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.

Header

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
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
*   Copyright (C) 1997-2011, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
******************************************************************************
*
* File CSTRING.C
*
* @author       Helena Shih
*
* Modification History:
*
*   Date        Name        Description
*   6/18/98     hshih       Created
*   09/08/98    stephen     Added include for ctype, for Mac Port
*   11/15/99    helena      Integrated S/390 IEEE changes. 
******************************************************************************
*/



#include <stdlib.h>
#include <stdio.h>
#include "unicode/utypes.h"
#include "cmemory.h"
#include "cstring.h"
#include "uassert.h"

/*
 * We hardcode case conversion for invariant characters to match our expectation
 * and the compiler execution charset.
 * This prevents problems on systems
 * - with non-default casing behavior, like Turkish system locales where
 *   tolower('I') maps to dotless i and toupper('i') maps to dotted I
 * - where there are no lowercase Latin characters at all, or using different
 *   codes (some old EBCDIC codepages)
 *
 * This works because the compiler usually runs on a platform where the execution
 * charset includes all of the invariant characters at their expected
 * code positions, so that the char * string literals in ICU code match
 * the char literals here.
 *
 * Note that the set of lowercase Latin letters is discontiguous in EBCDIC
 * and the set of uppercase Latin letters is discontiguous as well.
 */

U_CAPI UBool U_EXPORT2
uprv_isASCIILetter(char c) {
#if U_CHARSET_FAMILY==U_EBCDIC_FAMILY
    return
        ('a'<=c && c<='i') || ('j'<=c && c<='r') || ('s'<=c && c<='z') ||
        ('A'<=c && c<='I') || ('J'<=c && c<='R') || ('S'<=c && c<='Z');
#else
    return ('a'<=c && c<='z') || ('A'<=c && c<='Z');
#endif
}

U_CAPI char U_EXPORT2
uprv_toupper(char c) {
#if U_CHARSET_FAMILY==U_EBCDIC_FAMILY
    if(('a'<=c && c<='i') || ('j'<=c && c<='r') || ('s'<=c && c<='z')) {
        c=(char)(c+('A'-'a'));
    }
#else
    if('a'<=c && c<='z') {
        c=(char)(c+('A'-'a'));
    }
#endif
    return c;
}


#if 0
/*
 * Commented out because cstring.h defines uprv_tolower() to be
 * the same as either uprv_asciitolower() or uprv_ebcdictolower()
 * to reduce the amount of code to cover with tests.
 *
 * Note that this uprv_tolower() definition is likely to work for most
 * charset families, not just ASCII and EBCDIC, because its #else branch
 * is written generically.
 */
U_CAPI char U_EXPORT2
uprv_tolower(char c) {
#if U_CHARSET_FAMILY==U_EBCDIC_FAMILY
    if(('A'<=c && c<='I') || ('J'<=c && c<='R') || ('S'<=c && c<='Z')) {
        c=(char)(c+('a'-'A'));
    }
#else
    if('A'<=c && c<='Z') {
        c=(char)(c+('a'-'A'));
    }
#endif
    return c;
}
#endif

U_CAPI char U_EXPORT2
uprv_asciitolower(char c) {
    if(0x41<=c && c<=0x5a) {
        c=(char)(c+0x20);
    }
    return c;
}

U_CAPI char U_EXPORT2
uprv_ebcdictolower(char c) {
    if( (0xc1<=(uint8_t)c && (uint8_t)c<=0xc9) ||
        (0xd1<=(uint8_t)c && (uint8_t)c<=0xd9) ||
        (0xe2<=(uint8_t)c && (uint8_t)c<=0xe9)
    ) {
        c=(char)(c-0x40);
    }
    return c;
}


U_CAPI char* U_EXPORT2
T_CString_toLowerCase(char* str)
{
    char* origPtr = str;

    if (str) {
        do
            *str = (char)uprv_tolower(*str);
        while (*(str++));
    }

    return origPtr;
}

U_CAPI char* U_EXPORT2
T_CString_toUpperCase(char* str)
{
    char* origPtr = str;

    if (str) {
        do
            *str = (char)uprv_toupper(*str);
        while (*(str++));
    }

    return origPtr;
}

/*
 * Takes a int32_t and fills in  a char* string with that number "radix"-based.
 * Does not handle negative values (makes an empty string for them).
 * Writes at most 12 chars ("-2147483647" plus NUL).
 * Returns the length of the string (not including the NUL).
 */
U_CAPI int32_t U_EXPORT2
T_CString_integerToString(char* buffer, int32_t v, int32_t radix)
{
    char      tbuf[30];
    int32_t   tbx    = sizeof(tbuf);
    uint8_t   digit;
    int32_t   length = 0;
    uint32_t  uval;
    
    U_ASSERT(radix>=2 && radix<=16);
    uval = (uint32_t) v;
    if(v<0 && radix == 10) {
        /* Only in base 10 do we conside numbers to be signed. */
        uval = (uint32_t)(-v); 
        buffer[length++] = '-';
    }
    
    tbx = sizeof(tbuf)-1;
    tbuf[tbx] = 0;   /* We are generating the digits backwards.  Null term the end. */
    do {
        digit = (uint8_t)(uval % radix);
        tbuf[--tbx] = (char)(T_CString_itosOffset(digit));
        uval  = uval / radix;
    } while (uval != 0);
    
    /* copy converted number into user buffer  */
    uprv_strcpy(buffer+length, tbuf+tbx);
    length += sizeof(tbuf) - tbx -1;
    return length;
}



/*
 * Takes a int64_t and fills in  a char* string with that number "radix"-based.
 * Writes at most 21: chars ("-9223372036854775807" plus NUL).
 * Returns the length of the string, not including the terminating NULL.
 */
U_CAPI int32_t U_EXPORT2
T_CString_int64ToString(char* buffer, int64_t v, uint32_t radix)
{
    char      tbuf[30];
    int32_t   tbx    = sizeof(tbuf);
    uint8_t   digit;
    int32_t   length = 0;
    uint64_t  uval;
    
    U_ASSERT(radix>=2 && radix<=16);
    uval = (uint64_t) v;
    if(v<0 && radix == 10) {
        /* Only in base 10 do we conside numbers to be signed. */
        uval = (uint64_t)(-v); 
        buffer[length++] = '-';
    }
    
    tbx = sizeof(tbuf)-1;
    tbuf[tbx] = 0;   /* We are generating the digits backwards.  Null term the end. */
    do {
        digit = (uint8_t)(uval % radix);
        tbuf[--tbx] = (char)(T_CString_itosOffset(digit));
        uval  = uval / radix;
    } while (uval != 0);
    
    /* copy converted number into user buffer  */
    uprv_strcpy(buffer+length, tbuf+tbx);
    length += sizeof(tbuf) - tbx -1;
    return length;
}


U_CAPI int32_t U_EXPORT2
T_CString_stringToInteger(const char *integerString, int32_t radix)
{
    char *end;
    return uprv_strtoul(integerString, &end, radix);

}

U_CAPI int U_EXPORT2
uprv_stricmp(const char *str1, const char *str2) {
    if(str1==NULL) {
        if(str2==NULL) {
            return 0;
        } else {
            return -1;
        }
    } else if(str2==NULL) {
        return 1;
    } else {
        /* compare non-NULL strings lexically with lowercase */
        int rc;
        unsigned char c1, c2;

        for(;;) {
            c1=(unsigned char)*str1;
            c2=(unsigned char)*str2;
            if(c1==0) {
                if(c2==0) {
                    return 0;
                } else {
                    return -1;
                }
            } else if(c2==0) {
                return 1;
            } else {
                /* compare non-zero characters with lowercase */
                rc=(int)(unsigned char)uprv_tolower(c1)-(int)(unsigned char)uprv_tolower(c2);
                if(rc!=0) {
                    return rc;
                }
            }
            ++str1;
            ++str2;
        }
    }
}

U_CAPI int U_EXPORT2
uprv_strnicmp(const char *str1, const char *str2, uint32_t n) {
    if(str1==NULL) {
        if(str2==NULL) {
            return 0;
        } else {
            return -1;
        }
    } else if(str2==NULL) {
        return 1;
    } else {
        /* compare non-NULL strings lexically with lowercase */
        int rc;
        unsigned char c1, c2;

        for(; n--;) {
            c1=(unsigned char)*str1;
            c2=(unsigned char)*str2;
            if(c1==0) {
                if(c2==0) {
                    return 0;
                } else {
                    return -1;
                }
            } else if(c2==0) {
                return 1;
            } else {
                /* compare non-zero characters with lowercase */
                rc=(int)(unsigned char)uprv_tolower(c1)-(int)(unsigned char)uprv_tolower(c2);
                if(rc!=0) {
                    return rc;
                }
            }
            ++str1;
            ++str2;
        }
    }

    return 0;
}

U_CAPI char* U_EXPORT2
uprv_strdup(const char *src) {
    size_t len = uprv_strlen(src) + 1;
    char *dup = (char *) uprv_malloc(len);

    if (dup) {
        uprv_memcpy(dup, src, len);
    }

    return dup;
}

U_CAPI char* U_EXPORT2
uprv_strndup(const char *src, int32_t n) {
    char *dup;

    if(n < 0) {
        dup = uprv_strdup(src);
    } else {
        dup = (char*)uprv_malloc(n+1);
        if (dup) { 
            uprv_memcpy(dup, src, n);
            dup[n] = 0;
        }
    }

    return dup;
}