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
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;
}