def __init__(self, schemaDefObj, ioObj=None, dbCon=None, workPath=".", cleanUp=False, warnings="default", verbose=True):
"""Map PDBx/mmCIF instance data to SQL loadable data using external schema definition.
Args:
schemaDefObj (object): Description
ioObj (None, optional): Description
dbCon (None, optional): Description
workPath (str, optional): Description
cleanUp (bool, optional): Description
warnings (str, optional): Description
verbose (bool, optional): Description
"""
self.__verbose = verbose
self.__debug = False
self.__sD = schemaDefObj
self.__ioObj = ioObj
#
self.__dbCon = dbCon
self.__workingPath = workPath
self.__pathList = []
self.__cleanUp = cleanUp
#
# self.__sdp = SchemaDefDataPrep(schemaDefObj=schemaDefObj, ioObj=IoAdapter(), verbose=True)
#
self.__warningAction = warnings
self.__fTypeRow = "skip-max-width"
dtf = DataTransformFactory(schemaDefAccessObj=self.__sD, filterType=self.__fTypeRow)
self.__sdp = SchemaDefDataPrep(schemaDefAccessObj=self.__sD, dtObj=dtf, workPath=self.__workingPath, verbose=self.__verbose)
def __init__(self,
schemaDefObj,
ioObj=None,
dbCon=None,
workPath=".",
cleanUp=False,
warnings="default",
verbose=True):
self.__verbose = verbose
self.__debug = False
self.__sD = schemaDefObj
self.__ioObj = ioObj
#
self.__dbCon = dbCon
self.__workingPath = workPath
self.__pathList = []
self.__cleanUp = cleanUp
#
# self.__sdp = SchemaDefDataPrep(schemaDefAccessObj=schemaDefObj, ioObj=IoAdapter(), verbose=True)
#
self.__warningAction = warnings
#
self.__fTypeRow = "skip-max-width"
dtf = DataTransformFactory(schemaDefAccessObj=self.__sD,
filterType=self.__fTypeRow)
self.__sdp = SchemaDefDataPrep(schemaDefAccessObj=self.__sD,
dtObj=dtf,
workPath=self.__workingPath,
verbose=self.__verbose)
def __init__(self, cfgOb, schemaDefObj, cfgSectionName="site_info_configuration", dbCon=None, cachePath=".", workPath=".", cleanUp=False, warnings="default", verbose=True):
self.__verbose = verbose
self.__debug = False
self.__cfgOb = cfgOb
sectionName = cfgSectionName
self.__sD = schemaDefObj
#
self.__dbCon = dbCon
self.__cachePath = cachePath
self.__workPath = workPath
self.__pathList = []
self.__cleanUp = cleanUp
#
self.__colSep = "&##&\t"
self.__rowSep = "$##$\n"
#
#
self.__fTypeRow = "skip-max-width"
self.__fTypeCol = "skip-max-width"
#
self.__warningAction = warnings
dtf = DataTransformFactory(schemaDefAccessObj=self.__sD, filterType=self.__fTypeRow)
self.__sdp = SchemaDefDataPrep(schemaDefAccessObj=self.__sD, dtObj=dtf, workPath=self.__cachePath, verbose=self.__verbose)
self.__rpP = RepositoryProvider(cfgOb=self.__cfgOb, cachePath=self.__cachePath)
#
schemaName = self.__sD.getName()
modulePathMap = self.__cfgOb.get("DICT_METHOD_HELPER_MODULE_PATH_MAP", sectionName=sectionName)
dP = DictionaryApiProviderWrapper(self.__cfgOb, self.__cachePath, useCache=True)
dictApi = dP.getApiByName(schemaName)
rP = DictMethodResourceProvider(self.__cfgOb, cachePath=self.__cachePath)
self.__dmh = DictMethodRunner(dictApi, modulePathMap=modulePathMap, resourceProvider=rP)
def __simpleSchemaDataPrep(self, contentType, filterType, styleType, mockLength, rejectLength=0, dataSelectors=None, mergeContentTypes=None):
"""Internal method for preparing file-based data NOT requiring dynamic methods, slicing, or key injection.
Args:
contentType (str): Content type name
filterType (str): List of data processing options (separated by '|') (e.g. "drop-empty-attributes|drop-empty-tables|skip-max-width|...)
styleType (str): organization of output document (e.g. rowise-by-name)
mockLength (int): Expected length of the test data for the input content type
rejectLength (int, optional): number of input data sets rejected by the dataselection criteria. Defaults to 0.
dataSelectors (list of str, optional): data selection criteria. Defaults to None.
mergeContentTypes (list of str, optional): list content types to merge with the input data set. Defaults to None. (e.g. ['vrpt'])
"""
try:
dataSelectors = dataSelectors if dataSelectors else ["PUBLIC_RELEASE"]
dD = self.__schP.makeSchemaDef(contentType, dataTyping="ANY", saveSchema=True)
_ = SchemaDefAccess(dD)
inputPathList = self.__rpP.getLocatorObjList(contentType=contentType, mergeContentTypes=mergeContentTypes)
sd, _, _, _ = self.__schP.getSchemaInfo(databaseName=contentType, dataTyping="ANY")
dtf = DataTransformFactory(schemaDefAccessObj=sd, filterType=filterType)
sdp = SchemaDefDataPrep(schemaDefAccessObj=sd, dtObj=dtf, workPath=self.__cachePath, verbose=self.__verbose)
#
logger.debug("For %s mock length %d length of path list %d\n", contentType, mockLength, len(inputPathList))
self.assertEqual(len(inputPathList), mockLength)
tableDataDictList, containerNameList, rejectList = sdp.fetchDocuments(inputPathList, styleType=styleType, filterType=filterType, dataSelectors=dataSelectors)
logger.debug("For %s mock length %d reject length %d length of tddl list %d\n", contentType, mockLength, rejectLength, len(tableDataDictList))
self.assertEqual(len(tableDataDictList), mockLength - rejectLength)
self.assertEqual(len(containerNameList), mockLength - rejectLength)
if rejectList:
logger.debug("For %s rejecting components %r", contentType, rejectList)
#
self.assertEqual(len(rejectList), rejectLength)
fName = "simple-prep-%s-%s.json" % (contentType, styleType)
if self.__exportFlag:
fPath = os.path.join(self.__outputPath, fName)
self.__mU.doExport(fPath, tableDataDictList, fmt="json", indent=3)
if self.__diffFlag:
fPath = os.path.join(self.__savedOutputPath, fName)
refDocList = self.__mU.doImport(fPath, fmt="json")
self.assertEqual(len(refDocList), len(tableDataDictList))
#
jD = diff(refDocList, tableDataDictList, syntax="explicit", marshal=True)
if jD:
_, fn = os.path.split(fPath)
bn, _ = os.path.splitext(fn)
fPath = os.path.join(self.__outputPath, bn + "-diff.json")
logger.debug("jsondiff for %s %s = \n%s", contentType, styleType, pprint.pformat(jD, indent=3, width=100))
self.__mU.doExport(fPath, jD, fmt="json", indent=3)
self.assertEqual(len(jD), 0)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __testPrepDocumentsFromContainers(self, inputPathList, databaseName, collectionName, styleType="rowwise_by_name_with_cardinality", mergeContentTypes=None):
"""Test case - create loadable PDBx data from repository files
"""
try:
sd, _, _, _ = self.__schP.getSchemaInfo(databaseName)
#
dP = DictionaryApiProviderWrapper(self.__cfgOb, self.__cachePath, useCache=False)
dictApi = dP.getApiByName(databaseName)
rP = DictMethodResourceProvider(self.__cfgOb, configName=self.__configName, cachePath=self.__cachePath, siftsAbbreviated="TEST")
dmh = DictMethodRunner(dictApi, modulePathMap=self.__modulePathMap, resourceProvider=rP)
#
dtf = DataTransformFactory(schemaDefAccessObj=sd, filterType=self.__fTypeRow)
sdp = SchemaDefDataPrep(schemaDefAccessObj=sd, dtObj=dtf, workPath=self.__cachePath, verbose=self.__verbose)
containerList = self.__rpP.getContainerList(inputPathList)
for container in containerList:
cName = container.getName()
logger.debug("Processing container %s", cName)
dmh.apply(container)
if self.__export:
savePath = os.path.join(HERE, "test-output", cName + "-with-method.cif")
#self.__mU.doExport(savePath, [container], fmt="mmcif")
#
tableIdExcludeList = sd.getCollectionExcluded(collectionName)
tableIdIncludeList = sd.getCollectionSelected(collectionName)
sliceFilter = sd.getCollectionSliceFilter(collectionName)
sdp.setSchemaIdExcludeList(tableIdExcludeList)
sdp.setSchemaIdIncludeList(tableIdIncludeList)
#
docList, containerNameList, _ = sdp.processDocuments(
containerList, styleType=styleType, filterType=self.__fTypeRow, dataSelectors=["PUBLIC_RELEASE"], sliceFilter=sliceFilter, collectionName=collectionName
)
docList = sdp.addDocumentPrivateAttributes(docList, collectionName)
docList = sdp.addDocumentSubCategoryAggregates(docList, collectionName)
#
mergeS = "-".join(mergeContentTypes) if mergeContentTypes else ""
if self.__export and docList:
# for ii, doc in enumerate(docList[:1]):
for ii, doc in enumerate(docList):
cn = containerNameList[ii]
fp = os.path.join(HERE, "test-output", "prep-%s-%s-%s-%s.json" % (cn, databaseName, collectionName, mergeS))
self.__mU.doExport(fp, [doc], fmt="json", indent=3)
logger.debug("Exported %r", fp)
#
return docList, containerNameList
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __fullSchemaDataPrep(self,
contentType,
filterType,
styleType,
mockLength,
rejectLength=0,
dataSelectors=None,
mergeContentTypes=None,
excludeExtras=None):
"""Internal method for preparing file-based data requiring dynamic methods, slicing, or key injection.
Args:
contentType (str): Content type name
filterType (str): List of data processing options (separated by '|') (e.g. "drop-empty-attributes|drop-empty-tables|skip-max-width|...)
styleType (str): organization of output document (e.g. rowise-by-name)
mockLength (int): Expected length of the test data for the input content type
rejectLength (int, optional): number of input data sets rejected by the dataselection criteria. Defaults to 0.
dataSelectors (list of str, optional): data selection criteria. Defaults to None.
mergeContentTypes (list of str, optional): list content types to merge with the input data set. Defaults to None. (e.g. ['vrpt'])
"""
try:
excludeExtras = excludeExtras if excludeExtras else []
_ = mockLength
_ = rejectLength
dD = self.__schP.makeSchemaDef(contentType,
dataTyping="ANY",
saveSchema=True)
_ = SchemaDefAccess(dD)
inputPathList = self.__rpP.getLocatorObjList(
contentType=contentType, mergeContentTypes=mergeContentTypes)
sd, _, collectionNameList, _ = self.__schP.getSchemaInfo(
databaseName=contentType, dataTyping="ANY")
#
dP = DictionaryApiProviderWrapper(self.__cachePath,
cfgOb=self.__cfgOb,
configName=self.__configName,
useCache=True)
dictApi = dP.getApiByName(contentType)
#
rP = DictMethodResourceProvider(
self.__cfgOb,
configName=self.__configName,
cachePath=self.__cachePath,
restoreUseStash=False,
restoreUseGit=True,
providerTypeExclude=self.__excludeType,
)
dmh = DictMethodRunner(dictApi,
modulePathMap=self.__modulePathMap,
resourceProvider=rP)
#
dtf = DataTransformFactory(schemaDefAccessObj=sd,
filterType=filterType)
sdp = SchemaDefDataPrep(schemaDefAccessObj=sd,
dtObj=dtf,
workPath=self.__cachePath,
verbose=self.__verbose)
containerList = self.__rpP.getContainerList(inputPathList)
for container in containerList:
cName = container.getName()
logger.debug("Processing container %s", cName)
dmh.apply(container)
#
for collectionName in collectionNameList:
tableIdExcludeList = sd.getCollectionExcluded(collectionName)
tableIdIncludeList = sd.getCollectionSelected(collectionName)
sliceFilter = sd.getCollectionSliceFilter(collectionName)
sdp.setSchemaIdExcludeList(tableIdExcludeList)
sdp.setSchemaIdIncludeList(tableIdIncludeList)
#
docList, _, _ = sdp.processDocuments(
containerList,
styleType=styleType,
sliceFilter=sliceFilter,
filterType=filterType,
dataSelectors=dataSelectors,
collectionName=collectionName)
docList = sdp.addDocumentPrivateAttributes(
docList, collectionName)
docList = sdp.addDocumentSubCategoryAggregates(
docList, collectionName)
# Special exclusions for the test harness. (removes timestamped data items to allow diffs.)
self.__filterDocuments(docList, excludeExtras)
mergeS = "-".join(
mergeContentTypes) if mergeContentTypes else ""
fName = "full-prep-%s-%s-%s-%s.json" % (
contentType, collectionName, mergeS, styleType)
if self.__exportFlag:
self.__logDocumentOrder(docList)
fPath = os.path.join(self.__outputPath, fName)
self.__mU.doExport(fPath, docList, fmt="json", indent=3)
logger.debug("Exported %r", fPath)
#
if self.__diffFlag:
fPath = os.path.join(self.__savedOutputPath, fName)
refDocList = self.__mU.doImport(fPath, fmt="json")
self.assertEqual(len(refDocList), len(docList))
logger.debug("For %s %s len refDocList %d", contentType,
collectionName, len(refDocList))
logger.debug("For %s %s len docList %d", contentType,
collectionName, len(docList))
jD = diff(refDocList,
docList,
syntax="explicit",
marshal=True)
if jD:
_, fn = os.path.split(fPath)
bn, _ = os.path.splitext(fn)
fPath = os.path.join(self.__outputPath,
bn + "-diff.json")
logger.debug("jsondiff for %s %s = \n%s", contentType,
collectionName,
pprint.pformat(jD, indent=3, width=100))
self.__mU.doExport(fPath, jD, fmt="json", indent=3)
self.assertEqual(len(jD), 0)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()