From 70d6977ccc07b667da0ed165b7706afbb5190816 Mon Sep 17 00:00:00 2001 From: Samantha McVey Date: Wed, 9 Nov 2016 20:57:13 -0800 Subject: Use charlock_holmes to do encoding detection. In my tests it has properly identified incorrect encodings that used to be present on older commits. This will help ensure this won't happen again, giving people instant feedback and allowing all pull requests to be checked --- tests/encoding.rb | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'tests') diff --git a/tests/encoding.rb b/tests/encoding.rb index c4d41d19..ae7e495f 100644 --- a/tests/encoding.rb +++ b/tests/encoding.rb @@ -1,14 +1,18 @@ #!/usr/bin/env ruby +require 'charlock_holmes' $file_count = 0; markdown_files = Dir["./**/*.html.markdown"] markdown_files.each do |file| begin - file_bin = File.open(file, "rb") - contents = file_bin.read - if ! contents.valid_encoding? - puts "#{file} has an invalid encoding! Please save the file in UTF-8!" - else + contents = File.read(file) + detection = CharlockHolmes::EncodingDetector.detect(contents) + case detection[:encoding] + when 'UTF-8' + $file_count = $file_count + 1 + when 'ISO-8859-1' $file_count = $file_count + 1 + else + puts "#{file} was detected as #{detection[:encoding]} encoding! Please save the file in UTF-8!" end rescue Exception => msg puts msg @@ -20,6 +24,6 @@ if files_failed != 0 puts "Please resave the file as UTF-8." exit 1 else - puts "Success. All #{$file_count} files passed UTF-8 validity checks" + puts "Success. All #{$file_count} files Ruby's UTF-8 validity checks. This won't catch most problems." exit 0 end -- cgit v1.2.3