def AddCategory(self, categoryID, items):
"""Add Category"""
category = DataCategory(categoryID)
for item in items:
category.appendAttribute(item)
#
self.__container.append(category)
def add_category(self, category_id, items):
"""
This method creates a data category object, adds all items to it and appends it to the container
:param category_id: a string; an mmcif category e.g. 'emd_admin'
:param items: a list of strings; each element in the list is an item of mmcif category as defined by category_id
:return: a list of strings; each element represents a value for the corresponding element in data_items
"""
category = DataCategory(category_id)
for item in items:
category.appendAttribute(item)
self.__container.append(category)
def testEditAttributes(self):
"""Test case - get and extend atttribute names"""
try:
#
dcA = DataCategory("A", self.__attributeList, self.__rowListAsciiA)
self.assertEqual(0, dcA.getRowIndex())
self.assertEqual(None, dcA.getCurrentAttribute())
#
na = len(dcA.getAttributeList())
tL = dcA.getAttributeListWithOrder()
self.assertEqual(len(tL), na)
na = len(dcA.getAttributeList())
self.assertEqual(dcA.appendAttribute("ColNew"), na + 1)
row = dcA.getFullRow(0)
self.assertEqual(row[na], "?")
#
row = dcA.getFullRow(dcA.getRowCount() + 1)
for cV in row:
self.assertEqual(cV, "?")
#
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __generateData(self):
"""Generates data for test. __testValues must be in sync"""
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_test")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("details")
aCat.append([1, "data_my_big_data_file"])
aCat.append([2, "loop_my_big_data_loop"])
aCat.append([3, "save_my_big_data_saveframe"])
aCat.append([4, "_category.item"])
aCat.append([5, "Data_my_big_data_file"])
aCat.append([6, "Loop_my_big_data_loop"])
aCat.append([7, "Save_my_big_data_saveframe"])
aCat.append([8, "DatA_my_big_data_file"])
curContainer.append(aCat)
return curContainer
def writeDefaultDataTypeMap(self, outPath, dataTyping="ANY"):
"""Write data file containing application default dictionary to application data type mapping
data_rcsb_data_type_map
loop_
_pdbx_data_type_application_map.application_name
_pdbx_data_type_application_map.type_code
_pdbx_data_type_application_map.app_type_code
_pdbx_data_type_application_map.app_precision_default
_pdbx_data_type_application_map.app_width_default
# .... type mapping data ...
"""
try:
#
containerList = []
curContainer = DataContainer("rcsb_data_type_map")
aCat = DataCategory("pdbx_data_type_application_map")
aCat.appendAttribute("application_name")
aCat.appendAttribute("type_code")
aCat.appendAttribute("app_type_code")
aCat.appendAttribute("app_width_default")
aCat.appendAttribute("app_precision_default")
for (cifType, simpleType, defWidth, defPrecision) in zip(
DataTypeApplicationInfo.cifTypes,
DataTypeApplicationInfo.appTypes,
DataTypeApplicationInfo.defaultWidths,
DataTypeApplicationInfo.defaultPrecisions):
if self.__isNull(cifType):
continue
aCat.append(
[dataTyping, cifType, simpleType, defWidth, defPrecision])
curContainer.append(aCat)
containerList.append(curContainer)
#
mU = MarshalUtil(workPath=self.__workPath)
ok = mU.doExport(outPath,
containerList,
fmt="mmcif",
enforceAscii=True,
useCharRefs=True,
raiseExceptions=True)
return ok
except Exception as e:
logger.exception("Failing with %s", str(e))
return False
def test_edit_attributes(self, category_data):
dcA = DataCategory('A', category_data['attributeList'],
category_data['rowListAsciiA'])
assert 0 == dcA.getRowIndex()
assert None == dcA.getCurrentAttribute()
#
na = len(dcA.getAttributeList())
tL = dcA.getAttributeListWithOrder()
assert len(tL) == na
na = len(dcA.getAttributeList())
assert dcA.appendAttribute("ColNew") == na + 1
row = dcA.getFullRow(0)
assert row[na] == "?"
#
row = dcA.getFullRow(dcA.getRowCount() + 1)
for c in row:
assert c == "?"
def testWriteDataFile(self):
"""Test case - write data file"""
try:
#
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([7, 6, 5, 4, 3, 2, 1])
# aCat.printIt()
curContainer.append(aCat)
# curContainer.printIt()
#
myDataList.append(curContainer)
with open(self.__pathOutputFile1, "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
self.assertEqual(len(myDataList), 1)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def _createfile1(pathout):
my_data_list = []
cur_container = DataContainer("myblock")
acat = DataCategory("pdbx_item_enumeration")
acat.appendAttribute("name")
acat.appendAttribute("value")
acat.appendAttribute("detail")
acat.append(('1', '2', '3'))
cur_container.append(acat)
acat = DataCategory("exptl")
acat.appendAttribute('absorpt_coefficient_mu')
acat.appendAttribute('entry_id')
acat.appendAttribute('method')
acat.appendAttribute('details')
acat.append(('?', 'D_12345', 'X-RAY DIFFRACTION', 'some details'))
cur_container.append(acat)
acat = DataCategory("struct")
acat.appendAttribute('title')
acat.appendAttribute('pdbx_descriptor')
acat.append(('Start title', 'Start Descriptor'))
cur_container.append(acat)
my_data_list.append(cur_container)
# Second block
cur_container = DataContainer("secondblock")
acat = DataCategory("pdbx_item_enumeration")
acat.appendAttribute("name")
acat.appendAttribute("value")
acat.appendAttribute("detail")
acat.append(('3', '2', '1'))
cur_container.append(acat)
my_data_list.append(cur_container)
with open(pathout, "w") as ofh:
pdbxw = PdbxWriter(ofh)
pdbxw.setAlignmentFlag(flag=True)
pdbxw.write(my_data_list)
def _createfile2(pathout):
my_data_list = []
cur_container = DataContainer("test")
acat = DataCategory("new")
acat.appendAttribute("item")
acat.append(('1',))
cur_container.append(acat)
acat = DataCategory("second_category")
acat.appendAttribute('row')
acat.appendAttribute('rowb')
acat.append(('1', '2'))
cur_container.append(acat)
acat = DataCategory("third")
acat.appendAttribute('id')
acat.appendAttribute('val')
acat.append(('1', 'a'))
acat.append(('2', 'b'))
acat.append(('3', 'c'))
cur_container.append(acat)
acat = DataCategory("exptl")
acat.appendAttribute('method')
acat.appendAttribute('entry_id')
acat.append(('NEW', 'something'))
cur_container.append(acat)
acat = DataCategory("struct")
acat.appendAttribute('new')
acat.appendAttribute('pdbx_descriptor')
acat.append(('Something to add', 'Override descriptor'))
cur_container.append(acat)
my_data_list.append(cur_container)
with open(pathout, "w") as ofh:
pdbxw = PdbxWriter(ofh)
pdbxw.setAlignmentFlag(flag=True)
pdbxw.write(my_data_list)
def _makeKeyItem(self, catName, attName, keyItemList, iDef):
itemName = CifName.itemName(catName, attName)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([itemName, "Item", "Single", "2013-08-22"])
iDef.append(dc)
#
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append(['synthentic componsite key'])
iDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
dc.append([catName, attName])
iDef.append(dc)
tcontainer = 'Set'
purpose = 'Composite'
source = 'Derived'
contents = 'Name'
dimension = '[%d]' % len(keyItemList)
#
dc = DataCategory("type")
dc.appendAttribute("purpose")
dc.appendAttribute("source")
dc.appendAttribute("contents")
dc.appendAttribute("container")
dc.appendAttribute("dimension")
dc.append([purpose, source, contents, tcontainer, dimension])
iDef.append(dc)
dc = DataCategory("method")
dc.appendAttribute("purpose")
dc.appendAttribute("expression")
tmpl = '''
With row as %s
%s = [%s]
'''
mText = tmpl % (catName, itemName, ','.join(keyItemList))
dc.append(['Evaluation', mText])
iDef.append(dc)
def test_gen_ddlm(self, in_tmpdir, test_files):
myIo = IoAdapterPy()
containerList = myIo.readFile(
inputFilePath=str(test_files / 'mmcif_pdbx_v5_next.dic'))
dApi = DictionaryApi(containerList=containerList, consolidate=True)
parentD = dApi.getParentDictionary()
#
oCList = []
dDef = DataContainer('mmcif_pdbx_ddlm_auto')
dc = DataCategory("dictionary")
dc.appendAttribute("title")
dc.appendAttribute("class")
dc.appendAttribute("version")
dc.appendAttribute("date")
dc.appendAttribute("ddl_conformance")
dc.appendAttribute("text")
dc.append([
'mmcif_pdbx_ddlm_auto', 'Instance', 'latest', '2018-03-09',
'ddlm best effort',
'Software converted PDBx dictionary using DDLm semantics'
])
dDef.append(dc)
oCList.append(dDef)
catIdx = dApi.getCategoryIndex()
for catName in sorted(catIdx.keys()):
attNameList = catIdx[catName]
# created definition container -
cDef = DefinitionContainer(catName)
oCList.append(cDef)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([catName, "Category", "Loop", "2018-03-09"])
cDef.append(dc)
val = dApi.getCategoryDescription(category=catName)
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append([val])
cDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
valList = dApi.getCategoryGroupList(category=catName)
pcg = catName
for val in valList:
if val != 'inclusive_group':
pcg = val
break
dc.append([catName, pcg])
cDef.append(dc)
valList = dApi.getCategoryKeyList(category=catName)
if len(valList) < 1:
print("Missing caegory key for category %s\n" % catName)
else:
dc = DataCategory("category")
dc.appendAttribute("key_id")
kItemName = CifName.itemName(catName, "synthetic_key")
dc.append([kItemName])
cDef.append(dc)
iDef = DefinitionContainer(kItemName)
self._makeKeyItem(catName, "synthetic_key", valList, iDef)
oCList.append(iDef)
for attName in attNameList:
itemName = CifName.itemName(catName, attName)
iDef = DefinitionContainer(itemName)
oCList.append(iDef)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([itemName, "Item", "Single", "2013-08-22"])
iDef.append(dc)
#
val = dApi.getDescription(category=catName, attribute=attName)
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append([val])
iDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
#
if itemName in parentD:
dc.appendAttribute("linked_item_id")
dc.append([catName, attName, parentD[itemName][0]])
else:
dc.append([catName, attName])
iDef.append(dc)
#
#
aliasList = dApi.getItemAliasList(category=catName,
attribute=attName)
if len(aliasList) > 0:
dc = DataCategory("alias")
dc.appendAttribute("definition_id")
for alias in aliasList:
dc.append([alias[0]])
iDef.append(dc)
enList = dApi.getEnumListAltWithDetail(category=catName,
attribute=attName)
tC = dApi.getTypeCode(category=catName, attribute=attName)
tcontainer = 'Single'
purpose = 'Describe'
source = 'Recorded'
contents = 'Text'
#
if tC is None:
self.__lfh.write("Missing data type attribute %s\n" %
attName)
elif tC in [
'code', 'atcode', 'name', 'idname', 'symop', 'fax',
'phone', 'email', 'code30', 'ec-type'
]:
purpose = 'Encode'
contents = 'Text'
source = 'Assigned'
elif tC in ['ucode']:
purpose = 'Encode'
contents = 'Code'
source = 'Assigned'
elif tC in ['line', 'uline', 'text']:
purpose = 'Describe'
source = 'Recorded'
contents = 'Text'
elif tC in ['int']:
purpose = 'Number'
source = 'Recorded'
contents = 'Integer'
elif tC in ['int-range']:
purpose = 'Number'
source = 'Recorded'
contents = 'Range'
elif tC in ['float']:
purpose = 'Measurand'
source = 'Recorded'
contents = 'Real'
elif tC in ['float-range']:
purpose = 'Measurand'
source = 'Recorded'
contents = 'Range'
elif tC.startswith('yyyy'):
source = 'Assigned'
contents = 'Date'
purpose = 'Describe'
if len(enList) > 0:
purpose = 'State'
dc = DataCategory("type")
dc.appendAttribute("purpose")
dc.appendAttribute("source")
dc.appendAttribute("contents")
dc.appendAttribute("container")
dc.append([purpose, source, contents, tcontainer])
iDef.append(dc)
#
if (len(enList) > 0):
dc = DataCategory("enumeration_set")
dc.appendAttribute("state")
dc.appendAttribute("detail")
for en in enList:
dc.append([en[0], en[1]])
iDef.append(dc)
dfv = dApi.getDefaultValue(category=catName, attribute=attName)
bvList = dApi.getBoundaryList(category=catName,
attribute=attName)
if (((dfv is not None) and (dfv not in ['?', '.']))
or len(bvList) > 0):
row = []
dc = DataCategory("enumeration")
if dfv is not None:
dc.appendAttribute("default")
row.append(dfv)
if len(bvList) > 0:
dc.appendAttribute("range")
mminVp = -1000000
mmaxVp = 10000000
mminV = mmaxVp
mmaxV = mminVp
for bv in bvList:
minV = float(bv[0]) if bv[0] != '.' else mminVp
maxV = float(bv[1]) if bv[1] != '.' else mmaxVp
mminV = min(mminV, minV)
mmaxV = max(mmaxV, maxV)
if mminV == mminVp:
mminV = ''
if mmaxV == mmaxVp:
mmaxV = ''
row.append(str(mminV) + ":" + str(mmaxV))
dc.append(row)
iDef.append(dc)
myIo.writeFile(outputFilePath="mmcif_pdbx_ddlm_auto.dic",
containerList=oCList)
def test_write_data_file(self, writer_paths):
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append(
(1, 2, 3, 4, '55555555555555555555555555555555555555555555', 6, 7))
aCat.append((1, 2, 3, 4, '5555', 6, 7))
aCat.append((1, 2, 3, 4, '5555555555', 6, 7))
aCat.append((1, 2, 3, 4, '5', 6, 7))
curContainer.append(aCat)
myDataList.append(curContainer)
with open(str(writer_paths['pathOutputFile1']), "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.setAlignmentFlag(flag=True)
pdbxW.write(myDataList)
assert len(myDataList) == 1
def test_update_data_file(self, writer_paths):
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append((1, 2, 3, 4, 5, 6, 7))
aCat.append((1, 2, 3, 4, 5, 6, 7))
aCat.append((1, 2, 3, 4, 5, 6, 7))
aCat.append((1, 2, 3, 4, 5, 6, 7))
curContainer.append(aCat)
myDataList.append(curContainer)
with open(str(writer_paths['pathOutputFile1']), "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
#
# Read and update the data -
#
myDataList = []
with open(str(writer_paths['pathOutputFile1']), "r") as ifh:
pRd = PdbxReader(ifh)
pRd.read(myDataList)
#
myBlock = myDataList[0]
# myBlock.printIt()
myCat = myBlock.getObj('pdbx_seqtool_mapping_ref')
# myCat.printIt()
for iRow in range(0, myCat.getRowCount()):
myCat.setValue('some value', 'ref_mon_id', iRow)
myCat.setValue(100, 'ref_mon_num', iRow)
with open(str(writer_paths['pathOutputFile2']), "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
assert len(myDataList) == 1
def process_entry(file_in, file_out):
try:
cif_file = gemmi.cif.read(file_in) # pylint: disable=no-member
data_block = cif_file[0]
except Exception as e:
logger.error("Failed to read cif file in Gemmi")
logger.error(e)
return 1
logging.info("Finding Centre of Mass")
com = get_center_of_mass(data_block)
if not com:
return 1
try:
io = IoAdapterCore()
ccL = io.readFile(file_in)
except Exception as e:
logger.error("Failed to read cif file using IoAdapterCore %s", e)
return 1
if len(ccL) == 0:
logger.error("No data parsed from file")
return 1
# First block only
b0 = ccL[0]
obj = b0.getObj("struct")
# If category does not exist
if obj is None:
# Need entry.id
eid = "XXXX"
eobj = b0.getObj("entry")
if eobj:
if "id" in eobj.getAttributeList():
eid = eobj.getValue("id", 0)
obj = DataCategory("struct")
obj.appendAttribute("entry_id")
obj.setValue(eid, "entry_id", 0)
ccL[0].append(obj)
newdata = [["pdbx_center_of_mass_x", com.x],
["pdbx_center_of_mass_y", com.y],
["pdbx_center_of_mass_z", com.z]]
for [it, val] in newdata:
if it not in obj.getAttributeList():
obj.appendAttribute(it)
obj.setValue(str(val), it, 0)
try:
logging.info("Writing mmcif file: %s", file_out)
ret = io.writeFile(file_out, ccL)
if not ret:
logger.info("Writing failed error %s", ret)
return 1
except Exception as e:
logger.error("Failed to write ccif file in IoAdapater %s", e)
return 1
# existing_data = data_block.get_mmcif_category('_struct.')
# new_data = {
# **existing_data,
# 'pdbx_center_of_mass_x': [com.x],
# 'pdbx_center_of_mass_y': [com.y],
# 'pdbx_center_of_mass_z': [com.z]
# }
# logging.info("Writing mmcif file: %s", file_out)
# try:
# data_block.set_mmcif_category('_struct.', new_data)
# cif_file.write_file(file_out)
# except Exception as e:
# logger.error("Failed to write cif file in Gemmi")
# logger.error(e)
# return 1
return 0
def test_write_data_file(self, rw_data):
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([1, 2, 3, 4, 5, 6, 7])
aCat.append([7, 6, 5, 4, 3, 2, 1])
curContainer.append(aCat)
myDataList.append(curContainer)
with open(str(rw_data['pathOutputFile1']), "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
assert len(myDataList) == 1
def testUpdateDataFile(self):
"""Test case - update data file"""
try:
# Create a initial data file --
#
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append([9, 2, 3, 4, 5, 6, 7])
aCat.append([10, 2, 3, 4, 5, 6, 7])
aCat.append([11, 2, 3, 4, 5, 6, 7])
aCat.append([12, 2, 3, 4, 5, 6, 7])
curContainer.append(aCat)
myDataList.append(curContainer)
ofh = open(self.__pathOutputFile1, "w")
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
ofh.close()
#
#
# Read and update the data -
#
myDataList = []
ifh = open(self.__pathOutputFile1, "r")
pRd = PdbxReader(ifh)
pRd.read(myDataList)
ifh.close()
#
myBlock = myDataList[0]
# myBlock.printIt()
myCat = myBlock.getObj("pdbx_seqtool_mapping_ref")
# myCat.printIt()
for iRow in range(0, myCat.getRowCount()):
myCat.setValue("some value", "ref_mon_id", iRow)
myCat.setValue(100, "ref_mon_num", iRow)
with open(self.__pathOutputFile2, "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
#
self.assertEqual(len(myDataList), 1)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def _createfile2(pathout):
my_data_list = []
cur_container = DataContainer("test")
acat = DataCategory("new")
acat.appendAttribute("item")
acat.append(("1",))
cur_container.append(acat)
acat = DataCategory("second_category")
acat.appendAttribute("row")
acat.appendAttribute("rowb")
acat.append(("1", "2"))
cur_container.append(acat)
acat = DataCategory("third")
acat.appendAttribute("id")
acat.appendAttribute("val")
acat.append(("1", "a"))
acat.append(("2", "b"))
acat.append(("3", "c"))
cur_container.append(acat)
acat = DataCategory("exptl")
acat.appendAttribute("method")
acat.appendAttribute("entry_id")
acat.append(("NEW", "something"))
cur_container.append(acat)
acat = DataCategory("struct")
acat.appendAttribute("new")
acat.appendAttribute("pdbx_descriptor")
acat.append(("Something to add", "Override descriptor"))
cur_container.append(acat)
my_data_list.append(cur_container)
with open(pathout, "w") as ofh:
pdbxw = PdbxWriter(ofh)
pdbxw.setAlignmentFlag(flag=True)
pdbxw.write(my_data_list)
def testGenDDLm(self):
"""Generating alternative DDLm metadata format. (starting point)"""
try:
myIo = IoAdapterPy(self.__verbose, self.__lfh)
self.__containerList = myIo.readFile(
inputFilePath=self.__pathPdbxDictionary)
dApi = DictionaryApi(containerList=self.__containerList,
consolidate=True,
verbose=self.__verbose)
parentD = dApi.getParentDictionary()
#
oCList = []
dDef = DataContainer("mmcif_pdbx_ddlm_auto")
dc = DataCategory("dictionary")
dc.appendAttribute("title")
dc.appendAttribute("class")
dc.appendAttribute("version")
dc.appendAttribute("date")
dc.appendAttribute("ddl_conformance")
dc.appendAttribute("text")
dc.append([
"mmcif_pdbx_ddlm_auto", "Instance", "latest", "2018-03-09",
"ddlm best effort",
"Software converted PDBx dictionary using DDLm semantics"
])
dDef.append(dc)
oCList.append(dDef)
catIdx = dApi.getCategoryIndex()
for catName in sorted(catIdx.keys()):
attNameList = catIdx[catName]
# created definition container -
cDef = DefinitionContainer(catName)
oCList.append(cDef)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([catName, "Category", "Loop", "2018-03-09"])
cDef.append(dc)
val = dApi.getCategoryDescription(category=catName)
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append([val])
cDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
valList = dApi.getCategoryGroupList(category=catName)
pcg = catName
for val in valList:
if val != "inclusive_group":
pcg = val
break
dc.append([catName, pcg])
cDef.append(dc)
valList = dApi.getCategoryKeyList(category=catName)
if not valList:
self.__lfh.write("Missing caegory key for category %s\n" %
catName)
else:
dc = DataCategory("category")
dc.appendAttribute("key_id")
kItemName = CifName.itemName(catName, "synthetic_key")
dc.append([kItemName])
cDef.append(dc)
iDef = DefinitionContainer(kItemName)
self.__makeKeyItem(catName, "synthetic_key", valList, iDef)
oCList.append(iDef)
for attName in attNameList:
itemName = CifName.itemName(catName, attName)
iDef = DefinitionContainer(itemName)
oCList.append(iDef)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([itemName, "Item", "Single", "2013-08-22"])
iDef.append(dc)
#
val = dApi.getDescription(category=catName,
attribute=attName)
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append([val])
iDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
#
if itemName in parentD:
dc.appendAttribute("linked_item_id")
dc.append([catName, attName, parentD[itemName][0]])
else:
dc.append([catName, attName])
iDef.append(dc)
#
#
aliasList = dApi.getItemAliasList(category=catName,
attribute=attName)
if aliasList:
dc = DataCategory("alias")
dc.appendAttribute("definition_id")
for alias in aliasList:
dc.append([alias[0]])
iDef.append(dc)
enList = dApi.getEnumListAltWithDetail(category=catName,
attribute=attName)
tC = dApi.getTypeCode(category=catName, attribute=attName)
tcontainer = "Single"
purpose = "Describe"
source = "Recorded"
contents = "Text"
#
if tC is None:
self.__lfh.write("Missing data type attribute %s\n" %
attName)
elif tC in [
"code", "atcode", "name", "idname", "symop", "fax",
"phone", "email", "code30", "ec-type"
]:
purpose = "Encode"
contents = "Text"
source = "Assigned"
elif tC in ["ucode"]:
purpose = "Encode"
contents = "Code"
source = "Assigned"
elif tC in ["line", "uline", "text"]:
purpose = "Describe"
source = "Recorded"
contents = "Text"
elif tC in ["int"]:
purpose = "Number"
source = "Recorded"
contents = "Integer"
elif tC in ["int-range"]:
purpose = "Number"
source = "Recorded"
contents = "Range"
elif tC in ["float"]:
purpose = "Measurand"
source = "Recorded"
contents = "Real"
elif tC in ["float-range"]:
purpose = "Measurand"
source = "Recorded"
contents = "Range"
elif tC.startswith("yyyy"):
source = "Assigned"
contents = "Date"
purpose = "Describe"
if enList:
purpose = "State"
dc = DataCategory("type")
dc.appendAttribute("purpose")
dc.appendAttribute("source")
dc.appendAttribute("contents")
dc.appendAttribute("container")
dc.append([purpose, source, contents, tcontainer])
iDef.append(dc)
#
if enList:
dc = DataCategory("enumeration_set")
dc.appendAttribute("state")
dc.appendAttribute("detail")
for en in enList:
dc.append([en[0], en[1]])
iDef.append(dc)
dfv = dApi.getDefaultValue(category=catName,
attribute=attName)
bvList = dApi.getBoundaryList(category=catName,
attribute=attName)
if ((dfv is not None) and
(dfv not in ["?", "."])) or bvList:
row = []
dc = DataCategory("enumeration")
if dfv is not None:
dc.appendAttribute("default")
row.append(dfv)
if bvList:
dc.appendAttribute("range")
mminVp = -1000000
mmaxVp = 10000000
mminV = mmaxVp
mmaxV = mminVp
for bv in bvList:
minV = float(bv[0]) if bv[0] != "." else mminVp
maxV = float(bv[1]) if bv[1] != "." else mmaxVp
mminV = min(mminV, minV)
mmaxV = max(mmaxV, maxV)
if mminV == mminVp:
mminV = ""
if mmaxV == mmaxVp:
mmaxV = ""
row.append(str(mminV) + ":" + str(mmaxV))
dc.append(row)
iDef.append(dc)
myIo.writeFile(outputFilePath=os.path.join(
HERE, "test-output", "mmcif_pdbx_ddlm_auto.dic"),
containerList=oCList)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __makeKeyItem(self, catName, attName, keyItemList, iDef):
itemName = CifName.itemName(catName, attName)
#
dc = DataCategory("definition")
dc.appendAttribute("id")
dc.appendAttribute("scope")
dc.appendAttribute("class")
dc.appendAttribute("update")
dc.append([itemName, "Item", "Single", "2013-08-22"])
iDef.append(dc)
#
dc = DataCategory("description")
dc.appendAttribute("text")
dc.append(["synthentic componsite key"])
iDef.append(dc)
#
dc = DataCategory("name")
dc.appendAttribute("category_id")
dc.appendAttribute("object_id")
dc.append([catName, attName])
iDef.append(dc)
tcontainer = "Set"
purpose = "Composite"
source = "Derived"
contents = "Name"
dimension = "[%d]" % len(keyItemList)
#
dc = DataCategory("type")
dc.appendAttribute("purpose")
dc.appendAttribute("source")
dc.appendAttribute("contents")
dc.appendAttribute("container")
dc.appendAttribute("dimension")
dc.append([purpose, source, contents, tcontainer, dimension])
iDef.append(dc)
dc = DataCategory("method")
dc.appendAttribute("purpose")
dc.appendAttribute("expression")
tmpl = """
With row as %s
%s = [%s]
"""
mText = tmpl % (catName, itemName, ",".join(keyItemList))
dc.append(["Evaluation", mText])
iDef.append(dc)
def test_update_data_file(self, rw_data):
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.append([9, 2, 3, 4, 5, 6, 7])
aCat.append([10, 2, 3, 4, 5, 6, 7])
aCat.append([11, 2, 3, 4, 5, 6, 7])
aCat.append([12, 2, 3, 4, 5, 6, 7])
curContainer.append(aCat)
myDataList.append(curContainer)
ofh = open(str(rw_data['pathOutputFile1']), "w")
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
ofh.close()
myDataList = []
ifh = open(str(rw_data['pathOutputFile1']), "r")
pRd = PdbxReader(ifh)
pRd.read(myDataList)
ifh.close()
myBlock = myDataList[0]
myCat = myBlock.getObj('pdbx_seqtool_mapping_ref')
for iRow in range(0, myCat.getRowCount()):
myCat.setValue('some value', 'ref_mon_id', iRow)
myCat.setValue(100, 'ref_mon_num', iRow)
with open(str(rw_data['pathOutputFile2']), "w") as ofh:
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
assert len(myDataList) == 1
def test_single_row(self, rw_data):
myDataList = []
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.appendAttribute("details")
aCat.append([1, 2, 3, 4, 5, 6, 7, 'data_my_big_data_file'])
aCat.append([1, 2, 3, 4, 5, 6, 7, 'loop_my_big_data_loop'])
aCat.append([1, 2, 3, 4, 5, 6, 7, 'save_my_big_data_saveframe'])
aCat.append([1, 2, 3, 4, 5, 6, 7, '_category.item'])
curContainer.append(aCat)
bCat = curContainer.getObj("pdbx_seqtool_mapping_ref")
print("----attribute list %r\n" % bCat.getAttributeList())
row = bCat.getRow(0)
print("----ROW %r\n" % row)
with open(str(rw_data['pathOutputFile2']), "w") as ofh:
myDataList.append(curContainer)
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
assert len(myDataList) == 1
def __parser(self,
tokenizer,
containerList,
categorySelectionD=None,
excludeFlag=False):
""" Parser for PDBx data files and dictionaries.
Input - tokenizer() reentrant method recognizing data item names (_category.attribute)
quoted strings (single, double and multi-line semi-colon delimited), and unquoted
strings.
containerList - list-type container for data and definition objects parsed from
from the input file.
On return:
The input containerList is appended with data and definition objects -
"""
catSelectD = categorySelectionD if categorySelectionD is not None else {}
logger.debug("Exclude Flag %r Category selection %r", excludeFlag,
catSelectD)
# Working container - data or definition
curContainer = None
# the last container of type data -
previousDataContainer = None
#
# Working category container
categoryIndex = {}
curCategory = None
#
curRow = None
state = None
# Find the first reserved word and begin capturing data.
#
while True:
curCatName, curAttName, curQuotedString, curWord = next(tokenizer)
if curWord is None:
continue
reservedWord, state = self.__getState(curWord)
if reservedWord is not None:
break
while True:
#
# Set the current state -
#
# At this point in the processing cycle we are expecting a token containing
# either a '_category.attribute' or a reserved word.
#
if curCatName is not None:
state = "ST_KEY_VALUE_PAIR"
elif curWord is not None:
reservedWord, state = self.__getState(curWord)
else:
self.__syntaxError("Miscellaneous syntax error")
return
#
# Process _category.attribute value assignments
#
if state == "ST_KEY_VALUE_PAIR":
try:
curCategory = categoryIndex[curCatName]
except KeyError:
# A new category is encountered - create a container and add a row
curCategory = categoryIndex[curCatName] = DataCategory(
curCatName)
#
# check if we have all of the selection
if not excludeFlag and self.__allSelected(
curContainer, catSelectD):
return
try:
if catSelectD:
if not excludeFlag and curCatName in catSelectD:
curContainer.append(curCategory)
elif excludeFlag and curCatName not in catSelectD:
curContainer.append(curCategory)
else:
logger.debug(
"Skipped unselected/excluded category %s",
curCatName)
else:
curContainer.append(curCategory)
except AttributeError:
self.__syntaxError(
"Category cannot be added to data_ block")
return
curRow = []
curCategory.append(curRow)
else:
# Recover the existing row from the category
try:
# curRow = curCategory[0]
curRow = curCategory.getRow(0)
except IndexError:
self.__syntaxError(
"Internal index error accessing category data")
return
# Check for duplicate attributes and add attribute to table.
if curAttName in curCategory.getAttributeList():
self.__syntaxError(
"Duplicate attribute encountered in category")
return
else:
curCategory.appendAttribute(curAttName)
# Get the data for this attribute from the next token
tCat, _, curQuotedString, curWord = next(tokenizer)
if tCat is not None or (curQuotedString is None
and curWord is None):
self.__syntaxError("Missing data for item _%s.%s" %
(curCatName, curAttName))
if curWord is not None:
#
# Validation check token for misplaced reserved words -
#
reservedWord, state = self.__getState(curWord)
if reservedWord is not None:
self.__syntaxError("Unexpected reserved word: %s" %
(reservedWord))
curRow.append(curWord)
elif curQuotedString is not None:
curRow.append(curQuotedString)
else:
self.__syntaxError("Missing value in item-value pair")
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
continue
#
# Process a loop_ declaration and associated data -
#
elif state == "ST_TABLE":
# The category name in the next curCatName,curAttName pair
# defines the name of the category container.
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
if curCatName is None or curAttName is None:
self.__syntaxError("Unexpected token in loop_ declaration")
return
# Check for a previous category declaration.
if curCatName in categoryIndex:
self.__syntaxError(
"Duplicate category declaration in loop_")
return
curCategory = DataCategory(curCatName)
#
# check if we have all of the selection
if not excludeFlag and self.__allSelected(
curContainer, catSelectD):
return
try:
if catSelectD:
if not excludeFlag and curCatName in catSelectD:
curContainer.append(curCategory)
elif excludeFlag and curCatName not in catSelectD:
curContainer.append(curCategory)
else:
logger.debug(
"Skipped unselected/excluded category %s",
curCatName)
else:
curContainer.append(curCategory)
except AttributeError:
self.__syntaxError(
"loop_ declaration outside of data_ block or save_ frame"
)
return
curCategory.appendAttribute(curAttName)
# Read the rest of the loop_ declaration
while True:
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
if curCatName is None:
break
if curCatName != curCategory.getName():
self.__syntaxError(
"Changed category name in loop_ declaration")
return
curCategory.appendAttribute(curAttName)
# If the next token is a 'word', check it for any reserved words -
if curWord is not None:
reservedWord, state = self.__getState(curWord)
if reservedWord is not None:
if reservedWord == "stop":
return
else:
self.__syntaxError(
"Unexpected reserved word after loop declaration: %s"
% (reservedWord))
# Read the table of data for this loop_ -
while True:
curRow = []
curCategory.append(curRow)
for _ in curCategory.getAttributeList():
if curWord is not None:
curRow.append(curWord)
elif curQuotedString is not None:
curRow.append(curQuotedString)
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
# loop_ data processing ends if -
# A new _category.attribute is encountered
if curCatName is not None:
break
# A reserved word is encountered
if curWord is not None:
reservedWord, state = self.__getState(curWord)
if reservedWord is not None:
break
continue
elif state == "ST_DEFINITION":
# Ignore trailing unnamed saveframe delimiters e.g. 'save'
sName = self.__getContainerName(curWord)
if sName:
curContainer = DefinitionContainer(sName)
containerList.append(curContainer)
categoryIndex = {}
curCategory = None
else:
# reset current container to the last data contatiner
curContainer = previousDataContainer
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
elif state == "ST_DATA_CONTAINER":
#
dName = self.__getContainerName(curWord)
if not dName:
dName = "unidentified"
curContainer = DataContainer(dName)
containerList.append(curContainer)
categoryIndex = {}
curCategory = None
previousDataContainer = curContainer
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
elif state == "ST_STOP":
###
# curCatName, curAttName, curQuotedString, curWord = tokenizer.next()
continue
elif state == "ST_GLOBAL":
curContainer = DataContainer("blank-global")
curContainer.setGlobal()
containerList.append(curContainer)
categoryIndex = {}
curCategory = None
curCatName, curAttName, curQuotedString, curWord = next(
tokenizer)
elif state == "ST_UNKNOWN":
self.__syntaxError("Unrecogized syntax element: " +
str(curWord))
return
def testSingleRow(self):
"""Test case - read /write single row and null row in data file"""
try:
#
myDataList = []
# ofh = open(self.__pathOutputFile1, "w")
curContainer = DataContainer("myblock")
aCat = DataCategory("pdbx_seqtool_mapping_ref")
aCat.appendAttribute("ordinal")
aCat.appendAttribute("entity_id")
aCat.appendAttribute("auth_mon_id")
aCat.appendAttribute("auth_mon_num")
aCat.appendAttribute("pdb_chain_id")
aCat.appendAttribute("ref_mon_id")
aCat.appendAttribute("ref_mon_num")
aCat.appendAttribute("details")
aCat.append([1, 2, 3, 4, 5, 6, 7, "data_my_big_data_file"])
aCat.append([1, 2, 3, 4, 5, 6, 7, "loop_my_big_data_loop"])
aCat.append([1, 2, 3, 4, 5, 6, 7, "save_my_big_data_saveframe"])
aCat.append([1, 2, 3, 4, 5, 6, 7, "_category.item"])
# aCat.dumpIt()
curContainer.append(aCat)
#
bCat = curContainer.getObj("pdbx_seqtool_mapping_ref")
logger.debug("----attribute list %r", bCat.getAttributeList())
row = bCat.getRow(0)
logger.debug("----ROW %r", row)
#
with open(self.__pathOutputFile2, "w") as ofh:
myDataList.append(curContainer)
pdbxW = PdbxWriter(ofh)
pdbxW.write(myDataList)
self.assertEqual(len(myDataList), 1)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def _createfile1(pathout):
my_data_list = []
cur_container = DataContainer("myblock")
acat = DataCategory("pdbx_item_enumeration")
acat.appendAttribute("name")
acat.appendAttribute("value")
acat.appendAttribute("detail")
acat.append(("1", "2", "3"))
cur_container.append(acat)
acat = DataCategory("exptl")
acat.appendAttribute("absorpt_coefficient_mu")
acat.appendAttribute("entry_id")
acat.appendAttribute("method")
acat.appendAttribute("details")
acat.append(("?", "D_12345", "X-RAY DIFFRACTION", "some details"))
cur_container.append(acat)
acat = DataCategory("struct")
acat.appendAttribute("title")
acat.appendAttribute("pdbx_descriptor")
acat.append(("Start title", "Start Descriptor"))
cur_container.append(acat)
my_data_list.append(cur_container)
# Second block
cur_container = DataContainer("secondblock")
acat = DataCategory("pdbx_item_enumeration")
acat.appendAttribute("name")
acat.appendAttribute("value")
acat.appendAttribute("detail")
acat.append(("3", "2", "1"))
cur_container.append(acat)
my_data_list.append(cur_container)
with open(pathout, "w") as ofh:
pdbxw = PdbxWriter(ofh)
pdbxw.setAlignmentFlag(flag=True)
pdbxw.write(my_data_list)
