xt: eml comparison tests

While our codebase can still work with either MIME
implementation, add comparison tests to ensure we
handle corner cases in existing archives.

diff --git a/MANIFEST b/MANIFEST
index 055c8c9a2165f45e105f87e209355e53810d9f63..9c804a0780e1120526fe7428ae6fffb9666c03f9 100644 (file)
--- a/MANIFEST
+++ b/MANIFEST
@@ -331,6 +331,8 @@ t/www_listing.t
 t/www_static.t
 t/x-unknown-alpine.eml
 t/xcpdb-reshard.t
+xt/cmp-msgstr.t
+xt/cmp-msgview.t
 xt/git-http-backend.t
 xt/git_async_cmp.t
 xt/mem-msgview.t

diff --git a/xt/cmp-msgstr.t b/xt/cmp-msgstr.t
new file mode 100644 (file)
index 0000000..6bae0f6
--- /dev/null
+++ b/xt/cmp-msgstr.t
@@ -0,0 +1,108 @@
+#!perl -w
+# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use Test::More;
+use Benchmark qw(:all);
+use PublicInbox::Inbox;
+use PublicInbox::View;
+use PublicInbox::TestCommon;
+use PublicInbox::Eml;
+use Digest::MD5;
+use PublicInbox::MsgIter;
+require_mods(qw(Data::Dumper Email::MIME));
+Data::Dumper->import('Dumper');
+require PublicInbox::MIME;
+require_git(2.19);
+my ($tmpdir, $for_destroy) = tmpdir();
+my $inboxdir = $ENV{GIANT_INBOX_DIR};
+plan skip_all => "GIANT_INBOX_DIR not defined for $0" unless $inboxdir;
+my @cat = qw(cat-file --buffer --batch-check --batch-all-objects --unordered);
+my $ibx = PublicInbox::Inbox->new({ inboxdir => $inboxdir, name => 'cmp' });
+my $git = $ibx->git;
+my $fh = $git->popen(@cat);
+vec(my $vec = '', fileno($fh), 1) = 1;
+select($vec, undef, undef, 60) or die "timed out waiting for --batch-check";
+my $n = 0;
+my $m = 0;
+my $dig_cls = 'Digest::MD5';
+sub h ($) {
+       s/\s+\z//s; # E::M leaves trailing white space
+       s/\s+/ /sg;
+       "$_[0]: $_";
+}
+
+my $cmp = sub {
+       my ($p, $cmp_arg) = @_;
+       my $part = shift @$p;
+       push @$cmp_arg, '---'.join(', ', @$p).'---';
+       my $ct = $part->content_type // 'text/plain';
+       $ct =~ s/[ \t]+.*\z//s;
+       my ($s, $err);
+       eval {
+               push @$cmp_arg, map { h 'f' } $part->header('From');
+               push @$cmp_arg, map { h 't' } $part->header('To');
+               push @$cmp_arg, map { h 'cc' } $part->header('Cc');
+               push @$cmp_arg, map { h 'mid' } $part->header('Message-ID');
+               push @$cmp_arg, map { h 'refs' } $part->header('References');
+               push @$cmp_arg, map { h 'irt' } $part->header('In-Reply-To');
+               push @$cmp_arg, map { h 's' } $part->header('Subject');
+               push @$cmp_arg, map { h 'cd' }
+                                       $part->header('Content-Description');
+               ($s, $err) = msg_part_text($part, $ct);
+               if (defined $s) {
+                       $s =~ s/\s+\z//s;
+                       push @$cmp_arg, "S: ".$s;
+               } else {
+                       $part = $part->body;
+                       push @$cmp_arg, "T: $ct";
+                       if ($part =~ /[^\p{XPosixPrint}\s]/s) { # binary
+                               my $dig = $dig_cls->new;
+                               $dig->add($part);
+                               push @$cmp_arg, "M: ".$dig->hexdigest;
+                               push @$cmp_arg, "B: ".bytes::length($part);
+                       } else {
+                               $part =~ s/\s+\z//s;
+                               push @$cmp_arg, "X: ".$part;
+                       }
+               }
+       };
+       if ($@) {
+               $err //= '';
+               push @$cmp_arg, "E: $@ ($err)";
+       }
+};
+
+my $ndiff = 0;
+my $git_cb = sub {
+       my ($bref, $oid) = @_;
+       local $SIG{__WARN__} = sub { diag "$inboxdir $oid ", @_ };
+       ++$m;
+       PublicInbox::MIME->new($$bref)->each_part($cmp, my $m_ctx = [], 1);
+       PublicInbox::Eml->new($$bref)->each_part($cmp, my $e_ctx = [], 1);
+       if (join("\0", @$e_ctx) ne join("\0", @$m_ctx)) {
+               ++$ndiff;
+               open my $fh, '>', "$tmpdir/mime" or die $!;
+               print $fh Dumper($m_ctx) or die $!;
+               close $fh or die $!;
+               open $fh, '>', "$tmpdir/eml" or die $!;
+               print $fh Dumper($e_ctx) or die $!;
+               close $fh or die $!;
+               diag "$inboxdir $oid differ";
+               # using `git diff', diff(1) may not be installed
+               diag xqx([qw(git diff), "$tmpdir/mime", "$tmpdir/eml"]);
+       }
+};
+$git->cat_async_begin;
+my $t = timeit(1, sub {
+       while (<$fh>) {
+               my ($oid, $type) = split / /;
+               next if $type ne 'blob';
+               ++$n;
+               $git->cat_async($oid, $git_cb);
+       }
+       $git->cat_async_wait;
+});
+is($m, $n, "$inboxdir rendered all $m <=> $n messages");
+is($ndiff, 0, "$inboxdir $ndiff differences");
+done_testing();

diff --git a/xt/cmp-msgview.t b/xt/cmp-msgview.t
new file mode 100644 (file)
index 0000000..66fb467
--- /dev/null
+++ b/xt/cmp-msgview.t
@@ -0,0 +1,95 @@
+#!perl -w
+# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use Test::More;
+use Benchmark qw(:all);
+use PublicInbox::Inbox;
+use PublicInbox::View;
+use PublicInbox::TestCommon;
+use PublicInbox::Eml;
+use Digest::MD5;
+require_git(2.19);
+require_mods qw(Data::Dumper Email::MIME Plack::Util);
+Data::Dumper->import('Dumper');
+require PublicInbox::MIME;
+my ($tmpdir, $for_destroy) = tmpdir();
+my $inboxdir = $ENV{GIANT_INBOX_DIR};
+plan skip_all => "GIANT_INBOX_DIR not defined for $0" unless $inboxdir;
+my @cat = qw(cat-file --buffer --batch-check --batch-all-objects --unordered);
+my $ibx = PublicInbox::Inbox->new({ inboxdir => $inboxdir, name => 'perf' });
+my $git = $ibx->git;
+my $fh = $git->popen(@cat);
+vec(my $vec = '', fileno($fh), 1) = 1;
+select($vec, undef, undef, 60) or die "timed out waiting for --batch-check";
+my $mime_ctx = {
+       env => { HTTP_HOST => 'example.com', 'psgi.url_scheme' => 'https' },
+       -inbox => $ibx,
+       www => Plack::Util::inline_object(style => sub {''}),
+       obuf => \(my $mime_buf = ''),
+       mhref => '../',
+};
+my $eml_ctx = { %$mime_ctx, obuf => \(my $eml_buf = '') };
+my $n = 0;
+my $m = 0;
+my $ndiff_html = 0;
+my $dig_cls = 'Digest::MD5';
+my $digest_attach = sub { # ensure ->body (not ->body_raw) matches
+       my ($p, $cmp_arg) = @_;
+       my $part = shift @$p;
+       my $dig = $cmp_arg->[0] //= $dig_cls->new;
+       $dig->add($part->body_raw);
+       push @$cmp_arg, join(', ', @$p);
+};
+
+my $git_cb = sub {
+       my ($bref, $oid) = @_;
+       local $SIG{__WARN__} = sub { diag "$inboxdir $oid ", @_ };
+       ++$m;
+       my $mime = PublicInbox::MIME->new($$bref);
+       PublicInbox::View::multipart_text_as_html($mime, $mime_ctx);
+       my $eml = PublicInbox::Eml->new($$bref);
+       PublicInbox::View::multipart_text_as_html($eml, $eml_ctx);
+       if ($eml_buf ne $mime_buf) {
+               ++$ndiff_html;
+               open my $fh, '>', "$tmpdir/mime" or die $!;
+               print $fh $mime_buf or die $!;
+               close $fh or die $!;
+               open $fh, '>', "$tmpdir/eml" or die $!;
+               print $fh $eml_buf or die $!;
+               close $fh or die $!;
+               # using `git diff', diff(1) may not be installed
+               diag "$inboxdir $oid differs";
+               diag xqx([qw(git diff), "$tmpdir/mime", "$tmpdir/eml"]);
+       }
+       $eml_buf = $mime_buf = '';
+
+       # don't tolerate differences in attachment downloads
+       $mime = PublicInbox::MIME->new($$bref);
+       $mime->each_part($digest_attach, my $mime_cmp = [], 1);
+       $eml = PublicInbox::Eml->new($$bref);
+       $eml->each_part($digest_attach, my $eml_cmp = [], 1);
+       $mime_cmp->[0] = $mime_cmp->[0]->hexdigest;
+       $eml_cmp->[0] = $eml_cmp->[0]->hexdigest;
+       # don't have millions of "ok" lines
+       if (join("\0", @$eml_cmp) ne join("\0", @$mime_cmp)) {
+               diag Dumper([ $oid, eml => $eml_cmp, mime =>$mime_cmp ]);
+               is_deeply($eml_cmp, $mime_cmp, "$inboxdir $oid match");
+       }
+};
+$git->cat_async_begin;
+my $t = timeit(1, sub {
+       while (<$fh>) {
+               my ($oid, $type) = split / /;
+               next if $type ne 'blob';
+               ++$n;
+               $git->cat_async($oid, $git_cb);
+       }
+       $git->cat_async_wait;
+});
+is($m, $n, 'rendered all messages');
+
+# we'll tolerate minor differences in HTML rendering
+diag "$ndiff_html HTML differences";
+
+done_testing();