CSV parser with first 1kB block and wrong encoding causes unexpected behavior about csv HOT 3 CLOSED

require 'csv'

class CSVDemo
  attr_reader :errors

  def initialize(file)
    @file   = File.open(file, 'r', encoding: Encoding::UTF_8)
    @errors = []
  end

  def csv
    @_csv ||= CSV.new(file, encoding: Encoding::UTF_8, headers: true)
  end

  def validate!
    line_number = 2 # the header is skipped

    loop do
      row = csv.gets
      break unless row
      # here can be other code which can cause different ArgumentError
    rescue ArgumentError => exception
      raise if exception.message != 'invalid byte sequence in UTF-8'
      errors << "The line #{line_number} contains invalid UTF-8 characters"
    ensure
      line_number += 1
    end
  end

  private

  attr_reader :file
  attr_writer :errors
end

demo = CSVDemo.new('labels_invalid_iso8859-1_encoding.csv')
demo.validate!

puts demo.errors

# Returns:
# The line 2 contains invalid UTF-8 characters
#
# Expected:
# The line 2 contains invalid UTF-8 characters
# The line 4 contains invalid UTF-8 characters