|
1 /* |
|
2 ******************************************************************************** |
|
3 * Copyright (C) 1996-2012, International Business Machines |
|
4 * Corporation and others. All Rights Reserved. |
|
5 ******************************************************************************** |
|
6 * |
|
7 * File UCHAR.C |
|
8 * |
|
9 * Modification History: |
|
10 * |
|
11 * Date Name Description |
|
12 * 04/02/97 aliu Creation. |
|
13 * 4/15/99 Madhu Updated all the function definitions for C Implementation |
|
14 * 5/20/99 Madhu Added the function u_getVersion() |
|
15 * 8/19/1999 srl Upgraded scripts to Unicode3.0 |
|
16 * 11/11/1999 weiv added u_isalnum(), cleaned comments |
|
17 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion. |
|
18 * 06/20/2000 helena OS/400 port changes; mostly typecast. |
|
19 ****************************************************************************** |
|
20 */ |
|
21 |
|
22 #include "unicode/utypes.h" |
|
23 #include "unicode/uchar.h" |
|
24 #include "unicode/uscript.h" |
|
25 #include "unicode/udata.h" |
|
26 #include "uassert.h" |
|
27 #include "cmemory.h" |
|
28 #include "ucln_cmn.h" |
|
29 #include "utrie2.h" |
|
30 #include "udataswp.h" |
|
31 #include "uprops.h" |
|
32 #include "ustr_imp.h" |
|
33 |
|
34 #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0])) |
|
35 |
|
36 /* uchar_props_data.h is machine-generated by genprops --csource */ |
|
37 #define INCLUDED_FROM_UCHAR_C |
|
38 #include "uchar_props_data.h" |
|
39 |
|
40 /* constants and macros for access to the data ------------------------------ */ |
|
41 |
|
42 /* getting a uint32_t properties word from the data */ |
|
43 #define GET_PROPS(c, result) ((result)=UTRIE2_GET16(&propsTrie, c)); |
|
44 |
|
45 U_CFUNC UBool |
|
46 uprv_haveProperties(UErrorCode *pErrorCode) { |
|
47 if(U_FAILURE(*pErrorCode)) { |
|
48 return FALSE; |
|
49 } |
|
50 return TRUE; |
|
51 } |
|
52 |
|
53 /* API functions ------------------------------------------------------------ */ |
|
54 |
|
55 /* Gets the Unicode character's general category.*/ |
|
56 U_CAPI int8_t U_EXPORT2 |
|
57 u_charType(UChar32 c) { |
|
58 uint32_t props; |
|
59 GET_PROPS(c, props); |
|
60 return (int8_t)GET_CATEGORY(props); |
|
61 } |
|
62 |
|
63 /* Enumerate all code points with their general categories. */ |
|
64 struct _EnumTypeCallback { |
|
65 UCharEnumTypeRange *enumRange; |
|
66 const void *context; |
|
67 }; |
|
68 |
|
69 static uint32_t U_CALLCONV |
|
70 _enumTypeValue(const void *context, uint32_t value) { |
|
71 return GET_CATEGORY(value); |
|
72 } |
|
73 |
|
74 static UBool U_CALLCONV |
|
75 _enumTypeRange(const void *context, UChar32 start, UChar32 end, uint32_t value) { |
|
76 /* just cast the value to UCharCategory */ |
|
77 return ((struct _EnumTypeCallback *)context)-> |
|
78 enumRange(((struct _EnumTypeCallback *)context)->context, |
|
79 start, end+1, (UCharCategory)value); |
|
80 } |
|
81 |
|
82 U_CAPI void U_EXPORT2 |
|
83 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context) { |
|
84 struct _EnumTypeCallback callback; |
|
85 |
|
86 if(enumRange==NULL) { |
|
87 return; |
|
88 } |
|
89 |
|
90 callback.enumRange=enumRange; |
|
91 callback.context=context; |
|
92 utrie2_enum(&propsTrie, _enumTypeValue, _enumTypeRange, &callback); |
|
93 } |
|
94 |
|
95 /* Checks if ch is a lower case letter.*/ |
|
96 U_CAPI UBool U_EXPORT2 |
|
97 u_islower(UChar32 c) { |
|
98 uint32_t props; |
|
99 GET_PROPS(c, props); |
|
100 return (UBool)(GET_CATEGORY(props)==U_LOWERCASE_LETTER); |
|
101 } |
|
102 |
|
103 /* Checks if ch is an upper case letter.*/ |
|
104 U_CAPI UBool U_EXPORT2 |
|
105 u_isupper(UChar32 c) { |
|
106 uint32_t props; |
|
107 GET_PROPS(c, props); |
|
108 return (UBool)(GET_CATEGORY(props)==U_UPPERCASE_LETTER); |
|
109 } |
|
110 |
|
111 /* Checks if ch is a title case letter; usually upper case letters.*/ |
|
112 U_CAPI UBool U_EXPORT2 |
|
113 u_istitle(UChar32 c) { |
|
114 uint32_t props; |
|
115 GET_PROPS(c, props); |
|
116 return (UBool)(GET_CATEGORY(props)==U_TITLECASE_LETTER); |
|
117 } |
|
118 |
|
119 /* Checks if ch is a decimal digit. */ |
|
120 U_CAPI UBool U_EXPORT2 |
|
121 u_isdigit(UChar32 c) { |
|
122 uint32_t props; |
|
123 GET_PROPS(c, props); |
|
124 return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER); |
|
125 } |
|
126 |
|
127 U_CAPI UBool U_EXPORT2 |
|
128 u_isxdigit(UChar32 c) { |
|
129 uint32_t props; |
|
130 |
|
131 /* check ASCII and Fullwidth ASCII a-fA-F */ |
|
132 if( |
|
133 (c<=0x66 && c>=0x41 && (c<=0x46 || c>=0x61)) || |
|
134 (c>=0xff21 && c<=0xff46 && (c<=0xff26 || c>=0xff41)) |
|
135 ) { |
|
136 return TRUE; |
|
137 } |
|
138 |
|
139 GET_PROPS(c, props); |
|
140 return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER); |
|
141 } |
|
142 |
|
143 /* Checks if the Unicode character is a letter.*/ |
|
144 U_CAPI UBool U_EXPORT2 |
|
145 u_isalpha(UChar32 c) { |
|
146 uint32_t props; |
|
147 GET_PROPS(c, props); |
|
148 return (UBool)((CAT_MASK(props)&U_GC_L_MASK)!=0); |
|
149 } |
|
150 |
|
151 U_CAPI UBool U_EXPORT2 |
|
152 u_isUAlphabetic(UChar32 c) { |
|
153 return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_ALPHABETIC))!=0; |
|
154 } |
|
155 |
|
156 /* Checks if c is a letter or a decimal digit */ |
|
157 U_CAPI UBool U_EXPORT2 |
|
158 u_isalnum(UChar32 c) { |
|
159 uint32_t props; |
|
160 GET_PROPS(c, props); |
|
161 return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0); |
|
162 } |
|
163 |
|
164 /** |
|
165 * Checks if c is alphabetic, or a decimal digit; implements UCHAR_POSIX_ALNUM. |
|
166 * @internal |
|
167 */ |
|
168 U_CFUNC UBool |
|
169 u_isalnumPOSIX(UChar32 c) { |
|
170 return (UBool)(u_isUAlphabetic(c) || u_isdigit(c)); |
|
171 } |
|
172 |
|
173 /* Checks if ch is a unicode character with assigned character type.*/ |
|
174 U_CAPI UBool U_EXPORT2 |
|
175 u_isdefined(UChar32 c) { |
|
176 uint32_t props; |
|
177 GET_PROPS(c, props); |
|
178 return (UBool)(GET_CATEGORY(props)!=0); |
|
179 } |
|
180 |
|
181 /* Checks if the Unicode character is a base form character that can take a diacritic.*/ |
|
182 U_CAPI UBool U_EXPORT2 |
|
183 u_isbase(UChar32 c) { |
|
184 uint32_t props; |
|
185 GET_PROPS(c, props); |
|
186 return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0); |
|
187 } |
|
188 |
|
189 /* Checks if the Unicode character is a control character.*/ |
|
190 U_CAPI UBool U_EXPORT2 |
|
191 u_iscntrl(UChar32 c) { |
|
192 uint32_t props; |
|
193 GET_PROPS(c, props); |
|
194 return (UBool)((CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0); |
|
195 } |
|
196 |
|
197 U_CAPI UBool U_EXPORT2 |
|
198 u_isISOControl(UChar32 c) { |
|
199 return (uint32_t)c<=0x9f && (c<=0x1f || c>=0x7f); |
|
200 } |
|
201 |
|
202 /* Some control characters that are used as space. */ |
|
203 #define IS_THAT_CONTROL_SPACE(c) \ |
|
204 (c<=0x9f && ((c>=TAB && c<=CR) || (c>=0x1c && c <=0x1f) || c==NL)) |
|
205 |
|
206 /* Java has decided that U+0085 New Line is not whitespace any more. */ |
|
207 #define IS_THAT_ASCII_CONTROL_SPACE(c) \ |
|
208 (c<=0x1f && c>=TAB && (c<=CR || c>=0x1c)) |
|
209 |
|
210 /* Checks if the Unicode character is a space character.*/ |
|
211 U_CAPI UBool U_EXPORT2 |
|
212 u_isspace(UChar32 c) { |
|
213 uint32_t props; |
|
214 GET_PROPS(c, props); |
|
215 return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c)); |
|
216 } |
|
217 |
|
218 U_CAPI UBool U_EXPORT2 |
|
219 u_isJavaSpaceChar(UChar32 c) { |
|
220 uint32_t props; |
|
221 GET_PROPS(c, props); |
|
222 return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0); |
|
223 } |
|
224 |
|
225 /* Checks if the Unicode character is a whitespace character.*/ |
|
226 U_CAPI UBool U_EXPORT2 |
|
227 u_isWhitespace(UChar32 c) { |
|
228 uint32_t props; |
|
229 GET_PROPS(c, props); |
|
230 return (UBool)( |
|
231 ((CAT_MASK(props)&U_GC_Z_MASK)!=0 && |
|
232 c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */ |
|
233 IS_THAT_ASCII_CONTROL_SPACE(c) |
|
234 ); |
|
235 } |
|
236 |
|
237 U_CAPI UBool U_EXPORT2 |
|
238 u_isblank(UChar32 c) { |
|
239 if((uint32_t)c<=0x9f) { |
|
240 return c==9 || c==0x20; /* TAB or SPACE */ |
|
241 } else { |
|
242 /* Zs */ |
|
243 uint32_t props; |
|
244 GET_PROPS(c, props); |
|
245 return (UBool)(GET_CATEGORY(props)==U_SPACE_SEPARATOR); |
|
246 } |
|
247 } |
|
248 |
|
249 U_CAPI UBool U_EXPORT2 |
|
250 u_isUWhiteSpace(UChar32 c) { |
|
251 return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_WHITE_SPACE))!=0; |
|
252 } |
|
253 |
|
254 /* Checks if the Unicode character is printable.*/ |
|
255 U_CAPI UBool U_EXPORT2 |
|
256 u_isprint(UChar32 c) { |
|
257 uint32_t props; |
|
258 GET_PROPS(c, props); |
|
259 /* comparing ==0 returns FALSE for the categories mentioned */ |
|
260 return (UBool)((CAT_MASK(props)&U_GC_C_MASK)==0); |
|
261 } |
|
262 |
|
263 /** |
|
264 * Checks if c is in \p{graph}\p{blank} - \p{cntrl}. |
|
265 * Implements UCHAR_POSIX_PRINT. |
|
266 * @internal |
|
267 */ |
|
268 U_CFUNC UBool |
|
269 u_isprintPOSIX(UChar32 c) { |
|
270 uint32_t props; |
|
271 GET_PROPS(c, props); |
|
272 /* |
|
273 * The only cntrl character in graph+blank is TAB (in blank). |
|
274 * Here we implement (blank-TAB)=Zs instead of calling u_isblank(). |
|
275 */ |
|
276 return (UBool)((GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c)); |
|
277 } |
|
278 |
|
279 U_CAPI UBool U_EXPORT2 |
|
280 u_isgraph(UChar32 c) { |
|
281 uint32_t props; |
|
282 GET_PROPS(c, props); |
|
283 /* comparing ==0 returns FALSE for the categories mentioned */ |
|
284 return (UBool)((CAT_MASK(props)& |
|
285 (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK)) |
|
286 ==0); |
|
287 } |
|
288 |
|
289 /** |
|
290 * Checks if c is in |
|
291 * [^\p{space}\p{gc=Control}\p{gc=Surrogate}\p{gc=Unassigned}] |
|
292 * with space=\p{Whitespace} and Control=Cc. |
|
293 * Implements UCHAR_POSIX_GRAPH. |
|
294 * @internal |
|
295 */ |
|
296 U_CFUNC UBool |
|
297 u_isgraphPOSIX(UChar32 c) { |
|
298 uint32_t props; |
|
299 GET_PROPS(c, props); |
|
300 /* \p{space}\p{gc=Control} == \p{gc=Z}\p{Control} */ |
|
301 /* comparing ==0 returns FALSE for the categories mentioned */ |
|
302 return (UBool)((CAT_MASK(props)& |
|
303 (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK)) |
|
304 ==0); |
|
305 } |
|
306 |
|
307 U_CAPI UBool U_EXPORT2 |
|
308 u_ispunct(UChar32 c) { |
|
309 uint32_t props; |
|
310 GET_PROPS(c, props); |
|
311 return (UBool)((CAT_MASK(props)&U_GC_P_MASK)!=0); |
|
312 } |
|
313 |
|
314 /* Checks if the Unicode character can start a Unicode identifier.*/ |
|
315 U_CAPI UBool U_EXPORT2 |
|
316 u_isIDStart(UChar32 c) { |
|
317 /* same as u_isalpha() */ |
|
318 uint32_t props; |
|
319 GET_PROPS(c, props); |
|
320 return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_NL_MASK))!=0); |
|
321 } |
|
322 |
|
323 /* Checks if the Unicode character can be a Unicode identifier part other than starting the |
|
324 identifier.*/ |
|
325 U_CAPI UBool U_EXPORT2 |
|
326 u_isIDPart(UChar32 c) { |
|
327 uint32_t props; |
|
328 GET_PROPS(c, props); |
|
329 return (UBool)( |
|
330 (CAT_MASK(props)& |
|
331 (U_GC_ND_MASK|U_GC_NL_MASK| |
|
332 U_GC_L_MASK| |
|
333 U_GC_PC_MASK|U_GC_MC_MASK|U_GC_MN_MASK) |
|
334 )!=0 || |
|
335 u_isIDIgnorable(c)); |
|
336 } |
|
337 |
|
338 /*Checks if the Unicode character can be ignorable in a Java or Unicode identifier.*/ |
|
339 U_CAPI UBool U_EXPORT2 |
|
340 u_isIDIgnorable(UChar32 c) { |
|
341 if(c<=0x9f) { |
|
342 return u_isISOControl(c) && !IS_THAT_ASCII_CONTROL_SPACE(c); |
|
343 } else { |
|
344 uint32_t props; |
|
345 GET_PROPS(c, props); |
|
346 return (UBool)(GET_CATEGORY(props)==U_FORMAT_CHAR); |
|
347 } |
|
348 } |
|
349 |
|
350 /*Checks if the Unicode character can start a Java identifier.*/ |
|
351 U_CAPI UBool U_EXPORT2 |
|
352 u_isJavaIDStart(UChar32 c) { |
|
353 uint32_t props; |
|
354 GET_PROPS(c, props); |
|
355 return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0); |
|
356 } |
|
357 |
|
358 /*Checks if the Unicode character can be a Java identifier part other than starting the |
|
359 * identifier. |
|
360 */ |
|
361 U_CAPI UBool U_EXPORT2 |
|
362 u_isJavaIDPart(UChar32 c) { |
|
363 uint32_t props; |
|
364 GET_PROPS(c, props); |
|
365 return (UBool)( |
|
366 (CAT_MASK(props)& |
|
367 (U_GC_ND_MASK|U_GC_NL_MASK| |
|
368 U_GC_L_MASK| |
|
369 U_GC_SC_MASK|U_GC_PC_MASK| |
|
370 U_GC_MC_MASK|U_GC_MN_MASK) |
|
371 )!=0 || |
|
372 u_isIDIgnorable(c)); |
|
373 } |
|
374 |
|
375 U_CAPI int32_t U_EXPORT2 |
|
376 u_charDigitValue(UChar32 c) { |
|
377 uint32_t props; |
|
378 int32_t value; |
|
379 GET_PROPS(c, props); |
|
380 value=(int32_t)GET_NUMERIC_TYPE_VALUE(props)-UPROPS_NTV_DECIMAL_START; |
|
381 if(value<=9) { |
|
382 return value; |
|
383 } else { |
|
384 return -1; |
|
385 } |
|
386 } |
|
387 |
|
388 U_CAPI double U_EXPORT2 |
|
389 u_getNumericValue(UChar32 c) { |
|
390 uint32_t props; |
|
391 int32_t ntv; |
|
392 GET_PROPS(c, props); |
|
393 ntv=(int32_t)GET_NUMERIC_TYPE_VALUE(props); |
|
394 |
|
395 if(ntv==UPROPS_NTV_NONE) { |
|
396 return U_NO_NUMERIC_VALUE; |
|
397 } else if(ntv<UPROPS_NTV_DIGIT_START) { |
|
398 /* decimal digit */ |
|
399 return ntv-UPROPS_NTV_DECIMAL_START; |
|
400 } else if(ntv<UPROPS_NTV_NUMERIC_START) { |
|
401 /* other digit */ |
|
402 return ntv-UPROPS_NTV_DIGIT_START; |
|
403 } else if(ntv<UPROPS_NTV_FRACTION_START) { |
|
404 /* small integer */ |
|
405 return ntv-UPROPS_NTV_NUMERIC_START; |
|
406 } else if(ntv<UPROPS_NTV_LARGE_START) { |
|
407 /* fraction */ |
|
408 int32_t numerator=(ntv>>4)-12; |
|
409 int32_t denominator=(ntv&0xf)+1; |
|
410 return (double)numerator/denominator; |
|
411 } else if(ntv<UPROPS_NTV_BASE60_START) { |
|
412 /* large, single-significant-digit integer */ |
|
413 double numValue; |
|
414 int32_t mant=(ntv>>5)-14; |
|
415 int32_t exp=(ntv&0x1f)+2; |
|
416 numValue=mant; |
|
417 |
|
418 /* multiply by 10^exp without math.h */ |
|
419 while(exp>=4) { |
|
420 numValue*=10000.; |
|
421 exp-=4; |
|
422 } |
|
423 switch(exp) { |
|
424 case 3: |
|
425 numValue*=1000.; |
|
426 break; |
|
427 case 2: |
|
428 numValue*=100.; |
|
429 break; |
|
430 case 1: |
|
431 numValue*=10.; |
|
432 break; |
|
433 case 0: |
|
434 default: |
|
435 break; |
|
436 } |
|
437 |
|
438 return numValue; |
|
439 } else if(ntv<UPROPS_NTV_RESERVED_START) { |
|
440 /* sexagesimal (base 60) integer */ |
|
441 int32_t numValue=(ntv>>2)-0xbf; |
|
442 int32_t exp=(ntv&3)+1; |
|
443 |
|
444 switch(exp) { |
|
445 case 4: |
|
446 numValue*=60*60*60*60; |
|
447 break; |
|
448 case 3: |
|
449 numValue*=60*60*60; |
|
450 break; |
|
451 case 2: |
|
452 numValue*=60*60; |
|
453 break; |
|
454 case 1: |
|
455 numValue*=60; |
|
456 break; |
|
457 case 0: |
|
458 default: |
|
459 break; |
|
460 } |
|
461 |
|
462 return numValue; |
|
463 } else { |
|
464 /* reserved */ |
|
465 return U_NO_NUMERIC_VALUE; |
|
466 } |
|
467 } |
|
468 |
|
469 U_CAPI int32_t U_EXPORT2 |
|
470 u_digit(UChar32 ch, int8_t radix) { |
|
471 int8_t value; |
|
472 if((uint8_t)(radix-2)<=(36-2)) { |
|
473 value=(int8_t)u_charDigitValue(ch); |
|
474 if(value<0) { |
|
475 /* ch is not a decimal digit, try latin letters */ |
|
476 if(ch>=0x61 && ch<=0x7A) { |
|
477 value=(int8_t)(ch-0x57); /* ch - 'a' + 10 */ |
|
478 } else if(ch>=0x41 && ch<=0x5A) { |
|
479 value=(int8_t)(ch-0x37); /* ch - 'A' + 10 */ |
|
480 } else if(ch>=0xFF41 && ch<=0xFF5A) { |
|
481 value=(int8_t)(ch-0xFF37); /* fullwidth ASCII a-z */ |
|
482 } else if(ch>=0xFF21 && ch<=0xFF3A) { |
|
483 value=(int8_t)(ch-0xFF17); /* fullwidth ASCII A-Z */ |
|
484 } |
|
485 } |
|
486 } else { |
|
487 value=-1; /* invalid radix */ |
|
488 } |
|
489 return (int8_t)((value<radix) ? value : -1); |
|
490 } |
|
491 |
|
492 U_CAPI UChar32 U_EXPORT2 |
|
493 u_forDigit(int32_t digit, int8_t radix) { |
|
494 if((uint8_t)(radix-2)>(36-2) || (uint32_t)digit>=(uint32_t)radix) { |
|
495 return 0; |
|
496 } else if(digit<10) { |
|
497 return (UChar32)(0x30+digit); |
|
498 } else { |
|
499 return (UChar32)((0x61-10)+digit); |
|
500 } |
|
501 } |
|
502 |
|
503 /* miscellaneous, and support for uprops.cpp -------------------------------- */ |
|
504 |
|
505 U_CAPI void U_EXPORT2 |
|
506 u_getUnicodeVersion(UVersionInfo versionArray) { |
|
507 if(versionArray!=NULL) { |
|
508 uprv_memcpy(versionArray, dataVersion, U_MAX_VERSION_LENGTH); |
|
509 } |
|
510 } |
|
511 |
|
512 U_CFUNC uint32_t |
|
513 u_getMainProperties(UChar32 c) { |
|
514 uint32_t props; |
|
515 GET_PROPS(c, props); |
|
516 return props; |
|
517 } |
|
518 |
|
519 U_CFUNC uint32_t |
|
520 u_getUnicodeProperties(UChar32 c, int32_t column) { |
|
521 U_ASSERT(column>=0); |
|
522 if(column>=propsVectorsColumns) { |
|
523 return 0; |
|
524 } else { |
|
525 uint16_t vecIndex=UTRIE2_GET16(&propsVectorsTrie, c); |
|
526 return propsVectors[vecIndex+column]; |
|
527 } |
|
528 } |
|
529 |
|
530 U_CFUNC int32_t |
|
531 uprv_getMaxValues(int32_t column) { |
|
532 switch(column) { |
|
533 case 0: |
|
534 return indexes[UPROPS_MAX_VALUES_INDEX]; |
|
535 case 2: |
|
536 return indexes[UPROPS_MAX_VALUES_2_INDEX]; |
|
537 default: |
|
538 return 0; |
|
539 } |
|
540 } |
|
541 |
|
542 U_CAPI void U_EXPORT2 |
|
543 u_charAge(UChar32 c, UVersionInfo versionArray) { |
|
544 if(versionArray!=NULL) { |
|
545 uint32_t version=u_getUnicodeProperties(c, 0)>>UPROPS_AGE_SHIFT; |
|
546 versionArray[0]=(uint8_t)(version>>4); |
|
547 versionArray[1]=(uint8_t)(version&0xf); |
|
548 versionArray[2]=versionArray[3]=0; |
|
549 } |
|
550 } |
|
551 |
|
552 U_CAPI UScriptCode U_EXPORT2 |
|
553 uscript_getScript(UChar32 c, UErrorCode *pErrorCode) { |
|
554 uint32_t scriptX; |
|
555 if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
|
556 return USCRIPT_INVALID_CODE; |
|
557 } |
|
558 if((uint32_t)c>0x10ffff) { |
|
559 *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
|
560 return USCRIPT_INVALID_CODE; |
|
561 } |
|
562 scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
|
563 if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
|
564 return (UScriptCode)scriptX; |
|
565 } else if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) { |
|
566 return USCRIPT_COMMON; |
|
567 } else if(scriptX<UPROPS_SCRIPT_X_WITH_OTHER) { |
|
568 return USCRIPT_INHERITED; |
|
569 } else { |
|
570 return (UScriptCode)scriptExtensions[scriptX&UPROPS_SCRIPT_MASK]; |
|
571 } |
|
572 } |
|
573 |
|
574 U_CAPI UBool U_EXPORT2 |
|
575 uscript_hasScript(UChar32 c, UScriptCode sc) { |
|
576 const uint16_t *scx; |
|
577 uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
|
578 if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
|
579 return sc==(UScriptCode)scriptX; |
|
580 } |
|
581 |
|
582 scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK); |
|
583 if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) { |
|
584 scx=scriptExtensions+scx[1]; |
|
585 } |
|
586 if(sc>=USCRIPT_CODE_LIMIT) { |
|
587 /* Guard against bogus input that would make us go past the Script_Extensions terminator. */ |
|
588 return FALSE; |
|
589 } |
|
590 while(sc>*scx) { |
|
591 ++scx; |
|
592 } |
|
593 return sc==(*scx&0x7fff); |
|
594 } |
|
595 |
|
596 U_CAPI int32_t U_EXPORT2 |
|
597 uscript_getScriptExtensions(UChar32 c, |
|
598 UScriptCode *scripts, int32_t capacity, |
|
599 UErrorCode *pErrorCode) { |
|
600 uint32_t scriptX; |
|
601 int32_t length; |
|
602 const uint16_t *scx; |
|
603 uint16_t sx; |
|
604 if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
|
605 return 0; |
|
606 } |
|
607 if(capacity<0 || (capacity>0 && scripts==NULL)) { |
|
608 *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
|
609 return 0; |
|
610 } |
|
611 scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK; |
|
612 if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) { |
|
613 if(capacity==0) { |
|
614 *pErrorCode=U_BUFFER_OVERFLOW_ERROR; |
|
615 } else { |
|
616 scripts[0]=(UScriptCode)scriptX; |
|
617 } |
|
618 return 1; |
|
619 } |
|
620 |
|
621 scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK); |
|
622 if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) { |
|
623 scx=scriptExtensions+scx[1]; |
|
624 } |
|
625 length=0; |
|
626 do { |
|
627 sx=*scx++; |
|
628 if(length<capacity) { |
|
629 scripts[length]=(UScriptCode)(sx&0x7fff); |
|
630 } |
|
631 ++length; |
|
632 } while(sx<0x8000); |
|
633 if(length>capacity) { |
|
634 *pErrorCode=U_BUFFER_OVERFLOW_ERROR; |
|
635 } |
|
636 return length; |
|
637 } |
|
638 |
|
639 U_CAPI UBlockCode U_EXPORT2 |
|
640 ublock_getCode(UChar32 c) { |
|
641 return (UBlockCode)((u_getUnicodeProperties(c, 0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT); |
|
642 } |
|
643 |
|
644 /* property starts for UnicodeSet ------------------------------------------- */ |
|
645 |
|
646 static UBool U_CALLCONV |
|
647 _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32_t value) { |
|
648 /* add the start code point to the USet */ |
|
649 const USetAdder *sa=(const USetAdder *)context; |
|
650 sa->add(sa->set, start); |
|
651 return TRUE; |
|
652 } |
|
653 |
|
654 #define USET_ADD_CP_AND_NEXT(sa, cp) sa->add(sa->set, cp); sa->add(sa->set, cp+1) |
|
655 |
|
656 U_CFUNC void U_EXPORT2 |
|
657 uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) { |
|
658 if(U_FAILURE(*pErrorCode)) { |
|
659 return; |
|
660 } |
|
661 |
|
662 /* add the start code point of each same-value range of the main trie */ |
|
663 utrie2_enum(&propsTrie, NULL, _enumPropertyStartsRange, sa); |
|
664 |
|
665 /* add code points with hardcoded properties, plus the ones following them */ |
|
666 |
|
667 /* add for u_isblank() */ |
|
668 USET_ADD_CP_AND_NEXT(sa, TAB); |
|
669 |
|
670 /* add for IS_THAT_CONTROL_SPACE() */ |
|
671 sa->add(sa->set, CR+1); /* range TAB..CR */ |
|
672 sa->add(sa->set, 0x1c); |
|
673 sa->add(sa->set, 0x1f+1); |
|
674 USET_ADD_CP_AND_NEXT(sa, NL); |
|
675 |
|
676 /* add for u_isIDIgnorable() what was not added above */ |
|
677 sa->add(sa->set, DEL); /* range DEL..NBSP-1, NBSP added below */ |
|
678 sa->add(sa->set, HAIRSP); |
|
679 sa->add(sa->set, RLM+1); |
|
680 sa->add(sa->set, INHSWAP); |
|
681 sa->add(sa->set, NOMDIG+1); |
|
682 USET_ADD_CP_AND_NEXT(sa, ZWNBSP); |
|
683 |
|
684 /* add no-break spaces for u_isWhitespace() what was not added above */ |
|
685 USET_ADD_CP_AND_NEXT(sa, NBSP); |
|
686 USET_ADD_CP_AND_NEXT(sa, FIGURESP); |
|
687 USET_ADD_CP_AND_NEXT(sa, NNBSP); |
|
688 |
|
689 /* add for u_digit() */ |
|
690 sa->add(sa->set, U_a); |
|
691 sa->add(sa->set, U_z+1); |
|
692 sa->add(sa->set, U_A); |
|
693 sa->add(sa->set, U_Z+1); |
|
694 sa->add(sa->set, U_FW_a); |
|
695 sa->add(sa->set, U_FW_z+1); |
|
696 sa->add(sa->set, U_FW_A); |
|
697 sa->add(sa->set, U_FW_Z+1); |
|
698 |
|
699 /* add for u_isxdigit() */ |
|
700 sa->add(sa->set, U_f+1); |
|
701 sa->add(sa->set, U_F+1); |
|
702 sa->add(sa->set, U_FW_f+1); |
|
703 sa->add(sa->set, U_FW_F+1); |
|
704 |
|
705 /* add for UCHAR_DEFAULT_IGNORABLE_CODE_POINT what was not added above */ |
|
706 sa->add(sa->set, WJ); /* range WJ..NOMDIG */ |
|
707 sa->add(sa->set, 0xfff0); |
|
708 sa->add(sa->set, 0xfffb+1); |
|
709 sa->add(sa->set, 0xe0000); |
|
710 sa->add(sa->set, 0xe0fff+1); |
|
711 |
|
712 /* add for UCHAR_GRAPHEME_BASE and others */ |
|
713 USET_ADD_CP_AND_NEXT(sa, CGJ); |
|
714 } |
|
715 |
|
716 U_CFUNC void U_EXPORT2 |
|
717 upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) { |
|
718 if(U_FAILURE(*pErrorCode)) { |
|
719 return; |
|
720 } |
|
721 |
|
722 /* add the start code point of each same-value range of the properties vectors trie */ |
|
723 if(propsVectorsColumns>0) { |
|
724 /* if propsVectorsColumns==0 then the properties vectors trie may not be there at all */ |
|
725 utrie2_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa); |
|
726 } |
|
727 } |