Ugbot

-- Define the payments source table
CREATE TABLE payments (
  payment_id STRING,
  user_id STRING,
  amount DECIMAL(10, 2),
  timestamp TIMESTAMP(3),
  WATERMARK FOR timestamp AS timestamp - INTERVAL '5' SECOND
) WITH (
  'connector' = 'kafka',
  'topic' = 'payments',

Ugbot

-- Step 1: Set up environment to access the Paimon catalog
SET 'execution.runtime-mode' = 'batch';
SET 'table.dynamic-table-options.enabled' = 'true';

-- Step 2: Define the source table to read LAION Parquet files
CREATE TEMPORARY TABLE source_laion (
    id STRING,
    url STRING,
    text STRING,
    height INT,

Ugbot

// Sample for reading a file asynchronously using libuv
// taken from https://www.snip2code.com/Snippet/247423/Sample-for-reading-a-file-asynchronously

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <uv.h>

static uv_fs_t openReq;
static uv_fs_t readReq;

Ugbot

import json
import boto3
import csv
import io
from botocore.vendored import requests

s3Client = boto3.client('s3')

demo_query = """SELECT *
FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/trips_*.gz', 'TabSeparatedWithNames')

Ugbot

import ast
import boto3
from botocore.exceptions import ClientError

def stream_s3_file(bucket: str, key: str, file_size: int, chunk_bytes=5000) -> tuple[dict]:
    """Streams a S3 file via a generator.

    Args:
        bucket (str): S3 bucket
        key (str): S3 object path

Ugbot

const { Kafka } = require('kafkajs');
const axios = require('axios');

const fs = require('fs');

const kafka = new Kafka({
  clientId: 'my-app',
  brokers: ['BROKERS'], // Broker list
  ssl: {
    rejectUnauthorized: true,

Ugbot

import os
from clickhouse_driver import Client

# Initialize ClickHouse client
clickhouse_host = os.environ['CLICKHOUSE_HOST']
clickhouse_port = os.environ['CLICKHOUSE_PORT']
clickhouse_user = os.environ['CLICKHOUSE_USER']
clickhouse_password = os.environ['CLICKHOUSE_PASSWORD']
clickhouse_database = os.environ['CLICKHOUSE_DATABASE']
clickhouse_table = os.environ['CLICKHOUSE_TABLE']

Ugbot

#pragma once

#include "util/types.hpp"
#include "util/std.hpp"
#include "util/ndarray.hpp"
#include "util/collections.hpp"
#include "util/rand.hpp"
#include "util/hash.hpp"
#include "util/assert.hpp"
#include "util/bitset.hpp"

Ugbot

CREATE TABLE kafka_input (
    id INT,
    event_timestamp STRING,
    message STRING,
    proctime AS PROCTIME(),  
    eventtime AS TO_TIMESTAMP(event_timestamp),  
    WATERMARK FOR eventtime AS eventtime - INTERVAL '1' SECOND  
) WITH (
    'connector' = 'kafka',

Ugbot

SELECT
  window_start,
  CEIL(row_num / 50.0) AS bundle, 
  COUNT(*), 
  AVG(value), 
  MAX(value), 
  MIN(value)
FROM (
  SELECT 
    *,