Untitled

mail@pastecode.io avatarunknown
plain_text
a month ago
11 kB
1
Indexable
Never
# ================================================================================================================================================================================
# PPM PRODUCT CATALOG (PC) REPLICATION - CE CUSTOM TABLES REPLICATE
#   DATE     AUTHOR     VER   CHANGE DESCRIPTION
# --------  ---------  -----  ------------------
# 21.08.23  Veera      1.0   The below script replicates ppm table records dynamically from "etl_ppm_replication_master" "PC_EXT"
#
#
# ================================================================================================================================================================================

import json
import logging
import mysql.connector
import pandas as pd
import os
import sys
from base64 import b64decode as base_b64decode
from pandas import read_sql as pd_read_sql
from sqlalchemy import create_engine
from io import TextIOBase as io_TextIOBase
from json import load as json_load


# define Python user-defined exceptions
class Error(Exception):
    """Base class for other exceptions"""
    pass


# define Python user-defined exceptions
class ETL_PPM_REPLICATION_MASTER_ERROR(Error):
    pass


class DB_CONNECTION_ERROR(Error):
    pass


# Function to write SQL query to the log file
def write_sql(sql_log_file, query_info):
    sql_log_file.write(query_info)
    sql_log_file.write('\n')


source = 'SOURCE'



# Function to establish a database connection
def setDbConnection(logging, json_data, serverInfo):
    from sqlalchemy import create_engine
    from base64 import b64decode as base_b64decode
    try:
        cnx = cursor = schema = db_type = None
        encrypt = json_data.get(serverInfo, {}).get('ENCRYPT')
        host = json_data.get(serverInfo, {}).get('DB_HOST')
        port = json_data.get(serverInfo, {}).get('DB_PORT')
        user = json_data.get(serverInfo, {}).get('DB_USER')
        db_type = json_data.get(serverInfo, {}).get('DB_TYPE')
        schema = json_data.get(serverInfo, {}).get('DB_SCHEMA')
        if encrypt == 'Y':
            password = base_b64decode(json_data.get(serverInfo, {}).get('DB_PASSWORD')).decode('utf-8')
        else:
            password = json_data.get(serverInfo, {}).get('DB_PASSWORD')

        if db_type in ('MYSQL', 'MARIA'):
            import mysql.connector
            cnx = mysql.connector.connect(user=user, password=password, host=host, port=port, database=schema)
            cursor = cnx.cursor()
        elif db_type == 'ORACLE':
            import oracledb
            oracle_mode = oracledb.is_thin_mode()

            if oracle_mode:
                oracledb.init_oracle_client()
                print("Enabled python-oracledb Thick mode")

            cnx_text = ('oracle://%s:%s@%s:%s/?service_name=%s' % (user, password, host, port, schema))
            cnx = create_engine(cnx_text, encoding="utf8").raw_connection()
            cursor = cnx.cursor

        logging.info(f"Connected to database server {serverInfo}: {host}:{port}/{schema}")
    except mysql.connector.Error as dberr:
        logging.error("DATABASE CONNECTION ERROR")
        logging.error("Error - {} . Line No - {} ".format(str(dberr), str(sys.exc_info()[-1].tb_lineno)))
        cnx = cursor = schema = None
    except Exception as dbexp:
        logging.error("DATABASE CONNECTION EXCEPTION")
        logging.error("Error - {} . Line No - {} ".format(str(dberr), str(sys.exc_info()[-1].tb_lineno)))
        cnx = cursor = schema = None

    return cnx, cursor, schema, db_type


def main(args, sql_log_file, logging, json_data):
    # Connect to PPM_PC database
    conn_ppm, cursor_ppm, schema_ppm, user_ppm, password_ppm, host_ppm, port_ppm = setDbConnection(logging,json_data,
                                                                                                       'PPM_PC')

    # Connect to source database
    conn_source, cursor_source, schema_source, _, _, _, _ = setDbConnection(logging,json_data, source)

    # Fetch data from the etl_ppm_replication_master table
    primary_query = f"SELECT * FROM {schema_ppm}.etl_ppm_replication_master WHERE eprm_catalog='PC_EXT' AND eprm_enabled_flg='Y'"
    df = pd_read_sql(primary_query, con=conn_ppm)

    # Connect to target database
    replicationTarget_EXT = replicationTarget + '_EXT'
    db_type = json_data.get(replicationTarget_EXT, {}).get('DB_TYPE')
    if db_type == 'MYSQL':
        _, _, schema_target, user_target, password_target, host_target, port_target = setDbConnection(logging,json_data,
                                                                                                          replicationTarget_EXT)
        target_engine = create_engine(
            f"mysql+mysqlconnector://{user_target}:{password_target}@{host_target}:{port_target}/{schema_target}")
    else:
        _, _, schema_target, user_target, password_target, host_target, port_target = setDbConnection(json_data,
                                                                                                          replicationTarget_EXT)

        oracle_dsn = f"(DESCRIPTION=(ADDRESS_LIST=(ADDRESS=(PROTOCOL=TCP)(HOST={host_target})(PORT={port_target})))(CONNECT_DATA=(SERVICE_NAME={schema_target})(SID={sid})))"  # Add SID here
        dsn_kwargs = {
            'user': user_target,
            'password': password_target,
            'dsn': oracle_dsn,
            'encoding': 'UTF-8',
        }

        try:
            import cx_Oracle

            target_connection = cx_Oracle.connect(**dsn_kwargs)
            target_cursor = target_connection.cursor()
        except ImportError:
            logging.error("cx_Oracle library not found. Make sure it's installed to establish Oracle connections.")
            raise
        except cx_Oracle.DatabaseError as ex:
            logging.error(f"Error while connecting to Oracle database: {ex}")
            raise

    for _, row in df.iterrows():
        eprm_table_name = row['eprm_table_name'].lower()  # Convert table name to lowercase
        if eprm_table_name != 'pkg_prd_fed_ext_attrs':
            source_query = f"SELECT * FROM {schema_source}.{eprm_table_name} WHERE release_id='{releaseId}' AND op_id='{opId}' AND bu_id='{buId}'"
            try:
                source_df = pd_read_sql(source_query, con=conn_source)
                if 'updated_by' in source_df:
                    source_df['updated_by'] = replicationJobId
                if not source_df.empty:
                    source_df.to_sql(eprm_table_name, con=target_engine, if_exists='append', index=False)
                    write_sql(
                        f"-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ STATUS|{replicationTarget}| TABLE| {eprm_table_name}\n")
                    write_sql(f"-- #Query: Inserted {len(source_df)} record(s) and updated 'created_by'\n")
                    print(f"Inserting records into {eprm_table_name}")
                    logging.info(f"Inserted {len(source_df)} record(s) into {eprm_table_name} and updated 'created_by'")
            except mysql.connector.Error as err:
                print(f"Error occurred while executing the query: {source_query}: {err}")
                logging.info(f"Error occurred while executing the query: {source_query}: {err}")


if __name__ == '__main__':
    import logging
    from configparser import ConfigParser as conf_ConfigParser
    import argparse

    statFile = ""
    try:
        parser = argparse.ArgumentParser(description="PPM Product Catalog Replication Script")
        parser.add_argument('--releaseId', required=True, help="Release ID")
        parser.add_argument('--releaseType', required=True, help="Release Type")
        parser.add_argument('--replicationTarget', required=True, help="Replication Target")
        parser.add_argument('--opId', required=True, help="Operation ID")
        parser.add_argument('--buId', required=True, help="Business Unit ID")
        parser.add_argument('--replicationJobId', required=True, help="Replication Job ID")
        args = parser.parse_args()
        replicationJobId = args.replicationJobId

        # File based variables
        json_file_path = "/app/scripts/PPM_Release_Management/Product_Catalog_ETL/config/ppm_pc_replication.json"
        conf_file_path = "/app/scripts/PPM_Release_Management/Product_Catalog_ETL/config/ppm_pc_replication.conf"
        sql_log_file = f"/app/scripts/PPM_Release_Management/Product_Catalog_ETL/logs/{replicationJobId}_ppm_pc_replication_insert.sql"
        log_file = f'/app/scripts/PPM_Release_Management/Product_Catalog_ETL/logs/{replicationJobId}_ppm_pc_replication_insert.log'
        statFile = f'/app/scripts/PPM_Release_Management/Product_Catalog_ETL/logs/{replicationJobId}_ppm_pc_replication_insert.status'

        # Status file for reading in main shell script
        print("statFile: %s" % statFile)
        statFile = open(statFile, "w")

        # Core ppm_pc_replication Configuration
        if not os.path.exists(conf_file_path):
            print("CONFIGURATION FILE: ", conf_file_path)
            raise FileNotFoundError("CONFIGURATION FILE MISSING")
        CONFIG = conf_ConfigParser()
        CONFIG.read(conf_file_path)
        print(CONFIG.sections())

        # Set up logging
        logging.basicConfig(
            filename=log_file,
            level=CONFIG.get('CONFIG_LOGGING', 'LOG_LEVEL', raw=True),
            format=CONFIG.get('CONFIG_LOG_FORMAT', 'LOG_FORMAT_DISP', raw=True),
            datefmt=CONFIG.get('CONFIG_LOG_FORMAT', 'LOG_FORMAT_DATE', raw=True)
        )
        logging.info('LOGGER initiated')

        # Read JSON data from file
        if not os.path.exists(json_file_path):
            logging.error("CREDENTIAL FILE MISSING")
            logging.error("CREDENTIAL FILE: %s" % json_file_path)
            raise FileNotFoundError("CREDENTIAL FILE MISSING")
        with open(json_file_path) as json_file:
            json_data = json_load(json_file)

        # Open SQL log file for writing
        sql_log_file = open(sql_log_file, "w")

        if main(args, sql_log_file, logging, json_data):
            print("Inserting data")
            statFile.write("SUCCESS")
        else:
            statFile.write("FAILED")

        sql_log_file.close()
    except FileNotFoundError as ferr:
        print("Error - {} . Line No - {} ".format(str(ferr), str(sys.exc_info()[-1].tb_lineno)))
        statFile.write("FAILED")

    except Exception as err:
        print("Error - {} . Line No - {} ".format(str(err), str(sys.exc_info()[-1].tb_lineno)))
        statFile.write("FAILED")

    if isinstance(statFile, io_TextIOBase):
        statFile.close()

for above code iam getting below error
Error - not enough values to unpack (expected 7, got 4) . Line No - 214