ICU 61.1  61.1
utf16.h
Go to the documentation of this file.
1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /*
4 *******************************************************************************
5 *
6 * Copyright (C) 1999-2012, International Business Machines
7 * Corporation and others. All Rights Reserved.
8 *
9 *******************************************************************************
10 * file name: utf16.h
11 * encoding: UTF-8
12 * tab size: 8 (not used)
13 * indentation:4
14 *
15 * created on: 1999sep09
16 * created by: Markus W. Scherer
17 */
18 
34 #ifndef __UTF16_H__
35 #define __UTF16_H__
36 
37 #include "unicode/umachine.h"
38 #ifndef __UTF_H__
39 # include "unicode/utf.h"
40 #endif
41 
42 /* single-code point definitions -------------------------------------------- */
43 
50 #define U16_IS_SINGLE(c) !U_IS_SURROGATE(c)
51 
58 #define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
59 
66 #define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
67 
74 #define U16_IS_SURROGATE(c) U_IS_SURROGATE(c)
75 
83 #define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
84 
92 #define U16_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0)
93 
98 #define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
99 
111 #define U16_GET_SUPPLEMENTARY(lead, trail) \
112  (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET)
113 
114 
122 #define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
123 
131 #define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
132 
140 #define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
141 
147 #define U16_MAX_LENGTH 2
148 
166 #define U16_GET_UNSAFE(s, i, c) { \
167  (c)=(s)[i]; \
168  if(U16_IS_SURROGATE(c)) { \
169  if(U16_IS_SURROGATE_LEAD(c)) { \
170  (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \
171  } else { \
172  (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \
173  } \
174  } \
175 }
176 
200 #define U16_GET(s, start, i, length, c) { \
201  (c)=(s)[i]; \
202  if(U16_IS_SURROGATE(c)) { \
203  uint16_t __c2; \
204  if(U16_IS_SURROGATE_LEAD(c)) { \
205  if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
206  (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
207  } \
208  } else { \
209  if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
210  (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
211  } \
212  } \
213  } \
214 }
215 
216 #ifndef U_HIDE_DRAFT_API
217 
241 #define U16_GET_OR_FFFD(s, start, i, length, c) { \
242  (c)=(s)[i]; \
243  if(U16_IS_SURROGATE(c)) { \
244  uint16_t __c2; \
245  if(U16_IS_SURROGATE_LEAD(c)) { \
246  if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
247  (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
248  } else { \
249  (c)=0xfffd; \
250  } \
251  } else { \
252  if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
253  (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
254  } else { \
255  (c)=0xfffd; \
256  } \
257  } \
258  } \
259 }
260 
261 #endif // U_HIDE_DRAFT_API
262 
263 /* definitions with forward iteration --------------------------------------- */
264 
284 #define U16_NEXT_UNSAFE(s, i, c) { \
285  (c)=(s)[(i)++]; \
286  if(U16_IS_LEAD(c)) { \
287  (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \
288  } \
289 }
290 
312 #define U16_NEXT(s, i, length, c) { \
313  (c)=(s)[(i)++]; \
314  if(U16_IS_LEAD(c)) { \
315  uint16_t __c2; \
316  if((i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
317  ++(i); \
318  (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
319  } \
320  } \
321 }
322 
323 #ifndef U_HIDE_DRAFT_API
324 
346 #define U16_NEXT_OR_FFFD(s, i, length, c) { \
347  (c)=(s)[(i)++]; \
348  if(U16_IS_SURROGATE(c)) { \
349  uint16_t __c2; \
350  if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
351  ++(i); \
352  (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
353  } else { \
354  (c)=0xfffd; \
355  } \
356  } \
357 }
358 
359 #endif // U_HIDE_DRAFT_API
360 
374 #define U16_APPEND_UNSAFE(s, i, c) { \
375  if((uint32_t)(c)<=0xffff) { \
376  (s)[(i)++]=(uint16_t)(c); \
377  } else { \
378  (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
379  (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
380  } \
381 }
382 
400 #define U16_APPEND(s, i, capacity, c, isError) { \
401  if((uint32_t)(c)<=0xffff) { \
402  (s)[(i)++]=(uint16_t)(c); \
403  } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \
404  (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
405  (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
406  } else /* c>0x10ffff or not enough space */ { \
407  (isError)=TRUE; \
408  } \
409 }
410 
421 #define U16_FWD_1_UNSAFE(s, i) { \
422  if(U16_IS_LEAD((s)[(i)++])) { \
423  ++(i); \
424  } \
425 }
426 
440 #define U16_FWD_1(s, i, length) { \
441  if(U16_IS_LEAD((s)[(i)++]) && (i)!=(length) && U16_IS_TRAIL((s)[i])) { \
442  ++(i); \
443  } \
444 }
445 
458 #define U16_FWD_N_UNSAFE(s, i, n) { \
459  int32_t __N=(n); \
460  while(__N>0) { \
461  U16_FWD_1_UNSAFE(s, i); \
462  --__N; \
463  } \
464 }
465 
481 #define U16_FWD_N(s, i, length, n) { \
482  int32_t __N=(n); \
483  while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
484  U16_FWD_1(s, i, length); \
485  --__N; \
486  } \
487 }
488 
502 #define U16_SET_CP_START_UNSAFE(s, i) { \
503  if(U16_IS_TRAIL((s)[i])) { \
504  --(i); \
505  } \
506 }
507 
522 #define U16_SET_CP_START(s, start, i) { \
523  if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
524  --(i); \
525  } \
526 }
527 
528 /* definitions with backward iteration -------------------------------------- */
529 
550 #define U16_PREV_UNSAFE(s, i, c) { \
551  (c)=(s)[--(i)]; \
552  if(U16_IS_TRAIL(c)) { \
553  (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \
554  } \
555 }
556 
577 #define U16_PREV(s, start, i, c) { \
578  (c)=(s)[--(i)]; \
579  if(U16_IS_TRAIL(c)) { \
580  uint16_t __c2; \
581  if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
582  --(i); \
583  (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
584  } \
585  } \
586 }
587 
588 #ifndef U_HIDE_DRAFT_API
589 
610 #define U16_PREV_OR_FFFD(s, start, i, c) { \
611  (c)=(s)[--(i)]; \
612  if(U16_IS_SURROGATE(c)) { \
613  uint16_t __c2; \
614  if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
615  --(i); \
616  (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
617  } else { \
618  (c)=0xfffd; \
619  } \
620  } \
621 }
622 
623 #endif // U_HIDE_DRAFT_API
624 
636 #define U16_BACK_1_UNSAFE(s, i) { \
637  if(U16_IS_TRAIL((s)[--(i)])) { \
638  --(i); \
639  } \
640 }
641 
654 #define U16_BACK_1(s, start, i) { \
655  if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
656  --(i); \
657  } \
658 }
659 
673 #define U16_BACK_N_UNSAFE(s, i, n) { \
674  int32_t __N=(n); \
675  while(__N>0) { \
676  U16_BACK_1_UNSAFE(s, i); \
677  --__N; \
678  } \
679 }
680 
695 #define U16_BACK_N(s, start, i, n) { \
696  int32_t __N=(n); \
697  while(__N>0 && (i)>(start)) { \
698  U16_BACK_1(s, start, i); \
699  --__N; \
700  } \
701 }
702 
716 #define U16_SET_CP_LIMIT_UNSAFE(s, i) { \
717  if(U16_IS_LEAD((s)[(i)-1])) { \
718  ++(i); \
719  } \
720 }
721 
739 #define U16_SET_CP_LIMIT(s, start, i, length) { \
740  if((start)<(i) && ((i)<(length) || (length)<0) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \
741  ++(i); \
742  } \
743 }
744 
745 #endif
Basic types and constants for UTF.
C API: Code point macros.