www: do not obfuscate addresses in URLs

As they are likely Message-IDs.   If an email address ends up in
a URL, then it's likely public, so there's even less reason to
obfuscate that particular address.

[km: add xt/perf-obfuscate.t]
[ew: modernize perf test (5.10.1), use diag instead of print]

This version of the patch avoids the massive slowdown noted by Kyle in
<https://public-inbox.org/meta/87wnt9or6t.fsf@kyleam.com/>.
Performance remains roughly the same, if not slightly faster
(which may be due to me testing this on a busy server).  Results
from xt/perf-obfuscate.t against 6078 messages on a local mirror
of <https://public-inbox.org/meta/>:

	before: 6.67 usr + 0.04 sys = 6.71 CPU
	 after: 6.64 usr + 0.04 sys = 6.68 CPU

Reported-by: Kyle Meyer <kyle@kyleam.com>
Helped-by: Kyle Meyer <kyle@kyleam.com>
Link: https://public-inbox.org/meta/87a6q8p5qa.fsf@kyleam.com/

1 files changed, 64 insertions, 0 deletions

diff --git a/xt/perf-obfuscate.t b/xt/perf-obfuscate.t
new file mode 100644
index 00000000..d4e7fb99
--- /dev/null
+++ b/xt/perf-obfuscate.t
@@ -0,0 +1,64 @@
+#!perl -w
+# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use v5.10.1;
+use PublicInbox::TestCommon;
+use Benchmark qw(:all);
+use PublicInbox::Inbox;
+use PublicInbox::View;
+
+my $inboxdir = $ENV{GIANT_INBOX_DIR};
+plan skip_all => "GIANT_INBOX_DIR not defined for $0" unless $inboxdir;
+
+my $obfuscate = $ENV{PI_OBFUSCATE} ? 1 : 0;
+diag "obfuscate=$obfuscate\n";
+
+my @cat = qw(cat-file --buffer --batch-check --batch-all-objects);
+if (require_git(2.19, 1)) {
+        push @cat, '--unordered';
+} else {
+        warn
+"git <2.19, cat-file lacks --unordered, locality suffers\n";
+}
+require_mods qw(Plack::Util);
+use_ok 'Plack::Util';
+my $ibx = PublicInbox::Inbox->new({ inboxdir => $inboxdir, name => 'name' ,
+                                    obfuscate => $obfuscate});
+my $git = $ibx->git;
+my $fh = $git->popen(@cat);
+my $vec = '';
+vec($vec, fileno($fh), 1) = 1;
+select($vec, undef, undef, 60) or die "timed out waiting for --batch-check";
+
+my $ctx = {
+        env => { HTTP_HOST => 'example.com', 'psgi.url_scheme' => 'https' },
+        ibx => $ibx,
+        www => Plack::Util::inline_object(style => sub {''}),
+};
+my ($mime, $res, $oid, $type);
+my $n = 0;
+my $obuf = '';
+my $m = 0;
+
+my $cb = sub {
+        $mime = PublicInbox::Eml->new(shift);
+        PublicInbox::View::multipart_text_as_html($mime, $ctx);
+        ++$m;
+        $obuf = '';
+};
+
+my $t = timeit(1, sub {
+        $ctx->{obuf} = \$obuf;
+        $ctx->{mhref} = '../';
+        while (<$fh>) {
+                ($oid, $type) = split / /;
+                next if $type ne 'blob';
+                ++$n;
+                $git->cat_async($oid, $cb);
+        }
+        $git->cat_async_wait;
+});
+diag 'multipart_text_as_html took '.timestr($t)." for $n <=> $m messages";
+is($m, $n, 'rendered all messages');
+done_testing();