def _check_is_anonymised_dataset_file_and_dir(
ds, tmp_path, anon_is_expected=True, ignore_private_tags=False
):
temp_filepath = str(tmp_path / "test.dcm")
try:
create.set_default_transfer_syntax(ds)
ds.file_meta = TEST_FILE_META
ds.save_as(temp_filepath, write_like_original=False)
if anon_is_expected:
assert is_anonymised_dataset(ds, ignore_private_tags)
assert is_anonymised_file(temp_filepath, ignore_private_tags)
assert is_anonymised_directory(tmp_path, ignore_private_tags)
else:
assert not is_anonymised_dataset(ds, ignore_private_tags)
assert not is_anonymised_file(temp_filepath, ignore_private_tags)
assert not is_anonymised_directory(tmp_path, ignore_private_tags)
finally:
remove_file(temp_filepath)
def test_anonymise_dataset_and_all_is_anonymised_functions(tmp_path):
# Create dataset with one instance of every identifying keyword and
# run basic anonymisation tests
ds = pydicom.dataset.Dataset()
for keyword in IDENTIFYING_KEYWORDS:
# Ignore file meta elements for now
tag = hex(pydicom.datadict.tag_for_keyword(keyword))
if pydicom.tag.Tag(tag).group == 0x0002:
continue
value = _get_non_anonymous_replacement_value(keyword)
setattr(ds, keyword, value)
_check_is_anonymised_dataset_file_and_dir(ds, tmp_path, anon_is_expected=False)
ds_anon = anonymise_dataset(ds)
_check_is_anonymised_dataset_file_and_dir(ds_anon, tmp_path, anon_is_expected=True)
# Test the anonymisation and check functions for each identifying
# element individually.
for elem in ds_anon.iterall():
# TODO: AffectedSOPInstanceUID and RequestedSOPInstanceUID
# are not writing to file. Investigate when UID anonymisation is
# implemented.
if elem.keyword in ("AffectedSOPInstanceUID", "RequestedSOPInstanceUID"):
continue
ds_single_non_anon_value = deepcopy(ds_anon)
setattr(
ds_single_non_anon_value,
elem.keyword,
_get_non_anonymous_replacement_value(elem.keyword),
)
_check_is_anonymised_dataset_file_and_dir(
ds_single_non_anon_value, tmp_path, anon_is_expected=False
)
ds_single_anon = anonymise_dataset(ds_single_non_anon_value)
_check_is_anonymised_dataset_file_and_dir(
ds_single_anon, tmp_path, anon_is_expected=True
)
# Test correct handling of private tags
ds_anon.add(pydicom.dataset.DataElement(0x0043102B, "SS", [4, 4, 0, 0]))
_check_is_anonymised_dataset_file_and_dir(
ds_anon, tmp_path, anon_is_expected=False, ignore_private_tags=False
)
_check_is_anonymised_dataset_file_and_dir(
ds_anon, tmp_path, anon_is_expected=True, ignore_private_tags=True
)
ds_anon.remove_private_tags()
_check_is_anonymised_dataset_file_and_dir(
ds_anon, tmp_path, anon_is_expected=True, ignore_private_tags=False
)
# Test blank anonymisation
# # Sanity check
_check_is_anonymised_dataset_file_and_dir(ds, tmp_path, anon_is_expected=False)
ds_anon_blank = anonymise_dataset(ds, replace_values=False)
_check_is_anonymised_dataset_file_and_dir(
ds_anon_blank, tmp_path, anon_is_expected=True
)
# Test handling of unknown tags by removing PatientName from
# baseline dict
patient_name_tag = pydicom.datadict.tag_for_keyword("PatientName")
try:
patient_name = get_baseline_dicom_dict().pop(patient_name_tag)
with pytest.raises(ValueError) as e_info:
anonymise_dataset(ds)
assert str(e_info.value).count(
"At least one of the non-private tags "
"within your DICOM file is not within "
"PyMedPhys's copy of the DICOM dictionary."
)
ds_anon_delete_unknown = anonymise_dataset(ds, delete_unknown_tags=True)
_check_is_anonymised_dataset_file_and_dir(
ds_anon_delete_unknown, tmp_path, anon_is_expected=True
)
with pytest.raises(AttributeError) as e_info:
ds_anon_delete_unknown.PatientName # pylint: disable = pointless-statement
assert str(e_info.value).count(
"'Dataset' object has no attribute " "'PatientName'"
)
ds_anon_ignore_unknown = anonymise_dataset(ds, delete_unknown_tags=False)
_check_is_anonymised_dataset_file_and_dir(
ds_anon_ignore_unknown, tmp_path, anon_is_expected=True
)
assert patient_name_tag in ds_anon_ignore_unknown
finally:
get_baseline_dicom_dict().setdefault(patient_name_tag, patient_name)
# Test copy_dataset=False:
anonymise_dataset(ds, copy_dataset=False)
assert is_anonymised_dataset(ds)
def test_anonymised_dataset_with_nested_name():
nested_name = dicom_dataset_from_dict(
{"OverrideSequence": [{"OperatorsName": "George"}]}
)
assert not is_anonymised_dataset(nested_name)
def test_anonymise_cli(tmp_path):
temp_filepath = str(tmp_path / "test.dcm")
try:
copyfile(TEST_FILEPATH, temp_filepath)
temp_anon_filepath = str(tmp_path / TEST_ANON_BASENAME)
# Basic file anonymisation
assert not is_anonymised_file(temp_filepath)
assert not exists(temp_anon_filepath)
anon_file_command = "pymedphys dicom anonymise".split() + [temp_filepath]
try:
subprocess.check_call(anon_file_command)
assert is_anonymised_file(temp_anon_filepath)
assert exists(temp_filepath)
finally:
remove_file(temp_anon_filepath)
# File anonymisation - preserve filenames
assert not is_anonymised_file(temp_filepath)
expected_anon_filepath = label_dicom_filepath_as_anonymised(temp_filepath)
assert not exists(expected_anon_filepath)
anon_file_pres_command = "pymedphys dicom anonymise -f".split() + [
temp_filepath
]
try:
subprocess.check_call(anon_file_pres_command)
assert is_anonymised_file(expected_anon_filepath)
assert exists(temp_filepath)
finally:
remove_file(expected_anon_filepath)
# File anonymisation - clear values
assert not is_anonymised_file(temp_filepath)
assert not exists(temp_anon_filepath)
temp_cleared_anon_filepath = str(tmp_path / TEST_ANON_BASENAME)
anon_file_clear_command = "pymedphys dicom anonymise -c".split() + [
temp_filepath
]
try:
subprocess.check_call(anon_file_clear_command)
assert is_anonymised_file(temp_cleared_anon_filepath)
assert pydicom.dcmread(temp_cleared_anon_filepath).PatientName == ""
assert exists(temp_filepath)
finally:
remove_file(temp_cleared_anon_filepath)
# File anonymisation - leave keywords unchanged
assert not is_anonymised_file(temp_filepath)
assert not exists(temp_anon_filepath)
anon_file_keep_command = (
"pymedphys dicom anonymise".split()
+ [temp_filepath]
+ "-k PatientName".split()
)
try:
subprocess.check_call(anon_file_keep_command)
assert not is_anonymised_file(temp_anon_filepath)
ds = pydicom.dcmread(temp_anon_filepath)
ds.PatientName = "Anonymous"
assert is_anonymised_dataset(ds)
assert exists(temp_filepath)
finally:
remove_file(temp_anon_filepath)
# File anonymisation - private tag handling
assert not is_anonymised_file(temp_filepath)
assert not exists(temp_anon_filepath)
anon_file_private_command = "pymedphys dicom anonymise -p".split() + [
temp_filepath
]
try:
subprocess.check_call(anon_file_private_command)
assert not is_anonymised_file(temp_anon_filepath)
assert is_anonymised_file(temp_anon_filepath, ignore_private_tags=True)
assert exists(temp_filepath)
finally:
remove_file(temp_anon_filepath)
# TODO: File anonymisation - unknown tag handling
# # Calling a subprocess reloads BASELINE_DICOM_DICT...
# Basic dir anonymisation
assert not is_anonymised_directory(tmp_path)
assert not exists(temp_anon_filepath)
anon_dir_command = "pymedphys dicom anonymise".split() + [str(tmp_path)]
try:
subprocess.check_call(anon_dir_command)
assert is_anonymised_file(temp_anon_filepath)
assert exists(temp_filepath)
finally:
remove_file(temp_anon_filepath)
finally:
remove_file(temp_filepath)
def test_anonymised_dataset_with_empty_patient_sex():
blank_sex_ds = dicom_dataset_from_dict({"PatientSex": None})
assert is_anonymised_dataset(blank_sex_ds)
hardcode_replace_ds = anonymise_dataset(blank_sex_ds)
assert hardcode_replace_ds["PatientSex"].value is None
