def setUp(self):
     self.__isMac = platform.system() == "Darwin"
     self.__excludeType = None if self.__isMac else "optional"
     self.__verbose = True
     #
     fileLimit = 100
     numProc = 2
     self.__cachePath = os.path.join(TOPDIR, "CACHE")
     self.__workPath = os.path.join(HERE, "test-output")
     mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
     configPath = os.path.join(TOPDIR, "rcsb", "db", "config",
                               "exdb-config-example.yml")
     #
     configName = "site_info_configuration"
     self.__cfgOb = ConfigUtil(configPath=configPath,
                               defaultSectionName=configName,
                               mockTopPath=mockTopPath)
     self.__resourceName = "MYSQL_DB"
     #
     self.__schP = SchemaProvider(self.__cfgOb,
                                  self.__cachePath,
                                  useCache=True)
     self.__rpP = RepositoryProvider(cfgOb=self.__cfgOb,
                                     numProc=numProc,
                                     fileLimit=fileLimit,
                                     cachePath=self.__cachePath)
     #
     #
     self.__startTime = time.time()
     logger.debug("Starting %s at %s", self.id(),
                  time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
Exemple #2
0
 def setUp(self):
     self.__verbose = True
     self.__numProc = 2
     self.__fileLimit = 100
     self.__chunkSize = 0
     self.__workPath = os.path.join(HERE, "test-output")
     self.__mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
     configPath = os.path.join(TOPDIR, "rcsb", "db", "config",
                               "exdb-config-example.yml")
     configName = "site_info_configuration"
     self.__cfgOb = ConfigUtil(configPath=configPath,
                               defaultSectionName=configName)
     self.__resourceName = "CRATE_DB"
     self.__schP = SchemaProvider(self.__cfgOb,
                                  self.__workPath,
                                  useCache=True)
     self.__rpP = RepositoryProvider(cfgOb=self.__cfgOb,
                                     numProc=self.__numProc,
                                     fileLimit=self.__fileLimit,
                                     cachePath=self.__workPath)
     #
     #
     self.__tableIdSkipD = {
         "ATOM_SITE": True,
         "ATOM_SITE_ANISOTROP": True,
         "__LOAD_STATUS__": True
     }
     self.__ioObj = IoAdapter(verbose=self.__verbose)
     #
     self.__startTime = time.time()
     logger.debug("Starting %s at %s", self.id(),
                  time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
    def setUp(self):
        self.__verbose = True
        #
        self.__mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
        self.__pathConfig = os.path.join(TOPDIR, "rcsb", "db", "config",
                                         "exdb-config-example.yml")
        self.__cachePath = os.path.join(TOPDIR, "CACHE")
        self.__updateId = "2018_25"
        self.__export = False
        #
        configName = "site_info_configuration"
        self.__cfgOb = ConfigUtil(configPath=self.__pathConfig,
                                  defaultSectionName=configName,
                                  mockTopPath=self.__mockTopPath)
        self.__schP = SchemaProvider(self.__cfgOb,
                                     self.__cachePath,
                                     useCache=True)
        self.__sandboxPath = self.__cfgOb.getPath("RCSB_EXCHANGE_SANDBOX_PATH",
                                                  sectionName=configName)
        #
        self.__mU = MarshalUtil(workPath=self.__cachePath)

        self.__startTime = time.time()
        logger.debug("Starting %s at %s", self.id(),
                     time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
 def __init__(self,
              cfgOb,
              cachePath,
              useCache=True,
              numProc=2,
              chunkSize=10,
              readBackCheck=False,
              documentLimit=None,
              doValidate=False,
              verbose=False):
     self.__cfgOb = cfgOb
     self.__cachePath = cachePath
     self.__useCache = useCache
     self.__readBackCheck = readBackCheck
     self.__numProc = numProc
     self.__chunkSize = chunkSize
     self.__documentLimit = documentLimit
     #
     self.__resourceName = "MONGO_DB"
     self.__verbose = verbose
     self.__statusList = []
     self.__schP = SchemaProvider(self.__cfgOb,
                                  self.__cachePath,
                                  useCache=self.__useCache)
     self.__docHelper = DocumentDefinitionHelper(cfgOb=self.__cfgOb)
     self.__valInst = None
     self.__doValidate = doValidate
Exemple #5
0
 def __init__(
     self,
     cfgOb,
     cachePath,
     resourceName="MONGO_DB",
     numProc=4,
     chunkSize=15,
     documentLimit=None,
     verbose=False,
     readBackCheck=False,
     maxStepLength=2000,
     schemaRebuildFlag=False,
 ):
     self.__verbose = verbose
     #
     # Limit the load length of each file type for testing  -  Set to None to remove -
     self.__documentLimit = documentLimit
     self.__maxStepLength = maxStepLength
     #
     # Controls for multiprocessing execution -
     self.__numProc = numProc
     self.__chunkSize = chunkSize
     #
     self.__cfgOb = cfgOb
     self.__resourceName = resourceName
     #
     self.__cachePath = cachePath if cachePath else "."
     self.__schP = SchemaProvider(cfgOb,
                                  cachePath,
                                  useCache=True,
                                  rebuildFlag=schemaRebuildFlag)
     #
     self.__readBackCheck = readBackCheck
     self.__mpFormat = "[%(levelname)s] %(asctime)s %(processName)s-%(module)s.%(funcName)s: %(message)s"
    def setUp(self):
        self.__numProc = 2
        # self.__fileLimit = 200
        self.__fileLimit = None
        self.__mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
        self.__cachePath = os.path.join(TOPDIR, "CACHE")
        self.__configPath = os.path.join(TOPDIR, "rcsb", "db", "config", "exdb-config-example-ihm.yml")
        configName = "site_info_configuration"
        self.__configName = configName
        self.__cfgOb = ConfigUtil(configPath=self.__configPath, defaultSectionName=configName, mockTopPath=self.__mockTopPath)
        self.__mU = MarshalUtil(workPath=self.__cachePath)

        #self.__schP = SchemaProvider(self.__cfgOb, self.__cachePath, useCache=False, rebuildFlag=True)
        self.__schP = SchemaProvider(self.__cfgOb, self.__cachePath, useCache=True)
        self.__rpP = RepositoryProvider(cfgOb=self.__cfgOb, numProc=self.__numProc, fileLimit=self.__fileLimit, cachePath=self.__cachePath)
        #
        self.__birdRepoPath = self.__cfgOb.getPath("BIRD_REPO_PATH", sectionName=configName)
        #
        self.__fTypeRow = "drop-empty-attributes|drop-empty-tables|skip-max-width|convert-iterables|normalize-enums|translateXMLCharRefs"
        self.__fTypeCol = "drop-empty-tables|skip-max-width|convert-iterables|normalize-enums|translateXMLCharRefs"
        self.__verbose = True
        #
        self.__modulePathMap = self.__cfgOb.get("DICT_METHOD_HELPER_MODULE_PATH_MAP", sectionName=configName)
        self.__testDirPath = os.path.join(HERE, "test-output", "pdbx-files")
        self.__testIhmDirPath = os.path.join(HERE, "test-output", "ihm-files")
        self.__export = True
        #
        #self.__extraOpts = None
        # The following for extended parent/child info -
        self.__extraOpts = 'addParentRefs|addPrimaryKey'
        #
        self.__alldatabaseNameD = {
            "ihm_dev": ["ihm_dev"],
            "pdbx": ["pdbx", "pdbx_ext"],
            "pdbx_core": ["pdbx_core_entity", "pdbx_core_entry", "pdbx_core_assembly", "pdbx_core_entity_instance", "pdbx_core_entity_instance_validation"],
            "bird": ["bird"],
            "bird_family": ["family"],
            "chem_comp": ["chem_comp"],
            "bird_chem_comp": ["bird_chem_comp"],
            "bird_chem_comp_core": ["bird_chem_comp_core"],
        }

        self.__databaseNameD = {
            "pdbx_core": ["pdbx_core_entity", "pdbx_core_entry", "pdbx_core_assembly", "pdbx_core_entity_instance", "pdbx_core_entity_instance_validation"],
            "bird_chem_comp_core": ["bird_chem_comp_core"],
        }
        self.__mergeContentTypeD = {"pdbx_core": ["vrpt"]}
        # self.__databaseNameD = {"chem_comp_core": ["chem_comp_core"], "bird_chem_comp_core": ["bird_chem_comp_core"]}
        # self.__databaseNameD = {"ihm_dev_full": ["ihm_dev_full"]}
        # self.__databaseNameD = {"pdbx_core": ["pdbx_core_entity_instance_validation"]}
        # self.__databaseNameD = {"pdbx_core": ["pdbx_core_entity_monomer"]}
        self.__startTime = time.time()
        logger.debug("Starting %s at %s", self.id(), time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
Exemple #7
0
 def __init__(self,
              cfgOb,
              objectAdapter=None,
              cachePath=".",
              useCache=True,
              **kwargs):
     self.__cfgOb = cfgOb
     self.__oAdapt = objectAdapter
     self.__resourceName = "MONGO_DB"
     _ = kwargs
     self.__statusList = []
     self.__schP = SchemaProvider(self.__cfgOb,
                                  cachePath,
                                  useCache=useCache)
     self.__valInst = None
Exemple #8
0
    def setUp(self):
        self.__verbose = True
        mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
        pathConfig = os.path.join(TOPDIR, "rcsb", "db", "config",
                                  "exdb-config-example.yml")
        configName = "site_info_configuration"
        self.__cachePath = os.path.join(TOPDIR, "CACHE")
        self.__cfgOb = ConfigUtil(configPath=pathConfig,
                                  defaultSectionName=configName,
                                  mockTopPath=mockTopPath)
        self.__schP = SchemaProvider(self.__cfgOb,
                                     self.__cachePath,
                                     useCache=False)
        #
        self.__validationLevels = self.__cfgOb.getList(
            "VALIDATION_LEVELS_TEST",
            sectionName="database_catalog_configuration")
        self.__encodingTypes = self.__cfgOb.getList(
            "ENCODING_TYPES_TEST",
            sectionName="database_catalog_configuration")
        #
        buildAll = True
        if buildAll:
            self.__databaseNameList = self.__cfgOb.getList(
                "DATABASE_NAMES_DEPLOYED",
                sectionName="database_catalog_configuration")
            self.__dataTypingList = self.__cfgOb.getList(
                "DATATYPING_DEPLOYED",
                sectionName="database_catalog_configuration")
            #
        else:
            self.__databaseNameList = self.__cfgOb.getList(
                "DATABASE_NAMES_TEST",
                sectionName="database_catalog_configuration")
            # self.__databaseNameList = ["repository_holdings"]
            self.__dataTypingList = self.__cfgOb.getList(
                "DATATYPING_TEST",
                sectionName="database_catalog_configuration")

        # self.__databaseNameList = ["sequence_clusters"]
        self.__saveSchema = True
        self.__compareDefSchema = False
        self.__compareSchema = False
        #
        self.__startTime = time.time()
        logger.debug("Starting %s at %s", self.id(),
                     time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
Exemple #9
0
 def setUp(self):
     self.__verbose = True
     mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
     self.__cachePath = os.path.join(TOPDIR, "CACHE")
     pathConfig = os.path.join(TOPDIR, "rcsb", "db", "config",
                               "exdb-config-example.yml")
     configName = "site_info_configuration"
     self.__cfgOb = ConfigUtil(configPath=pathConfig,
                               defaultSectionName=configName,
                               mockTopPath=mockTopPath)
     self.__schP = SchemaProvider(self.__cfgOb,
                                  self.__cachePath,
                                  useCache=True,
                                  clearPath=False)
     #
     self.__startTime = time.time()
     logger.debug("Starting %s at %s", self.id(),
                  time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
Exemple #10
0
 def setUp(self):
     self.__verbose = True
     #
     self.__mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
     self.__pathConfig = os.path.join(TOPDIR, "rcsb", "db", "config", "exdb-config-example.yml")
     self.__cachePath = os.path.join(TOPDIR, "CACHE")
     self.__updateId = "2018_25"
     #
     configName = "site_info_configuration"
     self.__cfgOb = ConfigUtil(configPath=self.__pathConfig, defaultSectionName=configName, mockTopPath=self.__mockTopPath)
     self.__schP = SchemaProvider(self.__cfgOb, self.__cachePath, useCache=True)
     #
     self.__sandboxPath = self.__cfgOb.getPath("RCSB_EXCHANGE_SANDBOX_PATH", sectionName=configName)
     #
     self.__dataSetId = "2018_23"
     self.__pathClusterData = self.__cfgOb.getPath("RCSB_SEQUENCE_CLUSTER_DATA_PATH", sectionName=configName)
     # self.__levels = ['100', '95', '90', '70', '50', '30']
     self.__levels = ["100"]
     #
     self.__startTime = time.time()
     logger.debug("Starting %s at %s", self.id(), time.strftime("%Y %m %d %H:%M:%S", time.localtime()))
Exemple #11
0
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 setUp(self):
        self.__isMac = platform.system() == "Darwin"
        self.__excludeType = None if self.__isMac else "optional"
        self.__numProc = 2
        mockTopPath = os.path.join(TOPDIR, "rcsb", "mock-data")
        self.__cachePath = os.path.join(TOPDIR, "CACHE")
        self.__outputPath = os.path.join(HERE, "test-output")
        self.__savedOutputPath = os.path.join(HERE, "test-saved-output")

        configPath = os.path.join(TOPDIR, "rcsb", "db", "config",
                                  "exdb-config-example.yml")
        configName = "site_info_configuration"
        self.__configName = configName
        self.__cfgOb = ConfigUtil(configPath=configPath,
                                  defaultSectionName=configName,
                                  mockTopPath=mockTopPath)
        self.__mU = MarshalUtil(workPath=self.__cachePath)
        self.__discoveryMode = self.__cfgOb.get("DISCOVERY_MODE",
                                                sectionName=configName,
                                                default="local")
        self.__fileLimit = 100 if self.__discoveryMode == "local" else 10
        self.__schP = SchemaProvider(self.__cfgOb,
                                     self.__cachePath,
                                     useCache=True)
        self.__rpP = RepositoryProvider(cfgOb=self.__cfgOb,
                                        numProc=self.__numProc,
                                        fileLimit=self.__fileLimit,
                                        cachePath=self.__cachePath)
        #
        #
        self.__fTypeRow = "drop-empty-attributes|drop-empty-tables|skip-max-width|convert-iterables|normalize-enums|translateXMLCharRefs"
        self.__fTypeCol = "drop-empty-tables|skip-max-width|convert-iterables|normalize-enums|translateXMLCharRefs"
        self.__chemCompMockLen = 24
        self.__pdbxMockLen = 30
        # removes timestamped data items to allow diffs.)
        excludeExtras = ["rcsb_load_status"]
        # excludeExtras = []
        #
        self.__verbose = True
        self.__modulePathMap = self.__cfgOb.get(
            "DICT_METHOD_HELPER_MODULE_PATH_MAP", sectionName=configName)
        #
        self.__exportFlag = True
        self.__diffFlag = False
        #
        self.__simpleTestCaseList = [
            {
                "contentType": "chem_comp",
                "mockLength": self.__chemCompMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name",
                "mergeContentTypes": None,
                "rejectLength": 2,
            },
            {
                "contentType": "chem_comp",
                "mockLength": self.__chemCompMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_no_name",
                "mergeContentTypes": None,
                "rejectLength": 2,
            },
            {
                "contentType": "chem_comp",
                "mockLength": self.__chemCompMockLen,
                "filterType": self.__fTypeCol,
                "styleType": "columnwise_by_name",
                "mergeContentTypes": None,
                "rejectLength": 2,
            },
            {
                "contentType": "chem_comp",
                "mockLength": self.__chemCompMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name",
                "mergeContentTypes": None,
                "rejectLength": 2,
            },
            {
                "contentType": "pdbx_core",
                "mockLength": self.__pdbxMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name",
                "mergeContentTypes": None,
                "rejectLength": 0,
            },
        ]
        #
        self.__fullTestCaseList = [
            {
                "contentType": "pdbx_core",
                "mockLength": self.__pdbxMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name_with_cardinality",
                "mergeContentTypes": ["vrpt"],
                "rejectLength": 0,
                "excludeExtras": excludeExtras,
            },
            {
                "contentType": "bird_chem_comp_core",
                "mockLength": self.__chemCompMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name_with_cardinality",
                "mergeContentTypes": None,
                "rejectLength": 2,
                "excludeExtras": excludeExtras,
            },
        ]
        #
        self.__fullTestCaseListA = [
            {
                "contentType": "pdbx_core",
                "mockLength": self.__pdbxMockLen,
                "filterType": self.__fTypeRow,
                "styleType": "rowwise_by_name_with_cardinality",
                "mergeContentTypes": ["vrpt"],
                "rejectLength": 0,
                "excludeExtras": excludeExtras,
            },
        ]
        #
        self.__startTime = time.time()
        logger.debug("Starting %s at %s", self.id(),
                     time.strftime("%Y %m %d %H:%M:%S", time.localtime()))