X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMID.pm;h=33d5af7450a2610702591c7ad864cb81e981084c;hb=7d4858ea519cfe71cddc425ef4d39d6eea250b23;hp=7f1ab15ea731db8f0f70304662afe338754b5c6c;hpb=b8eb1f39dc9aea6ce84373c50c47c6fc4ac8c503;p=public-inbox.git

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 7f1ab15e..33d5af74 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2019 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_mime mid_escape MID_ESC
-	mids references/;
+	mids references mids_for_index/;
 use URI::Escape qw(uri_escape_utf8);
 use Digest::SHA qw/sha1_hex/;
 require PublicInbox::Address;
@@ -26,11 +26,11 @@ sub mid_clean {
 	$mid;
 }
 
-# this is idempotent
+# this is idempotent, used for HTML anchor/ids and such
 sub id_compress {
 	my ($id, $force) = @_;
 
-	if ($force || $id =~ /[^\w\-]/ || length($id) > MID_MAX) {
+	if ($force || $id =~ /[^a-zA-Z0-9_\-]/ || length($id) > MID_MAX) {
 		utf8::encode($id);
 		return sha1_hex($id);
 	}
@@ -54,11 +54,10 @@ sub mid2path {
 # Only for v1 code paths:
 sub mid_mime ($) { mids($_[0]->header_obj)->[0] }
 
-sub mids ($) {
-	my ($hdr) = @_;
+# only intended for Message-ID and X-Alt-Message-ID
+sub extract_mids {
 	my @mids;
-	my @v = $hdr->header_raw('Message-Id');
-	foreach my $v (@v) {
+	for my $v (@_) {
 		my @cur = ($v =~ /<([^>]+)>/sg);
 		if (@cur) {
 			push(@mids, @cur);
@@ -66,7 +65,23 @@ sub mids ($) {
 			push(@mids, $v);
 		}
 	}
-	uniq_mids(\@mids);
+	\@mids;
+}
+
+sub mids ($) {
+	my ($hdr) = @_;
+	my @mids = $hdr->header_raw('Message-Id');
+	uniq_mids(extract_mids(@mids));
+}
+
+# we allow searching on X-Alt-Message-ID since PublicInbox::NNTP uses them
+# to placate some clients, and we want to ensure NNTP-only clients can
+# import and index without relying on HTTP endpoints
+sub mids_for_index ($) {
+	my ($hdr) = @_;
+	my @mids = $hdr->header_raw('Message-Id');
+	my @alts = $hdr->header_raw('X-Alt-Message-ID');
+	uniq_mids(extract_mids(@mids, @alts));
 }
 
 # last References should be IRT, but some mail clients do things
@@ -105,9 +120,7 @@ sub uniq_mids ($;$) {
 			warn "Message-ID: <$mid> too long, truncating\n";
 			$mid = substr($mid, 0, MAX_MID_SIZE);
 		}
-		next if $seen->{$mid};
-		push @ret, $mid;
-		$seen->{$mid} = 1;
+		push(@ret, $mid) unless $seen->{$mid}++;
 	}
 	\@ret;
 }