X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=2e883f810023f2a0bb3314e418437cca469365e0;hb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;hp=a120a291bd4d85c1e37ce4c1b549a7cdd2d948eb;hpb=6f384fc3c6f95dd0e9561b6ec9c371784805696e;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index a120a291..2e883f81 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 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
@@ -9,24 +9,13 @@ use warnings;
 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/;
-
-# User-generated content (UGC) may have excessively long lines
-# and screw up rendering on some browsers, so we use pre-wrap.
-#
-# We also force everything to the same scaled font-size because GUI
-# browsers (tested both Firefox and surf (webkit)) uses a larger font
-# for the Search <form> element than the rest of the page.  Font size
-# uniformity is important to people who rely on gigantic fonts.
-# Finally, we use monospace to ensure the Search field and button
-# has the same size and spacing as everything else which is
-# <pre>-formatted anyways.
-use constant STYLE =>
-	'<style>pre{white-space:pre-wrap}' .
-	'*{font-size:100%;font-family:monospace}</style>';
-
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape
+		to_attr prurl/;
 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) = @_;
 
@@ -43,13 +32,20 @@ sub new_msgid {
 	$class->new($msgid, mid_escape($msgid));
 }
 
-sub new_oneline {
-	my ($class, $raw) = @_;
-	$raw = '' unless defined $raw;
-	$raw =~ tr/\t\n / /s; # squeeze spaces
-	$raw =~ tr/\r//d; # kill CR
-	$class->new($raw);
-}
+# some of these overrides are standard C escapes so they're
+# easy-to-understand when rendered.
+my %escape_sequence = (
+	"\x00" => '\\0', # NUL
+	"\x07" => '\\a', # bell
+	"\x08" => '\\b', # backspace
+	"\x09" => "\t", # obvious to show as-is
+	"\x0a" => "\n", # obvious to show as-is
+	"\x0b" => '\\v', # vertical tab
+	"\x0c" => '\\f', # form feed
+	"\x0d" => '\\r', # carriage ret (not preceding \n)
+	"\x1b" => '^[', # ASCII escape (mutt seems to escape this way)
+	"\x7f" => '\\x7f', # DEL
+);
 
 my %xhtml_map = (
 	'"' => '&#34;',
@@ -60,18 +56,16 @@ my %xhtml_map = (
 );
 
 $xhtml_map{chr($_)} = 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)
-$xhtml_map{"\x7f"} = '\\x7f'; # DEL
+%xhtml_map = (%xhtml_map, %escape_sequence);
+
+# for post-processing the output of highlight.pm and perhaps other
+# highlighers in the future
+sub src_escape ($) {
+	$_[0] =~ s/\r\n/\n/sg;
+	$_[0] =~ s/&apos;/&#39;/sg; # workaround https://bugs.debian.org/927409
+	$_[0] =~ s/([\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
+	$_[0] = $enc_ascii->encode($_[0], Encode::HTMLCREF);
+}
 
 sub ascii_html {
 	my ($s) = @_;
@@ -90,8 +84,15 @@ sub raw {
 	}
 }
 
-sub prurl {
+# returns a protocol-relative URL string
+sub prurl ($$) {
 	my ($env, $u) = @_;
+	if (ref($u) eq 'ARRAY') {
+		my $h = $env->{HTTP_HOST} // $env->{SERVER_NAME};
+		my @host_match = grep(/\b\Q$h\E\b/, @$u);
+		$u = $host_match[0] // $u->[0];
+		# fall through to below:
+	}
 	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
 }
 
@@ -126,4 +127,25 @@ sub to_filename ($) {
 	$s
 }
 
+# convert a filename (or any string) to HTML attribute
+
+my %ESCAPES = map { chr($_) => sprintf('::%02x', $_) } (0..255);
+$ESCAPES{'/'} = ':'; # common
+
+sub to_attr ($) {
+	my ($str) = @_;
+
+	# git would never do this to us:
+	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{$1}/egms;
+	utf8::decode($str); # allow wide chars
+	$first . $str;
+}
+
 1;