convert any base to base 10 in C++ - c++

I have this code:
#include <stdio.h>
#include <ctype.h>
int validnumber(int b, char* p);
unsigned long base2dec(int b,char *p);
void dec2base (int b,unsigned long x);
char *number;
main() {
int base,temp=0,count;
unsigned long Decimal_number;
do {
printf ("Give the base of the number you want to tranform:");
scanf ("%d", &base);
if (base<2 || base>16)
printf("Not acceptable base number, numbers should be in range from 2 to 16\n\n");
} while (base<2 || base>16);
printf ("Give the number you want to tranform:");
scanf("%s", number);
for (count=0;count<32;count++) {
number [count]= toupper(number[count]);
}
temp=validnumber(base, number);
if (temp==0)
printf ("O arithmpos pou eisagatai periexei MH egkira symbola\n");
else
if (temp==1)
printf ("O arithmpos pou eisagatai periexei egkira symbola\n");
if (temp==1) {
Decimal_number = base2dec( base , number);
}
int validnumber(int b, char *p){
int count, a[32];
for (count=0;count<32;count++)
a[count]=p[count];
if (b>=2 && b<=10) {
for (count=0;count<32;count++) {
if (a[count]<48 || a[count]>48+b)
return 0;
break;
}
}
if (b>=11 && b<=16) {
for (count=0;count<32;count++) {
if ((a[count]>=48 && a[count]<=57) || (a[count]>=65 && a[count]<=70)) {
return 1;
}
}
}
}
From this point the main program must call the function:
unsigned long base2dec (int b, char * p)
which accepts as arguments the base b and a pointer p in character table that
corresponds to the imported string s and returns the number representing the s expressed in the decimal system.
Also, it should call the function:
void dec2base (int b, unsigned long x)
which accepts as arguments the base b and the value of the number x in the decimal system and displays the base value and the representation of the number x in this base. The main program calls this function for all of the base values from 2 to 16.
Are there any ideas on how to begin? Any guidance will be appreciated.

In your base2dec, you will simply call this method and pass in 'b' as it is and x which should be the converted string.
Here is an implementation of dec2base. It is implemented recursively.
void dec2base(int b, unsigned long x){
if (x == 0)
return;
int y = x % b;
x /= b;
if (y < 0)
x += 1;
dec2base(b, x);
//converted digits to hex after realizing this solution doesn't work
//for bases greater than 10. Credits to Trevor pointing this out.
cout<< hex << y < 0 ? y + (b * -1) : y;
return;
}

First of all please have a look at your formatting because the way your code is written makes it harder than it needs to be to follow.
Here is what I would do:
#include <stdexcept>
#include <iostream>
void dec2base(int b, long x)
{
// Quick check for zero
if (x == 0)
{
std::cout << '0';
return;
}
// Print the negative sign if present, also negate
if (x < 0)
{
std::cout << '-';
x = -x;
}
char buf[12];
int i = 0;
// Convert to a backwards BCD
do {
buf[i++] = static_cast<char>(x % b);
} while (x /= b);
// Print it starting from the last digit (really the first)
do {
if (buf[--i] <= 9) std::cout << static_cast<char>(buf[i] + '0');
else std::cout << static_cast<char>(buf[i] + ('a' - 10));
} while (i);
}
long base2dec(int b, char * p)
{
long digit; // Current digit
long mul = 1; // Current multiplier
char *pos = p; // Current position
bool neg = false; // Sign
long ret = 0; // The return value
// Find the last digit
while (*pos) pos++;
// Continue until the start of the string is reached
while (pos-- != p)
{
if (*pos < '0')
{
if (*pos == '-')
{
// Sign reached, save it an break out
neg = true;
break;
}
else // Shouldn't happen
{
throw std::invalid_argument("Not a number");
}
}
if (*pos > 'f')
throw std::invalid_argument("Not a number");
// Get a digit
if (*pos <= '9') digit = *pos - '0';
else if (*pos >= 'a') digit = *pos - ('a' - 10);
else if (*pos >= 'A' && *pos <= 'F')
digit = *pos - ('A' - 10);
else
throw std::invalid_argument("Not a number");
// Make sure it is not larger than or equal to the base
if (digit >= b)
throw std::invalid_argument("Not a number");
// Add the digit
ret += digit * mul;
// Increase the multiplier
mul *= b;
}
return neg ? -ret : ret;
}
int main()
{
long val = base2dec(16, "123f");
dec2base(16, val);
return 0;
}
I realize you didn't ask for a signed version but as it is very easy to implement I have done it. If you really don't need to deal with signed values it is simple to drop the relevant parts from the functions.
This is a very quick and dirty go at this and this could no doubt be improved both for readability and performance but is, I think, a good starting point.
Here is a slightly improved version of base2dec():
long base2dec(int b, char * p)
{
long digit; // Current digit
bool neg = false; // Sign
long ret = 0; // The return value
// Check for negative number
if (*p == '-')
{
neg = true;
p++;
}
// Continue until the end of the string is reached
for (; *p != 0; p++)
{
// Rough range check
if (*p < '0' || *p > 'f')
throw std::invalid_argument("Not a number");
// Get a digit
if (*p <= '9') digit = *p - '0';
else if (*p >= 'a') digit = *p - ('a' - 10);
else if (*p >= 'A' && *p <= 'F')
digit = *p - ('A' - 10);
else
throw std::invalid_argument("Not a number");
// Make sure it is not larger than or equal to the base
if (digit >= b)
throw std::invalid_argument("Not a number");
// Add the digit
ret = ret * b + digit;
}
return neg ? -ret : ret;
}
Regarding the validnumber() function. This check is best performed during the conversion both to avoid having to read the entire string twice and because base2dec() really ought to check for valid input anyway. If you still need a separate check then you need to fix validnumber(). There is no need to copy the string to an array and it is also better to use the same code for all bases. Here is a suggestion:
bool validnumber(int b, char *p)
{
// Check for valid base
if (b < 2 || b > 16) return false;
// Extract numeric and alpha parts of the base
int b_numeric = b <= 10 ? b : 10;
int b_alpha = b - 11;
// Ignore any sign
if (*p == '-') p++;
// Continue until the end of the string
for (; *p != 0; p++)
{
// Digits < 0 are always bad
if (*p < '0') return false;
// Check for valid numeric digits
if (*p > ('0' + b_numeric))
{
// Check for valid alpha digits
if (b <= 10) return false;
if (*p < 'A' || *p > ('a' + b_alpha)) return false;
if (*p > ('A' + b_alpha) && *p < 'a') return false;
}
}
return true;
}

Related

atoi() for int128_t type

How can I use argv values with int128_t support? I know about atoi() and family of functions exposed by <cstdlib> but somehow I cannot find one for int128_t fixed width integer. This might be because of the fact that this type isn't backed by either c or c++ standard, but is there any way for me to make this code work?
#include <iostream>
int main(int argc, char **argv) {
__int128_t value = atoint128_t(argv[1]);
}
Almost all answers posted are good enough for me but I'm selecting the one that is a drop by solution for my current code, so do look at other ones too.
Here's a simple way of implementing this:
__int128_t atoint128_t(const char *s)
{
const char *p = s;
__int128_t val = 0;
if (*p == '-' || *p == '+') {
p++;
}
while (*p >= '0' && *p <= '9') {
val = (10 * val) + (*p - '0');
p++;
}
if (*s == '-') val = val * -1;
return val;
}
This code checks each character to see if it's a digit (with an optional leading + or -), and if so it multiplies the current result by 10 and adds the value associated with that digit. It then inverts the sign if need be.
Note that this implementation does not check for overflow, which is consistent with the behavior of atoi.
EDIT:
Revised implementation that covers int128_MIN case by either adding or subtracting the value of each digit based on the sign, and skipping leading whitespace.
int myatoi(const char *s)
{
const char *p = s;
int neg = 0, val = 0;
while ((*p == '\n') || (*p == '\t') || (*p == ' ') ||
(*p == '\f') || (*p == '\r') || (*p == '\v')) {
p++;
}
if ((*p == '-') || (*p == '+')) {
if (*p == '-') {
neg = 1;
}
p++;
}
while (*p >= '0' && *p <= '9') {
if (neg) {
val = (10 * val) - (*p - '0');
} else {
val = (10 * val) + (*p - '0');
}
p++;
}
return val;
}
Here is a C++ implementation:
#include <string>
#include <stdexcept>
__int128_t atoint128_t(std::string const & in)
{
__int128_t res = 0;
size_t i = 0;
bool sign = false;
if (in[i] == '-')
{
++i;
sign = true;
}
if (in[i] == '+')
{
++i;
}
for (; i < in.size(); ++i)
{
const char c = in[i];
if (not std::isdigit(c))
throw std::runtime_error(std::string("Non-numeric character: ") + c)
res *= 10;
res += c - '0';
}
if (sign)
{
res *= -1;
}
return res;
}
int main()
{
__int128_t a = atoint128_t("170141183460469231731687303715884105727");
}
If you want to test it then there is a stream operator here.
Performance
I ran a few performance test. I generate 100,000 random numbers uniformly distributed in the entire support of __int128_t. Then I converted each of them 2000 times. All of these (200,000,000) conversions where completed within ~12 seconds.
Using this code:
#include <iostream>
#include <string>
#include <random>
#include <vector>
#include <chrono>
int main()
{
std::mt19937 gen(0);
std::uniform_int_distribution<> num(0, 9);
std::uniform_int_distribution<> len(1, 38);
std::uniform_int_distribution<> sign(0, 1);
std::vector<std::string> str;
for (int i = 0; i < 100000; ++i)
{
std::string s;
int l = len(gen);
if (sign(gen))
s += '-';
for (int u = 0; u < l; ++u)
s += std::to_string(num(gen));
str.emplace_back(s);
}
namespace sc = std::chrono;
auto start = sc::duration_cast<sc::microseconds>(sc::high_resolution_clock::now().time_since_epoch()).count();
__int128_t b = 0;
for (int u = 0; u < 200; ++u)
{
for (int i = 0; i < str.size(); ++i)
{
__int128_t a = atoint128_t(str[i]);
b += a;
}
}
auto time = sc::duration_cast<sc::microseconds>(sc::high_resolution_clock::now().time_since_epoch()).count() - start;
std::cout << time / 1000000. << 's' << std::endl;
}
Adding here a "not-so-naive" implementation in pure C, it's still kind of simple:
#include <stdio.h>
#include <inttypes.h>
__int128 atoi128(const char *s)
{
while (*s == ' ' || *s == '\t' || *s == '\n' || *s == '+') ++s;
int sign = 1;
if (*s == '-')
{
++s;
sign = -1;
}
size_t digits = 0;
while (s[digits] >= '0' && s[digits] <= '9') ++digits;
char scratch[digits];
for (size_t i = 0; i < digits; ++i) scratch[i] = s[i] - '0';
size_t scanstart = 0;
__int128 result = 0;
__int128 mask = 1;
while (scanstart < digits)
{
if (scratch[digits-1] & 1) result |= mask;
mask <<= 1;
for (size_t i = digits-1; i > scanstart; --i)
{
scratch[i] >>= 1;
if (scratch[i-1] & 1) scratch[i] |= 8;
}
scratch[scanstart] >>= 1;
while (scanstart < digits && !scratch[scanstart]) ++scanstart;
for (size_t i = scanstart; i < digits; ++i)
{
if (scratch[i] > 7) scratch[i] -= 3;
}
}
return result * sign;
}
int main(int argc, char **argv)
{
if (argc > 1)
{
__int128 x = atoi128(argv[1]);
printf("%" PRIi64 "\n", (int64_t)x); // just for demo with smaller numbers
}
}
It reads the number bit by bit, using a shifted BCD scratch space, see Double dabble for the algorithm (it's reversed here). This is a lot more efficient than doing many multiplications by 10 in general. *)
This relies on VLAs, without them, you can replace
char scratch[digits];
with
char *scratch = malloc(digits);
if (!scratch) return 0;
and add a
free(scratch);
at the end of the function.
Of course, the code above has the same limitations as the original atoi() (e.g. it will produce "random" garbage on overflow and has no way to check for that) .. if you need strtol()-style guarantees and error checking, extend it yourself (not a big problem, just work to do).
*) Of course, implementing double dabble in C always suffers from the fact you can't use "hardware carries", so there are extra bit masking and testing operations necessary. On the other hand, "naively" multiplying by 10 can be very efficient, as long as the platform provides multiplication instructions with a width "close" to your target type. Therefore, on your typical x86_64 platform (which has instructions for multiplying 64bit integers), this code is probably a lot slower than the naive decimal method. But it scales much better to really huge integers (which you would implement e.g. using arrays of uintmax_t).
is there any way for me to make this code work?
"What about implementing your own atoint128_t ?" #Marian
It is not to hard to roll your own atoint128_t().
Points to consider.
There is 0 or 1 more representable negative value than positive values. Accumulating the value using negative numbers provides more range.
Overflow is not defined for atoi(). Perhaps provide a capped value and set errno? Detecting potential OF prevents UB.
__int128_t constants need careful code to form correctly.
How to handle unusual input? atoi() is fairly loose and made sense years ago for speed/size, yet less UB is usually desired these days. Candidate cases: "", " ", "-", "z", "+123", "999..many...999", "the min int128", "locale_specific_space" + " 123" or even non-string NULL.
Code to do atoi() and atoint128_t() need only vary on the type, range, and names. The algorithm is the same.
#if 1
#define int_t __int128_t
#define int_MAX (((__int128_t)0x7FFFFFFFFFFFFFFF << 64) + 0xFFFFFFFFFFFFFFFF)
#define int_MIN (-1 - int_MAX)
#define int_atoi atoint128_t
#else
#define int_t int
#define int_MAX INT_MAX
#define int_MIN INT_MIN
#define int_atoi int_atoi
#endif
Sample code: Tailor as needed. Relies on C99 or later negative/positive and % functionality.
int_t int_atoi(const char *s) {
if (s == NULL) { // could omit this test
errno = EINVAL;
return 0;
}
while (isspace((unsigned char ) *s)) { // skip same leading white space like atoi()
s++;
}
char sign = *s; // remember if the sign was `-` for later
if (sign == '-' || sign == '+') {
s++;
}
int_t sum = 0;
while (isdigit((unsigned char)*s)) {
int digit = *s - '0';
if ((sum > int_MIN/10) || (sum == int_MIN/10 && digit <= -(int_MIN%10))) {
sum = sum * 10 - digit; // accumulate on the - side
} else {
sum = int_MIN;
errno = ERANGE;
break; // overflow
}
s++;
}
if (sign != '-') {
if (sum < -int_MAX) {
sum = int_MAX;
errno = ERANGE;
} else {
sum = -sum; // Make positive
}
}
return sum;
}
As #Lundin commented about the lack of overflow detection, etc. Modeling the string-->int128 after strtol() is a better idea.
For simplicity, consider __128_t strto__128_base10(const char *s, char *endptr);
This answer all ready handles overflow and flags errno like strtol(). Just need a few changes:
bool digit_found = false;
while (isdigit((unsigned char)*s)) {
digit_found = true;
// delete the `break`
// On overflow, continue looping to get to the end of the digits.
// break;
// after the `while()` loop:
if (!digit_found) { // optional test
errno = EINVAL;
}
if (endptr) {
*endptr = digit_found ? s : original_s;
}
A full long int strtol(const char *nptr, char **endptr, int base); like functionality would also handle other bases with special code when base is 0 or 16. #chqrlie
The C Standard does not mandate support for 128-bit integers.
Yet they are commonly supported by modern compilers: both gcc and clang support the types __int128_t and __uint128_t, but surprisingly still keep intmax_t and uintmax_t limited to 64 bits.
Beyond the basic arithmetic operators, there is not much support for these large integers, especially in the C library: no scanf() or printf() conversion specifiers, etc.
Here is an implementation of strtoi128(), strtou128() and atoi128() that is consistent with the C Standard's atoi(), strtol() and strtoul() specifications.
#include <ctype.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/* Change these typedefs for your local flavor of 128-bit integer types */
typedef __int128_t i128;
typedef __uint128_t u128;
static int strdigit__(char c) {
/* This is ASCII / UTF-8 specific, would not work for EBCDIC */
return (c >= '0' && c <= '9') ? c - '0'
: (c >= 'a' && c <= 'z') ? c - 'a' + 10
: (c >= 'A' && c <= 'Z') ? c - 'A' + 10
: 255;
}
static u128 strtou128__(const char *p, char **endp, int base) {
u128 v = 0;
int digit;
if (base == 0) { /* handle octal and hexadecimal syntax */
base = 10;
if (*p == '0') {
base = 8;
if ((p[1] == 'x' || p[1] == 'X') && strdigit__(p[2]) < 16) {
p += 2;
base = 16;
}
}
}
if (base < 2 || base > 36) {
errno = EINVAL;
} else
if ((digit = strdigit__(*p)) < base) {
v = digit;
/* convert to unsigned 128 bit with overflow control */
while ((digit = strdigit__(*++p)) < base) {
u128 v0 = v;
v = v * base + digit;
if (v < v0) {
v = ~(u128)0;
errno = ERANGE;
}
}
if (endp) {
*endp = (char *)p;
}
}
return v;
}
u128 strtou128(const char *p, char **endp, int base) {
if (endp) {
*endp = (char *)p;
}
while (isspace((unsigned char)*p)) {
p++;
}
if (*p == '-') {
p++;
return -strtou128__(p, endp, base);
} else {
if (*p == '+')
p++;
return strtou128__(p, endp, base);
}
}
i128 strtoi128(const char *p, char **endp, int base) {
u128 v;
if (endp) {
*endp = (char *)p;
}
while (isspace((unsigned char)*p)) {
p++;
}
if (*p == '-') {
p++;
v = strtou128__(p, endp, base);
if (v >= (u128)1 << 127) {
if (v > (u128)1 << 127)
errno = ERANGE;
return -(i128)(((u128)1 << 127) - 1) - 1;
}
return -(i128)v;
} else {
if (*p == '+')
p++;
v = strtou128__(p, endp, base);
if (v >= (u128)1 << 127) {
errno = ERANGE;
return (i128)(((u128)1 << 127) - 1);
}
return (i128)v;
}
}
i128 atoi128(const char *p) {
return strtoi128(p, (char**)NULL, 10);
}
char *utoa128(char *dest, u128 v, int base) {
char buf[129];
char *p = buf + 128;
const char *digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
*p = '\0';
if (base >= 2 && base <= 36) {
while (v > (unsigned)base - 1) {
*--p = digits[v % base];
v /= base;
}
*--p = digits[v];
}
return strcpy(dest, p);
}
char *itoa128(char *buf, i128 v, int base) {
char *p = buf;
u128 uv = (u128)v;
if (v < 0) {
*p++ = '-';
uv = -uv;
}
if (base == 10)
utoa128(p, uv, 10);
else
if (base == 16)
utoa128(p, uv, 16);
else
utoa128(p, uv, base);
return buf;
}
static char *perrno(char *buf, int err) {
switch (err) {
case EINVAL:
return strcpy(buf, "EINVAL");
case ERANGE:
return strcpy(buf, "ERANGE");
default:
sprintf(buf, "%d", err);
return buf;
}
}
int main(int argc, char *argv[]) {
char buf[130];
char xbuf[130];
char ebuf[20];
char *p1, *p2;
i128 v, v1;
u128 v2;
int i;
for (i = 1; i < argc; i++) {
printf("%s:\n", argv[i]);
errno = 0;
v = atoi128(argv[i]);
perrno(ebuf, errno);
printf(" atoi128(): %s 0x%s errno=%s\n",
itoa128(buf, v, 10), utoa128(xbuf, v, 16), ebuf);
errno = 0;
v1 = strtoi128(argv[i], &p1, 0);
perrno(ebuf, errno);
printf(" strtoi128(): %s 0x%s endptr:\"%s\" errno=%s\n",
itoa128(buf, v1, 10), utoa128(xbuf, v1, 16), p1, ebuf);
errno = 0;
v2 = strtou128(argv[i], &p2, 0);
perrno(ebuf, errno);
printf(" strtou128(): %s 0x%s endptr:\"%s\" errno=%s\n",
utoa128(buf, v2, 10), utoa128(xbuf, v2, 16), p2, ebuf);
}
return 0;
}

c++ Decimal to binary, then use operation, then back to decimal

I have an array with x numbers: sets[ ](long numbers) and a char array operations[ ] with x-1 numbers. For each number from sets[ ], its binary form(in 64bits) would be the same as a set of numbers( these numbers being from 0 to 63 ), 1's and 0's representing whether it is inside a subset or not ( 1 2 4 would be 1 1 0 1, since 3 is missing)
ex: decimal 5 --->000...00101 , meaning that this subset will only have those 2 last numbers inside it(#63 and #61)
now,using the chars i get in operations[], i should work with them and the binaries of these numbers as if they were operations on subsets(i hope subset is the right word), these operations being :
U = reunion ---> 101 U 010 = 111
A = intersection ---> 101 A 001 = 001
\ = A - B ---> 1110 - 0011 = 1100
/ = B-A ---> like the previous one
so basically I'd have to read numbers, make them binary, use them as if they were sets and use operations accordingly, then return the result of all these operations on them.
my code :
include <iostream>
using namespace std;
void makeBinaryVector(int vec[64], long xx)
{
// put xx in binary form in array "vec[]"
int k = 63;
long x = xx;
if(xx == 0)
for(int i=0;i<64;i++)
vec[i] = 0;
while(x != 0)
{
vec[k] = x % 2;
x = x / 2;
k--;
}
}
void OperationInA(int A[64], char op, int B[64])
{
int i;
if(op == 'U') //reunion
for(i=0;i<64;i++)
if(B[i] == 1)
A[i] = 1;
if(op == 'A') //intersection
for(i=0;i<64;i++)
{
if((B[i] == 1) && (A[i] == 1))
A[i] = 1;
else
A[i] = 0;
}
if(op == '\\') //A-B
for(i=0;i<64;i++)
{
if( (A[i] == 0 && B[i] == 0) || (A[i] == 0 && B[i] == 1) )
A[i] = 0;
else
if((A[i] == 1) && (B[i] == 1))
A[i] = 0;
else
if((A[i] == 1) && (B[i] == 0))
A[i] = 1;
}
if(op == '/') //B-A
for(i=0;i<64;i++)
{
if(B[i] == 0)
A[i] = 0;
else
if((B[i] == 1) && (A[i] == 0))
A[i] = 1;
else
if((B[i] == 1) && (A[i] == 1))
A[i] = 0;
}
}
unsigned long setOperations(long sets[], char operations[], unsigned int x)
{
unsigned int i = 1; //not 0, since i'll be reading the 1st number separately
unsigned int j = 0;
unsigned int n = x;
int t;
long a = sets[0];
int A[64];
for(t=0;t<64;t++)
A[t] = 0;
makeBinaryVector(A, a); //hold in A the first number, binary, and the results of operations
long b;
int B[64];
for(t=0;t<64;t++) //Hold the next number in B[], in binary form
B[t] = 0;
char op;
while(i < x && j < (x-1) )
{
b = sets[i];
makeBinaryVector(B, b);
op = operations[j];
OperationInA(A, op, B);
i++; j++;
}
//make array A a decimal number
unsigned int base = 1;
long nr = 0;
for(t=63; t>=0; t--)
{
nr = nr + A[t] * base;
base = base * 2;
}
return nr;
}
long sets[100];
char operations[100];
long n,i;
int main()
{
cin>>n;
for(i=0;i<n;i++)
cin>>sets[i];
for(i=0;i<n-1;i++)
cin>>operations[i];
cout<<setOperations(sets,operations,n);
return 0;
}
So everything seems fine, except when im trying this :
sets = {5, 2, 1}
operations = {'U' , '\'}
5 U 2 is 7(111), and 7 \ 1 is 6 (111 - 001 = 110 --> 6)
the result should be 6, however when i Input them like that the result is 4 (??)
however, if i simply input {7,1} and { \ } the result is 6,as it should be. but if i input them like i first mentioned {5,2,1} and {U,} then its gonna output 4.
I can't seem to understand or see what im doing wrong...
You don't have to "convert to binary numbers".
There's no such thing as 'binary numbers'. You can just perform the operations on the variables.
For the reunion, you can use the bitwise OR operator '|', and for the intersection, you can use the bitwise AND operator '&'.
Something like this:
if (op == 'A')
result = a & b;
else if (op == 'U')
result = a | b;
else if (op == '\\')
result = a - b;
else if (op == '/')
result = b - a;
Use bitwise operators on integers as shown in #Hugal31's answer.
Note that integer size is usually 32bit, not 64bit. On a 64bit system you need long long for 64bit integer. Use sizeof operator to check. int is 4 bytes (32bit) and long long is 8 bytes (64bit).
For the purpose of homework etc., your conversion to vector cannot be right. You should test it to see if it outputs the correct result. Otherwise use this:
void makebinary(int vec[32], int x)
{
int bitmask = 1;
for (int i = 31; i >= 0; i--)
{
vec[i] = (x & bitmask) ? 1 : 0;
bitmask <<= 1;
}
}
Note the use of shift operators. To AND the numbers you can do something like the following:
int vx[32];
int vy[32];
makebinary(vx, x);
makebinary(vy, y);
int result = 0;
int j = 1;
for (int i = 31; i >= 0; i--)
{
int n = (vx[i] & vy[i]) ? 1 : 0;
result += n * j;
j <<= 1;
}
This is of course pointless because you can just say int result = X & Y;

How do you implement your own string to integer conversion

So I want to take a string in such as 8302 and convert this into an integer by creating my own function and not using the stoi/atoi functions.
I tried so far by doing:
int stringToInt(string input)
{
int i = 0;
while(input[i] >= '0' && input[i] <= '9')
{
input[i] = input[i] * 10 + ......
i++;
}
return i;
}
I know i need to keep multiplying by 10 everytime i find an integer so i can increase it e.g 123 = 1*10*10+2*10+3. but i dont know how to code this. could anyone suggest a method?
It might be easiest to do it in a recursive manner. Use the following idea:
8302 = 830 * 10 + 2
That is:
If there is only one char in the string - return it; otherwise continue
Separate the last char in the string
Convert the string (without the last char) to integer - using recursion
Multiply by 10 and add the last char
There are a lot of details here:
how to convert 1 char to an integer? - subtract '0' from it
how to separate a char from the rest of the string? - use substr
when you have a working recursive solution, you might want to convert it to an iterative solution - this will make it faster, but maybe less readable
what to do with invalid strings like "aaa" or "123haha" - my algorithm doesn't handle that
Before you could define a char2int conversion:
inline int ctoi(char c) {
switch (c) {
case '0':
return 0;
case '1':
return 1;
case '2':
return 2;
case '3':
return 3;
case '4':
return 4;
case '5':
return 5;
case '6':
return 6;
case '7':
return 7;
case '8':
return 8;
case '9':
return 9;
default:
throw std::runtime_error("Invalid char conversion");
}
}
And use it:
int my_stoi_dec(const std::string& str) {
int rtn = 0;
int exp = 1;
for (auto cp = str.crbegin(); cp != str.crend(); ++cp) {
char c = *cp;
if (isdigit(c)) {
rtn += ctoi(c) * exp;
exp *= 10;
} else if (c == '+') {
return rtn;
} else if (c == '-') {
return rtn * -1;
} else {
throw std::runtime_error("Integer error conversion");
}
}
}
This one is very close to your attempt:
int toInt(const std::string& input)
{
int i = 0;
for (const auto c : input)
{
if (c < '0' || c > '9')
break;
i = i*10 + c-'0';
}
return i;
}
The only assumption is that the characters '0' to '9' lie directly next to each other in the character set. The if statement makes sure that we stop at non-digit characters. The digit-characters are converted to their integer value using c-'0'.
Please keep in mind that this only parses the first digits of a string. Strings that start with a sign + or - are not considered.
A good way is to find your first digit and go from there make a multiplayer variable and multiply it by ten every digit. for every char you add you have to subtract '0' from it as '0' is not equal to int 0.
example:
string s = "12346";
int multiplayer = 1;
int i = 0;
int result = 0;
while (s[i] >= '0' && s[i] <= '9')
++i;
--i;
for(i ; i >= 0 ; --i){
result += (s[i] - '0') * multiplayer;
multiplayer *= 10;
}
It is much better that you start your conversion from right to left.
So you will iterate your string starting from its end, and ending on its beginning. On each iteration, we will take the character, convert it to int and multiply it with its multiplier (its position in the result integer) and then add it to the final result.
This should work:
#include <iostream>
#include <string>
int stringToInt(std::string input)
{
int result = 0;
int multiplier = 1;
for (int i = input.length() - 1; i >= 0; i--) // start from right
{
if (input[i] - '0' < 0 || input[i] - '0' > 9) // if any character is not an integer, return maximum negative
{
result = INT16_MIN;
break;
}
result += (input[i] - '0') * multiplier; // convert to int, get its position and then add it to result.
multiplier *= 10; // get next position
}
return result;
}
int main()
{
std::string MyEx = "123456";
int MyInt = stringToInt(MyEx);
std::cout << MyInt;
return 0;
}
void enforce( bool b ) {
if ( !b ) {
throw std::range_error("Not a valid string to convert to integer");
}
}
int stringToInt(std::string) {
for ( std::size_t i( 0 ); i != ( last - first ); ++i ) {
enforce( ( '0' <= first[ i ] ) && ( first[ i ] <= '9' ) );
result += pow(10,i) * ( first[ i ] - '0' );
}
}
Source

Htoi incorrect output at 10 digits

When I input
0x123456789
I get incorrect outputs, I can't figure out why. At first I thought it was a max possible int value problem, but I changed my variables to unsigned long and the problem was still there.
#include <iostream>
using namespace std;
long htoi(char s[]);
int main()
{
cout << "Enter Hex \n";
char hexstring[20];
cin >> hexstring;
cout << htoi(hexstring) << "\n";
}
//Converts string to hex
long htoi(char s[])
{
int charsize = 0;
while (s[charsize] != '\0')
{
charsize++;
}
int base = 1;
unsigned long total = 0;
unsigned long multiplier = 1;
for (int i = charsize; i >= 0; i--)
{
if (s[i] == '0' || s[i] == 'x' || s[i] == 'X' || s[i] == '\0')
{
continue;
}
if ( (s[i] >= '0') && (s[i] <= '9') )
{
total = total + ((s[i] - '0') * multiplier);
multiplier = multiplier * 16UL;
continue;
}
if ((s[i] >= 'A') && (s[i] <= 'F'))
{
total = total + ((s[i] - '7') * multiplier); //'7' equals 55 in decimal, while 'A' equals 65
multiplier = multiplier * 16UL;
continue;
}
if ((s[i] >= 'a') && (s[i] <= 'f'))
{
total = total + ((s[i] - 'W') * multiplier); //W equals 87 in decimal, while 'a' equals 97
multiplier = multiplier * 16UL;
continue;
}
}
return total;
}
long probably is 32 bits on your computer as well. Try long long.
You need more than 32 bits to store that number. Your long type could well be as small as 32 bits.
Use a std::uint64_t instead. This is always a 64 bit unsigned type. If your compiler doesn't support that, use a long long. That must be at least 64 bits.
The idea follows the polynomial nature of a number. 123 is the same as
1*102 + 2*101 + 3*100
In other words, I had to multiply the first digit by ten two times. I had to multiply 2 by ten one time. And I multiplied the last digit by one. Again, reading from left to right:
Multiply zero by ten and add the 1 → 0*10+1 = 1.
Multiply that by ten and add the 2 → 1*10+2 = 12.
Multiply that by ten and add the 3 → 12*10+3 = 123.
We will do the same thing:
#include <cctype>
#include <ciso646>
#include <iostream>
using namespace std;
unsigned long long hextodec( const std::string& s )
{
unsigned long long result = 0;
for (char c : s)
{
result *= 16;
if (isdigit( c )) result |= c - '0';
else result |= toupper( c ) - 'A' + 10;
}
return result;
}
int main( int argc, char** argv )
{
cout << hextodec( argv[1] ) << "\n";
}
You may notice that the function is more than three lines. I did that for clarity. C++ idioms can make that loop a single line:
for (char c : s)
result = (result << 4) | (isdigit( c ) ? (c - '0') : (toupper( c ) - 'A' + 10));
You can also do validation if you like. What I have presented is not the only way to do the digit-to-value conversion. There exist other methods that are just as good (and some that are better).
I do hope this helps.
I found out what was happening, when I inputted "1234567890" it would skip over the '0' so I had to modify the code. The other problem was that long was indeed 32-bits, so I changed it to uint64_t as suggested by #Bathsheba. Here's the final working code.
#include <iostream>
using namespace std;
uint64_t htoi(char s[]);
int main()
{
char hexstring[20];
cin >> hexstring;
cout << htoi(hexstring) << "\n";
}
//Converts string to hex
uint64_t htoi(char s[])
{
int charsize = 0;
while (s[charsize] != '\0')
{
charsize++;
}
int base = 1;
uint64_t total = 0;
uint64_t multiplier = 1;
for (int i = charsize; i >= 0; i--)
{
if (s[i] == 'x' || s[i] == 'X' || s[i] == '\0')
{
continue;
}
if ( (s[i] >= '0') && (s[i] <= '9') )
{
total = total + ((uint64_t)(s[i] - '0') * multiplier);
multiplier = multiplier * 16;
continue;
}
if ((s[i] >= 'A') && (s[i] <= 'F'))
{
total = total + ((uint64_t)(s[i] - '7') * multiplier); //'7' equals 55 in decimal, while 'A' equals 65
multiplier = multiplier * 16;
continue;
}
if ((s[i] >= 'a') && (s[i] <= 'f'))
{
total = total + ((uint64_t)(s[i] - 'W') * multiplier); //W equals 87 in decimal, while 'a' equals 97
multiplier = multiplier * 16;
continue;
}
}
return total;
}

How should I approach a credit card number validation algorithm?

I'm writing a program to validate credit card numbers and I have to use Luhn's Algorithm. Let me say beforehand, that I have just started to learn to program (we covered loops like last week), so there a lot of things I am unfamiliar with. I am having trouble with one of my functions that checks the arithmetic. Basically, it has to double every second digit from right to left and add everything together. But if you double a number, like 5, and you get 10, then you will have to add 1+0=1 to the total sum instead of 10. That's the part I'm stuck on. How can I put that in a program?
Sample code so far:
int
doubleEvenSum(string creditCardNumber) {
int evenSum;
int countPosition;
int doublePosition;
int length;
length = creditCardNumber.length ();
countPosition = creditCardNumber.at(length - 2);
evenSum = 0;
while(countPosition>0) {
if ((2 * countPosition) < 10) {
doublePosition = 2 * countPosition;
}
else if ((2 * countPosition) > 9) {
???
}
evenSum = evenSum + doublePosition;
}
#include <stdio.h>
#include <string.h>
#include <ctype.h>
/*
return the Luhn (MOD10) checksum for a sequence of digits.
-1 is returned on error (a non-digit was in the sequence
*/
int mod10( char const* s)
{
int len = strlen(s);
int sum = 0;
int dbl = 0;
while (len) {
char digit;
int val;
--len;
digit = s[len];
if (!isdigit( (unsigned char) digit)) return -1; // non digit in the sequence
val = digit - '0'; // convert character to numeric value
if (dbl) {
// double the value
val *= 2;
// if the result is double-digits, add the digits together
if (val > 9) {
val = val - 10;
val = val + 1;
}
}
dbl = !dbl; // only double value every other time
sum += val;
}
return sum % 10;
}
Here is a different algorithm. I cut/pasted from a C# example; the second link discusses a number of optimization for Luhn.
Please study this example, and please run it through the debugger to study how the code behaves as it's executing. Understanding how code actually runs (as opposed to how you think it will run when you write it) is an essential skill. IMHO....
/*
* Validate credit card with Luhn Algorithm
*
* REFERENCES:
* - http://jlcoady.net/c-sharp/credit-card-validation-in-c-sharp
* - http://orb-of-knowledge.blogspot.com/2009/08/extremely-fast-luhn-function-for-c.html
*/
#include <stdio.h> // printf(), scanf(), etc
#include <string.h> // strlen (), etc
#include <ctype.h> // isdigit(), etc
#if !defined(FALSE)
#define FALSE 0
#define TRUE ~FALSE
#endif
/*
* type definitions (should go in separate header)
*/
enum CardType {
MASTERCARD=1, BANKCARD=2, VISA=3, AMEX=4, DISCOVER=5, DINERS=6, JCB=7
};
/*
* function prototypes (should also go in header)
*/
int luhn (int number[], int len);
bool validate (CardType cardType, char *cardNumber);
/*
* program main
*/
int
main (int argc, char *argv[])
{
char cc_number[80];
int cc_type;
for ( ;; ) {
printf ("Enter a credit card number and type (1, 2, 3, 4, 5. 6 or 7):\n");
printf (" MASTERCARD=1, BANKCARD=2, VISA=3, AMEX=4, DISCOVER=5, DINERS=6, JCB=7\n");
int iret = scanf ("%s %d", cc_number, &cc_type);
if (iret == 2)
break;
else
printf ("Incorrect input: please enter a valid CC# and CC type\n");
}
if (validate ((CardType)cc_type, cc_number))
printf ("Valid\n");
else
printf ("Invalid card type/number\n");
return 0;
}
/*
* validate card#
*/
bool
validate (CardType cardType, char *cardNumber)
{
// 16 or fewer digits?
int len = strlen(cardNumber);
if (strlen (cardNumber) > 16)
return false;
// number to validate
int number[16];
for(int i = 0; i < (int)strlen (cardNumber); i++) {
if(!isdigit(cardNumber[i]))
return FALSE;
number[i] = cardNumber[i] - '0';
}
// Validate based on card type, first if tests length, second tests prefix
switch(cardType) {
case MASTERCARD:
if(len != 16)
return FALSE;
if(number[0] != 5 || number[1] == 0 || number[1] > 5)
return FALSE;
break;
case BANKCARD:
if(len != 16)
return FALSE;
if(number[0] != 5 || number[1] != 6 || number[2] > 1)
return FALSE;
break;
case VISA:
if(len != 16 && len != 13)
return FALSE;
if(number[0] != 4)
return FALSE;
break;
case AMEX:
if(len != 15)
return FALSE;
if(number[0] != 3 || (number[1] != 4 && number[1] != 7))
return FALSE;
break;
case DISCOVER:
if(len != 16)
return FALSE;
if(number[0] != 6 || number[1] != 0 || number[2] != 1 || number[3] != 1)
return FALSE;
break;
case DINERS:
if(len != 14)
return FALSE;
if(number[0] != 3 || (number[1] != 0 && number[1] != 6 && number[1] != 8) || number[1] == 0 && number[2] > 5)
return FALSE;
break;
case JCB:
if(len != 16 && len != 15)
return FALSE;
if(number[0] != 3 || number[1] != 5)
return FALSE;
break;
default:
return FALSE;
}
int sum = luhn (number, len);
return (sum % 10 == 0);
}
// Use Luhn Algorithm to validate
int luhn (int number[], int len)
{
int sum = 0;
for(int i = len - 1; i >= 0; i--)
{
if(i % 2 == len % 2)
{
int n = number[i] * 2;
sum += (n / 10) + (n % 10);
}
else
sum += number[i];
}
return sum;
}
int luhnCardValidator(char cardNumbers[]) {
int sum = 0, nxtDigit, i;
for (i = 0; cardNumbers[i] != NULL_TERMINATOR ; i++) {
nxtDigit = cardNumbers[i] - START_OF_ASCII_NUMERIC;
if (i % 2 == 0)
nxtDigit = (nxtDigit > 4) ? (nxtDigit * 2 - 10) + 1 : nxtDigit * 2;
sum += nxtDigit;
}
return (sum % 10);
}
This:
... (nxtDigit > 4) ? (nxtDigit * 2 - 10) + 1 : ...
is the clever bit. If the digit is greater than 4, then the doubling will be 10 or more. In that case, you take the doubled number and subtract 10 which will give you the ones-digit then you add 1 (the tens-digit).
Just subtract 9 from the double of the number then you will equivalent of the sum of the digits.
For ex.
7= 7*2 = 14 = 1+4 = 5 OR 14-9 = 5
This is more efficient than writing code for adding both digits.