diff options
author | Eric Wong <e@yhbt.net> | 2020-05-10 22:37:12 +0000 |
---|---|---|
committer | Eric Wong <e@yhbt.net> | 2020-05-12 06:15:59 +0000 |
commit | 098fecd1fe516a00fbfd49622b82be382ebcdab6 (patch) | |
tree | 0b38bb0910e6f9b8c3600ba6ef105aac43bafed6 /lib/PublicInbox/ContentId.pm | |
parent | cd8cda10c9687533949a8a358fd7b858f704da6e (diff) | |
download | public-inbox-098fecd1fe516a00fbfd49622b82be382ebcdab6.tar.gz |
The old name may be confused with "Content-ID" as described in RFC 2392, so use an alternate name to avoid confusing future readers.
Diffstat (limited to 'lib/PublicInbox/ContentId.pm')
-rw-r--r-- | lib/PublicInbox/ContentId.pm | 99 |
1 files changed, 0 insertions, 99 deletions
diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm deleted file mode 100644 index 8d77934f..00000000 --- a/lib/PublicInbox/ContentId.pm +++ /dev/null @@ -1,99 +0,0 @@ -# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org> -# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> - -# Unstable internal API. -# Used for on-the-fly duplicate detection in V2 inboxes. -# This is not stored in any database anywhere and may change -# as changes in duplicate detection are needed. -# See L<public-inbox-v2-format(5)> manpage for more details. -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$v\0"); -} - -sub content_dig_i { - my ($dig) = $_[1]; - my ($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, undef) = msg_part_text($part, $ct); - if (defined $s) { - $s =~ s/\r\n/\n/gs; - $s =~ s/\s*\z//s; - utf8::encode($s); - } else { - $s = $part->body; - } - $dig->add($s); -} - -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: - # do NOT consider the Message-ID as part of the content_id - # if we got here, we've already got Message-ID reuse - my %seen = map { $_ => 1 } @{mids($hdr)}; - foreach my $mid (@{references($hdr)}) { - $dig->add("ref\0$mid\0") unless $seen{$mid}++; - } - - # 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, \&content_dig_i, $dig); - $dig; -} - -sub content_id ($) { - content_digest($_[0])->digest; -} - -1; |