From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.2 required=3.0 tests=ALL_TRUSTED,BAYES_00, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF, T_SCC_BODY_TEXT_LINE shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 42ACA1F62E for ; Sat, 10 Sep 2022 08:18:55 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=80x24.org; s=selector1; t=1662797935; bh=m6GDzY7n/C9AMUUa01VoHr5mWX3wO1S7vFB3cL2Ai6Q=; h=From:To:Subject:Date:In-Reply-To:References:From; b=wrD577wJHIO8Ay15dmk54azdM4JZb93YHGHChhgyIIkV9H43bQUG0GqNX0e12e+Un CM2x7i4Jcol8Sh6/oklsO5+Tq62c5GZEdO23KiSTJoLT4CQNHrL8XkLh4nVI/a1iI0 oz/w60dY/Im7zvuTR+VrSd36Mj7+SB2Y/MEJ/q3w= From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 20/38] view: reduce ascii_html calls and {obuf} use Date: Sat, 10 Sep 2022 08:17:11 +0000 Message-Id: <20220910081729.2011934-21-e@80x24.org> In-Reply-To: <20220910081729.2011934-1-e@80x24.org> References: <20220910081729.2011934-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: We can rely on {-html_tip} for some things at the top of the page, and reduce ascii_html and obfuscate_addrs calls by working on the whole buffer at once. --- lib/PublicInbox/View.pm | 127 +++++++++++++++++----------------------- t/psgi_v2.t | 4 +- 2 files changed, 58 insertions(+), 73 deletions(-) diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm index 08ba54bb..52d37a9f 100644 --- a/lib/PublicInbox/View.pm +++ b/lib/PublicInbox/View.pm @@ -38,7 +38,7 @@ sub msg_page_i { : $ctx->gone('over'); $ctx->{mhref} = ($ctx->{nr} || $ctx->{smsg}) ? "../${\mid_href($smsg->{mid})}/" : ''; - if (_msg_page_prepare_obuf($eml, $ctx)) { + if (_msg_page_prepare($eml, $ctx)) { $eml->each_part(\&add_text_body, $ctx, 1); $ctx->zmore('
'); } @@ -56,7 +56,7 @@ sub no_over_html ($) { my $eml = PublicInbox::Eml->new($bref); $ctx->{mhref} = ''; PublicInbox::WwwStream::init($ctx); - if (_msg_page_prepare_obuf($eml, $ctx)) { # sets {-title_html} + if (_msg_page_prepare($eml, $ctx)) { # sets {-title_html} $eml->each_part(\&add_text_body, $ctx, 1); $ctx->zmore('
'); } @@ -635,11 +635,9 @@ sub add_text_body { # callback for each_part } } -sub _msg_page_prepare_obuf { +sub _msg_page_prepare { my ($eml, $ctx) = @_; my $have_over = !!$ctx->{ibx}->over; - my $obfs_ibx = $ctx->{-obfs_ibx}; - $ctx->{obuf} = \(my $rv = ''); my $mids = mids_for_index($eml); my $nr = $ctx->{nr}++; if ($nr) { # unlikely @@ -647,80 +645,86 @@ sub _msg_page_prepare_obuf { warn "W: BUG? @$mids not deduplicated properly\n"; return; } - $rv .= + $ctx->{-html_tip} = "
WARNING: multiple messages have this Message-ID\n
";
 	} else {
 		$ctx->{first_hdr} = $eml->header_obj;
 		$ctx->{chash} = content_hash($eml) if $ctx->{smsg}; # reused MID
-		$rv .= ""; # anchor for body start
+		$ctx->{-html_tip} = ""; # anchor for body start
 	}
 	$ctx->{-upfx} = '../';
 	my @title; # (Subject[0], From[0])
+	my $hbuf = '';
 	for my $v ($eml->header('From')) {
 		my @n = PublicInbox::Address::names($v);
-		$v = ascii_html($v);
-		$title[1] //= ascii_html(join(', ', @n));
-		if ($obfs_ibx) {
-			obfuscate_addrs($obfs_ibx, $v);
-			obfuscate_addrs($obfs_ibx, $title[1]);
-		}
-		$rv .= "From: $v\n" if $v ne '';
+		$title[1] //= join(', ', @n);
+		$hbuf .= "From: $v\n" if $v ne '';
 	}
-	foreach my $h (qw(To Cc)) {
+	for my $h (qw(To Cc)) {
 		for my $v ($eml->header($h)) {
 			fold_addresses($v);
-			$v = ascii_html($v);
-			obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
-			$rv .= "$h: $v\n" if $v ne '';
+			$hbuf .= "$h: $v\n" if $v ne '';
 		}
 	}
 	my @subj = $eml->header('Subject');
-	if (@subj) {
-		my $v = ascii_html(shift @subj);
-		obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
-		$rv .= 'Subject: ';
-		$rv .= $have_over ? qq($v\n) : "$v\n";
-		$title[0] = $v;
-		for $v (@subj) { # multi-Subject message :<
-			$v = ascii_html($v);
-			obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
-			$rv .= "Subject: $v\n";
-		}
-	} else { # dummy anchor for thread skeleton at bottom of page
-		$rv .= qq() if $have_over;
-		$title[0] = '(no subject)';
-	}
-	for my $v ($eml->header('Date')) {
-		$v = ascii_html($v);
-		obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; # possible :P
-		$rv .= qq{Date: $v\n};
+	$hbuf .= "Subject: $_\n" for @subj;
+	$title[0] = $subj[0] // '(no subject)';
+	$hbuf .= "Date: $_\n" for $eml->header('Date');
+	$hbuf = ascii_html($hbuf);
+	$ctx->{-title_html} = ascii_html(join(' - ', @title));
+	if (my $obfs_ibx = $ctx->{-obfs_ibx}) {
+		obfuscate_addrs($obfs_ibx, $hbuf);
+		obfuscate_addrs($obfs_ibx, $ctx->{-title_html});
 	}
+
 	# [thread overview] link is typically added after Date,
 	# but added after Subject, or even nothing.
 	if ($have_over) {
-		chop $rv; # drop "\n", or noop if $rv eq ''
-		$rv .= qq{\t[thread overview]\n};
+		chop $hbuf; # drop "\n", or noop if $rv eq ''
+		$hbuf .= qq{\t[thread overview]\n};
+		$hbuf =~ s!^Subject:\x20(.*?)(\n[A-Z]|\z)
+				!Subject: $1$2!msx or
+			$hbuf .= qq();
+	}
+	if (scalar(@$mids) == 1) { # common case
+		my $x = ascii_html($mids->[0]);
+		$hbuf .= qq[Message-ID: <$x> (raw)\n];
 	}
 	if (!$nr) { # first (and only) message, common case
-		$ctx->{-title_html} = join(' - ', @title);
-		$rv = $ctx->html_top . $rv;
+		$ctx->zmore($ctx->html_top, $hbuf);
+	} else {
+		delete $ctx->{-title_html};
+		$ctx->zmore($ctx->{-html_tip}, $hbuf);
 	}
-
 	$ctx->{-linkify} //= PublicInbox::Linkify->new;
-	if (scalar(@$mids) == 1) { # common case
-		my $mhtml = ascii_html($mids->[0]);
-		$rv .= qq[Message-ID: <$mhtml> (raw)\n];
-	} else {
+	$hbuf = '';
+	if (scalar(@$mids) != 1) { # unlikely, but it happens :<
 		# X-Alt-Message-ID can happen if a message is injected from
 		# public-inbox-nntpd because of multiple Message-ID headers.
-		my $s = '';
 		for my $h (qw(Message-ID X-Alt-Message-ID)) {
-			$s .= "$h: $_\n" for ($eml->header_raw($h));
+			$hbuf .= "$h: $_\n" for ($eml->header_raw($h));
 		}
-		$ctx->{-linkify}->linkify_mids('..', \$s, 1);
-		$rv .= $s;
+		$ctx->{-linkify}->linkify_mids('..', \$hbuf, 1); # escapes HTML
+		$ctx->zmore($hbuf);
+		$hbuf = '';
+	}
+	my @irt = $eml->header_raw('In-Reply-To');
+	my $refs;
+	if (!@irt) {
+		$refs = references($eml);
+		$irt[0] = pop(@$refs) if scalar @$refs;
 	}
-	$rv .= _parent_headers($ctx, $eml);
+	$hbuf .= "In-Reply-To: $_\n" for @irt;
+
+	# do not display References: if search is present,
+	# we show the thread skeleton at the bottom, instead.
+	if (!$have_over) {
+		$refs //= references($eml);
+		$hbuf .= 'References: <'.join(">\n\t<", @$refs).">\n" if @$refs;
+	}
+	$ctx->{-linkify}->linkify_mids('..', \$hbuf); # escapes HTML
+	$ctx->zmore($hbuf .= "\n");
+	${$ctx->{obuf}} = ''; # TODO remove
 	1;
 }
 
@@ -770,27 +774,6 @@ sub thread_skel ($$$) {
 	$ctx->{parent_msg} = $parent;
 }
 
-sub _parent_headers {
-	my ($ctx, $hdr) = @_;
-	my @irt = $hdr->header_raw('In-Reply-To');
-	my $refs;
-	my $s = '';
-	if (!@irt) {
-		$refs = references($hdr);
-		$irt[0] = pop(@$refs) if scalar @$refs;
-	}
-	$s .= "In-Reply-To: $_\n" for @irt;
-
-	# do not display References: if search is present,
-	# we show the thread skeleton at the bottom, instead.
-	if (!$ctx->{ibx}->over) {
-		$refs //= references($hdr);
-		$s .= 'References: <'.join(">\n\t<", @$refs).">\n" if @$refs;
-	}
-	$ctx->{-linkify}->linkify_mids('..', \$s); # escapes HTML
-	$s .= "\n";
-}
-
 # appends to obuf
 sub html_footer {
 	my ($ctx, $hdr) = @_;
diff --git a/t/psgi_v2.t b/t/psgi_v2.t
index 7d73b606..6b1b3a39 100644
--- a/t/psgi_v2.t
+++ b/t/psgi_v2.t
@@ -1,5 +1,5 @@
 #!perl -w
-# Copyright (C) 2018-2021 all contributors 
+# Copyright (C) all contributors 
 # License: AGPL-3.0+ 
 use strict;
 use v5.10.1;
@@ -209,6 +209,8 @@ my $client1 = sub {
 	local $SIG{__WARN__} = 'DEFAULT';
 	$res = $cb->(GET('/v2test/a-mid@b/'));
 	$raw = $res->content;
+	like($raw, qr/WARNING: multiple messages have this Message-ID/,
+		'warned about duplicate Message-IDs');
 	like($raw, qr/^hello world$/m, 'got first message');
 	like($raw, qr/^hello world!$/m, 'got second message');
 	like($raw, qr/^hello ghosts$/m, 'got third message');