def test_multi_frame_three_to_one(self):
"""Test a multi-frame image where each frame is three fragments"""
# 2 frames, each 3 fragments long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x20\x00\x00\x00' \
b'\x40\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
assert next(frames) == (b'\x02\x00\x00\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
assert next(frames) == (b'\x03\x00\x00\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
pytest.raises(StopIteration, next, frames)
def test_multi_frame_varied_ratio(self):
"""Test a multi-frame image where each frames is random fragments"""
# 3 frames, 1st is 1 fragment, 2nd is 3 fragments, 3rd is 2 fragments
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x0E\x00\x00\x00' \
b'\x32\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x06\x00\x00\x00\x01\x00\x00\x00\x00\x01' \
b'\xFE\xFF\x00\xE0' \
b'\x02\x00\x00\x00\x02\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x06\x00\x00\x00\x03\x00\x00\x00\x00\x02' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x02\x00\x00\x00\x02\x04'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00\x00\x01', )
assert next(frames) == (b'\x02\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00\x00\x02')
assert next(frames) == (b'\x03\x00\x00\x00', b'\x02\x04')
pytest.raises(StopIteration, next, frames)
def test_multi_frame_varied_ratio(self):
"""Test a multi-frame image where each frames is random fragments"""
# 3 frames, 1st is 1 fragment, 2nd is 3 fragments, 3rd is 2 fragments
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x0E\x00\x00\x00' \
b'\x32\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x06\x00\x00\x00\x01\x00\x00\x00\x00\x01' \
b'\xFE\xFF\x00\xE0' \
b'\x02\x00\x00\x00\x02\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x06\x00\x00\x00\x03\x00\x00\x00\x00\x02' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x02\x00\x00\x00\x02\x04'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00\x00\x01', )
assert next(frames) == (b'\x02\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00\x00\x02')
assert next(frames) == (b'\x03\x00\x00\x00', b'\x02\x04')
pytest.raises(StopIteration, next, frames)
def test_multi_frame_three_to_one(self):
"""Test a multi-frame image where each frame is three fragments"""
# 2 frames, each 3 fragments long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x20\x00\x00\x00' \
b'\x40\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00',
b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
assert next(frames) == (b'\x02\x00\x00\x00',
b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
assert next(frames) == (b'\x03\x00\x00\x00',
b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
pytest.raises(StopIteration, next, frames)
def test_empty_bot_single_fragment(self):
"""Test a single-frame image where the frame is one fragments"""
# 1 frame, 1 fragment long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x00\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00', )
pytest.raises(StopIteration, next, frames)
def test_empty_bot_single_fragment(self):
"""Test a single-frame image where the frame is one fragments"""
# 1 frame, 1 fragment long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x00\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00', )
pytest.raises(StopIteration, next, frames)
def test_empty_bot_multi_fragments_per_frame(self):
"""Test parsing with multiple fragments per frame."""
# 4 frames in 6 fragments with JPEG EOI marker
bytestream = (b'\xFE\xFF\x00\xE0\x00\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\xFF\xD9'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00')
frames = generate_pixel_data(bytestream, 4)
for ii in range(4):
next(frames)
with pytest.raises(StopIteration):
next(frames)
def test_empty_bot_triple_fragment_single_frame(self):
"""Test a single-frame image where the frame is three fragments"""
# 1 frame, 3 fragments long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x00\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream, 1)
assert next(frames) == (b'\x01\x00\x00\x00', b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
pytest.raises(StopIteration, next, frames)
def test_empty_bot_no_nr_frames_raises(self):
"""Test parsing raises if not BOT and no nr_frames."""
# 1 frame, 3 fragments long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x00\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x03\x00\x00\x00'
msg = (r"Unable to determine the frame boundaries for the "
r"encapsulated pixel data as the Basic Offset Table is empty "
r"and `nr_frames` parameter is None")
with pytest.raises(ValueError, match=msg):
next(generate_pixel_data(bytestream))
def test_bot_triple_fragment_single_frame(self):
"""Test a single-frame image where the frame is three fragments"""
# 1 frame, 3 fragments long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00',
b'\x02\x00\x00\x00',
b'\x03\x00\x00\x00')
pytest.raises(StopIteration, next, frames)
def test_empty_bot_missing_marker(self):
"""Test parsing not BOT and missing marker with multi fragments."""
# 4 frames in 6 fragments with JPEG EOI marker (1 missing EOI)
bytestream = (b'\xFE\xFF\x00\xE0\x00\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xFF\xD9'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00')
msg = (r"The end of the encapsulated pixel data has been "
r"reached but one or more frame boundaries may have "
r"been missed; please confirm that the generated frame "
r"data is correct")
with pytest.warns(UserWarning, match=msg):
ii = 0
for frames in generate_pixel_data(bytestream, 4):
ii += 1
assert 3 == ii
def test_multi_frame_one_to_one(self):
"""Test a multi-frame image where each frame is one fragment"""
# 3 frames, each 1 fragment long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x0C\x00\x00\x00' \
b'\x18\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00', )
assert next(frames) == (b'\x02\x00\x00\x00', )
assert next(frames) == (b'\x03\x00\x00\x00', )
pytest.raises(StopIteration, next, frames)
def test_multi_frame_one_to_one(self):
"""Test a multi-frame image where each frame is one fragment"""
# 3 frames, each 1 fragment long
bytestream = b'\xFE\xFF\x00\xE0' \
b'\x0C\x00\x00\x00' \
b'\x00\x00\x00\x00' \
b'\x0C\x00\x00\x00' \
b'\x18\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x01\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x02\x00\x00\x00' \
b'\xFE\xFF\x00\xE0' \
b'\x04\x00\x00\x00' \
b'\x03\x00\x00\x00'
frames = generate_pixel_data(bytestream)
assert next(frames) == (b'\x01\x00\x00\x00', )
assert next(frames) == (b'\x02\x00\x00\x00', )
assert next(frames) == (b'\x03\x00\x00\x00', )
pytest.raises(StopIteration, next, frames)
def test_empty_bot_no_marker(self):
"""Test parsing not BOT and no final marker with multi fragments."""
# 4 frames in 6 fragments with JPEG EOI marker (1 missing EOI)
bytestream = (b'\xFE\xFF\x00\xE0\x00\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\x00\x00\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xD9\x00'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\xFF\xD9'
b'\xFE\xFF\x00\xE0\x04\x00\x00\x00\x01\xFF\x00\x00')
frames = generate_pixel_data(bytestream, 4)
for ii in range(3):
next(frames)
msg = (r"The end of the encapsulated pixel data has been "
r"reached but one or more frame boundaries may have "
r"been missed; please confirm that the generated frame "
r"data is correct")
with pytest.warns(UserWarning, match=msg):
next(frames)
with pytest.raises(StopIteration):
next(frames)
def get_pixeldata(ds: "Dataset") -> "numpy.ndarray":
"""Use the GDCM package to decode *Pixel Data*.
Returns
-------
numpy.ndarray
A correctly sized (but not shaped) array of the entire data volume
Raises
------
ImportError
If the required packages are not available.
TypeError
If the image could not be read by GDCM or if the *Pixel Data* type is
unsupported.
AttributeError
If the decoded amount of data does not match the expected amount.
"""
if not HAVE_GDCM:
raise ImportError("The GDCM handler requires both gdcm and numpy")
if HAVE_GDCM_IN_MEMORY_SUPPORT:
gdcm_data_element = create_data_element(ds)
gdcm_image = create_image(ds, gdcm_data_element)
else:
gdcm_image_reader = create_image_reader(ds)
if not gdcm_image_reader.Read():
raise TypeError("GDCM could not read DICOM image")
gdcm_image = gdcm_image_reader.GetImage()
# GDCM returns char* as type str. Python 3 decodes this to
# unicode strings by default.
# The SWIG docs mention that they always decode byte streams
# as utf-8 strings for Python 3, with the `surrogateescape`
# error handler configured.
# Therefore, we can encode them back to their original bytearray
# representation on Python 3 by using the same parameters.
pixel_bytearray = gdcm_image.GetBuffer().encode("utf-8", "surrogateescape")
# Here we need to be careful because in some cases, GDCM reads a
# buffer that is too large, so we need to make sure we only include
# the first n_rows * n_columns * dtype_size bytes.
expected_length_bytes = get_expected_length(ds)
if ds.PhotometricInterpretation == 'YBR_FULL_422':
# GDCM has already resampled the pixel data, see PS3.3 C.7.6.3.1.2
expected_length_bytes = expected_length_bytes // 2 * 3
if len(pixel_bytearray) > expected_length_bytes:
# We make sure that all the bytes after are in fact zeros
padding = pixel_bytearray[expected_length_bytes:]
if numpy.any(numpy.frombuffer(padding, numpy.byte)):
pixel_bytearray = pixel_bytearray[:expected_length_bytes]
else:
# We revert to the old behavior which should then result
# in a Numpy error later on.
pass
numpy_dtype = pixel_dtype(ds)
arr = numpy.frombuffer(pixel_bytearray, dtype=numpy_dtype)
expected_length_pixels = get_expected_length(ds, 'pixels')
if arr.size != expected_length_pixels:
raise AttributeError(
f"Amount of pixel data {arr.size} does not match the "
f"expected data {expected_length_pixels}"
)
file_meta: "FileMetaDataset" = ds.file_meta # type: ignore[has-type]
tsyntax = cast(UID, file_meta.TransferSyntaxUID)
if (
config.APPLY_J2K_CORRECTIONS
and tsyntax in [JPEG2000, JPEG2000Lossless]
):
nr_frames = getattr(ds, 'NumberOfFrames', 1)
codestream = next(generate_pixel_data(ds.PixelData, nr_frames))[0]
params = get_j2k_parameters(codestream)
j2k_precision = cast(
int, params.setdefault("precision", ds.BitsStored)
)
j2k_sign = params.setdefault("is_signed", None)
if not j2k_sign and ds.PixelRepresentation == 1:
# Convert unsigned J2K data to 2's complement
shift = cast(int, ds.BitsAllocated) - j2k_precision
pixel_module = ds.group_dataset(0x0028)
pixel_module.PixelRepresentation = 0
dtype = pixel_dtype(pixel_module)
arr = (arr.astype(dtype) << shift).astype(numpy_dtype) >> shift
if should_change_PhotometricInterpretation_to_RGB(ds):
ds.PhotometricInterpretation = "RGB"
return arr.copy()
