mirror of
https://github.com/ruby/ruby.git
synced 2025-08-15 13:39:04 +02:00

Implementation for Language Server Protocol (LSP) sometimes needs token information. For example both `m(1)` and `m(1, )` has same AST structure other than node locations then it's impossible to check the existence of `,` from AST. However in later case, it might be better to suggest variables list for the second argument. Token information is important for such case. This commit adds these methods. * Add `keep_tokens` option for `RubyVM::AbstractSyntaxTree.parse`, `.parse_file` and `.of` * Add `RubyVM::AbstractSyntaxTree::Node#tokens` which returns tokens for the node including tokens for descendants nodes. * Add `RubyVM::AbstractSyntaxTree::Node#all_tokens` which returns all tokens for the input script regardless the receiver node. [Feature #19070] Impacts on memory usage and performance are below: Memory usage: ``` $ cat test.rb root = RubyVM::AbstractSyntaxTree.parse_file(File.expand_path('../test/ruby/test_keyword.rb', __FILE__), keep_tokens: true) $ /usr/bin/time -f %Mkb /usr/local/bin/ruby -v ruby 3.2.0dev (2022-11-19T09:41:54Z 19070-keep_tokens d3af1b8057) [x86_64-linux] 11408kb # keep_tokens :false $ /usr/bin/time -f %Mkb /usr/local/bin/ruby test.rb 17508kb # keep_tokens :true $ /usr/bin/time -f %Mkb /usr/local/bin/ruby test.rb 30960kb ``` Performance: ``` $ cat ../ast_keep_tokens.yml prelude: | src = <<~SRC module M class C def m1(a, b) 1 + a + b end end end SRC benchmark: without_keep_tokens: | RubyVM::AbstractSyntaxTree.parse(src, keep_tokens: false) with_keep_tokens: | RubyVM::AbstractSyntaxTree.parse(src, keep_tokens: true) $ make benchmark COMPARE_RUBY="./ruby" ARGS=../ast_keep_tokens.yml /home/kaneko.y/.rbenv/shims/ruby --disable=gems -rrubygems -I../benchmark/lib ../benchmark/benchmark-driver/exe/benchmark-driver \ --executables="compare-ruby::./ruby -I.ext/common --disable-gem" \ --executables="built-ruby::./miniruby -I../lib -I. -I.ext/common ../tool/runruby.rb --extout=.ext -- --disable-gems --disable-gem" \ --output=markdown --output-compare -v ../ast_keep_tokens.yml compare-ruby: ruby 3.2.0dev (2022-11-19T09:41:54Z 19070-keep_tokens d3af1b8057) [x86_64-linux] built-ruby: ruby 3.2.0dev (2022-11-19T09:41:54Z 19070-keep_tokens d3af1b8057) [x86_64-linux] warming up.. | |compare-ruby|built-ruby| |:--------------------|-----------:|---------:| |without_keep_tokens | 21.659k| 21.303k| | | 1.02x| -| |with_keep_tokens | 6.220k| 5.691k| | | 1.09x| -| ```
25 lines
1 KiB
C
25 lines
1 KiB
C
#ifndef INTERNAL_PARSE_H /*-*-C-*-vi:se ft=c:*/
|
|
#define INTERNAL_PARSE_H
|
|
/**
|
|
* @author Ruby developers <ruby-core@ruby-lang.org>
|
|
* @copyright This file is a part of the programming language Ruby.
|
|
* Permission is hereby granted, to either redistribute and/or
|
|
* modify this file, provided that the conditions mentioned in the
|
|
* file COPYING are met. Consult the file for details.
|
|
* @brief Internal header for the parser.
|
|
*/
|
|
#include "ruby/ruby.h" /* for VALUE */
|
|
struct rb_iseq_struct; /* in vm_core.h */
|
|
|
|
/* parse.y */
|
|
VALUE rb_parser_set_yydebug(VALUE, VALUE);
|
|
void *rb_parser_load_file(VALUE parser, VALUE name);
|
|
void rb_parser_keep_script_lines(VALUE vparser);
|
|
void rb_parser_error_tolerant(VALUE vparser);
|
|
void rb_parser_keep_tokens(VALUE vparser);
|
|
|
|
RUBY_SYMBOL_EXPORT_BEGIN
|
|
VALUE rb_parser_set_context(VALUE, const struct rb_iseq_struct *, int);
|
|
RUBY_SYMBOL_EXPORT_END
|
|
|
|
#endif /* INTERNAL_PARSE_H */
|