Differences From Artifact [ce12e0f51c]:
- File src/OFString_UTF8.m — part of check-in [beb9051a10] at 2013-01-11 12:13:38 on branch trunk — Add -[OFMutableString appendCharacters:length:]. (user: js, size: 29801) [annotate] [blame] [check-ins using]
To Artifact [97c02a6c42]:
- File
src/OFString_UTF8.m
— part of check-in
[50916b8dbe]
at
2013-01-11 12:41:54
on branch trunk
— OFString: Improve API for characters / UTF-32.
With this change, there is a clear separation between characters and
UTF-32 strings now. Characters are just an array of characters in the
native endianess, with no BOM prepended. UTF-32 on the other hand may
have a BOM and can be swapped and is optionally zero-terminated.This also fixes a few missing UTF-16 init methods in OFMutableString. (user: js, size: 30904) [annotate] [blame] [check-ins using]
︙ | ︙ | |||
400 401 402 403 404 405 406 | } return self; } - initWithCharacters: (const of_unichar_t*)characters length: (size_t)length | < < < < < < < < < < < < < < < | | 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 | } return self; } - initWithCharacters: (const of_unichar_t*)characters length: (size_t)length { self = [super init]; @try { size_t i, j = 0; s = &s_store; s->cString = [self allocMemoryWithSize: (length * 4) + 1]; s->length = length; for (i = 0; i < length; i++) { char buffer[4]; switch (of_string_utf8_encode(characters[i], buffer)) { case 1: s->cString[j++] = buffer[0]; break; case 2: s->isUTF8 = YES; memcpy(s->cString + j, buffer, 2); |
︙ | ︙ | |||
578 579 580 581 582 583 584 585 586 587 588 589 590 591 | } s->cString[j] = '\0'; @try { s->cString = [self resizeMemory: s->cString size: s->cStringLength + 1]; } @catch (OFOutOfMemoryException *e) { /* We don't care, as we only tried to make it smaller */ } } @catch (id e) { [self release]; @throw e; } | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 | } s->cString[j] = '\0'; @try { s->cString = [self resizeMemory: s->cString size: s->cStringLength + 1]; } @catch (OFOutOfMemoryException *e) { /* We don't care, as we only tried to make it smaller */ } } @catch (id e) { [self release]; @throw e; } return self; } - initWithUTF32String: (const of_unichar_t*)characters length: (size_t)length byteOrder: (of_byte_order_t)byteOrder { self = [super init]; @try { size_t i, j = 0; BOOL swap = NO; if (length > 0 && *characters == 0xFEFF) { characters++; length--; } else if (length > 0 && *characters == 0xFFFE0000) { swap = YES; characters++; length--; } else if (byteOrder != OF_BYTE_ORDER_NATIVE) swap = YES; s = &s_store; s->cString = [self allocMemoryWithSize: (length * 4) + 1]; s->length = length; for (i = 0; i < length; i++) { char buffer[4]; size_t characterLen = of_string_utf8_encode( (swap ? OF_BSWAP32(characters[i]) : characters[i]), buffer); switch (characterLen) { case 1: s->cString[j++] = buffer[0]; break; case 2: s->isUTF8 = YES; memcpy(s->cString + j, buffer, 2); j += 2; break; case 3: s->isUTF8 = YES; memcpy(s->cString + j, buffer, 3); j += 3; break; case 4: s->isUTF8 = YES; memcpy(s->cString + j, buffer, 4); j += 4; break; default: @throw [OFInvalidEncodingException exceptionWithClass: [self class]]; } } s->cString[j] = '\0'; s->cStringLength = j; @try { s->cString = [self resizeMemory: s->cString size: j + 1]; } @catch (OFOutOfMemoryException *e) { /* We don't care, as we only tried to make it smaller */ } } @catch (id e) { [self release]; @throw e; } |
︙ | ︙ |