DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (b6d82b1a6b02)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
********************************************************************************
*   Copyright (C) 1996-2016, International Business Machines
*   Corporation and others.  All Rights Reserved.
********************************************************************************
*
* File UCHAR.C
*
* Modification History:
*
*   Date        Name        Description
*   04/02/97    aliu        Creation.
*   4/15/99     Madhu       Updated all the function definitions for C Implementation
*   5/20/99     Madhu       Added the function u_getVersion()
*   8/19/1999   srl         Upgraded scripts to Unicode3.0 
*   11/11/1999  weiv        added u_isalnum(), cleaned comments
*   01/11/2000  helena      Renamed u_getVersion to u_getUnicodeVersion.
*   06/20/2000  helena      OS/400 port changes; mostly typecast.
******************************************************************************
*/

#include "unicode/utypes.h"
#include "unicode/uchar.h"
#include "unicode/uscript.h"
#include "unicode/udata.h"
#include "uassert.h"
#include "cmemory.h"
#include "ucln_cmn.h"
#include "utrie2.h"
#include "udataswp.h"
#include "uprops.h"
#include "ustr_imp.h"

/* uchar_props_data.h is machine-generated by genprops --csource */
#define INCLUDED_FROM_UCHAR_C
#include "uchar_props_data.h"

/* constants and macros for access to the data ------------------------------ */

/* getting a uint32_t properties word from the data */
#define GET_PROPS(c, result) ((result)=UTRIE2_GET16(&propsTrie, c));

/* API functions ------------------------------------------------------------ */

/* Gets the Unicode character's general category.*/
U_CAPI int8_t U_EXPORT2
u_charType(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (int8_t)GET_CATEGORY(props);
}

/* Enumerate all code points with their general categories. */
struct _EnumTypeCallback {
    UCharEnumTypeRange *enumRange;
    const void *context;
};

static uint32_t U_CALLCONV
_enumTypeValue(const void *context, uint32_t value) {
    (void)context;
    return GET_CATEGORY(value);
}

static UBool U_CALLCONV
_enumTypeRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
    /* just cast the value to UCharCategory */
    return ((struct _EnumTypeCallback *)context)->
        enumRange(((struct _EnumTypeCallback *)context)->context,
                  start, end+1, (UCharCategory)value);
}

U_CAPI void U_EXPORT2
u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context) {
    struct _EnumTypeCallback callback;

    if(enumRange==NULL) {
        return;
    }

    callback.enumRange=enumRange;
    callback.context=context;
    utrie2_enum(&propsTrie, _enumTypeValue, _enumTypeRange, &callback);
}

/* Checks if ch is a lower case letter.*/
U_CAPI UBool U_EXPORT2
u_islower(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)==U_LOWERCASE_LETTER);
}

/* Checks if ch is an upper case letter.*/
U_CAPI UBool U_EXPORT2
u_isupper(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)==U_UPPERCASE_LETTER);
}

/* Checks if ch is a title case letter; usually upper case letters.*/
U_CAPI UBool U_EXPORT2
u_istitle(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)==U_TITLECASE_LETTER);
}

/* Checks if ch is a decimal digit. */
U_CAPI UBool U_EXPORT2
u_isdigit(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
}

U_CAPI UBool U_EXPORT2
u_isxdigit(UChar32 c) {
    uint32_t props;

    /* check ASCII and Fullwidth ASCII a-fA-F */
    if(
        (c<=0x66 && c>=0x41 && (c<=0x46 || c>=0x61)) ||
        (c>=0xff21 && c<=0xff46 && (c<=0xff26 || c>=0xff41))
    ) {
        return TRUE;
    }

    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
}

/* Checks if the Unicode character is a letter.*/
U_CAPI UBool U_EXPORT2
u_isalpha(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&U_GC_L_MASK)!=0);
}

U_CAPI UBool U_EXPORT2
u_isUAlphabetic(UChar32 c) {
    return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_ALPHABETIC))!=0;
}

/* Checks if c is a letter or a decimal digit */
U_CAPI UBool U_EXPORT2
u_isalnum(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0);
}

/**
 * Checks if c is alphabetic, or a decimal digit; implements UCHAR_POSIX_ALNUM.
 * @internal
 */
U_CFUNC UBool
u_isalnumPOSIX(UChar32 c) {
    return (UBool)(u_isUAlphabetic(c) || u_isdigit(c));
}

/* Checks if ch is a unicode character with assigned character type.*/
U_CAPI UBool U_EXPORT2
u_isdefined(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(GET_CATEGORY(props)!=0);
}

/* Checks if the Unicode character is a base form character that can take a diacritic.*/
U_CAPI UBool U_EXPORT2
u_isbase(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0);
}

/* Checks if the Unicode character is a control character.*/
U_CAPI UBool U_EXPORT2
u_iscntrl(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0);
}

U_CAPI UBool U_EXPORT2
u_isISOControl(UChar32 c) {
    return (uint32_t)c<=0x9f && (c<=0x1f || c>=0x7f);
}

/* Some control characters that are used as space. */
#define IS_THAT_CONTROL_SPACE(c) \
    (c<=0x9f && ((c>=TAB && c<=CR) || (c>=0x1c && c <=0x1f) || c==NL))

/* Java has decided that U+0085 New Line is not whitespace any more. */
#define IS_THAT_ASCII_CONTROL_SPACE(c) \
    (c<=0x1f && c>=TAB && (c<=CR || c>=0x1c))

/* Checks if the Unicode character is a space character.*/
U_CAPI UBool U_EXPORT2
u_isspace(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c));
}

U_CAPI UBool U_EXPORT2
u_isJavaSpaceChar(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0);
}

/* Checks if the Unicode character is a whitespace character.*/
U_CAPI UBool U_EXPORT2
u_isWhitespace(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(
                ((CAT_MASK(props)&U_GC_Z_MASK)!=0 &&
                    c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */
                IS_THAT_ASCII_CONTROL_SPACE(c)
           );
}

U_CAPI UBool U_EXPORT2
u_isblank(UChar32 c) {
    if((uint32_t)c<=0x9f) {
        return c==9 || c==0x20; /* TAB or SPACE */
    } else {
        /* Zs */
        uint32_t props;
        GET_PROPS(c, props);
        return (UBool)(GET_CATEGORY(props)==U_SPACE_SEPARATOR);
    }
}

U_CAPI UBool U_EXPORT2
u_isUWhiteSpace(UChar32 c) {
    return (u_getUnicodeProperties(c, 1)&U_MASK(UPROPS_WHITE_SPACE))!=0;
}

/* Checks if the Unicode character is printable.*/
U_CAPI UBool U_EXPORT2
u_isprint(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    /* comparing ==0 returns FALSE for the categories mentioned */
    return (UBool)((CAT_MASK(props)&U_GC_C_MASK)==0);
}

/**
 * Checks if c is in \p{graph}\p{blank} - \p{cntrl}.
 * Implements UCHAR_POSIX_PRINT.
 * @internal
 */
U_CFUNC UBool
u_isprintPOSIX(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    /*
     * The only cntrl character in graph+blank is TAB (in blank).
     * Here we implement (blank-TAB)=Zs instead of calling u_isblank().
     */
    return (UBool)((GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c));
}

U_CAPI UBool U_EXPORT2
u_isgraph(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    /* comparing ==0 returns FALSE for the categories mentioned */
    return (UBool)((CAT_MASK(props)&
                    (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
                   ==0);
}

/**
 * Checks if c is in
 * [^\p{space}\p{gc=Control}\p{gc=Surrogate}\p{gc=Unassigned}]
 * with space=\p{Whitespace} and Control=Cc.
 * Implements UCHAR_POSIX_GRAPH.
 * @internal
 */
U_CFUNC UBool
u_isgraphPOSIX(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    /* \p{space}\p{gc=Control} == \p{gc=Z}\p{Control} */
    /* comparing ==0 returns FALSE for the categories mentioned */
    return (UBool)((CAT_MASK(props)&
                    (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
                   ==0);
}

U_CAPI UBool U_EXPORT2
u_ispunct(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&U_GC_P_MASK)!=0);
}

/* Checks if the Unicode character can start a Unicode identifier.*/
U_CAPI UBool U_EXPORT2
u_isIDStart(UChar32 c) {
    /* same as u_isalpha() */
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_NL_MASK))!=0);
}

/* Checks if the Unicode character can be a Unicode identifier part other than starting the
 identifier.*/
U_CAPI UBool U_EXPORT2
u_isIDPart(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(
           (CAT_MASK(props)&
            (U_GC_ND_MASK|U_GC_NL_MASK|
             U_GC_L_MASK|
             U_GC_PC_MASK|U_GC_MC_MASK|U_GC_MN_MASK)
           )!=0 ||
           u_isIDIgnorable(c));
}

/*Checks if the Unicode character can be ignorable in a Java or Unicode identifier.*/
U_CAPI UBool U_EXPORT2
u_isIDIgnorable(UChar32 c) {
    if(c<=0x9f) {
        return u_isISOControl(c) && !IS_THAT_ASCII_CONTROL_SPACE(c);
    } else {
        uint32_t props;
        GET_PROPS(c, props);
        return (UBool)(GET_CATEGORY(props)==U_FORMAT_CHAR);
    }
}

/*Checks if the Unicode character can start a Java identifier.*/
U_CAPI UBool U_EXPORT2
u_isJavaIDStart(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0);
}

/*Checks if the Unicode character can be a Java identifier part other than starting the
 * identifier.
 */
U_CAPI UBool U_EXPORT2
u_isJavaIDPart(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return (UBool)(
           (CAT_MASK(props)&
            (U_GC_ND_MASK|U_GC_NL_MASK|
             U_GC_L_MASK|
             U_GC_SC_MASK|U_GC_PC_MASK|
             U_GC_MC_MASK|U_GC_MN_MASK)
           )!=0 ||
           u_isIDIgnorable(c));
}

U_CAPI int32_t U_EXPORT2
u_charDigitValue(UChar32 c) {
    uint32_t props;
    int32_t value;
    GET_PROPS(c, props);
    value=(int32_t)GET_NUMERIC_TYPE_VALUE(props)-UPROPS_NTV_DECIMAL_START;
    if(value<=9) {
        return value;
    } else {
        return -1;
    }
}

U_CAPI double U_EXPORT2
u_getNumericValue(UChar32 c) {
    uint32_t props;
    int32_t ntv;
    GET_PROPS(c, props);
    ntv=(int32_t)GET_NUMERIC_TYPE_VALUE(props);

    if(ntv==UPROPS_NTV_NONE) {
        return U_NO_NUMERIC_VALUE;
    } else if(ntv<UPROPS_NTV_DIGIT_START) {
        /* decimal digit */
        return ntv-UPROPS_NTV_DECIMAL_START;
    } else if(ntv<UPROPS_NTV_NUMERIC_START) {
        /* other digit */
        return ntv-UPROPS_NTV_DIGIT_START;
    } else if(ntv<UPROPS_NTV_FRACTION_START) {
        /* small integer */
        return ntv-UPROPS_NTV_NUMERIC_START;
    } else if(ntv<UPROPS_NTV_LARGE_START) {
        /* fraction */
        int32_t numerator=(ntv>>4)-12;
        int32_t denominator=(ntv&0xf)+1;
        return (double)numerator/denominator;
    } else if(ntv<UPROPS_NTV_BASE60_START) {
        /* large, single-significant-digit integer */
        double numValue;
        int32_t mant=(ntv>>5)-14;
        int32_t exp=(ntv&0x1f)+2;
        numValue=mant;

        /* multiply by 10^exp without math.h */
        while(exp>=4) {
            numValue*=10000.;
            exp-=4;
        }
        switch(exp) {
        case 3:
            numValue*=1000.;
            break;
        case 2:
            numValue*=100.;
            break;
        case 1:
            numValue*=10.;
            break;
        case 0:
        default:
            break;
        }

        return numValue;
    } else if(ntv<UPROPS_NTV_FRACTION20_START) {
        /* sexagesimal (base 60) integer */
        int32_t numValue=(ntv>>2)-0xbf;
        int32_t exp=(ntv&3)+1;

        switch(exp) {
        case 4:
            numValue*=60*60*60*60;
            break;
        case 3:
            numValue*=60*60*60;
            break;
        case 2:
            numValue*=60*60;
            break;
        case 1:
            numValue*=60;
            break;
        case 0:
        default:
            break;
        }

        return numValue;
    } else if(ntv<UPROPS_NTV_FRACTION32_START) {
        // fraction-20 e.g. 3/80
        int32_t frac20=ntv-UPROPS_NTV_FRACTION20_START;  // 0..0x17
        int32_t numerator=2*(frac20&3)+1;
        int32_t denominator=20<<(frac20>>2);
        return (double)numerator/denominator;
    } else if(ntv<UPROPS_NTV_RESERVED_START) {
        // fraction-32 e.g. 3/64
        int32_t frac32=ntv-UPROPS_NTV_FRACTION32_START;  // 0..15
        int32_t numerator=2*(frac32&3)+1;
        int32_t denominator=32<<(frac32>>2);
        return (double)numerator/denominator;
    } else {
        /* reserved */
        return U_NO_NUMERIC_VALUE;
    }
}

U_CAPI int32_t U_EXPORT2
u_digit(UChar32 ch, int8_t radix) {
    int8_t value;
    if((uint8_t)(radix-2)<=(36-2)) {
        value=(int8_t)u_charDigitValue(ch);
        if(value<0) {
            /* ch is not a decimal digit, try latin letters */
            if(ch>=0x61 && ch<=0x7A) {
                value=(int8_t)(ch-0x57);  /* ch - 'a' + 10 */
            } else if(ch>=0x41 && ch<=0x5A) {
                value=(int8_t)(ch-0x37);  /* ch - 'A' + 10 */
            } else if(ch>=0xFF41 && ch<=0xFF5A) {
                value=(int8_t)(ch-0xFF37);  /* fullwidth ASCII a-z */
            } else if(ch>=0xFF21 && ch<=0xFF3A) {
                value=(int8_t)(ch-0xFF17);  /* fullwidth ASCII A-Z */
            }
        }
    } else {
        value=-1;   /* invalid radix */
    }
    return (int8_t)((value<radix) ? value : -1);
}

U_CAPI UChar32 U_EXPORT2
u_forDigit(int32_t digit, int8_t radix) {
    if((uint8_t)(radix-2)>(36-2) || (uint32_t)digit>=(uint32_t)radix) {
        return 0;
    } else if(digit<10) {
        return (UChar32)(0x30+digit);
    } else {
        return (UChar32)((0x61-10)+digit);
    }
}

/* miscellaneous, and support for uprops.cpp -------------------------------- */

U_CAPI void U_EXPORT2
u_getUnicodeVersion(UVersionInfo versionArray) {
    if(versionArray!=NULL) {
        uprv_memcpy(versionArray, dataVersion, U_MAX_VERSION_LENGTH);
    }
}

U_CFUNC uint32_t
u_getMainProperties(UChar32 c) {
    uint32_t props;
    GET_PROPS(c, props);
    return props;
}

U_CFUNC uint32_t
u_getUnicodeProperties(UChar32 c, int32_t column) {
    U_ASSERT(column>=0);
    if(column>=propsVectorsColumns) {
        return 0;
    } else {
        uint16_t vecIndex=UTRIE2_GET16(&propsVectorsTrie, c);
        return propsVectors[vecIndex+column];
    }
}

U_CFUNC int32_t
uprv_getMaxValues(int32_t column) {
    switch(column) {
    case 0:
        return indexes[UPROPS_MAX_VALUES_INDEX];
    case 2:
        return indexes[UPROPS_MAX_VALUES_2_INDEX];
    default:
        return 0;
    }
}

U_CAPI void U_EXPORT2
u_charAge(UChar32 c, UVersionInfo versionArray) {
    if(versionArray!=NULL) {
        uint32_t version=u_getUnicodeProperties(c, 0)>>UPROPS_AGE_SHIFT;
        versionArray[0]=(uint8_t)(version>>4);
        versionArray[1]=(uint8_t)(version&0xf);
        versionArray[2]=versionArray[3]=0;
    }
}

U_CAPI UScriptCode U_EXPORT2
uscript_getScript(UChar32 c, UErrorCode *pErrorCode) {
    uint32_t scriptX;
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return USCRIPT_INVALID_CODE;
    }
    if((uint32_t)c>0x10ffff) {
        *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
        return USCRIPT_INVALID_CODE;
    }
    scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
    if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
        return (UScriptCode)scriptX;
    } else if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) {
        return USCRIPT_COMMON;
    } else if(scriptX<UPROPS_SCRIPT_X_WITH_OTHER) {
        return USCRIPT_INHERITED;
    } else {
        return (UScriptCode)scriptExtensions[scriptX&UPROPS_SCRIPT_MASK];
    }
}

U_CAPI UBool U_EXPORT2
uscript_hasScript(UChar32 c, UScriptCode sc) {
    const uint16_t *scx;
    uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
    if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
        return sc==(UScriptCode)scriptX;
    }

    scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK);
    if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) {
        scx=scriptExtensions+scx[1];
    }
    if(sc>=USCRIPT_CODE_LIMIT) {
        /* Guard against bogus input that would make us go past the Script_Extensions terminator. */
        return FALSE;
    }
    while(sc>*scx) {
        ++scx;
    }
    return sc==(*scx&0x7fff);
}

U_CAPI int32_t U_EXPORT2
uscript_getScriptExtensions(UChar32 c,
                            UScriptCode *scripts, int32_t capacity,
                            UErrorCode *pErrorCode) {
    uint32_t scriptX;
    int32_t length;
    const uint16_t *scx;
    uint16_t sx;
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }
    if(capacity<0 || (capacity>0 && scripts==NULL)) {
        *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }
    scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
    if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
        if(capacity==0) {
            *pErrorCode=U_BUFFER_OVERFLOW_ERROR;
        } else {
            scripts[0]=(UScriptCode)scriptX;
        }
        return 1;
    }

    scx=scriptExtensions+(scriptX&UPROPS_SCRIPT_MASK);
    if(scriptX>=UPROPS_SCRIPT_X_WITH_OTHER) {
        scx=scriptExtensions+scx[1];
    }
    length=0;
    do {
        sx=*scx++;
        if(length<capacity) {
            scripts[length]=(UScriptCode)(sx&0x7fff);
        }
        ++length;
    } while(sx<0x8000);
    if(length>capacity) {
        *pErrorCode=U_BUFFER_OVERFLOW_ERROR;
    }
    return length;
}

U_CAPI UBlockCode U_EXPORT2
ublock_getCode(UChar32 c) {
    return (UBlockCode)((u_getUnicodeProperties(c, 0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT);
}

/* property starts for UnicodeSet ------------------------------------------- */

static UBool U_CALLCONV
_enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
    /* add the start code point to the USet */
    const USetAdder *sa=(const USetAdder *)context;
    sa->add(sa->set, start);
    (void)end;
    (void)value;
    return TRUE;
}

#define USET_ADD_CP_AND_NEXT(sa, cp) sa->add(sa->set, cp); sa->add(sa->set, cp+1)

U_CFUNC void U_EXPORT2
uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
    if(U_FAILURE(*pErrorCode)) {
        return;
    }

    /* add the start code point of each same-value range of the main trie */
    utrie2_enum(&propsTrie, NULL, _enumPropertyStartsRange, sa);

    /* add code points with hardcoded properties, plus the ones following them */

    /* add for u_isblank() */
    USET_ADD_CP_AND_NEXT(sa, TAB);

    /* add for IS_THAT_CONTROL_SPACE() */
    sa->add(sa->set, CR+1); /* range TAB..CR */
    sa->add(sa->set, 0x1c);
    sa->add(sa->set, 0x1f+1);
    USET_ADD_CP_AND_NEXT(sa, NL);

    /* add for u_isIDIgnorable() what was not added above */
    sa->add(sa->set, DEL); /* range DEL..NBSP-1, NBSP added below */
    sa->add(sa->set, HAIRSP);
    sa->add(sa->set, RLM+1);
    sa->add(sa->set, INHSWAP);
    sa->add(sa->set, NOMDIG+1);
    USET_ADD_CP_AND_NEXT(sa, ZWNBSP);

    /* add no-break spaces for u_isWhitespace() what was not added above */
    USET_ADD_CP_AND_NEXT(sa, NBSP);
    USET_ADD_CP_AND_NEXT(sa, FIGURESP);
    USET_ADD_CP_AND_NEXT(sa, NNBSP);

    /* add for u_digit() */
    sa->add(sa->set, U_a);
    sa->add(sa->set, U_z+1);
    sa->add(sa->set, U_A);
    sa->add(sa->set, U_Z+1);
    sa->add(sa->set, U_FW_a);
    sa->add(sa->set, U_FW_z+1);
    sa->add(sa->set, U_FW_A);
    sa->add(sa->set, U_FW_Z+1);

    /* add for u_isxdigit() */
    sa->add(sa->set, U_f+1);
    sa->add(sa->set, U_F+1);
    sa->add(sa->set, U_FW_f+1);
    sa->add(sa->set, U_FW_F+1);

    /* add for UCHAR_DEFAULT_IGNORABLE_CODE_POINT what was not added above */
    sa->add(sa->set, WJ); /* range WJ..NOMDIG */
    sa->add(sa->set, 0xfff0);
    sa->add(sa->set, 0xfffb+1);
    sa->add(sa->set, 0xe0000);
    sa->add(sa->set, 0xe0fff+1);

    /* add for UCHAR_GRAPHEME_BASE and others */
    USET_ADD_CP_AND_NEXT(sa, CGJ);
}

U_CFUNC void U_EXPORT2
upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
    if(U_FAILURE(*pErrorCode)) {
        return;
    }

    /* add the start code point of each same-value range of the properties vectors trie */
    utrie2_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa);
}