def decode(data_element, dicom_character_set):
"""Apply the DICOM character encoding to the data element
data_element -- DataElement instance containing a value to convert
dicom_character_set -- the value of Specific Character Set (0008,0005),
which may be a single value,
a multiple value (code extension), or
may also be '' or None.
If blank or None, ISO_IR 6 is used.
"""
if not dicom_character_set:
dicom_character_set = ['ISO_IR 6']
encodings = convert_encodings(dicom_character_set)
# decode the string value to unicode
# PN is special case as may have 3 components with differenct chr sets
if data_element.VR == "PN":
# logger.warn("%s ... type: %s" %(str(data_element), type(data_element.VR)))
if in_py3:
if data_element.VM == 1:
data_element.value = data_element.value.decode(encodings)
else:
data_element.value = [
val.decode(encodings) for val in data_element.value
]
else:
if data_element.VM == 1:
data_element.value = PersonNameUnicode(data_element.value,
encodings)
else:
data_element.value = [
PersonNameUnicode(value, encodings)
for value in data_element.value
]
if data_element.VR in text_VRs:
# Remove the first encoding if this is a multi-byte encoding
if len(encodings) > 1:
del encodings[0]
# You can't re-decode unicode (string literals in py3)
if data_element.VM == 1:
if isinstance(data_element.value, unicode):
return
data_element.value = clean_escseq(
data_element.value.decode(encodings[0]), encodings)
else:
output = list()
for value in data_element.value:
if isinstance(value, unicode):
output.append(value)
else:
output.append(
clean_escseq(value.decode(encodings[0]), encodings))
data_element.value = output
def decode(data_element, dicom_character_set):
"""Apply the DICOM character encoding to the data element
data_element -- DataElement instance containing a value to convert
dicom_character_set -- the value of Specific Character Set (0008,0005),
which may be a single value,
a multiple value (code extension), or
may also be '' or None.
If blank or None, ISO_IR 6 is used.
"""
if not dicom_character_set:
dicom_character_set = ['ISO_IR 6']
have_character_set_list = True
try:
dicom_character_set.append # check if is list-like object
except AttributeError:
have_character_set_list = False
if have_character_set_list:
if not dicom_character_set[0]:
dicom_character_set[0] = "ISO_IR 6"
else:
dicom_character_set = [dicom_character_set]
encodings = [python_encoding[x] for x in dicom_character_set]
if len(encodings) == 1:
encodings = [encodings[0]]*3
if len(encodings) == 2:
encodings.append(encodings[1])
# decode the string value to unicode
# PN is special case as may have 3 components with differenct chr sets
if data_element.VR == "PN":
# logger.warn("%s ... type: %s" %(str(data_element), type(data_element.VR)))
if data_element.VM == 1:
data_element.value = PersonNameUnicode(data_element.value, encodings)
else:
data_element.value = [PersonNameUnicode(value, encodings)
for value in data_element.value]
if data_element.VR in ['SH', 'LO', 'ST', 'LT', 'UT']:
# Remove the first encoding if this is a multi-byte encoding
if len(encodings) > 1:
del encodings[0]
if data_element.VM == 1:
data_element.value = clean_escseq(
data_element.value.decode(
encodings[0]), encodings)
else:
data_element.value = [clean_escseq(
value.decode(encodings[0]), encodings)
for value in data_element.value]
def testUnicodeJp(self):
"""PN: 3component in unicode works (Japanese)............................"""
# Example name from PS3.5-2008 section H p. 98
pn = PersonNameUnicode(
"""Yamada^Tarou=\033$B;3ED\033(B^\033$BB@O:\033(B=\033$B$d$^$@\033(B^\033$B$?$m$&\033(B""",
[default_encoding, 'iso2022_jp'])
expected = ("Yamada", "Tarou")
got = (pn.family_name, pn.given_name)
self.assertEqual(got, expected, "PN: Expected single_byte name '{0!s}', got '{1!s}'".format(expected, got))
def testUnicodeKr(self):
"""PN: 3component in unicode works (Korean).............................."""
# Example name from PS3.5-2008 section I.2 p. 101
pn = PersonNameUnicode(
"""Hong^Gildong=\033$)C\373\363^\033$)C\321\316\324\327=\033$)C\310\253^\033$)C\261\346\265\277""",
[default_encoding, 'euc_kr'])
expected = ("Hong", "Gildong")
got = (pn.family_name, pn.given_name)
self.assertEqual(got, expected, "PN: Expected single_byte name '{0!s}', got '{1!s}'".format(expected, got))
# Copyright (c) 2008-2012 Darcy Mason
# This file is part of pydicom, relased under an MIT license.
# See the file license.txt included with this distribution, also
# available at https://github.com/darcymason/pydicom
import Tkinter
from dicom.valuerep import PersonNameUnicode
default_encoding = 'iso8859'
root = Tkinter.Tk()
# root.geometry("%dx%d%+d%+d" % (800, 600, 0, 0))
person_names = [
PersonNameUnicode(
"""Yamada^Tarou=\033$B;3ED\033(B^\033$BB@O:\033(B=\033$B$d$^$@\033(B^\033$B$?$m$&\033(B""",
[default_encoding, 'iso2022_jp']), # DICOM standard 2008-PS3.5 H.3 p 98
PersonNameUnicode(
"""Wang^XiaoDong=\xcd\xf5\x5e\xd0\xa1\xb6\xab=""",
[default_encoding, 'GB18030']), # DICOM standard 2008-PS3.5 J.3 p 105
PersonNameUnicode(
"""Wang^XiaoDong=\xe7\x8e\x8b\x5e\xe5\xb0\x8f\xe6\x9d\xb1=""",
[default_encoding, 'UTF-8']), # DICOM standard 2008-PS3.5 J.1 p 104
PersonNameUnicode(
"""Hong^Gildong=\033$)C\373\363^\033$)C\321\316\324\327=\033$)C\310\253^\033$)C\261\346\265\277""",
[default_encoding, 'euc_kr']), # DICOM standard 2008-PS3.5 I.2 p 101
]
for person_name in person_names:
label = Tkinter.Label(text=person_name)
label.pack()
root.mainloop()