From 69ae87044ca499aa401c73a9a1d764013539fb2d Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Sat, 14 Dec 2019 01:02:56 +0000
Subject: address: use Email::Address::XS if available

Email::Address::XS is a dependency of modern versions of Email::MIME,
so it's likely loaded and installed on newer systems, already;
and capable of handling more corner-cases than our pure-Perl
fallback.

We still fallback to the imperfect-but-good-enough-in-practice
pure-Perl code while avoiding the non-XS Email::Address (which
was susceptible to DoS attacks (CVE-2015-7686)).  We just need
to keep "git fast-import" happy.
---
 lib/PublicInbox/Address.pm   | 44 ++++++++++++++++++--------------------------
 lib/PublicInbox/AddressPP.pm | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+), 26 deletions(-)
 create mode 100644 lib/PublicInbox/AddressPP.pm

(limited to 'lib/PublicInbox')

diff --git a/lib/PublicInbox/Address.pm b/lib/PublicInbox/Address.pm
index a58d1eff..433b36eb 100644
--- a/lib/PublicInbox/Address.pm
+++ b/lib/PublicInbox/Address.pm
@@ -4,35 +4,27 @@ package PublicInbox::Address;
 use strict;
 use warnings;
 
-# very loose regexes, here.  We don't need RFC-compliance,
-# just enough to make thing sanely displayable and pass to git
+sub xs_emails { map { $_->address() } parse_email_addresses($_[0]) }
 
-sub emails {
-	($_[0] =~ /([\w\.\+=\?"\(\)\-!#\$%&'\*\/\^\`\|\{\}~]+\@[\w\.\-\(\)]+)
-		(?:\s[^>]*)?>?\s*(?:\(.*?\))?(?:,\s*|\z)/gx)
+sub xs_names {
+	map {
+		my $n = $_->name;
+		$n = $_->user if $n eq $_->address;
+		$n;
+	} parse_email_addresses($_[0]);
 }
 
-sub names {
-	my @p = split(/<?([^@<>]+)\@[\w\.\-]+>?\s*(\(.*?\))?(?:,\s*|\z)/,
-			$_[0]);
-	my @ret;
-	for (my $i = 0; $i <= $#p;) {
-		my $phrase = $p[$i++];
-		$phrase =~ tr/\r\n\t / /s;
-		$phrase =~ s/\A['"\s]*//;
-		$phrase =~ s/['"\s]*\z//;
-		my $user = $p[$i++] // '';
-		my $comment = $p[$i++] // '';
-		if ($phrase =~ /\S/) {
-			$phrase =~ s/\@\S+\z//;
-			push @ret, $phrase;
-		} elsif ($comment =~ /\A\((.*?)\)\z/) {
-			push @ret, $1;
-		} else {
-			push @ret, $user;
-		}
-	}
-	@ret;
+eval {
+	require Email::Address::XS;
+	Email::Address::XS->import(qw(parse_email_addresses));
+	*emails = \&xs_emails;
+	*names = \&xs_names;
+};
+
+if ($@) {
+	require PublicInbox::AddressPP;
+	*emails = \&PublicInbox::AddressPP::emails;
+	*names = \&PublicInbox::AddressPP::names;
 }
 
 1;
diff --git a/lib/PublicInbox/AddressPP.pm b/lib/PublicInbox/AddressPP.pm
new file mode 100644
index 00000000..cd7aedb9
--- /dev/null
+++ b/lib/PublicInbox/AddressPP.pm
@@ -0,0 +1,38 @@
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+package PublicInbox::AddressPP;
+use strict;
+
+# very loose regexes, here.  We don't need RFC-compliance,
+# just enough to make thing sanely displayable and pass to git
+# We favor Email::Address::XS for conformance if available
+
+sub emails {
+	($_[0] =~ /([\w\.\+=\?"\(\)\-!#\$%&'\*\/\^\`\|\{\}~]+\@[\w\.\-\(\)]+)
+		(?:\s[^>]*)?>?\s*(?:\(.*?\))?(?:,\s*|\z)/gx)
+}
+
+sub names {
+	my @p = split(/<?([^@<>]+)\@[\w\.\-]+>?\s*(\(.*?\))?(?:,\s*|\z)/,
+			$_[0]);
+	my @ret;
+	for (my $i = 0; $i <= $#p;) {
+		my $phrase = $p[$i++];
+		$phrase =~ tr/\r\n\t / /s;
+		$phrase =~ s/\A['"\s]*//;
+		$phrase =~ s/['"\s]*\z//;
+		my $user = $p[$i++] // '';
+		my $comment = $p[$i++] // '';
+		if ($phrase =~ /\S/) {
+			$phrase =~ s/\@\S+\z//;
+			push @ret, $phrase;
+		} elsif ($comment =~ /\A\((.*?)\)\z/) {
+			push @ret, $1;
+		} else {
+			push @ret, $user;
+		}
+	}
+	@ret;
+}
+
+1;
-- 
cgit v1.2.3-24-ge0c7