def exercise_detect_binary():
binary_string = '\xff\xf8\x00\x00\x00\x00\x00\x00'
from iotbx.cif import reader
try:
reader(input_string=binary_string)
except CifParserError, e:
pass
def exercise_mmcif_structure_factors():
miller_arrays = cif.reader(input_string=r3adrsf).as_miller_arrays()
assert len(miller_arrays) == 16
hl_coeffs = find_miller_array_from_labels(
miller_arrays, ','.join([
'scale_group_code=1', 'crystal_id=2', 'wavelength_id=3',
'_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso']))
assert hl_coeffs.is_hendrickson_lattman_array()
assert hl_coeffs.size() == 2
mas_as_cif_block = cif.miller_arrays_as_cif_block(
hl_coeffs, column_names=('_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso'))
abcd = []
for key in ('_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso'):
assert key in mas_as_cif_block.cif_block.keys()
abcd.append(flex.double(mas_as_cif_block.cif_block[key]))
hl_coeffs_from_cif_block = flex.hendrickson_lattman(*abcd)
assert approx_equal(hl_coeffs.data(), hl_coeffs_from_cif_block)
f_meas_au = find_miller_array_from_labels(
miller_arrays, ','.join([
'scale_group_code=1', 'crystal_id=1', 'wavelength_id=1',
'_refln.F_meas_au', '_refln.F_meas_sigma_au']))
assert f_meas_au.is_xray_amplitude_array()
assert f_meas_au.size() == 5
assert f_meas_au.sigmas() is not None
assert f_meas_au.space_group_info().symbol_and_number() == 'C 1 2 1 (No. 5)'
assert approx_equal(f_meas_au.unit_cell().parameters(),
(163.97, 45.23, 110.89, 90.0, 131.64, 90.0))
pdbx_I_plus_minus = find_miller_array_from_labels(
miller_arrays, ','.join(
['_refln.pdbx_I_plus', '_refln.pdbx_I_plus_sigma',
'_refln.pdbx_I_minus', '_refln.pdbx_I_minus_sigma']))
assert pdbx_I_plus_minus.is_xray_intensity_array()
assert pdbx_I_plus_minus.anomalous_flag()
assert pdbx_I_plus_minus.size() == 21
assert pdbx_I_plus_minus.unit_cell() is None # no symmetry information in
assert pdbx_I_plus_minus.space_group() is None # this CIF block
#
miller_arrays = cif.reader(input_string=r3ad7sf).as_miller_arrays()
assert len(miller_arrays) == 11
f_calc = find_miller_array_from_labels(
miller_arrays, ','.join([
'crystal_id=2', 'wavelength_id=1', '_refln.F_calc', '_refln.phase_calc']))
assert f_calc.is_complex_array()
assert f_calc.size() == 4
#
miller_arrays = cif.reader(input_string=integer_observations).as_miller_arrays()
assert len(miller_arrays) == 2
assert isinstance(miller_arrays[0].data(), flex.double)
assert isinstance(miller_arrays[0].sigmas(), flex.double)
#
miller_arrays = cif.reader(input_string=r3v56sf).as_miller_arrays()
assert len(miller_arrays) == 2
for ma in miller_arrays: assert ma.is_complex_array()
assert miller_arrays[0].info().labels == [
'r3v56sf', '_refln.pdbx_DELFWT', '_refln.pdbx_DELPHWT']
assert miller_arrays[1].info().labels == [
'r3v56sf', '_refln.pdbx_FWT', '_refln.pdbx_PHWT']
def exercise_validation():
cd = validation.smart_load_dictionary(name="cif_core.dic")
assert isinstance(cd.deepcopy(), validation.dictionary)
assert cd.deepcopy() == cd
assert isinstance(cd.copy(), validation.dictionary)
assert cd.copy() == cd
#
cm_invalid = cif.reader(input_string=cif_invalid).model()
s = StringIO()
cm_invalid.validate(cd, out=s)
assert sorted(cd.err.errors.keys()) == [
2001, 2002, 2101, 2102, 2501, 2503, 2504, 2505, 2506]
assert sorted(cd.err.warnings.keys()) == [1001, 1002, 1003]
cm_valid = cif.reader(input_string=cif_valid).model()
cd.err.reset()
s = StringIO()
cm_valid.validate(cd, out=s)
assert len(cd.err.errors.keys()) == 0
assert len(cd.err.warnings.keys()) == 0
cd2 = validation.smart_load_dictionary(name="cif_mm.dic")
cm_invalid_2 = cif.reader(input_string=cif_invalid_2).model()
s = StringIO()
cm_invalid_2.validate(cd2, out=s)
assert sorted(cd2.err.errors.keys()) == [
2001, 2101, 2102, 2201, 2202, 2203, 2301, 2503, 2504]
assert cd2.err.error_count == 12
assert sorted(cd2.err.warnings.keys()) == [1001, 1002]
def exercise_syntax_errors():
empty_loop_str = """\
data_fred
loop_
loop_
_a
_b
1 2
3 4
"""
try:
cif.reader(input_string=empty_loop_str)
except CifParserError as e:
pass
else:
raise Exception_expected
bad_semicolon_text_field = """\
data_sucrose
_a 1
_exptl_absorpt_process_details
;
Final HKLF 4 output contains 64446 reflections, Rint = 0.0650
(47528 with I > 3sig(I), Rint = 0.0624);
"""
try:
cif.reader(input_string=bad_semicolon_text_field)
except CifParserError as e:
pass
else:
raise Exception_expected
def exercise_validation():
cd = validation.smart_load_dictionary(name="cif_core.dic")
assert isinstance(cd.deepcopy(), validation.dictionary)
assert cd.deepcopy() == cd
assert isinstance(cd.copy(), validation.dictionary)
assert cd.copy() == cd
#
cm_invalid = cif.reader(input_string=cif_invalid).model()
s = StringIO()
cm_invalid.validate(cd, out=s)
assert sorted(cd.err.errors.keys()) == [
2001, 2002, 2101, 2102, 2501, 2503, 2504, 2505, 2506
]
assert sorted(cd.err.warnings.keys()) == [1001, 1002, 1003]
cm_valid = cif.reader(input_string=cif_valid).model()
cd.err.reset()
s = StringIO()
cm_valid.validate(cd, out=s)
assert len(list(cd.err.errors.keys())) == 0
assert len(list(cd.err.warnings.keys())) == 0
cd2 = validation.smart_load_dictionary(name="cif_mm.dic")
cm_invalid_2 = cif.reader(input_string=cif_invalid_2).model()
s = StringIO()
cm_invalid_2.validate(cd2, out=s)
assert sorted(cd2.err.errors.keys()) == [
2001, 2101, 2102, 2201, 2202, 2203, 2301, 2503, 2504
]
assert cd2.err.error_count == 12
assert sorted(cd2.err.warnings.keys()) == [1001, 1002]
def run(args, out=sys.stdout):
if len(args) == 0: args = ["--help"]
command_line = (option_parser(
usage="iotbx.cif.validate filepath|directory [options]").option(
None, "--file_ext", action="store", default="cif").option(
None, "--dic", action="append", dest="dictionaries").option(
None, "--show_warnings", action="store_true").option(
None, "--show_timings", action="store_true").option(
None,
"--strict",
action="store",
type="bool",
default="true")).process(args=args)
if len(command_line.args) != 1:
command_line.parser.show_help()
return
total_timer = time_log("total").start()
filepath = command_line.args[0]
if not os.path.isabs(filepath):
abs_path = libtbx.env.find_in_repositories(relative_path=filepath)
if abs_path is None:
abs_path = libtbx.env.find_in_repositories(relative_path=filepath,
test=os.path.isfile)
if abs_path is not None: filepath = abs_path
cif_dics = command_line.options.dictionaries
if cif_dics is None:
cif_dics = ["cif_core.dic"]
cif_dic = validation.smart_load_dictionary(name=cif_dics[0])
if len(cif_dics) > 1:
[
cif_dic.update(validation.smart_load_dictionary(name=d))
for d in cif_dics[1:]
]
show_warnings = command_line.options.show_warnings == True
show_timings = command_line.options.show_timings == True
strict = command_line.options.strict
if os.path.isdir(filepath):
file_ext = command_line.options.file_ext
crawl(filepath,
file_ext=file_ext,
cif_dic=cif_dic,
show_warnings=show_warnings,
show_timings=show_timings,
strict=strict)
elif os.path.isfile(filepath):
cm = cif.reader(file_path=filepath, strict=strict).model()
cm.validate(cif_dic, show_warnings=show_warnings)
else:
try:
file_object = urllib.request.urlopen(filepath)
except urllib.error.URLError as e:
pass
else:
cm = cif.reader(file_object=file_object, strict=strict).model()
cm.validate(cif_dic, show_warnings=show_warnings)
if show_timings:
total_timer.stop()
print(total_timer.report())
def exercise_build_with_wavelength():
m = cif.reader(input_string=cif_xray_structure_with_wavelength).model()
xs = cif.builders.crystal_structure_builder(m['global']).structure
assert approx_equal(xs.wavelength, 1.54184)
cif_xray_structure_missing_wavelength = \
cif_xray_structure_with_wavelength.replace('1.54184', '?')
m = cif.reader(input_string=cif_xray_structure_missing_wavelength).model()
xs = cif.builders.crystal_structure_builder(m['global']).structure
assert xs.wavelength == None
def exercise_syntax_errors():
empty_loop_str = """\
data_fred
loop_
loop_
_a
_b
1 2
3 4
"""
try:
cif.reader(input_string=empty_loop_str)
except CifParserError, e:
pass
def smart_load_dictionary(name=None,
file_path=None,
url=None,
registry_location=cifdic_register_url,
save_local=False,
store_dir=None):
from iotbx import cif
assert [name, file_path, url].count(None) < 3
cif_dic = None
if store_dir is None:
store_dir = libtbx.env.under_dist(module_name='iotbx',
path='cif/dictionaries')
if name is not None and [file_path, url].count(None) == 2:
if file_path is None:
if os.path.isfile(name):
file_path = name
else:
file_path = os.path.join(store_dir, name)
if not os.path.isfile(file_path):
gzip_path = file_path + '.gz'
if os.path.isfile(gzip_path):
if save_local:
gz = smart_open.for_reading(gzip_path)
f = smart_open.for_writing(file_path)
shutil.copyfileobj(gz, f)
gz.close()
f.close()
else:
file_path = gzip_path
if file_path is not None and os.path.isfile(file_path):
file_object = smart_open.for_reading(file_path)
cif_dic = dictionary(cif.reader(file_object=file_object).model())
file_object.close()
else:
if url is None:
url = locate_dictionary(name, registry_location=registry_location)
file_object = urlopen(url)
if save_local:
if name is None:
name = os.path.basename(url)
f = open(os.path.join(store_dir, name), 'wb')
shutil.copyfileobj(file_object, f)
f.close()
cif_dic = dictionary(
cif.reader(file_path=os.path.join(store_dir, name)).model())
else:
cif_dic = dictionary(cif.reader(file_object=file_object).model())
assert cif_dic is not None
return cif_dic
def exercise_miller_arrays_as_cif_block():
from iotbx.cif import reader
cif_model = reader(input_string=cif_miller_array,
builder=cif.builders.cif_model_builder()).model()
ma_builder = cif.builders.miller_array_builder(cif_model['global'])
ma1 = ma_builder.arrays()['_refln_F_squared_meas']
mas_as_cif_block = cif.miller_arrays_as_cif_block(ma1,
array_type='meas',
format="corecif")
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 1j] * ma1.size())),
array_type='calc')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 2j] * ma1.size())),
column_names=['_refln_A_calc', '_refln_B_calc'])
for key in ('_refln_F_squared_meas', '_refln_F_squared_sigma',
'_refln_F_calc', '_refln_phase_calc', '_refln_A_calc',
'_refln_A_calc'):
assert key in mas_as_cif_block.cif_block.keys(), key
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(ma1,
array_type='meas',
format="mmcif")
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 1j] * ma1.size())),
array_type='calc')
for key in ('_refln.F_squared_meas', '_refln.F_squared_sigma',
'_refln.F_calc', '_refln.phase_calc',
'_space_group_symop.operation_xyz', '_cell.length_a',
'_refln.index_h'):
assert key in mas_as_cif_block.cif_block.keys()
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1,
column_names=[
'_diffrn_refln_intensity_net', '_diffrn_refln_intensity_sigma'
],
miller_index_prefix='_diffrn_refln')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.std_string(ma1.size(), 'om')),
column_name='_diffrn_refln_intensity_u')
for key in ('_diffrn_refln_intensity_net', '_diffrn_refln_intensity_sigma',
'_diffrn_refln_intensity_u'):
assert key in mas_as_cif_block.cif_block.keys()
#
try:
reader(input_string=cif_global)
except CifParserError, e:
pass
def intensity_array_from_cif_file(cif_file):
"""Return an intensity miller array from a cif file."""
model = cif.reader(file_path=cif_file).build_crystal_structures()["1"]
ic = (model.structure_factors(
anomalous_flag=True, d_min=0.4,
algorithm="direct").f_calc().as_intensity_array())
return ic
def run(filename):
from iotbx import cif
if not os.path.exists(filename): return None
complete_cif_data = {}
cm = cif.reader(filename, strict=False, raise_if_errors=False).model()
for code, rc in cm.items():
for key, item in rc.items():
cif_key = key.split('.')[0]
sk = key.split(".")[1].strip()
complete_cif_data.setdefault(cif_key, [])
if type(item) == type(''):
item = [item]
else:
continue
for i, row in enumerate(item):
if len(complete_cif_data[cif_key]) < i + 1:
complete_cif_data[cif_key].append(empty())
func = get_func(cif_key, sk)
row = get_typed_field(cif_key, sk, row, func=func)
setattr(complete_cif_data[cif_key][i], sk, row)
for i, loop in enumerate(rc.iterloops()):
if not loop: continue
for j, (key, item) in enumerate(loop.items()):
if not j:
objs = []
for k in range(len(item)):
objs.append(empty())
cif_key = key.split('.')[0]
sk = key.split(".")[1].strip()
func = get_func(cif_key, sk)
for k in range(len(item)):
setattr(objs[k], sk,
get_typed_field(cif_key, sk, item[k], func))
complete_cif_data[cif_key] = objs
return complete_cif_data
def run(filename):
from iotbx import cif
complete_cif_data = {}
cm = cif.reader(filename, strict=False, raise_if_errors=False).model()
for code, rc in cm.items():
for key, item in rc.items():
cif_key = key.split('.')[0]
sk = key.split(".")[1].strip()
complete_cif_data.setdefault(cif_key, [])
if type(item)==type(''):
item=[item]
for i, row in enumerate(item):
if len(complete_cif_data[cif_key])<i+1:
complete_cif_data[cif_key].append(empty())
setattr(complete_cif_data[cif_key][i], sk, row)
for i, loop in enumerate(rc.iterloops()):
break
print(i, loop)
if not loop: continue
for j, (key, item) in enumerate(loop.items()):
if not j:
objs=[]
for k in range(len(item)):
objs.append(empty())
cif_key = key.split('.')[0]
sk = key.split(".")[1].strip()
for k in range(len(item)):
setattr(objs[k], sk, item[k])
complete_cif_data.setdefault(cif_key,objs)
return complete_cif_data
def smart_load_dictionary(name=None, file_path=None, url=None,
registry_location=cifdic_register_url,
save_local=False, store_dir=None):
from iotbx import cif
assert [name, file_path, url].count(None) < 3
cif_dic = None
if store_dir is None:
store_dir = libtbx.env.under_dist(
module_name='iotbx', path='cif/dictionaries')
if name is not None and [file_path, url].count(None) == 2:
if file_path is None:
if os.path.isfile(name):
file_path = name
else:
file_path = os.path.join(store_dir, name)
if not os.path.isfile(file_path):
gzip_path = file_path + '.gz'
if os.path.isfile(gzip_path):
if save_local:
gz = smart_open.for_reading(gzip_path)
f = smart_open.for_writing(file_path)
shutil.copyfileobj(gz, f)
gz.close()
f.close()
else:
file_path = gzip_path
if file_path is not None and os.path.isfile(file_path):
file_object = smart_open.for_reading(file_path)
cif_dic = dictionary(cif.reader(file_object=file_object).model())
file_object.close()
else:
if url is None:
url = locate_dictionary(name, registry_location=registry_location)
file_object = urlopen(url)
if save_local:
if name is None:
name = os.path.basename(url)
f = open(os.path.join(store_dir, name), 'wb')
shutil.copyfileobj(file_object, f)
f.close()
cif_dic = dictionary(cif.reader(
file_path=os.path.join(store_dir, name)).model())
else:
cif_dic = dictionary(cif.reader(
file_object=file_object).model())
assert cif_dic is not None
return cif_dic
def cif_dic_from_str(string):
on_this_dict = """
data_on_this_dictionary
_dictionary_name dummy
_dictionary_version 1.0
"""
return validation.dictionary(
cif.reader(input_string=on_this_dict+string).model())
def run_once(self, file_path, build_miller_arrays=False,
build_xray_structure=False):
reader = cif.reader(file_path=file_path, max_errors=10)
if reader.error_count(): self.parsing_error_count += 1
if build_xray_structure:
xs = reader.build_crystal_structure()
elif build_miller_arrays:
ma = reader.build_miller_arrays()
def run_once(self, file_path, build_miller_arrays=False,
build_xray_structure=False):
reader = cif.reader(file_path=file_path, max_errors=10)
if reader.error_count(): self.parsing_error_count += 1
if build_xray_structure:
xs = reader.build_crystal_structure()
elif build_miller_arrays:
ma = reader.build_miller_arrays()
def cif_dic_from_str(string):
on_this_dict = """
data_on_this_dictionary
_dictionary_name dummy
_dictionary_version 1.0
"""
return validation.dictionary(
cif.reader(input_string=on_this_dict + string).model())
def exercise_missing_atom_site_type_symbol():
m = cif.reader(input_string=cif_with_atom_site_type_symbol).model()
xs = cif.builders.crystal_structure_builder(m['9000000']).structure
sc = xs.scatterers()
assert len(sc) == 18
assert sc[0].label == 'Fe1'
assert sc[0].scattering_type == 'Fe'
assert sc[-1].label == 'O7'
assert sc[-1].scattering_type == 'O'
def exercise_missing_atom_site_type_symbol(): m = cif.reader(input_string=cif_with_atom_site_type_symbol).model() xs = cif.builders.crystal_structure_builder(m['9000000']).structure sc = xs.scatterers() assert len(sc) == 18 assert sc[0].label == 'Fe1' assert sc[0].scattering_type == 'Fe' assert sc[-1].label == 'O7' assert sc[-1].scattering_type == 'O'
def exercise_crystal_symmetry():
cm = cif.reader(input_string=p1_sym_ops).model()
cs_builder = cif.builders.crystal_symmetry_builder(cm["r1e5xsf"])
assert cs_builder.crystal_symmetry.space_group_info().symbol_and_number() \
== 'P 1 (No. 1)'
file_object = open_tmp_file(suffix=".cif")
file_object.write(p1_sym_ops)
file_object.close()
cs = crystal_symmetry_from_any.extract_from(file_name=file_object.name)
assert cs.space_group_info().symbol_and_number() == 'P 1 (No. 1)'
def exercise_crystal_symmetry():
cm = cif.reader(input_string=p1_sym_ops).model()
cs_builder = cif.builders.crystal_symmetry_builder(cm["r1e5xsf"])
assert cs_builder.crystal_symmetry.space_group_info().symbol_and_number() \
== 'P 1 (No. 1)'
file_object = open_tmp_file(suffix=".cif")
file_object.write(p1_sym_ops)
file_object.close()
cs = crystal_symmetry_from_any.extract_from(file_name=file_object.name)
assert cs.space_group_info().symbol_and_number() == 'P 1 (No. 1)'
def locate_dictionary(name, version=None, registry_location=cifdic_register_url):
from iotbx import cif
cm = cif.reader(file_object=urlopen(registry_location)).model()
if version is None: version = '.'
reg = cm["validation_dictionaries"]
for n, v, url in zip(reg['_cifdic_dictionary.name'],
reg['_cifdic_dictionary.version'],
reg['_cifdic_dictionary.URL']):
if n == name and v == str(version):
return url
def intensity_array_from_cif_file(cif_file):
"""Return an intensity miller array from a cif file."""
structures = cif.reader(file_path=cif_file).build_crystal_structures()
try:
model = structures["1"]
except KeyError:
raise KeyError("Unable to extract structure from cif file")
ic = (model.structure_factors(
anomalous_flag=True, d_min=0.4,
algorithm="direct").f_calc().as_intensity_array())
return ic
def read_CIF(fname, **kwargs):
"""Returns model read from CIF file"""
print("\nREADING STRUCTURAL INFORMATION FROM {} ...".format(
os.path.basename(fname)))
iucr_structure = \
reader(fname).build_crystal_structures()["BEA"]
if kwargs.get("expand_to_p1", 0):
print "\n...EXPANDING SRTUCTURE FROM .CIF IN P1...\n"
iucr_structure = iucr_structure.expand_to_p1(sites_mod_positive = True)
print("...DONE!\n")
return iucr_structure
def locate_dictionary(name,
version=None,
registry_location=cifdic_register_url):
from iotbx import cif
cm = cif.reader(file_object=urlopen(registry_location)).model()
if version is None: version = '.'
reg = cm["validation_dictionaries"]
for n, v, url in zip(reg['_cifdic_dictionary.name'],
reg['_cifdic_dictionary.version'],
reg['_cifdic_dictionary.URL']):
if n == name and v == str(version):
return url
def run(args, out=sys.stdout):
if len(args) == 0: args = ["--help"]
command_line = (option_parser(
usage="iotbx.cif.validate filepath|directory [options]")
.option(None, "--file_ext",
action="store",
default="cif")
.option(None, "--dic",
action="append",
dest="dictionaries")
.option(None, "--show_warnings",
action="store_true")
.option(None, "--show_timings",
action="store_true")
.option(None, "--strict",
action="store",
type="bool",
default="true")).process(args=args)
if len(command_line.args) != 1:
command_line.parser.show_help()
return
total_timer = time_log("total").start()
filepath = command_line.args[0]
if not os.path.isabs(filepath):
abs_path = libtbx.env.find_in_repositories(relative_path=filepath)
if abs_path is None:
abs_path = libtbx.env.find_in_repositories(
relative_path=filepath, test=os.path.isfile)
if abs_path is not None: filepath = abs_path
cif_dics = command_line.options.dictionaries
if cif_dics is None:
cif_dics = ["cif_core.dic"]
cif_dic = validation.smart_load_dictionary(name=cif_dics[0])
if len(cif_dics) > 1:
[cif_dic.update(
validation.smart_load_dictionary(name=d)) for d in cif_dics[1:]]
show_warnings = command_line.options.show_warnings == True
show_timings = command_line.options.show_timings == True
strict = command_line.options.strict
if os.path.isdir(filepath):
file_ext = command_line.options.file_ext
crawl(filepath, file_ext=file_ext,
cif_dic=cif_dic, show_warnings=show_warnings,
show_timings=show_timings, strict=strict)
elif os.path.isfile(filepath):
cm = cif.reader(file_path=filepath, strict=strict).model()
cm.validate(cif_dic, show_warnings=show_warnings)
else:
try:
file_object = urllib2.urlopen(filepath)
except urllib2.URLError, e:
pass
else:
def exercise_syntax_errors(): empty_loop_str = """\ data_fred loop_ loop_ _a _b 1 2 3 4 """ try: cif.reader(input_string=empty_loop_str) except CifParserError, e: pass else: raise Exception_expected bad_semicolon_text_field = """\ data_sucrose _a 1 _exptl_absorpt_process_details ; Final HKLF 4 output contains 64446 reflections, Rint = 0.0650 (47528 with I > 3sig(I), Rint = 0.0624); """ try: cif.reader(input_string=bad_semicolon_text_field) except CifParserError, e: pass else: raise Exception_expected
def read_cif(self, f):
#read a cif file One cif file can contain multiple structures
try:
if isinstance(f, str):
structures = cif.reader(
file_path=f,
raise_if_errors=True).build_crystal_structures()
else:
raise TypeError, 'read_cif: Cannot deal is type {}'.format(
type(f))
except libtbx.utils.Sorry as e:
print e
print "Error parsing cif file, check if the data tag does not contain any spaces."
exit()
return structures
def run(sf_file_name,pdb_file_name):
# check if files exist
if not isfile(sf_file_name): raise Sorry('{} is not a file'.format(sf_file_name))
if not isfile(pdb_file_name): raise Sorry('{} is not a file'.format(pdb_file_name))
# start processing file
cs = crystal_symmetry_from_any.extract_from(pdb_file_name)
base_array_info = miller.array_info(crystal_symmetry_from_file=cs)
all_miller_arrays = cif.reader(file_path=sf_file_name).build_miller_arrays(base_array_info=base_array_info)
#
for (data_name, miller_arrays) in all_miller_arrays.iteritems():
print data_name
for ma in miller_arrays.values():
print get_label(ma),ma
print 'wait here'
def _generate_ligand_restraints(self):
try:
from elbow.scripts import elbow_on_pdb_file
except ImportError:
wx.MessageBox('Couldnt find phenix.elbow, you will need to manually generate ligand restraints', 'Couldnt find phenix.elbow', wx.OK | wx.ICON_INFORMATION)
return
wx.MessageBox('Generating restraints for ligands using elbow. This may take a few minutes.', 'Generating Restraints', wx.OK | wx.ICON_INFORMATION)
rests = elbow_on_pdb_file.run(self._pdbf.as_pdb_string(), silent=True)
if rests is not None:
h, cifs, z = rests
for ci in cifs:
self._srv.process_cif_object(cif.reader(input_string=cifs[ci]).model())
self._residues.append(ci)
def import_cif(self):
filename = getOpenFileName(self, 'Open CIF File')
if os.path.exists(filename):
cif_info = cif.reader(file_path=filename).model()
for c in cif_info:
s = cif_info[c]
if '_cell_length_a' in s:
break
def value(text):
if '(' in text:
return float(text[:text.index('(')])
else:
return float(text)
if self.import_checkbox.isChecked():
self.refine.a = value(s['_cell_length_a'])
self.refine.b = value(s['_cell_length_b'])
self.refine.c = value(s['_cell_length_c'])
self.refine.alpha = value(s['_cell_angle_alpha'])
self.refine.beta = value(s['_cell_angle_beta'])
self.refine.gamma = value(s['_cell_angle_gamma'])
if '_space_group_IT_number' in s:
sgi = sgtbx.space_group_info(s['_space_group_IT_number'])
elif '_symmetry_Int_Tables_number' in s:
sgi = sgtbx.space_group_info(s['_symmetry_Int_Tables_number'])
elif '_space_group_name_H-M_alt' in s:
sgi = sgtbx.space_group_info(s['_space_group_name_H-M_alt'])
elif '_symmetry_space_group_name_H-M' in s:
sgi = sgtbx.space_group_info(
s['_symmetry_space_group_name_H-M'])
elif '_space_group_name_Hall' in s:
sgi = sgtbx.space_group_info('hall: ' +
s['_space_group_name_Hall'])
elif '_symmetry_space_group_name_Hall' in s:
sgi = sgtbx.space_group_info(
'hall: ' + s['_symmetry_space_group_name_Hall'])
else:
sgi = None
if sgi:
self.refine.space_group = sgi.type().lookup_symbol()
self.refine.symmetry = sgi.group().crystal_system().lower()
self.refine.laue_group = sgi.group().laue_group_type()
self.refine.centring = self.refine.space_group[0]
self.update_parameters()
def cif_dic_from_str(string):
header = """\
data_test.dic
_dictionary.title test.dic
_dictionary.version 1
loop_
_item_type_list.code
_item_type_list.primitive_code
_item_type_list.construct
_item_type_list.detail
code char
'[_,.;:"&<>()/\{}'`~!@#$%A-Za-z0-9*|+-]*'
; code item types/single words ...
;
"""
return validation.dictionary(
cif.reader(input_string=header+string).model())
def cif_dic_from_str(string):
header = """\
data_test.dic
_dictionary.title test.dic
_dictionary.version 1
loop_
_item_type_list.code
_item_type_list.primitive_code
_item_type_list.construct
_item_type_list.detail
code char
'[_,.;:"&<>()/\{}'`~!@#$%A-Za-z0-9*|+-]*'
; code item types/single words ...
;
"""
return validation.dictionary(
cif.reader(input_string=header + string).model())
def compare_data_with_model(cif_file, mtz_file):
from iotbx import cif, mtz
from scitbx.array_family import flex
import math
import random
# read model, compute Fc, square to F^2
model = cif.reader(file_path=cif_file).build_crystal_structures()["1"]
ic = (
model.structure_factors(anomalous_flag=True, d_min=0.55, algorithm="direct")
.f_calc()
.as_intensity_array()
)
# read experimental measurements
m = mtz.object(mtz_file)
mad = m.as_miller_arrays_dict(merge_equivalents=False)
idata = mad[("HKL_base", "HKL_base", "I")].as_anomalous_array()
match = idata.match_indices(ic)
# pair up, extract to vanilla arrays for easier handling
pairs = match.pairs()
icalc = flex.double()
iobs = flex.double()
sobs = flex.double()
for p in pairs:
iobs.append(idata.data()[p[0]])
sobs.append(idata.sigmas()[p[0]])
icalc.append(ic.data()[p[1]])
# estimate conversion scale - apply F^2
icalc *= flex.sum(iobs) / flex.sum(icalc)
d = (iobs - icalc) / sobs
dh = flex.histogram(d, data_min=-6, data_max=6, n_slots=120)
m = flex.sum(d) / d.size()
s = math.sqrt(flex.sum(d * d) / d.size() - m * m)
# mean and standard deviation -
print(m, s)
def exercise_atom_type_loop():
from cctbx import xray
cif_model = cif.reader(input_string=cif_xray_structure).model()
xs = cif.builders.crystal_structure_builder(cif_model['global']).structure
xs.set_inelastic_form_factors(photon=0.71073, table="henke")
loop = cif.atom_type_cif_loop(xray_structure=xs, format="mmcif")
s = StringIO()
print(loop, file=s)
assert not show_diff(
"\n".join([li.rstrip() for li in s.getvalue().splitlines()]), """\
loop_
_atom_type.symbol
_atom_type.scat_dispersion_real
_atom_type.scat_dispersion_imag
_atom_type.scat_Cromer_Mann_a1
_atom_type.scat_Cromer_Mann_a2
_atom_type.scat_Cromer_Mann_a3
_atom_type.scat_Cromer_Mann_a4
_atom_type.scat_Cromer_Mann_a5
_atom_type.scat_Cromer_Mann_a6
_atom_type.scat_Cromer_Mann_b1
_atom_type.scat_Cromer_Mann_b2
_atom_type.scat_Cromer_Mann_b3
_atom_type.scat_Cromer_Mann_b4
_atom_type.scat_Cromer_Mann_b5
_atom_type.scat_Cromer_Mann_b6
_atom_type.scat_Cromer_Mann_c
_atom_type.scat_source
_atom_type.scat_dispersion_source
C 0.00347 0.00161 2.18189 1.77612 1.08772 0.64146 0.20789 0.10522 13.45337 32.57901 0.74729 0.25125 80.97993 0.05873 0.0
;
6-Gaussian fit: Grosse-Kunstleve RW, Sauter NK, Adams PD:
Newsletter of the IUCr Commission on Crystallographic Computing 2004, 3, 22-31.
;
'Henke, Gullikson and Davis, At. Data and Nucl. Data Tables, 1993, 54, 2'
O 0.01158 0.00611 2.91262 2.58808 0.98057 0.69663 0.68508 0.13677 14.48462 6.03818 0.42255 0.15446 35.53892 0.03841 0.0
;
6-Gaussian fit: Grosse-Kunstleve RW, Sauter NK, Adams PD:
Newsletter of the IUCr Commission on Crystallographic Computing 2004, 3, 22-31.
;
'Henke, Gullikson and Davis, At. Data and Nucl. Data Tables, 1993, 54, 2'
""")
def exercise_atom_type_loop():
from cctbx import xray
cif_model = cif.reader(input_string=cif_xray_structure).model()
xs = cif.builders.crystal_structure_builder(cif_model['global']).structure
xs.set_inelastic_form_factors(photon=0.71073, table="henke")
loop = cif.atom_type_cif_loop(xray_structure=xs, format="mmcif")
s = StringIO()
print >> s, loop
assert not show_diff(
"\n".join([li.rstrip() for li in s.getvalue().splitlines()]), """\
loop_
_atom_type.symbol
_atom_type.scat_dispersion_real
_atom_type.scat_dispersion_imag
_atom_type.scat_Cromer_Mann_a1
_atom_type.scat_Cromer_Mann_a2
_atom_type.scat_Cromer_Mann_a3
_atom_type.scat_Cromer_Mann_a4
_atom_type.scat_Cromer_Mann_a5
_atom_type.scat_Cromer_Mann_a6
_atom_type.scat_Cromer_Mann_b1
_atom_type.scat_Cromer_Mann_b2
_atom_type.scat_Cromer_Mann_b3
_atom_type.scat_Cromer_Mann_b4
_atom_type.scat_Cromer_Mann_b5
_atom_type.scat_Cromer_Mann_b6
_atom_type.scat_Cromer_Mann_c
_atom_type.scat_source
_atom_type.scat_dispersion_source
C 0.00347 0.00161 2.18189 1.77612 1.08772 0.64146 0.20789 0.10522 13.45337 32.57901 0.74729 0.25125 80.97993 0.05873 0.0
;
6-Gaussian fit: Grosse-Kunstleve RW, Sauter NK, Adams PD:
Newsletter of the IUCr Commission on Crystallographic Computing 2004, 3, 22-31.
;
'Henke, Gullikson and Davis, At. Data and Nucl. Data Tables, 1993, 54, 2'
O 0.01158 0.00611 2.91262 2.58808 0.98057 0.69663 0.68508 0.13677 14.48462 6.03818 0.42255 0.15446 35.53892 0.03841 0.0
;
6-Gaussian fit: Grosse-Kunstleve RW, Sauter NK, Adams PD:
Newsletter of the IUCr Commission on Crystallographic Computing 2004, 3, 22-31.
;
'Henke, Gullikson and Davis, At. Data and Nucl. Data Tables, 1993, 54, 2'
""")
def __init__(self, filename, density=0, name=None):
"""
Args:
filename(str): cif file name
density(Optional[float]): compound density
name(Optional[str]): compound name
Raises:
IOError: If the file doesn't exist
RuntimeError:
"""
if iotbxcif is None:
raise RuntimeError("cctbx is required to read cif files")
f = self._get_cif_name(filename)
if f is None:
raise IOError("Cif file %s not found." % filename)
self.ciffile = f
# cctbx.xray.structure.structure
self.structure = (
iotbxcif.reader(file_path=f).build_crystal_structures().values()[0]
)
# Extract necessary information
scatterers = {}
for s in self.structure.scatterers():
e = s.scattering_type
if e in scatterers:
scatterers[e] += s.occupancy * s.multiplicity()
else:
scatterers[e] = s.occupancy * s.multiplicity()
if density == 0:
density = self.structure.crystal_density()
super(CompoundFromCif, self).__init__(
scatterers.keys(),
scatterers.values(),
types.fraction.mole,
density,
name=name,
)
def crawl(directory, file_ext, cif_dic, show_warnings, show_timings, strict):
timer = time_log("parsing")
validate_timer = time_log("validate")
for root, dirs, files in os.walk(directory):
cif_g = glob.glob(os.path.join(root, "*.%s" %file_ext))
files_to_read = cif_g
for path in files_to_read:
timer.start()
try:
cm = cif.reader(file_path=path, strict=strict).model()
except AssertionError:
continue
timer.stop()
s = StringIO()
validate_timer.start()
cm.validate(cif_dic, show_warnings=show_warnings, out=s)
validate_timer.stop()
if s.getvalue():
print path
print s.getvalue()
if show_timings:
print timer.legend
print timer.report()
print validate_timer.report()
def exercise_miller_arrays_as_cif_block():
from iotbx.cif import reader
cif_model = reader(input_string=cif_miller_array,
builder=cif.builders.cif_model_builder()).model()
ma_builder = cif.builders.miller_array_builder(cif_model['global'])
ma1 = ma_builder.arrays()['_refln_F_squared_meas']
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1, array_type='meas')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1-1j]*ma1.size())), array_type='calc')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1-2j]*ma1.size())), column_names=[
'_refln_A_calc', '_refln_B_calc'])
for key in ('_refln_F_squared_meas', '_refln_F_squared_sigma',
'_refln_F_calc', '_refln_phase_calc',
'_refln_A_calc', '_refln_A_calc'):
assert key in mas_as_cif_block.cif_block.keys()
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1, array_type='meas', format="mmcif")
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1-1j]*ma1.size())), array_type='calc')
for key in ('_refln.F_squared_meas', '_refln.F_squared_sigma',
'_refln.F_calc', '_refln.phase_calc',
'_space_group_symop.operation_xyz',
'_cell.length_a', '_refln.index_h'):
assert key in mas_as_cif_block.cif_block.keys()
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1, column_names=['_diffrn_refln_intensity_net',
'_diffrn_refln_intensity_sigma'],
miller_index_prefix='_diffrn_refln')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.std_string(ma1.size(), 'om')),
column_name='_diffrn_refln_intensity_u')
for key in ('_diffrn_refln_intensity_net', '_diffrn_refln_intensity_sigma',
'_diffrn_refln_intensity_u'):
assert key in mas_as_cif_block.cif_block.keys()
#
try: reader(input_string=cif_global)
except CifParserError, e: pass
else: raise Exception_expected
cif_model = reader(input_string=cif_global, strict=False).model()
assert not show_diff(str(cif_model), """\
data_1
_c 3
_d 4
""")
# exercise adding miller arrays with non-matching indices
cs = crystal.symmetry(unit_cell=uctbx.unit_cell((10, 10, 10, 90, 90, 90)),
space_group_info=sgtbx.space_group_info(symbol="P1"))
mi = flex.miller_index(((1,0,0), (1,2,3), (2,3,4)))
ms1 = miller.set(cs, mi)
ma1 = miller.array(ms1, data=flex.double((1,2,3)))
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1, column_name="_refln.F_meas_au")
ms2 = miller.set(cs, mi[:2])
ma2 = miller.array(ms2, data=flex.complex_double([1-2j]*ms2.size()))
mas_as_cif_block.add_miller_array(
ma2, column_names=("_refln.F_calc_au", "_refln.phase_calc")),
ms3 = miller.set(cs, flex.miller_index(((1,0,0), (5,6,7), (2,3,4))))
ma3 = miller.array(ms3, data=flex.double((4,5,6)))
mas_as_cif_block.add_miller_array(ma3, column_name="_refln.F_squared_meas")
ms4 = miller.set(cs, flex.miller_index(((1,2,3), (5,6,7), (1,1,1), (1,0,0), (2,3,4))))
ma4 = ms4.d_spacings()
mas_as_cif_block.add_miller_array(ma4, column_name="_refln.d_spacing")
# extract arrays from cif block and make sure we get back what we started with
arrays = cif.builders.miller_array_builder(mas_as_cif_block.cif_block).arrays()
recycled_arrays = (arrays['_refln.F_meas_au'],
arrays['_refln.F_calc_au'],
arrays['_refln.F_squared_meas'],
arrays['_refln.d_spacing'])
for orig, recycled in zip((ma1, ma2, ma3, ma4), recycled_arrays):
assert orig.size() == recycled.size()
recycled = recycled.customized_copy(anomalous_flag=orig.anomalous_flag())
orig, recycled = orig.common_sets(recycled)
assert orig.indices().all_eq(recycled.indices())
assert approx_equal(orig.data(), recycled.data(), eps=1e-5)
#
cif_model = reader(input_string=r3adrsf,
builder=cif.builders.cif_model_builder()).model()
cs = cif.builders.crystal_symmetry_builder(cif_model["r3adrsf"]).crystal_symmetry
ma_builder = cif.builders.miller_array_builder(
cif_model['r3adrAsf'],
base_array_info=miller.array_info(crystal_symmetry_from_file=cs))
miller_arrays = ma_builder.arrays().values()
assert len(miller_arrays) == 4
mas_as_cif_block = cif.miller_arrays_as_cif_block(
miller_arrays[0].map_to_asu(), column_names=miller_arrays[0].info().labels)
for array in miller_arrays[1:]:
labels = array.info().labels
if len(labels) > 1 :
for label in labels :
if label.startswith("wavelength_id") :
labels.remove(label)
mas_as_cif_block.add_miller_array(
array=array.map_to_asu(), column_names=array.info().labels)
s = StringIO()
print >> s, mas_as_cif_block.refln_loop
assert not show_diff(s.getvalue(), """\
loop_
_refln_index_h
_refln_index_k
_refln_index_l
_refln.crystal_id
_refln.scale_group_code
_refln.wavelength_id
_refln.pdbx_I_plus
_refln.pdbx_I_plus_sigma
_refln.pdbx_I_minus
_refln.pdbx_I_minus_sigma
-87 5 46 1 1 3 40.2 40.4 6.7 63.9
-87 5 45 1 1 3 47.8 29.7 35.1 30.5
-87 5 44 1 1 3 18.1 33.2 0.5 34.6
-87 5 43 1 1 3 6.1 45.4 12.9 51.6
-87 5 42 1 1 3 -6.6 45.6 -15.5 55.8
-87 7 37 1 1 3 6.3 43.4 ? ?
-87 7 36 1 1 3 -67.2 55.4 ? ?
-88 2 44 1 1 3 0 -1 35 38.5
-88 2 43 1 1 3 0 -1 57.4 41.5
-88 4 45 1 1 3 -1 46.1 -9.1 45.6
-88 4 44 1 1 3 -19.8 49.2 0.3 34.7
-88 6 44 1 1 3 -1.8 34.8 ? ?
""")
def run_once(file_path, build_miller_arrays=False, build_xray_structure=False):
reader = cif.reader(file_path=file_path, max_errors=10)
if build_xray_structure:
xs = reader.build_crystal_structure()
elif build_miller_arrays:
ma = reader.build_miller_arrays()
def exercise_parser(reader, builder):
cif_model = reader(
input_string=cif_xray_structure, builder=builder()).model()
xs_builder = cif.builders.crystal_structure_builder(cif_model['global'])
xs1 = xs_builder.structure
# also test construction of cif model from xray structure
xs_cif_block = xs1.as_cif_block()
xs2 = cif.builders.crystal_structure_builder(xs_cif_block).structure
sio = StringIO()
xs1.as_cif_simple(out=sio)
xs3 = reader(input_string=sio.getvalue()).build_crystal_structures(
data_block_name='global')
xs_iso = xs1.deep_copy_scatterers()
xs_iso.convert_to_isotropic()
xs4 = cif.builders.crystal_structure_builder(xs_iso.as_cif_block()).structure
for xs in (xs1, xs2, xs3):
sc = xs.scatterers()
assert list(sc.extract_labels()) == ['o','c']
assert list(sc.extract_scattering_types()) == ['O','C']
assert approx_equal(sc.extract_occupancies(), (0.8, 1))
assert approx_equal(sc.extract_sites(), ((0.5,0,0),(0,0,0)))
assert approx_equal(sc.extract_u_star(),
[(-1, -1, -1, -1, -1, -1), (1e-3, 5e-4, (1e-3)/3, 0, 0, 0)])
assert approx_equal(sc.extract_u_iso(), (0.1, -1))
assert approx_equal(xs.unit_cell().parameters(),
(10,20,30,90,90,90))
assert str(xs.space_group_info()) == 'C 1 2/m 1'
#
cif_model = reader(
input_string=cif_miller_array, builder=builder()).model()
ma_builder = cif.builders.miller_array_builder(cif_model['global'])
ma1 = ma_builder.arrays()['_refln_F_squared_meas']
if isinstance(cif_model, cif.model.cif):
assert (ma_builder.arrays()['_refln_observed_status'].data() ==
flex.std_string(['o'] * ma1.size()))
# also test construction of cif model from miller array
ma2 = cif.builders.miller_array_builder(
ma1.as_cif_block(array_type='meas')).arrays()['_refln_F_squared_meas']
for ma in (ma1, ma2):
sio = StringIO()
ma.show_array(sio)
assert not show_diff(sio.getvalue(), """\
(1, 0, 0) 748.71 13.87
(2, 0, 0) 1318.51 24.29
(3, 0, 0) 1333.51 33.75
(4, 0, 0) 196.58 10.85
(5, 0, 0) 3019.71 55.29
(6, 0, 0) 1134.38 23.94
(7, 0, 0) 124.01 15.16
(8, 0, 0) -1.22 10.49
(9, 0, 0) 189.09 20.3
(10, 0, 0) 564.68 35.61
(-10, 1, 0) 170.23 22.26
""")
sio = StringIO()
ma.show_summary(sio)
assert not show_diff(sio.getvalue(), """\
Miller array info: cif:_refln_F_squared_meas,_refln_F_squared_sigma
Observation type: xray.intensity
Type of data: double, size=11
Type of sigmas: double, size=11
Number of Miller indices: 11
Anomalous flag: False
Unit cell: (7.999, 9.372, 14.736, 82.625, 81.527, 81.726)
Space group: P -1 (No. 2)
""")
def exercise_lex_parse_build():
exercise_parser(cif.reader, cif.builders.cif_model_builder)
cm = cif.reader(input_string=cif_quoted_string).model()
assert cm['global']['_a'] == 'a"b'
assert cm['global']['_b'] == "a dog's life"
stdout = sys.stdout
s = StringIO()
sys.stdout = s
try: cif.reader(input_string=cif_invalid_missing_value)
except CifParserError: pass
else: raise Exception_expected
r = cif.reader(
input_string=cif_invalid_missing_value, raise_if_errors=False)
assert r.error_count() == 1
try: cif.reader(input_string=cif_invalid_string)
except CifParserError: pass
else: raise Exception_expected
a = cif.reader(input_string=cif_cod)
assert a.error_count() == 0
try: cif.reader(input_string=cif_invalid_semicolon_text_field)
except CifParserError: pass
else: raise Exception_expected
d = cif.reader(input_string=cif_valid_semicolon_text_field)
assert d.error_count() == 0
assert d.model()['1']['_a'] == '\n1\n'
e = cif.reader(input_string=cif_unquoted_string_semicolon)
assert not show_diff(str(e.model()), """\
data_1
_a ;1
_b ;
_c 2
""")
cif_str_1 = """\
data_1
_a 1
"""
cif_str_2 = """\
data_2
_b 2
"""
cm = cif.reader(input_string=cif_str_1).model()
assert cm.keys() == ['1']
cif.reader(input_string=cif_str_2, cif_object=cm).model()
assert cm.keys() == ['1', '2']
try: cm = cif.reader(input_string=cif_invalid_loop).model()
except CifParserError: pass
else: raise Exception_expected
try: cm = cif.reader(input_string=cif_invalid_loop_2).model()
except CifParserError: pass
else: raise Exception_expected
sys.stdout = stdout
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %(
'_refln_F_calc', '_refln_F_meas', '_refln_F_sigma')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_F_calc', '_refln_F_meas']
assert arrays['_refln_F_calc'].sigmas() is None
assert isinstance(arrays['_refln_F_meas'].sigmas(), flex.double)
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %(
'_refln_A_calc', '_refln_B_calc', '_refln_F_meas')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_A_calc', '_refln_F_meas']
assert arrays['_refln_A_calc'].is_complex_array()
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %(
'_refln_A_meas', '_refln_B_meas', '_refln_F_meas')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_A_meas', '_refln_F_meas']
assert arrays['_refln_A_meas'].is_complex_array()
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %(
'_refln_intensity_calc', '_refln_intensity_meas',
'_refln_intensity_sigma')),
data_block_name='global')
assert sorted(arrays.keys()) == [
'_refln_intensity_calc', '_refln_intensity_meas']
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %(
'_refln_F_calc', '_refln_phase_calc', '_refln_F_sigma')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_F_calc']
assert arrays['_refln_F_calc'].is_complex_array()
for data_block_name in (None, "global"):
miller_arrays = cif.reader(file_object=StringIO(
cif_miller_array_template %(
'_refln_F_calc',
'_refln_F_meas',
'_refln_F_sigma'))).as_miller_arrays(data_block_name=data_block_name)
assert " ".join(sorted([str(ma.info()) for ma in miller_arrays])) \
== "cif:global,_refln_F_calc cif:global,_refln_F_meas,_refln_F_sigma"
f = open_tmp_file(suffix="cif")
f.write(cif_miller_array_template %(
'_refln_F_calc',
'_refln_F_meas',
'_refln_F_sigma'))
f.close()
miller_arrays = any_reflection_file(file_name=f.name).as_miller_arrays()
assert len(miller_arrays) == 2
def get_cs(input_string):
cif_model = cif.reader(input_string=input_string).model()
return cif.builders.crystal_symmetry_builder(
cif_block=cif_model["test"]).crystal_symmetry
def exercise_mmcif_structure_factors():
miller_arrays = cif.reader(input_string=r3adrsf).as_miller_arrays()
assert len(miller_arrays) == 16
hl_coeffs = find_miller_array_from_labels(
miller_arrays, ','.join([
'scale_group_code=1', 'crystal_id=2', 'wavelength_id=3',
'_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso'
]))
assert hl_coeffs.is_hendrickson_lattman_array()
assert hl_coeffs.size() == 2
mas_as_cif_block = cif.miller_arrays_as_cif_block(
hl_coeffs,
column_names=('_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso'))
abcd = []
for key in ('_refln.pdbx_HL_A_iso', '_refln.pdbx_HL_B_iso',
'_refln.pdbx_HL_C_iso', '_refln.pdbx_HL_D_iso'):
assert key in list(mas_as_cif_block.cif_block.keys())
abcd.append(flex.double(mas_as_cif_block.cif_block[key]))
hl_coeffs_from_cif_block = flex.hendrickson_lattman(*abcd)
assert approx_equal(hl_coeffs.data(), hl_coeffs_from_cif_block)
f_meas_au = find_miller_array_from_labels(
miller_arrays, ','.join([
'scale_group_code=1', 'crystal_id=1', 'wavelength_id=1',
'_refln.F_meas_au', '_refln.F_meas_sigma_au'
]))
assert f_meas_au.is_xray_amplitude_array()
assert f_meas_au.size() == 5
assert f_meas_au.sigmas() is not None
assert f_meas_au.space_group_info().symbol_and_number(
) == 'C 1 2 1 (No. 5)'
assert approx_equal(f_meas_au.unit_cell().parameters(),
(163.97, 45.23, 110.89, 90.0, 131.64, 90.0))
pdbx_I_plus_minus = find_miller_array_from_labels(
miller_arrays, ','.join([
'_refln.pdbx_I_plus', '_refln.pdbx_I_plus_sigma',
'_refln.pdbx_I_minus', '_refln.pdbx_I_minus_sigma'
]))
assert pdbx_I_plus_minus.is_xray_intensity_array()
assert pdbx_I_plus_minus.anomalous_flag()
assert pdbx_I_plus_minus.size() == 21
assert pdbx_I_plus_minus.unit_cell() is None # no symmetry information in
assert pdbx_I_plus_minus.space_group() is None # this CIF block
#
miller_arrays = cif.reader(input_string=r3ad7sf).as_miller_arrays()
assert len(miller_arrays) == 11
f_calc = find_miller_array_from_labels(
miller_arrays, ','.join([
'crystal_id=2', 'wavelength_id=1', '_refln.F_calc',
'_refln.phase_calc'
]))
assert f_calc.is_complex_array()
assert f_calc.size() == 4
#
miller_arrays = cif.reader(
input_string=integer_observations).as_miller_arrays()
assert len(miller_arrays) == 2
assert isinstance(miller_arrays[0].data(), flex.double)
assert isinstance(miller_arrays[0].sigmas(), flex.double)
#
miller_arrays = cif.reader(input_string=r3v56sf).as_miller_arrays()
assert len(miller_arrays) == 2
for ma in miller_arrays:
assert ma.is_complex_array()
assert miller_arrays[0].info().labels == [
'r3v56sf', '_refln.pdbx_DELFWT', '_refln.pdbx_DELPHWT'
]
assert miller_arrays[1].info().labels == [
'r3v56sf', '_refln.pdbx_FWT', '_refln.pdbx_PHWT'
]
strict = command_line.options.strict
if os.path.isdir(filepath):
file_ext = command_line.options.file_ext
crawl(filepath, file_ext=file_ext,
cif_dic=cif_dic, show_warnings=show_warnings,
show_timings=show_timings, strict=strict)
elif os.path.isfile(filepath):
cm = cif.reader(file_path=filepath, strict=strict).model()
cm.validate(cif_dic, show_warnings=show_warnings)
else:
try:
file_object = urllib2.urlopen(filepath)
except urllib2.URLError, e:
pass
else:
cm = cif.reader(file_object=file_object, strict=strict).model()
cm.validate(cif_dic, show_warnings=show_warnings)
if show_timings:
total_timer.stop()
print total_timer.report()
def crawl(directory, file_ext, cif_dic, show_warnings, show_timings, strict):
timer = time_log("parsing")
validate_timer = time_log("validate")
for root, dirs, files in os.walk(directory):
cif_g = glob.glob(os.path.join(root, "*.%s" %file_ext))
files_to_read = cif_g
for path in files_to_read:
timer.start()
try:
cm = cif.reader(file_path=path, strict=strict).model()
def get_cs(input_string):
cif_model = cif.reader(input_string=input_string).model()
return cif.builders.crystal_symmetry_builder(
cif_block=cif_model["test"]).crystal_symmetry
def exercise_parser(reader, builder):
cif_model = reader(input_string=cif_xray_structure,
builder=builder()).model()
xs_builder = cif.builders.crystal_structure_builder(cif_model['global'])
xs1 = xs_builder.structure
# also test construction of cif model from xray structure
xs_cif_block = xs1.as_cif_block()
xs2 = cif.builders.crystal_structure_builder(xs_cif_block).structure
sio = StringIO()
xs1.as_cif_simple(out=sio)
xs3 = reader(input_string=sio.getvalue()).build_crystal_structures(
data_block_name='global')
xs_iso = xs1.deep_copy_scatterers()
xs_iso.convert_to_isotropic()
xs4 = cif.builders.crystal_structure_builder(
xs_iso.as_cif_block()).structure
for xs in (xs1, xs2, xs3):
sc = xs.scatterers()
assert list(sc.extract_labels()) == ['o', 'c']
assert list(sc.extract_scattering_types()) == ['O', 'C']
assert approx_equal(sc.extract_occupancies(), (0.8, 1))
assert approx_equal(sc.extract_sites(), ((0.5, 0, 0), (0, 0, 0)))
assert approx_equal(sc.extract_u_star(),
[(-1, -1, -1, -1, -1, -1),
(1e-3, 5e-4, (1e-3) / 3, 0, 0, 0)])
assert approx_equal(sc.extract_u_iso(), (0.1, -1))
assert approx_equal(xs.unit_cell().parameters(),
(10, 20, 30, 90, 90, 90))
assert str(xs.space_group_info()) == 'C 1 2/m 1'
#
cif_model = reader(input_string=cif_miller_array,
builder=builder()).model()
ma_builder = cif.builders.miller_array_builder(cif_model['global'])
ma1 = ma_builder.arrays()['_refln_F_squared_meas']
if isinstance(cif_model, cif.model.cif):
assert (ma_builder.arrays()['_refln_observed_status'].data() ==
flex.std_string(['o'] * ma1.size()))
# also test construction of cif model from miller array
ma2 = cif.builders.miller_array_builder(
ma1.as_cif_block(array_type='meas')).arrays()['_refln.F_squared_meas']
for ma in (ma1, ma2):
sio = StringIO()
ma.show_array(sio)
assert not show_diff(
sio.getvalue(), """\
(1, 0, 0) 748.71 13.87
(2, 0, 0) 1318.51 24.29
(3, 0, 0) 1333.51 33.75
(4, 0, 0) 196.58 10.85
(5, 0, 0) 3019.71 55.29
(6, 0, 0) 1134.38 23.94
(7, 0, 0) 124.01 15.16
(8, 0, 0) -1.22 10.49
(9, 0, 0) 189.09 20.3
(10, 0, 0) 564.68 35.61
(-10, 1, 0) 170.23 22.26
""")
sio = StringIO()
ma1.show_summary(sio)
# Miller array info: cif:_refln.F_squared_meas,_refln.F_squared_sigma
assert not show_diff(
sio.getvalue(), """\
Miller array info: cif:_refln_F_squared_meas,_refln_F_squared_sigma
Observation type: xray.intensity
Type of data: double, size=11
Type of sigmas: double, size=11
Number of Miller indices: 11
Anomalous flag: False
Unit cell: (7.999, 9.372, 14.736, 82.625, 81.527, 81.726)
Space group: P -1 (No. 2)
""")
sio = StringIO()
ma2.show_summary(sio)
# Miller array info: cif:_refln.F_squared_meas,_refln.F_squared_sigma
assert not show_diff(
sio.getvalue(), """\
Miller array info: cif:_refln.F_squared_meas,_refln.F_squared_sigma
Observation type: xray.intensity
Type of data: double, size=11
Type of sigmas: double, size=11
Number of Miller indices: 11
Anomalous flag: False
Unit cell: (7.999, 9.372, 14.736, 82.625, 81.527, 81.726)
Space group: P -1 (No. 2)
""")
def exercise_lex_parse_build():
exercise_parser(cif.reader, cif.builders.cif_model_builder)
cm = cif.reader(input_string=cif_quoted_string).model()
assert cm['global']['_a'] == 'a"b'
assert cm['global']['_b'] == "a dog's life"
stdout = sys.stdout
s = StringIO()
sys.stdout = s
try:
cif.reader(input_string=cif_invalid_missing_value)
except CifParserError:
pass
else:
raise Exception_expected
r = cif.reader(input_string=cif_invalid_missing_value,
raise_if_errors=False)
assert r.error_count() == 1
try:
cif.reader(input_string=cif_invalid_string)
except CifParserError:
pass
else:
raise Exception_expected
a = cif.reader(input_string=cif_cod)
assert a.error_count() == 0
try:
cif.reader(input_string=cif_invalid_semicolon_text_field)
except CifParserError:
pass
else:
raise Exception_expected
d = cif.reader(input_string=cif_valid_semicolon_text_field)
assert d.error_count() == 0
assert d.model()['1']['_a'] == '\n1\n'
e = cif.reader(input_string=cif_unquoted_string_semicolon)
assert not show_diff(
str(e.model()), """\
data_1
_a ;1
_b ;
_c 2
""")
cif_str_1 = """\
data_1
_a 1
"""
cif_str_2 = """\
data_2
_b 2
"""
cm = cif.reader(input_string=cif_str_1).model()
assert list(cm.keys()) == ['1']
cif.reader(input_string=cif_str_2, cif_object=cm).model()
assert list(cm.keys()) == ['1', '2']
try:
cm = cif.reader(input_string=cif_invalid_loop).model()
except CifParserError:
pass
else:
raise Exception_expected
try:
cm = cif.reader(input_string=cif_invalid_loop_2).model()
except CifParserError:
pass
else:
raise Exception_expected
sys.stdout = stdout
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %
('_refln_F_calc', '_refln_F_meas', '_refln_F_sigma')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_F_calc', '_refln_F_meas']
assert arrays['_refln_F_calc'].sigmas() is None
assert isinstance(arrays['_refln_F_meas'].sigmas(), flex.double)
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %
('_refln_A_calc', '_refln_B_calc', '_refln_F_meas')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_A_calc', '_refln_F_meas']
assert arrays['_refln_A_calc'].is_complex_array()
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %
('_refln_A_meas', '_refln_B_meas', '_refln_F_meas')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_A_meas', '_refln_F_meas']
assert arrays['_refln_A_meas'].is_complex_array()
arrays = miller.array.from_cif(
file_object=StringIO(cif_miller_array_template %
('_refln_intensity_calc', '_refln_intensity_meas',
'_refln_intensity_sigma')),
data_block_name='global')
assert sorted(
arrays.keys()) == ['_refln_intensity_calc', '_refln_intensity_meas']
arrays = miller.array.from_cif(file_object=StringIO(
cif_miller_array_template %
('_refln_F_calc', '_refln_phase_calc', '_refln_F_sigma')),
data_block_name='global')
assert sorted(arrays.keys()) == ['_refln_F_calc']
assert arrays['_refln_F_calc'].is_complex_array()
for data_block_name in (None, "global"):
miller_arrays = cif.reader(
file_object=StringIO(cif_miller_array_template %
('_refln_F_calc', '_refln_F_meas',
'_refln_F_sigma'))).as_miller_arrays(
data_block_name=data_block_name)
assert " ".join(sorted([str(ma.info()) for ma in miller_arrays])) \
== "cif:global,_refln_F_calc cif:global,_refln_F_meas,_refln_F_sigma"
f = open_tmp_file(suffix="cif")
f.write(cif_miller_array_template %
('_refln_F_calc', '_refln_F_meas', '_refln_F_sigma'))
f.close()
miller_arrays = any_reflection_file(file_name=f.name).as_miller_arrays()
assert len(miller_arrays) == 2
cs = crystal.symmetry(space_group_info=sgtbx.space_group_info("P1"))
miller_arrays = any_reflection_file(file_name=f.name).as_miller_arrays(
crystal_symmetry=cs, force_symmetry=True, anomalous=True)
assert miller_arrays[0].anomalous_flag() is True
assert miller_arrays[0].crystal_symmetry().space_group() == cs.space_group(
)
def exercise_miller_arrays_as_cif_block():
from iotbx.cif import reader
cif_model = reader(input_string=cif_miller_array,
builder=cif.builders.cif_model_builder()).model()
ma_builder = cif.builders.miller_array_builder(cif_model['global'])
ma1 = ma_builder.arrays()['_refln_F_squared_meas']
mas_as_cif_block = cif.miller_arrays_as_cif_block(ma1,
array_type='meas',
format="corecif")
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 1j] * ma1.size())),
array_type='calc')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 2j] * ma1.size())),
column_names=['_refln_A_calc', '_refln_B_calc'])
for key in ('_refln_F_squared_meas', '_refln_F_squared_sigma',
'_refln_F_calc', '_refln_phase_calc', '_refln_A_calc',
'_refln_A_calc'):
assert (key in mas_as_cif_block.cif_block.keys()), key
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(ma1,
array_type='meas',
format="mmcif")
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.complex_double([1 - 1j] * ma1.size())),
array_type='calc')
for key in ('_refln.F_squared_meas', '_refln.F_squared_sigma',
'_refln.F_calc', '_refln.phase_calc',
'_space_group_symop.operation_xyz', '_cell.length_a',
'_refln.index_h'):
assert key in mas_as_cif_block.cif_block.keys()
#
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1,
column_names=[
'_diffrn_refln_intensity_net', '_diffrn_refln_intensity_sigma'
],
miller_index_prefix='_diffrn_refln')
mas_as_cif_block.add_miller_array(
ma1.array(data=flex.std_string(ma1.size(), 'om')),
column_name='_diffrn_refln_intensity_u')
for key in ('_diffrn_refln_intensity_net', '_diffrn_refln_intensity_sigma',
'_diffrn_refln_intensity_u'):
assert key in list(mas_as_cif_block.cif_block.keys())
#
try:
reader(input_string=cif_global)
except CifParserError as e:
pass
else:
raise Exception_expected
cif_model = reader(input_string=cif_global, strict=False).model()
assert not show_diff(
str(cif_model), """\
data_1
_c 3
_d 4
""")
# exercise adding miller arrays with non-matching indices
cs = crystal.symmetry(unit_cell=uctbx.unit_cell((10, 10, 10, 90, 90, 90)),
space_group_info=sgtbx.space_group_info(symbol="P1"))
mi = flex.miller_index(((1, 0, 0), (1, 2, 3), (2, 3, 4)))
ms1 = miller.set(cs, mi)
ma1 = miller.array(ms1, data=flex.double((1, 2, 3)))
mas_as_cif_block = cif.miller_arrays_as_cif_block(
ma1, column_name="_refln.F_meas_au")
ms2 = miller.set(cs, mi[:2])
ma2 = miller.array(ms2, data=flex.complex_double([1 - 2j] * ms2.size()))
mas_as_cif_block.add_miller_array(ma2,
column_names=("_refln.F_calc_au",
"_refln.phase_calc")),
ms3 = miller.set(cs, flex.miller_index(((1, 0, 0), (5, 6, 7), (2, 3, 4))))
ma3 = miller.array(ms3, data=flex.double((4, 5, 6)))
mas_as_cif_block.add_miller_array(ma3, column_name="_refln.F_squared_meas")
ms4 = miller.set(
cs,
flex.miller_index(
((1, 2, 3), (5, 6, 7), (1, 1, 1), (1, 0, 0), (2, 3, 4))))
ma4 = ms4.d_spacings()
mas_as_cif_block.add_miller_array(ma4, column_name="_refln.d_spacing")
# extract arrays from cif block and make sure we get back what we started with
arrays = cif.builders.miller_array_builder(
mas_as_cif_block.cif_block).arrays()
recycled_arrays = (arrays['_refln.F_meas_au'], arrays['_refln.F_calc_au'],
arrays['_refln.F_squared_meas'],
arrays['_refln.d_spacing'])
for orig, recycled in zip((ma1, ma2, ma3, ma4), recycled_arrays):
assert orig.size() == recycled.size()
recycled = recycled.customized_copy(
anomalous_flag=orig.anomalous_flag())
orig, recycled = orig.common_sets(recycled)
assert orig.indices().all_eq(recycled.indices())
assert approx_equal(orig.data(), recycled.data(), eps=1e-5)
#
cif_model = reader(input_string=r3adrsf,
builder=cif.builders.cif_model_builder()).model()
cs = cif.builders.crystal_symmetry_builder(
cif_model["r3adrsf"]).crystal_symmetry
ma_builder = cif.builders.miller_array_builder(
cif_model['r3adrAsf'],
base_array_info=miller.array_info(crystal_symmetry_from_file=cs))
miller_arrays = list(ma_builder.arrays().values())
assert len(miller_arrays) == 4
mas_as_cif_block = cif.miller_arrays_as_cif_block(
miller_arrays[0].map_to_asu(),
column_names=miller_arrays[0].info().labels,
format="corecif")
for array in miller_arrays[1:]:
labels = array.info().labels
if len(labels) > 1:
for label in labels:
if label.startswith("wavelength_id"):
labels.remove(label)
mas_as_cif_block.add_miller_array(array=array.map_to_asu(),
column_names=array.info().labels)
s = StringIO()
print(mas_as_cif_block.refln_loop, file=s)
assert not show_diff(
s.getvalue(), """\
loop_
_refln_index_h
_refln_index_k
_refln_index_l
_refln.crystal_id
_refln.scale_group_code
_refln.wavelength_id
_refln.pdbx_I_plus
_refln.pdbx_I_plus_sigma
_refln.pdbx_I_minus
_refln.pdbx_I_minus_sigma
-87 5 46 1 1 3 40.2 40.4 6.7 63.9
-87 5 45 1 1 3 47.8 29.7 35.1 30.5
-87 5 44 1 1 3 18.1 33.2 0.5 34.6
-87 5 43 1 1 3 6.1 45.4 12.9 51.6
-87 5 42 1 1 3 -6.6 45.6 -15.5 55.8
-87 7 37 1 1 3 6.3 43.4 ? ?
-87 7 36 1 1 3 -67.2 55.4 ? ?
-88 2 44 1 1 3 0 -1 35 38.5
-88 2 43 1 1 3 0 -1 57.4 41.5
-88 4 45 1 1 3 -1 46.1 -9.1 45.6
-88 4 44 1 1 3 -19.8 49.2 0.3 34.7
-88 6 44 1 1 3 -1.8 34.8 ? ?
""")
def read_cif_file(self, ligand_path): from iotbx import cif cif_object = cif.reader(file_path=ligand_path, strict=False).model() return cif_object
def exercise_dictionary_merging():
#
# DDL1 merging
#
def cif_dic_from_str(string):
on_this_dict = """
data_on_this_dictionary
_dictionary_name dummy
_dictionary_version 1.0
"""
return validation.dictionary(
cif.reader(input_string=on_this_dict + string).model())
test_cif = cif.reader(input_string="""
data_test
_dummy 1234.5
""").model()
dict_official = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type numb
_enumeration_range 0: # i.e. any positive number
""")
dict_a = cif_dic_from_str("""
data_dummy_modified
_name '_dummy'
_enumeration_range 0:1000
""")
dict_b = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type_extended integer
""")
dict_c = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type char
""")
test_cif.validate(dict_official)
try:
dict_official.deepcopy().update(other=dict_a, mode="strict")
except AssertionError:
pass
else:
raise Exception_expected
dict_oa = dict_official.deepcopy()
dict_oa.update(other=dict_a, mode="overlay")
assert dict_oa["dummy"]["_type"] == "numb"
assert dict_oa["dummy"]["_enumeration_range"] == "0:1000"
assert test_cif.validate(dict_oa, out=StringIO()).error_count == 1
dict_ao = dict_a.deepcopy()
dict_ao.update(other=dict_official, mode="overlay")
assert dict_ao["dummy_modified"]["_type"] == "numb"
assert dict_ao["dummy_modified"]["_enumeration_range"] == "0:"
assert test_cif.validate(dict_ao).error_count == 0
dict_ob = dict_official.deepcopy()
dict_ob.update(other=dict_b, mode="overlay")
assert dict_ob["dummy"]["_type"] == "numb"
assert dict_ob["dummy"]["_type_extended"] == "integer"
assert test_cif.validate(dict_ob).error_count == 0
dict_ob = dict_official.deepcopy()
dict_ob.update(other=dict_b, mode="replace")
assert "_type" not in dict_ob["dummy"]
assert dict_ob["dummy"]["_type_extended"] == "integer"
assert test_cif.validate(dict_ob).error_count == 0
dict_oc = dict_official.deepcopy()
dict_oc.update(other=dict_c, mode="replace")
assert dict_oc["dummy"]["_type"] == "char"
assert test_cif.validate(dict_oc).error_count == 0
dict_oc = dict_official.deepcopy()
dict_oc.update(other=dict_c, mode="overlay")
errors = test_cif.validate(dict_oc)
#
# DDL2 merging
#
def cif_dic_from_str(string):
header = """\
data_test.dic
_dictionary.title test.dic
_dictionary.version 1
loop_
_item_type_list.code
_item_type_list.primitive_code
_item_type_list.construct
_item_type_list.detail
code char
'[_,.;:"&<>()/\{}'`~!@#$%A-Za-z0-9*|+-]*'
; code item types/single words ...
;
"""
return validation.dictionary(
cif.reader(input_string=header + string).model())
dic_a = cif_dic_from_str("""
save_fred
_category.description 'a description'
_category.id fred
_category.mandatory_code no
_category_key.name 'fred.id'
save_
""")
dic_b = cif_dic_from_str("""
save_fred
_category.id fred
_category.mandatory_code yes
_category_key.name 'fred.id'
loop_
_category_group.id 'inclusive_group'
'atom_group'
save_
""")
dic_c = cif_dic_from_str("""
save_bob
_category.id bob
_category.mandatory_code yes
_category_key.name 'bob.id'
save_
""")
assert dic_a.deepcopy() == dic_a
assert dic_a.copy() == dic_a
try:
dic_a.deepcopy().update(dic_b, mode="strict")
except AssertionError:
pass
else:
raise Exception_expected
dic_ab = dic_a.deepcopy()
dic_ab.update(dic_b, mode="replace")
assert dic_ab == dic_b
dic_ab = dic_a.deepcopy()
dic_ab.update(dic_b, mode="overlay")
assert dic_ab['test.dic']['fred']['_category.mandatory_code'] == 'yes'
assert '_category.description' in dic_ab['test.dic']['fred']
assert '_category_group.id' in dic_ab['test.dic']['fred']
for mode in ("strict", "replace", "overlay"):
dic_ac = dic_a.deepcopy()
dic_ac.update(dic_c, mode=mode)
assert 'fred' in dic_ac['test.dic']
assert 'bob' in dic_ac['test.dic']
def exercise_detect_binary(): binary_string = '\xff\xf8\x00\x00\x00\x00\x00\x00' from iotbx.cif import reader try: reader(input_string=binary_string) except CifParserError, e: pass else: raise Exception_expected
def exercise_dictionary_merging():
#
# DDL1 merging
#
def cif_dic_from_str(string):
on_this_dict = """
data_on_this_dictionary
_dictionary_name dummy
_dictionary_version 1.0
"""
return validation.dictionary(
cif.reader(input_string=on_this_dict+string).model())
test_cif = cif.reader(input_string="""
data_test
_dummy 1234.5
""").model()
dict_official = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type numb
_enumeration_range 0: # i.e. any positive number
""")
dict_a = cif_dic_from_str("""
data_dummy_modified
_name '_dummy'
_enumeration_range 0:1000
""")
dict_b = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type_extended integer
""")
dict_c = cif_dic_from_str("""
data_dummy
_name '_dummy'
_type char
""")
test_cif.validate(dict_official)
try: dict_official.deepcopy().update(other=dict_a, mode="strict")
except AssertionError: pass
else: raise Exception_expected
dict_oa = dict_official.deepcopy()
dict_oa.update(other=dict_a, mode="overlay")
assert dict_oa["dummy"]["_type"] == "numb"
assert dict_oa["dummy"]["_enumeration_range"] == "0:1000"
assert test_cif.validate(dict_oa, out=StringIO()).error_count == 1
dict_ao = dict_a.deepcopy()
dict_ao.update(other=dict_official, mode="overlay")
assert dict_ao["dummy_modified"]["_type"] == "numb"
assert dict_ao["dummy_modified"]["_enumeration_range"] == "0:"
assert test_cif.validate(dict_ao).error_count == 0
dict_ob = dict_official.deepcopy()
dict_ob.update(other=dict_b, mode="overlay")
assert dict_ob["dummy"]["_type"] == "numb"
assert dict_ob["dummy"]["_type_extended"] == "integer"
assert test_cif.validate(dict_ob).error_count == 0
dict_ob = dict_official.deepcopy()
dict_ob.update(other=dict_b, mode="replace")
assert "_type" not in dict_ob["dummy"]
assert dict_ob["dummy"]["_type_extended"] == "integer"
assert test_cif.validate(dict_ob).error_count == 0
dict_oc = dict_official.deepcopy()
dict_oc.update(other=dict_c, mode="replace")
assert dict_oc["dummy"]["_type"] == "char"
assert test_cif.validate(dict_oc).error_count == 0
dict_oc = dict_official.deepcopy()
dict_oc.update(other=dict_c, mode="overlay")
errors = test_cif.validate(dict_oc)
#
# DDL2 merging
#
def cif_dic_from_str(string):
header = """\
data_test.dic
_dictionary.title test.dic
_dictionary.version 1
loop_
_item_type_list.code
_item_type_list.primitive_code
_item_type_list.construct
_item_type_list.detail
code char
'[_,.;:"&<>()/\{}'`~!@#$%A-Za-z0-9*|+-]*'
; code item types/single words ...
;
"""
return validation.dictionary(
cif.reader(input_string=header+string).model())
dic_a = cif_dic_from_str(
"""
save_fred
_category.description 'a description'
_category.id fred
_category.mandatory_code no
_category_key.name 'fred.id'
save_
""")
dic_b = cif_dic_from_str(
"""
save_fred
_category.id fred
_category.mandatory_code yes
_category_key.name 'fred.id'
loop_
_category_group.id 'inclusive_group'
'atom_group'
save_
""")
dic_c = cif_dic_from_str(
"""
save_bob
_category.id bob
_category.mandatory_code yes
_category_key.name 'bob.id'
save_
""")
assert dic_a.deepcopy() == dic_a
assert dic_a.copy() == dic_a
try: dic_a.deepcopy().update(dic_b, mode="strict")
except AssertionError: pass
else: raise Exception_expected
dic_ab = dic_a.deepcopy()
dic_ab.update(dic_b, mode="replace")
assert dic_ab == dic_b
dic_ab = dic_a.deepcopy()
dic_ab.update(dic_b, mode="overlay")
assert dic_ab['test.dic']['fred']['_category.mandatory_code'] == 'yes'
assert '_category.description' in dic_ab['test.dic']['fred']
assert '_category_group.id' in dic_ab['test.dic']['fred']
for mode in ("strict", "replace", "overlay"):
dic_ac = dic_a.deepcopy()
dic_ac.update(dic_c, mode=mode)
assert 'fred' in dic_ac['test.dic']
assert 'bob' in dic_ac['test.dic']