velotiotech

{
    "conf":  {
             "spark.sql.catalog.glue_catalog1": "org.apache.iceberg.spark.SparkCatalog",
             "spark.sql.catalog.glue_catalog1.warehouse": 
                   "s3://YOUR-BUCKET-NAME/iceberg/glue_catalog1/tables/",
             "spark.sql.catalog.glue_catalog1.catalog-impl":    "org.apache.iceberg.aws.glue.GlueCatalog",
             "spark.sql.catalog.glue_catalog1.io-impl": "org.apache.iceberg.aws.s3.S3FileIO",
             "spark.sql.catalog.glue_catalog1.lock-impl": "org.apache.iceberg.aws.glue.DynamoLockManager",
             "spark.sql.catalog.glue_catalog1.lock.table": "myGlueLockTable",
  "spark.sql.extensions": "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions"

velotiotech

spark.sql(""" CREATE TABLE IF NOT EXISTS demo.db.iceberg_data_2(id INT, first_name String,
last_name String, address String, pincocde INT, net_income INT, source_of_income String,
state String, email_id String, description String, population INT, population_1 String,
population_2 String, population_3 String, population_4 String, population_5 String, population_6 String,
population_7 String, date INT)
USING iceberg
TBLPROPERTIES ('format'='parquet', 'format-version' = '2')
PARTITIONED BY (`date`)
location 's3a://abhishek-test-01012023/iceberg_v2/db/iceberg_data_2'""")

velotiotech

AWS_ACCESS_KEY_ID = "XXXXXXXXXXX"
AWS_SECRET_ACCESS_KEY = "XXXXXXXXXXX+XXXXXXXXXXX"

spark_jars_packages = "com.amazonaws:aws-java-sdk:1.12.246,org.apache.hadoop:hadoop-aws:3.2.2,org.apache.iceberg:iceberg-spark-runtime-3.3_2.12:1.1.0"

spark = pyspark.sql.SparkSession.builder \
   .config("spark.jars.packages", spark_jars_packages) \
   .config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions") \
   .config("spark.sql.catalog.demo", "org.apache.iceberg.spark.SparkCatalog") \
   .config("spark.sql.catalog.demo.warehouse", "s3a://abhishek-test-01012023/iceberg-sample-data/") \

velotiotech

docker exec -it <container-id> bash

velotiotech

docker cp input-data <Container ID>:/home/iceberg/data  

velotiotech

version: "3"

services:
  spark-iceberg:
    image: tabulario/spark-iceberg
    container_name: spark-iceberg
    build: spark/
    depends_on:
      - rest
      - minio

velotiotech

AWS_ACCESS_KEY_ID = "XXXXXXXXXXXXXX"
AWS_SECRET_ACCESS_KEY = "XXXXXXXXXXXXXXXXXXXXXXXXXXXXpiwvahk7e"

spark_jars_packages = "com.amazonaws:aws-java-sdk:1.12.246,org.apache.hadoop:hadoop-aws:3.2.2,org.apache.iceberg:iceberg-spark-runtime-3.3_2.12:1.1.0"

spark = pyspark.sql.SparkSession.builder \
   .config("spark.jars.packages", spark_jars_packages) \
   .config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions") \
   .config("spark.sql.catalog.demo", "org.apache.iceberg.spark.SparkCatalog") \
   .config("spark.sql.catalog.demo.warehouse", "s3a://abhishek-test-01012023/iceberg-sample-data/") \

velotiotech

def outer_function():
    x = 10
    
    def inner_function():
        nonlocal x
        x += 5
        print("Inner:", x)
    
    inner_function()
    print("Outer:", x)

velotiotech

#include <bits/stdc++.h>

int main() {
    std::vector<std::unique_ptr<int>> numbers;
    std::unique_ptr<int> ptr1(new int(20));
    std::unique_ptr<int> ptr2(new int(10));
    numbers.push_back(ptr1);
    numbers.push_back(ptr2);
    
    for (const auto& ptr : numbers) 

velotiotech

class numbers {
private:
    std::vector<std::unique_ptr<int>> numbers;
public:
    void addNumber(int value)
    {
        std::unique_ptr<int> ptr(new int(value));
        numbers.push_back(ptr);
    }
    void printNumbers()