56 #define U8_COUNT_TRAIL_BYTES(leadByte) \ 57 (U8_IS_LEAD(leadByte) ? \ 58 ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0) 71 #define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \ 72 (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)) 81 #define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) 91 #define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30" 98 #define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5))) 108 #define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00" 115 #define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7))) 173 #define U8_IS_SINGLE(c) (((c)&0x80)==0) 181 #define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32) 190 #define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40) 199 #define U8_LENGTH(c) \ 200 ((uint32_t)(c)<=0x7f ? 1 : \ 201 ((uint32_t)(c)<=0x7ff ? 2 : \ 202 ((uint32_t)(c)<=0xd7ff ? 3 : \ 203 ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \ 204 ((uint32_t)(c)<=0xffff ? 3 : 4)\ 215 #define U8_MAX_LENGTH 4 233 #define U8_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 234 int32_t _u8_get_unsafe_index=(int32_t)(i); \ 235 U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \ 236 U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \ 237 } UPRV_BLOCK_MACRO_END 260 #define U8_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ 261 int32_t _u8_get_index=(i); \ 262 U8_SET_CP_START(s, start, _u8_get_index); \ 263 U8_NEXT(s, _u8_get_index, length, c); \ 264 } UPRV_BLOCK_MACRO_END 291 #define U8_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ 292 int32_t _u8_get_index=(i); \ 293 U8_SET_CP_START(s, start, _u8_get_index); \ 294 U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \ 295 } UPRV_BLOCK_MACRO_END 316 #define U8_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 317 (c)=(uint8_t)(s)[(i)++]; \ 318 if(!U8_IS_SINGLE(c)) { \ 320 (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \ 321 } else if((c)<0xf0) { \ 323 (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \ 326 (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \ 330 } UPRV_BLOCK_MACRO_END 352 #define U8_NEXT(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, U_SENTINEL) 378 #define U8_NEXT_OR_FFFD(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, 0xfffd) 381 #define U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, sub) UPRV_BLOCK_MACRO_BEGIN { \ 382 (c)=(uint8_t)(s)[(i)++]; \ 383 if(!U8_IS_SINGLE(c)) { \ 385 if((i)!=(length) && \ 389 U8_LEAD3_T1_BITS[(c)&=0xf]&(1<<((__t=(s)[i])>>5)) && \ 393 U8_LEAD4_T1_BITS[(__t=(s)[i])>>4]&(1<<(c)) && \ 394 ((c)=((c)<<6)|(__t&0x3f), ++(i)!=(length)) && \ 395 (__t=(s)[i]-0x80)<=0x3f) && \ 397 ((c)=((c)<<6)|__t, ++(i)!=(length)) \ 399 (c)>=0xc2 && ((c)&=0x1f, 1)) && \ 401 (__t=(s)[i]-0x80)<=0x3f && \ 402 ((c)=((c)<<6)|__t, ++(i), 1)) { \ 407 } UPRV_BLOCK_MACRO_END 422 #define U8_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 425 (s)[(i)++]=(uint8_t)__uc; \ 428 (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ 431 (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ 433 (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ 434 (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ 436 (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ 438 (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ 440 } UPRV_BLOCK_MACRO_END 459 #define U8_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \ 462 (s)[(i)++]=(uint8_t)__uc; \ 463 } else if(__uc<=0x7ff && (i)+1<(capacity)) { \ 464 (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ 465 (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ 466 } else if((__uc<=0xd7ff || (0xe000<=__uc && __uc<=0xffff)) && (i)+2<(capacity)) { \ 467 (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ 468 (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ 469 (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ 470 } else if(0xffff<__uc && __uc<=0x10ffff && (i)+3<(capacity)) { \ 471 (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ 472 (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ 473 (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ 474 (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ 478 } UPRV_BLOCK_MACRO_END 490 #define U8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ 491 (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \ 492 } UPRV_BLOCK_MACRO_END 507 #define U8_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ 508 uint8_t __b=(s)[(i)++]; \ 509 if(U8_IS_LEAD(__b) && (i)!=(length)) { \ 510 uint8_t __t1=(s)[i]; \ 511 if((0xe0<=__b && __b<0xf0)) { \ 512 if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \ 513 ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ 516 } else if(__b<0xe0) { \ 517 if(U8_IS_TRAIL(__t1)) { \ 521 if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \ 522 ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \ 523 ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ 528 } UPRV_BLOCK_MACRO_END 542 #define U8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ 545 U8_FWD_1_UNSAFE(s, i); \ 548 } UPRV_BLOCK_MACRO_END 565 #define U8_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ 567 while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ 568 U8_FWD_1(s, i, length); \ 571 } UPRV_BLOCK_MACRO_END 586 #define U8_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ 587 while(U8_IS_TRAIL((s)[i])) { --(i); } \ 588 } UPRV_BLOCK_MACRO_END 607 #define U8_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ 608 if(U8_IS_TRAIL((s)[(i)])) { \ 609 (i)=utf8_back1SafeBody(s, start, (i)); \ 611 } UPRV_BLOCK_MACRO_END 639 #define U8_TRUNCATE_IF_INCOMPLETE(s, start, length) UPRV_BLOCK_MACRO_BEGIN { \ 640 if((length)>(start)) { \ 641 uint8_t __b1=s[(length)-1]; \ 642 if(U8_IS_SINGLE(__b1)) { \ 644 } else if(U8_IS_LEAD(__b1)) { \ 646 } else if(U8_IS_TRAIL(__b1) && ((length)-2)>=(start)) { \ 647 uint8_t __b2=s[(length)-2]; \ 648 if(0xe0<=__b2 && __b2<=0xf4) { \ 649 if(__b2<0xf0 ? U8_IS_VALID_LEAD3_AND_T1(__b2, __b1) : \ 650 U8_IS_VALID_LEAD4_AND_T1(__b2, __b1)) { \ 653 } else if(U8_IS_TRAIL(__b2) && ((length)-3)>=(start)) { \ 654 uint8_t __b3=s[(length)-3]; \ 655 if(0xf0<=__b3 && __b3<=0xf4 && U8_IS_VALID_LEAD4_AND_T1(__b3, __b2)) { \ 661 } UPRV_BLOCK_MACRO_END 684 #define U8_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 685 (c)=(uint8_t)(s)[--(i)]; \ 686 if(U8_IS_TRAIL(c)) { \ 687 uint8_t __b, __count=1, __shift=6; \ 694 U8_MASK_LEAD_BYTE(__b, __count); \ 695 (c)|=(UChar32)__b<<__shift; \ 698 (c)|=(UChar32)(__b&0x3f)<<__shift; \ 704 } UPRV_BLOCK_MACRO_END 726 #define U8_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 727 (c)=(uint8_t)(s)[--(i)]; \ 728 if(!U8_IS_SINGLE(c)) { \ 729 (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \ 731 } UPRV_BLOCK_MACRO_END 757 #define U8_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 758 (c)=(uint8_t)(s)[--(i)]; \ 759 if(!U8_IS_SINGLE(c)) { \ 760 (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \ 762 } UPRV_BLOCK_MACRO_END 775 #define U8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ 776 while(U8_IS_TRAIL((s)[--(i)])) {} \ 777 } UPRV_BLOCK_MACRO_END 791 #define U8_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ 792 if(U8_IS_TRAIL((s)[--(i)])) { \ 793 (i)=utf8_back1SafeBody(s, start, (i)); \ 795 } UPRV_BLOCK_MACRO_END 810 #define U8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ 813 U8_BACK_1_UNSAFE(s, i); \ 816 } UPRV_BLOCK_MACRO_END 832 #define U8_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ 834 while(__N>0 && (i)>(start)) { \ 835 U8_BACK_1(s, start, i); \ 838 } UPRV_BLOCK_MACRO_END 853 #define U8_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ 854 U8_BACK_1_UNSAFE(s, i); \ 855 U8_FWD_1_UNSAFE(s, i); \ 856 } UPRV_BLOCK_MACRO_END 875 #define U8_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \ 876 if((start)<(i) && ((i)<(length) || (length)<0)) { \ 877 U8_BACK_1(s, start, i); \ 878 U8_FWD_1(s, i, length); \ 880 } UPRV_BLOCK_MACRO_END #define U_CAPI
This is used to declare a function as a public ICU C API.
U_CAPI UChar32 utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict)
Function for handling "next code point" with error-checking.
U_CAPI int32_t utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i)
Function for handling "skip backward one code point" with error-checking.
Basic types and constants for UTF.
C API: Code point macros.
U_CAPI int32_t utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError)
Function for handling "append code point" with error-checking.
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
int8_t UBool
The ICU boolean type, a signed-byte integer.
U_CAPI UChar32 utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict)
Function for handling "previous code point" with error-checking.