Continued working on url_manipulation library

url_manipulation.c

@@ -1,5 +1,8 @@
 #include <string.h>
 #include <stdlib.h>
+#include <stdio.h>
+
+#define DEFAULT_PATH "/index.html"
 
 char* url_to_proto(char* url) {
         size_t length = strlen(url);
@@ -22,20 +25,49 @@ char* url_to_hostname(char* url) {
 	size_t length = strlen(url);
 	char* protocol = url_to_proto(url);
 
-        char* to_return = malloc(sizeof(char) * 256);
-
+        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
+	URL (length of protocol string + 3 (':','/','/'), we are copying the rest of the string into another
 	substring. */
-	strncpy(to_return,url+(strlen(protocol) + 3),(length - (strlen(protocol) + 3)));
-
 
+	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;
+		}
+	}
+	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 (sentinel == 0) {
+		to_return = DEFAULT_PATH;
+	}
+
+	/* 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;
 
 }

url_manipulation.h

@@ -10,3 +10,7 @@ Example - 'https://example.org' would return 'example.org'. */
 
 char* url_to_hostname(char* url);
 
+/* url_to_path - Returns the path portion of a URL.
+Example: 'https://example.org/index.html' will return '/index.html' 
+Any empty path will also return '/index.html' */
+char* url_to_path(char* url);