-# 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.
# See L<public-inbox-v2-format(5)> manpage for more details.
package PublicInbox::ContentHash;
use strict;
-use warnings;
-use base qw/Exporter/;
-our @EXPORT_OK = qw/content_hash content_digest/;
+use v5.10.1;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(content_hash content_digest git_sha);
use PublicInbox::MID qw(mids references);
use PublicInbox::MsgIter;
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");
$dig->add($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
# 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
content_digest($_[0])->digest;
}
+sub git_sha ($$) {
+ my ($n, $eml) = @_;
+ my $dig = Digest::SHA->new($n);
+ my $bref = ref($eml) eq 'SCALAR' ? $eml : \($eml->as_string);
+ $dig->add('blob '.length($$bref)."\0");
+ $dig->add($$bref);
+ $dig;
+}
+
1;