[Universal parser] Decouple IMEMO from rb_ast_t

This patch removes the `VALUE flags` member from the `rb_ast_t` structure making `rb_ast_t` no longer an IMEMO object.

## Background

We are trying to make the Ruby parser generated from parse.y a universal parser that can be used by other implementations such as mruby.
To achieve this, it is necessary to exclude VALUE and IMEMO from parse.y, AST, and NODE.

## Summary (file by file)

- `rubyparser.h`
  - Remove the `VALUE flags` member from `rb_ast_t`
- `ruby_parser.c` and `internal/ruby_parser.h`
  - Use TypedData_Make_Struct VALUE which wraps `rb_ast_t` `in ast_alloc()` so that GC can manage it
    - You can retrieve `rb_ast_t` from the VALUE by `rb_ruby_ast_data_get()`
  - Change the return type of `rb_parser_compile_XXXX()` functions from `rb_ast_t *` to `VALUE`
  - rb_ruby_ast_new() which internally `calls ast_alloc()` is to create VALUE vast outside ruby_parser.c
- `iseq.c` and `vm_core.h`
  - Amend the first parameter of `rb_iseq_new_XXXX()` functions from `rb_ast_body_t *` to `VALUE`
  - This keeps the VALUE of AST on the machine stack to prevent being removed by GC
- `ast.c`
  - Almost all change is replacement `rb_ast_t *ast` with `VALUE vast` (sorry for the big diff)
  - Fix `node_memsize()`
    - Now it includes `rb_ast_local_table_link`, `tokens` and script_lines
- `compile.c`, `load.c`, `node.c`, `parse.y`, `proc.c`, `ruby.c`, `template/prelude.c.tmpl`, `vm.c` and `vm_eval.c`
  - Follow-up due to the above changes
- `imemo.{c|h}`
  - If an object with `imemo_ast` appears, considers it a bug

Co-authored-by: Nobuyoshi Nakada <nobu@ruby-lang.org>
This commit is contained in:
HASUMI Hitoshi 2024-04-16 18:42:42 +09:00 committed by Yuichiro Kaneko
parent 9b5bc8e6ea
commit 2244c58b00
18 changed files with 413 additions and 286 deletions

View file

@ -293,9 +293,11 @@ arg_error(void)
}
static rb_ast_t *
ast_new(VALUE nb)
ast_new(node_buffer_t *nb)
{
return IMEMO_NEW(rb_ast_t, imemo_ast, nb);
rb_ast_t *ast = ruby_xcalloc(1, sizeof(rb_ast_t));
ast->node_buffer = nb;
return ast;
}
static VALUE
@ -742,69 +744,95 @@ parser_compile_generic(struct ruby_parser *parser, rb_parser_lex_gets_func *lex_
return rb_parser_compile(parser->parser_params, lex_gets, fname, (rb_parser_input_data)input, start);
}
rb_ast_t*
static void
ast_free(void *ptr)
{
rb_ast_t *ast = (rb_ast_t *)ptr;
if (ast) {
rb_ast_free(ast);
}
}
static const rb_data_type_t ast_data_type = {
"AST",
{
NULL,
ast_free,
NULL, // No dsize() because this object does not appear in ObjectSpace.
},
0, 0, RUBY_TYPED_FREE_IMMEDIATELY
};
static VALUE
ast_alloc(void)
{
rb_ast_t *ast;
return TypedData_Make_Struct(0, rb_ast_t, &ast_data_type, ast);
}
VALUE
rb_parser_compile_file_path(VALUE vparser, VALUE fname, VALUE file, int start)
{
struct ruby_parser *parser;
rb_ast_t *ast;
VALUE vast = ast_alloc();
TypedData_Get_Struct(vparser, struct ruby_parser, &ruby_parser_data_type, parser);
ast = parser_compile_file_path(parser, fname, file, start);
DATA_PTR(vast) = parser_compile_file_path(parser, fname, file, start);
RB_GC_GUARD(vparser);
return ast;
return vast;
}
rb_ast_t*
VALUE
rb_parser_compile_array(VALUE vparser, VALUE fname, VALUE array, int start)
{
struct ruby_parser *parser;
rb_ast_t *ast;
VALUE vast = ast_alloc();
TypedData_Get_Struct(vparser, struct ruby_parser, &ruby_parser_data_type, parser);
ast = parser_compile_array(parser, fname, array, start);
DATA_PTR(vast) = parser_compile_array(parser, fname, array, start);
RB_GC_GUARD(vparser);
return ast;
return vast;
}
rb_ast_t*
VALUE
rb_parser_compile_generic(VALUE vparser, rb_parser_lex_gets_func *lex_gets, VALUE fname, VALUE input, int start)
{
struct ruby_parser *parser;
rb_ast_t *ast;
VALUE vast = ast_alloc();
TypedData_Get_Struct(vparser, struct ruby_parser, &ruby_parser_data_type, parser);
ast = parser_compile_generic(parser, lex_gets, fname, input, start);
DATA_PTR(vast) = parser_compile_generic(parser, lex_gets, fname, input, start);
RB_GC_GUARD(vparser);
return ast;
return vast;
}
rb_ast_t*
VALUE
rb_parser_compile_string(VALUE vparser, const char *f, VALUE s, int line)
{
struct ruby_parser *parser;
rb_ast_t *ast;
VALUE vast = ast_alloc();
TypedData_Get_Struct(vparser, struct ruby_parser, &ruby_parser_data_type, parser);
ast = parser_compile_string(parser, f, s, line);
DATA_PTR(vast) = parser_compile_string(parser, f, s, line);
RB_GC_GUARD(vparser);
return ast;
return vast;
}
rb_ast_t*
VALUE
rb_parser_compile_string_path(VALUE vparser, VALUE f, VALUE s, int line)
{
struct ruby_parser *parser;
rb_ast_t *ast;
VALUE vast = ast_alloc();
TypedData_Get_Struct(vparser, struct ruby_parser, &ruby_parser_data_type, parser);
ast = parser_compile_string_path(parser, f, s, line);
DATA_PTR(vast) = parser_compile_string_path(parser, f, s, line);
RB_GC_GUARD(vparser);
return ast;
return vast;
}
VALUE
@ -1086,3 +1114,26 @@ rb_parser_aset_script_lines_for(VALUE path, rb_parser_ary_t *lines)
script_lines = rb_parser_build_script_lines_from(lines);
rb_hash_aset(hash, path, script_lines);
}
VALUE
rb_ruby_ast_new(const NODE *const root, rb_parser_ary_t *script_lines)
{
VALUE vast = ast_alloc();
rb_ast_t *ast = DATA_PTR(vast);
ast->body = (rb_ast_body_t){
.root = root,
.frozen_string_literal = -1,
.coverage_enabled = -1,
.script_lines = script_lines
};
return vast;
}
rb_ast_t *
rb_ruby_ast_data_get(VALUE vast)
{
rb_ast_t *ast;
if (NIL_P(vast)) return NULL;
TypedData_Get_Struct(vast, rb_ast_t, &ast_data_type, ast);
return ast;
}