X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiSearch.pm;h=ceb3624b5e46c59d620191b412e5574841edc6bf;hb=fbc11e24a72f41b0ed7ead30d199288a4d674be4;hp=66c16e0485fd611f7dbad6186301bb920426d8b5;hpb=ba135f3e25bf5d1b3aa3d34e31fefb55ee4c8d29;p=public-inbox.git

diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm
index 66c16e04..ceb3624b 100644
--- a/lib/PublicInbox/LeiSearch.pm
+++ b/lib/PublicInbox/LeiSearch.pm
@@ -1,39 +1,74 @@
-# 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>
 
+# read-only counterpart for PublicInbox::LeiStore
 package PublicInbox::LeiSearch;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::ExtSearch);
-use PublicInbox::Search;
+use PublicInbox::Search qw(xap_terms);
+use PublicInbox::ContentHash qw(content_digest content_hash);
+use PublicInbox::MID qw(mids mids_in);
 
-sub combined_docid ($$) {
+# get combined docid from over.num:
+# (not generic Xapian, only works with our sharding scheme)
+sub num2docid ($$) {
 	my ($self, $num) = @_;
-	($num - 1) * $self->{nshard} + 1;
+	my $nshard = $self->{nshard};
+	($num - 1) * $nshard + $num % $nshard + 1;
 }
 
 sub msg_keywords {
 	my ($self, $num) = @_; # num_or_mitem
 	my $xdb = $self->xdb; # set {nshard};
-	my $docid = ref($num) ? $num->get_docid : do {
-		# get combined docid from over.num:
-		# (not generic Xapian, only works with our sharding scheme)
-		my $nshard = $self->{nshard};
-		($num - 1) * $nshard + $num % $nshard + 1;
-	};
-	my %kw;
-	eval {
-		my $end = $xdb->termlist_end($docid);
-		my $cur = $xdb->termlist_begin($docid);
-		for (; $cur != $end; $cur++) {
-			$cur->skip_to('K');
-			last if $cur == $end;
-			my $kw = $cur->get_termname;
-			$kw =~ s/\AK//s and $kw{$kw} = undef;
-		}
-	};
+	my $docid = ref($num) ? $num->get_docid : num2docid($self, $num);
+	my $kw = xap_terms('K', $xdb, $docid);
 	warn "E: #$docid ($num): $@\n" if $@;
-	wantarray ? sort(keys(%kw)) : \%kw;
+	wantarray ? sort(keys(%$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;