Diff
Not logged in

Differences From Artifact [c920f06a63]:

To Artifact [c549181e96]:


1923
1924
1925
1926
1927
1928
1929
1930
1931


1932
1933
1934
1935
1936
1937


1938
1939
1940
1941
1942
1943
1944
1945
1946






1947













1948
1949
1950
1951
1952
1953

1954
1955
1956
1957
1958
1959
1960
1923
1924
1925
1926
1927
1928
1929


1930
1931
1932
1933
1934
1935


1936
1937
1938
1939

1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951

1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978







-
-
+
+




-
-
+
+


-






+
+
+
+
+
+
-
+
+
+
+
+
+
+
+
+
+
+
+
+






+







 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharNcasecmp(
    const Tcl_UniChar *ucs,	/* Unicode string to compare to uct. */
    const Tcl_UniChar *uct,	/* Unicode string ucs is compared to. */
    const unsigned short *ucs,	/* Unicode string to compare to uct. */
    const unsigned short *uct,	/* Unicode string ucs is compared to. */
    unsigned long numChars)	/* Number of unichars to compare. */
{
    for ( ; numChars != 0; numChars--, ucs++, uct++) {
	if (*ucs != *uct) {
	    Tcl_UniChar lcs = Tcl_UniCharToLower(*ucs);
	    Tcl_UniChar lct = Tcl_UniCharToLower(*uct);
	    unsigned short lcs = Tcl_UniCharToLower(*ucs);
	    unsigned short lct = Tcl_UniCharToLower(*uct);

	    if (lcs != lct) {
#if TCL_UTF_MAX < 4
	    /* special case for handling upper surrogates */
	    if (((lcs & 0xFC00) == 0xD800) && ((lct & 0xFC00) != 0xD800)) {
		return 1;
	    } else if (((lct & 0xFC00) == 0xD800)) {
		return -1;
	    }
		return (lcs - lct);
	    }
	}
    }
    return 0;
}
#endif

int
TclUniCharNcasecmp(
    const int *ucs,	/* Unicode string to compare to uct. */
    const int *uct,	/* Unicode string ucs is compared to. */
    unsigned long numChars)	/* Number of unichars to compare. */
{
    for ( ; numChars != 0; numChars--, ucs++, uct++) {
	if (*ucs != *uct) {
	    int lcs = Tcl_UniCharToLower(*ucs);
	    int lct = Tcl_UniCharToLower(*uct);

	    if (lcs != lct) {
		return (lcs - lct);
	    }
	}
    }
    return 0;
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsAlnum --
 *
 *	Test if a character is an alphanumeric Unicode character.
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319










































































































































































2320
2321
2322
2323
2324

2325
2326
2327
2328
2329
2330
2331
2326
2327
2328
2329
2330
2331
2332
2333
2334



2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508

2509
2510
2511
2512
2513
2514
2515
2516









-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+




-
+







 *	pattern: *?\[] (see the manual entry for details on what these mean).
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharCaseMatch(
    const Tcl_UniChar *uniStr,	/* Unicode String. */
    const Tcl_UniChar *uniPattern,
TclUniCharCaseMatch(
    const int *uniStr,	/* Unicode String. */
    const int *uniPattern,
				/* Pattern, which may contain special
				 * characters. */
    int nocase)			/* 0 for case sensitive, 1 for insensitive */
{
    int ch1 = 0, p;

    while (1) {
	p = *uniPattern;

	/*
	 * See if we're at the end of both the pattern and the string. If so,
	 * we succeeded. If we're at the end of the pattern but not at the end
	 * of the string, we failed.
	 */

	if (p == 0) {
	    return (*uniStr == 0);
	}
	if ((*uniStr == 0) && (p != '*')) {
	    return 0;
	}

	/*
	 * Check for a "*" as the next pattern character. It matches any
	 * substring. We handle this by skipping all the characters up to the
	 * next matching one in the pattern, and then calling ourselves
	 * recursively for each postfix of string, until either we match or we
	 * reach the end of the string.
	 */

	if (p == '*') {
	    /*
	     * Skip all successive *'s in the pattern
	     */

	    while (*(++uniPattern) == '*') {
		/* empty body */
	    }
	    p = *uniPattern;
	    if (p == 0) {
		return 1;
	    }
	    if (nocase) {
		p = Tcl_UniCharToLower(p);
	    }
	    while (1) {
		/*
		 * Optimization for matching - cruise through the string
		 * quickly if the next char in the pattern isn't a special
		 * character
		 */

		if ((p != '[') && (p != '?') && (p != '\\')) {
		    if (nocase) {
			while (*uniStr && (p != *uniStr)
				&& (p != Tcl_UniCharToLower(*uniStr))) {
			    uniStr++;
			}
		    } else {
			while (*uniStr && (p != *uniStr)) {
			    uniStr++;
			}
		    }
		}
		if (TclUniCharCaseMatch(uniStr, uniPattern, nocase)) {
		    return 1;
		}
		if (*uniStr == 0) {
		    return 0;
		}
		uniStr++;
	    }
	}

	/*
	 * Check for a "?" as the next pattern character. It matches any
	 * single character.
	 */

	if (p == '?') {
	    uniPattern++;
	    uniStr++;
	    continue;
	}

	/*
	 * Check for a "[" as the next pattern character. It is followed by a
	 * list of characters that are acceptable, or by a range (two
	 * characters separated by "-").
	 */

	if (p == '[') {
	    int startChar, endChar;

	    uniPattern++;
	    ch1 = (nocase ? Tcl_UniCharToLower(*uniStr) : *uniStr);
	    uniStr++;
	    while (1) {
		if ((*uniPattern == ']') || (*uniPattern == 0)) {
		    return 0;
		}
		startChar = (nocase ? Tcl_UniCharToLower(*uniPattern)
			: *uniPattern);
		uniPattern++;
		if (*uniPattern == '-') {
		    uniPattern++;
		    if (*uniPattern == 0) {
			return 0;
		    }
		    endChar = (nocase ? Tcl_UniCharToLower(*uniPattern)
			    : *uniPattern);
		    uniPattern++;
		    if (((startChar <= ch1) && (ch1 <= endChar))
			    || ((endChar <= ch1) && (ch1 <= startChar))) {
			/*
			 * Matches ranges of form [a-z] or [z-a].
			 */
			break;
		    }
		} else if (startChar == ch1) {
		    break;
		}
	    }
	    while (*uniPattern != ']') {
		if (*uniPattern == 0) {
		    uniPattern--;
		    break;
		}
		uniPattern++;
	    }
	    uniPattern++;
	    continue;
	}

	/*
	 * If the next pattern character is '\', just strip off the '\' so we
	 * do exact matching on the character that follows.
	 */

	if (p == '\\') {
	    if (*(++uniPattern) == '\0') {
		return 0;
	    }
	}

	/*
	 * There's no special character. Just make sure that the next bytes of
	 * each string match.
	 */

	if (nocase) {
	    if (Tcl_UniCharToLower(*uniStr) !=
		    Tcl_UniCharToLower(*uniPattern)) {
		return 0;
	    }
	} else if (*uniStr != *uniPattern) {
	    return 0;
	}
	uniStr++;
	uniPattern++;
    }
}

int
Tcl_UniCharCaseMatch(
    const unsigned short *uniStr,	/* Unicode String. */
    const unsigned short *uniPattern,
				/* Pattern, which may contain special
				 * characters. */
    int nocase)			/* 0 for case sensitive, 1 for insensitive */
{
    Tcl_UniChar ch1 = 0, p;
    unsigned short ch1 = 0, p;

    while (1) {
	p = *uniPattern;

	/*
	 * See if we're at the end of both the pattern and the string. If so,
	 * we succeeded. If we're at the end of the pattern but not at the end
2405
2406
2407
2408
2409
2410
2411
2412

2413
2414
2415
2416
2417
2418
2419
2590
2591
2592
2593
2594
2595
2596

2597
2598
2599
2600
2601
2602
2603
2604







-
+







	/*
	 * Check for a "[" as the next pattern character. It is followed by a
	 * list of characters that are acceptable, or by a range (two
	 * characters separated by "-").
	 */

	if (p == '[') {
	    Tcl_UniChar startChar, endChar;
	    unsigned short startChar, endChar;

	    uniPattern++;
	    ch1 = (nocase ? Tcl_UniCharToLower(*uniStr) : *uniStr);
	    uniStr++;
	    while (1) {
		if ((*uniPattern == ']') || (*uniPattern == 0)) {
		    return 0;
2476
2477
2478
2479
2480
2481
2482

2483
2484
2485
2486
2487
2488
2489
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675







+







	    return 0;
	}
	uniStr++;
	uniPattern++;
    }
}


/*
 *----------------------------------------------------------------------
 *
 * TclUniCharMatch --
 *
 *	See if a particular Unicode string matches a particular pattern.
 *	Allows case insensitivity. This is the Unicode equivalent of the char*