Last active
March 12, 2020 11:17
-
-
Save mlankenau/784e8bc2e0a7ba1050715e68a03e5303 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
defmodule TextFileUtils do | |
def fix_line_breaks(file_path) do | |
{:ok, file} = File.open(file_path) | |
out_file_path = "/tmp/fixed_file_#{:erlang.system_time}.tmp" | |
{:ok, out_file} = File.open(out_file_path, [:write]) | |
process_file(file, out_file, "") | |
File.close(file) | |
File.close(out_file) | |
out_file_path | |
end | |
defp process_file(in_file, out_file, last) do | |
c = IO.read(in_file, 1) | |
case {last, c} do | |
{"\r", "\n"} -> | |
#windows case | |
IO.write(out_file, "\n") | |
{"\r", _} -> | |
# weird osx excel case, only \r | |
IO.write(out_file, "\n") | |
IO.write(out_file, c) | |
{_, "\n" = c} -> | |
# unix case, only newline | |
IO.write(out_file, "\n") | |
{_, "\r" = c} -> | |
# we skip it | |
{_, :eof} -> | |
nil | |
{_, c} -> | |
IO.write(out_file, c) | |
end | |
if c != :eof do | |
process_file(in_file, out_file, c) | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment