From e3a82d79fd727c90638ef697cb1b5ad73c7e62c0 Mon Sep 17 00:00:00 2001 From: Koichi ITO Date: Sat, 16 Mar 2024 01:20:58 +0900 Subject: [PATCH] [ruby/prism] Fix token incompatibility for `Prism::Translation::Parser::Lexer` This PR fixes token incompatibility for `Prism::Translation::Parser::Lexer` when using escaped backslash in string literal: ```ruby "\\ foo \\ bar" ``` ## Parser gem (Expected) ```console $ bundle exec ruby -Ilib -rparser/ruby33 -ve \ 'buf = Parser::Source::Buffer.new("example.rb"); buf.source = File.read("example.rb"); p Parser::Ruby33.new.tokenize(buf)' ruby 3.3.0 (2023-12-25 revision https://github.com/ruby/prism/commit/5124f9ac75) [x86_64-darwin22] [s(:str, "\\ foo \\ bar"), [], [[:tSTRING, ["\\ foo \\ bar", #]], [:tNL, [nil, #]]]] ``` ## `Prism::Translation::Parser` (Actual) Previously, the tokens returned by the Parser gem were different. The escaped backslash does not match in the `tSTRING` token: ```console $ bundle exec ruby -Ilib -rprism -rprism/translation/parser33 -ve \ 'buf = Parser::Source::Buffer.new("example.rb"); buf.source = File.read("example.rb"); p Prism::Translation::Parser33.new.tokenize(buf)' ruby 3.3.0 (2023-12-25 revision https://github.com/ruby/prism/commit/5124f9ac75) [x86_64-darwin22] [s(:str, "\\ foo \\ bar"), [], [[:tSTRING, ["\\\\ foo \\\\ bar", #]], [:tNL, [nil, #]]]] ``` After this correction, the AST and tokens returned by the Parser gem are the same: ```console $ bundle exec ruby -Ilib -rprism -rprism/translation/parser33 -ve \ 'buf = Parser::Source::Buffer.new("example.rb"); buf.source = File.read("example.rb"); p Prism::Translation::Parser33.new.tokenize(buf)' ruby 3.3.0 (2023-12-25 revision https://github.com/ruby/prism/commit/5124f9ac75) [x86_64-darwin22] [s(:str, "\\ foo \\ bar"), [], [[:tSTRING, ["\\ foo \\ bar", #]], [:tNL, [nil, #]]]] ``` The reproduction test is based on the following strings.txt and exists: https://github.com/ruby/prism/blob/v0.24.0/test/prism/fixtures/strings.txt#L79 But, the restoration has not yet been performed due to remaining other issues in strings.txt. https://github.com/ruby/prism/commit/2c44e7e307 --- lib/prism/translation/parser/lexer.rb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/prism/translation/parser/lexer.rb b/lib/prism/translation/parser/lexer.rb index 9e5d27ef29..cb23fe8ac0 100644 --- a/lib/prism/translation/parser/lexer.rb +++ b/lib/prism/translation/parser/lexer.rb @@ -289,7 +289,7 @@ module Prism elsif ["\"", "'"].include?(value) && (next_token = lexed[index][0]) && next_token.type == :STRING_CONTENT && next_token.value.lines.count <= 1 && (next_next_token = lexed[index + 1][0]) && next_next_token.type == :STRING_END next_location = token.location.join(next_next_token.location) type = :tSTRING - value = next_token.value + value = next_token.value.gsub("\\\\", "\\") location = Range.new(source_buffer, offset_cache[next_location.start_offset], offset_cache[next_location.end_offset]) index += 2 elsif value.start_with?("<<")