user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
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	[thread overview]
Message-ID: <20220910081729.2011934-21-e@80x24.org> (raw)
In-Reply-To: <20220910081729.2011934-1-e@80x24.org>

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);
 			$ctx->zmore('</pre><hr>');
 		}
@@ -56,7 +56,7 @@ sub no_over_html ($) {
 	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('</pre><hr>');
 	}
@@ -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} =
 "<pre>WARNING: multiple messages have this Message-ID\n</pre><pre>";
 	} else {
 		$ctx->{first_hdr} = $eml->header_obj;
 		$ctx->{chash} = content_hash($eml) if $ctx->{smsg}; # reused MID
-		$rv .= "<pre\nid=b>"; # anchor for body start
+		$ctx->{-html_tip} = "<pre\nid=b>"; # 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 .= $have_over ? qq(<a\nhref="#r"\nid=t>$v</a>\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(<a\nhref="#r"\nid=t></a>) 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<a\nhref="#r">[thread overview]</a>\n};
+		chop $hbuf; # drop "\n", or noop if $rv eq ''
+		$hbuf .= qq{\t<a\nhref="#r">[thread overview]</a>\n};
+		$hbuf =~ s!^Subject:\x20(.*?)(\n[A-Z]|\z)
+				!Subject: <a\nhref="#r"\nid=t>$1</a>$2!msx or
+			$hbuf .= qq(<a\nhref="#r\nid=t></a>);
+	}
+	if (scalar(@$mids) == 1) { # common case
+		my $x = ascii_html($mids->[0]);
+		$hbuf .= qq[Message-ID: &lt;$x&gt; (<a href="raw">raw</a>)\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]);
-		$rv .= qq[Message-ID: &lt;$mhtml&gt; (<a href="raw">raw</a>)\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 <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;
@@ -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');

  parent reply	other threads:[~2022-09-10  8:18 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-10  8:16 [PATCH 00/38] www: reduce memory usage Eric Wong
2022-09-10  8:16 ` [PATCH 01/38] xt: fold perf-obfuscate into perf-msgview, future-proof Eric Wong
2022-09-10  8:16 ` [PATCH 02/38] www: gzip_filter: implicitly flush {obuf} on zmore/zflush Eric Wong
2022-09-10  8:16 ` [PATCH 03/38] view: rework single message page to compress earlier Eric Wong
2022-09-10  8:16 ` [PATCH 04/38] www_atom_stream: require 200 response Eric Wong
2022-09-10  8:16 ` [PATCH 05/38] www_stream: aresponse assumes 200, too Eric Wong
2022-09-10  8:16 ` [PATCH 06/38] www_text: reduce parameter passing for response header Eric Wong
2022-09-10  8:16 ` [PATCH 07/38] viewvcs: use shorter and simpler ctx->html_done Eric Wong
2022-09-10  8:16 ` [PATCH 08/38] www_listing: consolidate some ->zmore dispatches Eric Wong
2022-09-10  8:17 ` [PATCH 09/38] www_listing: avoid unnecessary work for common cases Eric Wong
2022-09-10  8:17 ` [PATCH 10/38] www: viewdiff: use return value for diff_hunk Eric Wong
2022-09-10  8:17 ` [PATCH 11/38] view: simplify _parent_headers Eric Wong
2022-09-10  8:17 ` [PATCH 12/38] view: eml_entry: reduce manipulation of ctx->{obuf} Eric Wong
2022-09-10  8:17 ` [PATCH 13/38] gzip_filter: ->translate can reuse zmore/zflush Eric Wong
2022-09-10  8:17 ` [PATCH 14/38] view: remove multipart_text_as_html Eric Wong
2022-09-10  8:17 ` [PATCH 15/38] view: reduce subroutine calls for submsg_hdr Eric Wong
2022-09-10  8:17 ` [PATCH 16/38] view: attach_link: reduce obuf manipulation Eric Wong
2022-09-10  8:17 ` [PATCH 17/38] viewdiff: reuse existing string in diff_before_or_after Eric Wong
2022-09-10  8:17 ` [PATCH 18/38] view: _th_index_lite: avoid one s///, improve symmetry Eric Wong
2022-09-10  8:17 ` [PATCH 19/38] view: _th_index_lite: use `//' defined-or op Eric Wong
2022-09-10  8:17 ` Eric Wong [this message]
2022-09-10  8:17 ` [PATCH 21/38] view: html_footer: golf out a few lines Eric Wong
2022-09-10  8:17 ` [PATCH 22/38] view: html_footer: remove obuf dependency Eric Wong
2022-09-10  8:17 ` [PATCH 23/38] view: html_footer: avoid escaping " in a few places Eric Wong
2022-09-10  8:17 ` [PATCH 24/38] viewdiff: diff_hunk: shorten conditionals, slightly Eric Wong
2022-09-10  8:17 ` [PATCH 25/38] view: switch a few things to ctx->zmore Eric Wong
2022-09-10  8:17 ` [PATCH 26/38] www: drop {obuf} use entirely, for now Eric Wong
2022-09-10  8:17 ` [PATCH 27/38] www: switch to zadd for the majority of buffering Eric Wong
2022-09-10  8:17 ` [PATCH 28/38] www: use PerlIO::scalar (zfh) for buffering Eric Wong
2022-09-10  8:17 ` [PATCH 29/38] viewdiff: diff_before_or_after: avoid extra capture Eric Wong
2022-09-10  8:17 ` [PATCH 30/38] viewdiff: diff_header: shorten function, slightly Eric Wong
2022-09-10  8:17 ` [PATCH 31/38] www_static: switch to `print $zfh', and optimize Eric Wong
2022-09-10  8:17 ` [PATCH 32/38] httpd/async: describe which ->write subs it can call Eric Wong
2022-09-10  8:17 ` [PATCH 33/38] translate: support multiple buffer args Eric Wong
2022-09-10  8:17 ` [PATCH 34/38] gzip_filter: write: use multi-arg translate Eric Wong
2022-09-10  8:17 ` [PATCH 35/38] feed: new_html_i: switch from zmore to `print $zfh' Eric Wong
2022-09-10  8:17 ` [PATCH 36/38] mbox*: use multi-arg ->translate and ->write Eric Wong
2022-09-10  8:17 ` [PATCH 37/38] www_listing: switch to `print $zfh' Eric Wong
2022-09-10  8:17 ` [PATCH 38/38] viewvcs: " Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220910081729.2011934-21-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/public-inbox.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).