File: os_mac_conv.c

package info (click to toggle)
vim 1:7.1.314-3+lenny2
  • links: PTS, VCS
  • area: main
  • in suites: lenny
  • size: 39,856 kB
  • ctags: 25,430
  • sloc: ansic: 279,681; cpp: 3,229; makefile: 2,958; perl: 1,232; sh: 857; awk: 715; xml: 507; cs: 458; asm: 114; python: 28; csh: 6
file content (558 lines) | stat: -rw-r--r-- 13,243 bytes parent folder | download
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
/* vi:set ts=8 sts=4 sw=4:
 *
 * VIM - Vi IMproved	by Bram Moolenaar
 *
 * Do ":help uganda"  in Vim to read copying and usage conditions.
 * Do ":help credits" in Vim to see a list of people who contributed.
 * See README.txt for an overview of the Vim source code.
 */
/*
 * os_mac_conv.c: Code specifically for Mac string conversions.
 *
 * This code has been put in a separate file to avoid the conflicts that are
 * caused by including both the X11 and Carbon header files.
 */

#define NO_X11_INCLUDES
#include "vim.h"

#if defined(MACOS_CONVERT) || defined(PROTO)
# ifdef PROTO
/* A few dummy types to be able to generate function prototypes. */
typedef int UniChar;
typedef int *TECObjectRef;
typedef int CFStringRef;
# endif

static char_u	    *mac_utf16_to_utf8 __ARGS((UniChar *from, size_t fromLen, size_t *actualLen));
static UniChar	    *mac_utf8_to_utf16 __ARGS((char_u *from, size_t fromLen, size_t *actualLen));

/* Converter for composing decomposed HFS+ file paths */
static TECObjectRef gPathConverter;
/* Converter used by mac_utf16_to_utf8 */
static TECObjectRef gUTF16ToUTF8Converter;

/*
 * A Mac version of string_convert_ext() for special cases.
 */
    char_u *
mac_string_convert(ptr, len, lenp, fail_on_error, from_enc, to_enc, unconvlenp)
    char_u		*ptr;
    int			len;
    int			*lenp;
    int			fail_on_error;
    int			from_enc;
    int			to_enc;
    int			*unconvlenp;
{
    char_u		*retval, *d;
    CFStringRef		cfstr;
    int			buflen, in, out, l, i;
    CFStringEncoding	from;
    CFStringEncoding	to;

    switch (from_enc)
    {
	case 'l':   from = kCFStringEncodingISOLatin1; break;
	case 'm':   from = kCFStringEncodingMacRoman; break;
	case 'u':   from = kCFStringEncodingUTF8; break;
	default:    return NULL;
    }
    switch (to_enc)
    {
	case 'l':   to = kCFStringEncodingISOLatin1; break;
	case 'm':   to = kCFStringEncodingMacRoman; break;
	case 'u':   to = kCFStringEncodingUTF8; break;
	default:    return NULL;
    }

    if (unconvlenp != NULL)
	*unconvlenp = 0;
    cfstr = CFStringCreateWithBytes(NULL, ptr, len, from, 0);

    if(cfstr == NULL)
	fprintf(stderr, "Encoding failed\n");
    /* When conversion failed, try excluding bytes from the end, helps when
     * there is an incomplete byte sequence.  Only do up to 6 bytes to avoid
     * looping a long time when there really is something unconvertible. */
    while (cfstr == NULL && unconvlenp != NULL && len > 1 && *unconvlenp < 6)
    {
	--len;
	++*unconvlenp;
	cfstr = CFStringCreateWithBytes(NULL, ptr, len, from, 0);
    }
    if (cfstr == NULL)
	return NULL;

    if (to == kCFStringEncodingUTF8)
	buflen = len * 6 + 1;
    else
	buflen = len + 1;
    retval = alloc(buflen);
    if (retval == NULL)
    {
	CFRelease(cfstr);
	return NULL;
    }

#if 0
    CFRange convertRange = CFRangeMake(0, CFStringGetLength(cfstr));
    /*  Determine output buffer size */
    CFStringGetBytes(cfstr, convertRange, to, NULL, FALSE, NULL, 0, (CFIndex *)&buflen);
    retval = (buflen > 0) ? alloc(buflen) : NULL;
    if (retval == NULL) {
	CFRelease(cfstr);
	return NULL;
    }

    if (lenp)
	*lenp = buflen / sizeof(char_u);

    if (!CFStringGetBytes(cfstr, convertRange, to, NULL, FALSE, retval, buflen, NULL))
#endif
    if (!CFStringGetCString(cfstr, (char *)retval, buflen, to))
    {
	CFRelease(cfstr);
	if (fail_on_error)
	{
	    vim_free(retval);
	    return NULL;
	}

	fprintf(stderr, "Trying char-by-char conversion...\n");
	/* conversion failed for the whole string, but maybe it will work
	 * for each character */
	for (d = retval, in = 0, out = 0; in < len && out < buflen - 1;)
	{
	    if (from == kCFStringEncodingUTF8)
		l = utf_ptr2len(ptr + in);
	    else
		l = 1;
	    cfstr = CFStringCreateWithBytes(NULL, ptr + in, l, from, 0);
	    if (cfstr == NULL)
	    {
		*d++ = '?';
		out++;
	    }
	    else
	    {
		if (!CFStringGetCString(cfstr, (char *)d, buflen - out, to))
		{
		    *d++ = '?';
		    out++;
		}
		else
		{
		    i = STRLEN(d);
		    d += i;
		    out += i;
		}
		CFRelease(cfstr);
	    }
	    in += l;
	}
	*d = NUL;
	if (lenp != NULL)
	    *lenp = out;
	return retval;
    }
    CFRelease(cfstr);
    if (lenp != NULL)
	*lenp = STRLEN(retval);

    return retval;
}

/*
 * Conversion from Apple MacRoman char encoding to UTF-8 or latin1, using
 * standard Carbon framework.
 * Input: "ptr[*sizep]".
 * "real_size" is the size of the buffer that "ptr" points to.
 * output is in-place, "sizep" is adjusted.
 * Returns OK or FAIL.
 */
    int
macroman2enc(ptr, sizep, real_size)
    char_u	*ptr;
    long	*sizep;
    long	real_size;
{
    CFStringRef		cfstr;
    CFRange		r;
    CFIndex		len = *sizep;

    /* MacRoman is an 8-bit encoding, no need to move bytes to
     * conv_rest[]. */
    cfstr = CFStringCreateWithBytes(NULL, ptr, len,
						kCFStringEncodingMacRoman, 0);
    /*
     * If there is a conversion error, try using another
     * conversion.
     */
    if (cfstr == NULL)
	return FAIL;

    r.location = 0;
    r.length = CFStringGetLength(cfstr);
    if (r.length != CFStringGetBytes(cfstr, r,
	    (enc_utf8) ? kCFStringEncodingUTF8 : kCFStringEncodingISOLatin1,
	    0, /* no lossy conversion */
	    0, /* not external representation */
	    ptr + *sizep, real_size - *sizep, &len))
    {
	CFRelease(cfstr);
	return FAIL;
    }
    CFRelease(cfstr);
    mch_memmove(ptr, ptr + *sizep, len);
    *sizep = len;

    return OK;
}

/*
 * Conversion from UTF-8 or latin1 to MacRoman.
 * Input: "from[fromlen]"
 * Output: "to[maxtolen]" length in "*tolenp"
 * Unconverted rest in rest[*restlenp].
 * Returns OK or FAIL.
 */
    int
enc2macroman(from, fromlen, to, tolenp, maxtolen, rest, restlenp)
    char_u	*from;
    size_t	fromlen;
    char_u	*to;
    int		*tolenp;
    int		maxtolen;
    char_u	*rest;
    int		*restlenp;
{
    CFStringRef	cfstr;
    CFRange	r;
    CFIndex	l;

    *restlenp = 0;
    cfstr = CFStringCreateWithBytes(NULL, from, fromlen,
	    (enc_utf8) ? kCFStringEncodingUTF8 : kCFStringEncodingISOLatin1,
	    0);
    while (cfstr == NULL && *restlenp < 3 && fromlen > 1)
    {
	rest[*restlenp++] = from[--fromlen];
	cfstr = CFStringCreateWithBytes(NULL, from, fromlen,
		(enc_utf8) ? kCFStringEncodingUTF8 : kCFStringEncodingISOLatin1,
		0);
    }
    if (cfstr == NULL)
	return FAIL;

    r.location = 0;
    r.length = CFStringGetLength(cfstr);
    if (r.length != CFStringGetBytes(cfstr, r,
		kCFStringEncodingMacRoman,
		0, /* no lossy conversion */
		0, /* not external representation (since vim
		    * handles this internally */
		to, maxtolen, &l))
    {
	CFRelease(cfstr);
	return FAIL;
    }
    CFRelease(cfstr);
    *tolenp = l;
    return OK;
}

/*
 * Initializes text converters
 */
    void
mac_conv_init()
{
    TextEncoding    utf8_encoding;
    TextEncoding    utf8_hfsplus_encoding;
    TextEncoding    utf8_canon_encoding;
    TextEncoding    utf16_encoding;

    utf8_encoding = CreateTextEncoding(kTextEncodingUnicodeDefault,
	    kTextEncodingDefaultVariant, kUnicodeUTF8Format);
    utf8_hfsplus_encoding = CreateTextEncoding(kTextEncodingUnicodeDefault,
	    kUnicodeHFSPlusCompVariant, kUnicodeUTF8Format);
    utf8_canon_encoding = CreateTextEncoding(kTextEncodingUnicodeDefault,
	    kUnicodeCanonicalCompVariant, kUnicodeUTF8Format);
    utf16_encoding = CreateTextEncoding(kTextEncodingUnicodeDefault,
	    kTextEncodingDefaultVariant, kUnicode16BitFormat);

    if (TECCreateConverter(&gPathConverter, utf8_encoding,
		utf8_hfsplus_encoding) != noErr)
	gPathConverter = NULL;

    if (TECCreateConverter(&gUTF16ToUTF8Converter, utf16_encoding,
		utf8_canon_encoding) != noErr)
    {
	/* On pre-10.3, Unicode normalization is not available so
	 * fall back to non-normalizing converter */
	if (TECCreateConverter(&gUTF16ToUTF8Converter, utf16_encoding,
		    utf8_encoding) != noErr)
	    gUTF16ToUTF8Converter = NULL;
    }
}

/*
 * Destroys text converters
 */
    void
mac_conv_cleanup()
{
    if (gUTF16ToUTF8Converter)
    {
	TECDisposeConverter(gUTF16ToUTF8Converter);
	gUTF16ToUTF8Converter = NULL;
    }

    if (gPathConverter)
    {
	TECDisposeConverter(gPathConverter);
	gPathConverter = NULL;
    }
}

/*
 * Conversion from UTF-16 UniChars to 'encoding'
 */
    char_u *
mac_utf16_to_enc(from, fromLen, actualLen)
    UniChar *from;
    size_t fromLen;
    size_t *actualLen;
{
    /* Following code borrows somewhat from os_mswin.c */
    vimconv_T	conv;
    size_t      utf8_len;
    char_u      *utf8_str;
    char_u      *result = NULL;

    /* Convert to utf-8 first, works better with iconv */
    utf8_len = 0;
    utf8_str = mac_utf16_to_utf8(from, fromLen, &utf8_len);

    if (utf8_str)
    {
	/* We might be called before we have p_enc set up. */
	conv.vc_type = CONV_NONE;

	/* If encoding (p_enc) is any unicode, it is actually in utf-8 (vim
	 * internal unicode is always utf-8) so don't convert in such cases */

	if ((enc_canon_props(p_enc) & ENC_UNICODE) == 0)
	    convert_setup(&conv, (char_u *)"utf-8",
		    p_enc? p_enc: (char_u *)"macroman");
	if (conv.vc_type == CONV_NONE)
	{
	    /* p_enc is utf-8, so we're done. */
	    result = utf8_str;
	}
	else
	{
	    result = string_convert(&conv, utf8_str, (int *)&utf8_len);
	    vim_free(utf8_str);
	}

	convert_setup(&conv, NULL, NULL);

	if (actualLen)
	    *actualLen = utf8_len;
    }
    else if (actualLen)
	*actualLen = 0;

    return result;
}

/*
 * Conversion from 'encoding' to UTF-16 UniChars
 */
    UniChar *
mac_enc_to_utf16(from, fromLen, actualLen)
    char_u *from;
    size_t fromLen;
    size_t *actualLen;
{
    /* Following code borrows somewhat from os_mswin.c */
    vimconv_T	conv;
    size_t      utf8_len;
    char_u      *utf8_str;
    UniChar     *result = NULL;
    Boolean     should_free_utf8 = FALSE;

    do
    {
	/* Use MacRoman by default, we might be called before we have p_enc
	 * set up.  Convert to utf-8 first, works better with iconv().  Does
	 * nothing if 'encoding' is "utf-8". */
	conv.vc_type = CONV_NONE;
	if ((enc_canon_props(p_enc) & ENC_UNICODE) == 0 &&
		convert_setup(&conv, p_enc ? p_enc : (char_u *)"macroman",
		    (char_u *)"utf-8") == FAIL)
	    break;

	if (conv.vc_type != CONV_NONE)
	{
	    utf8_len = fromLen;
	    utf8_str = string_convert(&conv, from, (int *)&utf8_len);
	    should_free_utf8 = TRUE;
	}
	else
	{
	    utf8_str = from;
	    utf8_len = fromLen;
	}

	if (utf8_str == NULL)
	    break;

	convert_setup(&conv, NULL, NULL);

	result = mac_utf8_to_utf16(utf8_str, utf8_len, actualLen);

	if (should_free_utf8)
	    vim_free(utf8_str);
	return result;
    }
    while (0);

    if (actualLen)
	*actualLen = 0;

    return result;
}

/*
 * Converts from UTF-16 UniChars to CFString
 */
    CFStringRef
mac_enc_to_cfstring(from, fromLen)
    char_u  *from;
    size_t  fromLen;
{
    UniChar	*utf16_str;
    size_t	utf16_len;
    CFStringRef	result = NULL;

    utf16_str = mac_enc_to_utf16(from, fromLen, &utf16_len);
    if (utf16_str)
    {
	result = CFStringCreateWithCharacters(NULL, utf16_str, utf16_len/sizeof(UniChar));
	vim_free(utf16_str);
    }

    return result;
}

/*
 * Converts a decomposed HFS+ UTF-8 path to precomposed UTF-8
 */
    char_u *
mac_precompose_path(decompPath, decompLen, precompLen)
    char_u  *decompPath;
    size_t  decompLen;
    size_t  *precompLen;
{
    char_u  *result = NULL;
    size_t  actualLen = 0;

    if (gPathConverter)
    {
	result = alloc(decompLen);
	if (result)
	{
	    if (TECConvertText(gPathConverter, decompPath,
			decompLen, &decompLen, result,
			decompLen, &actualLen) != noErr)
	    {
		vim_free(result);
		result = NULL;
	    }
	}
    }

    if (precompLen)
	*precompLen = actualLen;

    return result;
}

/*
 * Converts from UTF-16 UniChars to precomposed UTF-8
 */
    static char_u *
mac_utf16_to_utf8(from, fromLen, actualLen)
    UniChar *from;
    size_t fromLen;
    size_t *actualLen;
{
    ByteCount		utf8_len;
    ByteCount		inputRead;
    char_u		*result;

    if (gUTF16ToUTF8Converter)
    {
	result = alloc(fromLen * 6 + 1);
	if (result && TECConvertText(gUTF16ToUTF8Converter, (ConstTextPtr)from,
		    fromLen, &inputRead, result,
		    (fromLen*6+1)*sizeof(char_u), &utf8_len) == noErr)
	{
	    TECFlushText(gUTF16ToUTF8Converter, result, (fromLen*6+1)*sizeof(char_u), &inputRead);
	    utf8_len += inputRead;
	}
	else
	{
	    vim_free(result);
	    result = NULL;
	}
    }
    else
    {
	result = NULL;
    }

    if (actualLen)
	*actualLen = result ? utf8_len : 0;

    return result;
}

/*
 * Converts from UTF-8 to UTF-16 UniChars
 */
    static UniChar *
mac_utf8_to_utf16(from, fromLen, actualLen)
    char_u *from;
    size_t fromLen;
    size_t *actualLen;
{
    CFStringRef  utf8_str;
    CFRange      convertRange;
    UniChar      *result = NULL;

    utf8_str = CFStringCreateWithBytes(NULL, from, fromLen,
	    kCFStringEncodingUTF8, FALSE);

    if (utf8_str == NULL) {
	if (actualLen)
	    *actualLen = 0;
	return NULL;
    }

    convertRange = CFRangeMake(0, CFStringGetLength(utf8_str));
    result = (UniChar *)alloc(convertRange.length * sizeof(UniChar));

    CFStringGetCharacters(utf8_str, convertRange, result);

    CFRelease(utf8_str);

    if (actualLen)
	*actualLen = convertRange.length * sizeof(UniChar);

    return result;
}
#endif /* MACOS_CONVERT */