X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=23233f0e7e979c8ff524e1864a46489a747512c9;hb=78792fee4031aee0a8bd532bff98efc2b9409d68;hp=cd3a4df34bec61bad715fbf1546dec1c74338d2e;hpb=1988d730c0088e8b1f6193650c7ee929df8a2ed7;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index cd3a4df3..23233f0e 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # represents a header value in various forms.  Used for HTML generation
@@ -10,27 +10,13 @@ use Encode qw(find_encoding);
 use PublicInbox::MID qw/mid_clean mid_escape/;
 use base qw/Exporter/;
 our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape
-		to_attr from_attr/;
+		to_attr prurl mid_href/;
 my $enc_ascii = find_encoding('us-ascii');
 
 # safe-ish acceptable filename pattern for portability
 our $FN = '[a-zA-Z0-9][a-zA-Z0-9_\-\.]+[a-zA-Z0-9]'; # needs \z anchor
 
-sub new {
-	my ($class, $raw, $href) = @_;
-
-	# we never care about trailing whitespace
-	$raw =~ s/\s*\z//;
-	bless {
-		raw => $raw,
-		href => defined $href ? $href : $raw,
-	}, $class;
-}
-
-sub new_msgid {
-	my ($class, $msgid) = @_;
-	$class->new($msgid, mid_escape($msgid));
-}
+sub mid_href { ascii_html(mid_escape($_[0])) }
 
 # some of these overrides are standard C escapes so they're
 # easy-to-understand when rendered.
@@ -69,22 +55,12 @@ sub src_escape ($) {
 
 sub ascii_html {
 	my ($s) = @_;
-	$s =~ s/\r\n/\n/sg; # fixup bad line endings
 	$s =~ s/([<>&'"\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
 	$enc_ascii->encode($s, Encode::HTMLCREF);
 }
 
-sub as_html { ascii_html($_[0]->{raw}) }
-
-sub raw {
-	if (defined $_[1]) {
-		$_[0]->{raw} = $_[1];
-	} else {
-		$_[0]->{raw};
-	}
-}
-
-sub prurl {
+# returns a protocol-relative URL string
+sub prurl ($$) {
 	my ($env, $u) = @_;
 	if (ref($u) eq 'ARRAY') {
 		my $h = $env->{HTTP_HOST} // $env->{SERVER_NAME};
@@ -102,7 +78,7 @@ sub prurl {
 # However, &#8226; was chosen to make copy+paste errors more obvious
 sub obfuscate_addrs ($$;$) {
 	my $ibx = $_[0];
-	my $repl = $_[2] || '&#8226;';
+	my $repl = $_[2] // '&#8226;';
 	my $re = $ibx->{-no_obfuscate_re}; # regex of domains
 	my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
 	$_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
@@ -138,22 +114,12 @@ sub to_attr ($) {
 	return if index($str, '//') >= 0;
 
 	my $first = '';
+	utf8::encode($str); # to octets
 	if ($str =~ s/\A([^A-Ya-z])//ms) { # start with a letter
 		  $first = sprintf('Z%02x', ord($1));
 	}
 	$str =~ s/([^A-Za-z0-9_\.\-])/$ESCAPES{$1}/egms;
-	$first . $str;
-}
-
-# reverse the result of to_attr
-sub from_attr ($) {
-	my ($str) = @_;
-	my $first = '';
-	if ($str =~ s/\AZ([a-f0-9]{2})//ms) {
-		$first = chr(hex($1));
-	}
-	$str =~ s!::([a-f0-9]{2})!chr(hex($1))!egms;
-	$str =~ tr!:!/!;
+	utf8::decode($str); # allow wide chars
 	$first . $str;
 }