summaryrefslogtreecommitdiffstats
path: root/common/utf8conv.c
blob: bce9e3ac65b5bdfd71a9bc25d947637c0a74fe6e (plain)
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
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
/* utf8conf.c -  UTF8 character set conversion
 * Copyright (C) 1994, 1998, 1999, 2000, 2001, 2003, 2006,
 *               2008, 2010  Free Software Foundation, Inc.
 *
 * This file is part of GnuPG.
 *
 * GnuPG is free software; you can redistribute it and/or modify it
 * under the terms of either
 *
 *   - the GNU Lesser General Public License as published by the Free
 *     Software Foundation; either version 3 of the License, or (at
 *     your option) any later version.
 *
 * or
 *
 *   - the GNU General Public License as published by the Free
 *     Software Foundation; either version 2 of the License, or (at
 *     your option) any later version.
 *
 * or both in parallel, as here.
 *
 * GnuPG is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copies of the GNU General Public License
 * and the GNU Lesser General Public License along with this program;
 * if not, see <https://www.gnu.org/licenses/>.
 */

#include <config.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
#include <ctype.h>
#ifdef HAVE_LANGINFO_CODESET
#include <langinfo.h>
#endif
#include <errno.h>

#if HAVE_W32_SYSTEM
# /* Tell libgpg-error to provide the iconv macros.  */
# define GPGRT_ENABLE_W32_ICONV_MACROS 1
#elif HAVE_ANDROID_SYSTEM
# /* No iconv support.  */
#else
# include <iconv.h>
#endif


#include "util.h"
#include "common-defs.h"
#include "i18n.h"
#include "stringhelp.h"
#include "utf8conv.h"

#ifndef MB_LEN_MAX
#define MB_LEN_MAX 16
#endif

static const char *active_charset_name = "iso-8859-1";
static int no_translation;     /* Set to true if we let simply pass through. */
static int use_iconv;          /* iconv conversion functions required. */


#ifdef HAVE_ANDROID_SYSTEM
/* Fake stuff to get things building.  */
typedef void *iconv_t;
#define ICONV_CONST

static iconv_t
iconv_open (const char *tocode, const char *fromcode)
{
  (void)tocode;
  (void)fromcode;
  return (iconv_t)(-1);
}

static size_t
iconv (iconv_t cd, char **inbuf, size_t *inbytesleft,
       char **outbuf, size_t *outbytesleft)
{
  (void)cd;
  (void)inbuf;
  (void)inbytesleft;
  (void)outbuf;
  (void)outbytesleft;
  return (size_t)(0);
}

static int
iconv_close (iconv_t cd)
{
  (void)cd;
  return 0;
}
#endif /*HAVE_ANDROID_SYSTEM*/


/* Error handler for iconv failures. This is needed to not clutter the
   output with repeated diagnostics about a missing conversion. */
static void
handle_iconv_error (const char *to, const char *from, int use_fallback)
{
  if (errno == EINVAL)
    {
      static int shown1, shown2;
      int x;

      if (to && !strcmp (to, "utf-8"))
        {
          x = shown1;
          shown1 = 1;
        }
      else
        {
          x = shown2;
          shown2 = 1;
        }

      if (!x)
        log_info (_("conversion from '%s' to '%s' not available\n"),
                  from, to);
    }
  else
    {
      static int shown;

      if (!shown)
        log_info (_("iconv_open failed: %s\n"), strerror (errno));
      shown = 1;
    }

  if (use_fallback)
    {
      /* To avoid further error messages we fallback to UTF-8 for the
         native encoding.  Nowadays this seems to be the best bet in
         case of errors from iconv or nl_langinfo.  */
      active_charset_name = "utf-8";
      no_translation = 0;
      use_iconv = 0;
    }
}



int
set_native_charset (const char *newset)
{
  const char *full_newset;

  if (!newset)
    {
#ifdef HAVE_ANDROID_SYSTEM
      newset = "utf-8";
#elif defined HAVE_W32_SYSTEM
      static char codepage[30];
      unsigned int cpno;
      const char *aliases;

      /* We are a console program thus we need to use the
         GetConsoleOutputCP function and not the the GetACP which
         would give the codepage for a GUI program.  Note this is not
         a bulletproof detection because GetConsoleCP might return a
         different one for console input.  Not sure how to cope with
         that.  If the console Code page is not known we fall back to
         the system code page.  */
#ifndef HAVE_W32CE_SYSTEM
      cpno = GetConsoleOutputCP ();
      if (!cpno)
#endif
        cpno = GetACP ();
      sprintf (codepage, "CP%u", cpno );
      /* Resolve alias.  We use a long string string and not the usual
         array to optimize if the code is taken to a DSO.  Taken from
         libiconv 1.9.2. */
      newset = codepage;
      for (aliases = ("CP936"   "\0" "GBK" "\0"
                      "CP1361"  "\0" "JOHAB" "\0"
                      "CP20127" "\0" "ASCII" "\0"
                      "CP20866" "\0" "KOI8-R" "\0"
                      "CP21866" "\0" "KOI8-RU" "\0"
                      "CP28591" "\0" "ISO-8859-1" "\0"
                      "CP28592" "\0" "ISO-8859-2" "\0"
                      "CP28593" "\0" "ISO-8859-3" "\0"
                      "CP28594" "\0" "ISO-8859-4" "\0"
                      "CP28595" "\0" "ISO-8859-5" "\0"
                      "CP28596" "\0" "ISO-8859-6" "\0"
                      "CP28597" "\0" "ISO-8859-7" "\0"
                      "CP28598" "\0" "ISO-8859-8" "\0"
                      "CP28599" "\0" "ISO-8859-9" "\0"
                      "CP28605" "\0" "ISO-8859-15" "\0"
                      "CP65001" "\0" "UTF-8" "\0");
           *aliases;
           aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1)
        {
          if (!strcmp (codepage, aliases) ||(*aliases == '*' && !aliases[1]))
            {
              newset = aliases + strlen (aliases) + 1;
              break;
            }
        }

#else /*!HAVE_W32_SYSTEM && !HAVE_ANDROID_SYSTEM*/

#ifdef HAVE_LANGINFO_CODESET
      newset = nl_langinfo (CODESET);
#else /*!HAVE_LANGINFO_CODESET*/
      /* Try to get the used charset from environment variables.  */
      static char codepage[30];
      const char *lc, *dot, *mod;

      strcpy (codepage, "iso-8859-1");
      lc = getenv ("LC_ALL");
      if (!lc || !*lc)
        {
          lc = getenv ("LC_CTYPE");
          if (!lc || !*lc)
            lc = getenv ("LANG");
        }
      if (lc && *lc)
        {
          dot = strchr (lc, '.');
          if (dot)
            {
              mod = strchr (++dot, '@');
              if (!mod)
                mod = dot + strlen (dot);
              if (mod - dot < sizeof codepage && dot != mod)
                {
                  memcpy (codepage, dot, mod - dot);
                  codepage [mod - dot] = 0;
                }
            }
        }
      newset = codepage;
#endif /*!HAVE_LANGINFO_CODESET*/
#endif /*!HAVE_W32_SYSTEM && !HAVE_ANDROID_SYSTEM*/
    }

  full_newset = newset;
  if (strlen (newset) > 3 && !ascii_memcasecmp (newset, "iso", 3))
    {
      newset += 3;
      if (*newset == '-' || *newset == '_')
        newset++;
    }

  /* Note that we silently assume that plain ASCII is actually meant
     as Latin-1.  This makes sense because many Unix system don't have
     their locale set up properly and thus would get annoying error
     messages and we have to handle all the "bug" reports. Latin-1 has
     traditionally been the character set used for 8 bit characters on
     Unix systems. */
  if ( !*newset
       || !ascii_strcasecmp (newset, "8859-1" )
       || !ascii_strcasecmp (newset, "646" )
       || !ascii_strcasecmp (newset, "ASCII" )
       || !ascii_strcasecmp (newset, "ANSI_X3.4-1968" )
       )
    {
      active_charset_name = "iso-8859-1";
      no_translation = 0;
      use_iconv = 0;
    }
  else if ( !ascii_strcasecmp (newset, "utf8" )
            || !ascii_strcasecmp(newset, "utf-8") )
    {
      active_charset_name = "utf-8";
      no_translation = 1;
      use_iconv = 0;
    }
  else
    {
      iconv_t cd;

      cd = iconv_open (full_newset, "utf-8");
      if (cd == (iconv_t)-1)
        {
          handle_iconv_error (full_newset, "utf-8", 0);
          return -1;
        }
      iconv_close (cd);
      cd = iconv_open ("utf-8", full_newset);
      if (cd == (iconv_t)-1)
        {
          handle_iconv_error ("utf-8", full_newset, 0);
          return -1;
        }
      iconv_close (cd);
      active_charset_name = full_newset;
      no_translation = 0;
      use_iconv = 1;
    }
  return 0;
}

const char *
get_native_charset ()
{
  return active_charset_name;
}

/* Return true if the native charset is utf-8.  */
int
is_native_utf8 (void)
{
  return no_translation;
}


/* Convert string, which is in native encoding to UTF8 and return a
   new allocated UTF-8 string.  This function terminates the process
   on memory shortage.  */
char *
native_to_utf8 (const char *orig_string)
{
  const unsigned char *string = (const unsigned char *)orig_string;
  const unsigned char *s;
  char *buffer;
  unsigned char *p;
  size_t length = 0;

  if (no_translation)
    {
      /* Already utf-8 encoded. */
      buffer = xstrdup (orig_string);
    }
  else if (!use_iconv)
    {
      /* For Latin-1 we can avoid the iconv overhead. */
      for (s = string; *s; s++)
	{
	  length++;
	  if (*s & 0x80)
	    length++;
	}
      buffer = xmalloc (length + 1);
      for (p = (unsigned char *)buffer, s = string; *s; s++)
	{
	  if ( (*s & 0x80 ))
	    {
	      *p++ = 0xc0 | ((*s >> 6) & 3);
	      *p++ = 0x80 | (*s & 0x3f);
	    }
	  else
	    *p++ = *s;
	}
      *p = 0;
    }
  else
    {
      /* Need to use iconv.  */
      iconv_t cd;
      const char *inptr;
      char *outptr;
      size_t inbytes, outbytes;

      cd = iconv_open ("utf-8", active_charset_name);
      if (cd == (iconv_t)-1)
        {
          handle_iconv_error ("utf-8", active_charset_name, 1);
          return native_to_utf8 (string);
        }

      for (s=string; *s; s++ )
        {
          length++;
          if ((*s & 0x80))
            length += 5; /* We may need up to 6 bytes for the utf8 output. */
        }
      buffer = xmalloc (length + 1);

      inptr = string;
      inbytes = strlen (string);
      outptr = buffer;
      outbytes = length;
      if ( iconv (cd, (ICONV_CONST char **)&inptr, &inbytes,
                  &outptr, &outbytes) == (size_t)-1)
        {
          static int shown;

          if (!shown)
            log_info (_("conversion from '%s' to '%s' failed: %s\n"),
                      active_charset_name, "utf-8", strerror (errno));
          shown = 1;
          /* We don't do any conversion at all but use the strings as is. */
          strcpy (buffer, string);
        }
      else /* Success.  */
        {
          *outptr = 0;
          /* We could realloc the buffer now but I doubt that it makes
             much sense given that it will get freed anyway soon
             after.  */
        }
      iconv_close (cd);
    }
  return buffer;
}



static char *
do_utf8_to_native (const char *string, size_t length, int delim,
                   int with_iconv)
{
  int nleft;
  int i;
  unsigned char encbuf[8];
  int encidx;
  const unsigned char *s;
  size_t n;
  char *buffer = NULL;
  char *p = NULL;
  unsigned long val = 0;
  size_t slen;
  int resync = 0;

  /* First pass (p==NULL): count the extended utf-8 characters.  */
  /* Second pass (p!=NULL): create string.  */
  for (;;)
    {
      for (slen = length, nleft = encidx = 0, n = 0,
             s = (const unsigned char *)string;
           slen;
	   s++, slen--)
	{
	  if (resync)
	    {
	      if (!(*s < 128 || (*s >= 0xc0 && *s <= 0xfd)))
		{
		  /* Still invalid. */
		  if (p)
		    {
		      sprintf (p, "\\x%02x", *s);
		      p += 4;
		    }
		  n += 4;
		  continue;
		}
	      resync = 0;
	    }
	  if (!nleft)
	    {
	      if (!(*s & 0x80))
		{
                  /* Plain ascii. */
		  if ( delim != -1
                       && (*s < 0x20 || *s == 0x7f || *s == delim
                           || (delim && *s == '\\')))
		    {
		      n++;
		      if (p)
			*p++ = '\\';
		      switch (*s)
			{
                        case '\n': n++; if ( p ) *p++ = 'n'; break;
                        case '\r': n++; if ( p ) *p++ = 'r'; break;
                        case '\f': n++; if ( p ) *p++ = 'f'; break;
                        case '\v': n++; if ( p ) *p++ = 'v'; break;
                        case '\b': n++; if ( p ) *p++ = 'b'; break;
                        case    0: n++; if ( p ) *p++ = '0'; break;
			default:
			  n += 3;
			  if (p)
			    {
			      sprintf (p, "x%02x", *s);
			      p += 3;
			    }
			  break;
			}
		    }
		  else
		    {
		      if (p)
			*p++ = *s;
		      n++;
		    }
		}
	      else if ((*s & 0xe0) == 0xc0) /* 110x xxxx */
		{
		  val = *s & 0x1f;
		  nleft = 1;
		  encidx = 0;
		  encbuf[encidx++] = *s;
		}
	      else if ((*s & 0xf0) == 0xe0) /* 1110 xxxx */
		{
		  val = *s & 0x0f;
		  nleft = 2;
		  encidx = 0;
		  encbuf[encidx++] = *s;
		}
	      else if ((*s & 0xf8) == 0xf0) /* 1111 0xxx */
		{
		  val = *s & 0x07;
		  nleft = 3;
		  encidx = 0;
		  encbuf[encidx++] = *s;
		}
	      else if ((*s & 0xfc) == 0xf8) /* 1111 10xx */
		{
		  val = *s & 0x03;
		  nleft = 4;
		  encidx = 0;
		  encbuf[encidx++] = *s;
		}
	      else if ((*s & 0xfe) == 0xfc) /* 1111 110x */
		{
		  val = *s & 0x01;
		  nleft = 5;
		  encidx = 0;
		  encbuf[encidx++] = *s;
		}
	      else /* Invalid encoding: print as \xNN. */
		{
		  if (p)
		    {
		      sprintf (p, "\\x%02x", *s);
		      p += 4;
		    }
		  n += 4;
		  resync = 1;
		}
	    }
	  else if (*s < 0x80 || *s >= 0xc0) /* Invalid utf-8 */
	    {
	      if (p)
		{
		  for (i = 0; i < encidx; i++)
		    {
		      sprintf (p, "\\x%02x", encbuf[i]);
		      p += 4;
		    }
		  sprintf (p, "\\x%02x", *s);
		  p += 4;
		}
	      n += 4 + 4 * encidx;
	      nleft = 0;
	      encidx = 0;
	      resync = 1;
	    }
	  else
	    {
	      encbuf[encidx++] = *s;
	      val <<= 6;
	      val |= *s & 0x3f;
	      if (!--nleft)  /* Ready. */
		{
		  if (no_translation)
		    {
		      if (p)
			{
			  for (i = 0; i < encidx; i++)
			    *p++ = encbuf[i];
			}
		      n += encidx;
		      encidx = 0;
		    }
                  else if (with_iconv)
                    {
                      /* Our strategy for using iconv is a bit strange
                         but it better keeps compatibility with
                         previous versions in regard to how invalid
                         encodings are displayed.  What we do is to
                         keep the utf-8 as is and have the real
                         translation step then at the end.  Yes, I
                         know that this is ugly.  However we are short
                         of the 1.4 release and for this branch we
                         should not mess too much around with iconv
                         things.  One reason for this is that we don't
                         know enough about non-GNU iconv
                         implementation and want to minimize the risk
                         of breaking the code on too many platforms.  */
                        if ( p )
                          {
                            for (i=0; i < encidx; i++ )
                              *p++ = encbuf[i];
                          }
                        n += encidx;
                        encidx = 0;
                    }
		  else 	/* Latin-1 case. */
                    {
		      if (val >= 0x80 && val < 256)
			{
                          /* We can simply print this character */
			  n++;
			  if (p)
			    *p++ = val;
			}
		      else
			{
                          /* We do not have a translation: print utf8. */
			  if (p)
			    {
			      for (i = 0; i < encidx; i++)
				{
				  sprintf (p, "\\x%02x", encbuf[i]);
				  p += 4;
				}
			    }
			  n += encidx * 4;
			  encidx = 0;
			}
		    }
		}

	    }
	}
      if (!buffer)
	{
          /* Allocate the buffer after the first pass. */
	  buffer = p = xmalloc (n + 1);
	}
      else if (with_iconv)
        {
          /* Note: See above for comments.  */
          iconv_t cd;
          const char *inptr;
          char *outbuf, *outptr;
          size_t inbytes, outbytes;

          *p = 0;  /* Terminate the buffer. */

          cd = iconv_open (active_charset_name, "utf-8");
          if (cd == (iconv_t)-1)
            {
              handle_iconv_error (active_charset_name, "utf-8", 1);
              xfree (buffer);
              return utf8_to_native (string, length, delim);
            }

          /* Allocate a new buffer large enough to hold all possible
             encodings. */
          n = p - buffer + 1;
          inbytes = n - 1;;
          inptr = buffer;
          outbytes = n * MB_LEN_MAX;
          if (outbytes / MB_LEN_MAX != n)
            BUG (); /* Actually an overflow. */
          outbuf = outptr = xmalloc (outbytes);
          if ( iconv (cd, (ICONV_CONST char **)&inptr, &inbytes,
                      &outptr, &outbytes) == (size_t)-1)
            {
              static int shown;

              if (!shown)
                log_info (_("conversion from '%s' to '%s' failed: %s\n"),
                          "utf-8", active_charset_name, strerror (errno));
              shown = 1;
              /* Didn't worked out.  Try again but without iconv.  */
              xfree (buffer);
              buffer = NULL;
              xfree (outbuf);
              outbuf = do_utf8_to_native (string, length, delim, 0);
            }
            else /* Success.  */
              {
                *outptr = 0; /* Make sure it is a string. */
                /* We could realloc the buffer now but I doubt that it
                   makes much sense given that it will get freed
                   anyway soon after.  */
                xfree (buffer);
              }
          iconv_close (cd);
          return outbuf;
        }
      else /* Not using iconv. */
	{
	  *p = 0; /* Make sure it is a string. */
	  return buffer;
	}
    }
}

/* Convert string, which is in UTF-8 to native encoding.  Replace
   illegal encodings by some "\xnn" and quote all control
   characters. A character with value DELIM will always be quoted, it
   must be a vanilla ASCII character.  A DELIM value of -1 is special:
   it disables all quoting of control characters.  This function
   terminates the process on memory shortage.  */
char *
utf8_to_native (const char *string, size_t length, int delim)
{
  return do_utf8_to_native (string, length, delim, use_iconv);
}




/* Wrapper function for iconv_open, required for W32 as we dlopen that
   library on that system.  */
jnlib_iconv_t
jnlib_iconv_open (const char *tocode, const char *fromcode)
{
  return (jnlib_iconv_t)iconv_open (tocode, fromcode);
}


/* Wrapper function for iconv, required for W32 as we dlopen that
   library on that system.  */
size_t
jnlib_iconv (jnlib_iconv_t cd,
             const char **inbuf, size_t *inbytesleft,
             char **outbuf, size_t *outbytesleft)
{
  return iconv ((iconv_t)cd, (ICONV_CONST char**)inbuf, inbytesleft,
                outbuf, outbytesleft);
}

/* Wrapper function for iconv_close, required for W32 as we dlopen that
   library on that system.  */
int
jnlib_iconv_close (jnlib_iconv_t cd)
{
  return iconv_close ((iconv_t)cd);
}


#ifdef HAVE_W32_SYSTEM
/* Return a malloced string encoded for CODEPAGE from the wide char input
   string STRING.  Caller must free this value.  Returns NULL and sets
   ERRNO on failure.  Calling this function with STRING set to NULL is
   not defined.  */
static char *
wchar_to_cp (const wchar_t *string, unsigned int codepage)
{
  int n;
  char *result;

  n = WideCharToMultiByte (codepage, 0, string, -1, NULL, 0, NULL, NULL);
  if (n < 0)
    {
      gpg_err_set_errno (EINVAL);
      return NULL;
    }

  result = xtrymalloc (n+1);
  if (!result)
    return NULL;

  n = WideCharToMultiByte (codepage, 0, string, -1, result, n, NULL, NULL);
  if (n < 0)
    {
      xfree (result);
      gpg_err_set_errno (EINVAL);
      result = NULL;
    }
  return result;
}


/* Return a malloced wide char string from a CODEPAGE encoded input
   string STRING.  Caller must free this value.  Returns NULL and sets
   ERRNO on failure.  Calling this function with STRING set to NULL is
   not defined.  */
static wchar_t *
cp_to_wchar (const char *string, unsigned int codepage)
{
  int n;
  size_t nbytes;
  wchar_t *result;

  n = MultiByteToWideChar (codepage, 0, string, -1, NULL, 0);
  if (n < 0)
    {
      gpg_err_set_errno (EINVAL);
      return NULL;
    }

  nbytes = (size_t)(n+1) * sizeof(*result);
  if (nbytes / sizeof(*result) != (n+1))
    {
      gpg_err_set_errno (ENOMEM);
      return NULL;
    }
  result = xtrymalloc (nbytes);
  if (!result)
    return NULL;

  n = MultiByteToWideChar (codepage, 0, string, -1, result, n);
  if (n < 0)
    {
      xfree (result);
      gpg_err_set_errno (EINVAL);
      result = NULL;
    }
  return result;
}


/* Return a malloced string encoded in the active code page from the
 * wide char input string STRING.  Caller must free this value.
 * Returns NULL and sets ERRNO on failure.  Calling this function with
 * STRING set to NULL is not defined.  */
char *
wchar_to_native (const wchar_t *string)
{
  return wchar_to_cp (string, CP_ACP);
}


/* Return a malloced wide char string from an UTF-8 encoded input
 * string STRING.  Caller must free this value.  Returns NULL and sets
 * ERRNO on failure.  Calling this function with STRING set to NULL is
 * not defined.  */
wchar_t *
native_to_wchar (const char *string)
{
  return cp_to_wchar (string, CP_ACP);
}


/* Return a malloced string encoded in UTF-8 from the wide char input
 * string STRING.  Caller must free this value.  Returns NULL and sets
 * ERRNO on failure.  Calling this function with STRING set to NULL is
 * not defined.  */
char *
wchar_to_utf8 (const wchar_t *string)
{
  return wchar_to_cp (string, CP_UTF8);
}


/* Return a malloced wide char string from an UTF-8 encoded input
 * string STRING.  Caller must free this value.  Returns NULL and sets
 * ERRNO on failure.  Calling this function with STRING set to NULL is
 * not defined.  */
wchar_t *
utf8_to_wchar (const char *string)
{
  return cp_to_wchar (string, CP_UTF8);
}

#endif /*HAVE_W32_SYSTEM*/