55 #define U8_COUNT_TRAIL_BYTES(leadByte) \
56 (U8_IS_LEAD(leadByte) ? \
57 ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0)
70 #define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \
71 (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0))
80 #define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
90 #define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30"
97 #define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5)))
107 #define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00"
114 #define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7)))
172 #define U8_IS_SINGLE(c) (((c)&0x80)==0)
180 #define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32)
189 #define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40)
198 #define U8_LENGTH(c) \
199 ((uint32_t)(c)<=0x7f ? 1 : \
200 ((uint32_t)(c)<=0x7ff ? 2 : \
201 ((uint32_t)(c)<=0xd7ff ? 3 : \
202 ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \
203 ((uint32_t)(c)<=0xffff ? 3 : 4)\
214 #define U8_MAX_LENGTH 4
232 #define U8_GET_UNSAFE(s, i, c) { \
233 int32_t _u8_get_unsafe_index=(int32_t)(i); \
234 U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \
235 U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \
259 #define U8_GET(s, start, i, length, c) { \
260 int32_t _u8_get_index=(i); \
261 U8_SET_CP_START(s, start, _u8_get_index); \
262 U8_NEXT(s, _u8_get_index, length, c); \
290 #define U8_GET_OR_FFFD(s, start, i, length, c) { \
291 int32_t _u8_get_index=(i); \
292 U8_SET_CP_START(s, start, _u8_get_index); \
293 U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \
315 #define U8_NEXT_UNSAFE(s, i, c) { \
316 (c)=(uint8_t)(s)[(i)++]; \
317 if(!U8_IS_SINGLE(c)) { \
319 (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \
320 } else if((c)<0xf0) { \
322 (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \
325 (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \
351 #define U8_NEXT(s, i, length, c) { \
352 (c)=(uint8_t)(s)[(i)++]; \
353 if(!U8_IS_SINGLE(c)) { \
354 uint8_t __t1, __t2; \
356 (0xe0<=(c) && (c)<0xf0) && \
357 (((i)+1)<(length) || (length)<0) && \
358 U8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \
359 (__t2=(s)[(i)+1]-0x80)<=0x3f) { \
360 (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \
363 ((c)<0xe0 && (c)>=0xc2) && \
365 (__t1=(s)[i]-0x80)<=0x3f) { \
366 (c)=(((c)&0x1f)<<6)|__t1; \
370 (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -1); \
399 #define U8_NEXT_OR_FFFD(s, i, length, c) { \
400 (c)=(uint8_t)(s)[(i)++]; \
401 if(!U8_IS_SINGLE(c)) { \
402 uint8_t __t1, __t2; \
404 (0xe0<=(c) && (c)<0xf0) && \
405 (((i)+1)<(length) || (length)<0) && \
406 U8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \
407 (__t2=(s)[(i)+1]-0x80)<=0x3f) { \
408 (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \
411 ((c)<0xe0 && (c)>=0xc2) && \
413 (__t1=(s)[i]-0x80)<=0x3f) { \
414 (c)=(((c)&0x1f)<<6)|__t1; \
418 (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -3); \
436 #define U8_APPEND_UNSAFE(s, i, c) { \
437 if((uint32_t)(c)<=0x7f) { \
438 (s)[(i)++]=(uint8_t)(c); \
440 if((uint32_t)(c)<=0x7ff) { \
441 (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
443 if((uint32_t)(c)<=0xffff) { \
444 (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
446 (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
447 (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
449 (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
451 (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
472 #define U8_APPEND(s, i, capacity, c, isError) { \
473 if((uint32_t)(c)<=0x7f) { \
474 (s)[(i)++]=(uint8_t)(c); \
475 } else if((uint32_t)(c)<=0x7ff && (i)+1<(capacity)) { \
476 (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
477 (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
478 } else if((uint32_t)(c)<=0xd7ff && (i)+2<(capacity)) { \
479 (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
480 (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
481 (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
483 (i)=utf8_appendCharSafeBody(s, (i), (capacity), c, &(isError)); \
497 #define U8_FWD_1_UNSAFE(s, i) { \
498 (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \
514 #define U8_FWD_1(s, i, length) { \
515 uint8_t __b=(s)[(i)++]; \
516 if(U8_IS_LEAD(__b) && (i)!=(length)) { \
517 uint8_t __t1=(s)[i]; \
518 if((0xe0<=__b && __b<0xf0)) { \
519 if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \
520 ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \
523 } else if(__b<0xe0) { \
524 if(U8_IS_TRAIL(__t1)) { \
528 if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \
529 ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \
530 ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \
549 #define U8_FWD_N_UNSAFE(s, i, n) { \
552 U8_FWD_1_UNSAFE(s, i); \
572 #define U8_FWD_N(s, i, length, n) { \
574 while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
575 U8_FWD_1(s, i, length); \
593 #define U8_SET_CP_START_UNSAFE(s, i) { \
594 while(U8_IS_TRAIL((s)[i])) { --(i); } \
611 #define U8_SET_CP_START(s, start, i) { \
612 if(U8_IS_TRAIL((s)[(i)])) { \
613 (i)=utf8_back1SafeBody(s, start, (i)); \
638 #define U8_PREV_UNSAFE(s, i, c) { \
639 (c)=(uint8_t)(s)[--(i)]; \
640 if(U8_IS_TRAIL(c)) { \
641 uint8_t __b, __count=1, __shift=6; \
648 U8_MASK_LEAD_BYTE(__b, __count); \
649 (c)|=(UChar32)__b<<__shift; \
652 (c)|=(UChar32)(__b&0x3f)<<__shift; \
680 #define U8_PREV(s, start, i, c) { \
681 (c)=(uint8_t)(s)[--(i)]; \
682 if(!U8_IS_SINGLE(c)) { \
683 (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \
711 #define U8_PREV_OR_FFFD(s, start, i, c) { \
712 (c)=(uint8_t)(s)[--(i)]; \
713 if(!U8_IS_SINGLE(c)) { \
714 (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \
729 #define U8_BACK_1_UNSAFE(s, i) { \
730 while(U8_IS_TRAIL((s)[--(i)])) {} \
745 #define U8_BACK_1(s, start, i) { \
746 if(U8_IS_TRAIL((s)[--(i)])) { \
747 (i)=utf8_back1SafeBody(s, start, (i)); \
764 #define U8_BACK_N_UNSAFE(s, i, n) { \
767 U8_BACK_1_UNSAFE(s, i); \
786 #define U8_BACK_N(s, start, i, n) { \
788 while(__N>0 && (i)>(start)) { \
789 U8_BACK_1(s, start, i); \
807 #define U8_SET_CP_LIMIT_UNSAFE(s, i) { \
808 U8_BACK_1_UNSAFE(s, i); \
809 U8_FWD_1_UNSAFE(s, i); \
829 #define U8_SET_CP_LIMIT(s, start, i, length) { \
830 if((start)<(i) && ((i)<(length) || (length)<0)) { \
831 U8_BACK_1(s, start, i); \
832 U8_FWD_1(s, i, length); \
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.
Basic types and constants for UTF.
C API: Code point macros.
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.
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.
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
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.
#define U_STABLE
This is used to declare a function as a stable public ICU C API.
int8_t UBool
The ICU boolean type.