CharacterEncoder.st
author Michael Beyl <mb@exept.de>
Wed, 11 Jul 2012 13:38:13 +0200
changeset 14174 3a4f041c94a2
parent 14169 eab487f07a2b
child 14188 9ff8607b11a4
permissions -rw-r--r--
changed: #supportedExternalEncodings cp1251 encoding added
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
8048
293c8178c6eb utf8 errors
Claus Gittinger <cg@exept.de>
parents: 8033
diff changeset
     1
"
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     2
 COPYRIGHT (c) 2004 by eXept Software AG
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
     3
	      All Rights Reserved
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     4
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     5
 This software is furnished under a license and may be used
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     6
 only in accordance with the terms of that license and with the
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     7
 inclusion of the above copyright notice.   This software may not
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     8
 be provided or otherwise made available to, or used by, any
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
     9
 other person.  No title to or ownership of the software is
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    10
 hereby transferred.
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    11
"
8114
05274a80fcc4 separated implementation into dynamically (lazy) loaded classes
Claus Gittinger <cg@exept.de>
parents: 8105
diff changeset
    12
"{ Package: 'stx:libbasic' }"
05274a80fcc4 separated implementation into dynamically (lazy) loaded classes
Claus Gittinger <cg@exept.de>
parents: 8105
diff changeset
    13
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
    14
Object subclass:#CharacterEncoder
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    15
	instanceVariableNames:''
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
    16
	classVariableNames:'EncoderClassesByName EncodersByName CachedEncoders LastEncoder
8122
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
    17
		AccessLock NullEncoderInstance Jis7KanjiEscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
    18
		Jis7RomanEscapeSequence JisISO2022EscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
    19
		Jis7KanjiOldEscapeSequence'
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    20
	poolDictionaries:''
8114
05274a80fcc4 separated implementation into dynamically (lazy) loaded classes
Claus Gittinger <cg@exept.de>
parents: 8105
diff changeset
    21
	category:'Collections-Text-Encodings'
7969
1c252e9cf79c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7967
diff changeset
    22
!
1c252e9cf79c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7967
diff changeset
    23
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    24
CharacterEncoder subclass:#CompoundEncoder
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    25
	instanceVariableNames:'decoder encoder'
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    26
	classVariableNames:''
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    27
	poolDictionaries:''
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    28
	privateIn:CharacterEncoder
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    29
!
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    30
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    31
CharacterEncoder subclass:#DefaultEncoder
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    32
	instanceVariableNames:''
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    33
	classVariableNames:''
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    34
	poolDictionaries:''
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    35
	privateIn:CharacterEncoder
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    36
!
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    37
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    38
CharacterEncoder subclass:#InverseEncoder
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    39
	instanceVariableNames:'decoder'
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    40
	classVariableNames:''
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
    41
	poolDictionaries:''
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    42
	privateIn:CharacterEncoder
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    43
!
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    44
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    45
CharacterEncoder subclass:#NullEncoder
7893
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    46
	instanceVariableNames:''
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    47
	classVariableNames:''
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    48
	poolDictionaries:''
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    49
	privateIn:CharacterEncoder
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    50
!
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    51
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    52
CharacterEncoder subclass:#OtherEncoding
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    53
	instanceVariableNames:''
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    54
	classVariableNames:''
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    55
	poolDictionaries:''
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    56
	privateIn:CharacterEncoder
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    57
!
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
    58
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    59
CharacterEncoder subclass:#TwoStepEncoder
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    60
	instanceVariableNames:'encoder1 encoder2'
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    61
	classVariableNames:''
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    62
	poolDictionaries:''
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    63
	privateIn:CharacterEncoder
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    64
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
    65
7893
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    66
!CharacterEncoder class methodsFor:'documentation'!
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    67
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    68
copyright
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    69
"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    70
 COPYRIGHT (c) 2004 by eXept Software AG
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
    71
	      All Rights Reserved
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    72
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    73
 This software is furnished under a license and may be used
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    74
 only in accordance with the terms of that license and with the
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    75
 inclusion of the above copyright notice.   This software may not
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    76
 be provided or otherwise made available to, or used by, any
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    77
 other person.  No title to or ownership of the software is
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    78
 hereby transferred.
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    79
"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    80
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    81
7893
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    82
documentation
80df105ac17c checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7892
diff changeset
    83
"
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    84
    unfinished code - please read howToAddMoreCoders.
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    85
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    86
    Character mappings are based on information in character maps found at either:
8226
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    87
        http://std.dkuug.dk/i18n/charmaps
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    88
    or:
8226
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    89
        http://www.unicode.org/Public/MAPPINGS
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    90
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
    91
    No Warranty.
8226
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    92
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    93
    All the ISO 8859 codesets include ASCII as a proper codeset within them: 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    94
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    95
    ISO 8859-1: Latin 1 - Western European Languages. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    96
    ISO 8859-2: Latin 2 - Eastern European Languages. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    97
    ISO 8859-3: Latin 3 - Afrikaans, Catalan, Dutch, English, Esperanto, German, 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    98
                          Italian, Maltese, Spanish and Turkish. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
    99
    ISO 8859-4: Latin 4 - Danish, English, Estonian, Finnish, German, Greenlandic, Lappish and Latvian. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   100
    ISO 8859-5: Latin/Cyrillic - Bulgarian, Byelorussian, English, Macedonian, Russian, Serbo-Croat and Ukranian. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   101
    ISO 8859-6: Latin/Arabic - Arabic. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   102
    ISO 8859-7: Latin/Greek - Greek. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   103
    ISO 8859-8: Latin/Hebrew - Hebrew. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   104
    ISO 8859-9: Latin 5 - Danish, Dutch, English, Finnish, French, German, Irish, Italian, 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   105
                          Norwegian, Portuguese, Spanish, Swedish and Turkish. 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   106
    ISO 8859-10: Latin 6 - Danish, English, Estonian, Finnish, German, Greenlandic, Icelandic, 
81d95cffe5be *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8214
diff changeset
   107
                          Sami (Lappish), Latvian, Lithuanian, Norwegian, Faroese and Swedish.
8810
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
   108
    [author:]
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
   109
        Claus Gittinger
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   110
"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   111
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   112
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   113
examples
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   114
"
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   115
                                                                        [exBegin]                                                     
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   116
    |s1 s2|
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   117
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   118
    s1 := 'hello'.
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   119
    s2 := CharacterEncoder encodeString:s1 from:#'iso8859-1' into:#'unicode'.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   120
    s2       
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   121
                                                                        [exEnd]                                                     
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   122
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   123
                                                                        [exBegin]                                                     
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   124
    |s1 s2|
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   125
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   126
    s1 := 'hello'.
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   127
    s2 := CharacterEncoder encodeString:s1 from:#'iso8859-1' into:#'iso8859-7'.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   128
    s2      
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   129
                                                                        [exEnd]                                                     
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   130
"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   131
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   132
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   133
howToAddMoreCoders
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   134
"
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   135
    Coders can be hand-written or automagically generated via a mapping table.
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   136
    Examples for hand-written coders are UTF8_to_ISO10464 or JIS0208_to_JIS7.
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   137
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   138
    The table driven encode/decode methods can be generated from a character mapping document
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   139
    as found on the unicode consortium host
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   140
        (for example: 'http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT')
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   141
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   142
    or from the i18n character maps:
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   143
        (for example: 'http://std.dkuug.dk/i18n/charmaps/ISO-8859-1
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   144
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   145
    In order to add another coder (for example: for EBCDIC or ms-codePage 278),
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   146
    perform the following steps:
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   147
        - create a private subclass of CharacterEncoder named (for example) CP267.
8114
05274a80fcc4 separated implementation into dynamically (lazy) loaded classes
Claus Gittinger <cg@exept.de>
parents: 8105
diff changeset
   148
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   149
        - create a public subclass of CharacterEncoderImplementations::CharacterEncoderImplementation named (for example) CharacterEncoderImplementations::CP267.
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   150
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   151
        - define the mappingURL1_relativeName (if the table is found on 'www.unicode.org')
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   152
          or the mappingURL2_relativeName (if it is found on 'std.dkuug.dk') method, which
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   153
          should return the name of the tables file, relative to the top directory there
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   154
          (which is '.../Public/MAPPINGS' on www.unicode.org and '.../i18n/charmaops' on 'std.dkuug.dk'.
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   155
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   156
          In this example, the table from 'std.dkuug.dk' is used, and named 'EBCDIC-CP-FI' there.
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   157
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   158
        - generate code by evaluating:
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   159
            CharacterEncoder::CP267 generateCode
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   160
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   161
    Thats all !!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   162
7909
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   163
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   164
    The existing code was generated by:
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   165
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   166
        CharacterEncoder::SingleByteEncoder subclassesDo:[:cls | Transcript showCR:cls name. cls flushCode; generateCode ]
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   167
        CharacterEncoder::SingleByteEncoder subclassesDo:[:cls | cls allSubclassesDo:[:sub | Transcript showCR:sub name. sub flushCode; generateSubclassCode]]
7909
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   168
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   169
    or individually:
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   170
        CharacterEncoder::ASCII flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   171
        CharacterEncoder::ISO8859_1 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   172
        CharacterEncoder::ISO8859_2 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   173
        CharacterEncoder::ISO8859_3 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   174
        CharacterEncoder::ISO8859_4 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   175
        CharacterEncoder::ISO8859_5 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   176
        CharacterEncoder::ISO8859_6 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   177
        CharacterEncoder::ISO8859_7 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   178
        CharacterEncoder::ISO8859_8 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   179
        CharacterEncoder::ISO8859_9 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   180
        CharacterEncoder::ISO8859_10 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   181
        CharacterEncoder::ISO8859_11 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   182
        CharacterEncoder::ISO8859_13 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   183
        CharacterEncoder::ISO8859_14 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   184
        CharacterEncoder::ISO8859_15 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   185
        CharacterEncoder::ISO8859_16 flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   186
        CharacterEncoder::KOI8_R flushCode; generateCode.
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   187
        CharacterEncoder::GSM0338 flushCode; generateCode.
7909
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   188
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   189
        CharacterEncoder::KOI8_U flushCode; generateSubclassCode.
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   190
9143
28eeea2f0112 comments
Claus Gittinger <cg@exept.de>
parents: 9064
diff changeset
   191
        CharacterEncoder::JIS0208 flushCode; generateCode.
13072
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   192
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   193
    Please check if your encoder tables are complete; for example, with:
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   194
        0 to:255 do:[:ebc |
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   195
            |asc ebc2|
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   196
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   197
            asc := CharacterEncoderImplementations::EBCDIC new decode:ebc.
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   198
            asc notNil ifTrue:[
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   199
               ebc2 := CharacterEncoderImplementations::EBCDIC new encode:asc.
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   200
               self assert:(ebc2 = ebc)
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   201
            ].
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   202
        ].
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   203
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   204
        0 to:255 do:[:asc |
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   205
            |ebc asc2|
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   206
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   207
            ebc := CharacterEncoderImplementations::EBCDIC new encode:asc.
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   208
            ebc notNil ifTrue:[
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   209
               asc2 := CharacterEncoderImplementations::EBCDIC new decode:ebc.
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   210
               self assert:(asc2 = asc)
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   211
            ].
e189e07c16aa changed: #howToAddMoreCoders
Claus Gittinger <cg@exept.de>
parents: 13063
diff changeset
   212
        ].
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   213
"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   214
! !
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   215
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   216
!CharacterEncoder class methodsFor:'instance creation'!
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   217
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   218
encoderFor:encodingNameSymbol
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   219
    "given the name of an encoding, return an encoder-instance which can map these from/into unicode."
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   220
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   221
    ^ self
8156
bd5169c15b31 *** empty log message ***
ca
parents: 8155
diff changeset
   222
        encoderFor:encodingNameSymbol 
bd5169c15b31 *** empty log message ***
ca
parents: 8155
diff changeset
   223
        ifAbsent:[
bd5169c15b31 *** empty log message ***
ca
parents: 8155
diff changeset
   224
            "/ proceed to ignore this error in the future.    
8352
20d2476f538e add nullEncoder BEFORE raising an error
Claus Gittinger <cg@exept.de>
parents: 8262
diff changeset
   225
20d2476f538e add nullEncoder BEFORE raising an error
Claus Gittinger <cg@exept.de>
parents: 8262
diff changeset
   226
            (EncodersByName at:#unicode) at:encodingNameSymbol put:NullEncoderInstance. 
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   227
            (EncoderClassesByName at:#unicode) at:encodingNameSymbol put:NullEncoder.    
8352
20d2476f538e add nullEncoder BEFORE raising an error
Claus Gittinger <cg@exept.de>
parents: 8262
diff changeset
   228
8388
b5cf7abdfe64 no encoder: send a message to stdError instead of entering
Claus Gittinger <cg@exept.de>
parents: 8352
diff changeset
   229
            "/ self error:'no encoder for ' , encodingNameSymbol mayProceed:true.
13325
5dba5cb58029 changed: #encoderFor:
Claus Gittinger <cg@exept.de>
parents: 13072
diff changeset
   230
            ('CharacterEncoder [warning]: no encoder for ' , encodingNameSymbol) infoPrintCR.
8388
b5cf7abdfe64 no encoder: send a message to stdError instead of entering
Claus Gittinger <cg@exept.de>
parents: 8352
diff changeset
   231
            
8156
bd5169c15b31 *** empty log message ***
ca
parents: 8155
diff changeset
   232
            NullEncoderInstance
bd5169c15b31 *** empty log message ***
ca
parents: 8155
diff changeset
   233
        ]
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   234
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   235
    "
8388
b5cf7abdfe64 no encoder: send a message to stdError instead of entering
Claus Gittinger <cg@exept.de>
parents: 8352
diff changeset
   236
     CharacterEncoder encoderFor:#'blabla2'       
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   237
     CharacterEncoder encoderFor:#'latin1'       
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   238
     self encoderFor:#'arabic'       
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   239
     self encoderFor:#'ms-arabic'       
8814
501f04d1f533 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8810
diff changeset
   240
     self encoderFor:#'cp1250'       
501f04d1f533 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8810
diff changeset
   241
     self encoderFor:#'cp1251'       
501f04d1f533 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8810
diff changeset
   242
     self encoderFor:#'cp1252'       
501f04d1f533 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8810
diff changeset
   243
     self encoderFor:#'cp1253'       
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   244
     self encoderFor:#'iso8859-5'    
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   245
     self encoderFor:#'koi8-r'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   246
     self encoderFor:#'koi8-u'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   247
     self encoderFor:#'jis0208'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   248
     self encoderFor:#'jis7'      
8087
0a2ee76bcf55 last version before separating into extra classes
Claus Gittinger <cg@exept.de>
parents: 8062
diff changeset
   249
     self encoderFor:#'utf8'      
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   250
     (self encoderFor:#'utf16le') encodeString:'hello'      
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   251
     (self encoderFor:#'utf16le') encode:5    
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   252
     (self encoderFor:#'utf16be') encodeString:'hello'      
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   253
     (self encoderFor:#'utf16be') encode:5      
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   254
     (self encoderFor:#'utf32le') encodeString:'hello'      
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   255
     (self encoderFor:#'utf32be') encodeString:'hello'      
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   256
     self encoderFor:#'sgml'      
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   257
     self encoderFor:#'java'      
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   258
    "
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   259
13325
5dba5cb58029 changed: #encoderFor:
Claus Gittinger <cg@exept.de>
parents: 13072
diff changeset
   260
    "Modified: / 01-04-2011 / 14:27:22 / cg"
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   261
!
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   262
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   263
encoderFor:encodingNameSymbolArg ifAbsent:exceptionValue
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   264
    "given the name of an encoding, return an encoder-instance which can map these from/into unicode."
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   265
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   266
    |encodingNameSymbol enc clsName cls lcName name unicodeEncoders unicodeEncoderClasses|
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   267
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   268
    encodingNameSymbol := encodingNameSymbolArg.
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   269
    encodingNameSymbol isNil ifTrue:[ ^ NullEncoderInstance].
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   270
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   271
    encodingNameSymbol == #'iso10646-1' ifTrue:[ encodingNameSymbol := #unicode].
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   272
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   273
    lcName := encodingNameSymbol asLowercase.
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   274
    name := lcName asSymbolIfInterned.
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   275
    name isNil ifTrue:[name := lcName].
8052
4ca96b117b21 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 8048
diff changeset
   276
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   277
    name includesMatchCharacters ifTrue:[
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   278
        AccessLock critical:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   279
            unicodeEncoders := EncodersByName at:#unicode ifAbsent:nil.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   280
        ].
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   281
        unicodeEncoders notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   282
            unicodeEncoders keysAndValuesDo:[:eachEncodingAlias :eachEncoderInstance |
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   283
                (name matches:eachEncodingAlias) ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   284
                    ^ eachEncoderInstance.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   285
                ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   286
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   287
        ].
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   288
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   289
        AccessLock critical:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   290
            unicodeEncoderClasses := EncoderClassesByName at:#unicode.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   291
        ].
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   292
        unicodeEncoderClasses notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   293
            unicodeEncoderClasses keysAndValuesDo:[:eachEncodingAlias :eachEncoderClassOrName |
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   294
                (name matches:eachEncodingAlias) ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   295
                    eachEncoderClassOrName isBehavior ifTrue:[
8194
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   296
                        cls := eachEncoderClassOrName
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   297
                    ] ifFalse:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   298
                        cls := CharacterEncoderImplementations at:eachEncoderClassOrName.
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   299
                    ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   300
                    cls notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   301
                        ^ cls new.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   302
                    ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   303
                ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   304
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   305
        ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   306
        ^ exceptionValue value
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   307
    ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   308
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   309
    AccessLock critical:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   310
        unicodeEncoders := EncodersByName at:#unicode ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   311
        unicodeEncoders isNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   312
            EncodersByName at:#unicode put:(unicodeEncoders := Dictionary new).
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   313
        ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   314
        enc := unicodeEncoders at:name ifAbsent:nil.
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   315
    ].
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   316
    enc isNil ifTrue:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   317
        AccessLock critical:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   318
            unicodeEncoderClasses := EncoderClassesByName at:#unicode ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   319
            unicodeEncoderClasses isNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   320
                EncoderClassesByName at:#unicode put:(unicodeEncoderClasses := Dictionary new).
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   321
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   322
            clsName := unicodeEncoderClasses at:name ifAbsent:nil.
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   323
        ].
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   324
        clsName notNil ifTrue:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   325
            clsName isBehavior ifTrue:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   326
                cls := clsName
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   327
            ] ifFalse:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   328
                cls := CharacterEncoderImplementations at:clsName.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   329
            ].
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   330
            cls notNil ifTrue:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   331
                enc := cls new.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   332
                AccessLock critical:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   333
                    unicodeEncoders at:name put:enc.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   334
                ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   335
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   336
        ].
7973
6dea491d56f7 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7972
diff changeset
   337
    ].
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   338
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   339
    enc notNil ifTrue:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   340
        ^ enc 
7973
6dea491d56f7 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7972
diff changeset
   341
    ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   342
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   343
    "/ no direct encoder from unicode->name
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   344
    "/ search for unicode->any and: any->name
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   345
    AccessLock critical:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   346
        unicodeEncoderClasses := EncoderClassesByName at:#unicode ifAbsent:nil.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   347
    ].
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   348
    unicodeEncoderClasses keysAndValuesDo:[:eachEncodingAlias :eachEncoderClass |
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   349
        |dict2 enc1 enc2|
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   350
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   351
        AccessLock critical:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   352
            dict2 := EncoderClassesByName at:eachEncodingAlias ifAbsent:nil.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   353
        ].
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   354
        dict2 notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   355
            clsName := dict2 at:name ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   356
            clsName notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   357
                clsName isBehavior ifTrue:[
8194
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   358
                    cls := clsName
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   359
                ] ifFalse:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   360
                    cls := CharacterEncoderImplementations at:clsName.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   361
                ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   362
                cls notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   363
                    enc2 := cls new.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   364
                    enc1 := self encoderFor:eachEncodingAlias.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   365
                    (enc1 notNil and:[enc2 notNil]) ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   366
                        enc := TwoStepEncoder new encoder1:enc1 encoder2:enc2.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   367
                        AccessLock critical:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   368
                            unicodeEncoders at:name put:enc.    
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   369
                        ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   370
                        ^ enc.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   371
                    ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   372
                ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   373
            ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   374
        ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   375
    ].
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   376
8194
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   377
    EncoderClassesByName keysAndValuesDo:[:encoding1 :dict1 |
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   378
        dict1 keysAndValuesDo:[:encoding2 :clsName1|
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   379
            |clsName2 cls1 cls2 dict2 enc1 enc2|
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   380
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   381
            encoding2 = encodingNameSymbol ifTrue:[
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   382
                AccessLock critical:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   383
                    dict2 := EncoderClassesByName at:#unicode.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   384
                ].
8194
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   385
                clsName2 := dict2 at:encoding1 ifAbsent:nil.
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   386
                clsName2 notNil ifTrue:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   387
                    clsName1 isBehavior ifTrue:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   388
                        cls1 := clsName1
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   389
                    ] ifFalse:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   390
                        cls1 := CharacterEncoderImplementations at:clsName1.
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   391
                    ].
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   392
                    clsName2 isBehavior ifTrue:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   393
                        cls2 := clsName2
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   394
                    ] ifFalse:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   395
                        cls2 := CharacterEncoderImplementations at:clsName2.
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   396
                    ].
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   397
                    (cls1 notNil and:[cls2 notNil]) ifTrue:[
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   398
                        enc := TwoStepEncoder new encoder1:enc1 encoder2:enc2.
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   399
                        ^ enc.
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   400
                    ].
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   401
                ]
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   402
            ]
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   403
        ]
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   404
    ].
7027457dbe4f *** empty log message ***
ca
parents: 8190
diff changeset
   405
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   406
    ^ exceptionValue value
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   407
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   408
    "
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   409
     CharacterEncoder encoderFor:#'latin1'       
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   410
     self encoderFor:#'arabic'              
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   411
     self encoderFor:#'ms-arabic'           
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   412
     self encoderFor:#'iso8859-5'           
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   413
     self encoderFor:#'koi8-r'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   414
     self encoderFor:#'koi8-u'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   415
     self encoderFor:#'jis0208'      
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   416
     self encoderFor:#'jis7'      
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   417
     self encoderFor:#'unicode'      
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   418
    "
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   419
!
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   420
8210
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   421
encoderForUTF8
8211
c4377c6c20e4 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8210
diff changeset
   422
    "return an encoder-instance which can map unicode into/from utf8"
c4377c6c20e4 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8210
diff changeset
   423
8210
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   424
    ^ self encoderFor:#utf8
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   425
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   426
    "
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   427
     CharacterEncoder encoderFor:#'latin1'       
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   428
     self encoderFor:#'arabic'       
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   429
     self encoderFor:#'ms-arabic'       
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   430
     self encoderFor:#'iso8859-5'    
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   431
     self encoderFor:#'koi8-r'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   432
     self encoderFor:#'koi8-u'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   433
     self encoderFor:#'jis0208'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   434
     self encoderFor:#'jis7'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   435
     self encoderFor:#'utf8'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   436
     self encoderForUTF8'      
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   437
    "
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   438
!
cac1802b8603 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8194
diff changeset
   439
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   440
encoderToEncodeFrom:oldEncodingArg into:newEncodingArg
8135
f22398526ae2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8134
diff changeset
   441
    |oldEncoding newEncoding encoders encoderClasses encoder decoder clsName cls|
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   442
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   443
    oldEncoding := oldEncodingArg ? #unicode.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   444
    oldEncoding == #'iso10646-1' ifTrue:[ oldEncoding :=  #unicode].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   445
    newEncoding := newEncodingArg ? #unicode.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   446
    newEncoding == #'iso10646-1' ifTrue:[ newEncoding :=  #unicode].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   447
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   448
    oldEncoding = newEncoding ifTrue:[^ NullEncoderInstance].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   449
    (oldEncoding match:newEncoding) ifTrue:[^ NullEncoderInstance].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   450
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   451
    (oldEncoding = #unicode) ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   452
        "/ something -> unicode 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   453
        ^ self encoderFor:newEncoding.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
   454
    ].
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   455
8261
af6485d43bd2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8226
diff changeset
   456
    oldEncoding isSymbol ifFalse:[oldEncoding := oldEncoding asSymbol].
af6485d43bd2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8226
diff changeset
   457
    newEncoding isSymbol ifFalse:[newEncoding := newEncoding asSymbol].
8120
bafc72f60618 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8119
diff changeset
   458
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   459
    AccessLock critical:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   460
        encoders := EncodersByName at:oldEncoding ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   461
        encoders isNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   462
            EncodersByName at:oldEncoding put:(encoders := Dictionary new).
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   463
        ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   464
        encoder := encoders at:newEncodingArg ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   465
        encoder isNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   466
            encoderClasses := EncoderClassesByName at:oldEncoding ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   467
            encoderClasses isNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   468
                EncoderClassesByName at:oldEncoding put:(encoderClasses := Dictionary new).
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   469
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   470
            clsName := encoderClasses at:newEncoding ifAbsent:nil.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   471
            clsName notNil ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   472
                clsName isBehavior ifTrue:[
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   473
                    cls := clsName
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   474
                ] ifFalse:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   475
                    cls := CharacterEncoderImplementations at:clsName.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   476
                ]
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   477
            ].
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   478
        ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   479
    ].
8262
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   480
    cls notNil ifTrue:[
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   481
        encoder := cls new.
550c67712dfa do not autoload while in accesslock (deadlock)
Claus Gittinger <cg@exept.de>
parents: 8261
diff changeset
   482
    ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   483
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   484
    encoder isNil ifTrue:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   485
        (newEncoding == #unicode) ifTrue:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   486
            "/ something -> unicode 
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   487
            decoder := self encoderFor:oldEncoding.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   488
            encoder := InverseEncoder new decoder:decoder.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   489
        ] ifFalse:[
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   490
            "/ do it as: oldEncoding -> unicode -> newEncoding
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   491
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   492
            "/ something -> unicode 
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   493
            decoder := self encoderFor:oldEncoding.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   494
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   495
            "/ unicode -> something
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   496
            encoder := self encoderFor:newEncoding.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   497
            encoder := CompoundEncoder new encoder:encoder decoder:decoder.
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   498
        ].
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   499
    ].
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   500
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   501
    AccessLock critical:[
8155
5c67868ddc38 *** empty log message ***
ca
parents: 8154
diff changeset
   502
        (EncodersByName at:oldEncoding) at:newEncoding put:encoder
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   503
    ].
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   504
    ^ encoder
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   505
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   506
    "   CharacterEncoder initialize
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   507
     CharacterEncoder encoderToEncodeFrom:#'latin1' into:#'jis7'      
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   508
     CharacterEncoder encoderToEncodeFrom:#'koi8-r' into:#'mac-cyrillic'              
8087
0a2ee76bcf55 last version before separating into extra classes
Claus Gittinger <cg@exept.de>
parents: 8062
diff changeset
   509
     CharacterEncoder encoderToEncodeFrom:#'ms-arabic' into:#'mac-arabic'           
0a2ee76bcf55 last version before separating into extra classes
Claus Gittinger <cg@exept.de>
parents: 8062
diff changeset
   510
     CharacterEncoder encoderToEncodeFrom:#'iso8859-5' into:#'koi8-r'           
0a2ee76bcf55 last version before separating into extra classes
Claus Gittinger <cg@exept.de>
parents: 8062
diff changeset
   511
     CharacterEncoder encoderToEncodeFrom:#'koi8-r' into:#'koi8-u'       
7971
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   512
    "
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   513
! !
357e53496acc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7969
diff changeset
   514
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   515
!CharacterEncoder class methodsFor:'Compatibility-ST80'!
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   516
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   517
encoderNamed: encoderName
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   518
    "/ q & d hack
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   519
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   520
    encoderName == #default ifTrue:[
11262
5de131eaba9e changed #classMenuCompareTwoRepositoryVersions
Claus Gittinger <cg@exept.de>
parents: 11228
diff changeset
   521
        ^ DefaultEncoder new
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   522
    ].
11262
5de131eaba9e changed #classMenuCompareTwoRepositoryVersions
Claus Gittinger <cg@exept.de>
parents: 11228
diff changeset
   523
self halt:'should not be reached'.
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   524
    ^ self new
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   525
!
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   526
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   527
platformName
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   528
    ^ OperatingSystem platformName
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   529
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   530
    "Created: 20.6.1997 / 17:34:03 / cg"
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   531
    "Modified: 20.6.1997 / 17:38:40 / cg"
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   532
! !
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   533
11316
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   534
!CharacterEncoder class methodsFor:'accessing'!
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   535
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   536
nullEncoderInstance
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   537
    ^ NullEncoderInstance
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   538
! !
0b2757774461 access method #nullEncoderInstance
Stefan Vogel <sv@exept.de>
parents: 11300
diff changeset
   539
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   540
!CharacterEncoder class methodsFor:'class initialization'!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   541
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   542
initialize
8154
87ec7c3be46a *** empty log message ***
ca
parents: 8153
diff changeset
   543
    |ud|
87ec7c3be46a *** empty log message ***
ca
parents: 8153
diff changeset
   544
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   545
    AccessLock := RecursionLock new.
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   546
    NullEncoderInstance := NullEncoder new.
7973
6dea491d56f7 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7972
diff changeset
   547
8126
33f9c4850e84 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8122
diff changeset
   548
    EncodersByName := Dictionary new.
33f9c4850e84 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8122
diff changeset
   549
    EncoderClassesByName := Dictionary new.
33f9c4850e84 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8122
diff changeset
   550
    CachedEncoders := Dictionary new.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   551
8154
87ec7c3be46a *** empty log message ***
ca
parents: 8153
diff changeset
   552
    EncoderClassesByName at:#'unicode' put:(ud := Dictionary new).
87ec7c3be46a *** empty log message ***
ca
parents: 8153
diff changeset
   553
    ud at:#'fontspecific' put:NullEncoder.    
87ec7c3be46a *** empty log message ***
ca
parents: 8153
diff changeset
   554
    ud at:#'adobe-fontspecific' put:NullEncoder.    
8190
2c1bbf4a6a13 ms-oem untranslated
ca
parents: 8187
diff changeset
   555
    ud at:#'ms-oem' put:NullEncoder.    
13326
41549853fc87 changed: #initialize
Claus Gittinger <cg@exept.de>
parents: 13325
diff changeset
   556
    ud at:#'ms-default' put:NullEncoder.    
8152
e07693c46cf5 *** empty log message ***
ca
parents: 8151
diff changeset
   557
8135
f22398526ae2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8134
diff changeset
   558
    "/ className decoded-name array-of-encodingNames
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   559
    #(
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   560
        (ASCII              unicode     ( ascii 'us-ascii' 'iso-ir-6' 'ibm-367' 'ms-cp367' 'cp367'  'iso646-us' 'ibm-cp367' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   561
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   562
        (BIG5               unicode     ( big5 ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   563
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   564
        (CNS11643           unicode     ( 'cns11643' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   565
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   566
        (CP437              unicode     ( 'cp437'  'cp-437' 'ibm-437' 'ms-cp437' 'microsoft-cp437' 'ibm-cp437' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   567
13063
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   568
        (EBCDIC             unicode     ( 'ebcdic' ))
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   569
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   570
        (GB2313_1980        unicode     ( 'gb2313' 'gb2313-1980' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   571
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   572
        (HANGUL             unicode     ( 'hangul' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   573
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   574
        (ISO10646_1         unicode     ( unicode 'iso10646_1' 'iso10646-1' 'iso-10646-1' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   575
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   576
        (ISO10646_to_UTF8   unicode     ( utf8 'utf-8' ))
8904
d358f0a17f07 utf16 support
Claus Gittinger <cg@exept.de>
parents: 8856
diff changeset
   577
        (ISO10646_to_UTF16BE unicode    ( utf16b utf16be 'utf-16b' 'utf-16be' ))
d358f0a17f07 utf16 support
Claus Gittinger <cg@exept.de>
parents: 8856
diff changeset
   578
        (ISO10646_to_UTF16LE unicode    ( utf16l utf16le 'utf-16e' 'utf-16le' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   579
8855
289b5bda04bb guessEncoding - return the real encodings name
Claus Gittinger <cg@exept.de>
parents: 8814
diff changeset
   580
        (ISO8859_1          unicode     ( 'iso8859_1' 'iso8859-1' 'iso-8859-1' 'latin-1' 'latin1' 'iso-ir-100' 'ibm-819' 'ms-cp819' 'ibm-cp819' 'iso8859'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   581
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   582
        (ISO8859_2          unicode     ( 'iso8859_2' 'iso8859-2' 'iso-8859-2' 'latin2' 'latin-2' 'iso-ir-101'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   583
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   584
        (ISO8859_3          unicode     ( 'iso8859_3' 'iso8859-3' 'iso-8859-3' 'latin3' 'latin-3' 'iso-ir-109'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   585
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   586
        (ISO8859_4          unicode     ( 'iso8859_4' 'iso8859-4' 'iso-8859-4' 'latin4' 'latin-4' 'iso-ir-110'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   587
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   588
        (ISO8859_5          unicode     ( 'iso8859_5' 'iso8859-5' 'iso-8859-5' 'cyrillic' 'iso-ir-144' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   589
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   590
        (ISO8859_6          unicode     ( 'iso8859_6' 'iso8859-6' 'iso-8859-6' 'arabic' 'asmo-708' 'ecma-114' 'iso-ir-127' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   591
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   592
        (ISO8859_7          unicode     ( 'iso8859_7' 'iso8859-7' 'iso-8859-7' 'greek' 'iso-ir-126' 'ecma-118'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   593
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   594
        (ISO8859_8          unicode     ( 'iso8859_8' 'iso8859-8' 'iso-8859-8' 'hebrew' 'iso-ir-138' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   595
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   596
        (ISO8859_9          unicode     ( 'iso8859_9' 'iso8859-9' 'iso-8859-9' 'latin5' 'latin-5' 'iso-ir-148'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   597
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   598
        (ISO8859_10         unicode     ( 'iso8859_10' 'iso8859-10' 'iso-8859-10' 'latin6' 'latin-6' 'iso-ir-157'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   599
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   600
        (ISO8859_11         unicode     ( 'iso8859_11' 'iso8859-11' 'iso-8859-11' 'thai' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   601
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   602
        (ISO8859_13         unicode     ( 'iso8859_13' 'iso8859-13' 'iso-8859-13' 'latin7' 'latin-7' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   603
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   604
        (ISO8859_14         unicode     ( 'iso8859_14' 'iso8859-14' 'iso-8859-14' 'latin8' 'latin-8' 'latin-celtic' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   605
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   606
        (ISO8859_15         unicode     ( 'iso8859_15' 'iso8859-15' 'iso-8859-15' 'latin9' 'latin-9' 'iso-ir-203'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   607
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   608
        (ISO8859_16         unicode     ( 'iso8859_16' 'iso8859-16' 'iso-8859-16' 'latin10' 'latin-10' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   609
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   610
        (JIS0201            unicode     ( 'jis0201' #'jisx0201.1976-0'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   611
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   612
        (JIS0208            unicode     ( jis0208 'jisx0208' 'jisx0208.1983-0' 'jisx0208.1990-0'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   613
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   614
        (JIS0208_to_JIS7    jis0208     ( jis7 'jis-7' 'x-jis7' 'x-iso2022-jp' 'iso2022-jp'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   615
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   616
        (JIS0208_to_EUC     jis0208     ( euc #'x-euc-jp' ))
8122
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   617
8176
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   618
        (JIS0208_to_SJIS    jis0208     ( 'sjis' 'shiftjis' 'x-sjis' #'x-shift-jis' #'shift-jis'))
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   619
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   620
        (JIS0212            unicode     ( 'jis0212' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   621
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   622
        (JOHAB              unicode     ( 'johab' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   623
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   624
        (KOI7               unicode     ( 'koi7' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   625
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   626
        (KOI8_R             unicode     ( #'koi8-r' 'cp878' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   627
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   628
        (KOI8_U             unicode     ( #'koi8-u' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   629
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   630
        (KSC5601            unicode     ( #'ksc5601' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   631
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   632
        (MAC_Arabic         unicode     ( #'mac-arabic' 'macarabic' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   633
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   634
        (MAC_CentralEuropean unicode    ( #'mac-centraleuropean' #'mac-centraleurope' 'maccentraleurope' 'maccentraleuropean' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   635
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   636
        (MAC_Croatian       unicode     ( #'mac-croatian' 'maccroatian'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   637
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   638
        (MAC_Cyrillic       unicode     ( #'mac-cyrillic' 'maccyrillic' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   639
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   640
        (MAC_Dingbats       unicode     ( #'mac-dingbats'  'macdingbats'  'macdingbat'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   641
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   642
        (MAC_Farsi          unicode     ( #'mac-farsi' 'macfarsi' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   643
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   644
        (MAC_Greek          unicode     ( #'mac-greek' #'macgreek' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   645
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   646
        (MAC_Hebrew         unicode     ( #'mac-hebrew' #'machebrew'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   647
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   648
        (MAC_Iceland        unicode     ( #'mac-iceland' #'maciceland'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   649
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   650
        (MAC_Japanese       unicode     ( #'mac-japanese' #'macjapanese'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   651
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   652
        (MAC_Korean         unicode     ( #'mac-korean' #'mackorean'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   653
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   654
        (MAC_Roman          unicode     ( #'mac-roman' #'macroman'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   655
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   656
        (MAC_Romanian       unicode     ( #'mac-romanian' #'macromanian'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   657
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   658
        (MAC_Symbol         unicode     ( #'mac-symbol' #'macsymbol'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   659
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   660
        (MAC_Thai           unicode     ( #'mac-thai' #'macthai'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   661
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   662
        (MAC_Turkish        unicode     ( #'mac-turkish' #'macturkish'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   663
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   664
        (MS_Ansi            unicode     ( #'ms-ansi' 'ms-cp1252' 'microsoft-cp1252' 'cp1252' 'microsoft-ansi' 'windows-1252' 'windows-latin1'))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   665
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   666
        (MS_Arabic          unicode     ( 'ms-arabic' 'ms-cp1256' 'microsoft-cp1256' 'cp1256'  'microsoft-arabic' 'windows-1256'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   667
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   668
        (MS_Baltic          unicode     ( 'ms-baltic' 'ms-cp1257' 'microsoft-cp1257' 'cp1257' 'microsoft-baltic' 'windows-1257'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   669
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   670
        (MS_Cyrillic        unicode     ( 'ms-cyrillic' 'ms-cp1251' 'microsoft-cp1251' 'cp1251' 'microsoft-cyrillic' 'windows-1251'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   671
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   672
        (MS_EastEuropean    unicode     ( 'ms-easteuropean' 'ms-ee' 'cp1250' 'ms-cp1250' 'microsoft-cp1250' 'microsoft-easteuropean' 'windows-1250'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   673
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   674
        (MS_Greek           unicode     ( 'ms-greek' 'ms-cp1253' 'microsoft-cp1253' 'cp1253' 'microsoft-greek' 'windows-1253' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   675
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   676
        (MS_Hebrew          unicode     ( 'ms-hebrew' 'ms-cp1255' 'microsoft-cp1255' 'cp1255' 'microsoft-hebrew' 'windows-1255' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   677
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   678
"/        (MS_Symbol           unicode     ( 'ms-symbol' 'microsoft-symbol'  ))
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   679
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   680
        (MS_Turkish         unicode     ( 'ms-turkish' 'ms-cp1254' 'microsoft-cp1254' 'cp1254' 'microsoft-turkish' 'windows-1254'  ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   681
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   682
        (NEXT               unicode     ( 'next' 'nextstep'  ))
8186
ae97115c26f5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8176
diff changeset
   683
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   684
        (ISO10646_to_SGML       unicode     ( 'sgml' ))
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   685
        (ISO10646_to_JavaText   unicode     ( 'java' 'javaText' ))
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   686
    ) triplesDo:[:className :decodesTo :encodesTo |
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   687
        |dict|
8134
0296806cb4bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8132
diff changeset
   688
8151
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   689
        "/ notice that the encoders are not yet installed as autoloaded.
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   690
        "/ Therefore, we remember their names here.
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   691
        dict := EncoderClassesByName at:decodesTo ifAbsent:nil.
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   692
        dict isNil ifTrue:[
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   693
            EncoderClassesByName at:decodesTo put:(dict := Dictionary new).
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   694
        ].
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   695
        encodesTo do:[:eachEncodingAlias |
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   696
            (dict includesKey:eachEncodingAlias) ifTrue:[
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   697
                self halt:'conflicting alias'
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   698
            ].
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   699
            dict at:eachEncodingAlias put:className.    
1f0fc1d4516b *** empty log message ***
ca
parents: 8150
diff changeset
   700
        ].
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   701
    ].
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   702
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   703
    "
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   704
     self initialize
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   705
    "
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
   706
13326
41549853fc87 changed: #initialize
Claus Gittinger <cg@exept.de>
parents: 13325
diff changeset
   707
    "Modified: / 01-04-2011 / 14:30:06 / cg"
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   708
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   709
8122
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   710
!CharacterEncoder class methodsFor:'constants'!
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   711
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   712
jis7KanjiEscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   713
    "return the escape sequence used to switch to kanji in jis7 encoded strings.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   714
     This happens to be the same as ISO2022-JP's escape sequence."
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   715
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   716
    Jis7KanjiEscapeSequence isNil ifTrue:[
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   717
	Jis7KanjiEscapeSequence := Character esc asString , '$B'.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   718
    ].
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   719
    ^ Jis7KanjiEscapeSequence.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   720
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   721
    "Created: 26.2.1996 / 17:38:08 / cg"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   722
    "Modified: 30.6.1997 / 16:03:16 / cg"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   723
!
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   724
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   725
jis7KanjiOldEscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   726
    "return the escape sequence used to switch to kanji in some old jis7 encoded strings."
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   727
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   728
    Jis7KanjiOldEscapeSequence isNil ifTrue:[
8856
cb0a15744854 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8855
diff changeset
   729
        Jis7KanjiOldEscapeSequence := Character esc asString , '$@'.
8122
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   730
    ].
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   731
    ^ Jis7KanjiOldEscapeSequence.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   732
!
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   733
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   734
jis7RomanEscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   735
    "return the escape sequence used to switch to roman in jis7 encoded strings"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   736
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   737
    Jis7RomanEscapeSequence isNil ifTrue:[
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   738
	Jis7RomanEscapeSequence := Character esc asString , '(J'.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   739
    ].
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   740
    ^ Jis7RomanEscapeSequence.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   741
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   742
    "Created: 26.2.1996 / 17:38:08 / cg"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   743
    "Modified: 30.6.1997 / 16:03:16 / cg"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   744
!
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   745
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   746
jisISO2022EscapeSequence
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   747
    "return the escape sequence used to switch to kanji in iso2022 encoded strings"
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   748
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   749
    JisISO2022EscapeSequence isNil ifTrue:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   750
	JisISO2022EscapeSequence := Character esc asString , '&@' , Character esc asString , '$B'.
8122
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   751
    ].
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   752
    ^ JisISO2022EscapeSequence.
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   753
! !
29670db31014 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8120
diff changeset
   754
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   755
!CharacterEncoder class methodsFor:'encoding & decoding'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   756
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   757
decode:aCodePoint
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   758
    ^ self new decode:aCodePoint
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   759
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   760
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   761
decodeString:aString
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   762
    ^ self new decodeString:aString
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   763
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   764
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   765
decodeString:aString from:oldEncoding
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   766
    ^ self encodeString:aString from:oldEncoding into:#'unicode'
7967
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   767
!
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   768
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   769
encode:aCodePoint
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   770
    ^ self new encode:aCodePoint
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   771
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   772
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   773
     ISO8859_1 encode:16r00FF   
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   774
     ISO8859_1 decodeString:'hello'
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   775
     ISO8859_1 encodeString:(ISO8859_1 decodeString:'hello') 
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   776
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   777
     ISO8859_5 decodeString:(String 
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   778
				with:(Character value:16rE4)
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   779
				with:(Character value:16rE0)) 
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   780
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   781
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   782
7994
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   783
encode:codePoint from:oldEncodingArg into:newEncodingArg
8015
e85b0c11e871 caching encoders
Claus Gittinger <cg@exept.de>
parents: 7994
diff changeset
   784
    |oldEncoding newEncoding encoder|
7994
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   785
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   786
    oldEncoding := oldEncodingArg ? #'unicode'.
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   787
    oldEncoding == #'iso10646-1' ifTrue:[ oldEncoding :=  #'unicode'].
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   788
    newEncoding := newEncodingArg ? #'unicode'.
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   789
    newEncoding == #'iso10646-1' ifTrue:[ newEncoding :=  #'unicode'].
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   790
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   791
    oldEncoding == newEncoding ifTrue:[^ codePoint].
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   792
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   793
    oldEncoding == #'unicode' ifTrue:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   794
	newEncoding == #'iso8859-1' ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   795
	    codePoint <= 16rFF ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   796
		^ codePoint
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   797
	    ]
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   798
	]
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   799
    ].
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   800
    newEncoding == #'unicode' ifTrue:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   801
	oldEncoding == #'iso8859-1' ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   802
	    codePoint <= 16rFF ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   803
		^ codePoint
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   804
	    ]
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   805
	]
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   806
    ].
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   807
    encoder := self encoderToEncodeFrom:oldEncoding into:newEncoding.
8015
e85b0c11e871 caching encoders
Claus Gittinger <cg@exept.de>
parents: 7994
diff changeset
   808
    ^ encoder encode:codePoint.
7994
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   809
!
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   810
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   811
encodeString:aUnicodeString
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   812
    "given a string in unicode, return a string in my encoding for it"
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   813
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   814
    ^ self new encodeString:aUnicodeString
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   815
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   816
    "
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   817
     ISO8859_1 decodeString:'hello'
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   818
    "
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   819
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   820
7967
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   821
encodeString:aString from:oldEncodingArg into:newEncodingArg
8015
e85b0c11e871 caching encoders
Claus Gittinger <cg@exept.de>
parents: 7994
diff changeset
   822
    |oldEncoding newEncoding encoder|
7967
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   823
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   824
    oldEncoding := oldEncodingArg ? #'unicode'.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   825
    oldEncoding == #'iso10646-1' ifTrue:[ oldEncoding :=  #'unicode'].
7967
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   826
    newEncoding := newEncodingArg ? #'unicode'.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   827
    newEncoding == #'iso10646-1' ifTrue:[ newEncoding :=  #'unicode'].
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   828
7967
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   829
    oldEncoding == newEncoding ifTrue:[^ aString].
f9baf81d6991 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7964
diff changeset
   830
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   831
    oldEncoding == #'unicode' ifTrue:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   832
	newEncoding == #'iso8859-1' ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   833
	    aString bitsPerCharacter == 8 ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   834
		^ aString
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   835
	    ]
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   836
	]
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   837
    ].
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   838
    newEncoding == #'unicode' ifTrue:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   839
	oldEncoding == #'iso8859-1' ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   840
	    aString bitsPerCharacter == 8 ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   841
		^ aString
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   842
	    ]
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   843
	]
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   844
    ].
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   845
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
   846
    encoder := self encoderToEncodeFrom:oldEncoding into:newEncoding.
8015
e85b0c11e871 caching encoders
Claus Gittinger <cg@exept.de>
parents: 7994
diff changeset
   847
    ^ encoder encodeString:aString.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   848
!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   849
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
   850
encodeString:aString into:newEncoding
8016
6344e4e47261 characterEncoding stuff
Claus Gittinger <cg@exept.de>
parents: 8015
diff changeset
   851
    ^ self encodeString:aString from:#'unicode' into:newEncoding
13063
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   852
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   853
    "
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   854
     self encodeString:'hello' into:#ebcdic
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   855
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   856
     self encodeString:(self encodeString:'hello' into:#ebcdic) from:#ebcdic into:#ascii    
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   857
     self encodeString:(self encodeString:'hello' into:#ebcdic) from:#ebcdic into:#unicode    
a17ba204b911 comment/format in: #encodeString:into:
Claus Gittinger <cg@exept.de>
parents: 12608
diff changeset
   858
    "
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   859
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   860
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   861
!CharacterEncoder class methodsFor:'private'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   862
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   863
flushCode
8127
7531ed2cdf35 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8126
diff changeset
   864
    self initialize.
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   865
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   866
    self isAbstract ifFalse:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   867
	(self mapFileURL1_relativePathName notNil
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   868
	or:[ self mapFileURL2_relativePathName notNil]) ifTrue:[
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   869
	    self class removeSelector:#mapping.
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
   870
	].
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   871
    ].
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   872
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   873
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   874
     self flushCode
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   875
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   876
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   877
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   878
!CharacterEncoder class methodsFor:'private-mapping setup'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   879
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   880
generateCode
7909
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   881
    (CharacterEncoderCodeGenerator new targetClass:self) generateCode.
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   882
!
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   883
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   884
generateSubclassCode
a045c719fca2 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7904
diff changeset
   885
    (CharacterEncoderCodeGenerator new targetClass:self) generateSubclassCode.
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   886
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   887
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   888
mapFileURL1_codeColumn
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   889
    ^ 1
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   890
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
   891
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   892
mapFileURL1_relativePathName
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   893
    "raise an error: must be redefined in concrete subclass(es)"
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   894
    
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   895
    ^ nil
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   896
!
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   897
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   898
mapFileURL2_relativePathName
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   899
    "raise an error: must be redefined in concrete subclass(es)"
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   900
    
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   901
    ^ nil
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   902
!
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   903
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   904
mappingURL1
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   905
    "raise an error: must be redefined in concrete subclass(es)"
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   906
    
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   907
    |rel|
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   908
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   909
    rel := self mapFileURL1_relativePathName.
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   910
    rel isNil ifTrue:[
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   911
	^ nil
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   912
    ].
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   913
    ^ 'http://www.unicode.org/Public/MAPPINGS/' , rel
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   914
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   915
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   916
mappingURL2
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   917
    "raise an error: must be redefined in concrete subclass(es)"
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   918
    
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   919
    |rel|
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   920
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   921
    rel := self mapFileURL2_relativePathName.
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   922
    rel isNil ifTrue:[
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
   923
	^ nil
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
   924
    ].
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   925
    ^ 'http://std.dkuug.dk/i18n/charmaps/' , rel
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   926
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   927
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   928
!CharacterEncoder class methodsFor:'queries'!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
   929
7938
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   930
isEncoding:subSetEncodingArg subSetOf:superSetEncodingArg
7994
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   931
    "return true, if superSetEncoding encoding includes all characters of subSetEncoding.
42b5face56fb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7986
diff changeset
   932
     (this means: characters are included - not that they have the same encoding)"
7938
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   933
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   934
    |subSetEncoding superSetEncoding|
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   935
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   936
    subSetEncodingArg = superSetEncodingArg ifTrue:[^ true].
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   937
    subSetEncoding := subSetEncodingArg asLowercase.
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   938
    superSetEncoding := superSetEncodingArg asLowercase.
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   939
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   940
    (subSetEncoding match:superSetEncoding) ifTrue:[^ true].
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   941
8214
406c7fc10e12 assume ms-ansi is same as unicode
Claus Gittinger <cg@exept.de>
parents: 8211
diff changeset
   942
    (('iso10646*' match:superSetEncoding) 
406c7fc10e12 assume ms-ansi is same as unicode
Claus Gittinger <cg@exept.de>
parents: 8211
diff changeset
   943
    or:[superSetEncoding = 'unicode'
406c7fc10e12 assume ms-ansi is same as unicode
Claus Gittinger <cg@exept.de>
parents: 8211
diff changeset
   944
    or:[superSetEncoding = 'ms-ansi']]) ifTrue:[
406c7fc10e12 assume ms-ansi is same as unicode
Claus Gittinger <cg@exept.de>
parents: 8211
diff changeset
   945
        "/ assume that any character is in unicode
406c7fc10e12 assume ms-ansi is same as unicode
Claus Gittinger <cg@exept.de>
parents: 8211
diff changeset
   946
        ^ true.
7938
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   947
    ].
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   948
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   949
    "/ if the subSet is iso8859-*, that means ascii (i.e. the lower 7 bits of iso8859 only).
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   950
    ((subSetEncoding = 'iso8859*') or:[subSetEncoding = 'iso8859-*']) ifTrue:[
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   951
        ('ascii*' match:superSetEncoding) ifTrue:[^ true].
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   952
        ('ms-ansi*' match:superSetEncoding) ifTrue:[^ true].
7938
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   953
    ].
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   954
    (subSetEncoding = 'ascii') ifTrue:[
8168
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   955
        ('iso8859*' match:superSetEncoding) ifTrue:[^ true].
8f8da8bb046d *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8156
diff changeset
   956
        ('ms-ansi*' match:superSetEncoding) ifTrue:[^ true].
7938
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   957
    ].
a53aae4a05bb *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7932
diff changeset
   958
7923
e8286ccdf20c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7922
diff changeset
   959
    "/ TODO: check the charSets mappingTables...
e8286ccdf20c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7922
diff changeset
   960
    "/ self halt.
e8286ccdf20c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7922
diff changeset
   961
    ^ false.
e8286ccdf20c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7922
diff changeset
   962
!
e8286ccdf20c *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7922
diff changeset
   963
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   964
nameOfDecodedCode
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   965
    "Most coders decode from their code into unicode / encode from unicode into their code.
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   966
     There are a few exceptions to this, though - these must redefine this."
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   967
    
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   968
    ^ #'unicode'
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   969
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   970
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   971
nameOfEncoding
7974
9905043988ee *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7973
diff changeset
   972
    ^ (self nameWithoutPrefix asLowercase copyReplaceAll:$_ with:$-) asSymbol
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   973
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
   974
7959
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   975
supportedExternalEncodings
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   976
    "return an array of arrays containing the names of supported
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   977
     encodings which are supported for external resources (i.e. files).
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   978
     The first element contains the internally used symbolic name,
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   979
     the second contains a user-readable string (description).
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   980
     More than one external name may be mapped onto the same symbolic."
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   981
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
   982
    ^ #( 
8176
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   983
         ('utf8'        'Unicode as 8Bit characters'    )  
8904
d358f0a17f07 utf16 support
Claus Gittinger <cg@exept.de>
parents: 8856
diff changeset
   984
         ('utf16BE'     'Unicode as 16Bit big-endian'    )  
d358f0a17f07 utf16 support
Claus Gittinger <cg@exept.de>
parents: 8856
diff changeset
   985
         ('utf16LE'     'Unicode as 16Bit little-endian' )  
8176
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   986
"/         ('utf7'        'Unicode as 7Bit characters'    ) 
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   987
"/       nil
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   988
         ('ascii'       'Common 7bit subset of iso8859' )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   989
         ('iso8859-1'   'Latin1'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   990
         ('iso8859-2'   'Latin2'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   991
         ('iso8859-3'   'Latin3'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   992
         ('iso8859-4'   'Latin4'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   993
         ('iso8859-5'   'Cyrillic'                      )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   994
         ('iso8859-6'   'Arabic'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   995
         ('iso8859-7'   'Greek'                         )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   996
         ('iso8859-8'   'Hebrew'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   997
"/       nil
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   998
         ('koi7'        'Cyrillic (Old)'                )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
   999
         ('koi8-r'      'Cyrillic'                      )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1000
         ('koi8-u'      'Cyrillic (Ukraine)'            )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1001
"/       nil
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1002
         ('cp437'       'msdos US / codepage 437'       )
8810
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1003
         ('cp850'       'msdos Latin1 / codepage 850'   )
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1004
         ('cp1250'      'msdos Latin2 / codepage 1250'  )
14174
3a4f041c94a2 changed: #supportedExternalEncodings
Michael Beyl <mb@exept.de>
parents: 14169
diff changeset
  1005
         ('cp1251'      'msdos Latin2 / codepage 1251'  )
8176
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1006
"/         ('mac'         'macintosh 8 bit'               )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1007
         ('next'        'NeXT 8 bit'                    )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1008
"/         ('hp'          'hpux 8 bit'                    )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1009
"/       nil
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1010
         ('euc'         'EUC - extended unix code (japanese)'     )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1011
         ('jis7'        'JIS7 - jis 7bit escape codes (japanese)' )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1012
         ('iso-2022-jp' 'Same as jis 7bit'                        )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1013
         ('sjis'        'SJIS - shift jis 8bit codes (japanese)'  )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1014
"/       nil
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1015
         ('gb'          'GB - mainland china'                   )
66d1004f1806 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8168
diff changeset
  1016
         ('big5'        'BIG5 - taiwan'                         )
7959
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
  1017
"/         ('ksc'         'korean'                        )
8186
ae97115c26f5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8176
diff changeset
  1018
         ('sgml'        'SGML (XML/HTML) character escapes'     )
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
  1019
         ('java'        'JavaText (\uXXXX) character escapes'   )
7959
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
  1020
       )
10111
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
  1021
7485e9da838c +javaText encoder
Claus Gittinger <cg@exept.de>
parents: 9143
diff changeset
  1022
    "Modified: / 23-10-2006 / 13:27:48 / cg"
7959
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
  1023
!
0276f0a46dd1 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7956
diff changeset
  1024
7947
16b2306f9bc9 utf8 - full 30 bit range
Claus Gittinger <cg@exept.de>
parents: 7942
diff changeset
  1025
userFriendlyNameOfEncoding
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1026
    ^ self nameOfEncoding asUppercaseFirst
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1027
! !
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1028
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1029
!CharacterEncoder class methodsFor:'testing'!
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1030
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1031
isAbstract
11228
10b5c088d8f2 comment
Claus Gittinger <cg@exept.de>
parents: 10672
diff changeset
  1032
    "Return if this class is an abstract class.
10b5c088d8f2 comment
Claus Gittinger <cg@exept.de>
parents: 10672
diff changeset
  1033
     True is returned for CharacterEncoder here; false for subclasses.
10b5c088d8f2 comment
Claus Gittinger <cg@exept.de>
parents: 10672
diff changeset
  1034
     Abstract subclasses must redefine again."
10b5c088d8f2 comment
Claus Gittinger <cg@exept.de>
parents: 10672
diff changeset
  1035
7912
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1036
    ^ self == CharacterEncoder
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1037
! !
fbbb59645576 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7909
diff changeset
  1038
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1039
!CharacterEncoder class methodsFor:'utilities'!
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1040
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1041
guessEncodingOfBuffer:buffer
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1042
    "look for a string of the form
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1043
            encoding #name
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1044
     or:
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1045
            encoding: name
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1046
     within the given buffer 
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1047
     (which is usually the first few bytes of a textFile)."
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1048
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1049
    |lcBuffer quote peek|
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1050
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1051
    buffer size < 4 ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1052
        "not enough bytes to determine the contents"
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1053
        ^ nil.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1054
    ].
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1055
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1056
    "check the Byte Order Mark (BOM)"
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1057
    peek := (buffer at:1) codePoint.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1058
    peek < 16rFE ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1059
        (peek = 16rEF
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1060
            and:[(buffer at:2) codePoint = 16rBB 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1061
            and:[(buffer at:3) codePoint = 16rBF]]) ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1062
            ^ #utf8
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1063
        ].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1064
        (peek = 0 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1065
            and:[(buffer at:2) codePoint = 0 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1066
            and:[(buffer at:3) codePoint = 16rFE 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1067
            and:[(buffer at:4) codePoint = 16rFF]]]) ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1068
            ^ #utf32be
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1069
        ].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1070
    ] ifFalse:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1071
        peek = 16rFF ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1072
            (buffer at:2) codePoint = 16rFE ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1073
                "little endian"
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1074
                ((buffer at:3) codePoint = 0 and:[(buffer at:4) codePoint = 0]) ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1075
                    ^ #utf32le.   
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1076
                ].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1077
                ^ #utf16le
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1078
            ].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1079
        ] ifFalse:["peek = 16rFE"
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1080
            (buffer at:2) codePoint = 16rFF ifTrue:[
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1081
                "big endian"
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1082
                ^ #utf16be
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1083
            ].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1084
        ]
10672
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1085
    ].
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1086
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1087
    lcBuffer := buffer asLowercase.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1088
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1089
    "now look for an inline encoding markup"
10672
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1090
    #(charset encoding) do:[:keyWord |
8855
289b5bda04bb guessEncoding - return the real encodings name
Claus Gittinger <cg@exept.de>
parents: 8814
diff changeset
  1091
        |encoderOrNil idx s w enc|
289b5bda04bb guessEncoding - return the real encodings name
Claus Gittinger <cg@exept.de>
parents: 8814
diff changeset
  1092
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1093
        (idx := lcBuffer findString:keyWord) ~~ 0 ifTrue:[
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1094
            s := ReadStream on:buffer.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1095
            s position1Based:idx.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1096
            s skip:keyWord size.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1097
            s skipSeparators. 
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1098
10672
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1099
            "do not include '=' here, otherwise
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1100
             files containing xml code (<?xml charset='utf8'> will be parsed as UTF-8"
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1101
11300
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1102
            [':#=' includes:s peek] whileTrue:[
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1103
                s next.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1104
                s skipSeparators. 
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1105
            ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1106
            s skipSeparators.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1107
            ('"''' includes:s peek) ifTrue:[
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1108
                quote := s next.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1109
                w := s upTo:quote.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1110
            ] ifFalse:[
11300
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1111
                w := s upToMatching:[:ch | ch isSeparator or:[ch == $" or:[ch == $' or:[ch == $> ]]]].
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1112
            ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1113
            w notNil ifTrue:[
11300
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1114
                enc := w withoutQuotes.
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1115
                (enc startsWith:'x-') ifTrue:[
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1116
                    enc := enc copyFrom:3.
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1117
                ].
10672
b6230a13035b #guessEncodingOfBuffer - do NOT handle encoding=utf8
Stefan Vogel <sv@exept.de>
parents: 10111
diff changeset
  1118
                encoderOrNil := self encoderFor:enc ifAbsent:nil.
8855
289b5bda04bb guessEncoding - return the real encodings name
Claus Gittinger <cg@exept.de>
parents: 8814
diff changeset
  1119
                encoderOrNil notNil ifTrue:[
289b5bda04bb guessEncoding - return the real encodings name
Claus Gittinger <cg@exept.de>
parents: 8814
diff changeset
  1120
                    ^ encoderOrNil nameOfEncoding
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1121
                ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1122
"/                enc size >=3 ifTrue:[
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1123
"/                    Transcript showCR:'Unknown encoding: ' , (withoutQuotes value:w).
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1124
"/                ]
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1125
            ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1126
        ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1127
    ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1128
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1129
    "/ look for JIS7 / EUC encoding
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1130
    (buffer findString:self jisISO2022EscapeSequence) ~~ 0 ifTrue:[
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1131
        ^ #'iso2020-jp'
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1132
    ].
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1133
    (buffer findString:self jis7KanjiEscapeSequence) ~~ 0 ifTrue:[
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1134
        ^ #jis7
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1135
    ].
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1136
    (buffer findString:self jis7KanjiOldEscapeSequence) ~~ 0 ifTrue:[
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1137
        ^ #jis7
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1138
    ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1139
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1140
    "/ TODO:
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1141
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1142
"/    "/ look for EUC
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1143
"/    idx := aString findFirst:[:char | |ascii|
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1144
"/                                        ((ascii := char asciiValue) >= 16rA1)     
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1145
"/                                        and:[ascii <= 16rFE]].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1146
"/    idx ~~ 0 ifTrue:[
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1147
"/        ascii := (aString at:(idx + 1)) asciiValue.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1148
"/        (ascii >= 16rA1 and:[ascii <= 16rFE]) ifTrue:[
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1149
"/            ^ #euc
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1150
"/        ]
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1151
"/    ].
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1152
    "/ look for SJIS ...
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1153
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1154
    ^ nil
14169
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1155
!
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1156
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1157
guessEncodingOfFile:aFilename
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1158
    "look for a string
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1159
        encoding #name
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1160
     or:
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1161
        encoding: name
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1162
     within the given buffer 
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1163
     (which is usually the first few bytes of a textFile).
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1164
     If thats not found, use heuristics (in CharacterArray) to guess."
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1165
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1166
    |s buffer n "{Class: SmallInteger }"|
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1167
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1168
    s := aFilename asFilename readStreamOrNil.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1169
    s isNil ifTrue:[^ nil].
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1170
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1171
    buffer := String new:64.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1172
    n := s nextBytes:buffer size into:buffer.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1173
    s close.
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1174
eab487f07a2b comment/format in: #encoderFor:
Stefan Vogel <sv@exept.de>
parents: 14094
diff changeset
  1175
    ^ self guessEncodingOfBuffer:buffer.
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1176
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1177
    "
14094
b4db3e0f0102 changed:
Stefan Vogel <sv@exept.de>
parents: 13382
diff changeset
  1178
     self guessEncodingOfFile:'../../libview/resources/de.rs' asFilename
b4db3e0f0102 changed:
Stefan Vogel <sv@exept.de>
parents: 13382
diff changeset
  1179
     self guessEncodingOfFile:'../../libview/resources/ru.rs' asFilename
b4db3e0f0102 changed:
Stefan Vogel <sv@exept.de>
parents: 13382
diff changeset
  1180
     self guessEncodingOfFile:'../../libview/resources/th.rs' asFilename
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1181
    "
13382
8e998649b3ac changed:
Claus Gittinger <cg@exept.de>
parents: 13326
diff changeset
  1182
8e998649b3ac changed:
Claus Gittinger <cg@exept.de>
parents: 13326
diff changeset
  1183
    "Modified: / 31-05-2011 / 15:45:19 / cg"
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1184
!
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1185
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1186
guessEncodingOfStream:aStream
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1187
    "look for a string of the form
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1188
            encoding #name
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1189
     or:
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1190
            encoding: name
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1191
     in the first few bytes of aStream."
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1192
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1193
    |oldPosition buffer n|
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1194
13382
8e998649b3ac changed:
Claus Gittinger <cg@exept.de>
parents: 13326
diff changeset
  1195
    buffer := String new:64.
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1196
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1197
    oldPosition := aStream position.
14094
b4db3e0f0102 changed:
Stefan Vogel <sv@exept.de>
parents: 13382
diff changeset
  1198
    n := aStream nextBytes:buffer size into:buffer.
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1199
    aStream position:oldPosition.
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1200
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1201
    ^ self guessEncodingOfBuffer:buffer
13382
8e998649b3ac changed:
Claus Gittinger <cg@exept.de>
parents: 13326
diff changeset
  1202
8e998649b3ac changed:
Claus Gittinger <cg@exept.de>
parents: 13326
diff changeset
  1203
    "Modified: / 31-05-2011 / 15:45:23 / cg"
8810
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1204
!
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1205
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1206
showCharacterSet
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1207
    |font|
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1208
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1209
    "/ font := (Font family:'courier' face:'medium' style:'roman' size:12 encoding:'iso10646-1').
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1210
    font := View defaultFont.
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1211
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1212
    CharacterSetView
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1213
        openOn:font
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1214
        label:'Characters of ',self nameWithoutPrefix
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1215
        clickLabel:nil
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1216
        asInputFor:nil
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1217
        encoder:self
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1218
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1219
    "
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1220
     CharacterEncoderImplementations::CP1250 showCharacterSet
8f509238ef9f +showCharacterSet
Claus Gittinger <cg@exept.de>
parents: 8722
diff changeset
  1221
    "
8711
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1222
! !
c5f28b4c719d guessEncoding now implemented in CharacterEncoder
Claus Gittinger <cg@exept.de>
parents: 8388
diff changeset
  1223
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1224
!CharacterEncoder methodsFor:'encoding & decoding'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1225
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1226
decode:anEncoding
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1227
    "given an integer in my encoding, return a unicode codePoint for it"
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1228
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1229
    self subclassResponsibility
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1230
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1231
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1232
decodeString:anEncodedString
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1233
    "given a string in my encoding, return a unicode-string for it"
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1234
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1235
    |newString myCode uniCodePoint bits|
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1236
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1237
    newString := String new:(anEncodedString size).
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1238
    bits := newString bitsPerCharacter.
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1239
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1240
    1 to:anEncodedString size do:[:idx |
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1241
        uniCodePoint := (anEncodedString at:idx) codePoint.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1242
        myCode := self decode:uniCodePoint.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1243
        myCode > 16rFF ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1244
            myCode > 16rFFFF ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1245
                bits < 32 ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1246
                    newString := Unicode32String fromString:newString.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1247
                    bits := 32.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1248
                ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1249
            ] ifFalse:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1250
                bits < 16 ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1251
                    newString := Unicode16String fromString:newString.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1252
                    bits := 16.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1253
                ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1254
            ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1255
        ].
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1256
        newString at:idx put:(Character value:myCode).
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1257
    ].
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1258
    ^ newString
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1259
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1260
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1261
     ISO8859_1 decodeString:'hello'
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1262
    "
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1263
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1264
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1265
encode:aCodePoint
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1266
    "given a codePoint in unicode, return a byte in my encoding for it"
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1267
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1268
    self subclassResponsibility
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1269
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1270
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1271
encodeString:aUnicodeString
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1272
    "given a string in unicode, return a string in my encoding for it"
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1273
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1274
    |newString myCode uniCodePoint bits|
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1275
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1276
    newString := String new:(aUnicodeString size).
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1277
    bits := newString bitsPerCharacter.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1278
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1279
    1 to:aUnicodeString size do:[:idx |
8150
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1280
        uniCodePoint := (aUnicodeString at:idx) codePoint.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1281
        myCode := self encode:uniCodePoint.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1282
        myCode > 16rFF ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1283
            myCode > 16rFFFF ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1284
                bits < 32 ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1285
                    newString := Unicode32String fromString:newString.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1286
                    bits := 32.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1287
                ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1288
            ] ifFalse:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1289
                bits < 16 ifTrue:[
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1290
                    newString := Unicode16String fromString:newString.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1291
                    bits := 16.
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1292
                ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1293
            ]
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1294
        ].
ba9c6e587973 care for bitsPerCharacter change during encodeString/decodeString.
ca
parents: 8136
diff changeset
  1295
        newString at:idx put:(Character value:myCode).
8118
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1296
    ].
efc99c0f68bc *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8114
diff changeset
  1297
    ^ newString
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1298
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1299
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1300
!CharacterEncoder methodsFor:'error handling'!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1301
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1302
decodingError 
7904
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1303
    "report an error that there is no unicode-codePoint for a given codePoint in this encoding.
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1304
     (which is unlikely) or that the encoding is undefined for that value
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1305
     (for example, holes in the ISO8859-3 encoding)"
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1306
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1307
    |badCodePoint sender|
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1308
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1309
    sender := thisContext sender.
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1310
    ((sender selector == #encode:) or:[sender selector == #decode:]) ifFalse:[
11295
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1311
        badCodePoint := sender methodHome argAt:1
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1312
    ].
11295
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1313
    ^ (DecodingError new)
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1314
        defaultValue:(self defaultDecoderValue);
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1315
        parameter:badCodePoint;
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1316
        messageText:'invalid code'; 
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1317
        suspendedContext:sender;
94171df45ac5 encoding error handling
Claus Gittinger <cg@exept.de>
parents: 11262
diff changeset
  1318
        raiseRequest.
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1319
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1320
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1321
defaultDecoderValue
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1322
    "placed into a decoded string, in case there is no unicode codePoint
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1323
     for a given encoded codePoint.
7904
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1324
     (typically 16rFFFF)."
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1325
    
7904
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1326
    ^ 16rFFFF
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1327
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1328
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1329
defaultEncoderValue
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1330
    "placed into an encoded string, in case there is no codePoint
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1331
     for a given unicode codePoint.
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1332
     (typically $?)."
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1333
8101
f7023a4735bf Use the ANSI-blessed #codePoint instead of deprecated #asciiValue
Stefan Vogel <sv@exept.de>
parents: 8087
diff changeset
  1334
    ^ $? codePoint
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1335
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1336
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1337
encodingError
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1338
    "report an error that some unicode-codePoint cannot be represented by this encoder"
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1339
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1340
    |badCodePoint sender|
7904
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1341
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1342
    sender := thisContext sender.
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1343
    ((sender selector == #encode:) or:[sender selector == #decode:]) ifFalse:[
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1344
	badCodePoint := sender methodHome argAt:1
7904
e3940bba2746 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7903
diff changeset
  1345
    ].
8048
293c8178c6eb utf8 errors
Claus Gittinger <cg@exept.de>
parents: 8033
diff changeset
  1346
    ^ (EncodingError new)
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1347
	defaultValue:(self defaultEncoderValue);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1348
	parameter:badCodePoint;
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1349
	messageText:'unrepresentable unicode'; 
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1350
	suspendedContext:sender;
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1351
	raiseRequest
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1352
! !
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1353
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1354
!CharacterEncoder methodsFor:'printing'!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1355
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1356
printOn:aStream
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1357
    aStream 
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1358
	nextPutAll:(self nameOfDecodedCode);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1359
	nextPutAll:'->';
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1360
	nextPutAll:(self nameOfEncoding)
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1361
! !
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1362
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1363
!CharacterEncoder methodsFor:'private'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1364
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1365
newString:size
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1366
    self subclassResponsibility
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1367
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1368
7917
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1369
!CharacterEncoder methodsFor:'queries'!
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1370
11975
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1371
characterSize:codePoint
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1372
    "return the number of bytes required to encode codePoint"
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1373
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1374
    ^ self subclassResponsibility
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1375
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1376
    "Created: / 15-06-2005 / 15:11:04 / janfrog"
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1377
!
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1378
7917
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1379
isNullEncoder
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1380
    ^ false
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1381
!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1382
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1383
nameOfDecodedCode
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1384
    "Most coders decode from their code into unicode / encode from unicode into their code.
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1385
     There are a few exceptions to this, though - these must redefine this."
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1386
    
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1387
    ^ self class nameOfDecodedCode
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1388
!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1389
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1390
nameOfEncoding
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1391
    ^ self class nameOfEncoding
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1392
!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1393
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1394
userFriendlyNameOfEncoding
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1395
    ^ self class userFriendlyNameOfEncoding
7917
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1396
! !
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1397
11975
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1398
!CharacterEncoder methodsFor:'stream support'!
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1399
12608
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1400
readNext:charactersToRead charactersFrom:stream 
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1401
    ^ self decodeString:(stream next:charactersToRead)
11975
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1402
!
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1403
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1404
readNextCharacterFrom:aStream
12608
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1405
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1406
    | c |
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1407
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1408
    c := aStream next.
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1409
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1410
    ^ c isNil 
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1411
        ifTrue: [nil]
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1412
        ifFalse: [(self decode:c asInteger) asCharacter]
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1413
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1414
    "Created: / 14-06-2005 / 17:03:21 / janfrog"
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1415
    "Modified: / 15-06-2005 / 15:27:49 / janfrog"
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1416
    "Modified: / 20-06-2005 / 13:13:52 / masca"
12435
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1417
!
11975
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1418
12435
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1419
readNextInputCharacterFrom:aStream
12608
Claus Gittinger <cg@exept.de>
parents: 12435
diff changeset
  1420
    ^ aStream next
11975
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1421
! !
7b37b4dbd66f *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 11374
diff changeset
  1422
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1423
!CharacterEncoder::CompoundEncoder class methodsFor:'documentation'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1424
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1425
documentation
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1426
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1427
    A compoundEncoder uses two real encoders;
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1428
    to encode:
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1429
	string -> decoder(encode) -> encoder -> result
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1430
    to decode:
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1431
	string -> encoder -> decoder -> result
7956
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1432
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1433
    |e|
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1434
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1435
    e := CompoundEncoder new.
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1436
    e encoder:ISO8859_5 decoder:KOI8_R.
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1437
    e decode:16rB0.  'CYRILLIC CAPITAL LETTER A; 16rB0 in 8859-5; 16rE1 in KOI8-R'.
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1438
    e encode:16rE1.  
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1439
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1440
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1441
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1442
!CharacterEncoder::CompoundEncoder methodsFor:'accessing'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1443
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1444
encoder:encoderArg decoder:decoderArg  
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1445
    "set instance variables (automatically generated)"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1446
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1447
    decoder := decoderArg.
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1448
    encoder := encoderArg.
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1449
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1450
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1451
!CharacterEncoder::CompoundEncoder methodsFor:'encoding & decoding'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1452
7956
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1453
decode:aCode
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1454
    ^ decoder encode:(encoder decode:aCode)
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1455
!
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1456
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1457
decodeString:aString
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1458
    ^ decoder encodeString:(encoder decodeString:aString)
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1459
!
c43ee9e00bab *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7948
diff changeset
  1460
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1461
encode:aCode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1462
    ^ encoder encode:(decoder decode:aCode)
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1463
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1464
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1465
encodeString:aString
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1466
    ^ encoder encodeString:(decoder decodeString:aString)
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1467
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1468
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1469
!CharacterEncoder::CompoundEncoder methodsFor:'printing'!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1470
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1471
printOn:aStream
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1472
    aStream 
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1473
	nextPutAll:(decoder nameOfEncoding);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1474
	nextPutAll:'->'.
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1475
"/        nextPutAll:(decoder nameOfDecodedCode);
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1476
"/        nextPutAll:'->';
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1477
"/        nextPutAll:(encoder nameOfEncoding)
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1478
    encoder printOn:aStream
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1479
! !
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1480
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1481
!CharacterEncoder::DefaultEncoder class methodsFor:'documentation'!
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1482
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1483
documentation
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1484
"
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1485
    That is only a dummy for ST80 compatibility
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1486
"
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1487
! !
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1488
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1489
!CharacterEncoder::InverseEncoder class methodsFor:'documentation'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1490
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1491
documentation
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1492
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1493
    An inverseEncoder does the inverse - i.e. encode is really a decode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1494
    and decode is really an encode.
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1495
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1496
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1497
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1498
!CharacterEncoder::InverseEncoder methodsFor:'accessing'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1499
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1500
decoder:something
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1501
    decoder := something.
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1502
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1503
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1504
!CharacterEncoder::InverseEncoder methodsFor:'encoding & decoding'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1505
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1506
decode:aCode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1507
    ^ decoder encode:aCode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1508
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1509
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1510
decodeString:aString
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1511
    ^ decoder encodeString:aString
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1512
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1513
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1514
encode:aCode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1515
    ^ decoder decode:aCode
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1516
!
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1517
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1518
encodeString:aString
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1519
    ^ decoder decodeString:aString
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1520
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1521
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1522
!CharacterEncoder::InverseEncoder methodsFor:'printing'!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1523
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1524
printOn:aStream
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1525
    aStream 
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1526
	nextPutAll:(decoder nameOfEncoding);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1527
	nextPutAll:'->';
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1528
	nextPutAll:(decoder nameOfDecodedCode)
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1529
! !
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1530
12435
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1531
!CharacterEncoder::InverseEncoder methodsFor:'queries'!
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1532
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1533
characterSize:charOrcodePoint
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1534
    ^ decoder characterSize:charOrcodePoint
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1535
! !
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1536
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1537
!CharacterEncoder::InverseEncoder methodsFor:'stream support'!
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1538
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1539
readNextInputCharacterFrom:aStream
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1540
    ^ decoder readNextInputCharacterFrom:aStream
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1541
! !
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1542
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1543
!CharacterEncoder::NullEncoder class methodsFor:'documentation'!
7914
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1544
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1545
documentation
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1546
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1547
    A NullEncoder does nothing.
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1548
"
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1549
! !
86a3784b40dd *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7913
diff changeset
  1550
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1551
!CharacterEncoder::NullEncoder methodsFor:'encoding & decoding'!
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1552
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1553
decode:aCode
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1554
    ^ aCode
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1555
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1556
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1557
decodeString:aString
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1558
    ^ aString
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1559
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1560
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1561
encode:aCode
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1562
    ^ aCode
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1563
!
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1564
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1565
encodeString:aString
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1566
    ^ aString
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1567
! !
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1568
7917
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1569
!CharacterEncoder::NullEncoder methodsFor:'queries'!
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1570
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1571
isNullEncoder
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1572
    ^ true
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1573
! !
3649394bf5c0 checkin from browser
Claus Gittinger <cg@exept.de>
parents: 7915
diff changeset
  1574
7915
0b92b16542f6 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7914
diff changeset
  1575
!CharacterEncoder::OtherEncoding class methodsFor:'private'!
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1576
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1577
flushCode
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1578
!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1579
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1580
generateEncoderCode
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1581
! !
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1582
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1583
!CharacterEncoder::TwoStepEncoder class methodsFor:'documentation'!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1584
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1585
documentation
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1586
"
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1587
    A twoStepEncoder uses two real encoders;
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1588
    to encode:
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1589
	string -> encoder1(encode) -> encoder2(encode) -> result
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1590
    to decode:
7932
ee233bf44df5 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7924
diff changeset
  1591
	string -> encoder2(decode) -> encoder1(decode) -> result
7919
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1592
"
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1593
! !
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1594
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1595
!CharacterEncoder::TwoStepEncoder methodsFor:'accessing'!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1596
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1597
encoder1:encoder1Arg encoder2:encoder2Arg
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1598
    "set instance variables (automatically generated)"
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1599
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1600
    encoder1 := encoder1Arg.
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1601
    encoder2 := encoder2Arg.
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1602
! !
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1603
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1604
!CharacterEncoder::TwoStepEncoder methodsFor:'encoding & decoding'!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1605
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1606
decode:aCode
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1607
    ^ encoder1 decode:(encoder2 decode:aCode)
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1608
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1609
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1610
decodeString:aString
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1611
    ^ encoder1 decodeString:(encoder2 decodeString:aString)
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1612
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1613
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1614
encode:aCode
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1615
    ^ encoder2 encode:(encoder1 encode:aCode)
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1616
!
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1617
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1618
encodeString:aString
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1619
    ^ encoder2 encodeString:(encoder1 encodeString:aString)
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1620
! !
92b61bef1b1a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7917
diff changeset
  1621
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1622
!CharacterEncoder::TwoStepEncoder methodsFor:'printing'!
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1623
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1624
printOn:aStream
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1625
    aStream 
8136
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1626
	nextPutAll:(encoder1 nameOfDecodedCode);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1627
	nextPutAll:'->';
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1628
	nextPutAll:(encoder1 nameOfEncoding);
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1629
	nextPutAll:'->';
30b63b09b99a *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8135
diff changeset
  1630
	nextPutAll:(encoder2 nameOfEncoding)
7972
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1631
! !
91aa73f89491 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 7971
diff changeset
  1632
11300
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1633
!CharacterEncoder::TwoStepEncoder methodsFor:'queries'!
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1634
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1635
nameOfEncoding
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1636
    ^ "encoder1 nameOfEncoding , '-' ," encoder2 nameOfEncoding
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1637
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1638
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1639
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1640
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1641
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1642
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1643
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1644
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1645
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1646
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1647
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1648
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1649
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1650
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1651
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1652
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1653
! !
2e90a91ff766 nameOf two-step encoder
Claus Gittinger <cg@exept.de>
parents: 11295
diff changeset
  1654
7892
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1655
!CharacterEncoder class methodsFor:'documentation'!
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1656
149a145e871c initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
  1657
version
14174
3a4f041c94a2 changed: #supportedExternalEncodings
Michael Beyl <mb@exept.de>
parents: 14169
diff changeset
  1658
    ^ '$Header: /cvs/stx/stx/libbasic/CharacterEncoder.st,v 1.114 2012-07-11 11:38:13 mb Exp $'
12435
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1659
!
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1660
539c24148e90 added: #readNextInputCharacterFrom:
Claus Gittinger <cg@exept.de>
parents: 11975
diff changeset
  1661
version_CVS
14174
3a4f041c94a2 changed: #supportedExternalEncodings
Michael Beyl <mb@exept.de>
parents: 14169
diff changeset
  1662
    ^ '$Header: /cvs/stx/stx/libbasic/CharacterEncoder.st,v 1.114 2012-07-11 11:38:13 mb Exp $'
7899
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1663
! !
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1664
7577df77ba95 character encodings - first attempt
Claus Gittinger <cg@exept.de>
parents: 7893
diff changeset
  1665
CharacterEncoder initialize!