newlib/libc/stdlib/wcstoll.c

   1 /*
   2 FUNCTION
   3    <<wcstoll>>, <<wcstoll_l>>---wide string to long long
   4
   5 INDEX
   6         wcstoll
   7
   8 INDEX
   9         wcstoll_l
  10
  11 INDEX
  12         _wcstoll_r
  13
  14 SYNOPSIS
  15         #include <wchar.h>
  16         long long wcstoll(const wchar_t *__restrict <[s]>,
  17                           wchar_t **__restrict <[ptr]>,int <[base]>);
  18
  19         #include <wchar.h>
  20         long long wcstoll_l(const wchar_t *__restrict <[s]>,
  21                             wchar_t **__restrict <[ptr]>, int <[base]>,
  22                             locale_t <[locale]>);
  23
  24         long long _wcstoll_r(void *<[reent]>, const wchar_t *<[s]>,
  25                              wchar_t **<[ptr]>, int <[base]>);
  26
  27 DESCRIPTION
  28 The function <<wcstoll>> converts the wide string <<*<[s]>>> to
  29 a <<long long>>. First, it breaks down the string into three parts:
  30 leading whitespace, which is ignored; a subject string consisting
  31 of characters resembling an integer in the radix specified by <[base]>;
  32 and a trailing portion consisting of zero or more unparseable characters,
  33 and always including the terminating null character. Then, it attempts
  34 to convert the subject string into a <<long long>> and returns the
  35 result.
  36
  37 If the value of <[base]> is 0, the subject string is expected to look
  38 like a normal C integer constant: an optional sign, a possible `<<0x>>'
  39 indicating a hexadecimal base, and a number. If <[base]> is between
  40 2 and 36, the expected form of the subject is a sequence of letters
  41 and digits representing an integer in the radix specified by <[base]>,
  42 with an optional plus or minus sign. The letters <<a>>--<<z>> (or,
  43 equivalently, <<A>>--<<Z>>) are used to signify values from 10 to 35;
  44 only letters whose ascribed values are less than <[base]> are
  45 permitted. If <[base]> is 16, a leading <<0x>> is permitted.
  46
  47 The subject sequence is the longest initial sequence of the input
  48 string that has the expected form, starting with the first
  49 non-whitespace character.  If the string is empty or consists entirely
  50 of whitespace, or if the first non-whitespace character is not a
  51 permissible letter or digit, the subject string is empty.
  52
  53 If the subject string is acceptable, and the value of <[base]> is zero,
  54 <<wcstoll>> attempts to determine the radix from the input string. A
  55 string with a leading <<0x>> is treated as a hexadecimal value; a string with
  56 a leading 0 and no <<x>> is treated as octal; all other strings are
  57 treated as decimal. If <[base]> is between 2 and 36, it is used as the
  58 conversion radix, as described above. If the subject string begins with
  59 a minus sign, the value is negated. Finally, a pointer to the first
  60 character past the converted subject string is stored in <[ptr]>, if
  61 <[ptr]> is not <<NULL>>.
  62
  63 If the subject string is empty (or not in acceptable form), no conversion
  64 is performed and the value of <[s]> is stored in <[ptr]> (if <[ptr]> is
  65 not <<NULL>>).
  66
  67 The alternate function <<_wcstoll_r>> is a reentrant version.  The
  68 extra argument <[reent]> is a pointer to a reentrancy structure.
  69
  70 <<wcstoll_l>> is like <<wcstoll>> but performs the conversion based on the
  71 locale specified by the locale object locale.  If <[locale]> is
  72 LC_GLOBAL_LOCALE or not a valid locale object, the behaviour is undefined.
  73
  74 RETURNS
  75 <<wcstoll>>, <<wcstoll_l>> return the converted value, if any. If no
  76 conversion was made, 0 is returned.
  77
  78 <<wcstoll>>, <<wcstoll_l>> return <<LONG_LONG_MAX>> or <<LONG_LONG_MIN>>
  79 if the magnitude of the converted value is too large, and sets <<errno>>
  80 to <<ERANGE>>.
  81
  82 PORTABILITY
  83 <<wcstoll>> is ANSI.
  84 <<wcstoll_l>> is a GNU extension.
  85
  86 No supporting OS subroutines are required.
  87 */
  88
  89 /*-
  90  * Copyright (c) 1990 The Regents of the University of California.
  91  * All rights reserved.
  92  *
  93  * Redistribution and use in source and binary forms, with or without
  94  * modification, are permitted provided that the following conditions
  95  * are met:
  96  * 1. Redistributions of source code must retain the above copyright
  97  *    notice, this list of conditions and the following disclaimer.
  98  * 2. Redistributions in binary form must reproduce the above copyright
  99  *    notice, this list of conditions and the following disclaimer in the
 100  *    documentation and/or other materials provided with the distribution.
 101  * 3. Neither the name of the University nor the names of its contributors
 102  *    may be used to endorse or promote products derived from this software
 103  *    without specific prior written permission.
 104  *
 105  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 106  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 107  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 108  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 109  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 110  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 111  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 112  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 113  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 114  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 115  * SUCH DAMAGE.
 116  */
 117
 118 #define _GNU_SOURCE
 119 #include <_ansi.h>
 120 #include <limits.h>
 121 #include <wctype.h>
 122 #include <errno.h>
 123 #include <wchar.h>
 124 #include <reent.h>
 125 #include "../locale/setlocale.h"
 126
 127 /*
 128  * Convert a wide string to a long long integer.
 129  */
 130 long long
 131 _wcstoll_l (struct _reent *rptr, const wchar_t *nptr, wchar_t **endptr,
 132             int base, locale_t loc)
 133 {
 134         register const wchar_t *s = nptr;
 135         register unsigned long long acc;
 136         register int c;
 137         register unsigned long long cutoff;
 138         register int neg = 0, any, cutlim;
 139
 140         /*
 141          * Skip white space and pick up leading +/- sign if any.
 142          * If base is 0, allow 0x for hex and 0 for octal, else
 143          * assume decimal; if base is already 16, allow 0x.
 144          */
 145         do {
 146                 c = *s++;
 147         } while (iswspace_l(c, loc));
 148         if (c == L'-') {
 149                 neg = 1;
 150                 c = *s++;
 151         } else if (c == L'+')
 152                 c = *s++;
 153         if ((base == 0 || base == 16) &&
 154             c == L'0' && (*s == L'x' || *s == L'X')) {
 155                 c = s[1];
 156                 s += 2;
 157                 base = 16;
 158         }
 159         if (base == 0)
 160                 base = c == L'0' ? 8 : 10;
 161
 162         /*
 163          * Compute the cutoff value between legal numbers and illegal
 164          * numbers.  That is the largest legal value, divided by the
 165          * base.  An input number that is greater than this value, if
 166          * followed by a legal input character, is too big.  One that
 167          * is equal to this value may be valid or not; the limit
 168          * between valid and invalid numbers is then based on the last
 169          * digit.  For instance, if the range for longs is
 170          * [-2147483648..2147483647] and the input base is 10,
 171          * cutoff will be set to 214748364 and cutlim to either
 172          * 7 (neg==0) or 8 (neg==1), meaning that if we have accumulated
 173          * a value > 214748364, or equal but the next digit is > 7 (or 8),
 174          * the number is too big, and we will return a range error.
 175          *
 176          * Set any if any `digits' consumed; make it negative to indicate
 177          * overflow.
 178          */
 179         cutoff = neg ? -(unsigned long long)LONG_LONG_MIN : LONG_LONG_MAX;
 180         cutlim = cutoff % (unsigned long long)base;
 181         cutoff /= (unsigned long long)base;
 182         for (acc = 0, any = 0;; c = *s++) {
 183                 if (c >= L'0' && c <= L'9')
 184                         c -= L'0';
 185                 else if (c >= L'A' && c <= L'Z')
 186                         c -= L'A' - 10;
 187                 else if (c >= L'a' && c <= L'z')
 188                         c -= L'a' - 10;
 189                 else
 190                         break;
 191                 if (c >= base)
 192                         break;
 193                if (any < 0 || acc > cutoff || (acc == cutoff && c > cutlim))
 194                         any = -1;
 195                 else {
 196                         any = 1;
 197                         acc *= base;
 198                         acc += c;
 199                 }
 200         }
 201         if (any < 0) {
 202                 acc = neg ? LONG_LONG_MIN : LONG_LONG_MAX;
 203                 _REENT_ERRNO(rptr) = ERANGE;
 204         } else if (neg)
 205                 acc = -acc;
 206         if (endptr != 0)
 207                 *endptr = (wchar_t *) (any ? s - 1 : nptr);
 208         return (acc);
 209 }
 210
 211 long long
 212 _wcstoll_r (struct _reent *rptr,
 213         const wchar_t *nptr,
 214         wchar_t **endptr,
 215         int base)
 216 {
 217         return _wcstoll_l (rptr, nptr, endptr, base, __get_current_locale ());
 218 }
 219
 220 #ifndef _REENT_ONLY
 221
 222 long long
 223 wcstoll_l (const wchar_t *__restrict s, wchar_t **__restrict ptr, int base,
 224            locale_t loc)
 225 {
 226         return _wcstoll_l (_REENT, s, ptr, base, loc);
 227 }
 228
 229 long long
 230 wcstoll (const wchar_t *__restrict s,
 231         wchar_t **__restrict ptr,
 232         int base)
 233 {
 234         return _wcstoll_l (_REENT, s, ptr, base, __get_current_locale ());
 235 }
 236
 237 #endif