• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1 /*
2 ********************************************************************************
3 *   Copyright (C) 1996-2010, 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 "umutex.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.c is machine-generated by genprops --csource */
37 #include "uchar_props_data.c"
38 
39 /* constants and macros for access to the data ------------------------------ */
40 
41 /* getting a uint32_t properties word from the data */
42 #define GET_PROPS(c, result) ((result)=UTRIE2_GET16(&propsTrie, c));
43 
44 U_CFUNC UBool
uprv_haveProperties(UErrorCode * pErrorCode)45 uprv_haveProperties(UErrorCode *pErrorCode) {
46     if(U_FAILURE(*pErrorCode)) {
47         return FALSE;
48     }
49     return TRUE;
50 }
51 
52 /* API functions ------------------------------------------------------------ */
53 
54 /* Gets the Unicode character's general category.*/
55 U_CAPI int8_t U_EXPORT2
u_charType(UChar32 c)56 u_charType(UChar32 c) {
57     uint32_t props;
58     GET_PROPS(c, props);
59     return (int8_t)GET_CATEGORY(props);
60 }
61 
62 /* Enumerate all code points with their general categories. */
63 struct _EnumTypeCallback {
64     UCharEnumTypeRange *enumRange;
65     const void *context;
66 };
67 
68 static uint32_t U_CALLCONV
_enumTypeValue(const void * context,uint32_t value)69 _enumTypeValue(const void *context, uint32_t value) {
70     return GET_CATEGORY(value);
71 }
72 
73 static UBool U_CALLCONV
_enumTypeRange(const void * context,UChar32 start,UChar32 end,uint32_t value)74 _enumTypeRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
75     /* just cast the value to UCharCategory */
76     return ((struct _EnumTypeCallback *)context)->
77         enumRange(((struct _EnumTypeCallback *)context)->context,
78                   start, end+1, (UCharCategory)value);
79 }
80 
81 U_CAPI void U_EXPORT2
u_enumCharTypes(UCharEnumTypeRange * enumRange,const void * context)82 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context) {
83     struct _EnumTypeCallback callback;
84 
85     if(enumRange==NULL) {
86         return;
87     }
88 
89     callback.enumRange=enumRange;
90     callback.context=context;
91     utrie2_enum(&propsTrie, _enumTypeValue, _enumTypeRange, &callback);
92 }
93 
94 /* Checks if ch is a lower case letter.*/
95 U_CAPI UBool U_EXPORT2
u_islower(UChar32 c)96 u_islower(UChar32 c) {
97     uint32_t props;
98     GET_PROPS(c, props);
99     return (UBool)(GET_CATEGORY(props)==U_LOWERCASE_LETTER);
100 }
101 
102 /* Checks if ch is an upper case letter.*/
103 U_CAPI UBool U_EXPORT2
u_isupper(UChar32 c)104 u_isupper(UChar32 c) {
105     uint32_t props;
106     GET_PROPS(c, props);
107     return (UBool)(GET_CATEGORY(props)==U_UPPERCASE_LETTER);
108 }
109 
110 /* Checks if ch is a title case letter; usually upper case letters.*/
111 U_CAPI UBool U_EXPORT2
u_istitle(UChar32 c)112 u_istitle(UChar32 c) {
113     uint32_t props;
114     GET_PROPS(c, props);
115     return (UBool)(GET_CATEGORY(props)==U_TITLECASE_LETTER);
116 }
117 
118 /* Checks if ch is a decimal digit. */
119 U_CAPI UBool U_EXPORT2
u_isdigit(UChar32 c)120 u_isdigit(UChar32 c) {
121     uint32_t props;
122     GET_PROPS(c, props);
123     return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
124 }
125 
126 U_CAPI UBool U_EXPORT2
u_isxdigit(UChar32 c)127 u_isxdigit(UChar32 c) {
128     uint32_t props;
129 
130     /* check ASCII and Fullwidth ASCII a-fA-F */
131     if(
132         (c<=0x66 && c>=0x41 && (c<=0x46 || c>=0x61)) ||
133         (c>=0xff21 && c<=0xff46 && (c<=0xff26 || c>=0xff41))
134     ) {
135         return TRUE;
136     }
137 
138     GET_PROPS(c, props);
139     return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
140 }
141 
142 /* Checks if the Unicode character is a letter.*/
143 U_CAPI UBool U_EXPORT2
u_isalpha(UChar32 c)144 u_isalpha(UChar32 c) {
145     uint32_t props;
146     GET_PROPS(c, props);
147     return (UBool)((CAT_MASK(props)&U_GC_L_MASK)!=0);
148 }
149 
150 U_CAPI UBool U_EXPORT2
u_isUAlphabetic(UChar32 c)151 u_isUAlphabetic(UChar32 c) {
152     return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_ALPHABETIC))!=0;
153 }
154 
155 /* Checks if c is a letter or a decimal digit */
156 U_CAPI UBool U_EXPORT2
u_isalnum(UChar32 c)157 u_isalnum(UChar32 c) {
158     uint32_t props;
159     GET_PROPS(c, props);
160     return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0);
161 }
162 
163 /**
164  * Checks if c is alphabetic, or a decimal digit; implements UCHAR_POSIX_ALNUM.
165  * @internal
166  */
167 U_CFUNC UBool
u_isalnumPOSIX(UChar32 c)168 u_isalnumPOSIX(UChar32 c) {
169     return (UBool)(u_isUAlphabetic(c) || u_isdigit(c));
170 }
171 
172 /* Checks if ch is a unicode character with assigned character type.*/
173 U_CAPI UBool U_EXPORT2
u_isdefined(UChar32 c)174 u_isdefined(UChar32 c) {
175     uint32_t props;
176     GET_PROPS(c, props);
177     return (UBool)(GET_CATEGORY(props)!=0);
178 }
179 
180 /* Checks if the Unicode character is a base form character that can take a diacritic.*/
181 U_CAPI UBool U_EXPORT2
u_isbase(UChar32 c)182 u_isbase(UChar32 c) {
183     uint32_t props;
184     GET_PROPS(c, props);
185     return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0);
186 }
187 
188 /* Checks if the Unicode character is a control character.*/
189 U_CAPI UBool U_EXPORT2
u_iscntrl(UChar32 c)190 u_iscntrl(UChar32 c) {
191     uint32_t props;
192     GET_PROPS(c, props);
193     return (UBool)((CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0);
194 }
195 
196 U_CAPI UBool U_EXPORT2
u_isISOControl(UChar32 c)197 u_isISOControl(UChar32 c) {
198     return (uint32_t)c<=0x9f && (c<=0x1f || c>=0x7f);
199 }
200 
201 /* Some control characters that are used as space. */
202 #define IS_THAT_CONTROL_SPACE(c) \
203     (c<=0x9f && ((c>=TAB && c<=CR) || (c>=0x1c && c <=0x1f) || c==NL))
204 
205 /* Java has decided that U+0085 New Line is not whitespace any more. */
206 #define IS_THAT_ASCII_CONTROL_SPACE(c) \
207     (c<=0x1f && c>=TAB && (c<=CR || c>=0x1c))
208 
209 /* Checks if the Unicode character is a space character.*/
210 U_CAPI UBool U_EXPORT2
u_isspace(UChar32 c)211 u_isspace(UChar32 c) {
212     uint32_t props;
213     GET_PROPS(c, props);
214     return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c));
215 }
216 
217 U_CAPI UBool U_EXPORT2
u_isJavaSpaceChar(UChar32 c)218 u_isJavaSpaceChar(UChar32 c) {
219     uint32_t props;
220     GET_PROPS(c, props);
221     return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0);
222 }
223 
224 /* Checks if the Unicode character is a whitespace character.*/
225 U_CAPI UBool U_EXPORT2
u_isWhitespace(UChar32 c)226 u_isWhitespace(UChar32 c) {
227     uint32_t props;
228     GET_PROPS(c, props);
229     return (UBool)(
230                 ((CAT_MASK(props)&U_GC_Z_MASK)!=0 &&
231                     c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */
232                 IS_THAT_ASCII_CONTROL_SPACE(c)
233            );
234 }
235 
236 U_CAPI UBool U_EXPORT2
u_isblank(UChar32 c)237 u_isblank(UChar32 c) {
238     if((uint32_t)c<=0x9f) {
239         return c==9 || c==0x20; /* TAB or SPACE */
240     } else {
241         /* Zs */
242         uint32_t props;
243         GET_PROPS(c, props);
244         return (UBool)(GET_CATEGORY(props)==U_SPACE_SEPARATOR);
245     }
246 }
247 
248 U_CAPI UBool U_EXPORT2
u_isUWhiteSpace(UChar32 c)249 u_isUWhiteSpace(UChar32 c) {
250     return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_WHITE_SPACE))!=0;
251 }
252 
253 /* Checks if the Unicode character is printable.*/
254 U_CAPI UBool U_EXPORT2
u_isprint(UChar32 c)255 u_isprint(UChar32 c) {
256     uint32_t props;
257     GET_PROPS(c, props);
258     /* comparing ==0 returns FALSE for the categories mentioned */
259     return (UBool)((CAT_MASK(props)&U_GC_C_MASK)==0);
260 }
261 
262 /**
263  * Checks if c is in \p{graph}\p{blank} - \p{cntrl}.
264  * Implements UCHAR_POSIX_PRINT.
265  * @internal
266  */
267 U_CFUNC UBool
u_isprintPOSIX(UChar32 c)268 u_isprintPOSIX(UChar32 c) {
269     uint32_t props;
270     GET_PROPS(c, props);
271     /*
272      * The only cntrl character in graph+blank is TAB (in blank).
273      * Here we implement (blank-TAB)=Zs instead of calling u_isblank().
274      */
275     return (UBool)((GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c));
276 }
277 
278 U_CAPI UBool U_EXPORT2
u_isgraph(UChar32 c)279 u_isgraph(UChar32 c) {
280     uint32_t props;
281     GET_PROPS(c, props);
282     /* comparing ==0 returns FALSE for the categories mentioned */
283     return (UBool)((CAT_MASK(props)&
284                     (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
285                    ==0);
286 }
287 
288 /**
289  * Checks if c is in
290  * [^\p{space}\p{gc=Control}\p{gc=Surrogate}\p{gc=Unassigned}]
291  * with space=\p{Whitespace} and Control=Cc.
292  * Implements UCHAR_POSIX_GRAPH.
293  * @internal
294  */
295 U_CFUNC UBool
u_isgraphPOSIX(UChar32 c)296 u_isgraphPOSIX(UChar32 c) {
297     uint32_t props;
298     GET_PROPS(c, props);
299     /* \p{space}\p{gc=Control} == \p{gc=Z}\p{Control} */
300     /* comparing ==0 returns FALSE for the categories mentioned */
301     return (UBool)((CAT_MASK(props)&
302                     (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
303                    ==0);
304 }
305 
306 U_CAPI UBool U_EXPORT2
u_ispunct(UChar32 c)307 u_ispunct(UChar32 c) {
308     uint32_t props;
309     GET_PROPS(c, props);
310     return (UBool)((CAT_MASK(props)&U_GC_P_MASK)!=0);
311 }
312 
313 /* Checks if the Unicode character can start a Unicode identifier.*/
314 U_CAPI UBool U_EXPORT2
u_isIDStart(UChar32 c)315 u_isIDStart(UChar32 c) {
316     /* same as u_isalpha() */
317     uint32_t props;
318     GET_PROPS(c, props);
319     return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_NL_MASK))!=0);
320 }
321 
322 /* Checks if the Unicode character can be a Unicode identifier part other than starting the
323  identifier.*/
324 U_CAPI UBool U_EXPORT2
u_isIDPart(UChar32 c)325 u_isIDPart(UChar32 c) {
326     uint32_t props;
327     GET_PROPS(c, props);
328     return (UBool)(
329            (CAT_MASK(props)&
330             (U_GC_ND_MASK|U_GC_NL_MASK|
331              U_GC_L_MASK|
332              U_GC_PC_MASK|U_GC_MC_MASK|U_GC_MN_MASK)
333            )!=0 ||
334            u_isIDIgnorable(c));
335 }
336 
337 /*Checks if the Unicode character can be ignorable in a Java or Unicode identifier.*/
338 U_CAPI UBool U_EXPORT2
u_isIDIgnorable(UChar32 c)339 u_isIDIgnorable(UChar32 c) {
340     if(c<=0x9f) {
341         return u_isISOControl(c) && !IS_THAT_ASCII_CONTROL_SPACE(c);
342     } else {
343         uint32_t props;
344         GET_PROPS(c, props);
345         return (UBool)(GET_CATEGORY(props)==U_FORMAT_CHAR);
346     }
347 }
348 
349 /*Checks if the Unicode character can start a Java identifier.*/
350 U_CAPI UBool U_EXPORT2
u_isJavaIDStart(UChar32 c)351 u_isJavaIDStart(UChar32 c) {
352     uint32_t props;
353     GET_PROPS(c, props);
354     return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0);
355 }
356 
357 /*Checks if the Unicode character can be a Java identifier part other than starting the
358  * identifier.
359  */
360 U_CAPI UBool U_EXPORT2
u_isJavaIDPart(UChar32 c)361 u_isJavaIDPart(UChar32 c) {
362     uint32_t props;
363     GET_PROPS(c, props);
364     return (UBool)(
365            (CAT_MASK(props)&
366             (U_GC_ND_MASK|U_GC_NL_MASK|
367              U_GC_L_MASK|
368              U_GC_SC_MASK|U_GC_PC_MASK|
369              U_GC_MC_MASK|U_GC_MN_MASK)
370            )!=0 ||
371            u_isIDIgnorable(c));
372 }
373 
374 U_CAPI int32_t U_EXPORT2
u_charDigitValue(UChar32 c)375 u_charDigitValue(UChar32 c) {
376     uint32_t props;
377     int32_t value;
378     GET_PROPS(c, props);
379     value=(int32_t)GET_NUMERIC_TYPE_VALUE(props)-UPROPS_NTV_DECIMAL_START;
380     if(value<=9) {
381         return value;
382     } else {
383         return -1;
384     }
385 }
386 
387 U_CAPI double U_EXPORT2
u_getNumericValue(UChar32 c)388 u_getNumericValue(UChar32 c) {
389     uint32_t props;
390     int32_t ntv;
391     GET_PROPS(c, props);
392     ntv=(int32_t)GET_NUMERIC_TYPE_VALUE(props);
393 
394     if(ntv==UPROPS_NTV_NONE) {
395         return U_NO_NUMERIC_VALUE;
396     } else if(ntv<UPROPS_NTV_DIGIT_START) {
397         /* decimal digit */
398         return ntv-UPROPS_NTV_DECIMAL_START;
399     } else if(ntv<UPROPS_NTV_NUMERIC_START) {
400         /* other digit */
401         return ntv-UPROPS_NTV_DIGIT_START;
402     } else if(ntv<UPROPS_NTV_FRACTION_START) {
403         /* small integer */
404         return ntv-UPROPS_NTV_NUMERIC_START;
405     } else if(ntv<UPROPS_NTV_LARGE_START) {
406         /* fraction */
407         int32_t numerator=(ntv>>4)-12;
408         int32_t denominator=(ntv&0xf)+1;
409         return (double)numerator/denominator;
410     } else if(ntv<UPROPS_NTV_RESERVED_START) {
411         /* large, single-significant-digit integer */
412         double numValue;
413         int32_t mant=(ntv>>5)-14;
414         int32_t exp=(ntv&0x1f)+2;
415         numValue=mant;
416 
417         /* multiply by 10^exp without math.h */
418         while(exp>=4) {
419             numValue*=10000.;
420             exp-=4;
421         }
422         switch(exp) {
423         case 3:
424             numValue*=1000.;
425             break;
426         case 2:
427             numValue*=100.;
428             break;
429         case 1:
430             numValue*=10.;
431             break;
432         case 0:
433         default:
434             break;
435         }
436 
437         return numValue;
438     } else {
439         /* reserved */
440         return U_NO_NUMERIC_VALUE;
441     }
442 }
443 
444 U_CAPI int32_t U_EXPORT2
u_digit(UChar32 ch,int8_t radix)445 u_digit(UChar32 ch, int8_t radix) {
446     int8_t value;
447     if((uint8_t)(radix-2)<=(36-2)) {
448         value=(int8_t)u_charDigitValue(ch);
449         if(value<0) {
450             /* ch is not a decimal digit, try latin letters */
451             if(ch>=0x61 && ch<=0x7A) {
452                 value=(int8_t)(ch-0x57);  /* ch - 'a' + 10 */
453             } else if(ch>=0x41 && ch<=0x5A) {
454                 value=(int8_t)(ch-0x37);  /* ch - 'A' + 10 */
455             } else if(ch>=0xFF41 && ch<=0xFF5A) {
456                 value=(int8_t)(ch-0xFF37);  /* fullwidth ASCII a-z */
457             } else if(ch>=0xFF21 && ch<=0xFF3A) {
458                 value=(int8_t)(ch-0xFF17);  /* fullwidth ASCII A-Z */
459             }
460         }
461     } else {
462         value=-1;   /* invalid radix */
463     }
464     return (int8_t)((value<radix) ? value : -1);
465 }
466 
467 U_CAPI UChar32 U_EXPORT2
u_forDigit(int32_t digit,int8_t radix)468 u_forDigit(int32_t digit, int8_t radix) {
469     if((uint8_t)(radix-2)>(36-2) || (uint32_t)digit>=(uint32_t)radix) {
470         return 0;
471     } else if(digit<10) {
472         return (UChar32)(0x30+digit);
473     } else {
474         return (UChar32)((0x61-10)+digit);
475     }
476 }
477 
478 /* miscellaneous, and support for uprops.c ---------------------------------- */
479 
480 U_CAPI void U_EXPORT2
u_getUnicodeVersion(UVersionInfo versionArray)481 u_getUnicodeVersion(UVersionInfo versionArray) {
482     if(versionArray!=NULL) {
483         uprv_memcpy(versionArray, dataVersion, U_MAX_VERSION_LENGTH);
484     }
485 }
486 
487 U_CFUNC uint32_t
u_getUnicodeProperties(UChar32 c,int32_t column)488 u_getUnicodeProperties(UChar32 c, int32_t column) {
489     uint16_t vecIndex;
490 
491     if(column==-1) {
492         uint32_t props;
493         GET_PROPS(c, props);
494         return props;
495     } else if(
496                column<0 || column>=propsVectorsColumns
497     ) {
498         return 0;
499     } else {
500         vecIndex=UTRIE2_GET16(&propsVectorsTrie, c);
501         return propsVectors[vecIndex+column];
502     }
503 }
504 
505 U_CFUNC int32_t
uprv_getMaxValues(int32_t column)506 uprv_getMaxValues(int32_t column) {
507     switch(column) {
508     case 0:
509         return indexes[UPROPS_MAX_VALUES_INDEX];
510     case 2:
511         return indexes[UPROPS_MAX_VALUES_2_INDEX];
512     default:
513         return 0;
514     }
515 }
516 
517 U_CAPI void U_EXPORT2
u_charAge(UChar32 c,UVersionInfo versionArray)518 u_charAge(UChar32 c, UVersionInfo versionArray) {
519     if(versionArray!=NULL) {
520         uint32_t version=u_getUnicodeProperties(c, 0)>>UPROPS_AGE_SHIFT;
521         versionArray[0]=(uint8_t)(version>>4);
522         versionArray[1]=(uint8_t)(version&0xf);
523         versionArray[2]=versionArray[3]=0;
524     }
525 }
526 
527 U_CAPI UScriptCode U_EXPORT2
uscript_getScript(UChar32 c,UErrorCode * pErrorCode)528 uscript_getScript(UChar32 c, UErrorCode *pErrorCode) {
529     uint32_t scriptX;
530     if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
531         return USCRIPT_INVALID_CODE;
532     }
533     if((uint32_t)c>0x10ffff) {
534         *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
535         return USCRIPT_INVALID_CODE;
536     }
537     scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
538     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
539         return (UScriptCode)scriptX;
540     } else if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) {
541         return USCRIPT_COMMON;
542     } else if(scriptX<UPROPS_SCRIPT_X_WITH_OTHER) {
543         return USCRIPT_INHERITED;
544     } else {
545         return (UScriptCode)scriptExtensions[scriptX&UPROPS_SCRIPT_MASK];
546     }
547 }
548 
549 U_DRAFT UBool U_EXPORT2
uscript_hasScript(UChar32 c,UScriptCode sc)550 uscript_hasScript(UChar32 c, UScriptCode sc) {
551     UScriptCode script;
552     const uint16_t *scx;
553     uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
554     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
555         return sc==(UScriptCode)scriptX;
556     }
557 
558     scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK);
559     if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) {
560         script=USCRIPT_COMMON;
561     } else if(scriptX<UPROPS_SCRIPT_X_WITH_OTHER) {
562         script=USCRIPT_INHERITED;
563     } else {
564         script=(UScriptCode)scx[0];
565         scx=scriptExtensions+scx[1];
566     }
567     if(sc==script) {
568         return TRUE;
569     }
570     while(sc>*scx) {
571         ++scx;
572     }
573     return sc==(*scx&0x7fff);
574 }
575 
576 U_DRAFT int32_t U_EXPORT2
uscript_getScriptExtensions(UChar32 c,UScriptCode * scripts,int32_t capacity,UErrorCode * pErrorCode)577 uscript_getScriptExtensions(UChar32 c,
578                             UScriptCode *scripts, int32_t capacity,
579                             UErrorCode *pErrorCode) {
580     uint32_t scriptX;
581     int32_t length;
582     const uint16_t *scx;
583     uint16_t sx;
584     if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
585         return 0;
586     }
587     if(capacity<0 || (capacity>0 && scripts==NULL)) {
588         *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
589         return 0;
590     }
591     scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
592     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
593         return 0;
594     }
595 
596     length=0;
597     scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK);
598     if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) {
599         scx=scriptExtensions+scx[1];
600     }
601     do {
602         sx=*scx++;
603         if(length<capacity) {
604             scripts[length]=sx&0x7fff;
605         }
606         ++length;
607     } while(sx<0x8000);
608     if(length>capacity) {
609         *pErrorCode=U_BUFFER_OVERFLOW_ERROR;
610     }
611     return length;
612 }
613 
614 U_CAPI UBlockCode U_EXPORT2
ublock_getCode(UChar32 c)615 ublock_getCode(UChar32 c) {
616     return (UBlockCode)((u_getUnicodeProperties(c, 0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT);
617 }
618 
619 /* property starts for UnicodeSet ------------------------------------------- */
620 
621 static UBool U_CALLCONV
_enumPropertyStartsRange(const void * context,UChar32 start,UChar32 end,uint32_t value)622 _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
623     /* add the start code point to the USet */
624     const USetAdder *sa=(const USetAdder *)context;
625     sa->add(sa->set, start);
626     return TRUE;
627 }
628 
629 #define USET_ADD_CP_AND_NEXT(sa, cp) sa->add(sa->set, cp); sa->add(sa->set, cp+1)
630 
631 U_CFUNC void U_EXPORT2
uchar_addPropertyStarts(const USetAdder * sa,UErrorCode * pErrorCode)632 uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
633     if(U_FAILURE(*pErrorCode)) {
634         return;
635     }
636 
637     /* add the start code point of each same-value range of the main trie */
638     utrie2_enum(&propsTrie, NULL, _enumPropertyStartsRange, sa);
639 
640     /* add code points with hardcoded properties, plus the ones following them */
641 
642     /* add for u_isblank() */
643     USET_ADD_CP_AND_NEXT(sa, TAB);
644 
645     /* add for IS_THAT_CONTROL_SPACE() */
646     sa->add(sa->set, CR+1); /* range TAB..CR */
647     sa->add(sa->set, 0x1c);
648     sa->add(sa->set, 0x1f+1);
649     USET_ADD_CP_AND_NEXT(sa, NL);
650 
651     /* add for u_isIDIgnorable() what was not added above */
652     sa->add(sa->set, DEL); /* range DEL..NBSP-1, NBSP added below */
653     sa->add(sa->set, HAIRSP);
654     sa->add(sa->set, RLM+1);
655     sa->add(sa->set, INHSWAP);
656     sa->add(sa->set, NOMDIG+1);
657     USET_ADD_CP_AND_NEXT(sa, ZWNBSP);
658 
659     /* add no-break spaces for u_isWhitespace() what was not added above */
660     USET_ADD_CP_AND_NEXT(sa, NBSP);
661     USET_ADD_CP_AND_NEXT(sa, FIGURESP);
662     USET_ADD_CP_AND_NEXT(sa, NNBSP);
663 
664     /* add for u_digit() */
665     sa->add(sa->set, U_a);
666     sa->add(sa->set, U_z+1);
667     sa->add(sa->set, U_A);
668     sa->add(sa->set, U_Z+1);
669     sa->add(sa->set, U_FW_a);
670     sa->add(sa->set, U_FW_z+1);
671     sa->add(sa->set, U_FW_A);
672     sa->add(sa->set, U_FW_Z+1);
673 
674     /* add for u_isxdigit() */
675     sa->add(sa->set, U_f+1);
676     sa->add(sa->set, U_F+1);
677     sa->add(sa->set, U_FW_f+1);
678     sa->add(sa->set, U_FW_F+1);
679 
680     /* add for UCHAR_DEFAULT_IGNORABLE_CODE_POINT what was not added above */
681     sa->add(sa->set, WJ); /* range WJ..NOMDIG */
682     sa->add(sa->set, 0xfff0);
683     sa->add(sa->set, 0xfffb+1);
684     sa->add(sa->set, 0xe0000);
685     sa->add(sa->set, 0xe0fff+1);
686 
687     /* add for UCHAR_GRAPHEME_BASE and others */
688     USET_ADD_CP_AND_NEXT(sa, CGJ);
689 }
690 
691 U_CFUNC void U_EXPORT2
upropsvec_addPropertyStarts(const USetAdder * sa,UErrorCode * pErrorCode)692 upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
693     if(U_FAILURE(*pErrorCode)) {
694         return;
695     }
696 
697     /* add the start code point of each same-value range of the properties vectors trie */
698     if(propsVectorsColumns>0) {
699         /* if propsVectorsColumns==0 then the properties vectors trie may not be there at all */
700         utrie2_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa);
701     }
702 }
703