From: Dan Kogai Date: Wed, 21 May 2003 18:26:26 +0000 (+0900) Subject: [Encode] 1.95 released X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=03871ea64ce22022ff5d907fffa52338dafdb782;p=p5sagit%2Fp5-mst-13.2.git [Encode] 1.95 released Message-Id: <4B8D9AB5-8B6E-11D7-848A-000393AE4244@dan.co.jp> p4raw-id: //depot/perl@19578 --- diff --git a/ext/Encode/Changes b/ext/Encode/Changes index 4edb594..ded94e1 100644 --- a/ext/Encode/Changes +++ b/ext/Encode/Changes @@ -1,8 +1,14 @@ # Revision history for Perl extension Encode. # -# $Id: Changes,v 1.94 2003/05/10 18:13:59 dankogai Exp $ +# $Id: Changes,v 1.95 2003/05/21 08:41:11 dankogai Exp $ # -$Revision: 1.94 $ $Date: 2003/05/10 18:13:59 $ +$Revision: 1.95 $ $Date: 2003/05/21 08:41:11 $ +! ucm/8859-*.ucm + Since bogus entries were found in iso-8859-6, all entries are + re-generated once again out of + http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT + Thank David Graff for the discovery + Message-Id: <200305201819.h4KIJRRU013746@unagi.cis.upenn.edu> + lib/Encode/Unicode/UTF7.pm ! lib/Encode/Config.pm lib/Encode/Alias.pm Unicode/Unicode.pm t/Unicode.t lib/Encode/Supported.pod diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index e9dead4..37b350f 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,9 +1,9 @@ # -# $Id: Encode.pm,v 1.94 2003/05/10 18:14:36 dankogai Exp $ +# $Id: Encode.pm,v 1.95 2003/05/21 08:40:59 dankogai Exp $ # package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.94 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; our $DEBUG = 0; use XSLoader (); XSLoader::load(__PACKAGE__, $VERSION); diff --git a/ext/Encode/MANIFEST b/ext/Encode/MANIFEST index 0d08c79..f219c38 100644 --- a/ext/Encode/MANIFEST +++ b/ext/Encode/MANIFEST @@ -51,7 +51,7 @@ lib/Encode/KR/2022_KR.pm Encode extension lib/Encode/MIME/Header.pm Encode extension lib/Encode/PerlIO.pod Documents for Encode & PerlIO lib/Encode/Supported.pod Documents for supported encodings -lib/Encode/Unicode/UTF7.pm Encode extension +lib/Encode/Unicode/UTF7.pm Encode Extension t/Aliases.t test script t/CJKT.t test script t/Encode.t test script diff --git a/ext/Encode/META.yml b/ext/Encode/META.yml index 113e75c..f48c93f 100644 --- a/ext/Encode/META.yml +++ b/ext/Encode/META.yml @@ -1,6 +1,6 @@ #XXXXXXX This is a prototype!!! It will change in the future!!! XXXXX# name: Encode -version: 1.94 +version: 1.95 version_from: Encode.pm installdirs: perl requires: diff --git a/ext/Encode/Unicode/Unicode.pm b/ext/Encode/Unicode/Unicode.pm index 721c9f7..1829218 100644 --- a/ext/Encode/Unicode/Unicode.pm +++ b/ext/Encode/Unicode/Unicode.pm @@ -3,7 +3,7 @@ package Encode::Unicode; use strict; use warnings; -our $VERSION = do { my @r = (q$Revision: 1.38 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.39 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; use XSLoader; XSLoader::load(__PACKAGE__,$VERSION); diff --git a/ext/Encode/lib/Encode/Alias.pm b/ext/Encode/lib/Encode/Alias.pm index b29bfd9..d684ced 100644 --- a/ext/Encode/lib/Encode/Alias.pm +++ b/ext/Encode/lib/Encode/Alias.pm @@ -2,7 +2,7 @@ package Encode::Alias; use strict; no warnings 'redefine'; use Encode; -our $VERSION = do { my @r = (q$Revision: 1.35 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.36 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; our $DEBUG = 0; use base qw(Exporter); diff --git a/ext/Encode/lib/Encode/Config.pm b/ext/Encode/lib/Encode/Config.pm index 0fe77d6..724b444 100644 --- a/ext/Encode/lib/Encode/Config.pm +++ b/ext/Encode/lib/Encode/Config.pm @@ -2,7 +2,7 @@ # Demand-load module list # package Encode::Config; -our $VERSION = do { my @r = (q$Revision: 1.6 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.7 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; use strict; diff --git a/ext/Encode/lib/Encode/Unicode/UTF7.pm b/ext/Encode/lib/Encode/Unicode/UTF7.pm index bb1a79e..7de8e41 100644 --- a/ext/Encode/lib/Encode/Unicode/UTF7.pm +++ b/ext/Encode/lib/Encode/Unicode/UTF7.pm @@ -1,12 +1,12 @@ # -# $Id: UTF7.pm,v 0.1 2003/05/16 18:06:24 dankogai Exp dankogai $ +# $Id: UTF7.pm,v 0.2 2003/05/19 04:56:03 dankogai Exp $ # package Encode::Unicode::UTF7; use strict; no warnings 'redefine'; use base qw(Encode::Encoding); __PACKAGE__->Define('UTF-7'); -our $VERSION = do { my @r = (q$Revision: 0.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 0.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; use MIME::Base64; use Encode; @@ -19,7 +19,7 @@ my $specials = quotemeta "\'(),-./:?"; $OPTIONAL_DIRECT_CHARS and $specials .= quotemeta "!\"#$%&*;<=>@[]^_`{|}"; # \s will not work because it matches U+3000 DEOGRAPHIC SPACE -# We use qr/[\n\r\t\ ] instead +# We use qr/[\n\r\t\ ] instead my $re_asis = qr/(?:[\n\r\t\ A-Za-z0-9$specials])/; my $re_encoded = qr/(?:[^\n\r\t\ A-Za-z0-9$specials])/; my $e_utf16 = find_encoding("UTF-16BE"); diff --git a/ext/Encode/t/Unicode.t b/ext/Encode/t/Unicode.t index 882d700..efb3984 100644 --- a/ext/Encode/t/Unicode.t +++ b/ext/Encode/t/Unicode.t @@ -1,5 +1,5 @@ # -# $Id: Unicode.t,v 1.9 2002/05/06 10:26:48 dankogai Exp $ +# $Id: Unicode.t,v 1.12 2003/05/21 08:41:11 dankogai Exp $ # # This script is written entirely in ASCII, even though quoted literals # do include non-BMP unicode characters -- Are you happy, jhi? @@ -119,12 +119,12 @@ for my $file (@file){ open my $fh, '<', $path or die "$path:$!"; my $content; if (PerlIO::Layer->find('perlio')){ - binmode $fh => ':utf8'; - $content = join('' => <$fh>); + binmode $fh => ':utf8'; + $content = join('' => <$fh>); }else{ # ugh! - binmode $fh; - $content = join('' => <$fh>); - Encode::_utf8_on($content) + binmode $fh; + $content = join('' => <$fh>); + Encode::_utf8_on($content) } close $fh; is(decode("UTF-7", encode("UTF-7", $content)), $content, diff --git a/ext/Encode/ucm/8859-1.ucm b/ext/Encode/ucm/8859-1.ucm index 6e1caba..080424b 100644 --- a/ext/Encode/ucm/8859-1.ucm +++ b/ext/Encode/ucm/8859-1.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-1.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-1.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT # -# ./compile -n iso-8859-1 -o Encode/iso8859-1.ucm Encode/iso8859-1.enc "iso-8859-1" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,39 +136,39 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA1 |0 # INVERTED EXCLAMATION MARK \xA2 |0 # CENT SIGN diff --git a/ext/Encode/ucm/8859-10.ucm b/ext/Encode/ucm/8859-10.ucm index dcf79fe..eb1a80c 100644 --- a/ext/Encode/ucm/8859-10.ucm +++ b/ext/Encode/ucm/8859-10.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-10.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-10.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT # -# ./compile -n iso-8859-10 -o Encode/iso8859-10.ucm Encode/iso8859-10.enc "iso-8859-10" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,133 +136,133 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK - \xA2 |0 # LATIN CAPITAL LETTER E WITH MACRON - \xA3 |0 # LATIN CAPITAL LETTER G WITH CEDILLA - \xA4 |0 # LATIN CAPITAL LETTER I WITH MACRON - \xA5 |0 # LATIN CAPITAL LETTER I WITH TILDE - \xA6 |0 # LATIN CAPITAL LETTER K WITH CEDILLA \xA7 |0 # SECTION SIGN - \xA8 |0 # LATIN CAPITAL LETTER L WITH CEDILLA - \xA9 |0 # LATIN CAPITAL LETTER D WITH STROKE - \xAA |0 # LATIN CAPITAL LETTER S WITH CARON - \xAB |0 # LATIN CAPITAL LETTER T WITH STROKE - \xAC |0 # LATIN CAPITAL LETTER Z WITH CARON \xAD |0 # SOFT HYPHEN - \xAE |0 # LATIN CAPITAL LETTER U WITH MACRON - \xAF |0 # LATIN CAPITAL LETTER ENG \xB0 |0 # DEGREE SIGN - \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK - \xB2 |0 # LATIN SMALL LETTER E WITH MACRON - \xB3 |0 # LATIN SMALL LETTER G WITH CEDILLA - \xB4 |0 # LATIN SMALL LETTER I WITH MACRON - \xB5 |0 # LATIN SMALL LETTER I WITH TILDE - \xB6 |0 # LATIN SMALL LETTER K WITH CEDILLA \xB7 |0 # MIDDLE DOT - \xB8 |0 # LATIN SMALL LETTER L WITH CEDILLA - \xB9 |0 # LATIN SMALL LETTER D WITH STROKE - \xBA |0 # LATIN SMALL LETTER S WITH CARON - \xBB |0 # LATIN SMALL LETTER T WITH STROKE - \xBC |0 # LATIN SMALL LETTER Z WITH CARON - \xBD |0 # HORIZONTAL BAR - \xBE |0 # LATIN SMALL LETTER U WITH MACRON - \xBF |0 # LATIN SMALL LETTER ENG - \xC0 |0 # LATIN CAPITAL LETTER A WITH MACRON \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX \xC3 |0 # LATIN CAPITAL LETTER A WITH TILDE \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS \xC5 |0 # LATIN CAPITAL LETTER A WITH RING ABOVE \xC6 |0 # LATIN CAPITAL LETTER AE - \xC7 |0 # LATIN CAPITAL LETTER I WITH OGONEK - \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE - \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK \xCB |0 # LATIN CAPITAL LETTER E WITH DIAERESIS - \xCC |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX \xCF |0 # LATIN CAPITAL LETTER I WITH DIAERESIS \xD0 |0 # LATIN CAPITAL LETTER ETH - \xD1 |0 # LATIN CAPITAL LETTER N WITH CEDILLA - \xD2 |0 # LATIN CAPITAL LETTER O WITH MACRON \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX \xD5 |0 # LATIN CAPITAL LETTER O WITH TILDE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS - \xD7 |0 # LATIN CAPITAL LETTER U WITH TILDE \xD8 |0 # LATIN CAPITAL LETTER O WITH STROKE - \xD9 |0 # LATIN CAPITAL LETTER U WITH OGONEK \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE \xDE |0 # LATIN CAPITAL LETTER THORN \xDF |0 # LATIN SMALL LETTER SHARP S - \xE0 |0 # LATIN SMALL LETTER A WITH MACRON \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX \xE3 |0 # LATIN SMALL LETTER A WITH TILDE \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS \xE5 |0 # LATIN SMALL LETTER A WITH RING ABOVE \xE6 |0 # LATIN SMALL LETTER AE - \xE7 |0 # LATIN SMALL LETTER I WITH OGONEK - \xE8 |0 # LATIN SMALL LETTER C WITH CARON \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE - \xEA |0 # LATIN SMALL LETTER E WITH OGONEK \xEB |0 # LATIN SMALL LETTER E WITH DIAERESIS - \xEC |0 # LATIN SMALL LETTER E WITH DOT ABOVE \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX \xEF |0 # LATIN SMALL LETTER I WITH DIAERESIS \xF0 |0 # LATIN SMALL LETTER ETH - \xF1 |0 # LATIN SMALL LETTER N WITH CEDILLA - \xF2 |0 # LATIN SMALL LETTER O WITH MACRON \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX \xF5 |0 # LATIN SMALL LETTER O WITH TILDE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS - \xF7 |0 # LATIN SMALL LETTER U WITH TILDE \xF8 |0 # LATIN SMALL LETTER O WITH STROKE - \xF9 |0 # LATIN SMALL LETTER U WITH OGONEK \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE \xFE |0 # LATIN SMALL LETTER THORN + \xC0 |0 # LATIN CAPITAL LETTER A WITH MACRON + \xE0 |0 # LATIN SMALL LETTER A WITH MACRON + \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK + \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK + \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON + \xE8 |0 # LATIN SMALL LETTER C WITH CARON + \xA9 |0 # LATIN CAPITAL LETTER D WITH STROKE + \xB9 |0 # LATIN SMALL LETTER D WITH STROKE + \xA2 |0 # LATIN CAPITAL LETTER E WITH MACRON + \xB2 |0 # LATIN SMALL LETTER E WITH MACRON + \xCC |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE + \xEC |0 # LATIN SMALL LETTER E WITH DOT ABOVE + \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK + \xEA |0 # LATIN SMALL LETTER E WITH OGONEK + \xA3 |0 # LATIN CAPITAL LETTER G WITH CEDILLA + \xB3 |0 # LATIN SMALL LETTER G WITH CEDILLA + \xA5 |0 # LATIN CAPITAL LETTER I WITH TILDE + \xB5 |0 # LATIN SMALL LETTER I WITH TILDE + \xA4 |0 # LATIN CAPITAL LETTER I WITH MACRON + \xB4 |0 # LATIN SMALL LETTER I WITH MACRON + \xC7 |0 # LATIN CAPITAL LETTER I WITH OGONEK + \xE7 |0 # LATIN SMALL LETTER I WITH OGONEK + \xA6 |0 # LATIN CAPITAL LETTER K WITH CEDILLA + \xB6 |0 # LATIN SMALL LETTER K WITH CEDILLA \xFF |0 # LATIN SMALL LETTER KRA + \xA8 |0 # LATIN CAPITAL LETTER L WITH CEDILLA + \xB8 |0 # LATIN SMALL LETTER L WITH CEDILLA + \xD1 |0 # LATIN CAPITAL LETTER N WITH CEDILLA + \xF1 |0 # LATIN SMALL LETTER N WITH CEDILLA + \xAF |0 # LATIN CAPITAL LETTER ENG + \xBF |0 # LATIN SMALL LETTER ENG + \xD2 |0 # LATIN CAPITAL LETTER O WITH MACRON + \xF2 |0 # LATIN SMALL LETTER O WITH MACRON + \xAA |0 # LATIN CAPITAL LETTER S WITH CARON + \xBA |0 # LATIN SMALL LETTER S WITH CARON + \xAB |0 # LATIN CAPITAL LETTER T WITH STROKE + \xBB |0 # LATIN SMALL LETTER T WITH STROKE + \xD7 |0 # LATIN CAPITAL LETTER U WITH TILDE + \xF7 |0 # LATIN SMALL LETTER U WITH TILDE + \xAE |0 # LATIN CAPITAL LETTER U WITH MACRON + \xBE |0 # LATIN SMALL LETTER U WITH MACRON + \xD9 |0 # LATIN CAPITAL LETTER U WITH OGONEK + \xF9 |0 # LATIN SMALL LETTER U WITH OGONEK + \xAC |0 # LATIN CAPITAL LETTER Z WITH CARON + \xBC |0 # LATIN SMALL LETTER Z WITH CARON + \xBD |0 # HORIZONTAL BAR END CHARMAP diff --git a/ext/Encode/ucm/8859-11.ucm b/ext/Encode/ucm/8859-11.ucm index 5047598..29bd1cd 100644 --- a/ext/Encode/ucm/8859-11.ucm +++ b/ext/Encode/ucm/8859-11.ucm @@ -1,46 +1,46 @@ # -# $Id: 8859-11.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-11.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT # -# Written $Id: 8859-11.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ -# ./compile -n iso-8859-11 -o Encode/iso8859-11.ucm Encode/iso8859-11.enc "iso-8859-11" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -136,39 +136,39 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA1 |0 # THAI CHARACTER KO KAI \xA2 |0 # THAI CHARACTER KHO KHAI @@ -228,10 +228,6 @@ CHARMAP \xD8 |0 # THAI CHARACTER SARA U \xD9 |0 # THAI CHARACTER SARA UU \xDA |0 # THAI CHARACTER PHINTHU - \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE - \xDE |0 # LATIN CAPITAL LETTER THORN \xDF |0 # THAI CURRENCY SYMBOL BAHT \xE0 |0 # THAI CHARACTER SARA E \xE1 |0 # THAI CHARACTER SARA AE @@ -261,8 +257,4 @@ CHARMAP \xF9 |0 # THAI DIGIT NINE \xFA |0 # THAI CHARACTER ANGKHANKHU \xFB |0 # THAI CHARACTER KHOMUT - \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS - \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE - \xFE |0 # LATIN SMALL LETTER THORN - \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS END CHARMAP diff --git a/ext/Encode/ucm/8859-13.ucm b/ext/Encode/ucm/8859-13.ucm index f3a5eb4..ee48e6c 100644 --- a/ext/Encode/ucm/8859-13.ucm +++ b/ext/Encode/ucm/8859-13.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-13.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-13.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT # -# ./compile -n iso-8859-13 -o Encode/iso8859-13.ucm Encode/iso8859-13.enc "iso-8859-13" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,133 +136,133 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # RIGHT DOUBLE QUOTATION MARK \xA2 |0 # CENT SIGN \xA3 |0 # POUND SIGN \xA4 |0 # CURRENCY SIGN - \xA5 |0 # DOUBLE LOW-9 QUOTATION MARK \xA6 |0 # BROKEN BAR \xA7 |0 # SECTION SIGN - \xA8 |0 # LATIN CAPITAL LETTER O WITH STROKE \xA9 |0 # COPYRIGHT SIGN - \xAA |0 # LATIN CAPITAL LETTER R WITH CEDILLA \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK \xAC |0 # NOT SIGN \xAD |0 # SOFT HYPHEN \xAE |0 # REGISTERED SIGN - \xAF |0 # LATIN CAPITAL LETTER AE \xB0 |0 # DEGREE SIGN \xB1 |0 # PLUS-MINUS SIGN \xB2 |0 # SUPERSCRIPT TWO \xB3 |0 # SUPERSCRIPT THREE - \xB4 |0 # LEFT DOUBLE QUOTATION MARK \xB5 |0 # MICRO SIGN \xB6 |0 # PILCROW SIGN \xB7 |0 # MIDDLE DOT - \xB8 |0 # LATIN SMALL LETTER O WITH STROKE \xB9 |0 # SUPERSCRIPT ONE - \xBA |0 # LATIN SMALL LETTER R WITH CEDILLA \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK \xBC |0 # VULGAR FRACTION ONE QUARTER \xBD |0 # VULGAR FRACTION ONE HALF \xBE |0 # VULGAR FRACTION THREE QUARTERS - \xBF |0 # LATIN SMALL LETTER AE - \xC0 |0 # LATIN CAPITAL LETTER A WITH OGONEK - \xC1 |0 # LATIN CAPITAL LETTER I WITH OGONEK - \xC2 |0 # LATIN CAPITAL LETTER A WITH MACRON - \xC3 |0 # LATIN CAPITAL LETTER C WITH ACUTE \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS \xC5 |0 # LATIN CAPITAL LETTER A WITH RING ABOVE - \xC6 |0 # LATIN CAPITAL LETTER E WITH OGONEK - \xC7 |0 # LATIN CAPITAL LETTER E WITH MACRON - \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON + \xAF |0 # LATIN CAPITAL LETTER AE \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE - \xCA |0 # LATIN CAPITAL LETTER Z WITH ACUTE - \xCB |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE - \xCC |0 # LATIN CAPITAL LETTER G WITH CEDILLA - \xCD |0 # LATIN CAPITAL LETTER K WITH CEDILLA - \xCE |0 # LATIN CAPITAL LETTER I WITH MACRON - \xCF |0 # LATIN CAPITAL LETTER L WITH CEDILLA - \xD0 |0 # LATIN CAPITAL LETTER S WITH CARON - \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE - \xD2 |0 # LATIN CAPITAL LETTER N WITH CEDILLA \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE - \xD4 |0 # LATIN CAPITAL LETTER O WITH MACRON \xD5 |0 # LATIN CAPITAL LETTER O WITH TILDE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS \xD7 |0 # MULTIPLICATION SIGN - \xD8 |0 # LATIN CAPITAL LETTER U WITH OGONEK - \xD9 |0 # LATIN CAPITAL LETTER L WITH STROKE - \xDA |0 # LATIN CAPITAL LETTER S WITH ACUTE - \xDB |0 # LATIN CAPITAL LETTER U WITH MACRON + \xA8 |0 # LATIN CAPITAL LETTER O WITH STROKE \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE - \xDE |0 # LATIN CAPITAL LETTER Z WITH CARON \xDF |0 # LATIN SMALL LETTER SHARP S - \xE0 |0 # LATIN SMALL LETTER A WITH OGONEK - \xE1 |0 # LATIN SMALL LETTER I WITH OGONEK - \xE2 |0 # LATIN SMALL LETTER A WITH MACRON - \xE3 |0 # LATIN SMALL LETTER C WITH ACUTE \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS \xE5 |0 # LATIN SMALL LETTER A WITH RING ABOVE - \xE6 |0 # LATIN SMALL LETTER E WITH OGONEK - \xE7 |0 # LATIN SMALL LETTER E WITH MACRON - \xE8 |0 # LATIN SMALL LETTER C WITH CARON + \xBF |0 # LATIN SMALL LETTER AE \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE - \xEA |0 # LATIN SMALL LETTER Z WITH ACUTE + \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE + \xF5 |0 # LATIN SMALL LETTER O WITH TILDE + \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS + \xF7 |0 # DIVISION SIGN + \xB8 |0 # LATIN SMALL LETTER O WITH STROKE + \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xC2 |0 # LATIN CAPITAL LETTER A WITH MACRON + \xE2 |0 # LATIN SMALL LETTER A WITH MACRON + \xC0 |0 # LATIN CAPITAL LETTER A WITH OGONEK + \xE0 |0 # LATIN SMALL LETTER A WITH OGONEK + \xC3 |0 # LATIN CAPITAL LETTER C WITH ACUTE + \xE3 |0 # LATIN SMALL LETTER C WITH ACUTE + \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON + \xE8 |0 # LATIN SMALL LETTER C WITH CARON + \xC7 |0 # LATIN CAPITAL LETTER E WITH MACRON + \xE7 |0 # LATIN SMALL LETTER E WITH MACRON + \xCB |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE \xEB |0 # LATIN SMALL LETTER E WITH DOT ABOVE + \xC6 |0 # LATIN CAPITAL LETTER E WITH OGONEK + \xE6 |0 # LATIN SMALL LETTER E WITH OGONEK + \xCC |0 # LATIN CAPITAL LETTER G WITH CEDILLA \xEC |0 # LATIN SMALL LETTER G WITH CEDILLA - \xED |0 # LATIN SMALL LETTER K WITH CEDILLA + \xCE |0 # LATIN CAPITAL LETTER I WITH MACRON \xEE |0 # LATIN SMALL LETTER I WITH MACRON + \xC1 |0 # LATIN CAPITAL LETTER I WITH OGONEK + \xE1 |0 # LATIN SMALL LETTER I WITH OGONEK + \xCD |0 # LATIN CAPITAL LETTER K WITH CEDILLA + \xED |0 # LATIN SMALL LETTER K WITH CEDILLA + \xCF |0 # LATIN CAPITAL LETTER L WITH CEDILLA \xEF |0 # LATIN SMALL LETTER L WITH CEDILLA - \xF0 |0 # LATIN SMALL LETTER S WITH CARON + \xD9 |0 # LATIN CAPITAL LETTER L WITH STROKE + \xF9 |0 # LATIN SMALL LETTER L WITH STROKE + \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE \xF1 |0 # LATIN SMALL LETTER N WITH ACUTE + \xD2 |0 # LATIN CAPITAL LETTER N WITH CEDILLA \xF2 |0 # LATIN SMALL LETTER N WITH CEDILLA - \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE + \xD4 |0 # LATIN CAPITAL LETTER O WITH MACRON \xF4 |0 # LATIN SMALL LETTER O WITH MACRON - \xF5 |0 # LATIN SMALL LETTER O WITH TILDE - \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS - \xF7 |0 # DIVISION SIGN - \xF8 |0 # LATIN SMALL LETTER U WITH OGONEK - \xF9 |0 # LATIN SMALL LETTER L WITH STROKE + \xAA |0 # LATIN CAPITAL LETTER R WITH CEDILLA + \xBA |0 # LATIN SMALL LETTER R WITH CEDILLA + \xDA |0 # LATIN CAPITAL LETTER S WITH ACUTE \xFA |0 # LATIN SMALL LETTER S WITH ACUTE + \xD0 |0 # LATIN CAPITAL LETTER S WITH CARON + \xF0 |0 # LATIN SMALL LETTER S WITH CARON + \xDB |0 # LATIN CAPITAL LETTER U WITH MACRON \xFB |0 # LATIN SMALL LETTER U WITH MACRON - \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xD8 |0 # LATIN CAPITAL LETTER U WITH OGONEK + \xF8 |0 # LATIN SMALL LETTER U WITH OGONEK + \xCA |0 # LATIN CAPITAL LETTER Z WITH ACUTE + \xEA |0 # LATIN SMALL LETTER Z WITH ACUTE + \xDD |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE \xFD |0 # LATIN SMALL LETTER Z WITH DOT ABOVE + \xDE |0 # LATIN CAPITAL LETTER Z WITH CARON \xFE |0 # LATIN SMALL LETTER Z WITH CARON \xFF |0 # RIGHT SINGLE QUOTATION MARK + \xB4 |0 # LEFT DOUBLE QUOTATION MARK + \xA1 |0 # RIGHT DOUBLE QUOTATION MARK + \xA5 |0 # DOUBLE LOW-9 QUOTATION MARK END CHARMAP diff --git a/ext/Encode/ucm/8859-14.ucm b/ext/Encode/ucm/8859-14.ucm index a427b82..4e9a9d3 100644 --- a/ext/Encode/ucm/8859-14.ucm +++ b/ext/Encode/ucm/8859-14.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-14.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-14.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT # -# ./compile -n iso-8859-14 -o Encode/iso8859-14.ucm Encode/iso8859-14.enc "iso-8859-14" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,71 +136,46 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER B WITH DOT ABOVE - \xA2 |0 # LATIN SMALL LETTER B WITH DOT ABOVE \xA3 |0 # POUND SIGN - \xA4 |0 # LATIN CAPITAL LETTER C WITH DOT ABOVE - \xA5 |0 # LATIN SMALL LETTER C WITH DOT ABOVE - \xA6 |0 # LATIN CAPITAL LETTER D WITH DOT ABOVE \xA7 |0 # SECTION SIGN - \xA8 |0 # LATIN CAPITAL LETTER W WITH GRAVE \xA9 |0 # COPYRIGHT SIGN - \xAA |0 # LATIN CAPITAL LETTER W WITH ACUTE - \xAB |0 # LATIN SMALL LETTER D WITH DOT ABOVE - \xAC |0 # LATIN CAPITAL LETTER Y WITH GRAVE \xAD |0 # SOFT HYPHEN \xAE |0 # REGISTERED SIGN - \xAF |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS - \xB0 |0 # LATIN CAPITAL LETTER F WITH DOT ABOVE - \xB1 |0 # LATIN SMALL LETTER F WITH DOT ABOVE - \xB2 |0 # LATIN CAPITAL LETTER G WITH DOT ABOVE - \xB3 |0 # LATIN SMALL LETTER G WITH DOT ABOVE - \xB4 |0 # LATIN CAPITAL LETTER M WITH DOT ABOVE - \xB5 |0 # LATIN SMALL LETTER M WITH DOT ABOVE \xB6 |0 # PILCROW SIGN - \xB7 |0 # LATIN CAPITAL LETTER P WITH DOT ABOVE - \xB8 |0 # LATIN SMALL LETTER W WITH GRAVE - \xB9 |0 # LATIN SMALL LETTER P WITH DOT ABOVE - \xBA |0 # LATIN SMALL LETTER W WITH ACUTE - \xBB |0 # LATIN CAPITAL LETTER S WITH DOT ABOVE - \xBC |0 # LATIN SMALL LETTER Y WITH GRAVE - \xBD |0 # LATIN CAPITAL LETTER W WITH DIAERESIS - \xBE |0 # LATIN SMALL LETTER W WITH DIAERESIS - \xBF |0 # LATIN SMALL LETTER S WITH DOT ABOVE \xC0 |0 # LATIN CAPITAL LETTER A WITH GRAVE \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX @@ -216,21 +192,18 @@ CHARMAP \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX \xCF |0 # LATIN CAPITAL LETTER I WITH DIAERESIS - \xD0 |0 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX \xD1 |0 # LATIN CAPITAL LETTER N WITH TILDE \xD2 |0 # LATIN CAPITAL LETTER O WITH GRAVE \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX \xD5 |0 # LATIN CAPITAL LETTER O WITH TILDE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS - \xD7 |0 # LATIN CAPITAL LETTER T WITH DOT ABOVE \xD8 |0 # LATIN CAPITAL LETTER O WITH STROKE \xD9 |0 # LATIN CAPITAL LETTER U WITH GRAVE \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE - \xDE |0 # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX \xDF |0 # LATIN SMALL LETTER SHARP S \xE0 |0 # LATIN SMALL LETTER A WITH GRAVE \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE @@ -248,20 +221,48 @@ CHARMAP \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX \xEF |0 # LATIN SMALL LETTER I WITH DIAERESIS - \xF0 |0 # LATIN SMALL LETTER W WITH CIRCUMFLEX \xF1 |0 # LATIN SMALL LETTER N WITH TILDE \xF2 |0 # LATIN SMALL LETTER O WITH GRAVE \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX \xF5 |0 # LATIN SMALL LETTER O WITH TILDE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS - \xF7 |0 # LATIN SMALL LETTER T WITH DOT ABOVE \xF8 |0 # LATIN SMALL LETTER O WITH STROKE \xF9 |0 # LATIN SMALL LETTER U WITH GRAVE \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE - \xFE |0 # LATIN SMALL LETTER Y WITH CIRCUMFLEX \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS + \xA4 |0 # LATIN CAPITAL LETTER C WITH DOT ABOVE + \xA5 |0 # LATIN SMALL LETTER C WITH DOT ABOVE + \xB2 |0 # LATIN CAPITAL LETTER G WITH DOT ABOVE + \xB3 |0 # LATIN SMALL LETTER G WITH DOT ABOVE + \xD0 |0 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX + \xF0 |0 # LATIN SMALL LETTER W WITH CIRCUMFLEX + \xDE |0 # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX + \xFE |0 # LATIN SMALL LETTER Y WITH CIRCUMFLEX + \xAF |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS + \xA1 |0 # LATIN CAPITAL LETTER B WITH DOT ABOVE + \xA2 |0 # LATIN SMALL LETTER B WITH DOT ABOVE + \xA6 |0 # LATIN CAPITAL LETTER D WITH DOT ABOVE + \xAB |0 # LATIN SMALL LETTER D WITH DOT ABOVE + \xB0 |0 # LATIN CAPITAL LETTER F WITH DOT ABOVE + \xB1 |0 # LATIN SMALL LETTER F WITH DOT ABOVE + \xB4 |0 # LATIN CAPITAL LETTER M WITH DOT ABOVE + \xB5 |0 # LATIN SMALL LETTER M WITH DOT ABOVE + \xB7 |0 # LATIN CAPITAL LETTER P WITH DOT ABOVE + \xB9 |0 # LATIN SMALL LETTER P WITH DOT ABOVE + \xBB |0 # LATIN CAPITAL LETTER S WITH DOT ABOVE + \xBF |0 # LATIN SMALL LETTER S WITH DOT ABOVE + \xD7 |0 # LATIN CAPITAL LETTER T WITH DOT ABOVE + \xF7 |0 # LATIN SMALL LETTER T WITH DOT ABOVE + \xA8 |0 # LATIN CAPITAL LETTER W WITH GRAVE + \xB8 |0 # LATIN SMALL LETTER W WITH GRAVE + \xAA |0 # LATIN CAPITAL LETTER W WITH ACUTE + \xBA |0 # LATIN SMALL LETTER W WITH ACUTE + \xBD |0 # LATIN CAPITAL LETTER W WITH DIAERESIS + \xBE |0 # LATIN SMALL LETTER W WITH DIAERESIS + \xAC |0 # LATIN CAPITAL LETTER Y WITH GRAVE + \xBC |0 # LATIN SMALL LETTER Y WITH GRAVE END CHARMAP diff --git a/ext/Encode/ucm/8859-15.ucm b/ext/Encode/ucm/8859-15.ucm index 69cf924..7b72204 100644 --- a/ext/Encode/ucm/8859-15.ucm +++ b/ext/Encode/ucm/8859-15.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-15.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-15.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT # -# ./compile -n iso-8859-15 -o Encode/iso8859-15.ucm Encode/iso8859-15.enc "iso-8859-15" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,48 +136,45 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA1 |0 # INVERTED EXCLAMATION MARK \xA2 |0 # CENT SIGN \xA3 |0 # POUND SIGN - \xA4 |0 # EURO SIGN \xA5 |0 # YEN SIGN - \xA6 |0 # LATIN CAPITAL LETTER S WITH CARON \xA7 |0 # SECTION SIGN - \xA8 |0 # LATIN SMALL LETTER S WITH CARON \xA9 |0 # COPYRIGHT SIGN \xAA |0 # FEMININE ORDINAL INDICATOR \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK @@ -188,17 +186,12 @@ CHARMAP \xB1 |0 # PLUS-MINUS SIGN \xB2 |0 # SUPERSCRIPT TWO \xB3 |0 # SUPERSCRIPT THREE - \xB4 |0 # LATIN CAPITAL LETTER Z WITH CARON \xB5 |0 # MICRO SIGN \xB6 |0 # PILCROW SIGN \xB7 |0 # MIDDLE DOT - \xB8 |0 # LATIN SMALL LETTER Z WITH CARON \xB9 |0 # SUPERSCRIPT ONE \xBA |0 # MASCULINE ORDINAL INDICATOR \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - \xBC |0 # LATIN CAPITAL LIGATURE OE - \xBD |0 # LATIN SMALL LIGATURE OE - \xBE |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS \xBF |0 # INVERTED QUESTION MARK \xC0 |0 # LATIN CAPITAL LETTER A WITH GRAVE \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE @@ -264,4 +257,12 @@ CHARMAP \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE \xFE |0 # LATIN SMALL LETTER THORN \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS + \xBC |0 # LATIN CAPITAL LIGATURE OE + \xBD |0 # LATIN SMALL LIGATURE OE + \xA6 |0 # LATIN CAPITAL LETTER S WITH CARON + \xA8 |0 # LATIN SMALL LETTER S WITH CARON + \xBE |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS + \xB4 |0 # LATIN CAPITAL LETTER Z WITH CARON + \xB8 |0 # LATIN SMALL LETTER Z WITH CARON + \xA4 |0 # EURO SIGN END CHARMAP diff --git a/ext/Encode/ucm/8859-16.ucm b/ext/Encode/ucm/8859-16.ucm index 8cc3899..87563aa 100644 --- a/ext/Encode/ucm/8859-16.ucm +++ b/ext/Encode/ucm/8859-16.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-16.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-16.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT # -# ./compile -n iso-8859-16 -o Encode/iso8859-16.ucm Encode/iso8859-16.enc "iso-8859-16" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,77 +136,53 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK - \xA2 |0 # LATIN SMALL LETTER A WITH OGONEK - \xA3 |0 # LATIN CAPITAL LETTER L WITH STROKE - \xA4 |0 # EURO SIGN - \xA5 |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - \xA6 |0 # LATIN CAPITAL LETTER S WITH CARON \xA7 |0 # SECTION SIGN - \xA8 |0 # LATIN SMALL LETTER S WITH CARON \xA9 |0 # COPYRIGHT SIGN - \xAA |0 # LATIN CAPITAL LETTER S WITH COMMA BELOW - \xAB |0 # DOUBLE LOW-9 QUOTATION MARK - \xAC |0 # LATIN CAPITAL LETTER Z WITH ACUTE + \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK \xAD |0 # SOFT HYPHEN - \xAE |0 # LATIN SMALL LETTER Z WITH ACUTE - \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE \xB0 |0 # DEGREE SIGN \xB1 |0 # PLUS-MINUS SIGN - \xB2 |0 # LATIN CAPITAL LETTER C WITH CARON - \xB3 |0 # LATIN SMALL LETTER L WITH STROKE - \xB4 |0 # LATIN CAPITAL LETTER Z WITH CARON - \xB5 |0 # RIGHT DOUBLE QUOTATION MARK \xB6 |0 # PILCROW SIGN \xB7 |0 # MIDDLE DOT - \xB8 |0 # LATIN SMALL LETTER Z WITH CARON - \xB9 |0 # LATIN SMALL LETTER C WITH CARON - \xBA |0 # LATIN SMALL LETTER S WITH COMMA BELOW \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - \xBC |0 # LATIN CAPITAL LIGATURE OE - \xBD |0 # LATIN SMALL LIGATURE OE - \xBE |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS - \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE \xC0 |0 # LATIN CAPITAL LETTER A WITH GRAVE \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - \xC3 |0 # LATIN CAPITAL LETTER A WITH BREVE \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS - \xC5 |0 # LATIN CAPITAL LETTER C WITH ACUTE \xC6 |0 # LATIN CAPITAL LETTER AE \xC7 |0 # LATIN CAPITAL LETTER C WITH CEDILLA \xC8 |0 # LATIN CAPITAL LETTER E WITH GRAVE @@ -216,28 +193,19 @@ CHARMAP \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX \xCF |0 # LATIN CAPITAL LETTER I WITH DIAERESIS - \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE - \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE \xD2 |0 # LATIN CAPITAL LETTER O WITH GRAVE \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - \xD5 |0 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS - \xD7 |0 # LATIN CAPITAL LETTER S WITH ACUTE - \xD8 |0 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE \xD9 |0 # LATIN CAPITAL LETTER U WITH GRAVE \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER E WITH OGONEK - \xDE |0 # LATIN CAPITAL LETTER T WITH COMMA BELOW \xDF |0 # LATIN SMALL LETTER SHARP S \xE0 |0 # LATIN SMALL LETTER A WITH GRAVE \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX - \xE3 |0 # LATIN SMALL LETTER A WITH BREVE \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS - \xE5 |0 # LATIN SMALL LETTER C WITH ACUTE \xE6 |0 # LATIN SMALL LETTER AE \xE7 |0 # LATIN SMALL LETTER C WITH CEDILLA \xE8 |0 # LATIN SMALL LETTER E WITH GRAVE @@ -248,20 +216,53 @@ CHARMAP \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX \xEF |0 # LATIN SMALL LETTER I WITH DIAERESIS - \xF0 |0 # LATIN SMALL LETTER D WITH STROKE - \xF1 |0 # LATIN SMALL LETTER N WITH ACUTE \xF2 |0 # LATIN SMALL LETTER O WITH GRAVE \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX - \xF5 |0 # LATIN SMALL LETTER O WITH DOUBLE ACUTE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS - \xF7 |0 # LATIN SMALL LETTER S WITH ACUTE - \xF8 |0 # LATIN SMALL LETTER U WITH DOUBLE ACUTE \xF9 |0 # LATIN SMALL LETTER U WITH GRAVE \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS + \xC3 |0 # LATIN CAPITAL LETTER A WITH BREVE + \xE3 |0 # LATIN SMALL LETTER A WITH BREVE + \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK + \xA2 |0 # LATIN SMALL LETTER A WITH OGONEK + \xC5 |0 # LATIN CAPITAL LETTER C WITH ACUTE + \xE5 |0 # LATIN SMALL LETTER C WITH ACUTE + \xB2 |0 # LATIN CAPITAL LETTER C WITH CARON + \xB9 |0 # LATIN SMALL LETTER C WITH CARON + \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE + \xF0 |0 # LATIN SMALL LETTER D WITH STROKE + \xDD |0 # LATIN CAPITAL LETTER E WITH OGONEK \xFD |0 # LATIN SMALL LETTER E WITH OGONEK + \xA3 |0 # LATIN CAPITAL LETTER L WITH STROKE + \xB3 |0 # LATIN SMALL LETTER L WITH STROKE + \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE + \xF1 |0 # LATIN SMALL LETTER N WITH ACUTE + \xD5 |0 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + \xF5 |0 # LATIN SMALL LETTER O WITH DOUBLE ACUTE + \xBC |0 # LATIN CAPITAL LIGATURE OE + \xBD |0 # LATIN SMALL LIGATURE OE + \xD7 |0 # LATIN CAPITAL LETTER S WITH ACUTE + \xF7 |0 # LATIN SMALL LETTER S WITH ACUTE + \xA6 |0 # LATIN CAPITAL LETTER S WITH CARON + \xA8 |0 # LATIN SMALL LETTER S WITH CARON + \xD8 |0 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + \xF8 |0 # LATIN SMALL LETTER U WITH DOUBLE ACUTE + \xBE |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS + \xAC |0 # LATIN CAPITAL LETTER Z WITH ACUTE + \xAE |0 # LATIN SMALL LETTER Z WITH ACUTE + \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE + \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE + \xB4 |0 # LATIN CAPITAL LETTER Z WITH CARON + \xB8 |0 # LATIN SMALL LETTER Z WITH CARON + \xAA |0 # LATIN CAPITAL LETTER S WITH COMMA BELOW + \xBA |0 # LATIN SMALL LETTER S WITH COMMA BELOW + \xDE |0 # LATIN CAPITAL LETTER T WITH COMMA BELOW \xFE |0 # LATIN SMALL LETTER T WITH COMMA BELOW - \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS + \xB5 |0 # RIGHT DOUBLE QUOTATION MARK + \xA5 |0 # DOUBLE LOW-9 QUOTATION MARK + \xA4 |0 # EURO SIGN END CHARMAP diff --git a/ext/Encode/ucm/8859-2.ucm b/ext/Encode/ucm/8859-2.ucm index eeb8ee3..9e2fd38 100644 --- a/ext/Encode/ucm/8859-2.ucm +++ b/ext/Encode/ucm/8859-2.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-2.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-2.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-2.TXT # -# ./compile -n iso-8859-2 -o Encode/iso8859-2.ucm Encode/iso8859-2.enc "iso-8859-2" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,133 +136,133 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK - \xA2 |0 # BREVE - \xA3 |0 # LATIN CAPITAL LETTER L WITH STROKE \xA4 |0 # CURRENCY SIGN - \xA5 |0 # LATIN CAPITAL LETTER L WITH CARON - \xA6 |0 # LATIN CAPITAL LETTER S WITH ACUTE \xA7 |0 # SECTION SIGN \xA8 |0 # DIAERESIS - \xA9 |0 # LATIN CAPITAL LETTER S WITH CARON - \xAA |0 # LATIN CAPITAL LETTER S WITH CEDILLA - \xAB |0 # LATIN CAPITAL LETTER T WITH CARON - \xAC |0 # LATIN CAPITAL LETTER Z WITH ACUTE \xAD |0 # SOFT HYPHEN - \xAE |0 # LATIN CAPITAL LETTER Z WITH CARON - \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE \xB0 |0 # DEGREE SIGN - \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK - \xB2 |0 # OGONEK - \xB3 |0 # LATIN SMALL LETTER L WITH STROKE \xB4 |0 # ACUTE ACCENT - \xB5 |0 # LATIN SMALL LETTER L WITH CARON - \xB6 |0 # LATIN SMALL LETTER S WITH ACUTE - \xB7 |0 # CARON \xB8 |0 # CEDILLA - \xB9 |0 # LATIN SMALL LETTER S WITH CARON - \xBA |0 # LATIN SMALL LETTER S WITH CEDILLA - \xBB |0 # LATIN SMALL LETTER T WITH CARON - \xBC |0 # LATIN SMALL LETTER Z WITH ACUTE - \xBD |0 # DOUBLE ACUTE ACCENT - \xBE |0 # LATIN SMALL LETTER Z WITH CARON - \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE - \xC0 |0 # LATIN CAPITAL LETTER R WITH ACUTE \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - \xC3 |0 # LATIN CAPITAL LETTER A WITH BREVE \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS - \xC5 |0 # LATIN CAPITAL LETTER L WITH ACUTE - \xC6 |0 # LATIN CAPITAL LETTER C WITH ACUTE \xC7 |0 # LATIN CAPITAL LETTER C WITH CEDILLA - \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE - \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK \xCB |0 # LATIN CAPITAL LETTER E WITH DIAERESIS - \xCC |0 # LATIN CAPITAL LETTER E WITH CARON \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - \xCF |0 # LATIN CAPITAL LETTER D WITH CARON - \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE - \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE - \xD2 |0 # LATIN CAPITAL LETTER N WITH CARON \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - \xD5 |0 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS \xD7 |0 # MULTIPLICATION SIGN - \xD8 |0 # LATIN CAPITAL LETTER R WITH CARON - \xD9 |0 # LATIN CAPITAL LETTER U WITH RING ABOVE \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE - \xDB |0 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE - \xDE |0 # LATIN CAPITAL LETTER T WITH CEDILLA \xDF |0 # LATIN SMALL LETTER SHARP S - \xE0 |0 # LATIN SMALL LETTER R WITH ACUTE \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX - \xE3 |0 # LATIN SMALL LETTER A WITH BREVE \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS - \xE5 |0 # LATIN SMALL LETTER L WITH ACUTE - \xE6 |0 # LATIN SMALL LETTER C WITH ACUTE \xE7 |0 # LATIN SMALL LETTER C WITH CEDILLA - \xE8 |0 # LATIN SMALL LETTER C WITH CARON \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE - \xEA |0 # LATIN SMALL LETTER E WITH OGONEK \xEB |0 # LATIN SMALL LETTER E WITH DIAERESIS - \xEC |0 # LATIN SMALL LETTER E WITH CARON \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX - \xEF |0 # LATIN SMALL LETTER D WITH CARON - \xF0 |0 # LATIN SMALL LETTER D WITH STROKE - \xF1 |0 # LATIN SMALL LETTER N WITH ACUTE - \xF2 |0 # LATIN SMALL LETTER N WITH CARON \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX - \xF5 |0 # LATIN SMALL LETTER O WITH DOUBLE ACUTE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS \xF7 |0 # DIVISION SIGN - \xF8 |0 # LATIN SMALL LETTER R WITH CARON - \xF9 |0 # LATIN SMALL LETTER U WITH RING ABOVE \xFA |0 # LATIN SMALL LETTER U WITH ACUTE - \xFB |0 # LATIN SMALL LETTER U WITH DOUBLE ACUTE \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE + \xC3 |0 # LATIN CAPITAL LETTER A WITH BREVE + \xE3 |0 # LATIN SMALL LETTER A WITH BREVE + \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK + \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK + \xC6 |0 # LATIN CAPITAL LETTER C WITH ACUTE + \xE6 |0 # LATIN SMALL LETTER C WITH ACUTE + \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON + \xE8 |0 # LATIN SMALL LETTER C WITH CARON + \xCF |0 # LATIN CAPITAL LETTER D WITH CARON + \xEF |0 # LATIN SMALL LETTER D WITH CARON + \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE + \xF0 |0 # LATIN SMALL LETTER D WITH STROKE + \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK + \xEA |0 # LATIN SMALL LETTER E WITH OGONEK + \xCC |0 # LATIN CAPITAL LETTER E WITH CARON + \xEC |0 # LATIN SMALL LETTER E WITH CARON + \xC5 |0 # LATIN CAPITAL LETTER L WITH ACUTE + \xE5 |0 # LATIN SMALL LETTER L WITH ACUTE + \xA5 |0 # LATIN CAPITAL LETTER L WITH CARON + \xB5 |0 # LATIN SMALL LETTER L WITH CARON + \xA3 |0 # LATIN CAPITAL LETTER L WITH STROKE + \xB3 |0 # LATIN SMALL LETTER L WITH STROKE + \xD1 |0 # LATIN CAPITAL LETTER N WITH ACUTE + \xF1 |0 # LATIN SMALL LETTER N WITH ACUTE + \xD2 |0 # LATIN CAPITAL LETTER N WITH CARON + \xF2 |0 # LATIN SMALL LETTER N WITH CARON + \xD5 |0 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + \xF5 |0 # LATIN SMALL LETTER O WITH DOUBLE ACUTE + \xC0 |0 # LATIN CAPITAL LETTER R WITH ACUTE + \xE0 |0 # LATIN SMALL LETTER R WITH ACUTE + \xD8 |0 # LATIN CAPITAL LETTER R WITH CARON + \xF8 |0 # LATIN SMALL LETTER R WITH CARON + \xA6 |0 # LATIN CAPITAL LETTER S WITH ACUTE + \xB6 |0 # LATIN SMALL LETTER S WITH ACUTE + \xAA |0 # LATIN CAPITAL LETTER S WITH CEDILLA + \xBA |0 # LATIN SMALL LETTER S WITH CEDILLA + \xA9 |0 # LATIN CAPITAL LETTER S WITH CARON + \xB9 |0 # LATIN SMALL LETTER S WITH CARON + \xDE |0 # LATIN CAPITAL LETTER T WITH CEDILLA \xFE |0 # LATIN SMALL LETTER T WITH CEDILLA + \xAB |0 # LATIN CAPITAL LETTER T WITH CARON + \xBB |0 # LATIN SMALL LETTER T WITH CARON + \xD9 |0 # LATIN CAPITAL LETTER U WITH RING ABOVE + \xF9 |0 # LATIN SMALL LETTER U WITH RING ABOVE + \xDB |0 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + \xFB |0 # LATIN SMALL LETTER U WITH DOUBLE ACUTE + \xAC |0 # LATIN CAPITAL LETTER Z WITH ACUTE + \xBC |0 # LATIN SMALL LETTER Z WITH ACUTE + \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE + \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE + \xAE |0 # LATIN CAPITAL LETTER Z WITH CARON + \xBE |0 # LATIN SMALL LETTER Z WITH CARON + \xB7 |0 # CARON + \xA2 |0 # BREVE \xFF |0 # DOT ABOVE + \xB2 |0 # OGONEK + \xBD |0 # DOUBLE ACUTE ACCENT END CHARMAP diff --git a/ext/Encode/ucm/8859-3.ucm b/ext/Encode/ucm/8859-3.ucm index 1c2e80f..6066eb9 100644 --- a/ext/Encode/ucm/8859-3.ucm +++ b/ext/Encode/ucm/8859-3.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-3.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-3.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-3.TXT # -# ./compile -n iso-8859-3 -o Encode/iso8859-3.ucm Encode/iso8859-3.enc "iso-8859-3" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,74 +136,57 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER H WITH STROKE - \xA2 |0 # BREVE \xA3 |0 # POUND SIGN \xA4 |0 # CURRENCY SIGN - \xA6 |0 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX \xA7 |0 # SECTION SIGN \xA8 |0 # DIAERESIS - \xA9 |0 # LATIN CAPITAL LETTER I WITH DOT ABOVE - \xAA |0 # LATIN CAPITAL LETTER S WITH CEDILLA - \xAB |0 # LATIN CAPITAL LETTER G WITH BREVE - \xAC |0 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX \xAD |0 # SOFT HYPHEN - \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE \xB0 |0 # DEGREE SIGN - \xB1 |0 # LATIN SMALL LETTER H WITH STROKE \xB2 |0 # SUPERSCRIPT TWO \xB3 |0 # SUPERSCRIPT THREE \xB4 |0 # ACUTE ACCENT \xB5 |0 # MICRO SIGN - \xB6 |0 # LATIN SMALL LETTER H WITH CIRCUMFLEX \xB7 |0 # MIDDLE DOT \xB8 |0 # CEDILLA - \xB9 |0 # LATIN SMALL LETTER DOTLESS I - \xBA |0 # LATIN SMALL LETTER S WITH CEDILLA - \xBB |0 # LATIN SMALL LETTER G WITH BREVE - \xBC |0 # LATIN SMALL LETTER J WITH CIRCUMFLEX \xBD |0 # VULGAR FRACTION ONE HALF - \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE \xC0 |0 # LATIN CAPITAL LETTER A WITH GRAVE \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS - \xC5 |0 # LATIN CAPITAL LETTER C WITH DOT ABOVE - \xC6 |0 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX \xC7 |0 # LATIN CAPITAL LETTER C WITH CEDILLA \xC8 |0 # LATIN CAPITAL LETTER E WITH GRAVE \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE @@ -216,23 +200,17 @@ CHARMAP \xD2 |0 # LATIN CAPITAL LETTER O WITH GRAVE \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - \xD5 |0 # LATIN CAPITAL LETTER G WITH DOT ABOVE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS \xD7 |0 # MULTIPLICATION SIGN - \xD8 |0 # LATIN CAPITAL LETTER G WITH CIRCUMFLEX \xD9 |0 # LATIN CAPITAL LETTER U WITH GRAVE \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER U WITH BREVE - \xDE |0 # LATIN CAPITAL LETTER S WITH CIRCUMFLEX \xDF |0 # LATIN SMALL LETTER SHARP S \xE0 |0 # LATIN SMALL LETTER A WITH GRAVE \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS - \xE5 |0 # LATIN SMALL LETTER C WITH DOT ABOVE - \xE6 |0 # LATIN SMALL LETTER C WITH CIRCUMFLEX \xE7 |0 # LATIN SMALL LETTER C WITH CEDILLA \xE8 |0 # LATIN SMALL LETTER E WITH GRAVE \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE @@ -246,15 +224,38 @@ CHARMAP \xF2 |0 # LATIN SMALL LETTER O WITH GRAVE \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX - \xF5 |0 # LATIN SMALL LETTER G WITH DOT ABOVE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS \xF7 |0 # DIVISION SIGN - \xF8 |0 # LATIN SMALL LETTER G WITH CIRCUMFLEX \xF9 |0 # LATIN SMALL LETTER U WITH GRAVE \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS - \xFD |0 # LATIN SMALL LETTER U WITH BREVE + \xC6 |0 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX + \xE6 |0 # LATIN SMALL LETTER C WITH CIRCUMFLEX + \xC5 |0 # LATIN CAPITAL LETTER C WITH DOT ABOVE + \xE5 |0 # LATIN SMALL LETTER C WITH DOT ABOVE + \xD8 |0 # LATIN CAPITAL LETTER G WITH CIRCUMFLEX + \xF8 |0 # LATIN SMALL LETTER G WITH CIRCUMFLEX + \xAB |0 # LATIN CAPITAL LETTER G WITH BREVE + \xBB |0 # LATIN SMALL LETTER G WITH BREVE + \xD5 |0 # LATIN CAPITAL LETTER G WITH DOT ABOVE + \xF5 |0 # LATIN SMALL LETTER G WITH DOT ABOVE + \xA6 |0 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX + \xB6 |0 # LATIN SMALL LETTER H WITH CIRCUMFLEX + \xA1 |0 # LATIN CAPITAL LETTER H WITH STROKE + \xB1 |0 # LATIN SMALL LETTER H WITH STROKE + \xA9 |0 # LATIN CAPITAL LETTER I WITH DOT ABOVE + \xB9 |0 # LATIN SMALL LETTER DOTLESS I + \xAC |0 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX + \xBC |0 # LATIN SMALL LETTER J WITH CIRCUMFLEX + \xDE |0 # LATIN CAPITAL LETTER S WITH CIRCUMFLEX \xFE |0 # LATIN SMALL LETTER S WITH CIRCUMFLEX + \xAA |0 # LATIN CAPITAL LETTER S WITH CEDILLA + \xBA |0 # LATIN SMALL LETTER S WITH CEDILLA + \xDD |0 # LATIN CAPITAL LETTER U WITH BREVE + \xFD |0 # LATIN SMALL LETTER U WITH BREVE + \xAF |0 # LATIN CAPITAL LETTER Z WITH DOT ABOVE + \xBF |0 # LATIN SMALL LETTER Z WITH DOT ABOVE + \xA2 |0 # BREVE \xFF |0 # DOT ABOVE END CHARMAP diff --git a/ext/Encode/ucm/8859-4.ucm b/ext/Encode/ucm/8859-4.ucm index 66c2b83..901fe06 100644 --- a/ext/Encode/ucm/8859-4.ucm +++ b/ext/Encode/ucm/8859-4.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-4.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-4.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-4.TXT # -# ./compile -n iso-8859-4 -o Encode/iso8859-4.ucm Encode/iso8859-4.enc "iso-8859-4" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,133 +136,133 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK - \xA2 |0 # LATIN SMALL LETTER KRA - \xA3 |0 # LATIN CAPITAL LETTER R WITH CEDILLA \xA4 |0 # CURRENCY SIGN - \xA5 |0 # LATIN CAPITAL LETTER I WITH TILDE - \xA6 |0 # LATIN CAPITAL LETTER L WITH CEDILLA \xA7 |0 # SECTION SIGN \xA8 |0 # DIAERESIS - \xA9 |0 # LATIN CAPITAL LETTER S WITH CARON - \xAA |0 # LATIN CAPITAL LETTER E WITH MACRON - \xAB |0 # LATIN CAPITAL LETTER G WITH CEDILLA - \xAC |0 # LATIN CAPITAL LETTER T WITH STROKE \xAD |0 # SOFT HYPHEN - \xAE |0 # LATIN CAPITAL LETTER Z WITH CARON \xAF |0 # MACRON \xB0 |0 # DEGREE SIGN - \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK - \xB2 |0 # OGONEK - \xB3 |0 # LATIN SMALL LETTER R WITH CEDILLA \xB4 |0 # ACUTE ACCENT - \xB5 |0 # LATIN SMALL LETTER I WITH TILDE - \xB6 |0 # LATIN SMALL LETTER L WITH CEDILLA - \xB7 |0 # CARON \xB8 |0 # CEDILLA - \xB9 |0 # LATIN SMALL LETTER S WITH CARON - \xBA |0 # LATIN SMALL LETTER E WITH MACRON - \xBB |0 # LATIN SMALL LETTER G WITH CEDILLA - \xBC |0 # LATIN SMALL LETTER T WITH STROKE - \xBD |0 # LATIN CAPITAL LETTER ENG - \xBE |0 # LATIN SMALL LETTER Z WITH CARON - \xBF |0 # LATIN SMALL LETTER ENG - \xC0 |0 # LATIN CAPITAL LETTER A WITH MACRON \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX \xC3 |0 # LATIN CAPITAL LETTER A WITH TILDE \xC4 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS \xC5 |0 # LATIN CAPITAL LETTER A WITH RING ABOVE \xC6 |0 # LATIN CAPITAL LETTER AE - \xC7 |0 # LATIN CAPITAL LETTER I WITH OGONEK - \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE - \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK \xCB |0 # LATIN CAPITAL LETTER E WITH DIAERESIS - \xCC |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - \xCF |0 # LATIN CAPITAL LETTER I WITH MACRON - \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE - \xD1 |0 # LATIN CAPITAL LETTER N WITH CEDILLA - \xD2 |0 # LATIN CAPITAL LETTER O WITH MACRON - \xD3 |0 # LATIN CAPITAL LETTER K WITH CEDILLA \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX \xD5 |0 # LATIN CAPITAL LETTER O WITH TILDE \xD6 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS \xD7 |0 # MULTIPLICATION SIGN \xD8 |0 # LATIN CAPITAL LETTER O WITH STROKE - \xD9 |0 # LATIN CAPITAL LETTER U WITH OGONEK \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER U WITH TILDE - \xDE |0 # LATIN CAPITAL LETTER U WITH MACRON \xDF |0 # LATIN SMALL LETTER SHARP S - \xE0 |0 # LATIN SMALL LETTER A WITH MACRON \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX \xE3 |0 # LATIN SMALL LETTER A WITH TILDE \xE4 |0 # LATIN SMALL LETTER A WITH DIAERESIS \xE5 |0 # LATIN SMALL LETTER A WITH RING ABOVE \xE6 |0 # LATIN SMALL LETTER AE - \xE7 |0 # LATIN SMALL LETTER I WITH OGONEK - \xE8 |0 # LATIN SMALL LETTER C WITH CARON \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE - \xEA |0 # LATIN SMALL LETTER E WITH OGONEK \xEB |0 # LATIN SMALL LETTER E WITH DIAERESIS - \xEC |0 # LATIN SMALL LETTER E WITH DOT ABOVE \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX - \xEF |0 # LATIN SMALL LETTER I WITH MACRON - \xF0 |0 # LATIN SMALL LETTER D WITH STROKE - \xF1 |0 # LATIN SMALL LETTER N WITH CEDILLA - \xF2 |0 # LATIN SMALL LETTER O WITH MACRON - \xF3 |0 # LATIN SMALL LETTER K WITH CEDILLA \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX \xF5 |0 # LATIN SMALL LETTER O WITH TILDE \xF6 |0 # LATIN SMALL LETTER O WITH DIAERESIS \xF7 |0 # DIVISION SIGN \xF8 |0 # LATIN SMALL LETTER O WITH STROKE - \xF9 |0 # LATIN SMALL LETTER U WITH OGONEK \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xC0 |0 # LATIN CAPITAL LETTER A WITH MACRON + \xE0 |0 # LATIN SMALL LETTER A WITH MACRON + \xA1 |0 # LATIN CAPITAL LETTER A WITH OGONEK + \xB1 |0 # LATIN SMALL LETTER A WITH OGONEK + \xC8 |0 # LATIN CAPITAL LETTER C WITH CARON + \xE8 |0 # LATIN SMALL LETTER C WITH CARON + \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE + \xF0 |0 # LATIN SMALL LETTER D WITH STROKE + \xAA |0 # LATIN CAPITAL LETTER E WITH MACRON + \xBA |0 # LATIN SMALL LETTER E WITH MACRON + \xCC |0 # LATIN CAPITAL LETTER E WITH DOT ABOVE + \xEC |0 # LATIN SMALL LETTER E WITH DOT ABOVE + \xCA |0 # LATIN CAPITAL LETTER E WITH OGONEK + \xEA |0 # LATIN SMALL LETTER E WITH OGONEK + \xAB |0 # LATIN CAPITAL LETTER G WITH CEDILLA + \xBB |0 # LATIN SMALL LETTER G WITH CEDILLA + \xA5 |0 # LATIN CAPITAL LETTER I WITH TILDE + \xB5 |0 # LATIN SMALL LETTER I WITH TILDE + \xCF |0 # LATIN CAPITAL LETTER I WITH MACRON + \xEF |0 # LATIN SMALL LETTER I WITH MACRON + \xC7 |0 # LATIN CAPITAL LETTER I WITH OGONEK + \xE7 |0 # LATIN SMALL LETTER I WITH OGONEK + \xD3 |0 # LATIN CAPITAL LETTER K WITH CEDILLA + \xF3 |0 # LATIN SMALL LETTER K WITH CEDILLA + \xA2 |0 # LATIN SMALL LETTER KRA + \xA6 |0 # LATIN CAPITAL LETTER L WITH CEDILLA + \xB6 |0 # LATIN SMALL LETTER L WITH CEDILLA + \xD1 |0 # LATIN CAPITAL LETTER N WITH CEDILLA + \xF1 |0 # LATIN SMALL LETTER N WITH CEDILLA + \xBD |0 # LATIN CAPITAL LETTER ENG + \xBF |0 # LATIN SMALL LETTER ENG + \xD2 |0 # LATIN CAPITAL LETTER O WITH MACRON + \xF2 |0 # LATIN SMALL LETTER O WITH MACRON + \xA3 |0 # LATIN CAPITAL LETTER R WITH CEDILLA + \xB3 |0 # LATIN SMALL LETTER R WITH CEDILLA + \xA9 |0 # LATIN CAPITAL LETTER S WITH CARON + \xB9 |0 # LATIN SMALL LETTER S WITH CARON + \xAC |0 # LATIN CAPITAL LETTER T WITH STROKE + \xBC |0 # LATIN SMALL LETTER T WITH STROKE + \xDD |0 # LATIN CAPITAL LETTER U WITH TILDE \xFD |0 # LATIN SMALL LETTER U WITH TILDE + \xDE |0 # LATIN CAPITAL LETTER U WITH MACRON \xFE |0 # LATIN SMALL LETTER U WITH MACRON + \xD9 |0 # LATIN CAPITAL LETTER U WITH OGONEK + \xF9 |0 # LATIN SMALL LETTER U WITH OGONEK + \xAE |0 # LATIN CAPITAL LETTER Z WITH CARON + \xBE |0 # LATIN SMALL LETTER Z WITH CARON + \xB7 |0 # CARON \xFF |0 # DOT ABOVE + \xB2 |0 # OGONEK END CHARMAP diff --git a/ext/Encode/ucm/8859-5.ucm b/ext/Encode/ucm/8859-5.ucm index c3b9898..f03b494 100644 --- a/ext/Encode/ucm/8859-5.ucm +++ b/ext/Encode/ucm/8859-5.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-5.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-5.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-5.TXT # -# ./compile -n iso-8859-5 -o Encode/iso8859-5.ucm Encode/iso8859-5.enc "iso-8859-5" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,40 +136,42 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE + \xFD |0 # SECTION SIGN + \xAD |0 # SOFT HYPHEN \xA1 |0 # CYRILLIC CAPITAL LETTER IO \xA2 |0 # CYRILLIC CAPITAL LETTER DJE \xA3 |0 # CYRILLIC CAPITAL LETTER GJE @@ -181,7 +184,6 @@ CHARMAP \xAA |0 # CYRILLIC CAPITAL LETTER NJE \xAB |0 # CYRILLIC CAPITAL LETTER TSHE \xAC |0 # CYRILLIC CAPITAL LETTER KJE - \xAD |0 # SOFT HYPHEN \xAE |0 # CYRILLIC CAPITAL LETTER SHORT U \xAF |0 # CYRILLIC CAPITAL LETTER DZHE \xB0 |0 # CYRILLIC CAPITAL LETTER A @@ -248,7 +250,6 @@ CHARMAP \xED |0 # CYRILLIC SMALL LETTER E \xEE |0 # CYRILLIC SMALL LETTER YU \xEF |0 # CYRILLIC SMALL LETTER YA - \xF0 |0 # NUMERO SIGN \xF1 |0 # CYRILLIC SMALL LETTER IO \xF2 |0 # CYRILLIC SMALL LETTER DJE \xF3 |0 # CYRILLIC SMALL LETTER GJE @@ -261,7 +262,7 @@ CHARMAP \xFA |0 # CYRILLIC SMALL LETTER NJE \xFB |0 # CYRILLIC SMALL LETTER TSHE \xFC |0 # CYRILLIC SMALL LETTER KJE - \xFD |0 # SECTION SIGN \xFE |0 # CYRILLIC SMALL LETTER SHORT U \xFF |0 # CYRILLIC SMALL LETTER DZHE + \xF0 |0 # NUMERO SIGN END CHARMAP diff --git a/ext/Encode/ucm/8859-6.ucm b/ext/Encode/ucm/8859-6.ucm index 0a970cd..9c79e25 100644 --- a/ext/Encode/ucm/8859-6.ucm +++ b/ext/Encode/ucm/8859-6.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-6.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-6.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-6.TXT # -# ./compile -n iso-8859-6 -o Encode/iso8859-6.ucm Encode/iso8859-6.enc "iso-8859-6" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -56,16 +57,16 @@ CHARMAP \x2D |0 # HYPHEN-MINUS \x2E |0 # FULL STOP \x2F |0 # SOLIDUS - \x30 |0 # ARABIC-INDIC DIGIT ZERO - \x31 |0 # ARABIC-INDIC DIGIT ONE - \x32 |0 # ARABIC-INDIC DIGIT TWO - \x33 |0 # ARABIC-INDIC DIGIT THREE - \x34 |0 # ARABIC-INDIC DIGIT FOUR - \x35 |0 # ARABIC-INDIC DIGIT FIVE - \x36 |0 # ARABIC-INDIC DIGIT SIX - \x37 |0 # ARABIC-INDIC DIGIT SEVEN - \x38 |0 # ARABIC-INDIC DIGIT EIGHT - \x39 |0 # ARABIC-INDIC DIGIT NINE + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE \x3A |0 # COLON \x3B |0 # SEMICOLON \x3C |0 # LESS-THAN SIGN @@ -135,43 +136,43 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA4 |0 # CURRENCY SIGN - \xAC |0 # ARABIC COMMA \xAD |0 # SOFT HYPHEN + \xAC |0 # ARABIC COMMA \xBB |0 # ARABIC SEMICOLON \xBF |0 # ARABIC QUESTION MARK \xC1 |0 # ARABIC LETTER HAMZA diff --git a/ext/Encode/ucm/8859-7.ucm b/ext/Encode/ucm/8859-7.ucm index f92a11a..818ef79 100644 --- a/ext/Encode/ucm/8859-7.ucm +++ b/ext/Encode/ucm/8859-7.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-7.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-7.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT # -# ./compile -n iso-8859-7 -o Encode/iso8859-7.ucm Encode/iso8859-7.enc "iso-8859-7" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,42 +136,40 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE - \xA1 |0 # MODIFIER LETTER REVERSED COMMA - \xA2 |0 # MODIFIER LETTER APOSTROPHE \xA3 |0 # POUND SIGN \xA6 |0 # BROKEN BAR \xA7 |0 # SECTION SIGN @@ -179,21 +178,20 @@ CHARMAP \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK \xAC |0 # NOT SIGN \xAD |0 # SOFT HYPHEN - \xAF |0 # HORIZONTAL BAR \xB0 |0 # DEGREE SIGN \xB1 |0 # PLUS-MINUS SIGN \xB2 |0 # SUPERSCRIPT TWO \xB3 |0 # SUPERSCRIPT THREE + \xB7 |0 # MIDDLE DOT + \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + \xBD |0 # VULGAR FRACTION ONE HALF \xB4 |0 # GREEK TONOS \xB5 |0 # GREEK DIALYTIKA TONOS \xB6 |0 # GREEK CAPITAL LETTER ALPHA WITH TONOS - \xB7 |0 # MIDDLE DOT \xB8 |0 # GREEK CAPITAL LETTER EPSILON WITH TONOS \xB9 |0 # GREEK CAPITAL LETTER ETA WITH TONOS \xBA |0 # GREEK CAPITAL LETTER IOTA WITH TONOS - \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK \xBC |0 # GREEK CAPITAL LETTER OMICRON WITH TONOS - \xBD |0 # VULGAR FRACTION ONE HALF \xBE |0 # GREEK CAPITAL LETTER UPSILON WITH TONOS \xBF |0 # GREEK CAPITAL LETTER OMEGA WITH TONOS \xC0 |0 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS @@ -258,4 +256,7 @@ CHARMAP \xFC |0 # GREEK SMALL LETTER OMICRON WITH TONOS \xFD |0 # GREEK SMALL LETTER UPSILON WITH TONOS \xFE |0 # GREEK SMALL LETTER OMEGA WITH TONOS + \xAF |0 # HORIZONTAL BAR + \xA1 |0 # LEFT SINGLE QUOTATION MARK + \xA2 |0 # RIGHT SINGLE QUOTATION MARK END CHARMAP diff --git a/ext/Encode/ucm/8859-8.ucm b/ext/Encode/ucm/8859-8.ucm index b29179a..87f7054 100644 --- a/ext/Encode/ucm/8859-8.ucm +++ b/ext/Encode/ucm/8859-8.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-8.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-8.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-8.TXT # -# ./compile -n iso-8859-8 -o Encode/iso8859-8.ucm Encode/iso8859-8.enc "iso-8859-8" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,39 +136,39 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA2 |0 # CENT SIGN \xA3 |0 # POUND SIGN @@ -177,12 +178,11 @@ CHARMAP \xA7 |0 # SECTION SIGN \xA8 |0 # DIAERESIS \xA9 |0 # COPYRIGHT SIGN - \xAA |0 # MULTIPLICATION SIGN \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK \xAC |0 # NOT SIGN \xAD |0 # SOFT HYPHEN \xAE |0 # REGISTERED SIGN - \xAF |0 # OVERLINE + \xAF |0 # MACRON \xB0 |0 # DEGREE SIGN \xB1 |0 # PLUS-MINUS SIGN \xB2 |0 # SUPERSCRIPT TWO @@ -193,12 +193,12 @@ CHARMAP \xB7 |0 # MIDDLE DOT \xB8 |0 # CEDILLA \xB9 |0 # SUPERSCRIPT ONE - \xBA |0 # DIVISION SIGN \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK \xBC |0 # VULGAR FRACTION ONE QUARTER \xBD |0 # VULGAR FRACTION ONE HALF \xBE |0 # VULGAR FRACTION THREE QUARTERS - \xDF |0 # DOUBLE LOW LINE + \xAA |0 # MULTIPLICATION SIGN + \xBA |0 # DIVISION SIGN \xE0 |0 # HEBREW LETTER ALEF \xE1 |0 # HEBREW LETTER BET \xE2 |0 # HEBREW LETTER GIMEL @@ -226,4 +226,7 @@ CHARMAP \xF8 |0 # HEBREW LETTER RESH \xF9 |0 # HEBREW LETTER SHIN \xFA |0 # HEBREW LETTER TAV + \xFD |0 # LEFT-TO-RIGHT MARK + \xFE |0 # RIGHT-TO-LEFT MARK + \xDF |0 # DOUBLE LOW LINE END CHARMAP diff --git a/ext/Encode/ucm/8859-9.ucm b/ext/Encode/ucm/8859-9.ucm index c763763..249dc89 100644 --- a/ext/Encode/ucm/8859-9.ucm +++ b/ext/Encode/ucm/8859-9.ucm @@ -1,45 +1,46 @@ # -# $Id: 8859-9.ucm,v 1.0 2002/03/28 23:26:24 dankogai Exp $ +# $Id: 8859-9.ucm,v 1.1 2003/05/21 09:06:36 dankogai Exp $ +# +# Original table can be obtained at +# http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-9.TXT # -# ./compile -n iso-8859-9 -o Encode/iso8859-9.ucm Encode/iso8859-9.enc "iso-8859-9" 1 1 \x3F -# CHARMAP - \x00 |0 # - \x01 |0 # - \x02 |0 # - \x03 |0 # - \x04 |0 # - \x05 |0 # - \x06 |0 # - \x07 |0 # - \x08 |0 # - \x09 |0 # - \x0A |0 # - \x0B |0 # - \x0C |0 # - \x0D |0 # - \x0E |0 # - \x0F |0 # - \x10 |0 # - \x11 |0 # - \x12 |0 # - \x13 |0 # - \x14 |0 # - \x15 |0 # - \x16 |0 # - \x17 |0 # - \x18 |0 # - \x19 |0 # - \x1A |0 # - \x1B |0 # - \x1C |0 # - \x1D |0 # - \x1E |0 # - \x1F |0 # + \x00 |0 # NULL + \x01 |0 # START OF HEADING + \x02 |0 # START OF TEXT + \x03 |0 # END OF TEXT + \x04 |0 # END OF TRANSMISSION + \x05 |0 # ENQUIRY + \x06 |0 # ACKNOWLEDGE + \x07 |0 # BELL + \x08 |0 # BACKSPACE + \x09 |0 # CHARACTER TABULATION + \x0A |0 # LINE FEED (LF) + \x0B |0 # LINE TABULATION + \x0C |0 # FORM FEED (FF) + \x0D |0 # CARRIAGE RETURN (CR) + \x0E |0 # SHIFT OUT + \x0F |0 # SHIFT IN + \x10 |0 # DATA LINK ESCAPE + \x11 |0 # DEVICE CONTROL ONE + \x12 |0 # DEVICE CONTROL TWO + \x13 |0 # DEVICE CONTROL THREE + \x14 |0 # DEVICE CONTROL FOUR + \x15 |0 # NEGATIVE ACKNOWLEDGE + \x16 |0 # SYNCHRONOUS IDLE + \x17 |0 # END OF TRANSMISSION BLOCK + \x18 |0 # CANCEL + \x19 |0 # END OF MEDIUM + \x1A |0 # SUBSTITUTE + \x1B |0 # ESCAPE + \x1C |0 # INFORMATION SEPARATOR FOUR + \x1D |0 # INFORMATION SEPARATOR THREE + \x1E |0 # INFORMATION SEPARATOR TWO + \x1F |0 # INFORMATION SEPARATOR ONE \x20 |0 # SPACE \x21 |0 # EXCLAMATION MARK \x22 |0 # QUOTATION MARK @@ -135,39 +136,39 @@ CHARMAP \x7C |0 # VERTICAL LINE \x7D |0 # RIGHT CURLY BRACKET \x7E |0 # TILDE - \x7F |0 # + \x7F |0 # DELETE \x80 |0 # \x81 |0 # - \x82 |0 # - \x83 |0 # + \x82 |0 # BREAK PERMITTED HERE + \x83 |0 # NO BREAK HERE \x84 |0 # - \x85 |0 # - \x86 |0 # - \x87 |0 # - \x88 |0 # - \x89 |0 # - \x8A |0 # - \x8B |0 # - \x8C |0 # - \x8D |0 # - \x8E |0 # - \x8F |0 # - \x90 |0 # - \x91 |0 # - \x92 |0 # - \x93 |0 # - \x94 |0 # - \x95 |0 # - \x96 |0 # - \x97 |0 # - \x98 |0 # + \x85 |0 # NEXT LINE (NEL) + \x86 |0 # START OF SELECTED AREA + \x87 |0 # END OF SELECTED AREA + \x88 |0 # CHARACTER TABULATION SET + \x89 |0 # CHARACTER TABULATION WITH JUSTIFICATION + \x8A |0 # LINE TABULATION SET + \x8B |0 # PARTIAL LINE FORWARD + \x8C |0 # PARTIAL LINE BACKWARD + \x8D |0 # REVERSE LINE FEED + \x8E |0 # SINGLE SHIFT TWO + \x8F |0 # SINGLE SHIFT THREE + \x90 |0 # DEVICE CONTROL STRING + \x91 |0 # PRIVATE USE ONE + \x92 |0 # PRIVATE USE TWO + \x93 |0 # SET TRANSMIT STATE + \x94 |0 # CANCEL CHARACTER + \x95 |0 # MESSAGE WAITING + \x96 |0 # START OF GUARDED AREA + \x97 |0 # END OF GUARDED AREA + \x98 |0 # START OF STRING \x99 |0 # - \x9A |0 # - \x9B |0 # - \x9C |0 # - \x9D |0 # - \x9E |0 # - \x9F |0 # + \x9A |0 # SINGLE CHARACTER INTRODUCER + \x9B |0 # CONTROL SEQUENCE INTRODUCER + \x9C |0 # STRING TERMINATOR + \x9D |0 # OPERATING SYSTEM COMMAND + \x9E |0 # PRIVACY MESSAGE + \x9F |0 # APPLICATION PROGRAM COMMAND \xA0 |0 # NO-BREAK SPACE \xA1 |0 # INVERTED EXCLAMATION MARK \xA2 |0 # CENT SIGN @@ -216,7 +217,6 @@ CHARMAP \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE \xCE |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX \xCF |0 # LATIN CAPITAL LETTER I WITH DIAERESIS - \xD0 |0 # LATIN CAPITAL LETTER G WITH BREVE \xD1 |0 # LATIN CAPITAL LETTER N WITH TILDE \xD2 |0 # LATIN CAPITAL LETTER O WITH GRAVE \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE @@ -229,8 +229,6 @@ CHARMAP \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS - \xDD |0 # LATIN CAPITAL LETTER I WITH DOT ABOVE - \xDE |0 # LATIN CAPITAL LETTER S WITH CEDILLA \xDF |0 # LATIN SMALL LETTER SHARP S \xE0 |0 # LATIN SMALL LETTER A WITH GRAVE \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE @@ -248,7 +246,6 @@ CHARMAP \xED |0 # LATIN SMALL LETTER I WITH ACUTE \xEE |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX \xEF |0 # LATIN SMALL LETTER I WITH DIAERESIS - \xF0 |0 # LATIN SMALL LETTER G WITH BREVE \xF1 |0 # LATIN SMALL LETTER N WITH TILDE \xF2 |0 # LATIN SMALL LETTER O WITH GRAVE \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE @@ -261,7 +258,11 @@ CHARMAP \xFA |0 # LATIN SMALL LETTER U WITH ACUTE \xFB |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS + \xD0 |0 # LATIN CAPITAL LETTER G WITH BREVE + \xF0 |0 # LATIN SMALL LETTER G WITH BREVE + \xDD |0 # LATIN CAPITAL LETTER I WITH DOT ABOVE \xFD |0 # LATIN SMALL LETTER DOTLESS I + \xDE |0 # LATIN CAPITAL LETTER S WITH CEDILLA \xFE |0 # LATIN SMALL LETTER S WITH CEDILLA - \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS END CHARMAP