Tcl Source Code: Diff

Differences From Artifact [8c0c76d552]:

File generic/tclUtf.c — part of check-in [b6438b69ad] at 2017-11-30 13:14:43 on branch core-8-branch — Fix [8e1e31eac0fd6b6c4452bc108a98ab08c6b64588|8e1e31eac0]: lsort treats NUL chars strangely. Also fix various initializations, which only make a difference when TCL_UTF_MAX == 4. Add new test-cases which demonstrate the fix. For TCL_UTF_MAX == 4, surrogates will now be handled as expected as well when sorting. (user: jan.nijtmans size: 51591) [more...]

To Artifact [ae6a7420d8]:

File generic/tclUtf.c — part of check-in [8481a52495] at 2018-01-10 08:25:13 on branch core-8-branch — Fix [https://core.tcl.tk/tk/info/00a27923ee26437611e1ed83f96e15b6caabcd8b|00a27923ee]: (Tcl part, remaining is in Tk) text/entry dysfunctional when pasting an emoji on MacOSX. This changes the handling of incoming valid 4-byte UTF-8 sequences: Those are no longer split in 4 separate characters (as was done for invalid byte sequences) but replaced by a single ' replacement character' . (user: jan.nijtmans size: 51831) [more...]

︙
64 65 66 67 68 69 70 71 72 ~~73 74 75~~ 76 77 78 79 80 81 82	64 65 66 67 68 69 70 71 72 73 74 75 76 77 78	- - - -	1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, ~~#if TCL_UTF_MAX > 3~~ 4,4,4,4,4,4,4,4, ~~#else~~ ~~1,1,1,1,1,1,1,1,~~ ~~#endif~~ 1,1,1,1,1,1,1,1 }; /* --------------------------------------------------------------------------- * TclUtfCount --
︙
324 325 326 327 328 329 330 ~~331~~ 332 333 334 335 336 ~~337~~ 338 339 340 341 342 343 344	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	- - + + + + + + + + + + +	} /* * A three-byte-character lead-byte not followed by two trail-bytes * represents itself. / } ~~#if TCL_UTF_MAX > 3~~ else if (byte < 0xF8) { if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) { / * Four-byte-character lead byte followed by three trail bytes. / ~~#if TCL_UTF_MAX == 4~~ #if TCL_UTF_MAX == 3 byte = (((byte & 0x07) << 18) \| ((src[1] & 0x3F) << 12) \| ((src[2] & 0x3F) << 6) \| (src[3] & 0x3F)) - 0x10000; if (byte & 0x100000) { / out of range, < 0x10000 or > 0x10ffff / } else { / produce replacement character, and advance source pointer / chPtr = (Tcl_UniChar) 0xFFFD; return 4; } #elif TCL_UTF_MAX == 4 Tcl_UniChar surrogate; byte = (((byte & 0x07) << 18) \| ((src[1] & 0x3F) << 12) \| ((src[2] & 0x3F) << 6) \| (src[3] & 0x3F)) - 0x10000; surrogate = (Tcl_UniChar) (0xD800 + (byte >> 10)); if (byte & 0x100000) { /* out of range, < 0x10000 or > 0x10ffff */
︙
361 362 363 364 365 366 367 ~~368~~ 369 370 371 372 373 374 375	366 367 368 369 370 371 372 373 374 375 376 377 378 379	-	} /* * A four-byte-character lead-byte not followed by two trail-bytes * represents itself. / } ~~#endif~~ chPtr = (Tcl_UniChar) byte; return 1; } /* *---------------------------------------------------------------------------
︙
495 496 497 498 499 500 501 ~~502~~ 503 504 505 506 507 ~~508~~ 509 510 511 512 513 514 515	499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519	- + - +	if (length < 0) { while (src != '\0') { src += TclUtfToUniChar(src, &ch); i++; } if (i < 0) i = INT_MAX; / Bug [2738427] / } else { ~~register const char endPtr = src + length - ~~TCL_UTF_MAX~~;~~ register const char *endPtr = src + length - 4; while (src < endPtr) { src += TclUtfToUniChar(src, &ch); i++; } ~~endPtr += ~~TCL_UTF_MAX~~;~~ endPtr += 4; while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) { src += TclUtfToUniChar(src, &ch); i++; } if (src < endPtr) { i += endPtr - src; }
︙
673 674 675 676 677 678 679 ~~680~~ 681 682 683 684 685 686 687	677 678 679 680 681 682 683 684 685 686 687 688 689 690 691	- +	const char start) / Pointer to the beginning of the string, to * avoid going backwards too far. / { const char look; int i, byte; look = --src; ~~for (i = 0; i < ~~TCL_UTF_MAX~~; i++) {~~ for (i = 0; i < 4; i++) { if (look < start) { if (src < start) { src = start; } break; } byte = ((unsigned char ) look);
︙