def __init__(self, errors='strict', encoding=None,):
assert encoding
self.encoding = encoding
self.errors = errors
self.decoder = Charset.forName(self.encoding).newDecoder()
self.output_buffer = CharBuffer.allocate(1024)
self.buffer = ''
def __init__(self, errors='strict', encoding=None,):
assert encoding
self.encoding = encoding
self.errors = errors
self.decoder = Charset.forName(self.encoding).newDecoder()
self.output_buffer = CharBuffer.allocate(1024)
self.buffer = ''
def decode(self, input, errors='strict', final=True):
error_function = codecs.lookup_error(errors)
input_buffer = ByteBuffer.wrap(array('b', input))
decoder = Charset.forName(self.encoding).newDecoder()
output_buffer = CharBuffer.allocate(min(max(int(len(input) / 2), 256), 1024))
builder = StringBuilder(int(decoder.averageCharsPerByte() * len(input)))
while True:
result = decoder.decode(input_buffer, output_buffer, False)
pos = output_buffer.position()
output_buffer.rewind()
builder.append(output_buffer.subSequence(0, pos))
if result.isUnderflow():
if final:
_process_incomplete_decode(self.encoding, input, error_function, input_buffer, builder)
break
_process_decode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.toString(), input_buffer.position()
def encode(self, input, final=False):
error_function = codecs.lookup_error(self.errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
self.output_buffer.rewind()
builder = StringIO()
while True:
result = self.encoder.encode(input_buffer, self.output_buffer, final)
pos = self.output_buffer.position()
self.output_buffer.rewind()
builder.write(self.output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue()
def decode(self, input, errors='strict', final=True):
error_function = codecs.lookup_error(errors)
input_buffer = ByteBuffer.wrap(array('b', input))
decoder = Charset.forName(self.encoding).newDecoder()
output_buffer = CharBuffer.allocate(min(max(int(len(input) / 2), 256), 1024))
builder = StringBuilder(int(decoder.averageCharsPerByte() * len(input)))
while True:
result = decoder.decode(input_buffer, output_buffer, False)
pos = output_buffer.position()
output_buffer.rewind()
builder.append(output_buffer.subSequence(0, pos))
if result.isUnderflow():
if final:
_process_incomplete_decode(self.encoding, input, error_function, input_buffer, builder)
break
_process_decode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.toString(), input_buffer.position()
def encode(self, input, final=False):
error_function = codecs.lookup_error(self.errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
self.output_buffer.rewind()
builder = StringIO()
while True:
result = self.encoder.encode(input_buffer, self.output_buffer, final)
pos = self.output_buffer.position()
self.output_buffer.rewind()
builder.write(self.output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue()
def encode(self, input, errors='strict'):
error_function = codecs.lookup_error(errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
encoder = Charset.forName(self.encoding).newEncoder()
output_buffer = ByteBuffer.allocate(min(max(len(input) * 2, 256), 1024))
builder = StringIO()
while True:
result = encoder.encode(input_buffer, output_buffer, True)
pos = output_buffer.position()
output_buffer.rewind()
builder.write(output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue(), len(input)
def encode(self, input, errors='strict'):
error_function = codecs.lookup_error(errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
encoder = Charset.forName(self.encoding).newEncoder()
output_buffer = ByteBuffer.allocate(min(max(len(input) * 2, 256), 1024))
builder = StringIO()
while True:
result = encoder.encode(input_buffer, output_buffer, True)
pos = output_buffer.position()
output_buffer.rewind()
builder.write(output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue(), len(input)