diff options
Diffstat (limited to 'lib/PublicInbox/ContentId.pm')
-rw-r--r-- | lib/PublicInbox/ContentId.pm | 102 |
1 files changed, 102 insertions, 0 deletions
diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm new file mode 100644 index 00000000..b1d27eb8 --- /dev/null +++ b/lib/PublicInbox/ContentId.pm @@ -0,0 +1,102 @@ +# Copyright (C) 2018 all contributors <meta@public-inbox.org> +# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> + +package PublicInbox::ContentId; +use strict; +use warnings; +use base qw/Exporter/; +our @EXPORT_OK = qw/content_id content_digest/; +use PublicInbox::MID qw(mids references); +use PublicInbox::MsgIter; + +# not sure if less-widely supported hash families are worth bothering with +use Digest::SHA; + +sub digest_addr ($$$) { + my ($dig, $h, $v) = @_; + $v =~ tr/"//d; + $v =~ s/@([a-z0-9\_\.\-\(\)]*([A-Z])\S*)/'@'.lc($1)/ge; + utf8::encode($v); + $dig->add("$h\0$v\0"); +} + +sub content_digest ($) { + my ($mime) = @_; + my $dig = Digest::SHA->new(256); + my $hdr = $mime->header_obj; + + # 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)}) { + # do NOT consider the Message-ID as part of the content_id + # if we got here, we've already got Message-ID reuse + $seen{$mid} = 1; + } + foreach my $mid (@{references($hdr)}) { + next if $seen{$mid}; + $dig->add("ref\0$mid\0"); + } + + # Only use Sender: if From is not present + foreach my $h (qw(From Sender)) { + my @v = $hdr->header($h); + if (@v) { + digest_addr($dig, $h, $_) foreach @v; + } + } + foreach my $h (qw(Subject Date)) { + my @v = $hdr->header($h); + foreach my $v (@v) { + utf8::encode($v); + $dig->add("$h\0$v\0"); + } + } + # Some mail processors will add " to unquoted names that were + # not in the original message. For the purposes of deduplication, + # do not take it into account: + foreach my $h (qw(To Cc)) { + my @v = $hdr->header($h); + digest_addr($dig, $h, $_) foreach @v; + } + msg_iter($mime, sub { + my ($part, $depth, @idx) = @{$_[0]}; + $dig->add("\0$depth:".join('.', @idx)."\0"); + my $fn = $part->filename; + if (defined $fn) { + utf8::encode($fn); + $dig->add("fn\0$fn\0"); + } + my @d = $part->header('Content-Description'); + foreach my $d (@d) { + utf8::encode($d); + $dig->add("d\0$d\0"); + } + $dig->add("b\0"); + my $ct = $part->content_type || 'text/plain'; + my $s = eval { $part->body_str }; + if ($@ && $ct =~ m!\btext/plain\b!i) { + # Try to assume UTF-8 because Alpine + # seems to do wacky things and set + # charset=X-UNKNOWN + $part->charset_set('UTF-8'); + $s = eval { $part->body_str }; + } + if (defined $s) { + $s =~ s/\r\n/\n/gs; + $s =~ s/\s*\z//s; + utf8::encode($s); + } else { + $s = $part->body; + } + $dig->add($s); + }); + $dig; +} + +sub content_id ($) { + content_digest($_[0])->digest; +} + +1; |