('t/data/message_embed.eml');
+ my $cmt_a = $v2ibx->mm->last_commit_xap($schema_version, 0);
+ $im->add($eml);
+ $im->done;
+ my $cmt_b = $v2ibx->mm->last_commit_xap($schema_version, 0);
+ my $uv = $v2ibx->uidvalidity;
+ my $lc_key = "lc-v2:v2.example//$uv;0";
+ $oidx->dbh;
+ is($oidx->eidx_meta($lc_key, $cmt_b), $cmt_a,
+ 'update lc-v2 meta, old is as expected');
+ my $mid = mids($eml)->[0];
+ my $smsg = $v2ibx->over->next_by_mid($mid, \(my $id), \(my $prev));
+ my $oldmax = $oidx->max;
+ my $x3_orig = $oidx->get_xref3(3);
+ is(scalar(@$x3_orig), 1, '#3 has one xref');
+ $oidx->add_xref3(3, $smsg->{num}, $smsg->{blob}, 'v2.example');
+ my $x3 = $oidx->get_xref3(3);
+ is(scalar(@$x3), 2, 'injected xref3');
+ $oidx->commit_lazy;
+ my $opt = { 2 => \(my $err = '') };
+ ok(run_script([qw(-extindex --all), "$home/extindex"], undef, $opt),
+ 'extindex --all is noop');
+ is($err, '', 'no warnings in index');
+ $oidx->dbh;
+ is($oidx->max, $oldmax, 'oidx->max unchanged');
+ $oidx->dbh_close;
+ ok(run_script([qw(-extindex --reindex --all), "$home/extindex"],
+ undef, $opt), 'extindex --reindex');
+ $oidx->dbh;
+ ok($oidx->max > $oldmax, 'oidx->max bumped');
+ like($err, qr/split into 2 due to deduplication change/,
+ 'bifurcation noted');
+ my $added = $oidx->get_art($oidx->max);
+ is($added->{blob}, $smsg->{blob}, 'new blob indexed');
+ is_deeply(["v2.example:$smsg->{num}:$smsg->{blob}"],
+ $oidx->get_xref3($added->{num}),
+ 'xref3 corrected for bifurcated message');
+ is_deeply($oidx->get_xref3(3), $x3_orig, 'xref3 restored for #3');
+}
+
+if ('--reindex --rethread') {
+ my $before = $oidx->dbh->selectrow_array(<<'');
+SELECT MAX(tid) FROM over WHERE num > 0
+
+ my $opt = {};
+ ok(run_script([qw(-extindex --reindex --rethread --all),
+ "$home/extindex"], undef, $opt),
+ '--rethread');
+ my $after = $oidx->dbh->selectrow_array(<<'');
+SELECT MIN(tid) FROM over WHERE num > 0
+
+ # actual rethread logic is identical to v1/v2 and tested elsewhere
+ ok($after > $before, '--rethread updates MIN(tid)');
+}
+
if ('remove v1test and test gc') {
xsys([qw(git config --unset publicinbox.v1test.inboxdir)],
{ GIT_CONFIG => $cfg_path });
is(scalar(@it), 1, 'only one inbox left');
}
+if ('dedupe + dry-run') {
+ my @cmd = ('-extindex', "$home/extindex");
+ my $opt = { 2 => \(my $err = '') };
+ ok(run_script([@cmd, '--dedupe'], undef, $opt), '--dedupe');
+ ok(run_script([@cmd, qw(--dedupe --dry-run)], undef, $opt),
+ '--dry-run --dedupe');
+ is $err, '', 'no errors';
+ ok(!run_script([@cmd, qw(--dry-run)], undef, $opt),
+ '--dry-run alone fails');
+}
+
done_testing;