def Start(self, logger, moduleName, filelocs):
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory +
"/QC/") #delete and recreate the folder
hqc = HindsightQC(self.logger, self.fileUtilities,
self.bcpUtilities, self.localTempDirectory)
hqc.Get_sql_server_rowcounts("pre") #Get pre-ETL rowcounts
#Execute the pre-etl queries
for sqlFile in self.job["bcpParameters"].get("preETLQueries"):
RedshiftUtilities.PSqlExecute(
self.fileUtilities.GetApplicationDirectory("Hindsight") +
sqlFile, logger)
for subJob in self.job["bcpParameters"]["subJobs"]:
if subJob.get("destinationSchema") is None:
subJob["destinationSchema"] = self.job["bcpParameters"][
"destinationSchema"]
self.ProcessSubJob(subJob)
#Get SQL Server rowcounts
hqc.Get_sql_server_rowcounts("post")
#Execute the post-etl queries to prepare the data post-ETL prior to loading into the production tables
for sqlFile in self.job["bcpParameters"].get("postETLQueries"):
RedshiftUtilities.PSqlExecute(
self.fileUtilities.GetApplicationDirectory("Hindsight") +
sqlFile, logger)
#Get Redshift rowcounts
hqc.Get_redshift_rowcounts("post")
#Execute the post-etl qc queries
status = hqc.ValidateETL()
#Check whether the ETL passed the QC
#Check 1: inter-version counts. Are the difference beyond a particular threshold
#Check 2: pre-sql v/s post-redshift. Are the differences beyond a particular threshold
#If the ETL doesn't pass the QC, do not update/insert the prod tables
#If the ETL passed the QC, insert into production tables (data, attributes, history)
if status == True:
self.logger.info("ETL good to go")
for sqlFile in self.job["bcpParameters"].get(
"FinalLoadQueries"):
#===========================================================
# add a process to backup data/attributes history tables
# Download to S3
#===========================================================
RedshiftUtilities.PSqlExecute(
self.fileUtilities.GetApplicationDirectory("Hindsight")
+ sqlFile, logger)
else:
self.logger.warning("Bad ETL. No go!")
print hqc.TimeElaspsed()
except:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
###
# set up to run create folder
###
# self.fileUtilities.moduleName = self.moduleName
# self.fileUtilities.localBaseDirectory = self.localTempDirectory
# self.fileUtilities.CreateFolders(self.job["folders"])
###
self.ProcessCategories()
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
ApplicationBase.Start(self, logger, moduleName, filelocs)
# At some point this will be part of Start
ApplicationBase.ProcessInput(self, logger, moduleName, filelocs)
def Start(self, logger, moduleName, filelocs):
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
self.rawFolder = self.localTempDirectory + "/" + "Raw"
self.csvFolder = self.localTempDirectory + "/" + "CSV"
self.CheckWorkingFolders()
self.BulkDownload()
self.ProcessFiles()
self.BulkUploadToS3()
self.LoadAllFromS3()
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
main routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.info(self.moduleName + " - Processing: ")
outputCSVfileName = self.localTempDirectory + '/PheonixDocuments.csv'
self.logger.info(self.moduleName + " - Pull documents from Phoenix: ")
jsonDocuments = self.PullDataFromPhoenix()
self.logger.info(self.moduleName + " - save contents to CSV file from Phoenix: ")
self.ExportToCSV(outputCSVfileName, jsonDocuments)
self.logger.info(self.moduleName + " - push documents csv file to S3: ")
bucketName, s3TempKey = S3Utilities.UploadFileToS3Temp(self.awsParams.s3, outputCSVfileName)
self.logger.info(self.moduleName + " - Create document table: ")
psConnect = self.GetPSConnection()
self.CreatePostgresTables(psConnect)
self.logger.info(self.moduleName + " - pull document s3 to database server temp: ")
postgresTempFile = self.DownloadFromS3ToPSTempDir(psConnect, bucketName, s3TempKey)
self.logger.info(self.moduleName + " - load documents csv file: ")
self.LoadDataFromPostgresTempDir(psConnect, postgresTempFile)
self.logger.info(self.moduleName + " - clean up temp file: ")
S3Utilities.DeleteFile(self.awsParams.s3, bucketName, s3TempKey)
except:
logger.exception(moduleName + " - Exception in start!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
for table in self.job["tables"]:
self.ProcessTable(table)
self.LoadDataFromAthenaIntoRedShiftLocalScripts(table)
#self.LoadDataFromAthenaIntoRedShiftS3Scripts(table) # Test: Load all data from Athena
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
###
# set up to run create folder
###
self.fileUtilities.moduleName = self.moduleName
self.fileUtilities.localBaseDirectory = self.localTempDirectory
self.fileUtilities.CreateFolders(self.job["folders"])
###
self.fromDate = self.GetFromDate()
for databaseSettings in self.job["Databases"]:
if databaseSettings["execute"] == 'Y':
self.ProcessDatabase(databaseSettings)
else:
self.logger.debug(self.moduleName + " -- skip database " +
databaseSettings["common"]["name"])
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.csvFile = self.localTempDirectory + "/" + self.job[
"fileNameOut"]
self.csvFileHistory = self.localTempDirectory + "/" + self.job[
"fileNameOutHistory"]
self.GetAndTransform()
self.UploadToS3()
self.LoadAllFromS3(
self.job["s3ToDirectory"] + '/' + self.job["fileNameOut"] +
'.gz', self.job["tableName"])
self.LoadAllFromS3(
self.job["s3ToDirectory"] + '/' +
self.job["fileNameOutHistory"] + '.gz',
self.job["tableName"] + '_history')
self.LoadAllFromS3(
self.job["xReference"]["s3DataDirectory"],
self.job["tableName"] + self.job["xReference"]["tableNameSfx"])
self.ExecutePostETL()
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
main routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
###
# set up to run create folder
###
self.fileUtilities.moduleName = self.moduleName
self.fileUtilities.localBaseDirectory = self.localTempDirectory
self.fileUtilities.CreateFolders(self.job["folders"])
self.fromDate = self.GetFromDate()
###
localFilepath = self.GetMostRecentFile(self.job["foldertoscan"])
# localFilepath = r'C:\tmp\IHS Markit Outlook for Global Oil Market Fundamentals - September 2017.xlsx'
for tables in self.job["tables"]:
fname = self.fileUtilities.CreateTableSql(
tables, self.fileUtilities.sqlFolder)
RedshiftUtilities.PSqlExecute(fname, self.logger)
outPutFileName = self.fileUtilities.csvFolder +\
self.fromDate +\
"_" + tables["table"] + '.csv'
outputGZ = self.fileUtilities.gzipFolder + self.fromDate +\
"_" + tables["table"] + '.csv.gz'
tableJson = tables
xl = ExcelUtilities(logger)
if sys.version[0] == '3':
csvfile = open(outPutFileName, 'w', newline='')
elif sys.version[0] == '2':
csvfile = open(outPutFileName, 'wb')
csvWriter = csv.writer(csvfile, quoting=csv.QUOTE_ALL)
if localFilepath is not None:
self.ProcessFile(xl, localFilepath, csvWriter)
csvfile.close()
self.fileUtilities.GzipFile(outPutFileName, outputGZ)
self.BulkUploadToS3()
self.LoadData(tableJson)
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
main routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
s3Key = self.job["s3SrcDirectory"] + "/" + self.job["fileToLoad"]
self.logger.info(self.moduleName + " - Processing file: " + s3Key)
localFilepath = self.localTempDirectory + "/" + ntpath.basename(
s3Key)
S3Utilities.DownloadFileFromS3(self.awsParams.s3,
self.job["bucketName"], s3Key,
localFilepath)
df = pd.read_excel(localFilepath,
"Major Variables",
index_col=None,
na_values=['NaN'],
skiprows=1,
parse_cols="C:E,G:I",
header=None)
# Save the data as CSV
outputCSVfileName = self.localTempDirectory + '/SampleData.csv'
df.to_csv(outputCSVfileName,
sep=str(self.job["delimiter"]),
encoding='utf-8',
index=False)
# Update the CSV file into a temporary S3 location. Postgres will download it from there to its local directory
bucketName, s3TempKey = S3Utilities.UploadFileToS3Temp(
self.awsParams.s3, outputCSVfileName)
psConnect = self.GetPSConnection()
# Postgres tables are created using a connection (rather than psql)
self.CreatePostgresTables(psConnect)
postgresTempFile = self.DownloadFromS3ToPSTempDir(
psConnect, bucketName, s3TempKey)
self.LoadDataFromPostgresTempDir(psConnect, postgresTempFile)
S3Utilities.DeleteFile(self.awsParams.s3, bucketName, s3TempKey)
self.LoadBaseAttributes(psConnect)
self.LoadBaseData(psConnect, '1000', 'glm_value')
self.LoadBaseData(psConnect, '2000', 'arima_value')
self.LoadBaseData(psConnect, '3000', 'lasso_value')
# self.LoadBaseData(psConnect,'4000', 'nn_value')
# self.LoadBaseData(psConnect,'5000', 'spectre_value')
psConnect.close()
self.logger.debug(" SampleData CSV loaded to RedShift")
except:
logger.exception(moduleName + " - Exception in start!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
for srcFileParameter in self.job["srcFileParameters"]:
self.ProcessS3File(srcFileParameter)
except:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Starting point of this Project
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.GetFileFromS3()
Form1(logger, self.fileUtilities, self.localTempDirectory,
self.job, self.awsParams) #invoke the Form1 handler
except:
self.logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Application starting point
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.DownloadFilesFromS3()
ISO(logger, self.fileUtilities, self.localTempDirectory, self.job, self.awsParams) #invoke the ISO handler
except Exception as ex:
self.logger.exception(moduleName + " - Exception!")
self.logger.exception("{}".format(str(ex)))
raise
def Start(self, logger, moduleName, filelocs):
'''
start it
'''
ApplicationBase.Start(self, logger, moduleName, filelocs)
seedVal = 100
logger.info("Starting count with seed %s in Counter" % (seedVal))
for i in range(seedVal):
val = i + seedVal
# logger.info("v value in Counter %s" % (str(v)))
logger.info(
"this is the starting seed %s and the end value was %s in Counter"
% (seedVal, val))
def Start(self, logger, moduleName, filelocs):
'''
main routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
###
# establish connection to Access database
###
conn = self.EstablishConnection()
cur = conn.cursor()
sqlline = self.FixSQLStatement()
cur.execute(sqlline)
outputfileName = self.localTempDirectory + '/ENPdata.csv'
self.ConvertToCSV(cur, outputfileName)
###
# load the CSV to RedShift
###
self.logger.debug(self.moduleName + " - ENP load CSV to RedShift")
rsConnect = self.etlUtilities.GetAWSConnection(self.awsParams)
RedshiftUtilities.LoadFileIntoRedshift(
rsConnect, self.awsParams.s3, self.logger, self.fileUtilities,
outputfileName, self.job["destinationSchema"],
self.job["tableName"], self.job["fileFormat"],
self.job["dateFormat"], self.job["delimiter"])
self.logger.debug(self.moduleName +
" - ENP CSV loaded to RedShift")
# Cleanup
rsConnect.close()
cur.close()
conn.close()
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
paramsList = self.GetParamsList(filelocs["tblEtl"]["table"])
###
# set up to run create folder
###
self.fileUtilities.moduleName = self.moduleName
self.fileUtilities.localBaseDirectory = self.localTempDirectory
self.fileUtilities.CreateFolders(self.job["folders"])
###
for tblJson in self.job["tables"]:
fname = self.fileUtilities.CreateTableSql(
tblJson, self.fileUtilities.sqlFolder)
RedshiftUtilities.PSqlExecute(fname, self.logger)
sqlPullDataScript, fromDate = self.CreatePullScript(paramsList)
outputCSV = self.fileUtilities.csvFolder + fromDate + self.moduleName + ".CSV"
outputGZ = self.fileUtilities.gzipFolder + fromDate + self.moduleName + '.csv.gz'
self.BulkExtract(sqlPullDataScript, outputCSV)
self.fileUtilities.GzipFile(outputCSV, outputGZ)
self.BulkUploadToS3()
for tblJson in self.job["tables"]:
if "s3subfolder" in tblJson:
self.LoadData(tblJson["s3subfolder"], tblJson)
maxDate = self.GetMaxUpdateDate(tblJson)
sMaxDate = maxDate["lastrun"].strftime('%m/%d/%Y')
if self.etlUtilities.SetInstanceParameters(filelocs["tblEtl"]["table"],\
currProcId,\
json.dumps({"lastrun":sMaxDate})) is not True:
self.logger.info(self.moduleName +
" - we could not set the instance.")
self.UpdateTable(filelocs["tblEtl"]["schemaName"],
filelocs["tblEtl"]["table"], self.job["tables"],
currProcId)
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.CreatePackedFolder()
fileList = self.DownloadFiles()
self.ProcessFiles(fileList)
self.UploadPackedToS3()
self.LoadTables()
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
for sheet in self.job["ExcelSheets"]:
self.DownloadAllFiles(sheet)
self.ConvertExcel2Csv(sheet)
self.SkipPackAndLoad(self.job["ExcelSheets"])
if "postETLQueries" in self.job:
ApplicationBase.CreateTables(self, self.job["postETLQueries"])
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
main routine starts here
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.moduleName = moduleName
self.CreateTables(self.job["tempTablesScript"])
self.SetLastLiquidsBalanceFileInfo()
self.ProcessLiquidBalanceFile()
self.CreateTables(self.job["unpivotScript"])
self.CreateTables(self.job["cleanTempTablesScript"])
except Exception as err:
self.logger.error(self.moduleName + " - Exception in start.")
raise err
def Start(self, logger, moduleName, filelocs):
'''
Starting point of this Project
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.dbfUtilities = DBFUtilities(logger)
self.CreateFolders()
self.Process()
self.UploadPackedToS3()
self.LoadFilesIntoRedshift()
self.EmptyPackedFolder()
self.PostLoadETL()
except:
self.logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
for srcFileParameter in self.job["srcFileParameters"]:
self.DownloadAllFiles(srcFileParameter)
self.UnzipExcel(srcFileParameter)
self.SkipPackAndLoad(self.job["srcFileParameters"])
if "postETLQueries" in self.job:
ApplicationBase.CreateTables(self, self.job["postETLQueries"])
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory) #delete and recreate the folder
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory +
"/cleaned/") #delete and recreate the folder
self.DownloadFiles()
self.ProcessFiles()
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Main starting routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.logger.debug(self.moduleName + " -- " + " starting ")
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
###
# set up to run create folder
###
self.fileUtilities.moduleName = self.moduleName
self.fileUtilities.localBaseDirectory = self.localTempDirectory
self.fileUtilities.CreateFolders(self.job["folders"])
###
for tblJson in self.job["tables"]:
fname = self.fileUtilities.CreateTableSql(
tblJson, self.fileUtilities.sqlFolder)
RedshiftUtilities.PSqlExecute(fname, self.logger)
if "s3subfolder" in tblJson:
self.s3subFolder = tblJson["s3subfolder"]
outputFileName = self.ProcessRequest()
outputCSV = outputFileName
outputGZ = self.fileUtilities.gzipFolder + self.moduleName + '.csv.gz'
self.fileUtilities.GzipFile(outputCSV, outputGZ)
self.BulkUploadToS3(self.s3subFolder)
for tblJson in self.job["tables"]:
if "s3subfolder" in tblJson:
self.LoadData(tblJson["s3subfolder"], tblJson)
self.UpdateTable(filelocs["tblEtl"]["schemaName"],
filelocs["tblEtl"]["table"], self.job["tables"],
currProcId)
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
self.logger.debug(self.moduleName + " -- " + " finished ")
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.packedFolder = self.localTempDirectory + "/packed/"
self.CreateFolders()
lastModifiedDatetime = self.GetLastModifiedDatetime(filelocs)
maxModifiedDatetime = self.ProcessFiles(lastModifiedDatetime)
self.UploadPackedToS3()
self.LoadErcotTables()
self.SetLastModifiedDatetime(filelocs, DatetimeUtilities.ConvertToSTR(maxModifiedDatetime))
self.EmptyPackedFolder()
self.PostLoadETL()
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.tempFolder = self.localTempDirectory + "/Temp"
self.packedFolder = self.localTempDirectory + "/Packed"
self.rawDataFolder = self.localTempDirectory + "/RawData"
self.CleanWorkingFolders()
self.SynchronizeSourceFolder()
self.CleanUpAndPack()
self.UploadPackedToS3()
self.LoadAirMarketsTables()
except:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
currProcId = None
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
currProcId = self.etlUtilities.GetRunID(
filelocs["tblEtl"]["table"], self.moduleName)
self.ProcessRequest()
if self.job["cleanlocal"] == "Y":
self.fileUtilities.RemoveFolder(self.localTempDirectory)
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
if self.etlUtilities.CompleteInstance(filelocs["tblEtl"]["table"],\
currProcId, 'F') is not True:
self.logger.info(self.moduleName +
" - we could not Complete Instance.")
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.packedFolder = self.localTempDirectory + "/Packed"
self.rawFolder = self.localTempDirectory + "/Raw"
self.fileUtilities.RemoveFolder(self.packedFolder)
self.fileUtilities.RemoveFolder(self.rawFolder)
self.fileUtilities.CreateFolder(self.packedFolder)
self.fileUtilities.CreateFolder(self.rawFolder)
self.BulkExtractAll()
self.TransformAndPackAll()
self.BulkUploadToS3()
self.LoadAllFromS3()
except Exception as err:
self.logger.exception(moduleName + " - Exception! Error: " +
err.message)
raise Exception(err.message)
def Start(self, logger, moduleName, filelocs):
'''
start it
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
logger.exception(moduleName + "- starting play area")
# self.TestZipIt()
# self.MoveFolderToS3()
# self.TestConnectionSQLServer()
####
# nugget is wrong since latest changes
####
# self.TestGEForecastHistory()
# self.ExcelTest()
# self.TestDates(logger, moduleName)
self.TestShooju(logger, moduleName)
logger.exception(moduleName + "- ending play area")
except Exception as ex:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Start of routine
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.excelUtilities = ExcelUtilities(logger)
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory) #delete and recreate the folder
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory +
"/CSVS/") #delete and recreate the folder
self.BulkDownload()
self.UnzipExcel()
for sheetParams in self.job["ExcelSheets"]:
self.Excel2CsvSkipped(sheetParams)
self.PostLoadETL()
self.fileUtilities.EmptyFolderContents(
self.localTempDirectory) #clear contents of the folder
except Exception:
logger.exception(moduleName + " - Exception!")
raise
def Start(self, logger, moduleName, filelocs):
'''
Application starting point
'''
try:
ApplicationBase.Start(self, logger, moduleName, filelocs)
self.pandasUtilities = PandasUtilities(self.logger)
self.CreateFolders()
#===================================================================
# delete files from S3 bucket
#===================================================================
for folder in [
flder for flder in list(self.job["folderPath"].keys())
if flder != "raw"
]:
self.DeleteFilesFromAWS(self.job["folderPath"][folder].replace(
"/", ""))
#===================================================================
# Process the files
#===================================================================
self.ProcessQuarterlyFilings()
#===================================================================
# Load into Redshift
#===================================================================
for folder in [
flder for flder in list(self.job["folderPath"].keys())
if flder != "raw"
]:
self.LoadQFTables(self.job["folderPath"][folder].replace(
"/", ""))
#===================================================================
# do post load ETL & view creation
#===================================================================
self.PostLoadETL()
except Exception as ex:
self.logger.exception(moduleName + " - Exception!")
self.logger.exception(str(ex))
raise