Encoder_ISO10646_to_SGML.st
author Claus Gittinger <cg@exept.de>
Wed, 15 Mar 2006 11:37:12 +0100
changeset 9284 6afd161ee43c
parent 8171 ac837a7ca3a3
child 10108 8e610353f2fa
permissions -rw-r--r--
+skipTo:
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
8171
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     1
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     2
 COPYRIGHT (c) 2004 by eXept Software AG
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     3
              All Rights Reserved
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     4
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     5
 This software is furnished under a license and may be used
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     6
 only in accordance with the terms of that license and with the
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     7
 inclusion of the above copyright notice.   This software may not
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     8
 be provided or otherwise made available to, or used by, any
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
     9
 other person.  No title to or ownership of the software is
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    10
 hereby transferred.
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    11
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    12
8170
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    13
"{ Package: 'stx:libbasic' }"
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    14
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    15
"{ NameSpace: CharacterEncoderImplementations }"
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    16
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    17
TwoByteEncoder subclass:#ISO10646_to_SGML
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    18
	instanceVariableNames:''
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    19
	classVariableNames:''
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    20
	poolDictionaries:''
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    21
	category:'Collections-Text-Encodings'
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    22
!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    23
8171
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    24
!ISO10646_to_SGML class methodsFor:'documentation'!
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    25
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    26
copyright
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    27
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    28
 COPYRIGHT (c) 2004 by eXept Software AG
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    29
              All Rights Reserved
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    30
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    31
 This software is furnished under a license and may be used
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    32
 only in accordance with the terms of that license and with the
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    33
 inclusion of the above copyright notice.   This software may not
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    34
 be provided or otherwise made available to, or used by, any
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    35
 other person.  No title to or ownership of the software is
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    36
 hereby transferred.
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    37
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    38
!
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    39
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    40
documentation
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    41
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    42
    Incomplete - only knows how to encode/decode escaped decimal-code characters
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    43
    (i.e. &#nnnn; )
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    44
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    45
    TODO:
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    46
        add all other characters
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    47
        reuse this code in XML and HTML processing code.
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    48
"
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
    49
! !
8170
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    50
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    51
!ISO10646_to_SGML methodsFor:'encoding & decoding'!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    52
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    53
decode:aCode
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    54
    self shouldNotImplement "/ no single byte conversion possible
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    55
!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    56
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    57
decodeString:aStringOrByteCollection
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    58
    "given a string in SGML encoding (i.e. with SGML escaped characters),
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    59
     return a new string containing the same characters, in 16bit (or more) encoding.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    60
     Returns either a normal String, a TwoByteString or a FourByteString instance.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    61
     Only useful, when reading from external sources.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    62
     This only handles up-to 30bit characters."
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    63
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    64
    |nBits ch 
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    65
     in out codePoint t|
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    66
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    67
    nBits := 8.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    68
    in := aStringOrByteCollection readStream.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    69
    out := WriteStream on:(String new:10).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    70
    [in atEnd] whileFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    71
        ch := in next.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    72
        ch == $& ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    73
            in peekOrNil == $# ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    74
                in next.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    75
                codePoint := 0.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    76
                [ch := in peekOrNil.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    77
                 ch notNil and:[ch isDigit]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    78
                ] whileTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    79
                    codePoint := (codePoint * 10) + ch digitValue.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    80
                    in next.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    81
                ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    82
                codePoint > 16rFF ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    83
                    codePoint > 16rFFFF ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    84
                        nBits < 32 ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    85
                            t := out contents.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    86
                            out := WriteStream on:(Unicode32String fromString:t).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    87
                            out position:t size.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    88
                            nBits := 32.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    89
                        ]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    90
                    ] ifFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    91
                        nBits < 16 ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    92
                            t := out contents.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    93
                            out := WriteStream on:(Unicode16String fromString:t).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    94
                            out position:t size.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    95
                            nBits := 16.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    96
                        ]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    97
                    ]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    98
                ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    99
                out nextPut:(Character value:codePoint).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   100
                in peekOrNil == $; ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   101
                    in next.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   102
                ]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   103
            ] ifFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   104
                out nextPut:ch
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   105
            ]
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   106
        ] ifFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   107
            out nextPut:ch
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   108
        ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   109
    ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   110
    ^ out contents
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   111
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   112
    "
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   113
     CharacterEncoderImplementations::ISO10646_to_SGML
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   114
        decodeString:'&#1060;&#1072;&#1081;&#1083;' 
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   115
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   116
     CharacterEncoderImplementations::ISO10646_to_SGML
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   117
        decodeString:'#197;&bn...'
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   118
    "
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   119
!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   120
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   121
encode:aCode
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   122
    self shouldNotImplement "/ no single byte conversion possible
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   123
!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   124
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   125
encodeString:aUnicodeString
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   126
    "return the UTF-8 representation of a aUnicodeString.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   127
     The resulting string is only useful to be stored on some external file,
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   128
     not for being used inside ST/X.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   129
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   130
     If you work a lot with utf8 encoded textFiles, 
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   131
     this is a first-class candidate for a primitive."
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   132
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   133
    |ch in out codePoint|
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   134
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   135
    in := aUnicodeString readStream.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   136
    out := WriteStream on:(String new:10).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   137
    [in atEnd] whileFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   138
        ch := in next.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   139
        codePoint := ch codePoint.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   140
        (codePoint between:16r20 and:16r7F) ifTrue:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   141
            out nextPut:ch.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   142
        ] ifFalse:[
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   143
            out nextPutAll:'&#'.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   144
            out nextPutAll:(codePoint printString).
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   145
            out nextPutAll:';'.
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   146
        ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   147
    ].
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   148
    ^ out contents
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   149
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   150
    "
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   151
     CharacterEncoderImplementations::ISO10646_to_SGML
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   152
        encodeString:'hello äöü' 
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   153
    "
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   154
! !
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   155
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   156
!ISO10646_to_SGML class methodsFor:'documentation'!
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   157
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   158
version
8171
ac837a7ca3a3 *** empty log message ***
Claus Gittinger <cg@exept.de>
parents: 8170
diff changeset
   159
    ^ '$Header: /cvs/stx/stx/libbasic/Attic/Encoder_ISO10646_to_SGML.st,v 1.2 2004-03-12 12:52:36 cg Exp $'
8170
ffa1ed9338ad initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   160
! !