Untitled

mail@pastecode.io avatar
unknown
plain_text
a year ago
5.4 kB
2
Indexable
Never
import pandas as pd
import mysql.connector
import json
from base64 import b64decode as base_b64decode
import logging
from pandas import read_sql as pd_read_sql
from sqlalchemy import create_engine
import sys

releaseId = '275.2'
opId = 'HOB'
buId = 'DEFAULT'
replicationTarget = 'SIT'
source_target='SOURCE'
replicationJobId = 'REP_990_234'
json_file_path = "/app/scripts/PPM_Release_Management/Product_Catalog_ETL/config/ppm_reply.json"
sql_log_file = f"/app/scripts/PPM_Release_Management/Product_Catalog_ETL/logs/{replicationJobId}ppm_reply.sql"
log_file = f'/app/scripts/PPM_Release_Management/Product_Catalog_ETL/logs/{replicationJobId}ppm_reply.log'

# Set up logging
logging.basicConfig(
    filename=log_file,
    level=logging.INFO,
    format='%(asctime)s - %(message)s',
    datefmt='%Y-%m-%d %H:%M:%S'
)

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


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


try:
    # Function to establish a database connection
    def connect_to_database(json_data, replicationTarget):
        try:
            encrypt = json_data.get(replicationTarget, {}).get('ENCRYPT')
            host = json_data.get(replicationTarget, {}).get('DB_HOST')
            port = json_data.get(replicationTarget, {}).get('DB_PORT')
            user = json_data.get(replicationTarget, {}).get('DB_USER')
            db_type = json_data.get(replicationTarget, {}).get('DB_TYPE')
            schema = json_data.get(replicationTarget, {}).get('DB_SCHEMA')
            if encrypt == 'Y':
                password = base_b64decode(json_data.get(replicationTarget, {}).get('DB_PASSWORD')).decode('utf-8')
            else:
                password = json_data.get(replicationTarget, {}).get('DB_PASSWORD')

            if db_type == 'MYSQL':
                connection_string = f"mysql+mysqlconnector://{user}:{password}@{host}:{port}/{schema}"
                engine = create_engine(connection_string)
                logging.info(f"Connected to MySQL database server {replicationTarget}: {host}:{port}")

            return engine, schema

        except (mysql.connector.Error, Exception) as e:
            logging.error(f"An error occurred while connecting to the database: {str(e)}")
            raise e


    try:
        # Read JSON data from file
        with open(json_file_path) as json_file:
            json_data = json.load(json_file)
    except FileNotFoundError:
        print("File not found: " + json_file_path)

    try:
        # Connect to PPM_PC database
        engine_ppm, schema_ppm = connect_to_database(json_data, 'PPM_PC')

        # 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=engine_ppm)

        # Connect to source database
        engine_source, schema_source = connect_to_database(json_data, source_target)

        # Connect to target database
        replicationTarget_EXT = replicationTarget + '_EXT'
        engine_target, schema_target = connect_to_database(json_data, replicationTarget_EXT)

        for _, row in df.iterrows():
            eprm_table_name = row['eprm_table_name']
            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=engine_source)
                    if not source_df.empty:
                        # Convert the table name to lowercase
                        eprm_table_name_lower = eprm_table_name.lower()
                        target_table = f"{schema_target}.{eprm_table_name_lower}"
                        source_df.to_sql(name=target_table, con=engine_target, if_exists='append', index=False)
                        num_records = len(source_df)
                        query_info = f"-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ STATUS|{replicationTarget}| TABLE| {eprm_table_name}\n"
                        query_info += f"-- #Query: Inserted {num_records} records into {target_table}\n"
                        write_sql(query_info)
                        print(f"Inserted {num_records} records into {target_table}")
                        logging.info(f"Inserted {num_records} records into {target_table}")
                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}")

    except Exception as e:
        print("Error - {} . Line No - {} ".format(str(e), str(sys.exc_info()[-1].tb_lineno)))
        print("An Error occurred while constructing dataframe:", str(e))

except mysql.connector.Error as err:
    print("Error - {} . Line No - {} ".format(str(exp), str(sys.exc_info()[-1].tb_lineno)))
    print(f"An error occurred: {err}")
    logging.info(f"An error occurred: {err}")

finally:
    if sql_log_file:
        sql_log_file.close()