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, #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_encodingString

Returns the destination encoding as an encoding object.


4297
4298
4299
4300
4301
# File 'transcode.c', line 4297

static VALUE
ecerr_destination_encoding(VALUE self)
{
    return rb_attr_get(self, rb_intern("destination_encoding"));
}

#destination_encoding_nameString

Returns the destination encoding name as a string.


4285
4286
4287
4288
4289
# File 'transcode.c', line 4285

static VALUE
ecerr_destination_encoding_name(VALUE self)
{
    return rb_attr_get(self, rb_intern("destination_encoding_name"));
}

#error_bytesString

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

4339
4340
4341
4342
4343
# File 'transcode.c', line 4339

static VALUE
ecerr_error_bytes(VALUE self)
{
    return rb_attr_get(self, rb_intern("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

4381
4382
4383
4384
4385
# File 'transcode.c', line 4381

static VALUE
ecerr_incomplete_input(VALUE self)
{
    return rb_attr_get(self, rb_intern("incomplete_input"));
}

#readagain_bytesString

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


4351
4352
4353
4354
4355
# File 'transcode.c', line 4351

static VALUE
ecerr_readagain_bytes(VALUE self)
{
    return rb_attr_get(self, rb_intern("readagain_bytes"));
}

#source_encodingEncoding

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

4273
4274
4275
4276
4277
# File 'transcode.c', line 4273

static VALUE
ecerr_source_encoding(VALUE self)
{
    return rb_attr_get(self, rb_intern("source_encoding"));
}

#source_encoding_nameString

Returns the source encoding name as a string.


4247
4248
4249
4250
4251
# File 'transcode.c', line 4247

static VALUE
ecerr_source_encoding_name(VALUE self)
{
    return rb_attr_get(self, rb_intern("source_encoding_name"));
}