def test_get_dataset(self):
"""Test the different functions to get lists of data files."""
# Test base locations
charbase = os.path.join(DATA_ROOT, 'charset_files')
self.assertTrue(os.path.exists(charbase))
testbase = os.path.join(DATA_ROOT, 'test_files')
self.assertTrue(os.path.exists(testbase))
# Test file get
chardata = get_charset_files()
self.assertTrue(len(chardata) > 15)
# Test that top level file is included
bases = [basename(x) for x in chardata]
# Test that subdirectory files included
testdata = get_testdata_files()
bases = [basename(x) for x in testdata]
self.assertTrue('2693' in bases)
self.assertTrue(len(testdata) > 70)
# The files should be from their respective bases
[self.assertTrue(testbase in x) for x in testdata]
[self.assertTrue(charbase in x) for x in chardata]
def test_get_dataset(self):
"""Test the different functions to get lists of data files."""
# Test base locations
charbase = os.path.join(DATA_ROOT, 'charset_files')
assert os.path.exists(charbase)
testbase = os.path.join(DATA_ROOT, 'test_files')
assert os.path.exists(testbase)
# Test file get
chardata = get_charset_files()
assert 15 < len(chardata)
# Test that top level file is included
bases = [basename(x) for x in chardata]
# Test that subdirectory files included
testdata = get_testdata_files()
bases = [basename(x) for x in testdata]
assert '2693' in bases
assert 70 < len(testdata)
# The files should be from their respective bases
for x in testdata:
assert testbase in x
for x in chardata:
assert charbase in x
def test_japanese_multi_byte_personname(self):
"""Test japanese person name which has multi byte strings are
correctly encoded."""
file_path = get_charset_files('chrH32.dcm')[0]
ds = dcmread(file_path)
ds.decode()
if hasattr(ds.PatientName, 'original_string'):
original_string = ds.PatientName.original_string
ds.PatientName.original_string = None
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds_out = dcmread(fp)
assert original_string == ds_out.PatientName.original_string
japanese_pn = PersonName(u"Mori^Ogai=森^鷗外=もり^おうがい")
pyencs = pydicom.charset.convert_encodings(
["ISO 2022 IR 6", "ISO 2022 IR 87", "ISO 2022 IR 159"])
actual_encoded = bytes(japanese_pn.encode(pyencs))
expect_encoded = (
b"\x4d\x6f\x72\x69\x5e\x4f\x67\x61\x69\x3d\x1b\x24\x42\x3f"
b"\x39\x1b\x28\x42\x5e\x1b\x24\x28\x44\x6c\x3f\x1b\x24\x42"
b"\x33\x30\x1b\x28\x42\x3d\x1b\x24\x42\x24\x62\x24\x6a\x1b"
b"\x28\x42\x5e\x1b\x24\x42\x24\x2a\x24\x26\x24\x2c\x24\x24"
b"\x1b\x28\x42")
assert expect_encoded == actual_encoded
def test_get_dataset(self):
"""Test the different functions to get lists of data files."""
# Test base locations
charbase = os.path.join(DATA_ROOT, 'charset_files')
self.assertTrue(os.path.exists(charbase))
testbase = os.path.join(DATA_ROOT, 'test_files')
self.assertTrue(os.path.exists(testbase))
# Test file get
chardata = get_charset_files()
self.assertTrue(len(chardata) > 15)
# Test that top level file is included
bases = [basename(x) for x in chardata]
# Test that subdirectory files included
testdata = get_testdata_files()
bases = [basename(x) for x in testdata]
self.assertTrue('2693' in bases)
self.assertTrue(len(testdata) > 70)
# The files should be from their respective bases
[self.assertTrue(testbase in x) for x in testdata]
[self.assertTrue(charbase in x) for x in chardata]
def test_charset_patient_names(self, filename, patient_name):
"""Test patient names are correctly decoded and encoded."""
# check that patient names are correctly read
file_path = get_charset_files(filename + '.dcm')[0]
ds = dcmread(file_path)
ds.decode()
assert patient_name == ds.PatientName
# check that patient names are correctly written back
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds = dcmread(fp)
assert patient_name == ds.PatientName
# check that patient names are correctly written back
# without original byte string (PersonName3 only)
if hasattr(ds.PatientName, 'original_string'):
ds.PatientName.original_string = None
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds = dcmread(fp)
assert patient_name == ds.PatientName
def test_charset_patient_names(self, filename, patient_name):
"""Test patient names are correctly decoded and encoded."""
# check that patient names are correctly read
file_path = get_charset_files(filename + '.dcm')[0]
ds = dcmread(file_path)
ds.decode()
assert patient_name == ds.PatientName
# check that patient names are correctly written back
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds = dcmread(fp)
assert patient_name == ds.PatientName
# check that patient names are correctly written back
# without original byte string (PersonName3 only)
if hasattr(ds.PatientName, 'original_string'):
ds.PatientName.original_string = None
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds = dcmread(fp)
assert patient_name == ds.PatientName
def test_decoding_with_specific_tags(self):
"""Decoding is correctly applied even if Specific Character Set
is not in specific tags..."""
rus_file = get_charset_files("chrRuss.dcm")[0]
ds = dcmread(rus_file, specific_tags=['PatientName'])
ds.decode()
assert 2 == len(ds) # specific character set is always decoded
assert u'Люкceмбypг' == ds.PatientName
def test_decoding_with_specific_tags(self):
"""Decoding is correctly applied even if Specific Character Set
is not in specific tags..."""
rus_file = get_charset_files("chrRuss.dcm")[0]
ds = dcmread(rus_file, specific_tags=['PatientName'])
ds.decode()
assert 2 == len(ds) # specific character set is always decoded
assert u'Люкceмбypг' == ds.PatientName
def test_get_dataset_pattern(self):
"""Test that pattern is working properly."""
pattern = 'CT_small*'
filename = get_testdata_files(pattern)
assert filename[0].endswith('CT_small.dcm')
pattern = 'chrX1*'
filename = get_charset_files(pattern)
assert filename[0].endswith('chrX1.dcm')
def test_get_dataset_pattern(self):
"""Test that pattern is working properly."""
pattern = 'CT_small'
filename = get_testdata_files(pattern)
self.assertTrue(filename[0].endswith('CT_small.dcm'))
pattern = 'chrX1'
filename = get_charset_files(pattern)
self.assertTrue(filename[0].endswith('chrX1.dcm'))
def test_inherited_character_set_in_sequence(self):
"""charset: can read and decode SQ with parent encoding............."""
ds = dcmread(get_charset_files('chrSQEncoding1.dcm')[0])
ds.decode()
# These datasets inside of the SQ shall be decoded with the parent
# dataset's encoding
sequence = ds[0x32, 0x1064][0]
assert ['shift_jis', 'iso2022_jp'] == sequence._character_set
assert u'ﾔﾏﾀﾞ^ﾀﾛｳ=山田^太郎=やまだ^たろう' == sequence.PatientName
def test_inherited_character_set_in_sequence(self):
"""charset: can read and decode SQ with parent encoding............."""
ds = dcmread(get_charset_files('chrSQEncoding1.dcm')[0])
ds.decode()
# These datasets inside of the SQ shall be decoded with the parent
# dataset's encoding
sequence = ds[0x32, 0x1064][0]
assert ['shift_jis', 'iso2022_jp'] == sequence._character_set
assert u'ﾔﾏﾀﾞ^ﾀﾛｳ=山田^太郎=やまだ^たろう' == sequence.PatientName
def test_changed_character_set(self):
# Regression test for #629
multiPN_name = get_charset_files("chrFrenMulti.dcm")[0]
ds = dcmread(multiPN_name) # is Latin-1
ds.SpecificCharacterSet = 'ISO_IR 192'
from pydicom.filebase import DicomBytesIO
fp = DicomBytesIO()
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds_out = dcmread(fp)
# we expect UTF-8 encoding here
assert b'Buc^J\xc3\xa9r\xc3\xb4me' == ds_out.get_item(0x00100010).value
def test_changed_character_set(self):
# Regression test for #629
multiPN_name = get_charset_files("chrFrenMulti.dcm")[0]
ds = dcmread(multiPN_name) # is Latin-1
ds.SpecificCharacterSet = 'ISO_IR 192'
from pydicom.filebase import DicomBytesIO
fp = DicomBytesIO()
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds_out = dcmread(fp)
# we expect UTF-8 encoding here
assert b'Buc^J\xc3\xa9r\xc3\xb4me' == ds_out.get_item(0x00100010).value
def test_nested_character_sets(self):
"""charset: can read and decode SQ with different encodings........."""
ds = dcmread(get_charset_files("chrSQEncoding.dcm")[0])
ds.decode()
# These datasets inside of the SQ cannot be decoded with
# default_encoding OR UTF-8 (the parent dataset's encoding).
# Instead, we make sure that it is decoded using the
# (0008,0005) tag of the dataset
sequence = ds[0x32, 0x1064][0]
assert ['shift_jis', 'iso2022_jp'] == sequence._character_set
assert u'ﾔﾏﾀﾞ^ﾀﾛｳ=山田^太郎=やまだ^たろう' == sequence.PatientName
def test_nested_character_sets(self):
"""charset: can read and decode SQ with different encodings........."""
ds = dcmread(get_charset_files("chrSQEncoding.dcm")[0])
ds.decode()
# These datasets inside of the SQ cannot be decoded with
# default_encoding OR UTF-8 (the parent dataset's encoding).
# Instead, we make sure that it is decoded using the
# (0008,0005) tag of the dataset
sequence = ds[0x32, 0x1064][0]
assert ['shift_jis', 'iso2022_jp'] == sequence._character_set
assert u'ﾔﾏﾀﾞ^ﾀﾛｳ=山田^太郎=やまだ^たろう' == sequence.PatientName
def test_japanese_multi_byte_personname(self):
"""Test japanese person name which has multi byte strings are
correctly encoded."""
file_path = get_charset_files('chrH32.dcm')[0]
ds = dcmread(file_path)
ds.decode()
if hasattr(ds.PatientName, 'original_string'):
original_string = ds.PatientName.original_string
ds.PatientName.original_string = None
fp = DicomBytesIO()
fp.is_implicit_VR = False
fp.is_little_endian = True
ds.save_as(fp, write_like_original=False)
fp.seek(0)
ds_out = dcmread(fp)
assert original_string == ds_out.PatientName.original_string
def test_get_dataset(self):
"""Test the different functions to get lists of data files."""
# The cached files downloaded from the pydicom-data repo
cached_data_test_files = str(get_data_dir())
# If pydicom-data is available locally
ext_path = None
if 'pydicom-data' in external_data_sources():
ext_path = os.fspath(
external_data_sources()['pydicom-data'].data_path)
# Test base locations
charbase = os.path.join(DATA_ROOT, 'charset_files')
assert os.path.exists(charbase)
testbase = os.path.join(DATA_ROOT, 'test_files')
assert os.path.exists(testbase)
# Test file get
chardata = get_charset_files()
assert 15 < len(chardata)
# Test that top level file is included
bases = [basename(x) for x in chardata]
# Test that subdirectory files included
testdata = get_testdata_files()
bases = [basename(x) for x in testdata]
assert '2693' in bases
assert 70 < len(testdata)
# The files should be from their respective bases
for x in testdata:
# Don't check files from external sources other than pydicom-data
if (testbase not in x and cached_data_test_files not in x
and (ext_path not in x if ext_path else True)):
continue
assert (testbase in x or cached_data_test_files in x
or (ext_path in x if ext_path else False))
for x in chardata:
assert charbase in x
def test_charset_patient_names(self, filename, patient_name):
"""Test pixel_array for big endian matches little."""
file_path = get_charset_files(filename + '.dcm')[0]
ds = dcmread(file_path)
ds.decode()
assert patient_name == ds.PatientName
# Copyright 2008-2018 pydicom authors. See LICENSE file for details.
"""unittest cases for pydicom.charset module"""
import unittest
from pydicom.data import get_charset_files
from pydicom.data import get_testdata_files
import pydicom.charset
from pydicom.dataelem import DataElement
from pydicom import dcmread
latin1_file = get_charset_files("chrFren.dcm")[0]
jp_file = get_charset_files("chrH31.dcm")[0]
multiPN_file = get_charset_files("chrFrenMulti.dcm")[0]
sq_encoding_file = get_charset_files("chrSQEncoding.dcm")[0]
sq_encoding1_file = get_charset_files("chrSQEncoding1.dcm")[0]
explicit_ir6_file = get_charset_files("chrJapMultiExplicitIR6.dcm")[0]
normal_file = get_testdata_files("CT_small.dcm")[0]
class CharsetTests(unittest.TestCase):
def test_latin1(self):
"""charset: can read and decode latin_1 file........................"""
ds = dcmread(latin1_file)
ds.decode()
# Make sure don't get unicode encode error on converting to string
expected = u'Buc^J\xe9r\xf4me'
got = ds.PatientName
self.assertEqual(expected, got,
"Expected %r, got %r" % (expected, got))
"""List summary info for the test files in the charset directory"""
from glob import glob
import logging
import os
import pydicom
from pydicom.data import get_charset_files
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO, format='%(message)s')
logger = logging.getLogger('charlist')
# Get list of all DICOM files
names = get_charset_files("*.dcm")
# Collect summary information from the files
files_info = []
for name in names:
ds = pydicom.dcmread(name)
ds.decode()
fname = os.path.basename(name)
try:
files_info.append((fname, ds.SpecificCharacterSet, ds.PatientName))
except Exception:
try:
requested_seq = ds.RequestedProcedureCodeSequence[0]
spec_charset = requested_seq.SpecificCharacterSet
patient_name = requested_seq.PatientName
files_info.append((fname,
# -*- coding: utf-8 -*-
# Copyright 2008-2018 pydicom authors. See LICENSE file for details.
"""unittest cases for pydicom.charset module"""
import unittest
import pytest
from pydicom.data import get_charset_files
from pydicom.data import get_testdata_files
import pydicom.charset
from pydicom.dataelem import DataElement, RawDataElement, DataElement_from_raw
from pydicom import dcmread, Dataset
latin1_file = get_charset_files("chrFren.dcm")[0]
jp_file = get_charset_files("chrH31.dcm")[0]
multiPN_file = get_charset_files("chrFrenMulti.dcm")[0]
sq_encoding_file = get_charset_files("chrSQEncoding.dcm")[0]
sq_encoding1_file = get_charset_files("chrSQEncoding1.dcm")[0]
explicit_ir6_file = get_charset_files("chrJapMultiExplicitIR6.dcm")[0]
normal_file = get_testdata_files("CT_small.dcm")[0]
class CharsetTests(unittest.TestCase):
def test_latin1(self):
"""charset: can read and decode latin_1 file........................"""
ds = dcmread(latin1_file)
ds.decode()
# Make sure don't get unicode encode error on converting to string
expected = u'Buc^Jérôme'
got = ds.PatientName
