content_hash: handle References as octets

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

diff --git a/lib/PublicInbox/ContentHash.pm b/lib/PublicInbox/ContentHash.pm
index 112b1ea6c1e660722cf1e68982745edb93912599..1afbb413a697b99e6ae23b6ef20c1d488526613e 100644 (file)
--- a/lib/PublicInbox/ContentHash.pm
+++ b/lib/PublicInbox/ContentHash.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Unstable internal API.
@@ -20,6 +20,7 @@ use Digest::SHA;
 sub digest_addr ($$$) {
        my ($dig, $h, $v) = @_;
        $v =~ tr/"//d;
+       $v =~ tr/\r\n\t / /s;
        $v =~ s/@([a-z0-9\_\.\-\(\)]*([A-Z])\S*)/'@'.lc($1)/ge;
        utf8::encode($v);
        $dig->add("$h\0$v\0");
@@ -52,9 +53,9 @@ sub content_dig_i {
        $dig->add($s);
 }
 
-sub content_digest ($) {
-       my ($eml) = @_;
-       my $dig = Digest::SHA->new(256);
+sub content_digest ($;$) {
+       my ($eml, $dig) = @_;
+       $dig //= Digest::SHA->new(256);
 
        # References: and In-Reply-To: get used interchangeably
        # in some "duplicates" in LKML.  We treat them the same
@@ -62,8 +63,9 @@ sub content_digest ($) {
        # do NOT consider the Message-ID as part of the content_hash
        # if we got here, we've already got Message-ID reuse
        my %seen = map { $_ => 1 } @{mids($eml)};
-       foreach my $mid (@{references($eml)}) {
-               $dig->add("ref\0$mid\0") unless $seen{$mid}++;
+       for (grep { !$seen{$_}++ } @{references($eml)}) {
+               utf8::encode($_);
+               $dig->add("ref\0$_\0");
        }
 
        # Only use Sender: if From is not present
@@ -97,9 +99,9 @@ sub content_hash ($) {
 sub git_sha ($$) {
        my ($n, $eml) = @_;
        my $dig = Digest::SHA->new($n);
-       my $buf = $eml->as_string;
-       $dig->add('blob '.length($buf)."\0");
-       $dig->add($buf);
+       my $bref = ref($eml) eq 'SCALAR' ? $eml : \($eml->as_string);
+       $dig->add('blob '.length($$bref)."\0");
+       $dig->add($$bref);
        $dig;
 }