X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=800508861bcdb28dc435d121d7d1074d6814f2fd;hb=1a8eb0a43c68e64b77fdd3c4ebd977a1ab88e71b;hp=47b41a5844c875ddff9eeabf271485025a157f68;hpb=89f34da9a510bf87293721942d688b1425bb9cf7;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 47b41a58..80050886 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,34 +1,37 @@
-# Copyright (C) 2014, Eric Wong <normalperson@yhbt.net> and all contributors
+# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 #
-# represents a header value in various forms
+# represents a header value in various forms.  Used for HTML generation
+# in our web interface(s)
 package PublicInbox::Hval;
 use strict;
 use warnings;
-use fields qw(raw -as_utf8);
 use Encode qw(find_encoding);
-use CGI qw(escapeHTML);
-use URI::Escape qw(uri_escape);
+use PublicInbox::MID qw/mid_clean mid_escape/;
+use base qw/Exporter/;
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs/;
+
+# for user-generated content (UGC) which may have excessively long lines
+# and screw up rendering on some browsers.  This is the only CSS style
+# feature we use.
+use constant STYLE => '<style>pre{white-space:pre-wrap}</style>';
 
-my $enc_utf8 = find_encoding('utf8');
 my $enc_ascii = find_encoding('us-ascii');
 
 sub new {
-	my ($class, $raw) = @_;
-	my $self = fields::new($class);
+	my ($class, $raw, $href) = @_;
 
-	# we never care about leading/trailing whitespace
-	$raw =~ s/\A\s*//;
+	# we never care about trailing whitespace
 	$raw =~ s/\s*\z//;
-	$self->{raw} = $raw;
-	$self;
+	bless {
+		raw => $raw,
+		href => defined $href ? $href : $raw,
+	}, $class;
 }
 
 sub new_msgid {
-	my ($class, $raw) = @_;
-	$raw =~ s/\A<//;
-	$raw =~ s/>\z//;
-	$class->new($raw);
+	my ($class, $msgid) = @_;
+	$class->new($msgid, mid_escape($msgid));
 }
 
 sub new_oneline {
@@ -39,14 +42,68 @@ sub new_oneline {
 	$class->new($raw);
 }
 
-sub as_utf8 {
-	my ($self) = @_;
-	$self->{-as_utf8} ||= $enc_utf8->encode($self->{raw});
+my %xhtml_map = (
+	'"' => '&#34;',
+	'&' => '&#38;',
+	"'" => '&#39;',
+	'<' => '&lt;',
+	'>' => '&gt;',
+);
+
+$xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
+# some of these overrides are standard C escapes so they're
+# easy-to-understand when rendered.
+$xhtml_map{"\x00"} = '\\0'; # NUL
+$xhtml_map{"\x07"} = '\\a'; # bell
+$xhtml_map{"\x08"} = '\\b'; # backspace
+$xhtml_map{"\x09"} = "\t"; # obvious to show as-is
+$xhtml_map{"\x0a"} = "\n"; # obvious to show as-is
+$xhtml_map{"\x0b"} = '\\v'; # vertical tab
+$xhtml_map{"\x0c"} = '\\f'; # form feed
+$xhtml_map{"\x0d"} = '\\r'; # carriage ret (not preceding \n)
+$xhtml_map{"\x1b"} = '^['; # ASCII escape (mutt seems to escape this way)
+$xhtml_map{"\x7f"} = '\\x7f'; # DEL
+
+sub ascii_html {
+	my ($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 ascii_html { $enc_ascii->encode(escapeHTML($_[0]), Encode::HTMLCREF) }
+sub as_html { ascii_html($_[0]->{raw}) }
 
-sub as_html { ascii_html($_[0]->as_utf8) }
-sub as_href { ascii_html(uri_escape($_[0]->as_utf8)) }
+sub raw {
+	if (defined $_[1]) {
+		$_[0]->{raw} = $_[1];
+	} else {
+		$_[0]->{raw};
+	}
+}
+
+sub prurl {
+	my ($env, $u) = @_;
+	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
+}
+
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# &#8228; &#183; and &#890; were also candidates:
+#   https://public-inbox.org/meta/20170615015250.GA6484@starla/
+# However, &#8226; was chosen to make copy+paste errors more obvious
+sub obfuscate_addrs ($$) {
+	my $ibx = $_[0];
+	my $re = $ibx->{-no_obfuscate_re}; # regex of domains
+	my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
+	$_[1] =~ s/([\w\.\+=\-]+\@([\w\-]+\.[\w\.\-]+))/
+		my ($addr, $domain) = ($1, $2);
+		if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
+			$addr;
+		} else {
+			$addr =~ s!([^\.]+)\.!$1&#8226;!g;
+			$addr
+		}
+		/sge;
+}
 
 1;