X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=fb21041acafcaa534c3563a1f191f902acc631df;hb=6c853f5256f3a324c018a37a9e8a6b9fc8fdc063;hp=2b4439703f59b692e9c6c80a628c809185c103fa;hpb=e56b908c0e97c2f479b350dfb0868bc463413b89;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 2b443970..fb21041a 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
@@ -10,35 +10,14 @@ 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 fmt_ts ts2str/;
+use POSIX qw(strftime);
 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($msgid));
-}
-
-sub new_oneline {
-	my ($class, $raw) = @_;
-	$raw = '' unless defined $raw;
-	$raw =~ tr/\t\n / /s; # squeeze spaces
-	$raw =~ tr/\r//d; # kill CR
-	$class->new($raw);
-}
+sub mid_href { ascii_html(mid_escape($_[0])) }
 
 # some of these overrides are standard C escapes so they're
 # easy-to-understand when rendered.
@@ -66,31 +45,30 @@ my %xhtml_map = (
 $xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
 %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) = @_;
-	$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} // $env->{SERVER_NAME};
+		my @host_match = grep(/\b\Q$h\E\b/, @$u);
+		$u = $host_match[0] // $u->[0];
+		# fall through to below:
+	}
 	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
 }
 
@@ -101,9 +79,9 @@ sub prurl {
 # However, &#8226; was chosen to make copy+paste errors more obvious
 sub obfuscate_addrs ($$;$) {
 	my $ibx = $_[0];
-	my $repl = $_[2] || '&#8226;';
+	my $repl = $_[2] // '&#8226;';
 	my $re = $ibx->{-no_obfuscate_re}; # regex of domains
-	my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
+	my $addrs = $ibx->{-no_obfuscate}; # { $address => 1 }
 	$_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
 		my ($addr, $user, $domain) = ($1, $2, $3);
 		if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
@@ -117,12 +95,12 @@ sub obfuscate_addrs ($$;$) {
 
 # like format_sanitized_subject in git.git pretty.c with '%f' format string
 sub to_filename ($) {
-	my ($s, undef) = split(/\n/, $_[0]);
+	my $s = (split(/\n/, $_[0]))[0] // return; # empty string => undef
 	$s =~ s/[^A-Za-z0-9_\.]+/-/g;
 	$s =~ tr/././s;
 	$s =~ s/[\.\-]+\z//;
 	$s =~ s/\A[\.\-]+//;
-	$s
+	$s eq '' ? undef : $s;
 }
 
 # convert a filename (or any string) to HTML attribute
@@ -137,23 +115,19 @@ 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{$1}/egms;
+	utf8::decode($str); # allow wide chars
 	$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!:!/!;
-	$first . $str;
-}
+# for the t= query parameter passed to overview DB
+sub ts2str ($) { strftime('%Y%m%d%H%M%S', gmtime($_[0])) };
+
+# human-friendly format
+sub fmt_ts ($) { strftime('%Y-%m-%d %k:%M', gmtime($_[0])) }
 
 1;