Question

我一直在尝试根据当前区域设置检测某个wchar_t是否被视为数字。

首先，我尝试使用iswdigit，但之后我意识到它只返回1 0-9，因此它根本不是区域设置敏感的。

然后我尝试了iswalnum(c) && !isalpha(c)：

#include <locale.h>
#include <wchar.h>
#include <wctype.h>
#include <stdio.h>

int main() {
    wchar_t c = L'٠'; // U0660: Arabic-Indic Digit 0
    int len;
    setlocale(LC_ALL, "");
    printf("%d\n", iswalnum(c) && !iswalpha(c)); // Prints 1.
    return 0;
}

据推测，如果角色通过了字母或数字测试而不是数字测试，那么这只会是1。唯一的问题是，iswalpha(c)出于某种神秘的原因返回1。

这引出了我的问题：有没有办法在没有外部库的情况下使用标准C或POSIX来检查字符是否是区域设置敏感方式的数字？或者我只是搞砸了？

Answer 1

无论语言环境如何，C语言允许在\n类中使用的唯一字符是字符\n\r，digit，'0'，... {{ 1}}包含值'1'，'2'，'9'，...，'0'+0。如果您需要更高级别的语义信息，关于人类使用与区域设置匹配的文化约定可能被解释为数字或其他数字形式，您需要更高级别的语义库。

至于'0'+1为什么不起作用，'0'+2类被定义为'0'+9和iswalnum(c) && !iswalpha(c)的联合。现有的区域设置作者实践放置＆＃34;数字＆＃34;除alnum类中的标准十进制数以外，仅仅是因为它是最不惊讶的路径，至少alpha是有意义的。

Answer 2

正如R ..已经写过，没有内置解决方案，但我记得几年前我用JavaScript做过。对C的粗略一对一翻译：

#include <ctype.h>
#include <wchar.h>
// checks if it is a character resembling a digit
// between 0 (zero) and 9 (nine).
// Numbers (http://www.fileformat.info/info/unicode/category/No/list.htm)
// are not included.
// Restriction to 16-bit is arbitrary, no digits above at time of writing
// with a range of 0-9 (except e.g.: digits with a full stop or a comma following)
int is_utf16_digit(wchar_t w)
{
  // a small shortcut
  if (isdigit((int)w)) {
    return 1;
  }
  // a bit of range sectioning for legibility
  if (w <= 0x9ef) {
    if (   (w >= 0x0660 && w <= 0x0669)
        || (w >= 0x06f0 && w <= 0x06f9) // EXTENDED ARABIC-INDIC DIGITs
        || (w >= 0x0966 && w <= 0x096f) // DEVANAGARI DIGITs
        || (w >= 0x09e6 && w <= 0x09ef) // BENGALI DIGITs
       ) {
      return 1;
    } else {
      return 0;
    }
  } else if (w > 0x9ef && w <= 0xc6f) {
    if (   (w >= 0x0a66 && w <= 0x0a6f) // GURMUKHI DIGITs
        || (w >= 0x0ae6 && w <= 0x0aef) // GUJARATI DIGITs
        || (w >= 0x0b66 && w <= 0x0b6f) // ORIYA DIGITs
        || (w >= 0x0be7 && w <= 0x0bef) // TAMIL DIGITs
        || (w >= 0x0c66 && w <= 0x0c6f) // TELUGU DIGITs
       ) {
      return 1;
    } else {
      return 0;
    }
  } else if (w > 0xc6f && w <= 0xf29) {
    if (   (w >= 0x0ce6 && w <= 0x0cef) // KANNADA DIGITs
        || (w >= 0x0d66 && w <= 0x0d6f) // MALAYALAM DIGITs
        || (w >= 0x0e50 && w <= 0x0e59) // THAI DIGITs
        || (w >= 0x0ed0 && w <= 0x0ed9) // LAO DIGITs
        || (w >= 0x0f20 && w <= 0x0f29) // TIBETAN DIGITs
       ) {
      return 1;
    } else {
      return 0;
    }
  } else if (w > 0xf29 && w <= 0xff19) {
    if (   (w >= 0x1040 && w <= 0x1049) // MYANMAR DIGITs
        || (w >= 0x1369 && w <= 0x1371) // ETHIOPIC DIGITs
        || (w >= 0x17e0 && w <= 0x17e9) // KHMER DIGITs
        || (w >= 0x1810 && w <= 0x1819) // MONGOLIAN DIGITs
/*
  0x2460 - 0x2468 CIRCLED DIGITs 1-9
  0x24ea          CIRCLED DIGITs 0
  0x2474 - 0x247c PARENTHESIZED DIGITs 1-9
  0x2488 - 0x2490 DIGITs 1-9 FULL STOP
  0x24f5 - 0x24fd DOUBLE CIRCLED DIGIT 1-9
  and so on and so forth
*/
        || (w >= 0xff10 && w <= 0xff19) // FULLWIDTH DIGITs (meh?)
/*
  First characters larger than 16 bits:
  (0x10107 - 0x1010f AEGEAN NUMBERs 1-9)
  0x102e1 - 0x102e9 COPTIC EPACT DIGITs 1-9
  0x10a40 - 0x10a43 KHAROSHTHI DIGITs 1-4
  0x10e60 - 0x10e68 RUMI DIGITs 1-9
  Interestingly, the zero for DIGITs 1-9 FULL STOP is at 0x1f100.
  Forgotten by the committee?
  First consecutive digits are the digits with a comma:
  0x1f101 - 0x1f10a
*/
       ) {
      return 1;
    } else {
      return 0;
    }
  } else {
    return 0;
  }
}

#include <stdio.h>
#include <stdlib.h>
#include <locale.h>
#include <string.h>   
int main(int argc, char **argv)
{
  wchar_t *w;

  size_t slen, wlen;

  if (argc != 2) {
    fprintf(stderr, "Usage: %s string\n", argv[0]);
    exit(EXIT_FAILURE);
  }

  setlocale(LC_ALL, "");

  slen = strlen(argv[1]);
  w = malloc(slen * (sizeof(wchar_t) + 1));
  if (w == NULL) {
    fprintf(stderr, "malloc() failed to allocate %zu bytes\n", slen);
    exit(EXIT_FAILURE);
  }

  wlen = mbstowcs(w, argv[1], slen);
  if (wlen == (size_t) - 1) {
    fprintf(stderr, "mbstowcs() failed\n");
    exit(EXIT_FAILURE);
  }
  // adjusting memory size with a round of realloc() ommited

  while (*w != L'\0') {
    if (is_utf16_digit(*w)) {
      printf("\"%lc\" (0x%04x) is a digit\n", *w, *w);
    } else {
      printf("\"%lc\" (0x%04x) is not a digit\n", *w, *w);
    }
    w++;
  }
  exit(EXIT_SUCCESS);
}

一些字符表示来自不同语言的数字零的示例

$ ./isutf16digit "asd0asd٠asd೯asd０asd"
"a" (0x0061) is not a digit
"s" (0x0073) is not a digit
"d" (0x0064) is not a digit
"0" (0x0030) is a digit
"a" (0x0061) is not a digit
"s" (0x0073) is not a digit
"d" (0x0064) is not a digit
"٠" (0x0660) is a digit
"a" (0x0061) is not a digit
"s" (0x0073) is not a digit
"d" (0x0064) is not a digit
"೯" (0x0cef) is a digit
"a" (0x0061) is not a digit
"s" (0x0073) is not a digit
"d" (0x0064) is not a digit
"０" (0xff10) is a digit
"a" (0x0061) is not a digit
"s" (0x0073) is not a digit
"d" (0x0064) is not a digit

与iswalpha()一起应该这样做但是因为Unicode和标准C总是如此，没有专门的lib：它是可行的，但它是令人讨厌的。例如，见上文：测试代码非常复杂，它甚至可以保持很简单。

在C中检测区域设置敏感数字

2 个答案: