rbs 3.9.4 → 4.2.0

data/ext/rbs_extension/main.c

@@ -1,33 +1,649 @@
 #include "rbs_extension.h"
+#include "rbs/util/rbs_assert.h"
+#include "rbs/util/rbs_allocator.h"
 #include "rbs/util/rbs_constant_pool.h"
+#include "rbs/serialize.h"
+#include "ast_translation.h"
+#include "legacy_location.h"
+#include "rbs_string_bridging.h"
 
 #include "ruby/vm.h"
 
-static
-void Deinit_rbs_extension(ruby_vm_t *_) {
-  rbs_constant_pool_free(RBS_GLOBAL_CONSTANT_POOL);
+/**
+ * Raises `RBS::ParsingError` or `RuntimeError` on `tok` with message constructed with given `fmt`.
+ *
+ * ```
+ * foo.rbs:11:21...11:25: Syntax error: {message}, token=`{tok source}` ({tok type})
+ * ```
+ * */
+static NORETURN(void) raise_error(rbs_error_t *error, VALUE buffer) {
+    RBS_ASSERT(error != NULL, "raise_error() called with NULL error");
+
+    if (!error->syntax_error) {
+        rb_raise(rb_eRuntimeError, "Unexpected error");
+    }
+
+    VALUE location = rbs_new_location(buffer, error->token.range);
+    VALUE type = rb_str_new_cstr(rbs_token_type_str(error->token.type));
+
+    VALUE rb_error = rb_funcall(
+        RBS_ParsingError,
+        rb_intern("new"),
+        3,
+        location,
+        rb_str_new_cstr(error->message),
+        type
+    );
+
+    rb_exc_raise(rb_error);
+}
+
+void raise_error_if_any(rbs_parser_t *parser, VALUE buffer) {
+    if (parser->error != NULL) {
+        raise_error(parser->error, buffer);
+    }
+}
+
+/**
+ * Inserts the given array of type variables names into the parser's type variable table.
+ * @param parser
+ * @param variables A Ruby Array of Symbols, or nil.
+ */
+static void declare_type_variables(rbs_parser_t *parser, VALUE variables, VALUE buffer) {
+    if (NIL_P(variables)) return; // Nothing to do.
+
+    if (!RB_TYPE_P(variables, T_ARRAY)) {
+        rbs_parser_free(parser);
+        rb_raise(rb_eTypeError, "wrong argument type %" PRIsVALUE " (must be an Array of Symbols or nil)", rb_obj_class(variables));
+    }
+
+    rbs_parser_push_typevar_table(parser, true);
+
+    for (long i = 0; i < rb_array_len(variables); i++) {
+        VALUE symbol = rb_ary_entry(variables, i);
+
+        if (!RB_TYPE_P(symbol, T_SYMBOL)) {
+            rbs_parser_free(parser);
+            rb_raise(rb_eTypeError, "Type variables Array contains invalid value %" PRIsVALUE " of type %" PRIsVALUE " (must be an Array of Symbols or nil)", rb_inspect(symbol), rb_obj_class(symbol));
+        }
+
+        VALUE name_str = rb_sym2str(symbol);
+        uint8_t *copied_name = (uint8_t *) malloc((size_t) RSTRING_LEN(name_str));
+        memcpy((void *) copied_name, RSTRING_PTR(name_str), RSTRING_LEN(name_str));
+
+        rbs_constant_id_t id = rbs_constant_pool_insert_owned(
+            &parser->constant_pool,
+            copied_name,
+            RSTRING_LEN(name_str)
+        );
+
+        if (!rbs_parser_insert_typevar(parser, id)) {
+            raise_error(parser->error, buffer);
+        }
+    }
+}
+
+struct parse_type_arg {
+    VALUE buffer;
+    rb_encoding *encoding;
+    rbs_parser_t *parser;
+    VALUE require_eof;
+    VALUE void_allowed;
+    VALUE self_allowed;
+    VALUE classish_allowed;
+};
+
+struct parse_method_type_arg {
+    VALUE buffer;
+    rb_encoding *encoding;
+    rbs_parser_t *parser;
+    VALUE require_eof;
+};
+
+struct parse_signature_arg {
+    VALUE buffer;
+    rb_encoding *encoding;
+    rbs_parser_t *parser;
+    VALUE require_eof;
+};
+
+static VALUE ensure_free_parser(VALUE parser) {
+    rbs_parser_free((rbs_parser_t *) parser);
+    return Qnil;
+}
+
+static VALUE parse_type_try(VALUE a) {
+    struct parse_type_arg *arg = (struct parse_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    if (parser->next_token.type == pEOF) {
+        return Qnil;
+    }
+
+    bool void_allowed = RTEST(arg->void_allowed);
+    bool self_allowed = RTEST(arg->self_allowed);
+    bool classish_allowed = RTEST(arg->classish_allowed);
+
+    rbs_node_t *type;
+    rbs_parse_type(parser, &type, void_allowed, self_allowed, classish_allowed);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    if (RB_TEST(arg->require_eof)) {
+        rbs_parser_advance(parser);
+        if (parser->current_token.type != pEOF) {
+            rbs_parser_set_error(parser, parser->current_token, true, "expected a token `%s`", rbs_token_type_str(pEOF));
+            raise_error(parser->error, arg->buffer);
+        }
+    }
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_struct_to_ruby_value(ctx, type);
+}
+
+/**
+ * `end_pos` may point past the end of the buffer: clamping with a large
+ * number instead of measuring the buffer is ordinary, and the lexer stops at
+ * the end on its own.
+ * */
+static void validate_position_range(VALUE string, int start_pos, int end_pos) {
+    if (start_pos < 0 || end_pos < 0) {
+        rb_raise(rb_eArgError, "negative position range: %d...%d", start_pos, end_pos);
+    }
+    if (start_pos > end_pos) {
+        rb_raise(rb_eArgError, "invalid position range: %d...%d", start_pos, end_pos);
+    }
+
+    long size = RSTRING_LEN(string);
+    if ((long) start_pos > size) {
+        rb_raise(rb_eArgError, "position range starts past the end of the buffer: %d...%d, buffer is %ld bytes", start_pos, end_pos, size);
+    }
+}
+
+static rbs_lexer_t *alloc_lexer_from_buffer(rbs_allocator_t *allocator, VALUE string, rb_encoding *encoding, int start_pos, int end_pos) {
+    validate_position_range(string, start_pos, end_pos);
+
+    const char *encoding_name = rb_enc_name(encoding);
+
+    rbs_lexer_t *lexer = rbs_lexer_new(
+        allocator,
+        rbs_string_from_ruby_string(string),
+        rbs_encoding_find((const uint8_t *) encoding_name, (const uint8_t *) (encoding_name + strlen(encoding_name))),
+        start_pos,
+        end_pos
+    );
+
+    if (lexer == NULL) {
+        rb_raise(rb_eArgError, "position range starts inside a character: %d...%d", start_pos, end_pos);
+    }
+
+    return lexer;
+}
+
+// Build the parser options from the arguments the `_parse_*` entry points
+// receive. The optional syntax these enable is not part of the public
+// `RBS::Parser` API, so only the private entry points pass them through.
+static rbs_parser_options_t parser_options(VALUE enable_forwarding_params) {
+    return (rbs_parser_options_t) {
+        .enable_forwarding_params = RB_TEST(enable_forwarding_params),
+    };
+}
+
+static rbs_parser_t *alloc_parser_from_buffer_with_options(VALUE buffer, int start_pos, int end_pos, rbs_parser_options_t options) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+
+    validate_position_range(string, start_pos, end_pos);
+
+    rb_encoding *encoding = rb_enc_get(string);
+    const char *encoding_name = rb_enc_name(encoding);
+
+    rbs_parser_t *parser = rbs_parser_new_with_options(
+        rbs_string_from_ruby_string(string),
+        rbs_encoding_find((const uint8_t *) encoding_name, (const uint8_t *) (encoding_name + strlen(encoding_name))),
+        start_pos,
+        end_pos,
+        options
+    );
+
+    if (parser == NULL) {
+        rb_raise(rb_eArgError, "position range starts inside a character: %d...%d", start_pos, end_pos);
+    }
+
+    return parser;
+}
+
+static rbs_parser_t *alloc_parser_from_buffer(VALUE buffer, int start_pos, int end_pos) {
+    return alloc_parser_from_buffer_with_options(buffer, start_pos, end_pos, (rbs_parser_options_t) { 0 });
+}
+
+static VALUE rbsparser_parse_type(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables, VALUE require_eof, VALUE void_allowed, VALUE self_allowed, VALUE classish_allowed) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer(buffer, FIX2INT(start_pos), FIX2INT(end_pos));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = require_eof,
+        .void_allowed = void_allowed,
+        .self_allowed = self_allowed,
+        .classish_allowed = classish_allowed
+    };
+
+    VALUE result = rb_ensure(parse_type_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE parse_method_type_try(VALUE a) {
+    struct parse_method_type_arg *arg = (struct parse_method_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    if (parser->next_token.type == pEOF) {
+        return Qnil;
+    }
+
+    rbs_method_type_t *method_type = NULL;
+    rbs_parse_method_type(parser, &method_type, RB_TEST(arg->require_eof), true);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_struct_to_ruby_value(ctx, (rbs_node_t *) method_type);
+}
+
+static VALUE rbsparser_parse_method_type(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables, VALUE require_eof, VALUE enable_forwarding_params) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer_with_options(buffer, FIX2INT(start_pos), FIX2INT(end_pos), parser_options(enable_forwarding_params));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_method_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = require_eof
+    };
+
+    VALUE result = rb_ensure(parse_method_type_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE parse_signature_try(VALUE a) {
+    struct parse_signature_arg *arg = (struct parse_signature_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    rbs_signature_t *signature = NULL;
+    rbs_parse_signature(parser, &signature);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_struct_to_ruby_value(ctx, (rbs_node_t *) signature);
+}
+
+static VALUE rbsparser_parse_signature(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE enable_forwarding_params) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer_with_options(buffer, FIX2INT(start_pos), FIX2INT(end_pos), parser_options(enable_forwarding_params));
+    struct parse_signature_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = false
+    };
+
+    VALUE result = rb_ensure(parse_signature_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+// Serialize a parsed node into a binary Ruby string using the same encoder the
+// WebAssembly build uses. These `_*_to_bytes` entry points exist so the
+// round-trip (parse -> serialize -> deserialize) can be exercised on CRuby,
+// where it can be compared against the direct C -> Ruby translation.
+static VALUE serialized_node_to_string(rbs_parser_t *parser, rbs_node_t *node) {
+    rbs_string_t bytes = rbs_serialize_node(parser->allocator, &parser->constant_pool, node);
+    return rb_str_new(bytes.start, (long) rbs_string_len(bytes));
+}
+
+static VALUE parse_type_to_bytes_try(VALUE a) {
+    struct parse_type_arg *arg = (struct parse_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    if (parser->next_token.type == pEOF) {
+        return Qnil;
+    }
+
+    rbs_node_t *type;
+    rbs_parse_type(parser, &type, RTEST(arg->void_allowed), RTEST(arg->self_allowed), RTEST(arg->classish_allowed));
+
+    raise_error_if_any(parser, arg->buffer);
+
+    if (RB_TEST(arg->require_eof)) {
+        rbs_parser_advance(parser);
+        if (parser->current_token.type != pEOF) {
+            rbs_parser_set_error(parser, parser->current_token, true, "expected a token `%s`", rbs_token_type_str(pEOF));
+            raise_error(parser->error, arg->buffer);
+        }
+    }
+
+    return serialized_node_to_string(parser, type);
+}
+
+static VALUE rbsparser_parse_type_to_bytes(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables, VALUE require_eof, VALUE void_allowed, VALUE self_allowed, VALUE classish_allowed) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer(buffer, FIX2INT(start_pos), FIX2INT(end_pos));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = require_eof,
+        .void_allowed = void_allowed,
+        .self_allowed = self_allowed,
+        .classish_allowed = classish_allowed
+    };
+
+    VALUE result = rb_ensure(parse_type_to_bytes_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE parse_method_type_to_bytes_try(VALUE a) {
+    struct parse_method_type_arg *arg = (struct parse_method_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    if (parser->next_token.type == pEOF) {
+        return Qnil;
+    }
+
+    rbs_method_type_t *method_type = NULL;
+    rbs_parse_method_type(parser, &method_type, RB_TEST(arg->require_eof), true);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    return serialized_node_to_string(parser, (rbs_node_t *) method_type);
+}
+
+static VALUE rbsparser_parse_method_type_to_bytes(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables, VALUE require_eof, VALUE enable_forwarding_params) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer_with_options(buffer, FIX2INT(start_pos), FIX2INT(end_pos), parser_options(enable_forwarding_params));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_method_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = require_eof
+    };
+
+    VALUE result = rb_ensure(parse_method_type_to_bytes_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE parse_signature_to_bytes_try(VALUE a) {
+    struct parse_signature_arg *arg = (struct parse_signature_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    rbs_signature_t *signature = NULL;
+    rbs_parse_signature(parser, &signature);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    return serialized_node_to_string(parser, (rbs_node_t *) signature);
+}
+
+static VALUE rbsparser_parse_signature_to_bytes(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE enable_forwarding_params) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer_with_options(buffer, FIX2INT(start_pos), FIX2INT(end_pos), parser_options(enable_forwarding_params));
+    struct parse_signature_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = false
+    };
+
+    VALUE result = rb_ensure(parse_signature_to_bytes_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+struct parse_type_params_arg {
+    VALUE buffer;
+    rb_encoding *encoding;
+    rbs_parser_t *parser;
+    VALUE module_type_params;
+};
+
+static VALUE parse_type_params_try(VALUE a) {
+    struct parse_type_params_arg *arg = (struct parse_type_params_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    if (parser->next_token.type == pEOF) {
+        return Qnil;
+    }
+
+    rbs_node_list_t *params = NULL;
+    rbs_parse_type_params(parser, arg->module_type_params, &params);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_node_list_to_ruby_array(ctx, params);
+}
+
+static VALUE rbsparser_parse_type_params(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE module_type_params) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer(buffer, FIX2INT(start_pos), FIX2INT(end_pos));
+    struct parse_type_params_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .module_type_params = module_type_params
+    };
+
+    VALUE result = rb_ensure(parse_type_params_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE parse_inline_leading_annotation_try(VALUE a) {
+    struct parse_type_arg *arg = (struct parse_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    rbs_ast_ruby_annotations_t *annotation = NULL;
+    bool success = rbs_parse_inline_leading_annotation(parser, &annotation);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    if (!success || annotation == NULL) {
+        return Qnil;
+    }
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_struct_to_ruby_value(ctx, (rbs_node_t *) annotation);
+}
+
+static VALUE rbsparser_parse_inline_leading_annotation(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer(buffer, FIX2INT(start_pos), FIX2INT(end_pos));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = Qfalse
+    };
+
+    VALUE result = rb_ensure(parse_inline_leading_annotation_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
 }
 
-void
-Init_rbs_extension(void)
-{
+static VALUE parse_inline_trailing_annotation_try(VALUE a) {
+    struct parse_type_arg *arg = (struct parse_type_arg *) a;
+    rbs_parser_t *parser = arg->parser;
+
+    rbs_ast_ruby_annotations_t *annotation = NULL;
+    bool success = rbs_parse_inline_trailing_annotation(parser, &annotation);
+
+    raise_error_if_any(parser, arg->buffer);
+
+    if (!success || annotation == NULL) {
+        return Qnil;
+    }
+
+    rbs_translation_context_t ctx = rbs_translation_context_create(
+        &parser->constant_pool,
+        arg->buffer,
+        arg->encoding
+    );
+
+    return rbs_struct_to_ruby_value(ctx, (rbs_node_t *) annotation);
+}
+
+static VALUE rbsparser_parse_inline_trailing_annotation(VALUE self, VALUE buffer, VALUE start_pos, VALUE end_pos, VALUE variables) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_parser_t *parser = alloc_parser_from_buffer(buffer, FIX2INT(start_pos), FIX2INT(end_pos));
+    declare_type_variables(parser, variables, buffer);
+    struct parse_type_arg arg = {
+        .buffer = buffer,
+        .encoding = encoding,
+        .parser = parser,
+        .require_eof = Qfalse
+    };
+
+    VALUE result = rb_ensure(parse_inline_trailing_annotation_try, (VALUE) &arg, ensure_free_parser, (VALUE) parser);
+
+    RB_GC_GUARD(string);
+
+    return result;
+}
+
+static VALUE rbsparser_lex(VALUE self, VALUE buffer, VALUE end_pos) {
+    VALUE string = rb_funcall(buffer, rb_intern("content"), 0);
+    StringValue(string);
+    rb_encoding *encoding = rb_enc_get(string);
+
+    rbs_allocator_t *allocator = rbs_allocator_init();
+    rbs_lexer_t *lexer = alloc_lexer_from_buffer(allocator, string, encoding, 0, FIX2INT(end_pos));
+
+    VALUE results = rb_ary_new();
+    rbs_token_t token = NullToken;
+    while (token.type != pEOF) {
+        token = rbs_lexer_next_token(lexer);
+        VALUE type = ID2SYM(rb_intern(rbs_token_type_str(token.type)));
+        VALUE location = rbs_new_location(buffer, token.range);
+        VALUE pair = rb_ary_new3(2, type, location);
+        rb_ary_push(results, pair);
+    }
+
+    rbs_allocator_free(allocator);
+    RB_GC_GUARD(string);
+
+    return results;
+}
+
+void rbs__init_parser(void) {
+    RBS_Parser = rb_define_class_under(RBS, "Parser", rb_cObject);
+    rb_gc_register_mark_object(RBS_Parser);
+
+    EMPTY_ARRAY = rb_obj_freeze(rb_ary_new());
+    rb_gc_register_mark_object(EMPTY_ARRAY);
+
+    EMPTY_HASH = rb_obj_freeze(rb_hash_new());
+    rb_gc_register_mark_object(EMPTY_HASH);
+
+    rb_define_singleton_method(RBS_Parser, "_parse_type", rbsparser_parse_type, 8);
+    rb_define_singleton_method(RBS_Parser, "_parse_method_type", rbsparser_parse_method_type, 6);
+    rb_define_singleton_method(RBS_Parser, "_parse_signature", rbsparser_parse_signature, 4);
+    rb_define_singleton_method(RBS_Parser, "_parse_type_to_bytes", rbsparser_parse_type_to_bytes, 8);
+    rb_define_singleton_method(RBS_Parser, "_parse_method_type_to_bytes", rbsparser_parse_method_type_to_bytes, 6);
+    rb_define_singleton_method(RBS_Parser, "_parse_signature_to_bytes", rbsparser_parse_signature_to_bytes, 4);
+    rb_define_singleton_method(RBS_Parser, "_parse_type_params", rbsparser_parse_type_params, 4);
+    rb_define_singleton_method(RBS_Parser, "_parse_inline_leading_annotation", rbsparser_parse_inline_leading_annotation, 4);
+    rb_define_singleton_method(RBS_Parser, "_parse_inline_trailing_annotation", rbsparser_parse_inline_trailing_annotation, 4);
+    rb_define_singleton_method(RBS_Parser, "_lex", rbsparser_lex, 2);
+}
+
+static void Deinit_rbs_extension(ruby_vm_t *_) {
+}
+
+void Init_rbs_extension(void) {
 #ifdef HAVE_RB_EXT_RACTOR_SAFE
-  rb_ext_ractor_safe(true);
+    rb_ext_ractor_safe(true);
 #endif
-  rbs__init_constants();
-  rbs__init_location();
-  rbs__init_parser();
-
-  // Calculated based on the number of unique strings used with the `INTERN` macro in `parser.c`.
-  //
-  // ```bash
-  // grep -o 'INTERN("\([^"]*\)")' ext/rbs_extension/parser.c \
-  //     | sed 's/INTERN("\(.*\)")/\1/' \
-  //     | sort -u \
-  //     | wc -l
-  // ```
-  const size_t num_uniquely_interned_strings = 26;
-  rbs_constant_pool_init(RBS_GLOBAL_CONSTANT_POOL, num_uniquely_interned_strings);
-
-  ruby_vm_at_exit(Deinit_rbs_extension);
+    rbs__init_constants();
+    rbs__init_location();
+    rbs__init_parser();
+
+    ruby_vm_at_exit(Deinit_rbs_extension);
 }

data/ext/rbs_extension/rbs_extension.h

@@ -1,31 +1,16 @@
 #include <stdbool.h>
+#include "compat.h"
 
+SUPPRESS_RUBY_HEADER_DIAGNOSTICS_BEGIN
 #include "ruby.h"
 #include "ruby/re.h"
 #include "ruby/encoding.h"
+SUPPRESS_RUBY_HEADER_DIAGNOSTICS_END
 
+#include "class_constants.h"
 #include "rbs.h"
-#include "lexer.h"
-#include "parser.h"
 
 /**
- * Receives `parserstate` and `range`, which represents a string token or symbol token, and returns a string VALUE.
- *
- *    Input token | Output string
- *    ------------+-------------
- *    "foo\\n"    | foo\n
- *    'foo'       | foo
- *    `bar`       | bar
- *    :"baz\\t"   | baz\t
- *    :'baz'      | baz
+ * RBS::Parser class
  * */
-VALUE rbs_unquote_string(parserstate *state, range rg, int offset_bytes);
-
-/**
- * Raises RBS::ParsingError on `tok` with message constructed with given `fmt`.
- *
- * ```
- * foo.rbs:11:21...11:25: Syntax error: {message}, token=`{tok source}` ({tok type})
- * ```
- * */
-PRINTF_ARGS(NORETURN(void) raise_syntax_error(parserstate *state, token tok, const char *fmt, ...), 3, 4);
+extern VALUE RBS_Parser;