Exception: Encoding::InvalidByteSequenceError

Inherits:
EncodingError show all
Defined in:
transcode.c,
transcode.c

Overview

Raised by Encoding and String methods when the string being transcoded contains a byte invalid for the either the source or target encoding.

Instance Method Summary collapse

Methods inherited from Exception

#==, #backtrace, #backtrace_locations, #cause, #detailed_message, #exception, exception, #full_message, #initialize, #inspect, #message, #set_backtrace, #to_s, to_tty?

Constructor Details

This class inherits a constructor from Exception

Instance Method Details

#destination_encoding ⇒ String

Returns the destination encoding as an encoding object.

Returns:



4344
4345
4346
4347
4348
 
# File 'transcode.c', line 4344

static VALUE
ecerr_destination_encoding(VALUE self)
{
    return rb_attr_get(self, id_destination_encoding);
}

#destination_encoding_name ⇒ String

Returns the destination encoding name as a string.

Returns:



4332
4333
4334
4335
4336
 
# File 'transcode.c', line 4332

static VALUE
ecerr_destination_encoding_name(VALUE self)
{
    return rb_attr_get(self, id_destination_encoding_name);
}

#error_bytes ⇒ String

Returns the discarded bytes when Encoding::InvalidByteSequenceError occurs.

ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
begin
  ec.convert("abc\xA1\xFFdef")
rescue Encoding::InvalidByteSequenceError
  p $!      #=> #<Encoding::InvalidByteSequenceError: "\xA1" followed by "\xFF" on EUC-JP>
  puts $!.error_bytes.dump          #=> "\xA1"
  puts $!.readagain_bytes.dump      #=> "\xFF"
end

Returns:



4386
4387
4388
4389
4390
 
# File 'transcode.c', line 4386

static VALUE
ecerr_error_bytes(VALUE self)
{
    return rb_attr_get(self, id_error_bytes);
}

#incomplete_input? ⇒ Boolean

Returns true if the invalid byte sequence error is caused by premature end of string.

ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")

begin
  ec.convert("abc\xA1z")
rescue Encoding::InvalidByteSequenceError
  p $!      #=> #<Encoding::InvalidByteSequenceError: "\xA1" followed by "z" on EUC-JP>
  p $!.incomplete_input?    #=> false
end

begin
  ec.convert("abc\xA1")
  ec.finish
rescue Encoding::InvalidByteSequenceError
  p $!      #=> #<Encoding::InvalidByteSequenceError: incomplete "\xA1" on EUC-JP>
  p $!.incomplete_input?    #=> true
end

Returns:

  • (Boolean) 


4428
4429
4430
4431
4432
 
# File 'transcode.c', line 4428

static VALUE
ecerr_incomplete_input(VALUE self)
{
    return rb_attr_get(self, id_incomplete_input);
}

#readagain_bytes ⇒ String

Returns the bytes to be read again when Encoding::InvalidByteSequenceError occurs.

Returns:



4398
4399
4400
4401
4402
 
# File 'transcode.c', line 4398

static VALUE
ecerr_readagain_bytes(VALUE self)
{
    return rb_attr_get(self, id_readagain_bytes);
}

#source_encoding ⇒ Encoding

Returns the source encoding as an encoding object.

Note that the result may not be equal to the source encoding of the encoding converter if the conversion has multiple steps.

ec = Encoding::Converter.new("ISO-8859-1", "EUC-JP") # ISO-8859-1 -> UTF-8 -> EUC-JP
begin
  ec.convert("\xa0") # NO-BREAK SPACE, which is available in UTF-8 but not in EUC-JP.
rescue Encoding::UndefinedConversionError
  p $!.source_encoding              #=> #<Encoding:UTF-8>
  p $!.destination_encoding         #=> #<Encoding:EUC-JP>
  p $!.source_encoding_name         #=> "UTF-8"
  p $!.destination_encoding_name    #=> "EUC-JP"
end

Returns:



4320
4321
4322
4323
4324
 
# File 'transcode.c', line 4320

static VALUE
ecerr_source_encoding(VALUE self)
{
    return rb_attr_get(self, id_source_encoding);
}

#source_encoding_name ⇒ String

Returns the source encoding name as a string.

Returns:



4294
4295
4296
4297
4298
 
# File 'transcode.c', line 4294

static VALUE
ecerr_source_encoding_name(VALUE self)
{
    return rb_attr_get(self, id_source_encoding_name);
}