content_id: use Sender header if From is not available

[public-inbox.git] / lib / PublicInbox / ContentId.pm

diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm
index 65d5a76c09b43f4dec2edb08998c22ffe6d6e95e..9082b7694002168467ab3d2610a36631348116d2 100644 (file)
--- a/lib/PublicInbox/ContentId.pm
+++ b/lib/PublicInbox/ContentId.pm
@@ -5,26 +5,50 @@ package PublicInbox::ContentId;
 use strict;
 use warnings;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/content_id/;
+our @EXPORT_OK = qw/content_id content_digest/;
+use PublicInbox::MID qw(mids references);
 
 # not sure if less-widely supported hash families are worth bothering with
 use Digest::SHA;
 
-# Content-* headers are often no-ops, so maybe we don't need them
-my @ID_HEADERS = qw(Subject From Date Message-ID References To Cc In-Reply-To);
-
-sub content_id ($;$) {
-       my ($mime, $alg) = @_;
-       $alg ||= 256;
-       my $dig = Digest::SHA->new($alg);
+sub content_digest ($) {
+       my ($mime) = @_;
+       my $dig = Digest::SHA->new(256);
        my $hdr = $mime->header_obj;
 
-       foreach my $h (@ID_HEADERS) {
+       # 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 %seen;
+       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);
+       }
+
+       # Only use Sender: if From is not present
+       foreach my $h (qw(From Sender)) {
                my @v = $hdr->header_raw($h);
-               $dig->add($_) foreach @v;
+               if (@v) {
+                       $dig->add("$h: $_") foreach @v;
+                       last;
+               }
+       }
+
+       # Content-* headers are often no-ops, so maybe we don't need them
+       foreach my $h (qw(Subject Date To Cc)) {
+               my @v = $hdr->header_raw($h);
+               $dig->add("$h: $_") foreach @v;
        }
        $dig->add($mime->body_raw);
-       'SHA-' . $dig->algorithm . ':' . $dig->hexdigest;
+       $dig;
+}
+
+sub content_id ($) {
+       content_digest($_[0])->digest;
 }
 
 1;