prepare HTML rendering maintainer tests for upcoming changes

There'll be a number of upcoming changes to HTML rendering
of messages to hopefully reduce memory usage and speedups
by writing out to the gzip buffer earlier.

Update the tests now so it'll be easier to test before
and after results.

diff --git a/MANIFEST b/MANIFEST
index 336c7e6ada12bc89cb0bb4a0722ef0a118734bb2..ac21ddccb21c66ac52d667e098dfac949150a94b 100644 (file)
--- a/MANIFEST
+++ b/MANIFEST
@@ -582,7 +582,6 @@ t/x-unknown-alpine.eml
 t/xcpdb-reshard.t
 version-gen.perl
 xt/cmp-msgstr.t
-xt/cmp-msgview.t
 xt/create-many-inboxes.t
 xt/eml_check_limits.t
 xt/eml_octet-stream.t

diff --git a/xt/cmp-msgview.t b/xt/cmp-msgview.t
deleted file mode 100644 (file)
index 9b06f88..0000000
--- a/xt/cmp-msgview.t
+++ /dev/null
@@ -1,94 +0,0 @@
-#!perl -w
-# Copyright (C) 2020-2021 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' },
-       ibx => $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");
-       }
-};
-my $t = timeit(1, sub {
-       while (<$fh>) {
-               my ($oid, $type) = split / /;
-               next if $type ne 'blob';
-               ++$n;
-               $git->cat_async($oid, $git_cb);
-       }
-       $git->async_wait_all;
-});
-is($m, $n, 'rendered all messages');
-
-# we'll tolerate minor differences in HTML rendering
-diag "$ndiff_html HTML differences";
-
-done_testing();

diff --git a/xt/perf-msgview.t b/xt/perf-msgview.t
index cf550c1a284b80b9dd516444f93302a604bd194d..7f92ce858a2e4cb5172a6832447c9f0fe26b14bd 100644 (file)
--- a/xt/perf-msgview.t
+++ b/xt/perf-msgview.t
@@ -7,7 +7,7 @@ use PublicInbox::TestCommon;
 use Benchmark qw(:all);
 use PublicInbox::Inbox;
 use PublicInbox::View;
-use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::WwwStream;
 
 my $inboxdir = $ENV{GIANT_INBOX_DIR} // $ENV{GIANT_PI_DIR};
 my $blob = $ENV{TEST_BLOB};
@@ -31,26 +31,28 @@ if ($fh) {
                die "timed out waiting for --batch-check";
 }
 
-my $ctx = {
+my $ctx = bless {
        env => { HTTP_HOST => 'example.com', 'psgi.url_scheme' => 'https' },
        ibx => $ibx,
        www => Plack::Util::inline_object(style => sub {''}),
-};
-my ($mime, $res, $oid, $type);
+       gz => PublicInbox::GzipFilter::gzip_or_die(),
+}, 'PublicInbox::WwwStream';
+my ($eml, $res, $oid, $type);
 my $n = 0;
-my $obuf = '';
 my $m = 0;
+${$ctx->{obuf}} = '';
+$ctx->{mhref} = '../';
 
 my $cb = sub {
-       $mime = PublicInbox::Eml->new(shift);
-       PublicInbox::View::multipart_text_as_html($mime, $ctx);
+       $eml = PublicInbox::Eml->new(shift);
+       $eml->each_part(\&PublicInbox::View::add_text_body, $ctx, 1);
+       $ctx->zflush;
        ++$m;
-       $obuf = '';
+       delete $ctx->{zbuf};
+       ${$ctx->{obuf}} = '';
 };
 
 my $t = timeit(1, sub {
-       $ctx->{obuf} = \$obuf;
-       $ctx->{mhref} = '../';
        if (defined $blob) {
                my $nr = $ENV{NR} // 10000;
                for (1..$nr) {
@@ -67,6 +69,6 @@ my $t = timeit(1, sub {
        }
        $git->async_wait_all;
 });
-diag 'multipart_text_as_html took '.timestr($t)." for $n <=> $m messages";
+diag 'add_text_body took '.timestr($t)." for $n <=> $m messages";
 is($m, $n, 'rendered all messages');
 done_testing();

diff --git a/xt/perf-obfuscate.t b/xt/perf-obfuscate.t
index 640309d2cbc6f3fb2aa694f96950de28dc3173cb..4da361240f1dbf79ece5362c58d7d67fc400b742 100644 (file)
--- a/xt/perf-obfuscate.t
+++ b/xt/perf-obfuscate.t
@@ -1,5 +1,5 @@
 #!perl -w
-# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# Copyright (C) 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;
@@ -7,6 +7,7 @@ use PublicInbox::TestCommon;
 use Benchmark qw(:all);
 use PublicInbox::Inbox;
 use PublicInbox::View;
+use PublicInbox::WwwStream;
 
 my $inboxdir = $ENV{GIANT_INBOX_DIR};
 plan skip_all => "GIANT_INBOX_DIR not defined for $0" unless $inboxdir;
@@ -22,7 +23,6 @@ if (require_git(2.19, 1)) {
 "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;
@@ -31,26 +31,28 @@ my $vec = '';
 vec($vec, fileno($fh), 1) = 1;
 select($vec, undef, undef, 60) or die "timed out waiting for --batch-check";
 
-my $ctx = {
+my $ctx = bless {
        env => { HTTP_HOST => 'example.com', 'psgi.url_scheme' => 'https' },
        ibx => $ibx,
        www => Plack::Util::inline_object(style => sub {''}),
-};
-my ($mime, $res, $oid, $type);
+       gz => PublicInbox::GzipFilter::gzip_or_die(),
+}, 'PublicInbox::WwwStream';
+my ($eml, $res, $oid, $type);
 my $n = 0;
-my $obuf = '';
 my $m = 0;
+${$ctx->{obuf}} = '';
+$ctx->{mhref} = '../';
 
 my $cb = sub {
-       $mime = PublicInbox::Eml->new(shift);
-       PublicInbox::View::multipart_text_as_html($mime, $ctx);
+       $eml = PublicInbox::Eml->new(shift);
+       $eml->each_part(\&PublicInbox::View::add_text_body, $ctx, 1);
+       $ctx->zflush;
        ++$m;
-       $obuf = '';
+       delete $ctx->{zbuf};
+       ${$ctx->{obuf}} = '';
 };
 
 my $t = timeit(1, sub {
-       $ctx->{obuf} = \$obuf;
-       $ctx->{mhref} = '../';
        while (<$fh>) {
                ($oid, $type) = split / /;
                next if $type ne 'blob';
@@ -59,6 +61,6 @@ my $t = timeit(1, sub {
        }
        $git->async_wait_all;
 });
-diag 'multipart_text_as_html took '.timestr($t)." for $n <=> $m messages";
+diag 'add_text_body took '.timestr($t)." for $n <=> $m messages";
 is($m, $n, 'rendered all messages');
 done_testing();