File: strconv.h

package info (click to toggle)
wxpython4.0 4.2.3%2Bdfsg-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 221,752 kB
  • sloc: cpp: 962,555; python: 230,573; ansic: 170,731; makefile: 51,756; sh: 9,342; perl: 1,564; javascript: 584; php: 326; xml: 200
file content (737 lines) | stat: -rw-r--r-- 29,348 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
///////////////////////////////////////////////////////////////////////////////
// Name:        wx/strconv.h
// Purpose:     conversion routines for char sets any Unicode
// Author:      Ove Kaaven, Robert Roebling, Vadim Zeitlin
// Modified by:
// Created:     29/01/98
// Copyright:   (c) 1998 Ove Kaaven, Robert Roebling
//              (c) 1998-2006 Vadim Zeitlin
// Licence:     wxWindows licence
///////////////////////////////////////////////////////////////////////////////

#ifndef _WX_STRCONV_H_
#define _WX_STRCONV_H_

#include "wx/defs.h"
#include "wx/chartype.h"
#include "wx/buffer.h"

#include <stdlib.h>

class WXDLLIMPEXP_FWD_BASE wxString;

// the error value returned by wxMBConv methods
#define wxCONV_FAILED ((size_t)-1)

// ----------------------------------------------------------------------------
// wxMBConv (abstract base class for conversions)
// ----------------------------------------------------------------------------

// When deriving a new class from wxMBConv you must reimplement ToWChar() and
// FromWChar() methods which are not pure virtual only for historical reasons,
// don't let the fact that the existing classes implement MB2WC/WC2MB() instead
// confuse you.
//
// For many encodings you must override GetMaxCharLen().
//
// You also have to implement Clone() to allow copying the conversions
// polymorphically.
//
// And you might need to override GetMBNulLen() as well.
class WXDLLIMPEXP_BASE wxMBConv
{
public:
    // The functions doing actual conversion from/to narrow to/from wide
    // character strings.
    //
    // On success, the return value is the length (i.e. the number of
    // characters, not bytes) of the converted string including any trailing
    // L'\0' or (possibly multiple) '\0'(s). If the conversion fails or if
    // there is not enough space for everything, including the trailing NUL
    // character(s), in the output buffer, wxCONV_FAILED is returned.
    //
    // In the special case when dst is NULL (the value of dstLen is ignored
    // then) the return value is the length of the needed buffer but nothing
    // happens otherwise. If srcLen is wxNO_LEN, the entire string, up to and
    // including the trailing NUL(s), is converted, otherwise exactly srcLen
    // bytes are.
    //
    // Typical usage:
    //
    //          size_t dstLen = conv.ToWChar(NULL, 0, src);
    //          if ( dstLen == wxCONV_FAILED )
    //              ... handle error ...
    //          wchar_t *wbuf = new wchar_t[dstLen];
    //          conv.ToWChar(wbuf, dstLen, src);
    //          ... work with wbuf ...
    //          delete [] wbuf;
    //
    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const;

    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const;


    // Convenience functions for translating NUL-terminated strings: return
    // the buffer containing the converted string or empty buffer if the
    // conversion failed.
    wxWCharBuffer cMB2WC(const char *in) const
        { return DoConvertMB2WC(in, wxNO_LEN); }
    wxCharBuffer cWC2MB(const wchar_t *in) const
        { return DoConvertWC2MB(in, wxNO_LEN); }

    wxWCharBuffer cMB2WC(const wxScopedCharBuffer& in) const
        { return DoConvertMB2WC(in, in.length()); }
    wxCharBuffer cWC2MB(const wxScopedWCharBuffer& in) const
        { return DoConvertWC2MB(in, in.length()); }


    // Convenience functions for converting strings which may contain embedded
    // NULs and don't have to be NUL-terminated.
    //
    // inLen is the length of the buffer including trailing NUL if any or
    // wxNO_LEN if the input is NUL-terminated.
    //
    // outLen receives, if not NULL, the length of the converted string or 0 if
    // the conversion failed (returning 0 and not -1 in this case makes it
    // difficult to distinguish between failed conversion and empty input but
    // this is done for backwards compatibility). Notice that the rules for
    // whether outLen accounts or not for the last NUL are the same as for
    // To/FromWChar() above: if inLen is specified, outLen is exactly the
    // number of characters converted, whether the last one of them was NUL or
    // not. But if inLen == wxNO_LEN then outLen doesn't account for the last
    // NUL even though it is present.
    wxWCharBuffer
        cMB2WC(const char *in, size_t inLen, size_t *outLen) const;
    wxCharBuffer
        cWC2MB(const wchar_t *in, size_t inLen, size_t *outLen) const;

    // convenience functions for converting MB or WC to/from wxWin default
#if wxUSE_UNICODE
    wxWCharBuffer cMB2WX(const char *psz) const { return cMB2WC(psz); }
    wxCharBuffer cWX2MB(const wchar_t *psz) const { return cWC2MB(psz); }
    const wchar_t* cWC2WX(const wchar_t *psz) const { return psz; }
    const wchar_t* cWX2WC(const wchar_t *psz) const { return psz; }
#else // ANSI
    const char* cMB2WX(const char *psz) const { return psz; }
    const char* cWX2MB(const char *psz) const { return psz; }
    wxCharBuffer cWC2WX(const wchar_t *psz) const { return cWC2MB(psz); }
    wxWCharBuffer cWX2WC(const char *psz) const { return cMB2WC(psz); }
#endif // Unicode/ANSI

    // return the maximum number of bytes that can be required to encode a
    // single character in this encoding, e.g. 4 for UTF-8
    virtual size_t GetMaxCharLen() const { return 1; }

    // this function is used in the implementation of cMB2WC() to distinguish
    // between the following cases:
    //
    //      a) var width encoding with strings terminated by a single NUL
    //         (usual multibyte encodings): return 1 in this case
    //      b) fixed width encoding with 2 bytes/char and so terminated by
    //         2 NULs (UTF-16/UCS-2 and variants): return 2 in this case
    //      c) fixed width encoding with 4 bytes/char and so terminated by
    //         4 NULs (UTF-32/UCS-4 and variants): return 4 in this case
    //
    // anything else is not supported currently and -1 should be returned
    virtual size_t GetMBNulLen() const { return 1; }

    // return the maximal value currently returned by GetMBNulLen() for any
    // encoding
    static size_t GetMaxMBNulLen() { return 4 /* for UTF-32 */; }

    // return true if the converter's charset is UTF-8, i.e. char* strings
    // decoded using this object can be directly copied to wxString's internal
    // storage without converting to WC and then back to UTF-8 MB string
    virtual bool IsUTF8() const { return false; }

    // The old conversion functions. The existing classes currently mostly
    // implement these ones but we're in transition to using To/FromWChar()
    // instead and any new classes should implement just the new functions.
    // For now, however, we provide default implementation of To/FromWChar() in
    // this base class in terms of MB2WC/WC2MB() to avoid having to rewrite all
    // the conversions at once.
    //
    // On success, the return value is the length (i.e. the number of
    // characters, not bytes) not counting the trailing NUL(s) of the converted
    // string. On failure, (size_t)-1 is returned. In the special case when
    // outputBuf is NULL the return value is the same one but nothing is
    // written to the buffer.
    //
    // Note that outLen is the length of the output buffer, not the length of
    // the input (which is always supposed to be terminated by one or more
    // NULs, as appropriate for the encoding)!
    virtual size_t MB2WC(wchar_t *out, const char *in, size_t outLen) const;
    virtual size_t WC2MB(char *out, const wchar_t *in, size_t outLen) const;


    // make a heap-allocated copy of this object
    virtual wxMBConv *Clone() const = 0;

    // virtual dtor for any base class
    virtual ~wxMBConv() { }

private:
    // Common part of single argument cWC2MB() and cMB2WC() overloads above.
    wxCharBuffer DoConvertWC2MB(const wchar_t* pwz, size_t srcLen) const;
    wxWCharBuffer DoConvertMB2WC(const char* psz, size_t srcLen) const;
};

// ----------------------------------------------------------------------------
// wxMBConvLibc uses standard mbstowcs() and wcstombs() functions for
//              conversion (hence it depends on the current locale)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvLibc : public wxMBConv
{
public:
    virtual size_t MB2WC(wchar_t *outputBuf, const char *psz, size_t outputSize) const wxOVERRIDE;
    virtual size_t WC2MB(char *outputBuf, const wchar_t *psz, size_t outputSize) const wxOVERRIDE;

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvLibc; }

    virtual bool IsUTF8() const wxOVERRIDE { return wxLocaleIsUtf8; }
};

#ifdef __UNIX__

// ----------------------------------------------------------------------------
// wxConvBrokenFileNames is made for Unix in Unicode mode when
// files are accidentally written in an encoding which is not
// the system encoding. Typically, the system encoding will be
// UTF8 but there might be files stored in ISO8859-1 on disk.
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxConvBrokenFileNames : public wxMBConv
{
public:
    wxConvBrokenFileNames(const wxString& charset);
    wxConvBrokenFileNames(const wxConvBrokenFileNames& conv)
        : wxMBConv(),
          m_conv(conv.m_conv ? conv.m_conv->Clone() : NULL)
    {
    }
    virtual ~wxConvBrokenFileNames() { delete m_conv; }

    virtual size_t MB2WC(wchar_t *out, const char *in, size_t outLen) const wxOVERRIDE
    {
        return m_conv->MB2WC(out, in, outLen);
    }

    virtual size_t WC2MB(char *out, const wchar_t *in, size_t outLen) const wxOVERRIDE
    {
        return m_conv->WC2MB(out, in, outLen);
    }

    virtual size_t GetMBNulLen() const wxOVERRIDE
    {
        // cast needed to call a private function
        return m_conv->GetMBNulLen();
    }

    virtual bool IsUTF8() const wxOVERRIDE { return m_conv->IsUTF8(); }

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxConvBrokenFileNames(*this); }

private:
    // the conversion object we forward to
    wxMBConv *m_conv;

    wxDECLARE_NO_ASSIGN_CLASS(wxConvBrokenFileNames);
};

#endif // __UNIX__

// ----------------------------------------------------------------------------
// wxMBConvUTF7 (for conversion using UTF7 encoding)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF7 : public wxMBConv
{
public:
    wxMBConvUTF7() { }

    // compiler-generated copy ctor, assignment operator and dtor are ok
    // (assuming it's ok to copy the shift state -- not really sure about it)

    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;

    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF7; }

private:
    // UTF-7 decoder/encoder may be in direct mode or in shifted mode after a
    // '+' (and until the '-' or any other non-base64 character)
    struct StateMode
    {
        enum Mode
        {
            Direct,     // pass through state
            Shifted     // after a '+' (and before '-')
        };
    };

    // the current decoder state: this is only used by ToWChar() if srcLen
    // parameter is not wxNO_LEN, when working on the entire NUL-terminated
    // strings we neither update nor use the state
    class DecoderState : private StateMode
    {
    private:
        // current state: this one is private as we want to enforce the use of
        // ToDirect/ToShifted() methods below
        Mode mode;

    public:
        // the initial state is direct
        DecoderState() { mode = Direct; accum = bit = msb = 0; isLSB = false; }

        // switch to/from shifted mode
        void ToDirect() { mode = Direct; }
        void ToShifted() { mode = Shifted; accum = bit = 0; isLSB = false; }

        bool IsDirect() const { return mode == Direct; }
        bool IsShifted() const { return mode == Shifted; }


        // these variables are only used in shifted mode

        unsigned int accum; // accumulator of the bit we've already got
        unsigned int bit;   // the number of bits consumed mod 8
        unsigned char msb;  // the high byte of UTF-16 word
        bool isLSB;         // whether we're decoding LSB or MSB of UTF-16 word
    };

    DecoderState m_stateDecoder;


    // encoder state is simpler as we always receive entire Unicode characters
    // on input
    class EncoderState : private StateMode
    {
    private:
        Mode mode;

    public:
        EncoderState() { mode = Direct; accum = bit = 0; }

        void ToDirect() { mode = Direct; }
        void ToShifted() { mode = Shifted; accum = bit = 0; }

        bool IsDirect() const { return mode == Direct; }
        bool IsShifted() const { return mode == Shifted; }

        unsigned int accum;
        unsigned int bit;
    };

    EncoderState m_stateEncoder;
};

// ----------------------------------------------------------------------------
// wxMBConvUTF8 (for conversion using UTF8 encoding)
// ----------------------------------------------------------------------------

// this is the real UTF-8 conversion class, it has to be called "strict UTF-8"
// for compatibility reasons: the wxMBConvUTF8 class below also supports lossy
// conversions if it is created with non default options
class WXDLLIMPEXP_BASE wxMBConvStrictUTF8 : public wxMBConv
{
public:
    // compiler-generated default ctor and other methods are ok

    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;

    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvStrictUTF8(); }

    // NB: other mapping modes are not, strictly speaking, UTF-8, so we can't
    //     take the shortcut in that case
    virtual bool IsUTF8() const wxOVERRIDE { return true; }
};

class WXDLLIMPEXP_BASE wxMBConvUTF8 : public wxMBConvStrictUTF8
{
public:
    enum
    {
        MAP_INVALID_UTF8_NOT = 0,
        MAP_INVALID_UTF8_TO_PUA = 1,
        MAP_INVALID_UTF8_TO_OCTAL = 2
    };

    wxMBConvUTF8(int options = MAP_INVALID_UTF8_NOT) : m_options(options) { }

    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;

    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF8(m_options); }

    // NB: other mapping modes are not, strictly speaking, UTF-8, so we can't
    //     take the shortcut in that case
    virtual bool IsUTF8() const wxOVERRIDE { return m_options == MAP_INVALID_UTF8_NOT; }

private:
    int m_options;
};

// ----------------------------------------------------------------------------
// wxMBConvUTF16Base: for both LE and BE variants
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF16Base : public wxMBConv
{
public:
    enum { BYTES_PER_CHAR = 2 };

    virtual size_t GetMBNulLen() const wxOVERRIDE { return BYTES_PER_CHAR; }

protected:
    // return the length of the buffer using srcLen if it's not wxNO_LEN and
    // computing the length ourselves if it is; also checks that the length is
    // even if specified as we need an entire number of UTF-16 characters and
    // returns wxNO_LEN which indicates error if it is odd
    static size_t GetLength(const char *src, size_t srcLen);
};

// ----------------------------------------------------------------------------
// wxMBConvUTF16LE (for conversion using UTF16 Little Endian encoding)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF16LE : public wxMBConvUTF16Base
{
public:
    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }
    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF16LE; }
};

// ----------------------------------------------------------------------------
// wxMBConvUTF16BE (for conversion using UTF16 Big Endian encoding)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF16BE : public wxMBConvUTF16Base
{
public:
    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }
    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF16BE; }
};

// ----------------------------------------------------------------------------
// wxMBConvUTF32Base: base class for both LE and BE variants
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF32Base : public wxMBConv
{
public:
    enum { BYTES_PER_CHAR = 4 };

    virtual size_t GetMBNulLen() const wxOVERRIDE { return BYTES_PER_CHAR; }

protected:
    // this is similar to wxMBConvUTF16Base method with the same name except
    // that, of course, it verifies that length is divisible by 4 if given and
    // not by 2
    static size_t GetLength(const char *src, size_t srcLen);
};

// ----------------------------------------------------------------------------
// wxMBConvUTF32LE (for conversion using UTF32 Little Endian encoding)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF32LE : public wxMBConvUTF32Base
{
public:
    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }
    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF32LE; }
};

// ----------------------------------------------------------------------------
// wxMBConvUTF32BE (for conversion using UTF32 Big Endian encoding)
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxMBConvUTF32BE : public wxMBConvUTF32Base
{
public:
    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }
    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxMBConvUTF32BE; }
};

// ----------------------------------------------------------------------------
// wxCSConv (for conversion based on loadable char sets)
// ----------------------------------------------------------------------------

#include "wx/fontenc.h"

class WXDLLIMPEXP_BASE wxCSConv : public wxMBConv
{
public:
    // we can be created either from charset name or from an encoding constant
    // but we can't have both at once
    wxCSConv(const wxString& charset);
    wxCSConv(wxFontEncoding encoding);

    wxCSConv(const wxCSConv& conv);
    virtual ~wxCSConv();

    wxCSConv& operator=(const wxCSConv& conv);

    virtual size_t ToWChar(wchar_t *dst, size_t dstLen,
                           const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t FromWChar(char *dst, size_t dstLen,
                             const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;
    virtual size_t GetMBNulLen() const wxOVERRIDE;

    virtual bool IsUTF8() const wxOVERRIDE;

    virtual wxMBConv *Clone() const wxOVERRIDE { return new wxCSConv(*this); }

    void Clear();

    // return true if the conversion could be initialized successfully
    bool IsOk() const;

private:
    // common part of all ctors
    void Init();

    // Creates the conversion to use, called from all ctors to initialize
    // m_convReal.
    wxMBConv *DoCreate() const;

    // Set the name (may be only called when m_name == NULL), makes copy of
    // the charset string.
    void SetName(const char *charset);

    // Set m_encoding field respecting the rules below, i.e. making sure it has
    // a valid value if m_name == NULL (thus this should be always called after
    // SetName()).
    //
    // Input encoding may be valid or not.
    void SetEncoding(wxFontEncoding encoding);


    // The encoding we use is specified by the two fields below:
    //
    //  1. If m_name != NULL, m_encoding corresponds to it if it's one of
    //     encodings we know about (i.e. member of wxFontEncoding) or is
    //     wxFONTENCODING_SYSTEM otherwise.
    //
    //  2. If m_name == NULL, m_encoding is always valid, i.e. not one of
    //     wxFONTENCODING_{SYSTEM,DEFAULT,MAX}.
    char *m_name;
    wxFontEncoding m_encoding;

    // The conversion object for our encoding or NULL if we failed to create it
    // in which case we fall back to hard-coded ISO8859-1 conversion.
    wxMBConv *m_convReal;
};

// ----------------------------------------------------------------------------
// wxWhateverWorksConv: use whatever encoding works for the input
// ----------------------------------------------------------------------------

class WXDLLIMPEXP_BASE wxWhateverWorksConv : public wxMBConv
{
public:
    wxWhateverWorksConv()
    {
    }

    // Try to interpret the string as UTF-8, if it fails fall back to the
    // current locale encoding (wxConvLibc) and if this fails as well,
    // interpret it as wxConvISO8859_1 (which is used because it never fails
    // and this conversion is used when we really, really must produce
    // something on output).
    virtual size_t
    ToWChar(wchar_t *dst, size_t dstLen,
            const char *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;

    // Try to encode the string using the current locale encoding (wxConvLibc)
    // and fall back to UTF-8 (which never fails) if it doesn't work. Note that
    // we never use wxConvISO8859_1 here as we prefer to fall back on UTF-8
    // even for the strings containing only code points representable in 8869-1.
    virtual size_t
    FromWChar(char *dst, size_t dstLen,
              const wchar_t *src, size_t srcLen = wxNO_LEN) const wxOVERRIDE;

    // Use the value for UTF-8 here to make sure we try to decode up to 4 bytes
    // as UTF-8 before giving up.
    virtual size_t GetMaxCharLen() const wxOVERRIDE { return 4; }

    virtual wxMBConv *Clone() const wxOVERRIDE
    {
        return new wxWhateverWorksConv();
    }
};

// ----------------------------------------------------------------------------
// declare predefined conversion objects
// ----------------------------------------------------------------------------

// Note: this macro is an implementation detail (see the comment in
// strconv.cpp). The wxGet_XXX() and wxGet_XXXPtr() functions shouldn't be
// used by user code and neither should XXXPtr, use the wxConvXXX macro
// instead.
#define WX_DECLARE_GLOBAL_CONV(klass, name)                             \
    extern WXDLLIMPEXP_DATA_BASE(klass*) name##Ptr;                     \
    extern WXDLLIMPEXP_BASE klass* wxGet_##name##Ptr();                 \
    inline klass& wxGet_##name()                                        \
    {                                                                   \
        if ( !name##Ptr )                                               \
            name##Ptr = wxGet_##name##Ptr();                            \
        return *name##Ptr;                                              \
    }


// conversion to be used with all standard functions affected by locale, e.g.
// strtol(), strftime(), ...
WX_DECLARE_GLOBAL_CONV(wxMBConv, wxConvLibc)
#define wxConvLibc wxGet_wxConvLibc()

// conversion ISO-8859-1/UTF-7/UTF-8 <-> wchar_t
WX_DECLARE_GLOBAL_CONV(wxCSConv, wxConvISO8859_1)
#define wxConvISO8859_1 wxGet_wxConvISO8859_1()

WX_DECLARE_GLOBAL_CONV(wxMBConvStrictUTF8, wxConvUTF8)
#define wxConvUTF8 wxGet_wxConvUTF8()

WX_DECLARE_GLOBAL_CONV(wxMBConvUTF7, wxConvUTF7)
#define wxConvUTF7 wxGet_wxConvUTF7()

// conversion used when we may not afford to lose data when outputting Unicode
// strings (should be avoid in the other direction as it can misinterpret the
// input encoding)
WX_DECLARE_GLOBAL_CONV(wxWhateverWorksConv, wxConvWhateverWorks)
#define wxConvWhateverWorks wxGet_wxConvWhateverWorks()

// conversion used for the file names on the systems where they're not Unicode
// (basically anything except Windows)
//
// this is used by all file functions, can be changed by the application
//
// by default UTF-8 under Mac OS X and wxConvLibc elsewhere (but it's not used
// under Windows normally)
extern WXDLLIMPEXP_DATA_BASE(wxMBConv *) wxConvFileName;

// backwards compatible define
#define wxConvFile (*wxConvFileName)

// the current conversion object, may be set to any conversion, is used by
// default in a couple of places inside wx (initially same as wxConvLibc)
extern WXDLLIMPEXP_DATA_BASE(wxMBConv *) wxConvCurrent;

// the conversion corresponding to the current locale
WX_DECLARE_GLOBAL_CONV(wxCSConv, wxConvLocal)
#define wxConvLocal wxGet_wxConvLocal()

// the conversion corresponding to the encoding of the standard UI elements
//
// by default this is the same as wxConvLocal but may be changed if the program
// needs to use a fixed encoding
extern WXDLLIMPEXP_DATA_BASE(wxMBConv *) wxConvUI;

#undef WX_DECLARE_GLOBAL_CONV

// ----------------------------------------------------------------------------
// endianness-dependent conversions
// ----------------------------------------------------------------------------

#ifdef WORDS_BIGENDIAN
    typedef wxMBConvUTF16BE wxMBConvUTF16;
    typedef wxMBConvUTF32BE wxMBConvUTF32;
#else
    typedef wxMBConvUTF16LE wxMBConvUTF16;
    typedef wxMBConvUTF32LE wxMBConvUTF32;
#endif

// ----------------------------------------------------------------------------
// filename conversion macros
// ----------------------------------------------------------------------------

// filenames are multibyte on Unix and widechar on Windows
#if wxMBFILES && wxUSE_UNICODE
    #define wxFNCONV(name) wxConvFileName->cWX2MB(name)
    #define wxFNSTRINGCAST wxMBSTRINGCAST
#else
#if defined(__WXOSX__) && wxMBFILES
    #define wxFNCONV(name) wxConvFileName->cWC2MB( wxConvLocal.cWX2WC(name) )
#else
    #define wxFNCONV(name) name
#endif
    #define wxFNSTRINGCAST WXSTRINGCAST
#endif

// ----------------------------------------------------------------------------
// macros for the most common conversions
// ----------------------------------------------------------------------------

#if wxUSE_UNICODE
    #define wxConvertWX2MB(s)   wxConvCurrent->cWX2MB(s)
    #define wxConvertMB2WX(s)   wxConvCurrent->cMB2WX(s)

    // these functions should be used when the conversions really, really have
    // to succeed (usually because we pass their results to a standard C
    // function which would crash if we passed NULL to it), so these functions
    // always return a valid pointer if their argument is non-NULL

    inline wxWCharBuffer wxSafeConvertMB2WX(const char *s)
    {
        return wxConvWhateverWorks.cMB2WC(s);
    }

    inline wxCharBuffer wxSafeConvertWX2MB(const wchar_t *ws)
    {
        return wxConvWhateverWorks.cWC2MB(ws);
    }
#else // ANSI
    // no conversions to do
    #define wxConvertWX2MB(s)   (s)
    #define wxConvertMB2WX(s)   (s)
    #define wxSafeConvertMB2WX(s) (s)
    #define wxSafeConvertWX2MB(s) (s)
#endif // Unicode/ANSI

// Macro that indicates the default encoding for converting C strings
// to wxString. It provides a default value for a const wxMBConv&
// parameter (i.e. wxConvLibc) unless wxNO_IMPLICIT_WXSTRING_ENCODING
// is defined.
//
// Intended use:
// wxString(const char *data, ...,
//          const wxMBConv &conv wxSTRING_DEFAULT_CONV_ARG);
#ifndef wxNO_IMPLICIT_WXSTRING_ENCODING
#define wxSTRING_DEFAULT_CONV_ARG = wxConvLibc
#else
#define wxSTRING_DEFAULT_CONV_ARG
#endif

#endif // _WX_STRCONV_H_