diff options
Diffstat (limited to 'lib/PublicInbox/ContentHash.pm')
-rw-r--r-- | lib/PublicInbox/ContentHash.pm | 41 |
1 files changed, 24 insertions, 17 deletions
diff --git a/lib/PublicInbox/ContentHash.pm b/lib/PublicInbox/ContentHash.pm index bacc9cdd..95ca2929 100644 --- 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. @@ -15,7 +15,8 @@ use PublicInbox::MID qw(mids references); use PublicInbox::MsgIter; # not sure if less-widely supported hash families are worth bothering with -use Digest::SHA; +use PublicInbox::SHA; # faster, but no ->clone +use Digest::SHA; # we still need this for ->clone sub digest_addr ($$$) { my ($dig, $h, $v) = @_; @@ -44,7 +45,7 @@ sub content_dig_i { my $ct = $part->content_type || 'text/plain'; my ($s, undef) = msg_part_text($part, $ct); if (defined $s) { - $s =~ s/\r\n/\n/gs; + $s =~ s/\r\n/\n/gs; # TODO: consider \r+\n to match View $s =~ s/\s*\z//s; utf8::encode($s); } else { @@ -53,18 +54,26 @@ sub content_dig_i { $dig->add($s); } -sub content_digest ($;$) { - my ($eml, $dig) = @_; +sub content_digest ($;$$) { + my ($eml, $dig, $hash_mids) = @_; $dig //= Digest::SHA->new(256); # 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_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}++; + # if we got here, we've already got Message-ID reuse for v2. + # + # However, `lei q --dedupe=content' does use $hash_mids since + # it doesn't have any other dedupe + my $mids = mids($eml); + if ($hash_mids) { + $dig->add("mid\0$_\0") for @$mids; + } + my %seen = map { $_ => 1 } @$mids; + for (grep { !$seen{$_}++ } @{references($eml)}) { + utf8::encode($_); + $dig->add("ref\0$_\0"); } # Only use Sender: if From is not present @@ -74,8 +83,7 @@ sub content_digest ($;$) { last; } foreach my $h (qw(Subject Date)) { - my @v = $eml->header($h); - foreach my $v (@v) { + for my $v ($eml->header($h)) { utf8::encode($v); $dig->add("$h\0$v\0"); } @@ -84,23 +92,22 @@ sub content_digest ($;$) { # not in the original message. For the purposes of deduplication, # do not take it into account: foreach my $h (qw(To Cc)) { - my @v = $eml->header($h); - digest_addr($dig, $h, $_) foreach @v; + digest_addr($dig, $h, $_) for ($eml->header($h)); } msg_iter($eml, \&content_dig_i, $dig); $dig; } sub content_hash ($) { - content_digest($_[0])->digest; + content_digest($_[0], PublicInbox::SHA->new(256))->digest; } +# don't clone the result of this sub git_sha ($$) { my ($n, $eml) = @_; - my $dig = Digest::SHA->new($n); + my $dig = PublicInbox::SHA->new($n); my $bref = ref($eml) eq 'SCALAR' ? $eml : \($eml->as_string); - $dig->add('blob '.length($$bref)."\0"); - $dig->add($$bref); + $dig->add('blob '.length($$bref)."\0", $$bref); $dig; } |