X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FContentId.pm;h=0c4a8678beb02fa4db436ca12c55eda6bc0edc79;hb=261f705649bf5bc9c1954b29cfdb3c894cf44be2;hp=b1d27eb8e48a8e835c0d088f77e84f3a7e38dd88;hpb=cfb8d16578e7f2f2e300f9f436205e4a8fc7f322;p=public-inbox.git

diff --git a/lib/PublicInbox/ContentId.pm b/lib/PublicInbox/ContentId.pm
index b1d27eb8..0c4a8678 100644
--- a/lib/PublicInbox/ContentId.pm
+++ b/lib/PublicInbox/ContentId.pm
@@ -1,6 +1,11 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2019 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;
@@ -20,6 +25,33 @@ sub digest_addr ($$$) {
 	$dig->add("$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 $dig = Digest::SHA->new(256);
@@ -28,12 +60,9 @@ sub content_digest ($) {
 	# 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;
-	}
+	# 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)}) {
 		next if $seen{$mid};
 		$dig->add("ref\0$mid\0");
@@ -60,38 +89,7 @@ sub content_digest ($) {
 		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);
-	});
+	msg_iter($mime, \&content_dig_i, $dig);
 	$dig;
 }