From e50754fcfaeb80bef93f043c13895ce386ddb18c Mon Sep 17 00:00:00 2001 From: Vinicius Stock Date: Tue, 8 Oct 2024 10:47:08 -0400 Subject: [ruby/prism] Avoid breaking code units offset on binary encoding https://github.com/ruby/prism/commit/25a4cf6794 Co-authored-by: Kevin Newton --- test/prism/ruby/location_test.rb | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'test') diff --git a/test/prism/ruby/location_test.rb b/test/prism/ruby/location_test.rb index fc80a5b875..e360a0db72 100644 --- a/test/prism/ruby/location_test.rb +++ b/test/prism/ruby/location_test.rb @@ -140,6 +140,25 @@ module Prism assert_equal 7, location.end_code_units_column(Encoding::UTF_32LE) end + def test_code_units_handles_binary_encoding_with_multibyte_characters + # If the encoding is set to binary and the source contains multibyte + # characters, we avoid breaking the code unit offsets, but they will + # still be incorrect. + + program = Prism.parse(<<~RUBY).value + # -*- encoding: binary -*- + + 😀 + 😀 + RUBY + + # first 😀 + location = program.statements.body.first.receiver.location + + assert_equal 4, location.end_code_units_column(Encoding::UTF_8) + assert_equal 4, location.end_code_units_column(Encoding::UTF_16LE) + assert_equal 4, location.end_code_units_column(Encoding::UTF_32LE) + end + def test_chop location = Prism.parse("foo").value.location -- cgit v1.2.3