js: Convert non-UTF-8 encoded files to UTF-8 before parsing

Author: https://github.com/trflynn89
Commit: https://github.com/SerenityOS/serenity/commit/b36c3a68d8
Pull-request: https://github.com/SerenityOS/serenity/pull/13468
Reviewed-by: https://github.com/davidot
Reviewed-by: https://github.com/linusg

Meta/Lagom/CMakeLists.txt

@@ -388,7 +388,7 @@ if (BUILD_LAGOM)
     list(REMOVE_ITEM LIBJS_SOURCES "${CMAKE_CURRENT_SOURCE_DIR}/../../Userland/Libraries/LibJS/SyntaxHighlighter.cpp")
     lagom_lib(JS js
         SOURCES ${LIBJS_SOURCES} ${LIBJS_SUBDIR_SOURCES} ${LIBJS_SUBSUBDIR_SOURCES}
-        LIBS m LagomCrypto LagomRegex LagomUnicode
+        LIBS m LagomCrypto LagomRegex LagomUnicode LagomTextCodec
     )
 
     # Line

Userland/Utilities/CMakeLists.txt

@@ -122,7 +122,7 @@ target_link_libraries(ifconfig LibMain)
 target_link_libraries(ini LibMain)
 target_link_libraries(install-bin LibMain)
 target_link_libraries(jp LibMain)
-target_link_libraries(js LibJS LibLine LibMain)
+target_link_libraries(js LibJS LibLine LibMain LibTextCodec)
 link_with_unicode_data(js)
 target_link_libraries(kcov-example LibMain)
 target_link_libraries(keymap LibKeyboard LibMain)

Userland/Utilities/js.cpp

@@ -71,6 +71,7 @@
 #include <LibJS/SourceTextModule.h>
 #include <LibLine/Editor.h>
 #include <LibMain/Main.h>
+#include <LibTextCodec/Decoder.h>
 #include <fcntl.h>
 #include <signal.h>
 #include <stdio.h>
@@ -1653,7 +1654,16 @@ ErrorOr<int> serenity_main(Main::Arguments arguments)
                 auto file = TRY(Core::File::open(path, Core::OpenMode::ReadOnly));
                 auto file_contents = file->read_all();
                 auto source = StringView { file_contents };
-                builder.append(source);
+
+                if (Utf8View { file_contents }.validate()) {
+                    builder.append(source);
+                } else {
+                    auto* decoder = TextCodec::decoder_for("windows-1252");
+                    VERIFY(decoder);
+
+                    auto utf8_source = TextCodec::convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte_order_mark(*decoder, source);
+                    builder.append(utf8_source);
+                }
             }
 
             source_name = script_paths[0];