From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) 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=3.4.0
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id C90901FAEA
	for <meta@public-inbox.org>; Tue,  6 Mar 2018 08:42:42 +0000 (UTC)
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 08/34] mid: add `mids' and `references' methods for extraction
Date: Tue,  6 Mar 2018 08:42:16 +0000
Message-Id: <20180306084242.19988-9-e@80x24.org>
In-Reply-To: <20180306084242.19988-1-e@80x24.org>
References: <20180306084242.19988-1-e@80x24.org>
List-Id: <meta.public-inbox.org>

We'll be using a more consistent API for extracting Message-IDs
from various headers.
---
 lib/PublicInbox/MID.pm | 24 +++++++++++++++++++++++-
 t/mid.t                | 22 +++++++++++++++++++++-
 2 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 2c9822f..786c056 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -6,7 +6,8 @@ package PublicInbox::MID;
 use strict;
 use warnings;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/mid_clean id_compress mid2path mid_mime mid_escape MID_ESC/;
+our @EXPORT_OK = qw/mid_clean id_compress mid2path mid_mime mid_escape MID_ESC
+	mids references/;
 use URI::Escape qw(uri_escape_utf8);
 use Digest::SHA qw/sha1_hex/;
 use constant MID_MAX => 40; # SHA-1 hex length
@@ -48,6 +49,27 @@ sub mid2path {
 
 sub mid_mime ($) { $_[0]->header_obj->header_raw('Message-ID') }
 
+sub uniq_mids {
+	my ($hdr, @fields) = @_;
+	my %seen;
+	my @raw;
+	foreach my $f (@fields) {
+		push @raw, $hdr->header_raw($f);
+	}
+	my @mids = (join(' ', @raw) =~ /<([^>]+)>/g);
+	my $mids = scalar(@mids) == 0 ? \@raw: \@mids;
+	my @ret;
+	foreach (@$mids) {
+		next if $seen{$_};
+		push @ret, $_;
+		$seen{$_} = 1;
+	}
+	\@ret;
+}
+
+sub mids { uniq_mids($_[0], 'Message-Id') }
+sub references { uniq_mids($_[0], 'References', 'In-Reply-To') }
+
 # RFC3986, section 3.3:
 sub MID_ESC () { '^A-Za-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@' }
 sub mid_escape ($) { uri_escape_utf8($_[0], MID_ESC) }
diff --git a/t/mid.t b/t/mid.t
index 0bf3331..223be79 100644
--- a/t/mid.t
+++ b/t/mid.t
@@ -1,11 +1,31 @@
 # Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 use Test::More;
-use PublicInbox::MID qw(mid_escape);
+use PublicInbox::MID qw(mid_escape mids references);
 
 is(mid_escape('foo!@(bar)'), 'foo!@(bar)');
 is(mid_escape('foo%!@(bar)'), 'foo%25!@(bar)');
 is(mid_escape('foo%!@(bar)'), 'foo%25!@(bar)');
 
+{
+	use Email::MIME;
+	my $mime = Email::MIME->create;
+	$mime->header_set('Message-Id', '<mid-1@a>');
+	is_deeply(['mid-1@a'], mids($mime->header_obj), 'mids in common case');
+	$mime->header_set('Message-Id', '<mid-1@a>', '<mid-2@b>');
+	is_deeply(['mid-1@a', 'mid-2@b'], mids($mime->header_obj), '2 mids');
+	$mime->header_set('Message-Id', '<mid-1@a>', '<mid-1@a>');
+	is_deeply(['mid-1@a'], mids($mime->header_obj), 'dup mids');
+	$mime->header_set('Message-Id', '<mid-1@a> comment');
+	is_deeply(['mid-1@a'], mids($mime->header_obj), 'comment ignored');
+	$mime->header_set('Message-Id', 'bare-mid');
+	is_deeply(['bare-mid'], mids($mime->header_obj), 'bare mid OK');
+
+	$mime->header_set('References', '<hello> <world>');
+	$mime->header_set('In-Reply-To', '<weld>');
+	is_deeply(['hello', 'world', 'weld'], references($mime->header_obj),
+		'references combines with In-Reply-To');
+}
+
 done_testing();
 1;
-- 
EW