"{ Encoding: utf8 }"

"

 COPYRIGHT (c) 2004 by eXept Software AG

              All Rights Reserved

 This software is furnished under a license and may be used

 only in accordance with the terms of that license and with the

 inclusion of the above copyright notice.   This software may not

 be provided or otherwise made available to, or used by, any

 other person.  No title to or ownership of the software is

 hereby transferred.

"

"{ Package: 'stx:libbasic' }"

"{ NameSpace: CharacterEncoderImplementations }"

VariableBytesEncoder subclass:#MS_Ansi

	instanceVariableNames:''

	classVariableNames:''

	poolDictionaries:''

	category:'Collections-Text-Encodings'

!

!MS_Ansi class methodsFor:'documentation'!

copyright

"

 COPYRIGHT (c) 2004 by eXept Software AG

              All Rights Reserved

 This software is furnished under a license and may be used

 only in accordance with the terms of that license and with the

 inclusion of the above copyright notice.   This software may not

 be provided or otherwise made available to, or used by, any

 other person.  No title to or ownership of the software is

 hereby transferred.

"

!

documentation

"

    Microsoft ANSI - which is what Microsoft thought what is ANSI coding in the 80s (whatever that should be).

    It is definitely not an ANSI standard!!

    In fact it is CP1252 encoding which is based on iso8859-1. 

    Codepoints 0x80–0x9F which are control characters

    in iso8859 are mapped to special windows characters.

    Apparently, meanwhile Microsoft supports codepoints above 0xff as unicode.

    We map unicode codepoints which are defined in CP1552 to CP1552, 

    and leave others unchanged.

    So this encoder will return characters above 0xFF if required.

    (compare to MS_CP1252, which does not)

    [see with:]

        CharacterEncoderImplementations::MS_Ansi showCharacterSet

    [author:]

        Claus Gittinger

"

! !

!MS_Ansi class methodsFor:'mapping'!

mapFileURL2_relativePathName

    ^ 'CP1252'

    "

     self generateCode

    "

!

mapping

"

# From: http://std.dkuug.dk/i18n/charmaps/CP1252

<code_set_name> CP1252

<comment_char> %

<escape_char> /

% version: 1.0

% repertoiremap: mnemonic,ds

%  source: UNICODE 1.0

% alias MS-ANSI

CHARMAP

<NU>                   /x00   <U0000> NULL (NUL)

<SH>                   /x01   <U0001> START OF HEADING (SOH)

<SX>                   /x02   <U0002> START OF TEXT (STX)

<EX>                   /x03   <U0003> END OF TEXT (ETX)

<ET>                   /x04   <U0004> END OF TRANSMISSION (EOT)

<EQ>                   /x05   <U0005> ENQUIRY (ENQ)

<AK>                   /x06   <U0006> ACKNOWLEDGE (ACK)

<BL>                   /x07   <U0007> BELL (BEL)

<BS>                   /x08   <U0008> BACKSPACE (BS)

<HT>                   /x09   <U0009> CHARACTER TABULATION (HT)

<LF>                   /x0A   <U000A> LINE FEED (LF)

<VT>                   /x0B   <U000B> LINE TABULATION (VT)

<FF>                   /x0C   <U000C> FORM FEED (FF)

<CR>                   /x0D   <U000D> CARRIAGE RETURN (CR)

<SO>                   /x0E   <U000E> SHIFT OUT (SO)

<SI>                   /x0F   <U000F> SHIFT IN (SI)

<DL>                   /x10   <U0010> DATALINK ESCAPE (DLE)

<D1>                   /x11   <U0011> DEVICE CONTROL ONE (DC1)

<D2>                   /x12   <U0012> DEVICE CONTROL TWO (DC2)

<D3>                   /x13   <U0013> DEVICE CONTROL THREE (DC3)

<D4>                   /x14   <U0014> DEVICE CONTROL FOUR (DC4)

<NK>                   /x15   <U0015> NEGATIVE ACKNOWLEDGE (NAK)

<SY>                   /x16   <U0016> SYNCHRONOUS IDLE (SYN)

<EB>                   /x17   <U0017> END OF TRANSMISSION BLOCK (ETB)

<CN>                   /x18   <U0018> CANCEL (CAN)

<EM>                   /x19   <U0019> END OF MEDIUM (EM)

<SB>                   /x1A   <U001A> SUBSTITUTE (SUB)

<EC>                   /x1B   <U001B> ESCAPE (ESC)

<FS>                   /x1C   <U001C> FILE SEPARATOR (IS4)

<GS>                   /x1D   <U001D> GROUP SEPARATOR (IS3)

<RS>                   /x1E   <U001E> RECORD SEPARATOR (IS2)

<US>                   /x1F   <U001F> UNIT SEPARATOR (IS1)

<SP>                   /x20   <U0020> SPACE

<!!>                    /x21   <U0021> EXCLAMATION MARK

<'>                    /x22   <U0022> QUOTATION MARK

<Nb>                   /x23   <U0023> NUMBER SIGN

<DO>                   /x24   <U0024> DOLLAR SIGN

<%>                    /x25   <U0025> PERCENT SIGN

<&>                    /x26   <U0026> AMPERSAND

<'>                    /x27   <U0027> APOSTROPHE

<(>                    /x28   <U0028> LEFT PARENTHESIS

<)>                    /x29   <U0029> RIGHT PARENTHESIS

<*>                    /x2A   <U002A> ASTERISK

<+>                    /x2B   <U002B> PLUS SIGN

<,>                    /x2C   <U002C> COMMA

<->                    /x2D   <U002D> HYPHEN-MINUS

<.>                    /x2E   <U002E> FULL STOP

<//>                   /x2F   <U002F> SOLIDUS

<0>                    /x30   <U0030> DIGIT ZERO

<1>                    /x31   <U0031> DIGIT ONE

<2>                    /x32   <U0032> DIGIT TWO

<3>                    /x33   <U0033> DIGIT THREE

<4>                    /x34   <U0034> DIGIT FOUR

<5>                    /x35   <U0035> DIGIT FIVE

<6>                    /x36   <U0036> DIGIT SIX

<7>                    /x37   <U0037> DIGIT SEVEN

<8>                    /x38   <U0038> DIGIT EIGHT

<9>                    /x39   <U0039> DIGIT NINE

<:>                    /x3A   <U003A> COLON

<;>                    /x3B   <U003B> SEMICOLON

<<>                    /x3C   <U003C> LESS-THAN SIGN

<=>                    /x3D   <U003D> EQUALS SIGN

</>>                   /x3E   <U003E> GREATER-THAN SIGN

<?>                    /x3F   <U003F> QUESTION MARK

<At>                   /x40   <U0040> COMMERCIAL AT

<A>                    /x41   <U0041> LATIN CAPITAL LETTER A

<B>                    /x42   <U0042> LATIN CAPITAL LETTER B

<C>                    /x43   <U0043> LATIN CAPITAL LETTER C

<D>                    /x44   <U0044> LATIN CAPITAL LETTER D

<E>                    /x45   <U0045> LATIN CAPITAL LETTER E

<F>                    /x46   <U0046> LATIN CAPITAL LETTER F

<G>                    /x47   <U0047> LATIN CAPITAL LETTER G

<H>                    /x48   <U0048> LATIN CAPITAL LETTER H

<I>                    /x49   <U0049> LATIN CAPITAL LETTER I

<J>                    /x4A   <U004A> LATIN CAPITAL LETTER J

<K>                    /x4B   <U004B> LATIN CAPITAL LETTER K

<L>                    /x4C   <U004C> LATIN CAPITAL LETTER L

<M>                    /x4D   <U004D> LATIN CAPITAL LETTER M

<N>                    /x4E   <U004E> LATIN CAPITAL LETTER N

<O>                    /x4F   <U004F> LATIN CAPITAL LETTER O

<P>                    /x50   <U0050> LATIN CAPITAL LETTER P

<Q>                    /x51   <U0051> LATIN CAPITAL LETTER Q

<R>                    /x52   <U0052> LATIN CAPITAL LETTER R

<S>                    /x53   <U0053> LATIN CAPITAL LETTER S

<T>                    /x54   <U0054> LATIN CAPITAL LETTER T

<U>                    /x55   <U0055> LATIN CAPITAL LETTER U

<V>                    /x56   <U0056> LATIN CAPITAL LETTER V

<W>                    /x57   <U0057> LATIN CAPITAL LETTER W

<X>                    /x58   <U0058> LATIN CAPITAL LETTER X

<Y>                    /x59   <U0059> LATIN CAPITAL LETTER Y

<Z>                    /x5A   <U005A> LATIN CAPITAL LETTER Z

<<(>                   /x5B   <U005B> LEFT SQUARE BRACKET

<////>                 /x5C   <U005C> REVERSE SOLIDUS

<)/>>                  /x5D   <U005D> RIGHT SQUARE BRACKET

<'/>>                  /x5E   <U005E> CIRCUMFLEX ACCENT

<_>                    /x5F   <U005F> LOW LINE

<'!!>                   /x60   <U0060> GRAVE ACCENT

<a>                    /x61   <U0061> LATIN SMALL LETTER A

<b>                    /x62   <U0062> LATIN SMALL LETTER B

<c>                    /x63   <U0063> LATIN SMALL LETTER C

<d>                    /x64   <U0064> LATIN SMALL LETTER D

<e>                    /x65   <U0065> LATIN SMALL LETTER E

<f>                    /x66   <U0066> LATIN SMALL LETTER F

<g>                    /x67   <U0067> LATIN SMALL LETTER G

<h>                    /x68   <U0068> LATIN SMALL LETTER H

<i>                    /x69   <U0069> LATIN SMALL LETTER I

<j>                    /x6A   <U006A> LATIN SMALL LETTER J

<k>                    /x6B   <U006B> LATIN SMALL LETTER K

<l>                    /x6C   <U006C> LATIN SMALL LETTER L

<m>                    /x6D   <U006D> LATIN SMALL LETTER M

<n>                    /x6E   <U006E> LATIN SMALL LETTER N

<o>                    /x6F   <U006F> LATIN SMALL LETTER O

<p>                    /x70   <U0070> LATIN SMALL LETTER P

<q>                    /x71   <U0071> LATIN SMALL LETTER Q

<r>                    /x72   <U0072> LATIN SMALL LETTER R

<s>                    /x73   <U0073> LATIN SMALL LETTER S

<t>                    /x74   <U0074> LATIN SMALL LETTER T

<u>                    /x75   <U0075> LATIN SMALL LETTER U

<v>                    /x76   <U0076> LATIN SMALL LETTER V

<w>                    /x77   <U0077> LATIN SMALL LETTER W

<x>                    /x78   <U0078> LATIN SMALL LETTER X

<y>                    /x79   <U0079> LATIN SMALL LETTER Y

<z>                    /x7A   <U007A> LATIN SMALL LETTER Z

<(!!>                   /x7B   <U007B> LEFT CURLY BRACKET

<!!!!>                   /x7C   <U007C> VERTICAL LINE

<!!)>                   /x7D   <U007D> RIGHT CURLY BRACKET

<'?>                   /x7E   <U007E> TILDE

<DT>                   /x7F   <U007F> DELETE (DEL)

<.9>                   /x82   <U201A> SINGLE LOW-9 QUOTATION MARK

<f2>                   /x83   <U0192> LATIN SMALL LETTER F WITH HOOK

<:9>                   /x84   <U201E> DOUBLE LOW-9 QUOTATION MARK

<.3>                   /x85   <U2026> HORIZONTAL ELLIPSIS

<//->                  /x86   <U2020> DAGGER

<//=>                  /x87   <U2021> DOUBLE DAGGER

<1/>>                  /x88   <U02C6> MODIFIER LETTER CIRCUMFLEX ACCENT

<%0>                   /x89   <U2030> PER MILLE SIGN

<S<>                   /x8A   <U0160> LATIN CAPITAL LETTER S WITH CARON

<<1>                   /x8B   <U2039> SINGLE LEFT-POINTING ANGLE QUOTATION MARK

<OE>                   /x8C   <U0152> LATIN CAPITAL LIGATURE OE

<'6>                   /x91   <U2018> LEFT SINGLE QUOTATION MARK

<'9>                   /x92   <U2019> RIGHT SINGLE QUOTATION MARK

<'6>                   /x93   <U201C> LEFT DOUBLE QUOTATION MARK

<'9>                   /x94   <U201D> RIGHT DOUBLE QUOTATION MARK

<sb>                   /x95   <U2022> BULLET

<-N>                   /x96   <U2013> EN DASH

<-M>                   /x97   <U2014> EM DASH

<1?>                   /x98   <U02DC> SMALL TILDE

<TM>                   /x99   <U2122> TRADE MARK SIGN

<s<>                   /x9A   <U0161> LATIN SMALL LETTER S WITH CARON

</>1>                  /x9B   <U203A> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK

<oe>                   /x9C   <U0153> LATIN SMALL LIGATURE OE

<Y:>                   /x9F   <U0178> LATIN CAPITAL LETTER Y WITH DIAERESIS

<NS>                   /xA0   <U00A0> NO-BREAK SPACE

<!!I>                   /xA1   <U00A1> INVERTED EXCLAMATION MARK

<Ct>                   /xA2   <U00A2> CENT SIGN

<Pd>                   /xA3   <U00A3> POUND SIGN

<Cu>                   /xA4   <U00A4> CURRENCY SIGN

<Ye>                   /xA5   <U00A5> YEN SIGN

<BB>                   /xA6   <U00A6> BROKEN BAR

<SE>                   /xA7   <U00A7> SECTION SIGN

<':>                   /xA8   <U00A8> DIAERESIS

<Co>                   /xA9   <U00A9> COPYRIGHT SIGN

<-a>                   /xAA   <U00AA> FEMININE ORDINAL INDICATOR

<<<>                   /xAB   <U00AB> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK

<NO>                   /xAC   <U00AC> NOT SIGN

<-->                   /xAD   <U00AD> SOFT HYPHEN

<Rg>                   /xAE   <U00AE> REGISTERED SIGN

<'m>                   /xAF   <U00AF> MACRON

<DG>                   /xB0   <U00B0> DEGREE SIGN

<+->                   /xB1   <U00B1> PLUS-MINUS SIGN

<2S>                   /xB2   <U00B2> SUPERSCRIPT TWO

<3S>                   /xB3   <U00B3> SUPERSCRIPT THREE

<''>                   /xB4   <U00B4> ACUTE ACCENT

<My>                   /xB5   <U00B5> MICRO SIGN

<PI>                   /xB6   <U00B6> PILCROW SIGN

<.M>                   /xB7   <U00B7> MIDDLE DOT

<',>                   /xB8   <U00B8> CEDILLA

<1S>                   /xB9   <U00B9> SUPERSCRIPT ONE

<-o>                   /xBA   <U00BA> MASCULINE ORDINAL INDICATOR

</>/>>                 /xBB   <U00BB> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK

<14>                   /xBC   <U00BC> VULGAR FRACTION ONE QUARTER

<12>                   /xBD   <U00BD> VULGAR FRACTION ONE HALF

<34>                   /xBE   <U00BE> VULGAR FRACTION THREE QUARTERS

<?I>                   /xBF   <U00BF> INVERTED QUESTION MARK

<A!!>                   /xC0   <U00C0> LATIN CAPITAL LETTER A WITH GRAVE

<A'>                   /xC1   <U00C1> LATIN CAPITAL LETTER A WITH ACUTE

<A/>>                  /xC2   <U00C2> LATIN CAPITAL LETTER A WITH CIRCUMFLEX

<A?>                   /xC3   <U00C3> LATIN CAPITAL LETTER A WITH TILDE

<A:>                   /xC4   <U00C4> LATIN CAPITAL LETTER A WITH DIAERESIS

<AA>                   /xC5   <U00C5> LATIN CAPITAL LETTER A WITH RING ABOVE

<AE>                   /xC6   <U00C6> LATIN CAPITAL LETTER AE

<C,>                   /xC7   <U00C7> LATIN CAPITAL LETTER C WITH CEDILLA

<E!!>                   /xC8   <U00C8> LATIN CAPITAL LETTER E WITH GRAVE

<E'>                   /xC9   <U00C9> LATIN CAPITAL LETTER E WITH ACUTE

<E/>>                  /xCA   <U00CA> LATIN CAPITAL LETTER E WITH CIRCUMFLEX

<E:>                   /xCB   <U00CB> LATIN CAPITAL LETTER E WITH DIAERESIS

<I!!>                   /xCC   <U00CC> LATIN CAPITAL LETTER I WITH GRAVE

<I'>                   /xCD   <U00CD> LATIN CAPITAL LETTER I WITH ACUTE

<I/>>                  /xCE   <U00CE> LATIN CAPITAL LETTER I WITH CIRCUMFLEX

<I:>                   /xCF   <U00CF> LATIN CAPITAL LETTER I WITH DIAERESIS

<D->                   /xD0   <U00D0> LATIN CAPITAL LETTER ETH (Icelandic)

<N?>                   /xD1   <U00D1> LATIN CAPITAL LETTER N WITH TILDE

<O!!>                   /xD2   <U00D2> LATIN CAPITAL LETTER O WITH GRAVE

<O'>                   /xD3   <U00D3> LATIN CAPITAL LETTER O WITH ACUTE

<O/>>                  /xD4   <U00D4> LATIN CAPITAL LETTER O WITH CIRCUMFLEX

<O?>                   /xD5   <U00D5> LATIN CAPITAL LETTER O WITH TILDE

<O:>                   /xD6   <U00D6> LATIN CAPITAL LETTER O WITH DIAERESIS

<*X>                   /xD7   <U00D7> MULTIPLICATION SIGN

<O//>                  /xD8   <U00D8> LATIN CAPITAL LETTER O WITH STROKE

<U!!>                   /xD9   <U00D9> LATIN CAPITAL LETTER U WITH GRAVE

<U'>                   /xDA   <U00DA> LATIN CAPITAL LETTER U WITH ACUTE

<U/>>                  /xDB   <U00DB> LATIN CAPITAL LETTER U WITH CIRCUMFLEX

<U:>                   /xDC   <U00DC> LATIN CAPITAL LETTER U WITH DIAERESIS

<Y'>                   /xDD   <U00DD> LATIN CAPITAL LETTER Y WITH ACUTE

<TH>                   /xDE   <U00DE> LATIN CAPITAL LETTER THORN (Icelandic)

<ss>                   /xDF   <U00DF> LATIN SMALL LETTER SHARP S (German)

<a!!>                   /xE0   <U00E0> LATIN SMALL LETTER A WITH GRAVE

<a'>                   /xE1   <U00E1> LATIN SMALL LETTER A WITH ACUTE

<a/>>                  /xE2   <U00E2> LATIN SMALL LETTER A WITH CIRCUMFLEX

<a?>                   /xE3   <U00E3> LATIN SMALL LETTER A WITH TILDE

<a:>                   /xE4   <U00E4> LATIN SMALL LETTER A WITH DIAERESIS

<aa>                   /xE5   <U00E5> LATIN SMALL LETTER A WITH RING ABOVE

<ae>                   /xE6   <U00E6> LATIN SMALL LETTER AE

<c,>                   /xE7   <U00E7> LATIN SMALL LETTER C WITH CEDILLA

<e!!>                   /xE8   <U00E8> LATIN SMALL LETTER E WITH GRAVE

<e'>                   /xE9   <U00E9> LATIN SMALL LETTER E WITH ACUTE

<e/>>                  /xEA   <U00EA> LATIN SMALL LETTER E WITH CIRCUMFLEX

<e:>                   /xEB   <U00EB> LATIN SMALL LETTER E WITH DIAERESIS

<i!!>                   /xEC   <U00EC> LATIN SMALL LETTER I WITH GRAVE

<i'>                   /xED   <U00ED> LATIN SMALL LETTER I WITH ACUTE

<i/>>                  /xEE   <U00EE> LATIN SMALL LETTER I WITH CIRCUMFLEX

<i:>                   /xEF   <U00EF> LATIN SMALL LETTER I WITH DIAERESIS

<d->                   /xF0   <U00F0> LATIN SMALL LETTER ETH (Icelandic)

<n?>                   /xF1   <U00F1> LATIN SMALL LETTER N WITH TILDE

<o!!>                   /xF2   <U00F2> LATIN SMALL LETTER O WITH GRAVE

<o'>                   /xF3   <U00F3> LATIN SMALL LETTER O WITH ACUTE

<o/>>                  /xF4   <U00F4> LATIN SMALL LETTER O WITH CIRCUMFLEX

<o?>                   /xF5   <U00F5> LATIN SMALL LETTER O WITH TILDE

<o:>                   /xF6   <U00F6> LATIN SMALL LETTER O WITH DIAERESIS

<-:>                   /xF7   <U00F7> DIVISION SIGN

<o//>                  /xF8   <U00F8> LATIN SMALL LETTER O WITH STROKE

<u!!>                   /xF9   <U00F9> LATIN SMALL LETTER U WITH GRAVE

<u'>                   /xFA   <U00FA> LATIN SMALL LETTER U WITH ACUTE

<u/>>                  /xFB   <U00FB> LATIN SMALL LETTER U WITH CIRCUMFLEX

<u:>                   /xFC   <U00FC> LATIN SMALL LETTER U WITH DIAERESIS

<y'>                   /xFD   <U00FD> LATIN SMALL LETTER Y WITH ACUTE

<th>                   /xFE   <U00FE> LATIN SMALL LETTER THORN (Icelandic)

<y:>                   /xFF   <U00FF> LATIN SMALL LETTER Y WITH DIAERESIS

END CHARMAP

"

! !

!MS_Ansi class methodsFor:'queries'!

maxCode

    ^ 65535 

!

minCode

    ^ 0 

! !

!MS_Ansi methodsFor:'encoding & decoding'!

decode:codeArg

    |code "{ Class: SmallInteger }" t|

    code := codeArg.

    code <= 16r7F ifTrue:[ ^ code ].

    code >= 16rA0 ifTrue:[

        ^ codeArg.

    ].

    "similar to 8859-1 with different chars in the 8x..9x area"

    "we map CP1252 chars to unicode chars"

    t := #(

       "16r0080"    16r20AC " EURO character " 

       "16r0081"    16r0000 " invalid " 

       "16r0082"    16r201A " SINGLE LOW-9 QUOTATION MARK " 

       "16r0083"    16r0192 " LATIN SMALL LETTER F WITH HOOK " 

       "16r0084"    16r201E " DOUBLE LOW-9 QUOTATION MARK " 

       "16r0085"    16r2026 " HORIZONTAL ELLIPSIS " 

       "16r0086"    16r2020 " DAGGER " 

       "16r0087"    16r2021 " DOUBLE DAGGER " 

       "16r0088"    16r02C6 " MODIFIER LETTER CIRCUMFLEX ACCENT " 

       "16r0089"    16r2030 " PER MILLE SIGN " 

       "16r008A"    16r0160 " LATIN CAPITAL LETTER S WITH CARON " 

       "16r008B"    16r2039 " SINGLE LEFT-POINTING ANGLE QUOTATION MARK " 

       "16r008C"    16r0152 " LATIN CAPITAL LIGATURE OE " 

       "16r008D"    16r0000 " invalid " 

       "16r008E"    16r017D " LATIN CAPITAL Z WITH INVERSE CARON" 

       "16r008F"    16r0000 " invalid " 

       "16r0090"    16r0000 " invalid " 

       "16r0091"    16r2018 " LEFT SINGLE QUOTATION MARK " 

       "16r0092"    16r2019 " RIGHT SINGLE QUOTATION MARK " 

       "16r0093"    16r201C " LEFT DOUBLE QUOTATION MARK " 

       "16r0094"    16r201D " RIGHT DOUBLE QUOTATION MARK " 

       "16r0095"    16r2022 " BULLET " 

       "16r0096"    16r2013 " EN DASH " 

       "16r0097"    16r2014 " EM DASH " 

       "16r0098"    16r02DC " SMALL TILDE " 

       "16r0099"    16r2122 " TRADE MARK SIGN " 

       "16r009A"    16r0161 " LATIN SMALL LETTER S WITH CARON " 

       "16r009B"    16r203A " SINGLE RIGHT-POINTING ANGLE QUOTATION MARK " 

       "16r009C"    16r0153 " LATIN SMALL LIGATURE OE " 

       "16r009D"    16r0000 " invalid " 

       "16r009E"    16r017E " LATIN SMALL LETTER Z WITH INVERSE CARON " 

       "16r009F"    16r0178 " LATIN CAPITAL LETTER Y WITH DIAERESIS " 

       ) at:(code - 16r7F).

    t == 0 ifFalse:[^ t].

    ^ self decodingError.

    "Modified (format): / 12-07-2012 / 14:06:56 / cg"

!

decodeString:anEncodedStringOrByteCollection

    "given a string in my encoding, return a unicode-string for it"

    |newString myCode code bits size "{ Class:SmallInteger }"|

    size := anEncodedStringOrByteCollection size.

    newString := String new:size.

    bits := newString bitsPerCharacter.

    1 to:size do:[:idx |

        code := (anEncodedStringOrByteCollection at:idx) codePoint.

        myCode := self decode:code.

        myCode > 16rFF ifTrue:[

            myCode > 16rFFFF ifTrue:[

                bits < 32 ifTrue:[

                    newString := Unicode32String fromString:newString.

                    bits := 32.

                ]

            ] ifFalse:[

                bits < 16 ifTrue:[

                    newString := Unicode16String fromString:newString.

                    bits := 16.

                ]

            ]

        ].

        newString at:idx put:(Character codePoint:myCode).

    ].

    ^ newString

    "

     CharacterEncoderImplementations::ISO8859_1 decodeString:'hello'

    "

    "Created: / 16-01-2018 / 19:54:02 / stefan"

    "Modified (format): / 17-01-2018 / 16:30:59 / stefan"

!

encode:unicodeArg

    |unicode "{ Class: SmallInteger }" t|

    "/ the comment in mh... is not correct.

    false ifTrue:[

        "/ mh - it seems that microsoft has fixed ms-ansi to be unicode compatible

        "/ with XP, Vista etc.

        "/ as W95 is not supported anyhow, simply return identity here...

        ^ unicodeArg.

    ].

    "we map unicode chars to CP1252 where a mapping exists.

     If no mapping exists, we keep the unicode char"

    unicode := unicodeArg.

    unicode > 16r2122 ifTrue:[

        ^ unicode.

    ].

    unicode <= 16r151 ifTrue:[

        ^ unicode

    ].

    unicode <= 16r2DC ifTrue:[

        unicode <= 16r192 ifTrue:[

            unicode <= 16r178 ifTrue:[

                unicode <= 16r161 ifTrue:[

                    t := #[

                       "16r0152"    16r8C " LATIN CAPITAL LIGATURE OE " 

                       "16r0153"    16r9C " LATIN SMALL LIGATURE OE " 

                       "16r0154"    16r00 " keep unicode " 

                       "16r0155"    16r00 " keep unicode " 

                       "16r0156"    16r00 " keep unicode " 

                       "16r0157"    16r00 " keep unicode " 

                       "16r0158"    16r00 " keep unicode " 

                       "16r0159"    16r00 " keep unicode " 

                       "16r015A"    16r00 " keep unicode " 

                       "16r015B"    16r00 " keep unicode " 

                       "16r015C"    16r00 " keep unicode " 

                       "16r015D"    16r00 " keep unicode " 

                       "16r015E"    16r00 " keep unicode " 

                       "16r015F"    16r00 " keep unicode " 

                       "16r0160"    16r8A " LATIN CAPITAL LETTER S WITH CARON " 

                       "16r0161"    16r9A " LATIN SMALL LETTER S WITH CARON " 

                       ] at:(unicode - 16r151).

                    t == 0 ifFalse:[^ t].

                    ^ unicode

                ].

                unicode <= 16r177 ifTrue:[

                    ^ unicode

                ].

                ^  "16r0178" 16r009F " LATIN CAPITAL LETTER Y WITH DIAERESIS " 

            ].

            unicode <= 16r191 ifTrue:[

                ^ unicode

            ].

            ^  "16r0192" 16r0083 " LATIN SMALL LETTER F WITH HOOK " 

        ].

        unicode <= 16r2C5 ifTrue:[

            ^ unicode

        ].

        unicode == 16r2C6 ifTrue:[

            ^  "16r02C6" 16r0088 " MODIFIER LETTER CIRCUMFLEX ACCENT " 

        ].

        unicode <= 16r2DB ifTrue:[

            ^ unicode

        ].

        ^  "16r02DC" 16r0098 " SMALL TILDE " 

    ].

    unicode <= 16r2012 ifTrue:[

        ^ unicode

    ].

    unicode <= 16r203A ifTrue:[