Provide a method to use unicode command line arguments on Windows

For unicode command line characters Windows uses UTF-16, while Glib
and GTK use UTF-8. To solve that we retrieve the command line
via __wgetmainargs() and use g_utf16_to_utf8() to convert each argument.

The used method should support wildcards passed as arguments
(e.g. *.xml).

Two new, OS abstracted functions appear in linux.c (NOP), macos.c (NOP),
windows.c:

subsurface_command_line_init(...)
subsurface_command_line_exit(...)

which are being called in main()

Signed-off-by: Lubomir I. Ivanov <neolit123@gmail.com>
Signed-off-by: Dirk Hohndel <dirk@hohndel.org>

dive.h

@@ -434,6 +434,8 @@ extern const char *star_strings[];
 extern const char *default_filename;
 extern const char *existing_filename;
 extern const char *subsurface_default_filename(void);
+extern void subsurface_command_line_init(gint *, gchar ***);
+extern void subsurface_command_line_exit(gint *, gchar ***);
 #define AIR_PERMILLE 209
 
 #define FRACTION(n,x) ((unsigned)(n)/(x)),((unsigned)(n)%(x))

linux.c

@@ -91,3 +91,13 @@ void subsurface_ui_setup(GtkSettings *settings, GtkWidget *menubar,
 		divelist_font = DIVELIST_DEFAULT_FONT;
 	gtk_box_pack_start(GTK_BOX(vbox), menubar, FALSE, FALSE, 0);
 }
+
+void subsurface_command_line_init(gint *argc, gchar ***argv)
+{
+	/* this is a no-op */
+}
+
+void subsurface_command_line_exit(gint *argc, gchar ***argv)
+{
+	/* this is a no-op */
+}

macos.c

@@ -149,3 +149,13 @@ void subsurface_ui_setup(GtkSettings *settings, GtkWidget *menubar,
 
 	gtk_osxapplication_ready(osx_app);
 }
+
+void subsurface_command_line_init(gint *argc, gchar ***argv)
+{
+	/* this is a no-op */
+}
+
+void subsurface_command_line_exit(gint *argc, gchar ***argv)
+{
+	/* this is a no-op */
+}

main.c

@@ -223,6 +223,7 @@ int main(int argc, char **argv)
 
 	output_units = SI_units;
 
+	subsurface_command_line_init(&argc, &argv);
 	parse_xml_init();
 
 	init_ui(&argc, &argv);
@@ -268,6 +269,7 @@ int main(int argc, char **argv)
 	exit_ui();
 
 	parse_xml_exit();
+	subsurface_command_line_exit(&argc, &argv);
 
 #ifdef DEBUGFILE
 	if (debugfile)

windows.c

@@ -124,3 +124,57 @@ void subsurface_ui_setup(GtkSettings *settings, GtkWidget *menubar,
 		divelist_font = DIVELIST_DEFAULT_FONT;
 	gtk_box_pack_start(GTK_BOX(vbox), menubar, FALSE, FALSE, 0);
 }
+
+/* barely documented API */
+extern int __wgetmainargs(int *, wchar_t ***, wchar_t ***, int, int *);
+
+/* expand-convert the UTF-16 argument list to a list of UTF-8 strings */
+void subsurface_command_line_init(gint *argc, gchar ***argv)
+{
+	wchar_t **wargv, **wenviron;
+	gchar **argv_new;
+	gchar *s;
+	/* for si we assume that a struct address will equal the address
+	 * of its first and only int member */
+	gint i, n, ret, si;
+
+	/* memory leak tools may reports a potential issue here at a call
+	 * to strcpy_s in msvcrt, wich should be a false positive. but even if there
+	 * is some kind of a leak, it should be unique and have the same
+	 * lifespan as the process heap. */
+	ret = __wgetmainargs(&n, &wargv, &wenviron, TRUE, &si);
+	if (ret < 0) {
+		g_warning("Cannot convert command line");
+		return;
+	}
+	argv_new = g_malloc(sizeof(gchar *) * (n + 1));
+
+	for (i = 0; i < n; ++i) {
+		s = g_utf16_to_utf8((gunichar2 *)wargv[i], -1, NULL, NULL, NULL);
+		if (!s) {
+			g_warning("Cannot convert command line argument (%d) to UTF-8", (i + 1));
+			s = "\0";
+		}	else if (!g_utf8_validate(s, -1, NULL)) {
+			g_warning("Cannot validate command line argument '%s' (%d)", s, (i + 1));
+			g_free(s);
+			s = "\0";
+		}
+		argv_new[i] = s;
+	}
+	argv_new[n] = NULL;
+
+	/* update the argument list and count */
+	if (argv && argc) {
+		*argv = argv_new;
+		*argc = n;
+	}
+}
+
+/* once done, free the argument list */
+void subsurface_command_line_exit(gint *argc, gchar ***argv)
+{
+	int i;
+	for (i = 0; i < *argc; i++)
+		g_free((*argv)[i]);
+	g_free(*argv);
+}