Comment créer un job ETL avec Talend en 2026

#!/bin/bash

# Téléchargement de Talend Open Studio 8.0 (adaptez l'URL à la dernière version 2026)
URL="https://github.com/Talend/open-studio-dist/releases/download/8.0.2/TOS_DI-20230220_1200-V8.0.2.zip"
wget $URL

# Décompression
unzip TOS_DI-*.zip -d /opt/talend/

# Lancement (Linux/Mac, adaptez pour Windows: double-clic)
cd /opt/talend/TOS_DI-*/
./Talend-Studio

# Vérification: Studio s'ouvre avec Repository, Integration perspectives

db_host=localhost
db_port=3306
db_name=etl_db
db_user=root
db_pass=root
csv_input_path=/tmp/clients.csv
csv_output_path=/tmp/clients_clean.csv
batch_size=1000
log_level=INFO

CREATE DATABASE IF NOT EXISTS etl_db;
USE etl_db;

CREATE TABLE IF NOT EXISTS clients_clean (
  id INT PRIMARY KEY,
  nom VARCHAR(50) NOT NULL,
  email VARCHAR(100) UNIQUE,
  processed_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);

-- Insert sample pour test
INSERT INTO clients_clean (id, nom, email) VALUES (1, 'Dupont', 'dupont@test.com');

// Expression pour nettoyer email (copiez dans tMap cell)
((String)row1.email != null ? row1.email.toLowerCase().replaceAll("\\s+", "") : "") + "@validated.com"

// Filtre ligne (condition If)
!row1.email.contains("@fake.com") && row1.nom.length() > 2

// Variable globale pour compteur
((Integer)globalMap.get("total_records") == null ? 1 : ((Integer)globalMap.get("total_records") + 1))

import routines.Numeric;
import routines.DataOperations;
import routines.TalendDataGenerator;
import routines.TalendString;
import routines.java;
import routines.system.*;
import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.io.BufferedReader;
import java.io.FileReader;
import java.sql.*;

public class CSV_to_MySQL_0_1 {

  protected static void logIgnoredError(String message, Throwable cause) {
    System.err.println(message);
    if (cause != null) { cause.printStackTrace(); }
  }

  public static class row1Struct {
    public int id;
    public String nom;
    public String email;
  }

  public static class out1Struct {
    public int id;
    public String nom;
    public String email_clean;
  }

  private static class Context {
    public String db_host = "localhost";
    // ... autres contexts
  }

  public static void main(String[] args) {
    Context ctx = new Context();
    java.util.Map<String, Object> globalMap = java.util.Collections.synchronizedMap(new java.util.HashMap<String, Object>());
    globalMap.put("ctx", ctx);

    try {
      // Simule tFileInputDelimited
      File csvFile = new File("/tmp/clients.csv");
      BufferedReader br = new BufferedReader(new FileReader(csvFile));
      String line;
      int rowCount = 0;
      while ((line = br.readLine()) != null) {
        if (rowCount++ == 0) continue; // skip header
        String[] fields = line.split(",");
        row1Struct row1 = new row1Struct();
        row1.id = Integer.parseInt(fields[0]);
        row1.nom = fields[1];
        row1.email = fields[2];

        // tMap transformation
        out1Struct out1 = new out1Struct();
        out1.id = row1.id;
        out1.nom = row1.nom.toUpperCase();
        out1.email_clean = (row1.email != null ? row1.email.toLowerCase() : "");

        if (!out1.email_clean.contains("fake")) {
          // tMySQLOutput simule
          Class.forName("com.mysql.cj.jdbc.Driver");
          Connection conn = DriverManager.getConnection("jdbc:mysql://" + ctx.db_host + "/etl_db", "root", "root");
          PreparedStatement pstmt = conn.prepareStatement("INSERT INTO clients_clean (id, nom, email) VALUES (?, ?, ?)");
          pstmt.setInt(1, out1.id);
          pstmt.setString(2, out1.nom);
          pstmt.setString(3, out1.email_clean);
          pstmt.executeUpdate();
          pstmt.close();
          conn.close();
          globalMap.put("total_records", rowCount);
          System.out.println("Inserted: " + out1.id);
        }
      }
      br.close();
      System.out.println("Job complet: " + globalMap.get("total_records") + " rows.");
    } catch (Exception e) {
      logIgnoredError("Main job error", e);
    }
  }
}

#!/bin/bash

# Après export Talend (zip job), unzip et cd
cd CSV_to_MySQL_0_1/

# Compile (ajoutez jars Talend + MySQL)
javac -cp "lib/*:mysql-connector-j-8.0.33.jar" *.java

# Run avec contexts
java -cp "lib/*:mysql-connector-j-8.0.33.jar:.:$CLASSPATH" CSV_to_MySQL_0_1 "-Dfile.encoding=UTF-8" "-Dcontext=db_host=localhost"

# Logs: rows processed, errors en stderr