From c6ccc0b780d8885ac7e1a5249f50dfcb5a49e9c4 Mon Sep 17 00:00:00 2001
From: Nicolas Boisselier <nicolas.boisselier@gmail.com>
Date: Thu, 9 Nov 2023 11:25:56 +0100
Subject: [PATCH] html_escape

---
 lib/perl/NB/Functions.pm | 45 +++++++++++++++++++++++++---------------
 1 file changed, 28 insertions(+), 17 deletions(-)

diff --git a/lib/perl/NB/Functions.pm b/lib/perl/NB/Functions.pm
index 488294b6..5289c20f 100644
--- a/lib/perl/NB/Functions.pm
+++ b/lib/perl/NB/Functions.pm
@@ -193,6 +193,7 @@ our %CHAR_ENTITIES = (
 	&html_fix_entities
 	&html_unescape_fix_err
 	&html_unescape
+	&html_escape
 	&encoding_is_utf8
 	&encoding_is_latin
 	&del_accent
@@ -652,44 +653,54 @@ return $str;
 
 }
 
-#die &html_unescape("einbauf&#228hig | Zaza &#233; &eacute; | Nike Chaussure Air Jordan Phat&amp;#1601 pour Fille") if $ARGV[0] eq 'zaza';
+sub html_escape {
+#------------------------------------------------------------------------------
+# NB 09.11.23: Do what is says  
+#------------------------------------------------------------------------------
+	my $str = shift @_;
+	my $encode = shift @_; $encode ||= "utf8";
+
+	require CGI unless $INC{'CGI.pm'};
+	if (&encoding_is_latin($encode)) {
+		$str =~ s/(&#\w+;)/&CGI::escapeHTML("$1")/ge;
+	} else {
+		$str =~ s/(&#\w+;)/&CGI::escapeHTML(&Encode::encode($encode,"$1"))/ge;
+	}
+
+	foreach my $char (sort {length($a) <=> length($b)} keys %CHAR_ENTITIES) {
+		my $ent = $CHAR_ENTITIES{$char};
+
+		$str =~ s/\Q$char\E/$ent/g;
+	}
+
+	return $str;
+
+}
+
 sub html_unescape {
 #------------------------------------------------------------------------------
 # NB 22.03.07 
 # Replace html entities with proper char
 #------------------------------------------------------------------------------
-my $str = shift @_;
-my $encode = shift @_; $encode ||= "utf8";
+	my $str = shift @_;
+	my $encode = shift @_; $encode ||= "utf8";
 
 	$str =~ s/&amp;(#?[^;]+;)/&$1/g;
 
-#require HTML::Entities unless $INC{'HTML/Entities.pm'};
-#require Text::Unidecode unless $INC{'Text/Unidecode.pm'};
-#return &Text::Unidecode::unidecode(&HTML::Entitie::decode_entities($str));
-
-# use Data::Dumper; print Dumper(\%CHAR_ENTITIES)."\n";
 	foreach my $char (keys %CHAR_ENTITIES) {
 		my $ent = $CHAR_ENTITIES{$char};
 
-		#$char = &Encode::encode($encode,$char) if !&encoding_is_utf8($encode);
-		#&Encode::from_to($char,"utf8",$encode) if !&encoding_is_utf8($encode);
-		#$str =~ s/$ent/$char/g;
-
-		#$char = &Encode::decode('utf8',$char);
 		$str =~ s/\Q$ent\E/$char/g;
 	}
-	#return $str;
 
 	require CGI unless $INC{'CGI.pm'};
 	if (&encoding_is_latin($encode)) {
 		$str =~ s/(&#\w+;)/&CGI::unescapeHTML("$1")/ge;
-# NB 25.06.12		$str =~ s/(&\w+;)/&CGI::unescapeHTML("$1")/ge;
 	} else {
 		$str =~ s/(&#\w+;)/&Encode::encode($encode,&CGI::unescapeHTML("$1"))/ge;
-# NB 25.06.12		$str =~ s/(&\w+;)/&Encode::encode($encode,&CGI::unescapeHTML("$1"))/ge;
 	}
 
-return $str;
+	return $str;
 
 }
 
-- 
2.47.3