GDScript: Reintroduce binary tokenization on export

This adds back a function available in 3.x: exporting the GDScript
files in a binary form by converting the tokens recognized by the
tokenizer into a data format.

It is enabled by default on export but can be manually disabled. The
format helps with loading times since, the tokens are easily
reconstructed, and with hiding the source code, since recovering it
would require a specialized tool. Code comments are not stored in this
format.

The `--test` command can also include a `--use-binary-tokens` flag
which will run the GDScript tests with the binary format instead of the
regular source code by converting them in-memory before the test runs.

1 files changed, 22 insertions, 2 deletions

diff --git a/modules/gdscript/gdscript.cpp b/modules/gdscript/gdscript.cpp
index e78c113c6c..551adcb320 100644
--- a/modules/gdscript/gdscript.cpp
+++ b/modules/gdscript/gdscript.cpp
@@ -35,6 +35,7 @@
 #include "gdscript_compiler.h"
 #include "gdscript_parser.h"
 #include "gdscript_rpc_callable.h"
+#include "gdscript_tokenizer_buffer.h"
 #include "gdscript_warning.h"
 
 #ifdef TOOLS_ENABLED
@@ -740,7 +741,12 @@ Error GDScript::reload(bool p_keep_state) {
 
 	valid = false;
 	GDScriptParser parser;
-	Error err = parser.parse(source, path, false);
+	Error err;
+	if (!binary_tokens.is_empty()) {
+		err = parser.parse_binary(binary_tokens, path);
+	} else {
+		err = parser.parse(source, path, false);
+	}
 	if (err) {
 		if (EngineDebugger::is_active()) {
 			GDScriptLanguage::get_singleton()->debug_break_parse(_get_debug_path(), parser.get_errors().front()->get().line, "Parser Error: " + parser.get_errors().front()->get().message);
@@ -1050,6 +1056,19 @@ Error GDScript::load_source_code(const String &p_path) {
 	return OK;
 }
 
+void GDScript::set_binary_tokens_source(const Vector<uint8_t> &p_binary_tokens) {
+	binary_tokens = p_binary_tokens;
+}
+
+const Vector<uint8_t> &GDScript::get_binary_tokens_source() const {
+	return binary_tokens;
+}
+
+Vector<uint8_t> GDScript::get_as_binary_tokens() const {
+	GDScriptTokenizerBuffer tokenizer;
+	return tokenizer.parse_code_string(source);
+}
+
 const HashMap<StringName, GDScriptFunction *> &GDScript::debug_get_member_functions() const {
 	return member_functions;
 }
@@ -2805,6 +2824,7 @@ Ref<Resource> ResourceFormatLoaderGDScript::load(const String &p_path, const Str
 
 void ResourceFormatLoaderGDScript::get_recognized_extensions(List<String> *p_extensions) const {
 	p_extensions->push_back("gd");
+	p_extensions->push_back("gdc");
 }
 
 bool ResourceFormatLoaderGDScript::handles_type(const String &p_type) const {
@@ -2813,7 +2833,7 @@ bool ResourceFormatLoaderGDScript::handles_type(const String &p_type) const {
 
 String ResourceFormatLoaderGDScript::get_resource_type(const String &p_path) const {
 	String el = p_path.get_extension().to_lower();
-	if (el == "gd") {
+	if (el == "gd" || el == "gdc") {
 		return "GDScript";
 	}
 	return "";