How to get ASCII code of C `char` portably in ANSI C

Question

As you all know, ANSI C does not require implementations to use ASCII code points for the char type. However it does define a basic character set with alphanumeric characters, whitespace characters and other printable characters. Are there library functions to portably convert a char to its ASCII code and back?

Answer 1

Here are some functions to do the job, which return 0 if the character is not found; hopefully they are self-explanatory:

char const ascii_table[] = " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~";

int char_to_ascii(int ch)
{
    char const *p = strchr(ascii_table, ch);
    return p ? p - ascii_table + 32 : 0;
}

int ascii_to_char(int a)
{
     return (a >= 32 && a < 128) ? ascii_table[a-32] : 0;
}

Expanding this to cover 0-127 instead of 32-127 is left as an exercise to the reader

Answer 2

Are there library functions to portably convert a char to its ASCII code and back?

There are no such functions in the standard library.

Hovewer, let's be realistic: It's very unlikely that your code will ever be used on a platform that doesn't use ASCII.

I would do this:

char char_to_ascii(char ch)
{
    return ch;
}

char ascii_to_char(char ch)
{
    return ch;
}

And then, if you need to compile the code for an exotic platform that doesn't use ASCII, you write proper implementations for those functions.

Answer 3

There are no ANSI C library functions that can do this.

However, I recently created an ASCII table that does exactly this. It maps most of the characters (including escape codes) available in ANSI C, and also escape ( '\e' , available in GNU C). The rest are mapped to zero:

unsigned int othertoascii[UINT_MAX+1] = {
  ['\a'] = 0x07, ['\b'] = 0x08, ['\t'] = 0x09,
  ['\n'] = 0x0a, ['\v'] = 0x0b, ['\f'] = 0x0c,
  ['\r'] = 0x0d, ['\e'] = 0x1b, [' ']  = 0x20,
  ['!']  = 0x21, ['"']  = 0x22, ['#']  = 0x23,
  ['$']  = 0x24, ['%']  = 0x25, ['&']  = 0x26,
  ['\''] = 0x27, ['(']  = 0x28, [')']  = 0x29,
  ['*']  = 0x2a, ['+']  = 0x2b, [',']  = 0x2c,
  ['-']  = 0x2d, ['.']  = 0x2e, ['/']  = 0x2f,
  ['0']  = 0x30, ['1']  = 0x31, ['2']  = 0x32,
  ['3']  = 0x33, ['4']  = 0x34, ['5']  = 0x35,
  ['6']  = 0x36, ['7']  = 0x37, ['8']  = 0x38,
  ['9']  = 0x39, [':']  = 0x3a, [';']  = 0x3b,
  ['<']  = 0x3c, ['=']  = 0x3d, ['>']  = 0x3e,
  ['?']  = 0x3f, ['@']  = 0x40, ['A']  = 0x41,
  ['B']  = 0x42, ['C']  = 0x43, ['D']  = 0x44,
  ['E']  = 0x45, ['F']  = 0x46, ['G']  = 0x47,
  ['H']  = 0x48, ['I']  = 0x49, ['J']  = 0x4a,
  ['K']  = 0x4b, ['L']  = 0x4c, ['M']  = 0x4d,
  ['N']  = 0x4e, ['O']  = 0x4f, ['P']  = 0x50,
  ['Q']  = 0x51, ['R']  = 0x52, ['S']  = 0x53,
  ['T']  = 0x54, ['U']  = 0x55, ['V']  = 0x56,
  ['W']  = 0x57, ['X']  = 0x58, ['Y']  = 0x59,
  ['Z']  = 0x5a, ['[']  = 0x5b, ['\\'] = 0x5c,
  [']']  = 0x5d, ['^']  = 0x5e, ['_']  = 0x5f,
  ['`']  = 0x60, ['a']  = 0x61, ['b']  = 0x62,
  ['c']  = 0x63, ['d']  = 0x64, ['e']  = 0x65,
  ['f']  = 0x66, ['g']  = 0x67, ['h']  = 0x68,
  ['i']  = 0x69, ['j']  = 0x6a, ['k']  = 0x6b,
  ['l']  = 0x6c, ['m']  = 0x6d, ['n']  = 0x6e,
  ['o']  = 0x6f, ['p']  = 0x70, ['q']  = 0x71,
  ['r']  = 0x72, ['s']  = 0x73, ['t']  = 0x74,
  ['u']  = 0x75, ['v']  = 0x76, ['w']  = 0x77,
  ['x']  = 0x78, ['y']  = 0x79, ['z']  = 0x7a,
  ['{']  = 0x7b, ['|']  = 0x7c, ['}']  = 0x7d,
  ['~']  = 0x7e
};

unsigned int asciitoother[UINT_MAX+1] = {
  [0x07] = '\a', [0x08] = '\b', [0x09] = '\t',
  [0x0a] = '\n', [0x0b] = '\v', [0x0c] = '\f',
  [0x0d] = '\r', [0x1b] = '\e', [0x20] =  ' ',
  [0x21] =  '!', [0x22] =  '"', [0x23] =  '#',
  [0x24] =  '$', [0x25] =  '%', [0x26] =  '&',
  [0x27] = '\'', [0x28] =  '(', [0x29] =  ')',
  [0x2a] =  '*', [0x2b] =  '+', [0x2c] =  ',',
  [0x2d] =  '-', [0x2e] =  '.', [0x2f] =  '/',
  [0x30] =  '0', [0x31] =  '1', [0x32] =  '2',
  [0x33] =  '3', [0x34] =  '4', [0x35] =  '5',
  [0x36] =  '6', [0x37] =  '7', [0x38] =  '8',
  [0x39] =  '9', [0x3a] =  ':', [0x3b] =  ';',
  [0x3c] =  '<', [0x3d] =  '=', [0x3e] =  '>',
  [0x3f] =  '?', [0x40] =  '@', [0x41] =  'A',
  [0x42] =  'B', [0x43] =  'C', [0x44] =  'D',
  [0x45] =  'E', [0x46] =  'F', [0x47] =  'G',
  [0x48] =  'H', [0x49] =  'I', [0x4a] =  'J',
  [0x4b] =  'K', [0x4c] =  'L', [0x4d] =  'M',
  [0x4e] =  'N', [0x4f] =  'O', [0x50] =  'P',
  [0x51] =  'Q', [0x52] =  'R', [0x53] =  'S',
  [0x54] =  'T', [0x55] =  'U', [0x56] =  'V',
  [0x57] =  'W', [0x58] =  'X', [0x59] =  'Y',
  [0x5a] =  'Z', [0x5b] =  '[', [0x5c] = '\\',
  [0x5d] =  ']', [0x5e] =  '^', [0x5f] =  '_',
  [0x60] =  '`', [0x61] =  'a', [0x62] =  'b',
  [0x63] =  'c', [0x64] =  'd', [0x65] =  'e',
  [0x66] =  'f', [0x67] =  'g', [0x68] =  'h',
  [0x69] =  'i', [0x6a] =  'j', [0x6b] =  'k',
  [0x6c] =  'l', [0x6d] =  'm', [0x6e] =  'n',
  [0x6f] =  'o', [0x70] =  'p', [0x71] =  'q',
  [0x72] =  'r', [0x73] =  's', [0x74] =  't',
  [0x75] =  'u', [0x76] =  'v', [0x77] =  'w',
  [0x78] =  'x', [0x79] =  'y', [0x7a] =  'z',
  [0x7b] =  '{', [0x7c] =  '|', [0x7d] =  '}',
  [0x7e] =  '~'
};

Here's an example program that uses this:

#include <stdio.h>

int main(void)
{
    unsigned char c = othertoascii['0'];
    c += 5;
    c = asciitoother[c];
    putchar(c);
    return 0;
}