From: Eric Wong (Contractor, The Linux Foundation) <e@80x24.org>
Date: Fri, 2 Mar 2018 09:39:31 +0000 (+0000)
Subject: content_id: use `mids' and `references' for MID extraction
X-Git-Tag: v1.1.0-pre1~196
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=7cacb4ae964408519f5577b895897c447c272da6;p=public-inbox.git

content_id: use `mids' and `references' for MID extraction

These already take care of deduping internally, so we'll save
ourselves at least some of the trouble while using a more
consistent API.  While we're at it, hash the header name as
well, since we need to distinguish which header a certain value
came from.
---

diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm
index 7ec638ca..d1a009e7 100644
--- a/lib/PublicInbox/ContentId.pm
+++ b/lib/PublicInbox/ContentId.pm
@@ -6,6 +6,7 @@ use strict;
 use warnings;
 use base qw/Exporter/;
 our @EXPORT_OK = qw/content_id/;
+use PublicInbox::MID qw(mids references);
 
 # not sure if less-widely supported hash families are worth bothering with
 use Digest::SHA;
@@ -22,20 +23,18 @@ sub content_id ($;$) {
 	# References: and In-Reply-To: get used interchangeably
 	# in some "duplicates" in LKML.  We treat them the same
 	# in SearchIdx, so treat them the same for this:
-	my @mid = $hdr->header_raw('Message-ID');
-	@mid = (join(' ', @mid) =~ /<([^>]+)>/g);
-	my $refs = join(' ', $hdr->header_raw('References'),
-			$hdr->header_raw('In-Reply-To'));
-	my @refs = ($refs =~ /<([^>]+)>/g);
 	my %seen;
-	foreach my $mid (@mid, @refs) {
-		next if $seen{$mid};
-		$dig->add($mid);
+	foreach my $mid (@{mids($hdr)}) {
+		$dig->add('mid: '.$mid);
 		$seen{$mid} = 1;
 	}
+	foreach my $mid (@{references($hdr)}) {
+		next if $seen{$mid};
+		$dig->add('ref: '.$mid);
+	}
 	foreach my $h (@ID_HEADERS) {
 		my @v = $hdr->header_raw($h);
-		$dig->add($_) foreach @v;
+		$dig->add("$h: $_") foreach @v;
 	}
 	$dig->add($mime->body_raw);
 	'SHA-' . $dig->algorithm . ':' . $dig->hexdigest;