From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] lei note-event: ignore kw_changed exceptions
Date: Sun, 26 Sep 2021 00:02:32 +0000 [thread overview]
Message-ID: <20210926000232.5004-1-e@80x24.org> (raw)
The note-event worker may see changes before a Xapian shard
commit happens, meaning keyword lookups fail as a result.
Just emit the request to the lei/store worker since it's a
fairly cheap operation at this point.
We'll try harder to look for kw changes, too, since
deduplication changes may lead to multiple docids being
resolved for a single message.
---
lib/PublicInbox/LeiNoteEvent.pm | 4 +++-
lib/PublicInbox/LeiSearch.pm | 12 +++++++++---
2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/lib/PublicInbox/LeiNoteEvent.pm b/lib/PublicInbox/LeiNoteEvent.pm
index d24294850fd2..2a7b52c13487 100644
--- a/lib/PublicInbox/LeiNoteEvent.pm
+++ b/lib/PublicInbox/LeiNoteEvent.pm
@@ -42,7 +42,9 @@ sub eml_event ($$$$) {
$sto->wq_do('index_eml_only', $eml, $vmd, $xoids);
} elsif ($state =~ /\Atag-(?:rw|ro)\z/) {
my $docids = [];
- my $c = $self->{lse}->kw_changed($eml, $vmd->{kw}, $docids);
+ my $c = eval {
+ $self->{lse}->kw_changed($eml, $vmd->{kw}, $docids);
+ } // 1; # too new, assume changed since still to-be-committed.
if (scalar @$docids) { # already in lei/store
$sto->wq_do('set_eml_vmd', undef, $vmd, $docids) if $c;
} elsif (my $xoids = $self->{lei}->ale->xoids_for($eml)) {
diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm
index a10e6e176775..568277a6f404 100644
--- a/lib/PublicInbox/LeiSearch.pm
+++ b/lib/PublicInbox/LeiSearch.pm
@@ -9,6 +9,7 @@ use parent qw(PublicInbox::ExtSearch); # PublicInbox::Search->reopen
use PublicInbox::Search qw(xap_terms);
use PublicInbox::ContentHash qw(content_digest content_hash);
use PublicInbox::MID qw(mids mids_for_index);
+use Carp qw(croak);
# get combined docid from over.num:
# (not generic Xapian, only works with our sharding scheme)
@@ -131,14 +132,19 @@ sub xoids_for {
# returns true if $eml is indexed by lei/store and keywords don't match
sub kw_changed {
my ($self, $eml, $new_kw_sorted, $docids) = @_;
+ my $cur_kw;
if ($eml) {
my $xoids = xoids_for($self, $eml) // return;
$docids //= [];
@$docids = sort { $a <=> $b } values %$xoids;
}
- my $cur_kw = eval { msg_keywords($self, $docids->[0]) };
- die "E: #$docids->[0] keyword lookup failure: $@\n" if $@;
-
+ for my $id (@$docids) {
+ $cur_kw = eval { msg_keywords($self, $id) } and last;
+ }
+ if (!defined($cur_kw) && $@) {
+ $docids = join(', num:', @$docids);
+ croak "E: num:$docids keyword lookup failure: $@";
+ }
# RFC 5550 sec 5.9 on the $Forwarded keyword states:
# "Once set, the flag SHOULD NOT be cleared"
if (exists($cur_kw->{forwarded}) &&
reply other threads:[~2021-09-26 0:02 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210926000232.5004-1-e@80x24.org \
--to=e@80x24.org \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).