def testCompareCollectionSchema(self):
try:
difPathList = []
for databaseName in self.__databaseNameList:
dD = self.__schP.makeSchemaDef(databaseName,
dataTyping="ANY",
saveSchema=False)
sD = SchemaDefAccess(dD)
for cd in sD.getCollectionInfo():
collectionName = cd["NAME"]
for encodingType in self.__encodingTypes:
if encodingType.lower() != "json":
continue
for level in self.__validationLevels:
pth = self.__schP.jsonSchemaCompare(
databaseName, collectionName, encodingType,
level)
if pth:
difPathList.append(pth)
if difPathList:
logger.info("JSON schema difference path list %r",
[os.path.split(pth)[1] for pth in difPathList])
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testBuildCollectionSchema(self):
schemaDifPathList = []
for databaseName in self.__databaseNameList:
dD = self.__schP.makeSchemaDef(databaseName,
dataTyping="ANY",
saveSchema=False)
sD = SchemaDefAccess(dD)
for cd in sD.getCollectionInfo():
collectionName = cd["NAME"]
for encodingType in self.__encodingTypes:
if encodingType.lower() == "rcsb":
continue
for level in self.__validationLevels:
self.__schP.makeSchema(databaseName,
collectionName,
encodingType=encodingType,
level=level,
saveSchema=self.__saveSchema)
if self.__compareSchema and encodingType.lower(
) == "json":
pth = self.__schP.jsonSchemaCompare(
databaseName, collectionName, encodingType,
level)
if pth:
schemaDifPathList.append(pth)
if schemaDifPathList:
logger.info("Path dif list %r", schemaDifPathList)
def getSchemaInfo(self, databaseName, dataTyping="ANY"):
"""Convenience method to return essential schema details for the input repository content type.
Args:
databaseName (str): schema name (e.g. pdbx, bird, chem_comp, ...)
dataTyping (str, optional): Application name for the target schema (e.g. ANY, SQL, ...)
Returns:
tuple: SchemaDefAccess(object), target database name, target collection name list, primary index attribute list
"""
sd = None
dbName = None
collectionNameList = []
docIndexD = {}
try:
mU = MarshalUtil(workPath=self.__workPath)
schemaLocator = self.__getSchemaDefLocator(databaseName,
dataTyping=dataTyping)
if self.__rebuildFlag:
filePath = os.path.join(
self.__schemaCachePath,
self.__fileU.getFileName(schemaLocator))
self.makeSchemaDef(databaseName,
dataTyping=dataTyping,
saveSchema=True)
else:
filePath = self.__reload(schemaLocator,
self.__schemaCachePath,
useCache=self.__useCache)
if not filePath:
logger.error("Unable to recover schema %s (%s)", databaseName,
dataTyping)
logger.debug("ContentType %r dataTyping %r schemaLocator %r",
databaseName, dataTyping, schemaLocator)
schemaDef = mU.doImport(filePath, fmt="json")
if schemaDef:
logger.debug(
"Using cached schema definition for %s application %s",
databaseName, dataTyping)
sd = SchemaDefAccess(schemaDef)
if sd:
dbName = sd.getDatabaseName()
collectionInfoList = sd.getCollectionInfo()
logger.debug("Schema %s database name %s collections %r",
databaseName, dbName, collectionInfoList)
for cd in collectionInfoList:
collectionName = cd["NAME"]
collectionNameList.append(collectionName)
docIndexD[collectionName] = sd.getDocumentIndices(
collectionName)
except Exception as e:
logger.exception("Retreiving schema %s for %s failing with %s",
databaseName, dataTyping, str(e))
return sd, dbName, collectionNameList, docIndexD
def testLoadPdbxFiles(self):
try:
cD = self.__schP.makeSchemaDef("pdbx",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
inputPathList = self.__rpP.getLocatorObjList(contentType="pdbx")
logger.debug("Input path list %r", inputPathList)
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
sdl = SchemaDefLoader(
self.__cfgOb,
schemaDefObj=sd,
dbCon=client,
cachePath=self.__cachePath,
workPath=self.__workPath,
cleanUp=False,
warnings="error",
verbose=self.__verbose,
restoreUseStash=False,
restoreUseGit=True,
providerTypeExclude=self.__excludeType,
)
ok = sdl.load(inputPathList=inputPathList,
loadType="batch-insert",
deleteOpt="all")
self.assertTrue(ok)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testLoadBirdReference(self):
try:
cD = self.__schP.makeSchemaDef("bird",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
inputPathList = self.__rpP.getLocatorObjList(contentType="bird")
inputPathList.extend(
self.__rpP.getLocatorObjList(contentType="bird_family"))
#
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
sdl = SchemaDefLoader(
self.__cfgOb,
schemaDefObj=sd,
dbCon=client,
cachePath=self.__cachePath,
workPath=self.__workPath,
cleanUp=False,
warnings="error",
verbose=self.__verbose,
restoreUseStash=False,
restoreUseGit=True,
providerTypeExclude=self.__excludeType,
)
ok = sdl.load(inputPathList=inputPathList,
loadType="batch-file")
self.assertTrue(ok)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testLoadChemCompReference(self):
try:
cD = self.__schP.makeSchemaDef("chem_comp",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
inputPathList = self.__rpP.getLocatorObjList(
contentType="chem_comp")
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
sdl = SchemaDefLoader(self.__cfgOb,
schemaDefObj=sd,
dbCon=client,
cachePath=self.__cachePath,
workPath=self.__workPath,
cleanUp=False,
warnings="error",
verbose=self.__verbose)
ok = sdl.load(inputPathList=inputPathList,
loadType="batch-file")
self.assertTrue(ok)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testSchemaCreate(self):
"""Create table schema for BIRD, chemical component, and PDBx data."""
cD = self.__schP.makeSchemaDef("bird",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
#
cD = self.__schP.makeSchemaDef("chem_comp",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
#
# cD = self.__schP.makeSchemaDef("pdbx", dataTyping="SQL", saveSchema=True)
# sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
def testBuildColSchemaWithRefs(self):
for databaseName in ["ihm_dev_full"]:
dD = self.__schP.makeSchemaDef(databaseName,
dataTyping="ANY",
saveSchema=False)
sD = SchemaDefAccess(dD)
for cd in sD.getCollectionInfo():
collectionName = cd["NAME"]
for schemaType in self.__encodingTypes:
if schemaType.lower() == "rcsb":
continue
for level in self.__validationLevels:
self.__schP.makeSchema(
databaseName,
collectionName,
encodingType=schemaType,
level=level,
saveSchema=True,
extraOpts="addParentRefs|addPrimaryKey")
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 testSQLMethods(self):
schemaNames = ["pdbx_core"]
dataTyping = "SQL"
for schemaName in schemaNames:
dD = self.__sdu.makeSchemaDef(schemaName,
dataTyping=dataTyping,
saveSchema=False)
sD = SchemaDefAccess(dD)
self.__testSchemaCreate(sD)
self.__testImportExport(sD)
self.__testSelectionAndConditions(sD)
def testCompareSchemaCategories(self):
"""Compare common categories across schema definitions."""
try:
sdCc = SchemaDefAccess(
self.__schP.makeSchemaDef("chem_comp_core",
dataTyping="ANY",
saveSchema=False))
sdBcc = SchemaDefAccess(
self.__schP.makeSchemaDef("bird_chem_comp_core",
dataTyping="ANY",
saveSchema=False))
#
logger.info("")
for schemaId in ["CHEM_COMP", "PDBX_CHEM_COMP_AUDIT"]:
atCcL = sdCc.getAttributeIdList(schemaId)
atBCcL = sdBcc.getAttributeIdList(schemaId)
logger.debug("%s attributes (%d) %r", schemaId, len(atCcL),
atCcL)
logger.debug("%s attributes (%d) %r", schemaId, len(atBCcL),
atBCcL)
sDif = set(atCcL) - set(atBCcL)
if sDif:
logger.info("For %s attribute differences %r", schemaId,
sDif)
self.assertEqual(len(sDif), 0)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testReLoadBirdReference(self):
try:
cD = self.__schP.makeSchemaDef("bird",
dataTyping="SQL",
saveSchema=True)
sd = SchemaDefAccess(cD)
self.__schemaCreate(sd)
inputPathList = self.__rpP.getLocatorObjList(contentType="bird")
inputPathList.extend(
self.__rpP.getLocatorObjList(contentType="bird_family"))
#
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
sdl = SchemaDefLoader(self.__cfgOb,
schemaDefObj=sd,
dbCon=client,
cachePath=self.__cachePath,
workPath=self.__workPath,
cleanUp=False,
warnings="error",
verbose=self.__verbose)
sdl.load(inputPathList=inputPathList, loadType="batch-file")
#
logger.debug(
"INFO BATCH FILE RELOAD TEST --------------------------------------------\n"
)
ok = sdl.load(inputPathList=inputPathList,
loadType="batch-file",
deleteOpt="all")
self.assertTrue(ok)
#
logger.debug(
"\n\n\n+INFO BATCH INSERT RELOAD TEST --------------------------------------------\n"
)
ok = sdl.load(inputPathList=inputPathList,
loadType="batch-file",
deleteOpt="selected")
self.assertTrue(ok)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __testAccessors(self, schemaDef):
"""Verify data and accessor mapping -"""
sd = SchemaDefAccess(schemaDef)
logger.debug("Schema name %s", sd.getName())
logger.debug("Schema name %s", sd.getAppName())
logger.debug("Database name %s", sd.getDatabaseName())
logger.debug("Versioned database name %s",
sd.getVersionedDatabaseName())
logger.debug("Collection info %r", sd.getCollectionInfo())
for dS in sd.getDataSelectorNames():
logger.debug("Selector %s %r", dS, sd.getDataSelectors(dS))
collectionInfoL = sd.getCollectionInfo()
for dD in collectionInfoL:
collectionName = dD["NAME"]
logger.debug("Collection excluded %r",
sd.getCollectionExcluded(collectionName))
logger.debug("Collection included %r",
sd.getCollectionSelected(collectionName))
logger.debug("Collection document key attribute names %r",
sd.getDocumentKeyAttributeNames(collectionName))
schemaIdList = sd.getSchemaIdList()
for schemaId in schemaIdList:
#
aIdL = sd.getAttributeIdList(schemaId)
tObj = sd.getSchemaObject(schemaId)
attributeIdList = tObj.getAttributeIdList()
self.assertEqual(len(aIdL), len(attributeIdList))
attributeNameList = tObj.getAttributeNameList()
logger.debug("Ordered attribute Id list %s",
str(attributeIdList))
logger.debug("Ordered attribute name list %s",
str(attributeNameList))
#
mAL = tObj.getMapAttributeNameList()
logger.debug("Ordered mapped attribute name list %s", str(mAL))
mAL = tObj.getMapAttributeIdList()
logger.debug("Ordered mapped attribute id list %s", str(mAL))
cL = tObj.getMapInstanceCategoryList()
logger.debug("Mapped category list %s", str(cL))
for cV in cL:
aL = tObj.getMapInstanceAttributeList(cV)
logger.debug("Mapped attribute list in %s : %s", cV, str(aL))
return True
def main():
parser = argparse.ArgumentParser()
#
defaultConfigName = "site_info_configuration"
#
parser.add_argument(
"--update_chem_comp_ref",
default=False,
action="store_true",
help="Update schema for Chemical Component reference definitions")
parser.add_argument(
"--update_chem_comp_core_ref",
default=False,
action="store_true",
help="Update core schema for Chemical Component reference definitions")
parser.add_argument(
"--update_bird_chem_comp_ref",
default=False,
action="store_true",
help="Update schema for Bird Chemical Component reference definitions")
parser.add_argument(
"--update_bird_chem_comp_core_ref",
default=False,
action="store_true",
help=
"Update core schema for Bird Chemical Component reference definitions")
parser.add_argument("--update_bird_ref",
default=False,
action="store_true",
help="Update schema for Bird reference definitions")
parser.add_argument(
"--update_bird_family_ref",
default=False,
action="store_true",
help="Update schema for Bird Family reference definitions")
parser.add_argument("--update_pdbx",
default=False,
action="store_true",
help="Update schema for PDBx entry data")
parser.add_argument("--update_pdbx_core",
default=False,
action="store_true",
help="Update schema for PDBx core entry/entity data")
parser.add_argument(
"--update_pdbx_comp_model_core",
default=False,
action="store_true",
help="Update schema for PDBx computational model core entry/entity data"
)
#
parser.add_argument("--update_repository_holdings",
default=False,
action="store_true",
help="Update schema for repository holdings")
parser.add_argument("--update_entity_sequence_clusters",
default=False,
action="store_true",
help="Update schema for entity sequence clusters")
parser.add_argument("--update_data_exchange",
default=False,
action="store_true",
help="Update schema for data exchange status")
parser.add_argument("--update_ihm_dev",
default=False,
action="store_true",
help="Update schema for I/HM dev entry data")
parser.add_argument("--update_drugbank_core",
default=False,
action="store_true",
help="Update DrugBank schema")
#
parser.add_argument(
"--update_config_all",
default=False,
action="store_true",
help="Update using configuration settings (e.g. DATABASE_NAMES_ALL)")
parser.add_argument(
"--update_config_deployed",
default=False,
action="store_true",
help=
"Update using configuration settings (e.g. DATABASE_NAMES_DEPLOYED)")
parser.add_argument(
"--update_config_test",
default=False,
action="store_true",
help="Update using configuration settings (e.g. DATABASE_NAMES_TEST)")
#
parser.add_argument("--config_path",
default=None,
help="Path to configuration options file")
parser.add_argument("--config_name",
default=defaultConfigName,
help="Configuration section name")
#
parser.add_argument("--cache_path",
default=None,
help="Schema cache directory path")
parser.add_argument(
"--encoding_types",
default=None,
help="Schema encoding (rcsb|json|bson) (comma separated)")
parser.add_argument(
"--validation_levels",
default=None,
help="Schema validation level (full|min) (comma separated)")
parser.add_argument("--compare_only",
default=False,
action="store_true",
help="Perform comparison with cached schema")
#
parser.add_argument("--debug",
default=False,
action="store_true",
help="Turn on verbose logging")
parser.add_argument(
"--mock",
default=False,
action="store_true",
help="Use MOCK repository configuration for dependencies and testing")
# parser.add_argument("--working_path", default=None, help="Working/alternative path for temporary and schema files")
args = parser.parse_args()
#
debugFlag = args.debug
if debugFlag:
logger.setLevel(logging.DEBUG)
# ----------------------- - ----------------------- - ----------------------- - ----------------------- - ----------------------- -
# Configuration Details
configPath = args.config_path
configName = args.config_name
cachePath = args.cache_path
compareOnly = args.compare_only
#
encodingTypes = args.encoding_types.split(
",") if args.encoding_types else []
validationLevels = args.validation_levels.split(
",") if args.validation_levels else []
dataTypingList = ["ANY", "SQL"]
if not configPath:
configPath = os.getenv("DBLOAD_CONFIG_PATH", None)
try:
if os.access(configPath, os.R_OK):
os.environ["DBLOAD_CONFIG_PATH"] = configPath
logger.info("Using configuation path %s (%s)", configPath,
configName)
else:
logger.error("Missing or access issue with config file %r",
configPath)
exit(1)
mockTopPath = os.path.join(TOPDIR, "rcsb",
"mock-data") if args.mock else None
cfgOb = ConfigUtil(configPath=configPath,
defaultSectionName=defaultConfigName,
mockTopPath=mockTopPath)
if configName != defaultConfigName:
cfgOb.replaceSectionName(defaultConfigName, configName)
except Exception as e:
logger.error("Missing or access issue with config file %r with %s",
configPath, str(e))
exit(1)
#
databaseNameList = []
if args.update_chem_comp_ref:
databaseNameList.append("chem_comp")
if args.update_bird_chem_comp_ref:
databaseNameList.append("bird_chem_comp")
if args.update_chem_comp_core_ref:
databaseNameList.append("chem_comp_core")
if args.update_bird_chem_comp_core_ref:
databaseNameList.append("bird_chem_comp_core")
if args.update_bird_ref:
databaseNameList.append("bird")
if args.update_bird_family_ref:
databaseNameList.append("bird_family")
if args.update_pdbx:
databaseNameList.append("pdbx")
if args.update_pdbx_core:
databaseNameList.append("pdbx_core")
if args.update_pdbx_comp_model_core:
databaseNameList.append("pdbx_comp_model_core")
if args.update_repository_holdings:
databaseNameList.append("repository_holdings")
if args.update_entity_sequence_clusters:
databaseNameList.append("sequence_clusters")
if args.update_data_exchange:
databaseNameList.append("data_exchange")
if args.update_ihm_dev:
databaseNameList.append("ihm_dev")
if args.update_drugbank_core:
databaseNameList.append("drugbank_core")
if args.update_config_deployed:
databaseNameList = cfgOb.getList(
"DATABASE_NAMES_DEPLOYED",
sectionName="database_catalog_configuration")
dataTypingList = cfgOb.getList(
"DATATYPING_DEPLOYED",
sectionName="database_catalog_configuration")
validationLevels = cfgOb.getList(
"VALIDATION_LEVELS_DEPLOYED",
sectionName="database_catalog_configuration")
encodingTypes = cfgOb.getList(
"ENCODING_TYPES_DEPLOYED",
sectionName="database_catalog_configuration")
if args.update_config_all:
databaseNameList = cfgOb.getList(
"DATABASE_NAMES_ALL", sectionName="database_catalog_configuration")
dataTypingList = cfgOb.getList(
"DATATYPING_ALL", sectionName="database_catalog_configuration")
validationLevels = cfgOb.getList(
"VALIDATION_LEVELS_ALL",
sectionName="database_catalog_configuration")
encodingTypes = cfgOb.getList(
"ENCODING_TYPES_ALL", sectionName="database_catalog_configuration")
if args.update_config_test:
databaseNameList = cfgOb.getList(
"DATABASE_NAMES_TEST",
sectionName="database_catalog_configuration")
dataTypingList = cfgOb.getList(
"DATATYPING_TEST", sectionName="database_catalog_configuration")
validationLevels = cfgOb.getList(
"VALIDATION_LEVELS_TEST",
sectionName="database_catalog_configuration")
encodingTypes = cfgOb.getList(
"ENCODING_TYPES_TEST",
sectionName="database_catalog_configuration")
#
scnD = cfgOb.get("document_collection_names",
sectionName="document_helper_configuration")
#
databaseNameList = list(set(databaseNameList))
logger.debug("Collections %s", list(scnD.items()))
logger.debug("databaseNameList %s", databaseNameList)
if compareOnly:
schP = SchemaProvider(cfgOb, cachePath, useCache=True)
difPathList = []
for databaseName in databaseNameList:
for dataTyping in dataTypingList:
logger.debug("Building schema %s with types %s", databaseName,
dataTyping)
pth = schP.schemaDefCompare(databaseName, dataTyping)
if pth:
difPathList.append(pth)
if difPathList:
logger.info("Schema definition difference path list %r",
difPathList)
difPathList = []
for databaseName in databaseNameList:
dD = schP.makeSchemaDef(databaseName,
dataTyping="ANY",
saveSchema=False)
sD = SchemaDefAccess(dD)
for cd in sD.getCollectionInfo():
collectionName = cd["NAME"]
for encodingType in encodingTypes:
if encodingType.lower() != "json":
continue
for level in validationLevels:
pth = schP.jsonSchemaCompare(databaseName,
collectionName,
encodingType, level)
if pth:
difPathList.append(pth)
if difPathList:
logger.info("JSON schema difference path list %r", difPathList)
else:
schP = SchemaProvider(cfgOb, cachePath, useCache=False)
for databaseName in databaseNameList:
for encodingType in encodingTypes:
if encodingType == "rcsb":
for dataTyping in dataTypingList:
logger.info(
"Creating schema definition for content type %s data typing %s",
databaseName, dataTyping)
schP.makeSchemaDef(databaseName,
dataTyping=dataTyping,
saveSchema=True)
else:
if databaseName in scnD:
for dD in scnD[databaseName]:
collectionName = dD["NAME"]
for validationLevel in validationLevels:
logger.info(
"Creating %r schema for content type %s collection %s",
encodingType, databaseName, collectionName)
schP.makeSchema(databaseName,
collectionName,
encodingType=encodingType,
level=validationLevel,
saveSchema=True)
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()
