Module: Eco::Data::Files::InstanceMethods

Includes:
Language::AuxiliarLogger
Defined in:
lib/eco/data/files/helpers.rb

Instance Method Summary collapse

Methods included from Language::AuxiliarLogger

#logger

Instance Method Details

#get_file_content(file, encoding, tolerance: 5) ⇒ String

It offers a resilient way to read content from a file

Returns:

  • (String) —

    the content of the file



19
20
21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/eco/data/files/helpers.rb', line 19

def get_file_content(file, encoding, tolerance: 5)
  unless self.class.file_exists?(file)
    logger.error("File does not exist: #{file}")
    exit(1)
  end
  encoding ||= self.class.encoding(file)
  encoding   = (encoding == "bom") ? "#{encoding}|utf-8": encoding
  unless !encoding || encoding == 'utf-8'
    msg = "File encoding: '#{encoding}'"
    logger.debug(msg)
    puts msg
  end
  read_with_tolerance(file, encoding: encoding, tolerance: tolerance)
end

#read_with_tolerance(file, encoding:, tolerance: 5) ⇒ Object 



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/eco/data/files/helpers.rb', line 34

def read_with_tolerance(file, encoding:, tolerance: 5)
  if content = File.read(file, encoding: encoding)
    content = content.encode("utf-8") unless encoding.include?('utf-8')
    content.scrub do |bytes|
      replacement = '<' + bytes.unpack('H*')[0] + '>'
      if tolerance <= 0
        logger.error("There were more than 5 encoding errors in the file '#{file}'.")
        return content
      else
        tolerance -= 1
        logger.error("Encoding problem in file '#{file}': '#{replacement}'.")
        replacement
      end
    end
  end
end