From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.0
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 85BBD20281;
	Tue, 23 May 2017 18:39:40 +0000 (UTC)
Date: Tue, 23 May 2017 18:39:40 +0000
From: Eric Wong <e@80x24.org>
To: =?utf-8?B?w4Z2YXIgQXJuZmrDtnLDsA==?= Bjarmason <avarab@gmail.com>
Cc: meta@public-inbox.org
Subject: Re: Feature R/BUG: Auto uri_unescape() & utf8 handling
Message-ID: <20170523183940.GA9543@dcvr>
References: <CACBZZX5Gnow08r=0A1J_kt3a=zpGyMfvsqu8nAN7kacNnDm+dg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <CACBZZX5Gnow08r=0A1J_kt3a=zpGyMfvsqu8nAN7kacNnDm+dg@mail.gmail.com>
List-Id: <meta@public-inbox.org>

Ævar Arnfjörð Bjarmason <avarab@gmail.com> wrote:
> BUG:
> 
> The code is missing a utf8::decode() or equivalent somewhere, try
> searching for: https://public-inbox.org/git/?q=%C3%86var
> 
> The search works, but the text in the search box is garbled, the
> second search is https://public-inbox.org/git/?q=%C3%83%E2%80%A0var
> third https://public-inbox.org/git/?q=%C3%83%C6%92%C3%A2%E2%82%AC%C2%A0var
> etc.

Thanks for the report, I'm testing the patch below on
public-inbox.org and it seems fine.  I'll need to write a test for
this...

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 1c2d75c..2613c8e 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -6,7 +6,7 @@ package PublicInbox::MID;
 use strict;
 use warnings;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/mid_clean id_compress mid2path mid_mime mid_escape/;
+our @EXPORT_OK = qw/mid_clean id_compress mid2path mid_mime mid_escape MID_ESC/;
 use URI::Escape qw(uri_escape_utf8);
 use Digest::SHA qw/sha1_hex/;
 use constant MID_MAX => 40; # SHA-1 hex length
diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm
index cec87c6..42bc648 100644
--- a/lib/PublicInbox/SearchView.pm
+++ b/lib/PublicInbox/SearchView.pm
@@ -222,7 +222,9 @@ sub mset_thread {
 
 sub ctx_prepare {
 	my ($q, $ctx) = @_;
-	my $qh = ascii_html($q->{'q'});
+	my $qh = $q->{'q'};
+	utf8::decode($qh);
+	$qh = ascii_html($qh);
 	$ctx->{-q_value_html} = $qh;
 	$ctx->{-atom} = '?'.$q->qs_html(x => 'A', r => undef);
 	$ctx->{-title_html} = "$qh - search results";
@@ -254,8 +256,9 @@ sub adump {
 package PublicInbox::SearchQuery;
 use strict;
 use warnings;
+use URI::Escape qw(uri_escape);
 use PublicInbox::Hval;
-use PublicInbox::MID qw(mid_escape);
+use PublicInbox::MID qw(MID_ESC);
 
 sub new {
 	my ($class, $qp) = @_;
@@ -280,7 +283,7 @@ sub qs_html {
 		$self = $tmp;
 	}
 
-	my $q = mid_escape($self->{'q'});
+	my $q = uri_escape($self->{'q'}, MID_ESC);
 	$q =~ s/%20/+/g; # improve URL readability
 	my $qs = "q=$q";
 
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 13b3921..f3c702e 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -42,6 +42,7 @@ sub call {
 
 	# we don't care about multi-value
 	my %qp = map {
+		utf8::decode($_);
 		my ($k, $v) = split('=', uri_unescape($_), 2);
 		$v = '' unless defined $v;
 		$v =~ tr/+/ /;