Add CSV::InvalidEncodingError

lib/csv.rb

@@ -854,6 +854,15 @@ def initialize(message, line_number)
  end
  end
 
+ # The error thrown when the parser encounters invalid encoding in CSV.
+ class InvalidEncodingError < MalformedCSVError
+ attr_reader :encoding
+ def initialize(encoding, line_number)
+ @encoding = encoding
+ super("Invalid byte sequence in #{encoding}", line_number)
+ end
+ end
+
  #
  # A FieldInfo Struct contains details about a field's position in the data
  # source it was read from. CSV will pass this Struct to some blocks that make

lib/csv/parser.rb

@@ -414,8 +414,7 @@ def parse(&block)
  else
  lineno = @lineno + 1
  end
- message = "Invalid byte sequence in #{@encoding}"
- raise MalformedCSVError.new(message, lineno)
+ raise InvalidEncodingError.new(@encoding, lineno)
  rescue UnexpectedError => error
  if @scanner
  ignore_broken_line
@@ -876,8 +875,7 @@ def build_scanner
  !line.valid_encoding?
  end
  if index
- message = "Invalid byte sequence in #{@encoding}"
- raise MalformedCSVError.new(message, @lineno + index + 1)
+ raise InvalidEncodingError.new(@encoding, @lineno + index + 1)
  end
  end
  Scanner.new(string)

test/csv/interface/test_read.rb

@@ -113,11 +113,11 @@ def test_open_encoding_invalid
  file << "\u{1F600},\u{1F601}"
  end
  CSV.open(@input.path, encoding: "EUC-JP") do |csv|
- error = assert_raise(CSV::MalformedCSVError) do
+ error = assert_raise(CSV::InvalidEncodingError) do
  csv.shift
  end
- assert_equal("Invalid byte sequence in EUC-JP in line 1.",
- error.message)
+ assert_equal([Encoding::EUC_JP, "Invalid byte sequence in EUC-JP in line 1."],
+[error.encoding, error.message])
  end
  end
 

test/csv/test_encodings.rb

@@ -280,12 +280,12 @@ def test_row_separator_detection_with_invalid_encoding
  def test_invalid_encoding_row_error
  csv = CSV.new("valid,x\rinvalid,\xF8\r".force_encoding("UTF-8"),
  encoding: "UTF-8", row_sep: "\r")
- error = assert_raise(CSV::MalformedCSVError) do
+ error = assert_raise(CSV::InvalidEncodingError) do
  csv.shift
  csv.shift
  end
- assert_equal("Invalid byte sequence in UTF-8 in line 2.",
- error.message)
+ assert_equal([Encoding::UTF_8, "Invalid byte sequence in UTF-8 in line 2."],
+[error.encoding, error.message])
  end
 
  def test_string_input_transcode