Upgrade Encode from 2.39 to 2.40

15 files changed, 211 insertions, 35 deletions

diff --git a/MANIFEST b/MANIFEST
index c19638e6b5..c7e9e91616 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -741,6 +741,7 @@ cpan/Encode/t/piconv.t			Test for piconv.t
 cpan/Encode/t/rt.pl			test script
 cpan/Encode/t/unibench.pl		benchmark script
 cpan/Encode/t/Unicode.t			test script
+cpan/Encode/t/utf8ref.t			test script
 cpan/Encode/t/utf8strict.t		test script
 cpan/Encode/TW/Makefile.PL		Encode extension
 cpan/Encode/TW/TW.pm			Encode extension
diff --git a/Porting/Maintainers.pl b/Porting/Maintainers.pl
index 460f845c6c..9ba90e6c77 100755
--- a/Porting/Maintainers.pl
+++ b/Porting/Maintainers.pl
@@ -493,7 +493,7 @@ use File::Glob qw(:case);
     'Encode' =>
 	{
 	'MAINTAINER'	=> 'dankogai',
-	'DISTRIBUTION'	=> 'DANKOGAI/Encode-2.39.tar.gz',
+	'DISTRIBUTION'	=> 'DANKOGAI/Encode-2.40.tar.gz',
 	'FILES'		=> q[cpan/Encode],
 	'UPSTREAM'	=> undef,
 	},
diff --git a/cpan/Encode/Changes b/cpan/Encode/Changes
index 37868a0e3a..9eba2ed060 100644
--- a/cpan/Encode/Changes
+++ b/cpan/Encode/Changes
@@ -1,6 +1,36 @@
 # Revision history for Perl extension Encode.
 #
-# $Id: Changes,v 2.39 2009/11/26 09:23:59 dankogai Exp dankogai $
+# $Id: Changes,v 2.40 2010/09/18 18:39:51 dankogai Exp dankogai $
+#
+$Revision: 2.40 $ $Date: 2010/09/18 18:39:51 $
+! Encode.pm Encode.xs
++ t/utf8ref.t
+  Addressed: RT#59981: find_encoding("UTF-8")->encode crashes
+    decode_utf8() is now a little faster, too.
+  http://rt.cpan.org/Ticket/Display.html?id=59981
+  http://rt.cpan.org/Ticket/Display.html?id=58541
+! lib/Encode/Unicode/UTF7.pm
+  Addressed: RT#56443 utf-8 flag is not turned off after calling
+    Encode::encode('UTF-7', $string) to encode an ascii string
+  http://rt.cpan.org/Ticket/Display.html?id=56443
+! t/utf8strict.t
+  Addressed: RT#57799
+  http://rt.cpan.org/Ticket/Display.html?id=57799
+! lib/Encode/Guess.pm
+  Addressed: RT#46080: guess_encoding documentation
+  http://rt.cpan.org/Ticket/Display.html?id=46080
+! ucm/nextstep.ucm
+  Addressed: RT#59668: nextstep encoding is broken - missing ASCII characters
+  http://rt.cpan.org/Ticket/Display.html?id=59668
+! lib/Encode/MIME/Header.pm t/mime-header.t
+  Addressed: RT#52103: Encode::MIME::Header encoded words not separated by
+    white space
+  http://rt.cpan.org/Ticket/Display.html?id=52103
+! t/guess.t lib/Encode/Guess.pm
+  Addressed: Encode: silenced a warning by from_to(..., 'Guess', ...)
+  http://coderepos.org/share/changeset/37731
+
+2.39 2009/11/26 09:23:59
 ! Encode.xs t/fallback.t
   $utf8 = decode('utf8', $malformed, sub{ ... }) # now works!
   http://rt.cpan.org/Ticket/Display.html?id=51204
@@ -8,7 +38,7 @@
   $ENV{'PERL_CORE'} tricks removed since they are no longer necessary.
   Message-Id: <20091116161513.GA25556@bestpractical.com>
 
-$Revision: 2.39 $ $Date: 2009/11/26 09:23:59 $
+2.38 2009/11/16 14:08:13
 ! Encode.xs
   Addressed: Encode memory corruption [perl #70528]
   Message-Id: <alpine.LFD.2.00.0911152328070.9483@ein.m-l.org>
diff --git a/cpan/Encode/Encode.pm b/cpan/Encode/Encode.pm
index f1dff7820c..4e8cd3c7e5 100644
--- a/cpan/Encode/Encode.pm
+++ b/cpan/Encode/Encode.pm
@@ -1,10 +1,10 @@
 #
-# $Id: Encode.pm,v 2.39 2009/11/26 09:23:48 dankogai Exp $
+# $Id: Encode.pm,v 2.40 2010/09/18 18:39:51 dankogai Exp dankogai $
 #
 package Encode;
 use strict;
 use warnings;
-our $VERSION = sprintf "%d.%02d", q$Revision: 2.39 $ =~ /(\d+)/g;
+our $VERSION = sprintf "%d.%02d", q$Revision: 2.40 $ =~ /(\d+)/g;
 sub DEBUG () { 0 }
 use XSLoader ();
 XSLoader::load( __PACKAGE__, $VERSION );
@@ -203,18 +203,32 @@ sub encode_utf8($) {
     return $str;
 }
 
+my $utf8enc;
+
 sub decode_utf8($;$) {
-    my ( $str, $check ) = @_;
-    return $str if is_utf8($str);
-    if ($check) {
-        return decode( "utf8", $str, $check );
-    }
-    else {
-        return decode( "utf8", $str );
-        return $str;
-    }
+    my ( $octets, $check ) = @_;
+    return $octets if is_utf8($octets);
+    return undef unless defined $octets;
+    $octets .= '' if ref $octets;
+    $check   ||= 0;
+    $utf8enc ||= find_encoding('utf8');
+    my $string = $utf8enc->decode( $octets, $check );
+    $_[0] = $octets if $check and !ref $check and !( $check & LEAVE_SRC() );
+    return $string;
 }
 
+# sub decode_utf8($;$) {
+#     my ( $str, $check ) = @_;
+#     return $str if is_utf8($str);
+#     if ($check) {
+#         return decode( "utf8", $str, $check );
+#     }
+#     else {
+#         return decode( "utf8", $str );
+#         return $str;
+#     }
+# }
+
 predefine_encodings(1);
 
 #
diff --git a/cpan/Encode/Encode.xs b/cpan/Encode/Encode.xs
index b2e912785f..d014d318e2 100644
--- a/cpan/Encode/Encode.xs
+++ b/cpan/Encode/Encode.xs
@@ -1,5 +1,5 @@
 /*
- $Id: Encode.xs,v 2.18 2009/11/26 09:23:59 dankogai Exp dankogai $
+ $Id: Encode.xs,v 2.19 2010/09/18 18:39:51 dankogai Exp dankogai $
  */
 
 #define PERL_NO_GET_CONTEXT
@@ -432,7 +432,7 @@ PREINIT:
 CODE:
 {
     dSP; ENTER; SAVETMPS;
-    if (src == &PL_sv_undef) src = newSV(0);
+    if (src == &PL_sv_undef || SvROK(src)) src = sv_2mortal(newSV(0));
     s = (U8 *) SvPV(src, slen);
     e = (U8 *) SvEND(src);
     dst = newSV(slen>0?slen:1); /* newSV() abhors 0 -- inaba */
@@ -496,7 +496,7 @@ PREINIT:
 CODE:
 {
     check = SvROK(check_sv) ? ENCODE_PERLQQ|ENCODE_LEAVE_SRC : SvIV(check_sv);
-    if (src == &PL_sv_undef) src = newSV(0);
+    if (src == &PL_sv_undef || SvROK(src)) src = sv_2mortal(newSV(0));
     s = (U8 *) SvPV(src, slen);
     e = (U8 *) SvEND(src);
     dst = newSV(slen>0?slen:1); /* newSV() abhors 0 -- inaba */
diff --git a/cpan/Encode/MANIFEST b/cpan/Encode/MANIFEST
index 48fa14353c..3fe6582a22 100644
--- a/cpan/Encode/MANIFEST
+++ b/cpan/Encode/MANIFEST
@@ -97,6 +97,7 @@ t/perlio.t	test script
 t/piconv.t	test script
 t/rt.pl		even more test script
 t/unibench.pl	benchmark script
+t/utf8ref.t	test script
 t/utf8strict.t	test script
 ucm/8859-1.ucm	Unicode Character Map
 ucm/8859-10.ucm	Unicode Character Map
diff --git a/cpan/Encode/META.yml b/cpan/Encode/META.yml
index 2a5c1ab762..b1757ab22a 100644
--- a/cpan/Encode/META.yml
+++ b/cpan/Encode/META.yml
@@ -1,6 +1,6 @@
 --- #YAML:1.0
 name:               Encode
-version:            2.39
+version:            2.40
 abstract:           ~
 author:  []
 license:            unknown
@@ -14,7 +14,7 @@ no_index:
     directory:
         - t
         - inc
-generated_by:       ExtUtils::MakeMaker version 6.55_02
+generated_by:       ExtUtils::MakeMaker version 6.56
 meta-spec:
     url:      http://module-build.sourceforge.net/META-spec-v1.4.html
     version:  1.4
diff --git a/cpan/Encode/lib/Encode/Guess.pm b/cpan/Encode/lib/Encode/Guess.pm
index 1ad7147e7f..9636a8ad8a 100644
--- a/cpan/Encode/lib/Encode/Guess.pm
+++ b/cpan/Encode/lib/Encode/Guess.pm
@@ -2,7 +2,7 @@ package Encode::Guess;
 use strict;
 use warnings;
 use Encode qw(:fallbacks find_encoding);
-our $VERSION = do { my @r = ( q$Revision: 2.3 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
+our $VERSION = do { my @r = ( q$Revision: 2.4 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
 
 my $Canon = 'Guess';
 sub DEBUG () { 0 }
@@ -53,7 +53,7 @@ sub decode($$;$) {
         require Carp;
         Carp::croak($guessed);
     }
-    my $utf8 = $guessed->decode( $octet, $chk );
+    my $utf8 = $guessed->decode( $octet, $chk || 0 );
     $_[1] = $octet if $chk;
     return $utf8;
 }
@@ -279,7 +279,7 @@ the internal suspects list.
   my $decoder = guess_encoding($data, qw/euc-jp euc-kr euc-cn/);
   die $decoder unless ref($decoder);
   my $utf8 = $decoder->decode($data);
-  # check only ascii and utf8
+  # check only ascii, utf8 and UTF-(16|32) with BOM
   my $decoder = guess_encoding($data);
 
 =back
diff --git a/cpan/Encode/lib/Encode/MIME/Header.pm b/cpan/Encode/lib/Encode/MIME/Header.pm
index 9728dc32d8..5f209b2bd5 100644
--- a/cpan/Encode/lib/Encode/MIME/Header.pm
+++ b/cpan/Encode/lib/Encode/MIME/Header.pm
@@ -3,7 +3,7 @@ use strict;
 use warnings;
 no warnings 'redefine';
 
-our $VERSION = do { my @r = ( q$Revision: 2.11 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
+our $VERSION = do { my @r = ( q$Revision: 2.12 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
 use Encode qw(find_encoding encode_utf8 decode_utf8);
 use MIME::Base64;
 use Carp;
@@ -127,11 +127,12 @@ sub encode($$;$) {
         for my $word (@word) {
             use bytes ();
             if ( bytes::length($subline) + bytes::length($word) >
-                $obj->{bpl} )
+                $obj->{bpl} - 1 )
             {
                 push @subline, $subline;
                 $subline = '';
             }
+            $subline .= ' ' if ($subline =~ /\?=$/ and $word =~ /^=\?/);
             $subline .= $word;
         }
         $subline and push @subline, $subline;
diff --git a/cpan/Encode/lib/Encode/Unicode/UTF7.pm b/cpan/Encode/lib/Encode/Unicode/UTF7.pm
index 6ee4619585..151917cc56 100644
--- a/cpan/Encode/lib/Encode/Unicode/UTF7.pm
+++ b/cpan/Encode/lib/Encode/Unicode/UTF7.pm
@@ -1,5 +1,5 @@
 #
-# $Id: UTF7.pm,v 2.4 2006/06/03 20:28:48 dankogai Exp $
+# $Id: UTF7.pm,v 2.5 2010/09/18 18:39:51 dankogai Exp dankogai $
 #
 package Encode::Unicode::UTF7;
 use strict;
@@ -7,7 +7,7 @@ use warnings;
 no warnings 'redefine';
 use base qw(Encode::Encoding);
 __PACKAGE__->Define('UTF-7');
-our $VERSION = do { my @r = ( q$Revision: 2.4 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
+our $VERSION = do { my @r = ( q$Revision: 2.5 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
 use MIME::Base64;
 use Encode;
 
@@ -35,7 +35,9 @@ sub encode($$;$) {
     my $bytes = '';
     while ( pos($str) < $len ) {
         if ( $str =~ /\G($re_asis+)/ogc ) {
-            $bytes .= $1;
+	    my $octets = $1;
+	    utf8::downgrade($octets);
+	    $bytes .= $octets;
         }
         elsif ( $str =~ /\G($re_encoded+)/ogsc ) {
             if ( $1 eq "+" ) {
diff --git a/cpan/Encode/t/guess.t b/cpan/Encode/t/guess.t
index 37ddd5a0b1..81ab91b562 100644
--- a/cpan/Encode/t/guess.t
+++ b/cpan/Encode/t/guess.t
@@ -17,7 +17,7 @@ use File::Spec;
 use Encode qw(decode encode find_encoding _utf8_off);
 
 #use Test::More qw(no_plan);
-use Test::More tests => 30;
+use Test::More tests => 32;
 use_ok("Encode::Guess");
 {
     no warnings;
@@ -63,6 +63,16 @@ is (decode('Guess', encode('euc-jp', $utf8on)), $utf8on, "decode('Guess')");
 eval{ encode('Guess', $utf8on) };
 like($@, qr/not defined/io, "no encode()");
 
+{
+    my $warning;
+    local $SIG{__WARN__} = sub { $warning = shift };
+    my $euc_jp = my $euc_jp_clone = encode('euc-jp', $utf8on);
+    Encode::from_to($euc_jp, 'Guess', 'euc-jp');
+    is $euc_jp_clone, $euc_jp, "from_to(..., 'Guess')";
+    ok !$warning, "no warning";
+    diag $warning if $warning;
+}
+
 my %CJKT = 
     (
      'euc-cn'    => File::Spec->catfile(dirname(__FILE__), 'gb2312.utf'),
diff --git a/cpan/Encode/t/mime-header.t b/cpan/Encode/t/mime-header.t
index 47d77ca56c..246eb46647 100644
--- a/cpan/Encode/t/mime-header.t
+++ b/cpan/Encode/t/mime-header.t
@@ -1,5 +1,5 @@
 #
-# $Id: mime-header.t,v 2.4 2009/01/21 22:55:07 dankogai Exp $
+# $Id: mime-header.t,v 2.5 2010/09/18 18:39:51 dankogai Exp dankogai $
 # This script is written in utf8
 #
 BEGIN {
@@ -74,8 +74,8 @@ EOS
 
 my $bheader =<<'EOS';
 From:=?UTF-8?B?IOWwj+mjvCDlvL4g?=<dankogai@dan.co.jp>
-To: dankogai@dan.co.jp (=?UTF-8?B?5bCP6aO8?==Kogai,=?UTF-8?B?IOW8vg==?==Dan
- )
+To: dankogai@dan.co.jp (=?UTF-8?B?5bCP6aO8?==Kogai,=?UTF-8?B?IOW8vg==?==
+ Dan)
 Subject:
  =?UTF-8?B?IOa8ouWtl+OAgeOCq+OCv+OCq+ODiuOAgeOBsuOCieOBjOOBquOCkuWQq+OCgA==?=
  =?UTF-8?B?44CB6Z2e5bi444Gr6ZW344GE44K/44Kk44OI44Or6KGM44GM5LiA5L2T5YWo?=
@@ -123,6 +123,6 @@ is(Encode::encode('MIME-Q', "\x{fc}"), '=?UTF-8?Q?=C3=BC?=', 'Encode latin1 char
 
 my $rt42627 = Encode::decode_utf8("\x{c2}\x{a3}xxxxxxxxxxxxxxxxxxx0");
 is(Encode::encode('MIME-Q', $rt42627), 
-   '=?UTF-8?Q?=C2=A3xxxxxxxxxxxxxxxxxxx?==?UTF-8?Q?0?=',
+   '=?UTF-8?Q?=C2=A3xxxxxxxxxxxxxxxxxxx?= =?UTF-8?Q?0?=',
    'MIME-Q encoding does not truncate trailing zeros');
 __END__;
diff --git a/cpan/Encode/t/utf8ref.t b/cpan/Encode/t/utf8ref.t
new file mode 100644
index 0000000000..57cfcbcc96
--- /dev/null
+++ b/cpan/Encode/t/utf8ref.t
@@ -0,0 +1,20 @@
+#
+# $Id: utf8ref.t,v 1.1 2010/09/18 18:39:51 dankogai Exp dankogai $
+#
+
+use strict;
+use warnings;
+use Encode;
+use Test::More;
+plan tests => 4;
+#plan 'no_plan';
+
+# my $a = find_encoding('ASCII');
+my $u = find_encoding('UTF-8');
+my $r = [];
+no warnings 'uninitialized';
+is encode_utf8($r), ''.$r;
+is $u->encode($r), '';
+$r = {};
+is decode_utf8($r), ''.$r;
+is $u->decode($r), '';
diff --git a/cpan/Encode/t/utf8strict.t b/cpan/Encode/t/utf8strict.t
index 37e771340f..3f362f4981 100644
--- a/cpan/Encode/t/utf8strict.t
+++ b/cpan/Encode/t/utf8strict.t
@@ -16,6 +16,7 @@ BEGIN {
      exit 0;
      }
      # http://smontagu.damowmow.com/utf8test.html
+     # The numbers below, like 2.1.2 are test numbers on this web page
      %ORD = (
          0x00000080 => 0, # 2.1.2
          0x00000800 => 0, # 2.1.3
@@ -44,7 +45,7 @@ BEGIN {
 	 %SEQ = (
 		 qq/dd 64 73 73/    => 0, # 2.3.1
 		 qq/dd 67 41 41/    => 0, # 2.3.2
-		 qq/ee 42 73 73 73/ => 0, # 2.3.3
+		 qq/ee 42 73 73 71/ => 0, # 2.3.3
 		 qq/f4 90 80 80/ => 1, # 2.3.4 -- out of range so NG
 		 # "3 Malformed sequences" are checked by perl.
 		 # "4 Overlong sequences"  are checked by perl.
@@ -53,7 +54,7 @@ BEGIN {
 	 %SEQ = (
 		 qq/ed 9f bf/    => 0, # 2.3.1
 		 qq/ee 80 80/    => 0, # 2.3.2
-		 qq/f4 8f bf bf/ => 0, # 2.3.3
+		 qq/f4 8f bf bd/ => 0, # 2.3.3
 		 qq/f4 90 80 80/ => 1, # 2.3.4 -- out of range so NG
 		 # "3 Malformed sequences" are checked by perl.
 		 # "4 Overlong sequences"  are checked by perl.
diff --git a/cpan/Encode/ucm/nextstep.ucm b/cpan/Encode/ucm/nextstep.ucm
index b5d3d462ff..2ec37ad296 100644
--- a/cpan/Encode/ucm/nextstep.ucm
+++ b/cpan/Encode/ucm/nextstep.ucm
@@ -1,5 +1,5 @@
 #
-# $Id: nextstep.ucm,v 2.0 2004/05/16 20:55:28 dankogai Exp $
+# $Id: nextstep.ucm,v 2.1 2010/09/18 18:39:51 dankogai Exp dankogai $
 #
 # Original table can be obtained at
 # http://www.unicode.org/Public/MAPPINGS/VENDORS/NEXT/NEXTSTEP.TXT
@@ -41,6 +41,102 @@ CHARMAP
 <U001D> \x1D |0 # <control>
 <U001E> \x1E |0 # <control>
 <U001F> \x1F |0 # <control>
+<U0020> \x20 |0 # SPACE
+<U0021> \x21 |0 # EXCLAMATION MARK
+<U0022> \x22 |0 # QUOTATION MARK
+<U0023> \x23 |0 # NUMBER SIGN
+<U0024> \x24 |0 # DOLLAR SIGN
+<U0025> \x25 |0 # PERCENT SIGN
+<U0026> \x26 |0 # AMPERSAND
+<U0027> \x27 |0 # APOSTROPHE
+<U0028> \x28 |0 # LEFT PARENTHESIS
+<U0029> \x29 |0 # RIGHT PARENTHESIS
+<U002A> \x2A |0 # ASTERISK
+<U002B> \x2B |0 # PLUS SIGN
+<U002C> \x2C |0 # COMMA
+<U002D> \x2D |0 # HYPHEN-MINUS
+<U002E> \x2E |0 # FULL STOP
+<U002F> \x2F |0 # SOLIDUS
+<U0030> \x30 |0 # DIGIT ZERO
+<U0031> \x31 |0 # DIGIT ONE
+<U0032> \x32 |0 # DIGIT TWO
+<U0033> \x33 |0 # DIGIT THREE
+<U0034> \x34 |0 # DIGIT FOUR
+<U0035> \x35 |0 # DIGIT FIVE
+<U0036> \x36 |0 # DIGIT SIX
+<U0037> \x37 |0 # DIGIT SEVEN
+<U0038> \x38 |0 # DIGIT EIGHT
+<U0039> \x39 |0 # DIGIT NINE
+<U003A> \x3A |0 # COLON
+<U003B> \x3B |0 # SEMICOLON
+<U003C> \x3C |0 # LESS-THAN SIGN
+<U003D> \x3D |0 # EQUALS SIGN
+<U003E> \x3E |0 # GREATER-THAN SIGN
+<U003F> \x3F |0 # QUESTION MARK
+<U0040> \x40 |0 # COMMERCIAL AT
+<U0041> \x41 |0 # LATIN CAPITAL LETTER A
+<U0042> \x42 |0 # LATIN CAPITAL LETTER B
+<U0043> \x43 |0 # LATIN CAPITAL LETTER C
+<U0044> \x44 |0 # LATIN CAPITAL LETTER D
+<U0045> \x45 |0 # LATIN CAPITAL LETTER E
+<U0046> \x46 |0 # LATIN CAPITAL LETTER F
+<U0047> \x47 |0 # LATIN CAPITAL LETTER G
+<U0048> \x48 |0 # LATIN CAPITAL LETTER H
+<U0049> \x49 |0 # LATIN CAPITAL LETTER I
+<U004A> \x4A |0 # LATIN CAPITAL LETTER J
+<U004B> \x4B |0 # LATIN CAPITAL LETTER K
+<U004C> \x4C |0 # LATIN CAPITAL LETTER L
+<U004D> \x4D |0 # LATIN CAPITAL LETTER M
+<U004E> \x4E |0 # LATIN CAPITAL LETTER N
+<U004F> \x4F |0 # LATIN CAPITAL LETTER O
+<U0050> \x50 |0 # LATIN CAPITAL LETTER P
+<U0051> \x51 |0 # LATIN CAPITAL LETTER Q
+<U0052> \x52 |0 # LATIN CAPITAL LETTER R
+<U0053> \x53 |0 # LATIN CAPITAL LETTER S
+<U0054> \x54 |0 # LATIN CAPITAL LETTER T
+<U0055> \x55 |0 # LATIN CAPITAL LETTER U
+<U0056> \x56 |0 # LATIN CAPITAL LETTER V
+<U0057> \x57 |0 # LATIN CAPITAL LETTER W
+<U0058> \x58 |0 # LATIN CAPITAL LETTER X
+<U0059> \x59 |0 # LATIN CAPITAL LETTER Y
+<U005A> \x5A |0 # LATIN CAPITAL LETTER Z
+<U005B> \x5B |0 # LEFT SQUARE BRACKET
+<U005C> \x5C |0 # REVERSE SOLIDUS
+<U005D> \x5D |0 # RIGHT SQUARE BRACKET
+<U005E> \x5E |0 # CIRCUMFLEX ACCENT
+<U005F> \x5F |0 # LOW LINE
+<U0060> \x60 |0 # GRAVE ACCENT
+<U0061> \x61 |0 # LATIN SMALL LETTER A
+<U0062> \x62 |0 # LATIN SMALL LETTER B
+<U0063> \x63 |0 # LATIN SMALL LETTER C
+<U0064> \x64 |0 # LATIN SMALL LETTER D
+<U0065> \x65 |0 # LATIN SMALL LETTER E
+<U0066> \x66 |0 # LATIN SMALL LETTER F
+<U0067> \x67 |0 # LATIN SMALL LETTER G
+<U0068> \x68 |0 # LATIN SMALL LETTER H
+<U0069> \x69 |0 # LATIN SMALL LETTER I
+<U006A> \x6A |0 # LATIN SMALL LETTER J
+<U006B> \x6B |0 # LATIN SMALL LETTER K
+<U006C> \x6C |0 # LATIN SMALL LETTER L
+<U006D> \x6D |0 # LATIN SMALL LETTER M
+<U006E> \x6E |0 # LATIN SMALL LETTER N
+<U006F> \x6F |0 # LATIN SMALL LETTER O
+<U0070> \x70 |0 # LATIN SMALL LETTER P
+<U0071> \x71 |0 # LATIN SMALL LETTER Q
+<U0072> \x72 |0 # LATIN SMALL LETTER R
+<U0073> \x73 |0 # LATIN SMALL LETTER S
+<U0074> \x74 |0 # LATIN SMALL LETTER T
+<U0075> \x75 |0 # LATIN SMALL LETTER U
+<U0076> \x76 |0 # LATIN SMALL LETTER V
+<U0077> \x77 |0 # LATIN SMALL LETTER W
+<U0078> \x78 |0 # LATIN SMALL LETTER X
+<U0079> \x79 |0 # LATIN SMALL LETTER Y
+<U007A> \x7A |0 # LATIN SMALL LETTER Z
+<U007B> \x7B |0 # LEFT CURLY BRACKET
+<U007C> \x7C |0 # VERTICAL LINE
+<U007D> \x7D |0 # RIGHT CURLY BRACKET
+<U007E> \x7E |0 # TILDE
+<U007F> \x7F |0 # <control>
 <U00a0> \x80 |0 # NO-BREAK SPACE
 <U00a1> \xa1 |0 # INVERTED EXCLAMATION MARK
 <U00a2> \xa2 |0 # CENT SIGN