X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=2379b918514d398763fd3cf17a1151e60e1b5ed1;hp=68f895460821569e9ba67a01902af6248e9692c5;hb=ef9ce6f2dfc9fcbb91e3cec0b7a2b7f7e359be5d;hpb=8c61f7e039599b89edc1dea137af8bcf99ee9a49

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 68f89546..2379b918 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,40 +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 href);
 use Encode qw(find_encoding);
-use URI::Escape qw(uri_escape_utf8);
+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_ascii = find_encoding('us-ascii');
 
 sub new {
 	my ($class, $raw, $href) = @_;
-	my $self = fields::new($class);
 
-	# 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->{href} = defined $href ? $href : $raw;
-	$self;
+	bless {
+		raw => $raw,
+		href => defined $href ? $href : $raw,
+	}, $class;
 }
 
 sub new_msgid {
 	my ($class, $msgid) = @_;
-	$msgid =~ s/\A\s*<?//;
-	$msgid =~ s/>?\s*\z//;
-
-	if (length($msgid) <= 40) {
-		$class->new($msgid);
-	} else {
-		require Digest::SHA;
-		my $hex = Digest::SHA::sha1_hex($msgid);
-		$class->new($msgid, $hex);
-	}
+	$class->new($msgid, mid_escape($msgid));
 }
 
 sub new_oneline {
@@ -53,15 +50,28 @@ my %xhtml_map = (
 	'>' => '&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
-	$s =~ s/([<>&'"])/$xhtml_map{$1}/ge;
+	$s =~ s/([<>&'"\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
 	$enc_ascii->encode($s, Encode::HTMLCREF);
 }
 
 sub as_html { ascii_html($_[0]->{raw}) }
-sub as_href { ascii_html(uri_escape_utf8($_[0]->{href})) }
 
 sub raw {
 	if (defined $_[1]) {
@@ -71,4 +81,16 @@ sub raw {
 	}
 }
 
+sub prurl {
+	my ($env, $u) = @_;
+	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
+}
+
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# &#8228; &#183; and &#890; were also candidates:
+#   https://public-inbox.org/meta/20170615015250.GA6484@starla/
+# However, &#8226; was chosen to make copy+paste errors more obvious
+sub obfuscate_addrs ($) { $_[0] =~ s/(\S+@[^\.]+)\./$1&#8226;/g }
+
 1;