summaryrefslogtreecommitdiff
path: root/app/wlib/mswlib/simple-gettext.c
blob: 412eece940d82bc0ffbb84e2951c339a9409548c (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
/* \file simple-gettext.c  
 * a simplified version of gettext.
 * Copyright (C) 1995, 1996, 1997, 1999,
 *               2005 Free Software Foundation, Inc.
 *
 * This file is part of XTrackCAD.
 *
 * GnuPG is free software; you can redistribute it and/or modify
 * it under the terms of 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.
 *
 * 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 copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
 */

/* This is a simplified version of gettext written by Ulrich Drepper.
 * It is used for the Win32 version of GnuPG beucase all the overhead
 * of gettext is not needed and we have to do some special Win32 stuff.
 * I decided that this is far easier than to tweak gettext for the special
 * cases (I tried it but it is a lot of code).	wk 15.09.99
 */

/*
 * Based on the simple-gettext from GnuPG a version appropriate for the 
 * needs of XTrackCAD was derived. This is a workaround for any compiler 
 * specifics or runtime library dependencies. mf 26.07.09
 */

#ifdef USE_SIMPLE_GETTEXT
#if !defined (_WIN32) && !defined (__CYGWIN32__)
#error This file can only be used under Windows or Cygwin32
#endif

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <windows.h>

#include "mswint.h"

#if _MSC_VER > 1300
	#define stricmp _stricmp
	#define strnicmp _strnicmp
	#define strdup _strdup
	#define fileno _fileno
#endif

typedef unsigned long u32;

/* The magic number of the GNU message catalog format.	*/
#define MAGIC	      0x950412de
#define MAGIC_SWAPPED 0xde120495

/* Revision number of the currently used .mo (binary) file format.  */
#define MO_REVISION_NUMBER 0


/* Header for binary .mo file format.  */
struct mo_file_header
{
  /* The magic number.	*/
  u32 magic;
  /* The revision number of the file format.  */
  u32 revision;
  /* The number of strings pairs.  */
  u32 nstrings;
  /* Offset of table with start offsets of original strings.  */
  u32 orig_tab_offset;
  /* Offset of table with start offsets of translation strings.  */
  u32 trans_tab_offset;
  /* Size of hashing table.  */
  u32 hash_tab_size;
  /* Offset of first hashing entry.  */
  u32 hash_tab_offset;
};

struct string_desc
{
  /* Length of addressed string.  */
  u32 length;
  /* Offset of string in file.	*/
  u32 offset;
};


struct overflow_space_s
{
  struct overflow_space_s *next;
  u32 idx;
  char d[1];
};

struct loaded_domain
{
  char *data;
  int must_swap;
  u32 nstrings;
  char *mapped;  /* 0 = not yet mapped, 1 = mapped,
                    2 = mapped to
                    overflow space */
  struct overflow_space_s *overflow_space;
  struct string_desc *orig_tab;
  struct string_desc *trans_tab;
  u32 hash_size;
  u32 *hash_tab;
};

static struct loaded_domain *the_domain;

/**
 *	Translate the input string from UTF8 to Windows codepage.
 * 
 * \param str IN string in UTF-8 format to translate.
 * \param len IN number of chars to translate
 * \param  dummy IN ?
 * \return pointer to translated string. Free after usage
 */
char *
utf8_to_native( char *str, unsigned int len, int dummy )
{
	/* maximum output length is size of string * 2 */ 
	int buflen = (len + 1) * 2;
	char *buf = malloc( buflen );
	int wcharLen;
	/* maximum result size is size of UTF-8 string */
	char *resBuffer = malloc( len + 1 );

	if( !resBuffer ) {
		resBuffer = "ERROR in UTF-8 MALLOC";
	} else {
		/* as Windows has no way fo a direct translation fom UTF-8 to */
		/* the system codepage, we need to take two steps */

		/* 1. convert from UTF-8 to UTF-16 */
		wcharLen = MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)str, -1, (LPWSTR)buf, buflen / 2 );
	
		/* 2. convert from UTF-8 to system codepage */
		WideCharToMultiByte(CP_ACP, 0, (LPWSTR)buf, wcharLen, resBuffer, len + 1, NULL, NULL );


	}
	free(buf);
	return( resBuffer );	
}


static u32
do_swap_u32( u32 i )
{
  return (i << 24) | ((i & 0xff00) << 8) | ((i >> 8) & 0xff00) | (i >> 24);
}

#define SWAPIT(flag, data) ((flag) ? do_swap_u32(data) : (data) )


/* We assume to have `unsigned long int' value with at least 32 bits.  */
#define HASHWORDBITS 32

/* The so called `hashpjw' function by P.J. Weinberger
   [see Aho/Sethi/Ullman, COMPILERS: Principles, Techniques and Tools,
   1986, 1987 Bell Telephone Laboratories, Inc.]  */

static unsigned long
hash_string( const char *str_param )
{
    unsigned long int hval, g;
    const char *str = str_param;

    hval = 0;
    while (*str != '\0')
    {
	hval <<= 4;
	hval += (unsigned long int) *str++;
	g = hval & ((unsigned long int) 0xf << (HASHWORDBITS - 4));
	if (g != 0)
	{
	  hval ^= g >> (HASHWORDBITS - 8);
	  hval ^= g;
	}
    }
    return hval;
}


static struct loaded_domain *
load_domain( const char *filename )
{
    FILE *fp;
    size_t size;
    struct stat st;
    struct mo_file_header *data = NULL;
    struct loaded_domain *domain = NULL;
    size_t to_read;
    char *read_ptr;

    fp = fopen( filename, "rb" );
    if( !fp )
       return NULL; /* can't open the file */
    /* we must know about the size of the file */
    if( fstat( fileno(fp ), &st )
	|| (size = (size_t)st.st_size) != st.st_size
	|| size < sizeof (struct mo_file_header) ) {
	fclose( fp );
	return NULL;
    }

    data = malloc( size );
    if( !data ) {
	fclose( fp );
	return NULL; /* out of memory */
    }

    to_read = size;
    read_ptr = (char *) data;
    do {
	unsigned long int nb = fread( read_ptr, 1, to_read, fp );
	if( nb < to_read ) {
	    fclose (fp);
	    free(data);
	    return NULL; /* read error */
	}
	read_ptr += nb;
	to_read -= nb;
    } while( to_read > 0 );
    fclose (fp);

    /* Using the magic number we can test whether it really is a message
     * catalog file.  */
    if( data->magic != MAGIC && data->magic != MAGIC_SWAPPED ) {
	/* The magic number is wrong: not a message catalog file.  */
	free( data );
	return NULL;
    }

    domain = calloc( 1, sizeof *domain );
    if( !domain )  {
	free( data );
	return NULL;
    }
    domain->data = (char *) data;
    domain->must_swap = data->magic != MAGIC;

    /* Fill in the information about the available tables.  */
    switch( SWAPIT(domain->must_swap, data->revision) ) {
      case 0:
	domain->nstrings = SWAPIT(domain->must_swap, data->nstrings);
	domain->orig_tab = (struct string_desc *)
	  ((char *) data + SWAPIT(domain->must_swap, data->orig_tab_offset));
	domain->trans_tab = (struct string_desc *)
	  ((char *) data + SWAPIT(domain->must_swap, data->trans_tab_offset));
	domain->hash_size = SWAPIT(domain->must_swap, data->hash_tab_size);
	domain->hash_tab = (u32 *)
	  ((char *) data + SWAPIT(domain->must_swap, data->hash_tab_offset));
      break;

      default: /* This is an invalid revision.	*/
	free( data );
	free( domain );
	return NULL;
    }

    /* Allocate an array to keep track of code page mappings. */
    domain->mapped = calloc( 1, domain->nstrings );
    if( !domain->mapped ) {
        free( data );
        free( domain );
        return NULL;
    }

    return domain;
}


/**
 * Set the file used for translations. Pass a NULL to disable
 * translation.  A new filename may be set at anytime.  WARNING: 
 * After changing the filename you should not access any data 
 * retrieved by gettext().
 */
int
set_gettext_file ( const char *filename, const char *regkey )
{
    struct loaded_domain *domain = NULL;

    if( filename && *filename ) {
	if( filename[0] == '/'
	    || ( isalpha(filename[0])
		 && filename[1] == ':'
		 && (filename[2] == '/' || filename[2] == '\\') )
	   ) {
	    /* absolute path - use it as is */
	    domain = load_domain( filename );
	}
	if (!domain)
	    return -1;
    }

    if( the_domain ) {
        struct overflow_space_s *os, *os2;
	free( the_domain->data );
  	free( the_domain->mapped );
        for (os=the_domain->overflow_space; os; os = os2) {
            os2 = os->next;
            free (os);
        }
	free( the_domain );
	the_domain = NULL;
    }
    the_domain = domain;
    return 0;
}

/**
 * Return the required string from the message table. Before returning the result, 
 * codepage translation from UTF8 to current codepage is performed.
 */

static const char*
get_string( struct loaded_domain *domain, u32 idx )
{
  struct overflow_space_s *os;
  char *p;

  p = domain->data + SWAPIT(domain->must_swap, domain->trans_tab[idx].offset);
  if (!domain->mapped[idx]) 
    {
      size_t plen, buflen;
      char *buf;

      domain->mapped[idx] = 1;

      plen = strlen (p);
      buf = utf8_to_native (p, plen, -1);
      buflen = strlen (buf);
	  if (buflen <= plen){
        strcpy (p, buf);
		free( buf );
	  } else {
          /* There is not enough space for the translation - store it
             in the overflow_space else and mark that in the mapped
             array.  Because we expect that this won't happen too
             often, we use a simple linked list.  */
          os = malloc (sizeof *os + buflen);
          if (os)
            {
              os->idx = idx;
              strcpy (os->d, buf);
              os->next = domain->overflow_space;
              domain->overflow_space = os;
              p = os->d;
            }
          else
            p = "ERROR in GETTEXT MALLOC";
          free (buf);
	   }
    }
  else if (domain->mapped[idx] == 2) 
    { /* We need to get the string from the overflow_space. */
      for (os=domain->overflow_space; os; os = os->next)
        if (os->idx == idx)
          return (const char*)os->d;
      p = "ERROR in GETTEXT\n";
    }
  return (const char*)p;
}

/**
 * This is the translation function itself.
 */

char *
gettext( const char *msgid )
{
    struct loaded_domain *domain;
    size_t act = 0;
    size_t top, bottom;

    if( !(domain = the_domain) )
	goto not_found;

    /* Locate the MSGID and its translation.  */
    if( domain->hash_size > 2 && domain->hash_tab ) {
	/* Use the hashing table.  */
	u32 len = strlen (msgid);
	u32 hash_val = hash_string (msgid);
	u32 idx = hash_val % domain->hash_size;
	u32 incr = 1 + (hash_val % (domain->hash_size - 2));
	u32 nstr = SWAPIT (domain->must_swap, domain->hash_tab[idx]);

	if ( !nstr ) /* Hash table entry is empty.  */
	    goto not_found;

	if( SWAPIT(domain->must_swap,
		    domain->orig_tab[nstr - 1].length) == len
	    && !strcmp( msgid,
		       domain->data + SWAPIT(domain->must_swap,
				    domain->orig_tab[nstr - 1].offset)) )
	    return (char *)get_string( domain, nstr - 1 );

	for(;;) {
	    if (idx >= domain->hash_size - incr)
		idx -= domain->hash_size - incr;
	    else
		idx += incr;

	    nstr = SWAPIT(domain->must_swap, domain->hash_tab[idx]);
	    if( !nstr )
		goto not_found; /* Hash table entry is empty.  */

	    if ( SWAPIT(domain->must_swap,
				domain->orig_tab[nstr - 1].length) == len
		 && !strcmp (msgid,
			 domain->data + SWAPIT(domain->must_swap,
					   domain->orig_tab[nstr - 1].offset)))
		return (char *)get_string( domain, nstr-1 );
	}
	/* NOTREACHED */
    }

    /* Now we try the default method:  binary search in the sorted
       array of messages.  */
    bottom = 0;
    top = domain->nstrings;
    while( bottom < top ) {
	int cmp_val;

	act = (bottom + top) / 2;
	cmp_val = strcmp(msgid, domain->data
			       + SWAPIT(domain->must_swap,
					domain->orig_tab[act].offset));
	if (cmp_val < 0)
	    top = act;
	else if (cmp_val > 0)
	    bottom = act + 1;
	else
	    return (char *)get_string( domain, act );
    }

  not_found:
    return (char *)msgid;
}

/**
 * This is the main initialization function for simple gettext. The message file is 
 * opened and read into memory. The function must be called once before translating 
 * a string.
 *
 * The message files are expected to be in a directory named in the UNIXish form en_US
 * in the path passed to this function. The filename is expected to be domainname.mo
 *
 * \param domainname IN domain
 * \param dirname IN directory for the message files
 * \return    always NULL
 */

char *
bindtextdomain( char *domainname, char *dirname )
{
	char *loc;
	char *dir;

	/* get thread's locale in UNIXish style eg. en_US */
	loc = g_win32_getlocale();

	/* make sure that path does not end with trailing slash */
	if( dirname[ strlen(dirname) ] == '/' )
		dirname[ strlen(dirname) ] = '\0';

	/* allocate buffer for filename, 20 bytes should be enough for extension etc. */
	dir = malloc( strlen( domainname ) + strlen( dirname ) + strlen( loc ) + 20 );
	
	if( dir ) {
		/* create the full filename */
		sprintf( dir, "%s/%s/LC_MESSAGES/%s.mo", dirname, loc, domainname );
		/* load the file */
		set_gettext_file( dir, NULL );
		free( dir );
	}
	
	free( loc );
	return( NULL );
}

/**
 * This is a dummy function to maintain source code compatibility 
 * with other implementations of gettext.
 * For this implementation, UTF-8 input encoding is assumed
 *
 * \param domainname IN domain
 * \param codeset In codeset 
 * \return    always NULL
 */

char *
bind_textdomain_codeset(char *domainname, char *codeset )
{
	return( NULL );
}

/**
 * This is a dummy function to maintain source code compatibility 
 * with other implementations of gettext.
 *
 * \param domainname IN domain
 * \return    always NULL
 */

char *
textdomain( char *domainname )
{
	return( NULL );
}
#endif /* USE_SIMPLE_GETTEXT */