This version is pure C and can optionally normalize the resource path. Using it with C++ is trivial:
#include
#include
int main(int argc, char** argv)
{
const std::string src("/some.url/foo/../bar/%2e/");
std::cout << "src=\"" << src << "\"" << std::endl;
// either do it the C++ conformant way:
char* dst_buf = new char[src.size() + 1];
urldecode(dst_buf, src.c_str(), 1);
std::string dst1(dst_buf);
delete[] dst_buf;
std::cout << "dst1=\"" << dst1 << "\"" << std::endl;
// or in-place with the &[0] trick to skip the new/delete
std::string dst2;
dst2.resize(src.size() + 1);
dst2.resize(urldecode(&dst2[0], src.c_str(), 1));
std::cout << "dst2=\"" << dst2 << "\"" << std::endl;
}
Outputs:
src="/some.url/foo/../bar/%2e/"
dst1="/some.url/bar/"
dst2="/some.url/bar/"
And the actual function:
#include
#include
/**
* decode a percent-encoded C string with optional path normalization
*
* The buffer pointed to by @dst must be at least strlen(@src) bytes.
* Decoding stops at the first character from @src that decodes to null.
* Path normalization will remove redundant slashes and slash+dot sequences,
* as well as removing path components when slash+dot+dot is found. It will
* keep the root slash (if one was present) and will stop normalization
* at the first questionmark found (so query parameters won't be normalized).
*
* @param dst destination buffer
* @param src source buffer
* @param normalize perform path normalization if nonzero
* @return number of valid characters in @dst
* @author Johan Lindh
* @legalese BSD licensed (http://opensource.org/licenses/BSD-2-Clause)
*/
ptrdiff_t urldecode(char* dst, const char* src, int normalize)
{
char* org_dst = dst;
int slash_dot_dot = 0;
char ch, a, b;
do {
ch = *src++;
if (ch == '%' && isxdigit(a = src[0]) && isxdigit(b = src[1])) {
if (a < 'A') a -= '0';
else if(a < 'a') a -= 'A' - 10;
else a -= 'a' - 10;
if (b < 'A') b -= '0';
else if(b < 'a') b -= 'A' - 10;
else b -= 'a' - 10;
ch = 16 * a + b;
src += 2;
}
if (normalize) {
switch (ch) {
case '/':
if (slash_dot_dot < 3) {
/* compress consecutive slashes and remove slash-dot */
dst -= slash_dot_dot;
slash_dot_dot = 1;
break;
}
/* fall-through */
case '?':
/* at start of query, stop normalizing */
if (ch == '?')
normalize = 0;
/* fall-through */
case '\0':
if (slash_dot_dot > 1) {
/* remove trailing slash-dot-(dot) */
dst -= slash_dot_dot;
/* remove parent directory if it was two dots */
if (slash_dot_dot == 3)
while (dst > org_dst && *--dst != '/')
/* empty body */;
slash_dot_dot = (ch == '/') ? 1 : 0;
/* keep the root slash if any */
if (!slash_dot_dot && dst == org_dst && *dst == '/')
++dst;
}
break;
case '.':
if (slash_dot_dot == 1 || slash_dot_dot == 2) {
++slash_dot_dot;
break;
}
/* fall-through */
default:
slash_dot_dot = 0;
}
}
*dst++ = ch;
} while(ch);
return (dst - org_dst) - 1;
}