From 69329215485cf2ab9d8cd1fa7faf65d8ec42dc0b Mon Sep 17 00:00:00 2001
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Date: Wed, 18 Apr 2018 09:13:10 +0000
Subject: v2: generate better Message-IDs for duplicates

While hunting duplicates, I noticed a leading '-' in some
Message-IDs as a result of RFC4648 encoding.  While '-' seems
allowed by RFC5322 and URL-friendly (RFC4648), they are uncommon
and make using Message-IDs as arguments for command-line tools
more difficult.  So prefix them with a datestamp to at least
give readers some sense of the age.  And shorten the "localhost"
hostname to "z" to save space.
---
 lib/PublicInbox/Import.pm     | 18 ++++++++++--------
 lib/PublicInbox/V2Writable.pm |  6 +++---
 2 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'lib/PublicInbox')

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 9e8900f3..c7a96e1e 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -14,6 +14,7 @@ use PublicInbox::Address;
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 use PublicInbox::ContentId qw(content_digest);
 use PublicInbox::MDA;
+use POSIX qw(strftime);
 
 sub new {
 	my ($class, $git, $name, $email, $ibx) = @_;
@@ -330,7 +331,7 @@ sub v1_mid0 ($) {
 	my $mids = mids($hdr);
 
 	if (!scalar(@$mids)) { # spam often has no Message-Id
-		my $mid0 = digest2mid(content_digest($mime));
+		my $mid0 = digest2mid(content_digest($mime), $hdr);
 		append_mid($hdr, $mid0);
 		return $mid0;
 	}
@@ -445,18 +446,19 @@ sub atfork_child {
 	}
 }
 
-sub digest2mid ($) {
-	my ($dig) = @_;
+sub digest2mid ($$) {
+	my ($dig, $hdr) = @_;
 	my $b64 = $dig->clone->b64digest;
 	# Make our own URLs nicer:
 	# See "Base 64 Encoding with URL and Filename Safe Alphabet" in RFC4648
 	$b64 =~ tr!+/=!-_!d;
 
-	# We can make this more meaningful with a date prefix or other things,
-	# but this is only needed for crap that fails to generate a Message-ID
-	# or reuses one.  In other words, it's usually spammers who hit this
-	# so they don't deserve nice Message-IDs :P
-	$b64 . '@localhost';
+	# Add a date prefix to prevent a leading '-' in case that trips
+	# up some tools (e.g. if a Message-ID were a expected as a
+	# command-line arg)
+	my $dt = msg_datestamp($hdr);
+	$dt = POSIX::strftime('%Y%m%d%H%M%S', gmtime($dt));
+	"$dt.$b64" . '@z';
 }
 
 sub clean_purge_buffer {
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 66f8a8a3..0dcdedae 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -174,19 +174,19 @@ sub num_for_harder {
 
 	my $hdr = $mime->header_obj;
 	my $dig = content_digest($mime);
-	$$mid0 = PublicInbox::Import::digest2mid($dig);
+	$$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
 	my $num = $self->{mm}->mid_insert($$mid0);
 	unless (defined $num) {
 		# it's hard to spoof the last Received: header
 		my @recvd = $hdr->header_raw('Received');
 		$dig->add("Received: $_") foreach (@recvd);
-		$$mid0 = PublicInbox::Import::digest2mid($dig);
+		$$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
 		$num = $self->{mm}->mid_insert($$mid0);
 
 		# fall back to a random Message-ID and give up determinism:
 		until (defined($num)) {
 			$dig->add(rand);
-			$$mid0 = PublicInbox::Import::digest2mid($dig);
+			$$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
 			warn "using random Message-ID <$$mid0> as fallback\n";
 			$num = $self->{mm}->mid_insert($$mid0);
 		}
-- 
cgit v1.2.3-24-ge0c7