Singleton Design Principle for pyspark database connector A singleton is a design pattern that ensures that a class has only one instance, and provide...

[Prototype998]

Singleton Design Principle for pyspark database connector

A singleton is a design pattern that ensures that a class has only one instance, and provides a global access point to that instance. Here is an example of how you could implement a singleton design for a PySpark database connector in Python:

# Define the singleton decorator
def singleton(cls):
    instances = {}
    def get_instance(*args, **kwargs):
        if cls not in instances:
            instances[cls] = cls(*args, **kwargs)
        return instances[cls]
    return get_instance
 
# Define the MongoDBConnector class
@singleton
class MongoDBConnector:    
    def __init__(self, connection_string):
        self.spark = SparkSession.builder.getOrCreate()
        self.uri = connection_string
        self.dataframes = {}
    
    def connect(self, database_name, collection_name):
        key = (database_name, collection_name)
        if key not in self.dataframes:
            dataframe = self.spark.read.format("com.mongodb.spark.sql.DefaultSource").option("uri", self.uri).option("database", database_name).option("collection", collection_name).load()
            self.dataframes[key] = dataframe
        return self.dataframes[key]
    
    def get_dataframe(self, database_name, collection_name):
        key = (database_name, collection_name)
        if key in self.dataframes:
            return self.dataframes[key]
        else:
            return None
 
# Create an instance of the MongoDBConnector class
mongo_connector = MongoDBConnector(connectionString)
 
# Connect to the "sample_supplies" database and "sales" collection
df1 = mongo_connector.connect("sample_supplies", "sales")
 
# Connect to the "sample_airbnb" database and "listingsAndReviews" collection
df2 = mongo_connector.connect("sample_airbnb", "listingsAndReviews")
 
# Print the id values of the DataFrame objects
print(id(df1))
print(id(df2))
 
# Try to get the DataFrame object for the "sample_supplies" database and "sales" collection
df3 = mongo_connector.get_dataframe("sample_supplies", "sales")
 
# Print the id value of the DataFrame object
print(id(df3))
 
# Try to get the DataFrame object for the "sample_supplies" database and "sales" collection
df4 = mongo_connector.get_dataframe("sample_airbnb", "listingsAndReviews")
 
# Print the id value of the DataFrame object
print(id(df4))

source:-chatgpt