Add encoding on parsing CSV file

lib/csv_importer/csv_reader.rb

@@ -8,12 +8,13 @@ class CSVReader
  attribute :file # IO
  attribute :path, String
  attribute :quote_char, String, default: '"'
+ attribute :encoding, String, default: 'UTF-8:UTF-8'
 
  def csv_rows
  @csv_rows ||= begin
  sane_content = sanitize_content(read_content)
  separator = detect_separator(sane_content)
- cells = CSV.parse(sane_content, col_sep: separator, quote_char: quote_char, skip_blanks: true)
+ cells = CSV.parse(sane_content, col_sep: separator, quote_char: quote_char, skip_blanks: true, encoding: encoding)
  sanitize_cells(cells)
  end
  end
@@ -43,8 +44,9 @@ def read_content
  end
 
  def sanitize_content(csv_content)
+ internal_encoding = encoding.split(':').last
  csv_content
- .encode(Encoding.find('UTF-8'), {invalid: :replace, undef: :replace, replace: ''}) # Remove invalid byte sequences
+ .encode(Encoding.find(internal_encoding), {invalid: :replace, undef: :replace, replace: ''}) # Remove invalid byte sequences
  .gsub(/\r\r?\n?/, "\n") # Replaces windows line separators with "\n"
  end
 

spec/csv_importer/csv_reader_spec.rb

@@ -33,5 +33,10 @@ module CSVImporter
  reader = CSVReader.new(content: "first_name,last_name\n'bob','the builder'", quote_char: "'")
  expect(reader.rows).to eq [["bob", "the builder"]]
  end
+
+ it "supports custom encoding" do
+ reader = CSVReader.new(content: "メール,氏名".encode('SJIS'), encoding: 'SJIS:UTF-8')
+ expect(reader.header).to eq ["メール", "氏名"]
+ end
  end
 end