Added testing code for retrieving HTTP response

Makefile

@@ -1,4 +1,4 @@
 main: main.c
-	gcc main.c -o main -L/usr/lib -lXm -lXt -lX11 -l:libXmHTML.so.1.1.10 
+	gcc main.c url_manipulation.c easysock.c -o main -L/usr/lib -lXm -lXt -lX11 -l:libXmHTML.so.1.1.10 
 
 

main.c

@@ -79,12 +79,17 @@ void testFunc(Widget w, XtPointer client_data, XmPushButtonCallbackStruct *callb
 	and make the connection for us. It returns the socket, so that the HTTP request can be made.
 	First parameter is IP version - set to -1 because we don't know yet if the address is IPv4 or IPv6. */
 
+	char* request = "GET /~fdc/sample.html HTTP/1.1\nHost: www.columbia.edu\n\n"
+	char* response = malloc(sizeof(char) * 5000);
+
 	struct sockaddr* address_struct;
 	int remote_socket = create_remote(-1,'T',url_to_hostname(url),port,address_struct);
 
+	send(remote_socket,request,strlen(request),0);
 	
+	recv(remote_socket,response,sizeof(response),0);		
 
-	XmHTMLTextSetString(result_widget,"");
+	XmHTMLTextSetString(result_widget,response);
 //	printf("%d\n",val);
 //	exit(2);
 }

url_manipulation.c

@@ -1,5 +1,8 @@
 #include <string.h>
 #include <stdlib.h>
+#include <stdio.h>
+
+#define DEFAULT_PATH "/"
 
 char* url_to_proto(char* url) {
         size_t length = strlen(url);
@@ -17,25 +20,64 @@ char* url_to_proto(char* url) {
 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). */
+	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* 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;
+		}
+	}
 
 
+	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;
 
 }

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);