Luna/libluna/src/NumberParsing.cpp

#include <limits.h>
#include <luna/CType.h>
#include <luna/NumberParsing.h>

// This function assumes you have called is_valid_digit_for_base() to validate the digit first.
static isize parse_digit_unchecked(char c)
{
    if (_isdigit(c)) return c - '0';
    if (_islower(c)) return (c - 'a') + 10;
    return (c - 'A') + 10;
}

static bool is_valid_digit_for_base(int base, char c)
{
    if (!_isalnum(c)) return false;
    if (parse_digit_unchecked(c) >= (isize)base) return false;
    return true;
}

static usize do_unsigned_parse(const char* str, const char** endptr, int base)
{
    usize val = 0;

    // 1. If base is zero or 16, the string may then include a "0x" prefix, and the number will be read in base 16;
    // otherwise, a zero base is taken as 10 (decimal) unless the next character is '0', in which case it is taken as
    // 8 (octal).
    if ((base == 0 || base == 16) && *str == '0')
    {
        str++;
        if (_tolower(*str) == 'x')
        {
            base = 16;
            str++;
        }
        else if (base == 0)
            base = 8;
    }
    else if (base == 0)
        base = 10;

    // 2. The remainder of the string is converted to an unsigned long value in
    // the obvious manner, stopping at the first character which is not a
    // valid digit in the given base.
    while (is_valid_digit_for_base(base, *str))
    {
        val = ((usize)base * val) + (usize)parse_digit_unchecked(*str);
        str++;
    }

    // 3. If endptr is not NULL, this function stores the address of the first invalid character in *endptr.
    if (endptr) *endptr = str;

    return val;
}

usize parse_unsigned_integer(const char* str, const char** endptr, int base)
{
    // The string may begin with an arbitrary amount of white space (as determined by isspace(3)),
    while (_isspace(*str)) str++;

    // followed by a single optional '+' or '-' sign.
    if (*str == '-' || *str == '+') str++;

    return do_unsigned_parse(str, endptr, base);
}

#define SSIZE_MAX LONG_MAX
#define SSIZE_MIN (-SSIZE_MAX - (isize)1)

isize parse_signed_integer(const char* str, const char** endptr, int base)
{
    bool negative = false;

    // The string may begin with an arbitrary amount of white space (as determined by isspace(3)),
    while (_isspace(*str)) str++;

    // followed by a single optional '+' or '-' sign.
    if (*str == '-' || *str == '+')
    {
        if (*str == '-') negative = true;
        str++;
    }

    usize rc = do_unsigned_parse(str, endptr, base);

    // If an underflow occurs, this function returns SSIZE_MIN. If an overflow occurs, this function returns SSIZE_MAX.
    if (rc > SSIZE_MAX) { return negative ? SSIZE_MIN : SSIZE_MAX; }

    return negative ? -(isize)rc : (isize)rc;
}

usize scan_unsigned_integer(const char** str, int base)
{
    return parse_unsigned_integer(*str, str, base);
}

isize scan_signed_integer(const char** str, int base)
{
    return parse_signed_integer(*str, str, base);
}