lei q: import flags when clobbering/augmenting Maildirs

[public-inbox.git] / lib / PublicInbox / LeiSearch.pm

diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm
index 440bacf527e60037d1854017cb529eba96570419..ceb3624b5e46c59d620191b412e5574841edc6bf 100644 (file)
--- a/lib/PublicInbox/LeiSearch.pm
+++ b/lib/PublicInbox/LeiSearch.pm
@@ -1,11 +1,14 @@
 # Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
+# read-only counterpart for PublicInbox::LeiStore
 package PublicInbox::LeiSearch;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::ExtSearch);
 use PublicInbox::Search qw(xap_terms);
+use PublicInbox::ContentHash qw(content_digest content_hash);
+use PublicInbox::MID qw(mids mids_in);
 
 # get combined docid from over.num:
 # (not generic Xapian, only works with our sharding scheme)
@@ -24,4 +27,48 @@ sub msg_keywords {
        wantarray ? sort(keys(%$kw)) : $kw;
 }
 
+# when a message has no Message-IDs at all, this is needed for
+# unsent Draft messages, at least
+sub content_key ($) {
+       my ($eml) = @_;
+       my $dig = content_digest($eml);
+       my $chash = $dig->clone->digest;
+       my $mids = mids_in($eml,
+                       qw(Message-ID X-Alt-Message-ID Resent-Message-ID));
+       unless (@$mids) {
+               $eml->{-lei_fake_mid} = $mids->[0] =
+                               PublicInbox::Import::digest2mid($dig, $eml);
+       }
+       ($chash, $mids);
+}
+
+sub _cmp_1st { # git->cat_async callback
+       my ($bref, $oid, $type, $size, $cmp) = @_; # cmp: [chash, found, smsg]
+       return if defined($cmp->[1]->[0]); # $found->[0]
+       if (content_hash(PublicInbox::Eml->new($bref)) eq $cmp->[0]) {
+               push @{$cmp->[1]}, $cmp->[2]->{num};
+       }
+}
+
+# returns true if $eml is indexed by lei/store and keywords don't match
+sub kw_changed {
+       my ($self, $eml, $new_kw_sorted) = @_;
+       my ($chash, $mids) = content_key($eml);
+       my $over = $self->over;
+       my $git = $self->git;
+       my $found = [];
+       for my $mid (@$mids) {
+               my ($id, $prev);
+               while (my $cur = $over->next_by_mid($mid, \$id, \$prev)) {
+                       $git->cat_async($cur->{blob}, \&_cmp_1st,
+                                       [ $chash, $found, $cur ]);
+                       last if scalar(@$found);
+               }
+       }
+       $git->cat_async_wait;
+       my $num = $found->[0] // return;
+       my @cur_kw = msg_keywords($self, $num);
+       join("\0", @$new_kw_sorted) eq join("\0", @cur_kw) ? 0 : 1;
+}
+
 1;