From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,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 4CEC61FB0E for ; Thu, 21 Oct 2021 21:10:33 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 07/15] lei_search: try harder to associate "lei index"-ed messages Date: Thu, 21 Oct 2021 21:10:24 +0000 Message-Id: <20211021211032.22666-8-e@80x24.org> In-Reply-To: <20211021211032.22666-1-e@80x24.org> References: <20211021211032.22666-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: Allow checking for keyword changes if we have an known OID, even if the blob isn't currently reachable. --- lib/PublicInbox/LeiSearch.pm | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm index 3e046b2146c6..1fb38da1d7aa 100644 --- a/lib/PublicInbox/LeiSearch.pm +++ b/lib/PublicInbox/LeiSearch.pm @@ -7,7 +7,7 @@ use strict; use v5.10.1; use parent qw(PublicInbox::ExtSearch); # PublicInbox::Search->reopen use PublicInbox::Search qw(xap_terms); -use PublicInbox::ContentHash qw(content_digest content_hash); +use PublicInbox::ContentHash qw(content_digest content_hash git_sha); use PublicInbox::MID qw(mids mids_for_index); use Carp qw(croak); @@ -118,6 +118,13 @@ sub xoids_for { } } $git->async_wait_all; + + # it could be an 'lei index'-ed file that just got renamed + if (scalar(keys %$xoids) < ($min // 1) && defined($self->{topdir})) { + my $hex = git_sha(1, $eml)->hexdigest; + my @n = $overs[0]->blob_exists($hex); + for (@n) { $xoids->{$hex} //= $_ } + } scalar(keys %$xoids) ? $xoids : undef; } @@ -129,6 +136,10 @@ sub kw_changed { my $xoids = xoids_for($self, $eml) // return; $docids //= []; @$docids = sort { $a <=> $b } values %$xoids; + if (!@$docids && $self->over) { + my $bin = git_sha(1, $eml)->digest; + @$docids = $self->over->oidbin_exists($bin); + } } for my $id (@$docids) { $cur_kw = eval { msg_keywords($self, $id) } and last;