X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMID.pm;h=35b517e09f5d12ff264bcd0bd8afe77f1b96e69d;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=369bb034c8dd9d5c03ce4beb2e35d1c5fc632a9c;hpb=9cdeab04ebd95c7f778ba5f258399377b180f2cc;p=public-inbox.git

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 369bb034..35b517e0 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Various Message-ID-related functions.
@@ -7,7 +7,7 @@ use strict;
 use warnings;
 use base qw/Exporter/;
 our @EXPORT_OK = qw(mid_clean id_compress mid2path mid_escape MID_ESC
-	mids references mids_for_index $MID_EXTRACT);
+	mids references mids_for_index mids_in $MID_EXTRACT);
 use URI::Escape qw(uri_escape_utf8);
 use Digest::SHA qw/sha1_hex/;
 require PublicInbox::Address;
@@ -73,14 +73,17 @@ sub mids ($) {
 	uniq_mids(extract_mids(@mids));
 }
 
+# for Resent-Message-ID and maybe others
+sub mids_in ($@) {
+	my ($eml, @headers) = @_;
+	uniq_mids(extract_mids(map { ($eml->header_raw($_)) } @headers));
+}
+
 # we allow searching on X-Alt-Message-ID since PublicInbox::NNTP uses them
 # to placate some clients, and we want to ensure NNTP-only clients can
 # import and index without relying on HTTP endpoints
 sub mids_for_index ($) {
-	my ($hdr) = @_;
-	my @mids = $hdr->header_raw('Message-ID');
-	my @alts = $hdr->header_raw('X-Alt-Message-ID');
-	uniq_mids(extract_mids(@mids, @alts));
+	mids_in($_[0], qw(Message-ID X-Alt-Message-ID));
 }
 
 # last References should be IRT, but some mail clients do things
@@ -119,13 +122,13 @@ sub uniq_mids ($;$) {
 			warn "Message-ID: <$mid> too long, truncating\n";
 			$mid = substr($mid, 0, MAX_MID_SIZE);
 		}
-		push(@ret, $mid) unless $seen->{$mid}++;
+		$seen->{$mid} //= push(@ret, $mid);
 	}
 	\@ret;
 }
 
 # RFC3986, section 3.3:
-sub MID_ESC () { '^A-Za-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@' }
+sub MID_ESC () { '^A-Za-z0-9\-\._~!\$\&\'\(\)\*\+,;=:@' }
 sub mid_escape ($) { uri_escape_utf8($_[0], MID_ESC) }
 
 1;