Re: [perl #32687] Encode::is_utf8 on tainted UTF8 string

[p5sagit/p5-mst-13.2.git] / ext / Encode / JP / JP.pm

diff --git a/ext/Encode/JP/JP.pm b/ext/Encode/JP/JP.pm
index 931d4e3..e78e54d 100644 (file)
--- a/ext/Encode/JP/JP.pm
+++ b/ext/Encode/JP/JP.pm
@@ -1,18 +1,18 @@
 package Encode::JP;
 BEGIN {
-    if (ord("A") == 193) {
-       die "Encode::JP not supported on EBCDIC\n";
+    if ( ord("A") == 193 ) {
+        die "Encode::JP not supported on EBCDIC\n";
     }
 }
+use strict;
+use warnings;
 use Encode;
-our $VERSION = do { my @r = (q$Revision: 1.21 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = ( q$Revision: 2.3 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
 
 use XSLoader;
-XSLoader::load('Encode::JP',$VERSION);
+XSLoader::load( __PACKAGE__, $VERSION );
 
-use Encode::JP::JIS;
-use Encode::JP::2022_JP;
-use Encode::JP::2022_JP1;
+use Encode::JP::JIS7;
 
 1;
 __END__
@@ -36,18 +36,18 @@ supported are as follows.
   --------------------------------------------------------------------
   euc-jp      /\beuc.*jp$/i    EUC (Extended Unix Character)
               /\bjp.*euc/i   
-             /\bujis$/i
+          /\bujis$/i
   shiftjis    /\bshift.*jis$/i Shift JIS (aka MS Kanji)
-             /\bsjis$/i
+          /\bsjis$/i
   7bit-jis    /\bjis$/i                7bit JIS
   iso-2022-jp                  ISO-2022-JP                  [RFC1468]
-                               = 7bit JIS with all Halfwidth Kana 
-                                 converted to Fullwidth
+                = 7bit JIS with all Halfwidth Kana 
+                  converted to Fullwidth
   iso-2022-jp-1                        ISO-2022-JP-1                [RFC2237]
                                 = ISO-2022-JP with JIS X 0212-1990
-                                 support.  See below
+                  support.  See below
   MacJapanese                  Shift JIS + Apple vendor mappings
-  cp932                         Code Page 932  
+  cp932       /\bwindows-31j$/i Code Page 932
                                 = Shift JIS + MS/IBM vendor mappings
   jis0201-raw                   JIS0201, raw format
   jis0208-raw                   JIS0201, raw format
@@ -56,7 +56,7 @@ supported are as follows.
 
 =head1 DESCRIPTION
 
-To find how to use this module in detail, see L<Encode>.
+To find out how to use this module in detail, see L<Encode>.
 
 =head1 Note on ISO-2022-JP(-1)?
 
@@ -65,9 +65,12 @@ adds support for JIS X 0212-1990.  That means you can use the same
 code to decode to utf8 but not vice versa.
 
   $utf8 = decode('iso-2022-jp-1', $stream);
+
+and
+
   $utf8 = decode('iso-2022-jp',   $stream);
 
-Yields the same result but
+yield the same result but
 
   $with_0212 = encode('iso-2022-jp-1', $utf8);
 
@@ -75,22 +78,22 @@ is now different from
 
   $without_0212 = encode('iso-2022-jp', $utf8 );
 
-In the latter case, characters that map to 0212 are at first converted
-to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu') then
-fed to decoding engine.  U+FFFD is not used to preserve text layout as
-much as possible.
+In the latter case, characters that map to 0212 are first converted
+to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu' or
+'geta mark') then fed to the decoding engine.  U+FFFD is not used,
+in order to preserve text layout as much as possible.
 
 =head1 BUGS
 
-ASCII part (0x00-0x7f) is preserved for all encodings, even though it
-conflicts with mappings by the Unicode Consortium.  See
+The ASCII region (0x00-0x7f) is preserved for all encodings, even
+though this conflicts with mappings by the Unicode Consortium.  See
 
 L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
 
-to find why it is implemented that way.
+to find out why it is implemented that way.
 
 =head1 SEE ALSO
 
-L<Encode>,L<Encode::CJKguide>
+L<Encode>
 
 =cut