wget: move from cpp-cheat

README.adoc

@@ -13120,6 +13120,12 @@ The example allocates two ints and uses them, and then deallocates back.
 
 Bibliography: https://stackoverflow.com/questions/6988487/what-does-the-brk-system-call-do/31082353#31082353
 
+==== socket
+
+A bit like `read` and `write`, but from / to the Internet!
+
+* link:userland/posix/wget.c[] tiny `wget` re-implementation. See: https://stackoverflow.com/questions/11208299/how-to-make-an-http-get-request-in-c-without-libcurl/35680609#35680609
+
 === Userland multithreading
 
 The following sections are related to multithreading in userland:

path_properties.py

@@ -37,6 +37,7 @@ class PathProperties:
         'cc_flags_after': ['-lm', LF],
         'cc_pedantic': True,
         'cxx_std': default_cxx_std,
+        # Shuts system down, consumes a lot of memory, etc.
         'disrupts_system': False,
         # Expected program exit status. When signals are raised, this refers
         # to the native exit status. as reported by Bash #?.
@@ -60,15 +61,20 @@ class PathProperties:
         # it only generates intermediate object files. Therefore it
         # should not be run while testing.
         'no_executable': False,
-        # The script requires a non-trivial argument to be passed to run properly.
+        # The script requires a non-trivial to determine argument to be passed to run properly.
         'requires_argument': False,
+        # Let's not test stuff that relies on the internet by default, user might be offline,
+        # or Internet might be slow and make tests slow.
+        'requires_internet': False,
+        # Requires certain of our custom kernel modules to be inserted to run.
+        'requires_kernel_modules': False,
+        # gem5 syscall emulation cannot handle dynamically linked exectuables properly.
+        # https://stackoverflow.com/questions/50542222/how-to-run-a-dynamically-linked-executable-syscall-emulation-mode-se-py-in-gem5
         'requires_dynamic_library': False,
         'requires_m5ops': False,
         # gem5 fatal: syscall getcpu (#168) unimplemented.
         'requires_syscall_getcpu': False,
         'requires_semihosting': False,
-        # Requires certain of our custom kernel modules to be inserted to run.
-        'requires_kernel_modules': False,
         # The example requires sudo, which usually implies that it can do something
         # deeply to the system it runs on, which would preventing further interactive
         # or test usage of the system, for example poweroff or messing up the GUI.
@@ -168,6 +174,7 @@ class PathProperties:
             not self['more_than_1s'] and
             not self['no_executable'] and
             not self['requires_argument'] and
+            not self['requires_internet'] and
             not self['requires_kernel_modules'] and
             not self['requires_sudo'] and
             not self['skip_run_unclassified'] and
@@ -556,6 +563,7 @@ path_properties_tuples = (
                         'pthread_self.c': {
                             'test_run_args': {'cpus': 2},
                         },
+                        'wget.c': {'requires_internet': True},
                         'sleep_forever.c': {'more_than_1s': True},
                         'virt_to_phys_test.c': {'more_than_1s': True},
                     }

userland/posix/wget.c

@@ -0,0 +1,99 @@
+/* https://cirosantilli.com/linux-kernel-module-cheat#socket */
+
+#define _XOPEN_SOURCE 700
+#include <arpa/inet.h>
+#include <assert.h>
+#include <netdb.h> /* getprotobyname */
+#include <netinet/in.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+int main(int argc, char** argv) {
+    char buffer[BUFSIZ];
+    enum CONSTEXPR { MAX_REQUEST_LEN = 1024};
+    char request[MAX_REQUEST_LEN];
+    char request_template[] = "GET / HTTP/1.1\r\nHost: %s\r\n\r\n";
+    struct protoent *protoent;
+    char *hostname = "example.com";
+    in_addr_t in_addr;
+    int request_len;
+    int socket_file_descriptor;
+    ssize_t nbytes_total, nbytes_last;
+    struct hostent *hostent;
+    struct sockaddr_in sockaddr_in;
+    unsigned short server_port = 80;
+
+    if (argc > 1)
+        hostname = argv[1];
+    if (argc > 2)
+        server_port = strtoul(argv[2], NULL, 10);
+
+    request_len = snprintf(request, MAX_REQUEST_LEN, request_template, hostname);
+    if (request_len >= MAX_REQUEST_LEN) {
+        fprintf(stderr, "request length large: %d\n", request_len);
+        exit(EXIT_FAILURE);
+    }
+
+    /* Build the socket. */
+    protoent = getprotobyname("tcp");
+    if (protoent == NULL) {
+        perror("getprotobyname");
+        exit(EXIT_FAILURE);
+    }
+    socket_file_descriptor = socket(AF_INET, SOCK_STREAM, protoent->p_proto);
+    if (socket_file_descriptor == -1) {
+        perror("socket");
+        exit(EXIT_FAILURE);
+    }
+
+    /* Build the address. */
+    hostent = gethostbyname(hostname);
+    if (hostent == NULL) {
+        fprintf(stderr, "error: gethostbyname(\"%s\")\n", hostname);
+        exit(EXIT_FAILURE);
+    }
+    in_addr = inet_addr(inet_ntoa(*(struct in_addr*)*(hostent->h_addr_list)));
+    if (in_addr == (in_addr_t)-1) {
+        fprintf(stderr, "error: inet_addr(\"%s\")\n", *(hostent->h_addr_list));
+        exit(EXIT_FAILURE);
+    }
+    sockaddr_in.sin_addr.s_addr = in_addr;
+    sockaddr_in.sin_family = AF_INET;
+    sockaddr_in.sin_port = htons(server_port);
+
+    /* Actually connect. */
+    if (connect(socket_file_descriptor, (struct sockaddr*)&sockaddr_in, sizeof(sockaddr_in)) == -1) {
+        perror("connect");
+        exit(EXIT_FAILURE);
+    }
+
+    /* Send HTTP request. */
+    nbytes_total = 0;
+    while (nbytes_total < request_len) {
+        nbytes_last = write(socket_file_descriptor, request + nbytes_total, request_len - nbytes_total);
+        if (nbytes_last == -1) {
+            perror("write");
+            exit(EXIT_FAILURE);
+        }
+        nbytes_total += nbytes_last;
+    }
+
+    /* Read the response. */
+    fprintf(stderr, "debug: before first read\n");
+    while ((nbytes_total = read(socket_file_descriptor, buffer, BUFSIZ)) > 0) {
+        fprintf(stderr, "debug: after a read\n");
+        write(STDOUT_FILENO, buffer, nbytes_total);
+    }
+    fprintf(stderr, "debug: after last read\n");
+    if (nbytes_total == -1) {
+        perror("read");
+        exit(EXIT_FAILURE);
+    }
+
+    close(socket_file_descriptor);
+    exit(EXIT_SUCCESS);
+}