ruby newline conversion sample

test_newline_conversion.rb

require 'tempfile'

$tmp = Tempfile.new.binmode
$tmp.write("a" "\r\n" "\r" "\x1a" "1" "\r")
$tmp.flush

def read(mode, **opts)
  File.open($tmp.path, mode, **opts) do |f|
    f.readlines.join('')
  end
end

def classify(str)
  case str
  when "a" "\n"   "\r"
    "DOS crlf+eof"
  when "a" "\n"   "\n" "\x1a" "1" "\n"
    "universal newline"
  when "a" "\r\n" "\r" "\x1a" "1" "\r"
    "no conversion"
  else
    str
  end
end

def format(modestr, **opts)
  if opts.empty?
    modestr.inspect
  else
    "\"#{modestr}\" with #{opts.map { |k, v| "#{k.to_s}: #{v}"}.join(", ")}"
  end
end

def test(modestr, **opts)
  puts sprintf("%18s %s", classify(read(modestr, **opts)), format(modestr, **opts))
end

test("rt")
test("rt", universal_newline: false)
test("rt", crlf_newline: true)
test("r")
test("r", universal_newline: true)
test("r", universal_newline: false)
test("r", crlf_newline: false)
test("r", textmode: true)
test("r", textmode: false)
test("r:US-ASCII:UTF-8")
test("r:US-ASCII:UTF-8", universal_newline: false)

# ruby 3.1.2p20 (2022-04-12 revision 4491bb740a) [x64-mingw-ucrt]
# R:\>ruby .\test_newline_conversion.rb
#  universal newline "rt"
#      no conversion "rt" with universal_newline: false
#       DOS crlf+eof "rt" with crlf_newline: true
#       DOS crlf+eof "r"
#  universal newline "r" with universal_newline: true
#      no conversion "r" with universal_newline: false
#      no conversion "r" with crlf_newline: false
#  universal newline "r" with textmode: true
#       DOS crlf+eof "r" with textmode: false
#  universal newline "r:US-ASCII:UTF-8"
#      no conversion "r:US-ASCII:UTF-8" with universal_newline: false

# ruby 3.1.2p20 (2022-04-12 revision 4491bb740a) [x86_64-linux]
# /mnt/r$ ruby ./test_newline_conversion.rb
#  universal newline "rt"
#      no conversion "rt" with universal_newline: false
#      no conversion "rt" with crlf_newline: true
#      no conversion "r"
#  universal newline "r" with universal_newline: true
#      no conversion "r" with universal_newline: false
#      no conversion "r" with crlf_newline: false
#  universal newline "r" with textmode: true
#      no conversion "r" with textmode: false
#      no conversion "r:US-ASCII:UTF-8"
#      no conversion "r:US-ASCII:UTF-8" with universal_newline: false