URL Encoding in C (urlencode / encodeURIComponent)

url-encode.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

char* urlencode(char* originalText)
{
    // allocate memory for the worst possible case (all characters need to be encoded)
    char *encodedText = (char *)malloc(sizeof(char)*strlen(originalText)*3+1);
    
    const char *hex = "0123456789abcdef";
    
    int pos = 0;
    for (int i = 0; i < strlen(originalText); i++) {
        if (('a' <= originalText[i] && originalText[i] <= 'z')
            || ('A' <= originalText[i] && originalText[i] <= 'Z')
            || ('0' <= originalText[i] && originalText[i] <= '9')) {
                encodedText[pos++] = originalText[i];
            } else {
                encodedText[pos++] = '%';
                encodedText[pos++] = hex[originalText[i] >> 4];
                encodedText[pos++] = hex[originalText[i] & 15];
            }
    }
    encodedText[pos] = '\0';
    return encodedText;
}

int main()
{
    printf("%s", urlencode("Hello / world ="));

    return 0;
}

Thanks!

Incredible!

I think you should free encodedText

Thank you!

I'd just test the return value of "malloc()". It must not be NULL.

Also, I'd rather say : char* urlencode(const char* originalText)

This isn't a good approach at all.

First, URLs sometimes can be very large, and now malloc will have to allocate a chunk of memory in the heap. In the worst scenario, anyone can pass an arbitrarily large URL which may cause a buffer overflow.

thanks, short version:
static void urlencode(char * s, char * d)
{
const char *hex = "0123456789ABCDEF";

while(*s)
{
    if (('a' <= *s && *s <= 'z')
        || ('A' <= *s && *s <= 'Z')
        || ('0' <= *s && *s <= '9')) {
            *d++ = *s;
    } else {
        *d++ = '%';
        *d++ = hex[(*s >> 4) & 0x0F];
        *d++ = hex[*s & 0x0F];
    }
    s++;
}
*d = '\0';

}