You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
84 lines
2.5 KiB
C
84 lines
2.5 KiB
C
#include <string.h>
|
|
#include <stdlib.h>
|
|
#include <stdio.h>
|
|
|
|
#define DEFAULT_PATH "/"
|
|
|
|
char* url_to_proto(char* url) {
|
|
size_t length = strlen(url);
|
|
int sentinel = 0;
|
|
char* to_return = malloc(sizeof(char) * 10);
|
|
for (int i=0;i<length;i++) {
|
|
if (*(url + (sizeof(char) * i)) == ':') { /* If the character is ':' ...*/
|
|
sentinel = i; /* ...Then we stop scanning the string */
|
|
}
|
|
}
|
|
strncpy(to_return,url,sentinel);
|
|
return to_return;
|
|
}
|
|
|
|
char* url_to_hostname(char* url) {
|
|
/* This function relies on a hack-y assumption: that, given a string
|
|
that represents a URL (e.g. https://www.example.com/index.html), the length of the host portion
|
|
of the address is the distance between the second slash (:/'/') and the third ('/'index.html),
|
|
or the second slash and the end of the string, if the path isn't present. */
|
|
|
|
size_t length = strlen(url);
|
|
char* protocol = url_to_proto(url);
|
|
|
|
char* temp_substring = malloc(sizeof(char) * 256);
|
|
char* to_return = malloc(sizeof(char) * 256);
|
|
|
|
/* This is a very roundabout way of saying that, starting from a certain point in the
|
|
URL (length of protocol string + 3 (':','/','/'), we are copying the rest of the string into another
|
|
substring. */
|
|
|
|
strncpy(temp_substring,url+(strlen(protocol) + 3),(length - (strlen(protocol) + 3)));
|
|
|
|
/* Now we need to substring _this_ substring, by returning only the part before the next slash. */
|
|
int sentinel = 0;
|
|
for (int i=0;i<strlen(temp_substring);i++) {
|
|
if (*(temp_substring+(sizeof(char) * i)) == '/') {
|
|
sentinel = i;
|
|
}
|
|
}
|
|
|
|
|
|
if (sentinel == 0) { /* If there are no more slashes */
|
|
return temp_substring;
|
|
}
|
|
strncpy(to_return,temp_substring,sentinel);
|
|
free(temp_substring);
|
|
return to_return;
|
|
}
|
|
|
|
char* url_to_path(char* url) {
|
|
/* Assumption: The path starts from the third slash to the end of the string. */
|
|
int str_len = strlen(url);
|
|
int sentinel = 0;
|
|
int num_slashes = 0;
|
|
char* to_return = malloc(sizeof(char) * 512);
|
|
for (int i=0;i<strlen(url);i++) {
|
|
if (*(url + (sizeof(char) * i)) == '/') {
|
|
num_slashes++;
|
|
sentinel = i;
|
|
}
|
|
if (num_slashes == 3) {
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (num_slashes < 3 || sentinel == str_len) { /* If we don't find the requisite number of slashes after
|
|
parsing the string OR the third slash is at the end of the string
|
|
("e.g. www.example.com/")... */
|
|
|
|
strcpy(to_return,DEFAULT_PATH); /* ...Then return the default path - "/" */
|
|
return to_return;
|
|
}
|
|
|
|
/* Copy all bytes of the string, starting from the third slash */
|
|
strncpy(to_return, url+(sizeof(char) * sentinel), strlen(url)-(sizeof(char) * sentinel));
|
|
return to_return;
|
|
|
|
}
|