Used named entities instead of numeric when encoding latin1 characters

CVS version numbers

copypage.pl: 1.17 -> 1.18

1 files changed, 21 insertions, 8 deletions

diff --git a/copypage.pl b/copypage.pl
index 1a66abe9751..d91ea335a3f 100755
--- a/copypage.pl
+++ b/copypage.pl
@@ -63,6 +63,26 @@ if (open WMLRC, "$language/.wmlrc")
 	}
 }
 
+# Table of entities used when copying to non-latin1 encodings
+@entities = (
+	' ', '¡', '¢', '£', '¤', '¥',
+	'¦', '§', '¨', '©', 'ª', '«', '¬',
+	'­', '®', '¯', '°', '±', '²', '³',
+	'´', 'µ', '¶', '·', '¸', '¹',
+	'º', '»', '¼', '½', '¾', '¿',
+	'À', 'Á', 'Â', 'Ã', 'Ä', 'Å',
+	'Æ', 'Ç', 'È', 'É', 'Ê', 'Ë',
+	'Ì', 'Í', 'Î', 'Ï', 'Ð', 'Ñ',
+	'Ò', 'Ó', 'Ô', 'Õ', 'Ö', '×',
+	'Ø', 'Ù', 'Ú', 'Û', 'Ü', 'Ý',
+	'Þ', 'ß', 'à', 'á', 'â', 'ã',
+	'ä', 'å', 'æ', 'ç', 'è', 'é',
+	'ê', 'ë', 'ì', 'í', 'î', 'ï',
+	'ð', 'ñ', 'ò', 'ó', 'ô', 'õ',
+	'ö', '÷', 'ø', 'ù', 'ú', 'û',
+	'ü', 'ý', 'þ', 'ÿ'
+);
+
 # Loop over command line
 foreach $page (@ARGV)
 {
@@ -210,7 +230,7 @@ sub copy
 			if ($recodelatin1)
 			{
 				# Recode any non-ASCII characters as entities
-				s/([\xA0-\xFF])/&entity($1)/ge;
+				s/([\xA0-\xFF])/$entities[ord($1)-160]/ge;
 			}
 
 			print DST $_;
@@ -230,10 +250,3 @@ sub copy
 	print "and to remove $dsttitle when finished\n"
 		if defined $dsttitle;
 }
-
-# Subroutine to encode a latin-1 character as a HTML entity
-sub entity
-{
-	# Exploiting the fact that latin-1 is a subset of Unicode
-	return '&#' . ord(shift) . ';'
-}