Add a test for for PerlIO ":encoding(...)" layer.

[perl5.git] / ext / Encode / Encode.pm

diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm
index a274f38..b84623a 100644 (file)
--- a/ext/Encode/Encode.pm
+++ b/ext/Encode/Encode.pm
@@ -102,17 +102,14 @@ sub define_alias
 # Allow variants of iso-8859-1 etc.
 define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
 
-# This is a font issue, not an encoding issue.
-# (The currency symbol of the Latin 1 upper half is redefined
-# as the euro symbol.)
-define_alias( qr/^(.+)\@euro$/i => '"$1"' );
-
-# Solaris has this as a generic Latin-1 encoding.
-define_alias( qr/^iso_8859_1$/ => 'iso-8859-1' );
-
 # At least HP-UX has these.
 define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
 
+# This is a font issue, not an encoding issue.
+# (The currency symbol of the Latin 1 upper half
+#  has been redefined as the euro symbol.)
+define_alias( qr/^(.+)\@euro$/i => '"$1"' );
+
 # Allow latin-1 style names as well
 define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' );
 
@@ -126,9 +123,15 @@ define_alias( 'ascii'    => 'US-ascii',
 # At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
 define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"');
 
-# Standardize on the dashed version.
+# Standardize on the dashed versions.
+define_alias( qr/^utf8$/i  => 'utf-8' );
 define_alias( qr/^koi8r$/i => 'koi8-r' );
 
+# TODO: the HP-UX '8' encodings:  arabic8 greek8 hebrew8 roman8 turkish8
+# TODO: the Thai Encoding tis620
+# TODO: the Chinese Encoding gb18030
+# TODO: what is the Japanese 'ujis' encoding seen in some Linuxes?
+
 # Map white space and _ to '-'
 define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
 
@@ -736,9 +739,15 @@ If Perl is configured to use the new 'perlio' IO system then
 C<Encode> provides a "layer" (See L<perliol>) which can transform
 data as it is read or written.
 
+Here is how the blind poet would modernise the encoding:
+
     use Encode;
-    open(my $ilyad,'>:encoding(iso-8859-7)','ilyad.greek');
-    print $ilyad @epic;
+    open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek');
+    open(my $utf8,'>:utf8','iliad.utf8');
+    my @epic = <$iliad>;
+    print $utf8 @epic;
+    close($utf8);
+    close($illiad);
 
 In addition the new IO system can also be configured to read/write
 UTF-8 encoded characters (as noted above this is efficient):