ruby/rubyparser.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1350 строки
33 KiB
C
Исходник Обычный вид История

#ifndef RUBY_RUBYPARSER_H
#define RUBY_RUBYPARSER_H 1
/*
* This is a header file for librubyparser interface
*/
2023-08-25 08:58:33 +03:00
#include <stdarg.h> /* for va_list */
#include <assert.h>
2023-08-25 08:58:33 +03:00
#ifdef UNIVERSAL_PARSER
#define rb_encoding const void
#define OnigCodePoint unsigned int
#include "parser_st.h"
#ifndef RUBY_RUBY_H
#include "parser_value.h"
#endif
#else
#include "ruby/encoding.h"
#endif
#ifndef FLEX_ARY_LEN
/* From internal/compilers.h */
/* A macro for defining a flexible array, like: VALUE ary[FLEX_ARY_LEN]; */
#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)
# define FLEX_ARY_LEN /* VALUE ary[]; */
#elif defined(__GNUC__) && !defined(__STRICT_ANSI__)
# define FLEX_ARY_LEN 0 /* VALUE ary[0]; */
#else
# define FLEX_ARY_LEN 1 /* VALUE ary[1]; */
#endif
#endif
#if defined(__GNUC__)
# if defined(__MINGW_PRINTF_FORMAT)
# define RUBYPARSER_ATTRIBUTE_FORMAT(string_index, argument_index) __attribute__((format(__MINGW_PRINTF_FORMAT, string_index, argument_index)))
# else
# define RUBYPARSER_ATTRIBUTE_FORMAT(string_index, argument_index) __attribute__((format(printf, string_index, argument_index)))
# endif
#elif defined(__clang__)
# define RUBYPARSER_ATTRIBUTE_FORMAT(string_index, argument_index) __attribute__((__format__(__printf__, string_index, argument_index)))
#else
# define RUBYPARSER_ATTRIBUTE_FORMAT(string_index, argument_index)
#endif
/*
* Parser String
*/
enum rb_parser_string_coderange_type {
/** The object's coderange is unclear yet. */
RB_PARSER_ENC_CODERANGE_UNKNOWN = 0,
RB_PARSER_ENC_CODERANGE_7BIT = 1,
RB_PARSER_ENC_CODERANGE_VALID = 2,
RB_PARSER_ENC_CODERANGE_BROKEN = 3
};
typedef struct rb_parser_string {
enum rb_parser_string_coderange_type coderange;
rb_encoding *enc;
/* Length of the string, not including terminating NUL character. */
long len;
/* Pointer to the contents of the string. */
char *ptr;
} rb_parser_string_t;
enum rb_parser_shareability {
rb_parser_shareable_none,
rb_parser_shareable_literal,
rb_parser_shareable_copy,
rb_parser_shareable_everything,
};
typedef void* rb_parser_input_data;
/*
* AST Node
*/
enum node_type {
NODE_SCOPE,
NODE_BLOCK,
NODE_IF,
NODE_UNLESS,
NODE_CASE,
NODE_CASE2,
NODE_CASE3,
NODE_WHEN,
NODE_IN,
NODE_WHILE,
NODE_UNTIL,
NODE_ITER,
NODE_FOR,
NODE_FOR_MASGN,
NODE_BREAK,
NODE_NEXT,
NODE_REDO,
NODE_RETRY,
NODE_BEGIN,
NODE_RESCUE,
NODE_RESBODY,
NODE_ENSURE,
NODE_AND,
NODE_OR,
NODE_MASGN,
NODE_LASGN,
NODE_DASGN,
NODE_GASGN,
NODE_IASGN,
NODE_CDECL,
NODE_CVASGN,
NODE_OP_ASGN1,
NODE_OP_ASGN2,
NODE_OP_ASGN_AND,
NODE_OP_ASGN_OR,
NODE_OP_CDECL,
NODE_CALL,
NODE_OPCALL,
NODE_FCALL,
NODE_VCALL,
NODE_QCALL,
NODE_SUPER,
NODE_ZSUPER,
NODE_LIST,
NODE_ZLIST,
NODE_HASH,
NODE_RETURN,
NODE_YIELD,
NODE_LVAR,
NODE_DVAR,
NODE_GVAR,
NODE_IVAR,
NODE_CONST,
NODE_CVAR,
NODE_NTH_REF,
NODE_BACK_REF,
NODE_MATCH,
NODE_MATCH2,
NODE_MATCH3,
2024-01-05 06:03:11 +03:00
NODE_INTEGER,
NODE_FLOAT,
NODE_RATIONAL,
NODE_IMAGINARY,
NODE_STR,
NODE_DSTR,
NODE_XSTR,
NODE_DXSTR,
NODE_EVSTR,
NODE_REGX,
NODE_DREGX,
NODE_ONCE,
NODE_ARGS,
NODE_ARGS_AUX,
NODE_OPT_ARG,
NODE_KW_ARG,
NODE_POSTARG,
NODE_ARGSCAT,
NODE_ARGSPUSH,
NODE_SPLAT,
NODE_BLOCK_PASS,
NODE_DEFN,
NODE_DEFS,
NODE_ALIAS,
NODE_VALIAS,
NODE_UNDEF,
NODE_CLASS,
NODE_MODULE,
NODE_SCLASS,
NODE_COLON2,
NODE_COLON3,
NODE_DOT2,
NODE_DOT3,
NODE_FLIP2,
NODE_FLIP3,
NODE_SELF,
NODE_NIL,
NODE_TRUE,
NODE_FALSE,
NODE_ERRINFO,
NODE_DEFINED,
NODE_POSTEXE,
NODE_SYM,
NODE_DSYM,
NODE_ATTRASGN,
NODE_LAMBDA,
NODE_ARYPTN,
NODE_HSHPTN,
NODE_FNDPTN,
NODE_ERROR,
NODE_LINE,
NODE_FILE,
NODE_ENCODING,
NODE_LAST
};
typedef struct rb_ast_id_table {
int size;
ID ids[FLEX_ARY_LEN];
} rb_ast_id_table_t;
typedef struct rb_code_position_struct {
int lineno;
int column;
} rb_code_position_t;
typedef struct rb_code_location_struct {
rb_code_position_t beg_pos;
rb_code_position_t end_pos;
} rb_code_location_t;
#define YYLTYPE rb_code_location_t
#define YYLTYPE_IS_DECLARED 1
typedef struct rb_parser_ast_token {
int id;
const char *type_name;
rb_parser_string_t *str;
rb_code_location_t loc;
} rb_parser_ast_token_t;
/*
* Array-like object for parser
*/
[Universal parser] DeVALUE of p->debug_lines and ast->body.script_lines This patch is part of universal parser work. ## Summary - Decouple VALUE from members below: - `(struct parser_params *)->debug_lines` - `(rb_ast_t *)->body.script_lines` - Instead, they are now `rb_parser_ary_t *` - They can also be a `(VALUE)FIXNUM` as before to hold line count - `ISEQ_BODY(iseq)->variable.script_lines` remains VALUE - In order to do this, - Add `VALUE script_lines` param to `rb_iseq_new_with_opt()` - Introduce `rb_parser_build_script_lines_from()` to convert `rb_parser_ary_t *` into `VALUE` ## Other details - Extend `rb_parser_ary_t *`. It previously could only store `rb_parser_ast_token *`, now can store script_lines, too - Change tactics of building the top-level `SCRIPT_LINES__` in `yycompile0()` - Before: While parsing, each line of the script is added to `SCRIPT_LINES__[path]` - After: After `yyparse(p)`, `SCRIPT_LINES__[path]` will be built from `p->debug_lines` - Remove the second parameter of `rb_parser_set_script_lines()` to make it simple - Introduce `script_lines_free()` to be called from `rb_ast_free()` because the GC no longer takes care of the script_lines - Introduce `rb_parser_string_deep_copy()` in parse.y to maintain script_lines when `rb_ruby_parser_free()` called - With regard to this, please see *Future tasks* below ## Future tasks - Decouple IMEMO from `rb_ast_t *` - This lifts the five-members-restriction of Ruby object, - So we will be able to move the ownership of the `lex.string_buffer` from parser to AST - Then we remove `rb_parser_string_deep_copy()` to make the whole thing simple
2024-03-28 04:26:42 +03:00
typedef void* rb_parser_ary_data;
enum rb_parser_ary_data_type {
PARSER_ARY_DATA_AST_TOKEN = 1,
PARSER_ARY_DATA_SCRIPT_LINE,
PARSER_ARY_DATA_NODE
[Universal parser] DeVALUE of p->debug_lines and ast->body.script_lines This patch is part of universal parser work. ## Summary - Decouple VALUE from members below: - `(struct parser_params *)->debug_lines` - `(rb_ast_t *)->body.script_lines` - Instead, they are now `rb_parser_ary_t *` - They can also be a `(VALUE)FIXNUM` as before to hold line count - `ISEQ_BODY(iseq)->variable.script_lines` remains VALUE - In order to do this, - Add `VALUE script_lines` param to `rb_iseq_new_with_opt()` - Introduce `rb_parser_build_script_lines_from()` to convert `rb_parser_ary_t *` into `VALUE` ## Other details - Extend `rb_parser_ary_t *`. It previously could only store `rb_parser_ast_token *`, now can store script_lines, too - Change tactics of building the top-level `SCRIPT_LINES__` in `yycompile0()` - Before: While parsing, each line of the script is added to `SCRIPT_LINES__[path]` - After: After `yyparse(p)`, `SCRIPT_LINES__[path]` will be built from `p->debug_lines` - Remove the second parameter of `rb_parser_set_script_lines()` to make it simple - Introduce `script_lines_free()` to be called from `rb_ast_free()` because the GC no longer takes care of the script_lines - Introduce `rb_parser_string_deep_copy()` in parse.y to maintain script_lines when `rb_ruby_parser_free()` called - With regard to this, please see *Future tasks* below ## Future tasks - Decouple IMEMO from `rb_ast_t *` - This lifts the five-members-restriction of Ruby object, - So we will be able to move the ownership of the `lex.string_buffer` from parser to AST - Then we remove `rb_parser_string_deep_copy()` to make the whole thing simple
2024-03-28 04:26:42 +03:00
};
typedef struct rb_parser_ary {
[Universal parser] DeVALUE of p->debug_lines and ast->body.script_lines This patch is part of universal parser work. ## Summary - Decouple VALUE from members below: - `(struct parser_params *)->debug_lines` - `(rb_ast_t *)->body.script_lines` - Instead, they are now `rb_parser_ary_t *` - They can also be a `(VALUE)FIXNUM` as before to hold line count - `ISEQ_BODY(iseq)->variable.script_lines` remains VALUE - In order to do this, - Add `VALUE script_lines` param to `rb_iseq_new_with_opt()` - Introduce `rb_parser_build_script_lines_from()` to convert `rb_parser_ary_t *` into `VALUE` ## Other details - Extend `rb_parser_ary_t *`. It previously could only store `rb_parser_ast_token *`, now can store script_lines, too - Change tactics of building the top-level `SCRIPT_LINES__` in `yycompile0()` - Before: While parsing, each line of the script is added to `SCRIPT_LINES__[path]` - After: After `yyparse(p)`, `SCRIPT_LINES__[path]` will be built from `p->debug_lines` - Remove the second parameter of `rb_parser_set_script_lines()` to make it simple - Introduce `script_lines_free()` to be called from `rb_ast_free()` because the GC no longer takes care of the script_lines - Introduce `rb_parser_string_deep_copy()` in parse.y to maintain script_lines when `rb_ruby_parser_free()` called - With regard to this, please see *Future tasks* below ## Future tasks - Decouple IMEMO from `rb_ast_t *` - This lifts the five-members-restriction of Ruby object, - So we will be able to move the ownership of the `lex.string_buffer` from parser to AST - Then we remove `rb_parser_string_deep_copy()` to make the whole thing simple
2024-03-28 04:26:42 +03:00
enum rb_parser_ary_data_type data_type;
rb_parser_ary_data *data;
long len; // current size
long capa; // capacity
} rb_parser_ary_t;
/* Header part of AST Node */
typedef struct RNode {
VALUE flags;
rb_code_location_t nd_loc;
int node_id;
} NODE;
typedef struct RNode_SCOPE {
NODE node;
rb_ast_id_table_t *nd_tbl;
struct RNode *nd_body;
struct RNode_ARGS *nd_args;
} rb_node_scope_t;
typedef struct RNode_BLOCK {
NODE node;
struct RNode *nd_head;
struct RNode *nd_end;
struct RNode *nd_next;
} rb_node_block_t;
typedef struct RNode_IF {
NODE node;
struct RNode *nd_cond;
struct RNode *nd_body;
struct RNode *nd_else;
} rb_node_if_t;
typedef struct RNode_UNLESS {
NODE node;
struct RNode *nd_cond;
struct RNode *nd_body;
struct RNode *nd_else;
rb_code_location_t keyword_loc;
rb_code_location_t then_keyword_loc;
rb_code_location_t end_keyword_loc;
} rb_node_unless_t;
typedef struct RNode_CASE {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
2024-09-21 18:13:16 +03:00
rb_code_location_t case_keyword_loc;
rb_code_location_t end_keyword_loc;
} rb_node_case_t;
typedef struct RNode_CASE2 {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
2024-09-21 18:17:52 +03:00
rb_code_location_t case_keyword_loc;
rb_code_location_t end_keyword_loc;
} rb_node_case2_t;
typedef struct RNode_CASE3 {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
2024-09-21 18:22:59 +03:00
rb_code_location_t case_keyword_loc;
rb_code_location_t end_keyword_loc;
} rb_node_case3_t;
typedef struct RNode_WHEN {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
struct RNode *nd_next;
2024-09-05 12:41:10 +03:00
rb_code_location_t keyword_loc;
rb_code_location_t then_keyword_loc;
} rb_node_when_t;
typedef struct RNode_IN {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
struct RNode *nd_next;
} rb_node_in_t;
2024-07-29 09:43:20 +03:00
typedef struct RNode_LOOP {
NODE node;
struct RNode *nd_cond;
struct RNode *nd_body;
long nd_state;
rb_code_location_t keyword_loc;
rb_code_location_t closing_loc;
2024-07-29 09:43:20 +03:00
} rb_node_while_t, rb_node_until_t;
typedef struct RNode_ITER {
NODE node;
struct RNode *nd_body;
struct RNode *nd_iter;
2024-07-29 09:43:20 +03:00
} rb_node_iter_t, rb_node_for_t;
typedef struct RNode_FOR_MASGN {
NODE node;
struct RNode *nd_var;
} rb_node_for_masgn_t;
2024-07-29 09:43:20 +03:00
typedef struct RNode_EXITS {
NODE node;
2023-10-05 07:05:24 +03:00
struct RNode *nd_chain;
struct RNode *nd_stts;
rb_code_location_t keyword_loc;
2024-07-29 09:43:20 +03:00
} rb_node_exits_t, rb_node_break_t, rb_node_next_t, rb_node_redo_t;
typedef struct RNode_RETRY {
NODE node;
} rb_node_retry_t;
typedef struct RNode_BEGIN {
NODE node;
struct RNode *nd_body;
} rb_node_begin_t;
typedef struct RNode_RESCUE {
NODE node;
struct RNode *nd_head;
struct RNode *nd_resq;
struct RNode *nd_else;
} rb_node_rescue_t;
typedef struct RNode_RESBODY {
NODE node;
struct RNode *nd_args;
struct RNode *nd_exc_var;
struct RNode *nd_body;
struct RNode *nd_next;
} rb_node_resbody_t;
typedef struct RNode_ENSURE {
NODE node;
struct RNode *nd_head;
struct RNode *nd_ensr;
} rb_node_ensure_t;
2024-07-29 09:43:20 +03:00
typedef struct {
NODE node;
struct RNode *nd_1st;
struct RNode *nd_2nd;
rb_code_location_t operator_loc;
2024-07-29 09:43:20 +03:00
} rb_node_and_t, rb_node_or_t;
typedef struct RNode_MASGN {
NODE node;
struct RNode *nd_head;
struct RNode *nd_value;
struct RNode *nd_args;
} rb_node_masgn_t;
typedef struct RNode_LASGN {
NODE node;
ID nd_vid;
struct RNode *nd_value;
} rb_node_lasgn_t;
typedef struct RNode_DASGN {
NODE node;
ID nd_vid;
struct RNode *nd_value;
} rb_node_dasgn_t;
typedef struct RNode_GASGN {
NODE node;
ID nd_vid;
struct RNode *nd_value;
} rb_node_gasgn_t;
typedef struct RNode_IASGN {
NODE node;
ID nd_vid;
struct RNode *nd_value;
} rb_node_iasgn_t;
typedef struct RNode_CDECL {
NODE node;
ID nd_vid;
struct RNode *nd_value;
struct RNode *nd_else;
enum rb_parser_shareability shareability;
} rb_node_cdecl_t;
typedef struct RNode_CVASGN {
NODE node;
ID nd_vid;
struct RNode *nd_value;
} rb_node_cvasgn_t;
typedef struct RNode_OP_ASGN1 {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_index;
struct RNode *nd_rvalue;
2024-09-26 20:01:08 +03:00
rb_code_location_t call_operator_loc;
rb_code_location_t opening_loc;
rb_code_location_t closing_loc;
rb_code_location_t binary_operator_loc;
} rb_node_op_asgn1_t;
typedef struct RNode_OP_ASGN2 {
NODE node;
struct RNode *nd_recv;
struct RNode *nd_value;
ID nd_vid;
ID nd_mid;
bool nd_aid;
2024-09-26 20:32:27 +03:00
rb_code_location_t call_operator_loc;
rb_code_location_t message_loc;
rb_code_location_t binary_operator_loc;
} rb_node_op_asgn2_t;
typedef struct RNode_OP_ASGN_AND {
NODE node;
struct RNode *nd_head;
struct RNode *nd_value;
} rb_node_op_asgn_and_t;
typedef struct RNode_OP_ASGN_OR {
NODE node;
struct RNode *nd_head;
struct RNode *nd_value;
} rb_node_op_asgn_or_t;
typedef struct RNode_OP_CDECL {
NODE node;
struct RNode *nd_head;
struct RNode *nd_value;
ID nd_aid;
enum rb_parser_shareability shareability;
} rb_node_op_cdecl_t;
typedef struct RNode_CALL {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_args;
} rb_node_call_t;
typedef struct RNode_OPCALL {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_args;
} rb_node_opcall_t;
typedef struct RNode_FCALL {
NODE node;
ID nd_mid;
struct RNode *nd_args;
} rb_node_fcall_t;
typedef struct RNode_VCALL {
NODE node;
ID nd_mid;
} rb_node_vcall_t;
typedef struct RNode_QCALL {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_args;
} rb_node_qcall_t;
typedef struct RNode_SUPER {
NODE node;
struct RNode *nd_args;
} rb_node_super_t;
typedef struct RNode_ZSUPER {
NODE node;
} rb_node_zsuper_t;
/*
Structure of LIST:
LIST +--> LIST
* head --> element | * head
* alen (length of list) | * nd_end (point to the last LIST)
* next -----------------+ * next
*/
typedef struct RNode_LIST {
NODE node;
struct RNode *nd_head; /* element */
union {
long nd_alen;
struct RNode *nd_end; /* Second list node has this structure */
} as;
struct RNode *nd_next; /* next list node */
} rb_node_list_t;
typedef struct RNode_ZLIST {
NODE node;
} rb_node_zlist_t;
typedef struct RNode_HASH {
NODE node;
struct RNode *nd_head;
long nd_brace;
} rb_node_hash_t;
typedef struct RNode_RETURN {
NODE node;
struct RNode *nd_stts;
rb_code_location_t keyword_loc;
} rb_node_return_t;
typedef struct RNode_YIELD {
NODE node;
struct RNode *nd_head;
} rb_node_yield_t;
typedef struct RNode_LVAR {
NODE node;
ID nd_vid;
} rb_node_lvar_t;
typedef struct RNode_DVAR {
NODE node;
ID nd_vid;
} rb_node_dvar_t;
typedef struct RNode_GVAR {
NODE node;
ID nd_vid;
} rb_node_gvar_t;
typedef struct RNode_IVAR {
NODE node;
ID nd_vid;
} rb_node_ivar_t;
typedef struct RNode_CONST {
NODE node;
ID nd_vid;
} rb_node_const_t;
typedef struct RNode_CVAR {
NODE node;
ID nd_vid;
} rb_node_cvar_t;
typedef struct RNode_NTH_REF {
NODE node;
long nd_nth;
} rb_node_nth_ref_t;
typedef struct RNode_BACK_REF {
NODE node;
long nd_nth;
} rb_node_back_ref_t;
typedef struct RNode_MATCH2 {
NODE node;
struct RNode *nd_recv;
struct RNode *nd_value;
struct RNode *nd_args;
} rb_node_match2_t;
typedef struct RNode_MATCH3 {
NODE node;
struct RNode *nd_recv;
struct RNode *nd_value;
} rb_node_match3_t;
2024-01-05 06:03:11 +03:00
typedef struct RNode_INTEGER {
NODE node;
char *val;
2024-01-05 06:03:11 +03:00
int minus;
int base;
} rb_node_integer_t;
typedef struct RNode_FLOAT {
NODE node;
char *val;
2024-01-05 06:03:11 +03:00
int minus;
} rb_node_float_t;
typedef struct RNode_RATIONAL {
NODE node;
char *val;
2024-01-05 06:03:11 +03:00
int minus;
int base;
int seen_point;
} rb_node_rational_t;
enum rb_numeric_type {
integer_literal,
float_literal,
rational_literal
};
typedef struct RNode_IMAGINARY {
NODE node;
char *val;
2024-01-05 06:03:11 +03:00
int minus;
int base;
int seen_point;
enum rb_numeric_type type;
} rb_node_imaginary_t;
typedef struct RNode_STR {
NODE node;
struct rb_parser_string *string;
} rb_node_str_t;
2024-07-29 09:43:20 +03:00
/* NODE_DSTR, NODE_DXSTR, NODE_DREGX, NODE_DSYM */
typedef struct RNode_DSTR {
NODE node;
struct rb_parser_string *string;
union {
long nd_alen;
long nd_cflag;
struct RNode *nd_end; /* Second dstr node has this structure. See also RNode_LIST */
} as;
struct RNode_LIST *nd_next;
} rb_node_dstr_t;
typedef rb_node_str_t rb_node_xstr_t;
typedef rb_node_dstr_t rb_node_dxstr_t;
typedef struct RNode_EVSTR {
NODE node;
struct RNode *nd_body;
} rb_node_evstr_t;
2024-07-29 09:43:20 +03:00
typedef struct RNode_REGX { /* also RNode_MATCH */
NODE node;
struct rb_parser_string *string;
int options;
2024-07-29 09:43:20 +03:00
} rb_node_regx_t, rb_node_match_t;
typedef rb_node_dstr_t rb_node_dregx_t;
typedef struct RNode_ONCE {
NODE node;
struct RNode *nd_body;
} rb_node_once_t;
struct rb_args_info {
NODE *pre_init;
NODE *post_init;
int pre_args_num; /* count of mandatory pre-arguments */
int post_args_num; /* count of mandatory post-arguments */
ID first_post_arg;
ID rest_arg;
ID block_arg;
struct RNode_KW_ARG *kw_args;
NODE *kw_rest_arg;
struct RNode_OPT_ARG *opt_args;
unsigned int no_kwarg: 1;
unsigned int ruby2_keywords: 1;
unsigned int forwarding: 1;
};
typedef struct RNode_ARGS {
NODE node;
struct rb_args_info nd_ainfo;
} rb_node_args_t;
typedef struct RNode_ARGS_AUX {
NODE node;
ID nd_pid;
int nd_plen;
struct RNode *nd_next;
} rb_node_args_aux_t;
typedef struct RNode_OPT_ARG {
NODE node;
struct RNode *nd_body;
struct RNode_OPT_ARG *nd_next;
} rb_node_opt_arg_t;
typedef struct RNode_KW_ARG {
NODE node;
struct RNode *nd_body;
struct RNode_KW_ARG *nd_next;
} rb_node_kw_arg_t;
typedef struct RNode_POSTARG {
NODE node;
struct RNode *nd_1st;
struct RNode *nd_2nd;
} rb_node_postarg_t;
typedef struct RNode_ARGSCAT {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
} rb_node_argscat_t;
typedef struct RNode_ARGSPUSH {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
} rb_node_argspush_t;
typedef struct RNode_SPLAT {
NODE node;
struct RNode *nd_head;
2024-09-24 14:05:12 +03:00
rb_code_location_t operator_loc;
} rb_node_splat_t;
typedef struct RNode_BLOCK_PASS {
NODE node;
struct RNode *nd_head;
struct RNode *nd_body;
Optimized forwarding callers and callees This patch optimizes forwarding callers and callees. It only optimizes methods that only take `...` as their parameter, and then pass `...` to other calls. Calls it optimizes look like this: ```ruby def bar(a) = a def foo(...) = bar(...) # optimized foo(123) ``` ```ruby def bar(a) = a def foo(...) = bar(1, 2, ...) # optimized foo(123) ``` ```ruby def bar(*a) = a def foo(...) list = [1, 2] bar(*list, ...) # optimized end foo(123) ``` All variants of the above but using `super` are also optimized, including a bare super like this: ```ruby def foo(...) super end ``` This patch eliminates intermediate allocations made when calling methods that accept `...`. We can observe allocation elimination like this: ```ruby def m x = GC.stat(:total_allocated_objects) yield GC.stat(:total_allocated_objects) - x end def bar(a) = a def foo(...) = bar(...) def test m { foo(123) } end test p test # allocates 1 object on master, but 0 objects with this patch ``` ```ruby def bar(a, b:) = a + b def foo(...) = bar(...) def test m { foo(1, b: 2) } end test p test # allocates 2 objects on master, but 0 objects with this patch ``` How does it work? ----------------- This patch works by using a dynamic stack size when passing forwarded parameters to callees. The caller's info object (known as the "CI") contains the stack size of the parameters, so we pass the CI object itself as a parameter to the callee. When forwarding parameters, the forwarding ISeq uses the caller's CI to determine how much stack to copy, then copies the caller's stack before calling the callee. The CI at the forwarded call site is adjusted using information from the caller's CI. I think this description is kind of confusing, so let's walk through an example with code. ```ruby def delegatee(a, b) = a + b def delegator(...) delegatee(...) # CI2 (FORWARDING) end def caller delegator(1, 2) # CI1 (argc: 2) end ``` Before we call the delegator method, the stack looks like this: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | 5| delegatee(...) # CI2 (FORWARDING) | 6| end | 7| | 8| def caller | -> 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The ISeq for `delegator` is tagged as "forwardable", so when `caller` calls in to `delegator`, it writes `CI1` on to the stack as a local variable for the `delegator` method. The `delegator` method has a special local called `...` that holds the caller's CI object. Here is the ISeq disasm fo `delegator`: ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` The local called `...` will contain the caller's CI: CI1. Here is the stack when we enter `delegator`: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 -> 4| # | CI1 (argc: 2) 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The CI at `delegatee` on line 5 is tagged as "FORWARDING", so it knows to memcopy the caller's stack before calling `delegatee`. In this case, it will memcopy self, 1, and 2 to the stack before calling `delegatee`. It knows how much memory to copy from the caller because `CI1` contains stack size information (argc: 2). Before executing the `send` instruction, we push `...` on the stack. The `send` instruction pops `...`, and because it is tagged with `FORWARDING`, it knows to memcopy (using the information in the CI it just popped): ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` Instruction 001 puts the caller's CI on the stack. `send` is tagged with FORWARDING, so it reads the CI and _copies_ the callers stack to this stack: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | CI1 (argc: 2) -> 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | self 9| delegator(1, 2) # CI1 (argc: 2) | 1 10| end | 2 ``` The "FORWARDING" call site combines information from CI1 with CI2 in order to support passing other values in addition to the `...` value, as well as perfectly forward splat args, kwargs, etc. Since we're able to copy the stack from `caller` in to `delegator`'s stack, we can avoid allocating objects. I want to do this to eliminate object allocations for delegate methods. My long term goal is to implement `Class#new` in Ruby and it uses `...`. I was able to implement `Class#new` in Ruby [here](https://github.com/ruby/ruby/pull/9289). If we adopt the technique in this patch, then we can optimize allocating objects that take keyword parameters for `initialize`. For example, this code will allocate 2 objects: one for `SomeObject`, and one for the kwargs: ```ruby SomeObject.new(foo: 1) ``` If we combine this technique, plus implement `Class#new` in Ruby, then we can reduce allocations for this common operation. Co-Authored-By: John Hawthorn <john@hawthorn.email> Co-Authored-By: Alan Wu <XrXr@users.noreply.github.com>
2024-04-15 20:48:53 +03:00
unsigned int forwarding: 1;
rb_code_location_t operator_loc;
} rb_node_block_pass_t;
typedef struct RNode_DEFN {
NODE node;
ID nd_mid;
struct RNode *nd_defn;
} rb_node_defn_t;
typedef struct RNode_DEFS {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_defn;
} rb_node_defs_t;
typedef struct RNode_ALIAS {
NODE node;
struct RNode *nd_1st;
struct RNode *nd_2nd;
2024-09-03 10:12:30 +03:00
rb_code_location_t keyword_loc;
} rb_node_alias_t;
typedef struct RNode_VALIAS {
NODE node;
ID nd_alias;
ID nd_orig;
rb_code_location_t keyword_loc;
} rb_node_valias_t;
typedef struct RNode_UNDEF {
NODE node;
rb_parser_ary_t *nd_undefs;
2024-09-03 11:53:55 +03:00
rb_code_location_t keyword_loc;
} rb_node_undef_t;
typedef struct RNode_CLASS {
NODE node;
struct RNode *nd_cpath;
struct RNode *nd_body;
struct RNode *nd_super;
} rb_node_class_t;
typedef struct RNode_MODULE {
NODE node;
struct RNode *nd_cpath;
struct RNode *nd_body;
} rb_node_module_t;
typedef struct RNode_SCLASS {
NODE node;
struct RNode *nd_recv;
struct RNode *nd_body;
} rb_node_sclass_t;
typedef struct RNode_COLON2 {
NODE node;
struct RNode *nd_head;
ID nd_mid;
} rb_node_colon2_t;
typedef struct RNode_COLON3 {
NODE node;
ID nd_mid;
} rb_node_colon3_t;
2024-07-29 09:43:20 +03:00
/* NODE_DOT2, NODE_DOT3, NODE_FLIP2, NODE_FLIP3 */
typedef struct RNode_DOTS {
NODE node;
struct RNode *nd_beg;
struct RNode *nd_end;
2024-07-29 09:43:20 +03:00
} rb_node_dot2_t, rb_node_dot3_t, rb_node_flip2_t, rb_node_flip3_t;
typedef struct RNode_SELF {
NODE node;
long nd_state; /* Default 1. See NEW_SELF. */
} rb_node_self_t;
typedef struct RNode_NIL {
NODE node;
} rb_node_nil_t;
typedef struct RNode_TRUE {
NODE node;
} rb_node_true_t;
typedef struct RNode_FALSE {
NODE node;
} rb_node_false_t;
typedef struct RNode_ERRINFO {
NODE node;
} rb_node_errinfo_t;
typedef struct RNode_DEFINED {
NODE node;
struct RNode *nd_head;
} rb_node_defined_t;
typedef struct RNode_POSTEXE {
NODE node;
struct RNode *nd_body;
} rb_node_postexe_t;
typedef struct RNode_SYM {
NODE node;
struct rb_parser_string *string;
} rb_node_sym_t;
typedef rb_node_dstr_t rb_node_dsym_t;
typedef struct RNode_ATTRASGN {
NODE node;
struct RNode *nd_recv;
ID nd_mid;
struct RNode *nd_args;
} rb_node_attrasgn_t;
typedef struct RNode_LAMBDA {
NODE node;
struct RNode *nd_body;
} rb_node_lambda_t;
typedef struct RNode_ARYPTN {
NODE node;
struct RNode *nd_pconst;
NODE *pre_args;
NODE *rest_arg;
NODE *post_args;
} rb_node_aryptn_t;
typedef struct RNode_HSHPTN {
NODE node;
struct RNode *nd_pconst;
struct RNode *nd_pkwargs;
struct RNode *nd_pkwrestarg;
} rb_node_hshptn_t;
typedef struct RNode_FNDPTN {
NODE node;
struct RNode *nd_pconst;
NODE *pre_rest_arg;
NODE *args;
NODE *post_rest_arg;
} rb_node_fndptn_t;
typedef struct RNode_LINE {
NODE node;
} rb_node_line_t;
typedef struct RNode_FILE {
NODE node;
struct rb_parser_string *path;
} rb_node_file_t;
typedef struct RNode_ENCODING {
NODE node;
rb_encoding *enc;
} rb_node_encoding_t;
typedef struct RNode_ERROR {
NODE node;
} rb_node_error_t;
#define RNODE(obj) ((NODE *)(obj))
#define RNODE_SCOPE(node) ((rb_node_scope_t *)(node))
#define RNODE_BLOCK(node) ((rb_node_block_t *)(node))
#define RNODE_IF(node) ((rb_node_if_t *)(node))
#define RNODE_UNLESS(node) ((rb_node_unless_t *)(node))
#define RNODE_CASE(node) ((rb_node_case_t *)(node))
#define RNODE_CASE2(node) ((rb_node_case2_t *)(node))
#define RNODE_CASE3(node) ((rb_node_case3_t *)(node))
#define RNODE_WHEN(node) ((rb_node_when_t *)(node))
#define RNODE_IN(node) ((rb_node_in_t *)(node))
#define RNODE_WHILE(node) ((rb_node_while_t *)(node))
#define RNODE_UNTIL(node) ((rb_node_until_t *)(node))
#define RNODE_ITER(node) ((rb_node_iter_t *)(node))
#define RNODE_FOR(node) ((rb_node_for_t *)(node))
#define RNODE_FOR_MASGN(node) ((rb_node_for_masgn_t *)(node))
#define RNODE_BREAK(node) ((rb_node_break_t *)(node))
#define RNODE_NEXT(node) ((rb_node_next_t *)(node))
#define RNODE_REDO(node) ((rb_node_redo_t *)(node))
#define RNODE_RETRY(node) ((rb_node_retry_t *)(node))
#define RNODE_BEGIN(node) ((rb_node_begin_t *)(node))
#define RNODE_RESCUE(node) ((rb_node_rescue_t *)(node))
#define RNODE_RESBODY(node) ((rb_node_resbody_t *)(node))
#define RNODE_ENSURE(node) ((rb_node_ensure_t *)(node))
#define RNODE_AND(node) ((rb_node_and_t *)(node))
#define RNODE_OR(node) ((rb_node_or_t *)(node))
#define RNODE_MASGN(node) ((rb_node_masgn_t *)(node))
#define RNODE_LASGN(node) ((rb_node_lasgn_t *)(node))
#define RNODE_DASGN(node) ((rb_node_dasgn_t *)(node))
#define RNODE_GASGN(node) ((rb_node_gasgn_t *)(node))
#define RNODE_IASGN(node) ((rb_node_iasgn_t *)(node))
#define RNODE_CDECL(node) ((rb_node_cdecl_t *)(node))
#define RNODE_CVASGN(node) ((rb_node_cvasgn_t *)(node))
#define RNODE_OP_ASGN1(node) ((rb_node_op_asgn1_t *)(node))
#define RNODE_OP_ASGN2(node) ((rb_node_op_asgn2_t *)(node))
#define RNODE_OP_ASGN_AND(node) ((rb_node_op_asgn_and_t *)(node))
#define RNODE_OP_ASGN_OR(node) ((rb_node_op_asgn_or_t *)(node))
#define RNODE_OP_CDECL(node) ((rb_node_op_cdecl_t *)(node))
#define RNODE_CALL(node) ((rb_node_call_t *)(node))
#define RNODE_OPCALL(node) ((rb_node_opcall_t *)(node))
#define RNODE_FCALL(node) ((rb_node_fcall_t *)(node))
#define RNODE_VCALL(node) ((rb_node_vcall_t *)(node))
#define RNODE_QCALL(node) ((rb_node_qcall_t *)(node))
#define RNODE_SUPER(node) ((rb_node_super_t *)(node))
#define RNODE_ZSUPER(node) ((rb_node_zsuper_t *)(node))
#define RNODE_LIST(node) ((rb_node_list_t *)(node))
#define RNODE_ZLIST(node) ((rb_node_zlist_t *)(node))
#define RNODE_HASH(node) ((rb_node_hash_t *)(node))
#define RNODE_RETURN(node) ((rb_node_return_t *)(node))
#define RNODE_YIELD(node) ((rb_node_yield_t *)(node))
#define RNODE_LVAR(node) ((rb_node_lvar_t *)(node))
#define RNODE_DVAR(node) ((rb_node_dvar_t *)(node))
#define RNODE_GVAR(node) ((rb_node_gvar_t *)(node))
#define RNODE_IVAR(node) ((rb_node_ivar_t *)(node))
#define RNODE_CONST(node) ((rb_node_const_t *)(node))
#define RNODE_CVAR(node) ((rb_node_cvar_t *)(node))
#define RNODE_NTH_REF(node) ((rb_node_nth_ref_t *)(node))
#define RNODE_BACK_REF(node) ((rb_node_back_ref_t *)(node))
#define RNODE_MATCH(node) ((rb_node_match_t *)(node))
#define RNODE_MATCH2(node) ((rb_node_match2_t *)(node))
#define RNODE_MATCH3(node) ((rb_node_match3_t *)(node))
#define RNODE_INTEGER(node) ((rb_node_integer_t *)(node))
#define RNODE_FLOAT(node) ((rb_node_float_t *)(node))
#define RNODE_RATIONAL(node) ((rb_node_rational_t *)(node))
#define RNODE_IMAGINARY(node) ((rb_node_imaginary_t *)(node))
#define RNODE_STR(node) ((rb_node_str_t *)(node))
#define RNODE_DSTR(node) ((rb_node_dstr_t *)(node))
#define RNODE_XSTR(node) ((rb_node_xstr_t *)(node))
#define RNODE_DXSTR(node) ((rb_node_dxstr_t *)(node))
#define RNODE_EVSTR(node) ((rb_node_evstr_t *)(node))
#define RNODE_REGX(node) ((rb_node_regx_t *)(node))
#define RNODE_DREGX(node) ((rb_node_dregx_t *)(node))
#define RNODE_ONCE(node) ((rb_node_once_t *)(node))
#define RNODE_ARGS(node) ((rb_node_args_t *)(node))
#define RNODE_ARGS_AUX(node) ((rb_node_args_aux_t *)(node))
#define RNODE_OPT_ARG(node) ((rb_node_opt_arg_t *)(node))
#define RNODE_KW_ARG(node) ((rb_node_kw_arg_t *)(node))
#define RNODE_POSTARG(node) ((rb_node_postarg_t *)(node))
#define RNODE_ARGSCAT(node) ((rb_node_argscat_t *)(node))
#define RNODE_ARGSPUSH(node) ((rb_node_argspush_t *)(node))
#define RNODE_SPLAT(node) ((rb_node_splat_t *)(node))
#define RNODE_BLOCK_PASS(node) ((rb_node_block_pass_t *)(node))
#define RNODE_DEFN(node) ((rb_node_defn_t *)(node))
#define RNODE_DEFS(node) ((rb_node_defs_t *)(node))
#define RNODE_ALIAS(node) ((rb_node_alias_t *)(node))
#define RNODE_VALIAS(node) ((rb_node_valias_t *)(node))
#define RNODE_UNDEF(node) ((rb_node_undef_t *)(node))
#define RNODE_CLASS(node) ((rb_node_class_t *)(node))
#define RNODE_MODULE(node) ((rb_node_module_t *)(node))
#define RNODE_SCLASS(node) ((rb_node_sclass_t *)(node))
#define RNODE_COLON2(node) ((rb_node_colon2_t *)(node))
#define RNODE_COLON3(node) ((rb_node_colon3_t *)(node))
#define RNODE_DOT2(node) ((rb_node_dot2_t *)(node))
#define RNODE_DOT3(node) ((rb_node_dot3_t *)(node))
#define RNODE_FLIP2(node) ((rb_node_flip2_t *)(node))
#define RNODE_FLIP3(node) ((rb_node_flip3_t *)(node))
#define RNODE_SELF(node) ((rb_node_self_t *)(node))
#define RNODE_NIL(node) ((rb_node_nil_t *)(node))
#define RNODE_TRUE(node) ((rb_node_true_t *)(node))
#define RNODE_FALSE(node) ((rb_node_false_t *)(node))
#define RNODE_ERRINFO(node) ((rb_node_errinfo_t *)(node))
#define RNODE_DEFINED(node) ((rb_node_defined_t *)(node))
#define RNODE_POSTEXE(node) ((rb_node_postexe_t *)(node))
#define RNODE_SYM(node) ((rb_node_sym_t *)(node))
#define RNODE_DSYM(node) ((rb_node_dsym_t *)(node))
#define RNODE_ATTRASGN(node) ((rb_node_attrasgn_t *)(node))
#define RNODE_LAMBDA(node) ((rb_node_lambda_t *)(node))
#define RNODE_ARYPTN(node) ((rb_node_aryptn_t *)(node))
#define RNODE_HSHPTN(node) ((rb_node_hshptn_t *)(node))
#define RNODE_FNDPTN(node) ((rb_node_fndptn_t *)(node))
#define RNODE_LINE(node) ((rb_node_line_t *)(node))
#define RNODE_FILE(node) ((rb_node_file_t *)(node))
#define RNODE_ENCODING(node) ((rb_node_encoding_t *)(node))
/* FL : 0..4: T_TYPES, 5: KEEP_WB, 6: PROMOTED, 7: FINALIZE, 8: UNUSED, 9: UNUSED, 10: EXIVAR, 11: FREEZE */
/* NODE_FL: 0..4: UNUSED, 5: UNUSED, 6: UNUSED, 7: NODE_FL_NEWLINE,
* 8..14: nd_type,
* 15..: nd_line
*/
#define NODE_FL_NEWLINE (((VALUE)1)<<7)
#define NODE_TYPESHIFT 8
#define NODE_TYPEMASK (((VALUE)0x7f)<<NODE_TYPESHIFT)
#define nd_fl_newline(n) ((n)->flags & NODE_FL_NEWLINE)
#define nd_set_fl_newline(n) ((n)->flags |= NODE_FL_NEWLINE)
#define nd_unset_fl_newline(n) ((n)->flags &= ~NODE_FL_NEWLINE)
#define nd_type(n) ((int) ((RNODE(n)->flags & NODE_TYPEMASK)>>NODE_TYPESHIFT))
#define nd_set_type(n,t) \
rb_node_set_type(n, t)
#define nd_init_type(n,t) \
(n)->flags=(((n)->flags&~NODE_TYPEMASK)|((((unsigned long)(t))<<NODE_TYPESHIFT)&NODE_TYPEMASK))
typedef struct node_buffer_struct node_buffer_t;
[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>
2024-04-16 12:42:42 +03:00
#ifdef UNIVERSAL_PARSER
typedef struct rb_parser_config_struct rb_parser_config_t;
#endif
typedef struct rb_ast_body_struct {
const NODE *root;
[Universal parser] DeVALUE of p->debug_lines and ast->body.script_lines This patch is part of universal parser work. ## Summary - Decouple VALUE from members below: - `(struct parser_params *)->debug_lines` - `(rb_ast_t *)->body.script_lines` - Instead, they are now `rb_parser_ary_t *` - They can also be a `(VALUE)FIXNUM` as before to hold line count - `ISEQ_BODY(iseq)->variable.script_lines` remains VALUE - In order to do this, - Add `VALUE script_lines` param to `rb_iseq_new_with_opt()` - Introduce `rb_parser_build_script_lines_from()` to convert `rb_parser_ary_t *` into `VALUE` ## Other details - Extend `rb_parser_ary_t *`. It previously could only store `rb_parser_ast_token *`, now can store script_lines, too - Change tactics of building the top-level `SCRIPT_LINES__` in `yycompile0()` - Before: While parsing, each line of the script is added to `SCRIPT_LINES__[path]` - After: After `yyparse(p)`, `SCRIPT_LINES__[path]` will be built from `p->debug_lines` - Remove the second parameter of `rb_parser_set_script_lines()` to make it simple - Introduce `script_lines_free()` to be called from `rb_ast_free()` because the GC no longer takes care of the script_lines - Introduce `rb_parser_string_deep_copy()` in parse.y to maintain script_lines when `rb_ruby_parser_free()` called - With regard to this, please see *Future tasks* below ## Future tasks - Decouple IMEMO from `rb_ast_t *` - This lifts the five-members-restriction of Ruby object, - So we will be able to move the ownership of the `lex.string_buffer` from parser to AST - Then we remove `rb_parser_string_deep_copy()` to make the whole thing simple
2024-03-28 04:26:42 +03:00
rb_parser_ary_t *script_lines;
int line_count;
signed int frozen_string_literal:2; /* -1: not specified, 0: false, 1: true */
signed int coverage_enabled:2; /* -1: not specified, 0: false, 1: true */
} rb_ast_body_t;
typedef struct rb_ast_struct {
node_buffer_t *node_buffer;
rb_ast_body_t body;
#ifdef UNIVERSAL_PARSER
const rb_parser_config_t *config;
#endif
} rb_ast_t;
/*
* Parser Interface
*/
typedef struct parser_params rb_parser_t;
#ifndef INTERNAL_IMEMO_H
typedef struct rb_imemo_tmpbuf_struct rb_imemo_tmpbuf_t;
#endif
#ifdef UNIVERSAL_PARSER
typedef struct rb_parser_config_struct {
/* Memory */
void *(*malloc)(size_t size);
void *(*calloc)(size_t number, size_t size);
void *(*realloc)(void *ptr, size_t newsiz);
void (*free)(void *ptr);
void *(*alloc_n)(size_t nelems, size_t elemsiz);
void *(*alloc)(size_t elemsiz);
void *(*realloc_n)(void *ptr, size_t newelems, size_t newsiz);
void *(*zalloc)(size_t elemsiz);
void *(*rb_memmove)(void *dest, const void *src, size_t t, size_t n);
void *(*nonempty_memcpy)(void *dest, const void *src, size_t t, size_t n);
void *(*xmalloc_mul_add)(size_t x, size_t y, size_t z);
// VALUE rb_suppress_tracing(VALUE (*func)(VALUE), VALUE arg);
VALUE (*compile_callback)(VALUE (*func)(VALUE), VALUE arg);
NODE *(*reg_named_capture_assign)(struct parser_params* p, VALUE regexp, const rb_code_location_t *loc);
/* Variable */
VALUE (*attr_get)(VALUE obj, ID id);
/* Array */
VALUE (*ary_push)(VALUE ary, VALUE elem);
VALUE (*ary_new_from_args)(long n, ...);
VALUE (*ary_unshift)(VALUE ary, VALUE item);
/* Symbol */
ID (*make_temporary_id)(size_t n);
int (*is_local_id)(ID);
int (*is_attrset_id)(ID);
int (*is_global_name_punct)(const int c);
int (*id_type)(ID id);
ID (*id_attrset)(ID);
ID (*intern)(const char *name);
ID (*intern2)(const char *name, long len);
ID (*intern3)(const char *name, long len, rb_encoding *enc);
ID (*intern_str)(VALUE str);
int (*is_notop_id)(ID);
int (*enc_symname_type)(const char *name, long len, rb_encoding *enc, unsigned int allowed_attrset);
const char *(*id2name)(ID id);
VALUE (*id2str)(ID id);
VALUE (*id2sym)(ID x);
ID (*sym2id)(VALUE sym);
/* String */
RBIMPL_ATTR_FORMAT(RBIMPL_PRINTF_FORMAT, 2, 3)
VALUE (*str_catf)(VALUE str, const char *format, ...);
VALUE (*str_cat_cstr)(VALUE str, const char *ptr);
VALUE (*str_resize)(VALUE str, long len);
VALUE (*str_new)(const char *ptr, long len);
VALUE (*str_new_cstr)(const char *ptr);
VALUE (*str_to_interned_str)(VALUE);
VALUE (*enc_str_new)(const char *ptr, long len, rb_encoding *enc);
RBIMPL_ATTR_FORMAT(RBIMPL_PRINTF_FORMAT, 2, 0)
VALUE (*str_vcatf)(VALUE str, const char *fmt, va_list ap);
RBIMPL_ATTR_FORMAT(RBIMPL_PRINTF_FORMAT, 1, 2)
VALUE (*rb_sprintf)(const char *format, ...);
char *(*rstring_ptr)(VALUE str);
long (*rstring_len)(VALUE str);
VALUE (*obj_as_string)(VALUE);
/* Numeric */
VALUE (*int2num)(int v);
/* IO */
int (*stderr_tty_p)(void);
void (*write_error_str)(VALUE mesg);
VALUE (*io_write)(VALUE io, VALUE str);
VALUE (*io_flush)(VALUE io);
VALUE (*io_puts)(int argc, const VALUE *argv, VALUE out);
/* IO (Ractor) */
VALUE (*debug_output_stdout)(void);
VALUE (*debug_output_stderr)(void);
/* Encoding */
int (*is_usascii_enc)(rb_encoding *enc);
int (*enc_isalnum)(OnigCodePoint c, rb_encoding *enc);
int (*enc_precise_mbclen)(const char *p, const char *e, rb_encoding *enc);
int (*mbclen_charfound_p)(int len);
int (*mbclen_charfound_len)(int len);
const char *(*enc_name)(rb_encoding *enc);
char *(*enc_prev_char)(const char *s, const char *p, const char *e, rb_encoding *enc);
rb_encoding* (*enc_get)(VALUE obj);
int (*enc_asciicompat)(rb_encoding *enc);
rb_encoding *(*utf8_encoding)(void);
VALUE (*enc_associate)(VALUE obj, rb_encoding *enc);
rb_encoding *(*ascii8bit_encoding)(void);
int (*enc_codelen)(int c, rb_encoding *enc);
int (*enc_mbcput)(unsigned int c, void *buf, rb_encoding *enc);
int (*enc_find_index)(const char *name);
rb_encoding *(*enc_from_index)(int idx);
int (*enc_isspace)(OnigCodePoint c, rb_encoding *enc);
rb_encoding *(*usascii_encoding)(void);
int (*enc_mbminlen)(rb_encoding *enc);
bool (*enc_isascii)(OnigCodePoint c, rb_encoding *enc);
OnigCodePoint (*enc_mbc_to_codepoint)(const char *p, const char *e, rb_encoding *enc);
/* Compile */
// int rb_local_defined(ID id, const rb_iseq_t *iseq);
int (*local_defined)(ID, const void*);
// int rb_dvar_defined(ID id, const rb_iseq_t *iseq);
int (*dvar_defined)(ID, const void*);
/* Error (Exception) */
RBIMPL_ATTR_FORMAT(RBIMPL_PRINTF_FORMAT, 6, 0)
VALUE (*syntax_error_append)(VALUE, VALUE, int, int, rb_encoding*, const char*, va_list);
RBIMPL_ATTR_FORMAT(RBIMPL_PRINTF_FORMAT, 2, 3)
void (*raise)(VALUE exc, const char *fmt, ...);
VALUE (*syntax_error_new)(void);
/* Eval */
VALUE (*errinfo)(void);
void (*set_errinfo)(VALUE err);
void (*exc_raise)(VALUE mesg);
VALUE (*make_exception)(int argc, const VALUE *argv);
/* GC */
void (*sized_xfree)(void *x, size_t size);
void *(*sized_realloc_n)(void *ptr, size_t new_count, size_t element_size, size_t old_count);
void (*gc_guard)(VALUE);
void (*gc_mark)(VALUE);
/* Re */
VALUE (*reg_compile)(VALUE str, int options, const char *sourcefile, int sourceline);
VALUE (*reg_check_preprocess)(VALUE str);
int (*memcicmp)(const void *x, const void *y, long len);
/* Error */
void (*compile_warn)(const char *file, int line, const char *fmt, ...) RUBYPARSER_ATTRIBUTE_FORMAT(3, 4);
void (*compile_warning)(const char *file, int line, const char *fmt, ...) RUBYPARSER_ATTRIBUTE_FORMAT(3, 4);
void (*bug)(const char *fmt, ...) RUBYPARSER_ATTRIBUTE_FORMAT(1, 2);
void (*fatal)(const char *fmt, ...) RUBYPARSER_ATTRIBUTE_FORMAT(1, 2);
VALUE (*verbose)(void);
int *(*errno_ptr)(void);
/* VM */
VALUE (*make_backtrace)(void);
/* Util */
unsigned long (*scan_hex)(const char *start, size_t len, size_t *retlen);
unsigned long (*scan_oct)(const char *start, size_t len, size_t *retlen);
unsigned long (*scan_digits)(const char *str, ssize_t len, int base, size_t *retlen, int *overflow);
double (*strtod)(const char *s00, char **se);
/* Misc */
int (*rtest)(VALUE obj);
int (*nil_p)(VALUE obj);
VALUE qnil;
VALUE qfalse;
2024-01-11 15:27:19 +03:00
VALUE (*eArgError)(void);
int (*long2int)(long);
/* For Ripper */
int enc_coderange_7bit;
int enc_coderange_unknown;
VALUE (*static_id2sym)(ID id);
long (*str_coderange_scan_restartable)(const char *s, const char *e, rb_encoding *enc, int *cr);
} rb_parser_config_t;
#undef rb_encoding
#undef OnigCodePoint
#endif /* UNIVERSAL_PARSER */
RUBY_SYMBOL_EXPORT_BEGIN
void rb_ruby_parser_free(void *ptr);
#ifdef UNIVERSAL_PARSER
2024-01-14 11:55:11 +03:00
rb_parser_t *rb_ruby_parser_allocate(const rb_parser_config_t *config);
rb_parser_t *rb_ruby_parser_new(const rb_parser_config_t *config);
#endif
RUBY_SYMBOL_EXPORT_END
#endif /* RUBY_RUBYPARSER_H */