Tcl Source Code

Check-in [8e353afbe6]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Feature branch to explore making use of the Hoehrmann UTF-8 decoder. http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | dgp-hoehrmann-decoder
Files: files | file ages | folders
SHA1: 8e353afbe61701af8d6d2f50923ef3bc57485184
User & Date: dgp 2012-07-03 19:02:36
Context
2012-07-03
19:02
Feature branch to explore making use of the Hoehrmann UTF-8 decoder. http://bjoern.hoehrmann.de/utf-... Closed-Leaf check-in: 8e353afbe6 user: dgp tags: dgp-hoehrmann-decoder
14:52
Factor out a number of common patterns of use of Tcl_DStringAppend. check-in: 4dd736c95f user: dkf tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to generic/tclUtf.c.

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
 *	number of bytes from the UTF-8 string that were consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */





































int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{
    register int byte;

    /*
     * Unroll 1 to 3 byte UTF-8 sequences, use loop to handle longer ones.
     */

    byte = *((unsigned char *) src);
    if (byte < 0xC0) {
	/*
	 * Handles properly formed UTF-8 characters between 0x01 and 0x7F.
	 * Also treats \0 and naked trail bytes 0x80 to 0xBF as valid
	 * characters representing themselves.
	 */

	*chPtr = (Tcl_UniChar) byte;
	return 1;
    } else if (byte < 0xE0) {
	if ((src[1] & 0xC0) == 0x80) {
	    /*
	     * Two-byte-character lead-byte followed by a trail-byte.
	     */

	    *chPtr = (Tcl_UniChar) (((byte & 0x1F) << 6) | (src[1] & 0x3F));
	    return 2;
	}

	/*
	 * A two-byte-character lead-byte not followed by trail-byte
	 * represents itself.
	 */

	*chPtr = (Tcl_UniChar) byte;
	return 1;
    } else if (byte < 0xF0) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80)) {
	    /*
	     * Three-byte-character lead byte followed by two trail bytes.
	     */




	    *chPtr = (Tcl_UniChar) (((byte & 0x0F) << 12)
		    | ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
	    return 3;
	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */

	*chPtr = (Tcl_UniChar) byte;
	return 1;
    }
#if TCL_UTF_MAX > 3
    {
	int ch, total, trail;

	total = totalBytes[byte];
	trail = total - 1;
	if (trail > 0) {
	    ch = byte & (0x3F >> trail);
	    do {
		src++;
		if ((*src & 0xC0) != 0x80) {
		    *chPtr = byte;
		    return 1;
		}
		ch <<= 6;
		ch |= (*src & 0x3F);
		trail--;
	    } while (trail > 0);
	    *chPtr = ch;
	    return total;
	}
    }
#endif

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







<
|
<
<
<
|
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<

>
>
>
|
<
|
<
|
<
<
<
<
<
|
|
<
<
<
<
|
<
<
<
<
|
|
<
<
<
|
<
<
<
<
<
<
|
<
<
<
|







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
 *	number of bytes from the UTF-8 string that were consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

#define UTF8_ACCEPT 0
#define UTF8_REJECT 1

static const unsigned char utf8d[] = {
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f
  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf
  2,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df
  0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
  0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
  0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2
  1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4
  1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6
  1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8
};

static unsigned int 
decode(
    unsigned int *state,
    unsigned int *codep,
    unsigned int byte)
{
    unsigned int type = utf8d[byte];

    *codep = (*state != UTF8_ACCEPT) ?
	    (byte & 0x3fu) | (*codep << 6) :
	    (0xff >> type) & (byte);

    *state = utf8d[256 + *state*16 + type];
    return *state;
}

int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{

    const char *p = src;



    unsigned int codepoint, state = UTF8_ACCEPT;







    int count = 1;

























    while (*p && count <= TCL_UTF_MAX) {
	switch (decode(&state, &codepoint, (unsigned char)*p)) {
	case UTF8_ACCEPT:
	    *chPtr = (Tcl_UniChar) codepoint;

	    return count;

	case UTF8_REJECT:





	    *chPtr = (Tcl_UniChar)(*src);
	    return 1;




	default:




	    count++;
	    p++;



	}






    }



    *chPtr = (Tcl_UniChar)(*src);
    return 1;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --