146#ifndef U_HIDE_DEPRECATED_API
154#ifdef U_USE_UTF_DEPRECATES
194#define UTF8_ERROR_VALUE_1 0x15
201#define UTF8_ERROR_VALUE_2 0x9f
209#define UTF_ERROR_VALUE 0xffff
217#define UTF_IS_ERROR(c) \
218 (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)
225#define UTF_IS_VALID(c) \
226 (UTF_IS_UNICODE_CHAR(c) && \
227 (c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2)
233#define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800)
240#define UTF_IS_UNICODE_NONCHAR(c) \
242 ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
243 (uint32_t)(c)<=0x10ffff)
260#define UTF_IS_UNICODE_CHAR(c) \
261 ((uint32_t)(c)<0xd800 || \
262 ((uint32_t)(c)>0xdfff && \
263 (uint32_t)(c)<=0x10ffff && \
264 !UTF_IS_UNICODE_NONCHAR(c)))
272#define UTF8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte])
278#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
281#define UTF8_IS_SINGLE(uchar) (((uchar)&0x80)==0)
283#define UTF8_IS_LEAD(uchar) ((uint8_t)((uchar)-0xc0)<0x3e)
285#define UTF8_IS_TRAIL(uchar) (((uchar)&0xc0)==0x80)
288#define UTF8_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0x7f)
304# define UTF8_CHAR_LENGTH(c) \
305 ((uint32_t)(c)<=0x7f ? 1 : \
306 ((uint32_t)(c)<=0x7ff ? 2 : \
307 ((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \
311# define UTF8_CHAR_LENGTH(c) \
312 ((uint32_t)(c)<=0x7f ? 1 : \
313 ((uint32_t)(c)<=0x7ff ? 2 : \
314 ((uint32_t)(c)<=0xffff ? 3 : \
315 ((uint32_t)(c)<=0x10ffff ? 4 : \
316 ((uint32_t)(c)<=0x3ffffff ? 5 : \
317 ((uint32_t)(c)<=0x7fffffff ? 6 : 3) \
326#define UTF8_MAX_CHAR_LENGTH 4
329#define UTF8_ARRAY_SIZE(size) ((5*(size))/2)
332#define UTF8_GET_CHAR_UNSAFE(s, i, c) { \
333 int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \
334 UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \
335 UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \
339#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
340 int32_t _utf8_get_char_safe_index=(int32_t)(i); \
341 UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \
342 UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \
346#define UTF8_NEXT_CHAR_UNSAFE(s, i, c) { \
348 if((uint8_t)((c)-0xc0)<0x35) { \
349 uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \
350 UTF8_MASK_LEAD_BYTE(c, __count); \
354 (c)=((c)<<6)|((s)[(i)++]&0x3f); \
356 (c)=((c)<<6)|((s)[(i)++]&0x3f); \
358 (c)=((c)<<6)|((s)[(i)++]&0x3f); \
366#define UTF8_APPEND_CHAR_UNSAFE(s, i, c) { \
367 if((uint32_t)(c)<=0x7f) { \
368 (s)[(i)++]=(uint8_t)(c); \
370 if((uint32_t)(c)<=0x7ff) { \
371 (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
373 if((uint32_t)(c)<=0xffff) { \
374 (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
376 (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
377 (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
379 (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
381 (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
386#define UTF8_FWD_1_UNSAFE(s, i) { \
387 (i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \
391#define UTF8_FWD_N_UNSAFE(s, i, n) { \
394 UTF8_FWD_1_UNSAFE(s, i); \
400#define UTF8_SET_CHAR_START_UNSAFE(s, i) { \
401 while(UTF8_IS_TRAIL((s)[i])) { --(i); } \
405#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
408 if(UTF8_IS_LEAD(c)) { \
409 (c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \
411 (c)=UTF8_ERROR_VALUE_1; \
417#define UTF8_APPEND_CHAR_SAFE(s, i, length, c) { \
418 if((uint32_t)(c)<=0x7f) { \
419 (s)[(i)++]=(uint8_t)(c); \
421 (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \
426#define UTF8_FWD_1_SAFE(s, i, length) U8_FWD_1(s, i, length)
429#define UTF8_FWD_N_SAFE(s, i, length, n) U8_FWD_N(s, i, length, n)
432#define UTF8_SET_CHAR_START_SAFE(s, start, i) U8_SET_CP_START(s, start, i)
435#define UTF8_PREV_CHAR_UNSAFE(s, i, c) { \
437 if(UTF8_IS_TRAIL(c)) { \
438 uint8_t __b, __count=1, __shift=6; \
445 UTF8_MASK_LEAD_BYTE(__b, __count); \
446 (c)|=(UChar32)__b<<__shift; \
449 (c)|=(UChar32)(__b&0x3f)<<__shift; \
458#define UTF8_BACK_1_UNSAFE(s, i) { \
459 while(UTF8_IS_TRAIL((s)[--(i)])) {} \
463#define UTF8_BACK_N_UNSAFE(s, i, n) { \
466 UTF8_BACK_1_UNSAFE(s, i); \
472#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i) { \
473 UTF8_BACK_1_UNSAFE(s, i); \
474 UTF8_FWD_1_UNSAFE(s, i); \
478#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict) { \
482 (c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \
484 (c)=UTF8_ERROR_VALUE_1; \
490#define UTF8_BACK_1_SAFE(s, start, i) U8_BACK_1(s, start, i)
493#define UTF8_BACK_N_SAFE(s, start, i, n) U8_BACK_N(s, start, i, n)
496#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length) U8_SET_CP_LIMIT(s, start, i, length)
501#define UTF_IS_FIRST_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xd800)
504#define UTF_IS_SECOND_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xdc00)
507#define UTF_IS_SURROGATE_FIRST(c) (((c)&0x400)==0)
510#define UTF_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
513#define UTF16_GET_PAIR_VALUE(first, second) \
514 (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET)
517#define UTF_FIRST_SURROGATE(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
520#define UTF_SECOND_SURROGATE(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
523#define UTF16_LEAD(supplementary) UTF_FIRST_SURROGATE(supplementary)
526#define UTF16_TRAIL(supplementary) UTF_SECOND_SURROGATE(supplementary)
529#define UTF16_IS_SINGLE(uchar) !UTF_IS_SURROGATE(uchar)
532#define UTF16_IS_LEAD(uchar) UTF_IS_FIRST_SURROGATE(uchar)
535#define UTF16_IS_TRAIL(uchar) UTF_IS_SECOND_SURROGATE(uchar)
538#define UTF16_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0xffff)
541#define UTF16_CHAR_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
544#define UTF16_MAX_CHAR_LENGTH 2
547#define UTF16_ARRAY_SIZE(size) (size)
560#define UTF16_GET_CHAR_UNSAFE(s, i, c) { \
562 if(UTF_IS_SURROGATE(c)) { \
563 if(UTF_IS_SURROGATE_FIRST(c)) { \
564 (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \
566 (c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \
572#define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
574 if(UTF_IS_SURROGATE(c)) { \
576 if(UTF_IS_SURROGATE_FIRST(c)) { \
577 if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \
578 (c)=UTF16_GET_PAIR_VALUE((c), __c2); \
582 (c)=UTF_ERROR_VALUE; \
585 if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
586 (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
590 (c)=UTF_ERROR_VALUE; \
593 } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
594 (c)=UTF_ERROR_VALUE; \
599#define UTF16_NEXT_CHAR_UNSAFE(s, i, c) { \
601 if(UTF_IS_FIRST_SURROGATE(c)) { \
602 (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \
607#define UTF16_APPEND_CHAR_UNSAFE(s, i, c) { \
608 if((uint32_t)(c)<=0xffff) { \
609 (s)[(i)++]=(uint16_t)(c); \
611 (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
612 (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
617#define UTF16_FWD_1_UNSAFE(s, i) { \
618 if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \
624#define UTF16_FWD_N_UNSAFE(s, i, n) { \
627 UTF16_FWD_1_UNSAFE(s, i); \
633#define UTF16_SET_CHAR_START_UNSAFE(s, i) { \
634 if(UTF_IS_SECOND_SURROGATE((s)[i])) { \
640#define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
642 if(UTF_IS_FIRST_SURROGATE(c)) { \
644 if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \
646 (c)=UTF16_GET_PAIR_VALUE((c), __c2); \
650 (c)=UTF_ERROR_VALUE; \
652 } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
654 (c)=UTF_ERROR_VALUE; \
659#define UTF16_APPEND_CHAR_SAFE(s, i, length, c) { \
660 if((uint32_t)(c)<=0xffff) { \
661 (s)[(i)++]=(uint16_t)(c); \
662 } else if((uint32_t)(c)<=0x10ffff) { \
663 if((i)+1<(length)) { \
664 (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
665 (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
667 (s)[(i)++]=UTF_ERROR_VALUE; \
670 (s)[(i)++]=UTF_ERROR_VALUE; \
675#define UTF16_FWD_1_SAFE(s, i, length) U16_FWD_1(s, i, length)
678#define UTF16_FWD_N_SAFE(s, i, length, n) U16_FWD_N(s, i, length, n)
681#define UTF16_SET_CHAR_START_SAFE(s, start, i) U16_SET_CP_START(s, start, i)
684#define UTF16_PREV_CHAR_UNSAFE(s, i, c) { \
686 if(UTF_IS_SECOND_SURROGATE(c)) { \
687 (c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \
692#define UTF16_BACK_1_UNSAFE(s, i) { \
693 if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \
699#define UTF16_BACK_N_UNSAFE(s, i, n) { \
702 UTF16_BACK_1_UNSAFE(s, i); \
708#define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) { \
709 if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \
715#define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) { \
717 if(UTF_IS_SECOND_SURROGATE(c)) { \
719 if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
721 (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
725 (c)=UTF_ERROR_VALUE; \
727 } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
729 (c)=UTF_ERROR_VALUE; \
734#define UTF16_BACK_1_SAFE(s, start, i) U16_BACK_1(s, start, i)
737#define UTF16_BACK_N_SAFE(s, start, i, n) U16_BACK_N(s, start, i, n)
740#define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
760#define UTF32_IS_SAFE(c, strict) \
762 (uint32_t)(c)<=0x10ffff : \
763 UTF_IS_UNICODE_CHAR(c))
776#define UTF32_IS_SINGLE(uchar) 1
778#define UTF32_IS_LEAD(uchar) 0
780#define UTF32_IS_TRAIL(uchar) 0
785#define UTF32_NEED_MULTIPLE_UCHAR(c) 0
787#define UTF32_CHAR_LENGTH(c) 1
789#define UTF32_MAX_CHAR_LENGTH 1
794#define UTF32_ARRAY_SIZE(size) (size)
797#define UTF32_GET_CHAR_UNSAFE(s, i, c) { \
802#define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
804 if(!UTF32_IS_SAFE(c, strict)) { \
805 (c)=UTF_ERROR_VALUE; \
812#define UTF32_NEXT_CHAR_UNSAFE(s, i, c) { \
817#define UTF32_APPEND_CHAR_UNSAFE(s, i, c) { \
822#define UTF32_FWD_1_UNSAFE(s, i) { \
827#define UTF32_FWD_N_UNSAFE(s, i, n) { \
832#define UTF32_SET_CHAR_START_UNSAFE(s, i) { \
836#define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
838 if(!UTF32_IS_SAFE(c, strict)) { \
839 (c)=UTF_ERROR_VALUE; \
844#define UTF32_APPEND_CHAR_SAFE(s, i, length, c) { \
845 if((uint32_t)(c)<=0x10ffff) { \
853#define UTF32_FWD_1_SAFE(s, i, length) { \
858#define UTF32_FWD_N_SAFE(s, i, length, n) { \
859 if(((i)+=(n))>(length)) { \
865#define UTF32_SET_CHAR_START_SAFE(s, start, i) { \
871#define UTF32_PREV_CHAR_UNSAFE(s, i, c) { \
876#define UTF32_BACK_1_UNSAFE(s, i) { \
881#define UTF32_BACK_N_UNSAFE(s, i, n) { \
886#define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i) { \
890#define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict) { \
892 if(!UTF32_IS_SAFE(c, strict)) { \
893 (c)=UTF_ERROR_VALUE; \
898#define UTF32_BACK_1_SAFE(s, start, i) { \
903#define UTF32_BACK_N_SAFE(s, start, i, n) { \
911#define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length) { \
921#define UTF_ARRAY_SIZE(size) UTF16_ARRAY_SIZE(size)
924#define UTF_GET_CHAR_UNSAFE(s, i, c) UTF16_GET_CHAR_UNSAFE(s, i, c)
927#define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
931#define UTF_NEXT_CHAR_UNSAFE(s, i, c) UTF16_NEXT_CHAR_UNSAFE(s, i, c)
934#define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict) UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
938#define UTF_APPEND_CHAR_UNSAFE(s, i, c) UTF16_APPEND_CHAR_UNSAFE(s, i, c)
941#define UTF_APPEND_CHAR_SAFE(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
945#define UTF_FWD_1_UNSAFE(s, i) UTF16_FWD_1_UNSAFE(s, i)
948#define UTF_FWD_1_SAFE(s, i, length) UTF16_FWD_1_SAFE(s, i, length)
952#define UTF_FWD_N_UNSAFE(s, i, n) UTF16_FWD_N_UNSAFE(s, i, n)
955#define UTF_FWD_N_SAFE(s, i, length, n) UTF16_FWD_N_SAFE(s, i, length, n)
959#define UTF_SET_CHAR_START_UNSAFE(s, i) UTF16_SET_CHAR_START_UNSAFE(s, i)
962#define UTF_SET_CHAR_START_SAFE(s, start, i) UTF16_SET_CHAR_START_SAFE(s, start, i)
966#define UTF_PREV_CHAR_UNSAFE(s, i, c) UTF16_PREV_CHAR_UNSAFE(s, i, c)
969#define UTF_PREV_CHAR_SAFE(s, start, i, c, strict) UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
973#define UTF_BACK_1_UNSAFE(s, i) UTF16_BACK_1_UNSAFE(s, i)
976#define UTF_BACK_1_SAFE(s, start, i) UTF16_BACK_1_SAFE(s, start, i)
980#define UTF_BACK_N_UNSAFE(s, i, n) UTF16_BACK_N_UNSAFE(s, i, n)
983#define UTF_BACK_N_SAFE(s, start, i, n) UTF16_BACK_N_SAFE(s, start, i, n)
987#define UTF_SET_CHAR_LIMIT_UNSAFE(s, i) UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
990#define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
999#define UTF_IS_SINGLE(uchar) U16_IS_SINGLE(uchar)
1006#define UTF_IS_LEAD(uchar) U16_IS_LEAD(uchar)
1013#define UTF_IS_TRAIL(uchar) U16_IS_TRAIL(uchar)
1020#define UTF_NEED_MULTIPLE_UCHAR(c) UTF16_NEED_MULTIPLE_UCHAR(c)
1027#define UTF_CHAR_LENGTH(c) U16_LENGTH(c)
1034#define UTF_MAX_CHAR_LENGTH U16_MAX_LENGTH
1045#define UTF_GET_CHAR(s, start, i, length, c) U16_GET(s, start, i, length, c)
1058#define UTF_NEXT_CHAR(s, i, length, c) U16_NEXT(s, i, length, c)
1071#define UTF_APPEND_CHAR(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
1082#define UTF_FWD_1(s, i, length) U16_FWD_1(s, i, length)
1093#define UTF_FWD_N(s, i, length, n) U16_FWD_N(s, i, length, n)
1109#define UTF_SET_CHAR_START(s, start, i) U16_SET_CP_START(s, start, i)
1122#define UTF_PREV_CHAR(s, start, i, c) U16_PREV(s, start, i, c)
1135#define UTF_BACK_1(s, start, i) U16_BACK_1(s, start, i)
1148#define UTF_BACK_N(s, start, i, n) U16_BACK_N(s, start, i, n)
1164#define UTF_SET_CHAR_LIMIT(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
"Smart pointer" base class; do not use directly: use LocalPointer etc.
C API: 16-bit Unicode handling macros.
C API: 8-bit Unicode handling macros.
C API: Code point macros.