AWS Glue exemplos usando o SDK para JavaScript (v3)

import { ListJobsCommand, GlueClient } from "@aws-sdk/client-glue";

const client = new GlueClient({});

export const main = async () => {
  const command = new ListJobsCommand({});

  const { JobNames } = await client.send(command);
  const formattedJobNames = JobNames.join("\n");
  console.log("Job names: ");
  console.log(formattedJobNames);
  return JobNames;
};

Crie e execute um crawler que examine um bucket público do Amazon Simple Storage Service (Amazon S3) e gere um banco de dados de metadados que descreva os dados no formato CSV que encontrar.

const createCrawler = (name, role, dbName, tablePrefix, s3TargetPath) => {
  const client = new GlueClient({});

  const command = new CreateCrawlerCommand({
    Name: name,
    Role: role,
    DatabaseName: dbName,
    TablePrefix: tablePrefix,
    Targets: {
      S3Targets: [{ Path: s3TargetPath }],
    },
  });

  return client.send(command);
};

const getCrawler = (name) => {
  const client = new GlueClient({});

  const command = new GetCrawlerCommand({
    Name: name,
  });

  return client.send(command);
};

const startCrawler = (name) => {
  const client = new GlueClient({});

  const command = new StartCrawlerCommand({
    Name: name,
  });

  return client.send(command);
};

const crawlerExists = async ({ getCrawler }, crawlerName) => {
  try {
    await getCrawler(crawlerName);
    return true;
  } catch {
    return false;
  }
};

/**
 * @param {{ createCrawler: import('../../../actions/create-crawler.js').createCrawler}} actions
 */
const makeCreateCrawlerStep = (actions) => async (context) => {
  if (await crawlerExists(actions, process.env.CRAWLER_NAME)) {
    log("Crawler already exists. Skipping creation.");
  } else {
    await actions.createCrawler(
      process.env.CRAWLER_NAME,
      process.env.ROLE_NAME,
      process.env.DATABASE_NAME,
      process.env.TABLE_PREFIX,
      process.env.S3_TARGET_PATH,
    );

    log("Crawler created successfully.", { type: "success" });
  }

  return { ...context };
};

/**
 * @param {(name: string) => Promise<import('@aws-sdk/client-glue').GetCrawlerCommandOutput>} getCrawler
 * @param {string} crawlerName
 */
const waitForCrawler = async (getCrawler, crawlerName) => {
  const waitTimeInSeconds = 30;
  const { Crawler } = await getCrawler(crawlerName);

  if (!Crawler) {
    throw new Error(`Crawler with name ${crawlerName} not found.`);
  }

  if (Crawler.State === "READY") {
    return;
  }

  log(`Crawler is ${Crawler.State}. Waiting ${waitTimeInSeconds} seconds...`);
  await wait(waitTimeInSeconds);
  return waitForCrawler(getCrawler, crawlerName);
};

const makeStartCrawlerStep =
  ({ startCrawler, getCrawler }) =>
  async (context) => {
    log("Starting crawler.");
    await startCrawler(process.env.CRAWLER_NAME);
    log("Crawler started.", { type: "success" });

    log("Waiting for crawler to finish running. This can take a while.");
    await waitForCrawler(getCrawler, process.env.CRAWLER_NAME);
    log("Crawler ready.", { type: "success" });

    return { ...context };
  };

Liste informações sobre bancos de dados e tabelas em seu AWS Glue Data Catalog.

const getDatabase = (name) => {
  const client = new GlueClient({});

  const command = new GetDatabaseCommand({
    Name: name,
  });

  return client.send(command);
};

const getTables = (databaseName) => {
  const client = new GlueClient({});

  const command = new GetTablesCommand({
    DatabaseName: databaseName,
  });

  return client.send(command);
};

const makeGetDatabaseStep =
  ({ getDatabase }) =>
  async (context) => {
    const {
      Database: { Name },
    } = await getDatabase(process.env.DATABASE_NAME);
    log(`Database: ${Name}`);
    return { ...context };
  };

/**
 * @param {{ getTables: () => Promise<import('@aws-sdk/client-glue').GetTablesCommandOutput}} config
 */
const makeGetTablesStep =
  ({ getTables }) =>
  async (context) => {
    const { TableList } = await getTables(process.env.DATABASE_NAME);
    log("Tables:");
    log(TableList.map((table) => `  • ${table.Name}\n`));
    return { ...context };
  };

Crie e execute um trabalho que extraia dados em CSV do bucket do Amazon S3 de origem, transforme-os removendo e renomeando campos, e carregue a saída formatada em JSON em outro bucket do Amazon S3.

const createJob = (name, role, scriptBucketName, scriptKey) => {
  const client = new GlueClient({});

  const command = new CreateJobCommand({
    Name: name,
    Role: role,
    Command: {
      Name: "glueetl",
      PythonVersion: "3",
      ScriptLocation: `s3://${scriptBucketName}/${scriptKey}`,
    },
    GlueVersion: "3.0",
  });

  return client.send(command);
};

const startJobRun = (jobName, dbName, tableName, bucketName) => {
  const client = new GlueClient({});

  const command = new StartJobRunCommand({
    JobName: jobName,
    Arguments: {
      "--input_database": dbName,
      "--input_table": tableName,
      "--output_bucket_url": `s3://${bucketName}/`,
    },
  });

  return client.send(command);
};

const makeCreateJobStep =
  ({ createJob }) =>
  async (context) => {
    log("Creating Job.");
    await createJob(
      process.env.JOB_NAME,
      process.env.ROLE_NAME,
      process.env.BUCKET_NAME,
      process.env.PYTHON_SCRIPT_KEY,
    );
    log("Job created.", { type: "success" });

    return { ...context };
  };

/**
 * @param {(name: string, runId: string) => Promise<import('@aws-sdk/client-glue').GetJobRunCommandOutput> }  getJobRun
 * @param {string} jobName
 * @param {string} jobRunId
 */
const waitForJobRun = async (getJobRun, jobName, jobRunId) => {
  const waitTimeInSeconds = 30;
  const { JobRun } = await getJobRun(jobName, jobRunId);

  if (!JobRun) {
    throw new Error(`Job run with id ${jobRunId} not found.`);
  }

  switch (JobRun.JobRunState) {
    case "FAILED":
    case "TIMEOUT":
    case "STOPPED":
    case "ERROR":
      throw new Error(
        `Job ${JobRun.JobRunState}. Error: ${JobRun.ErrorMessage}`,
      );
    case "SUCCEEDED":
      return;
    default:
      break;
  }

  log(
    `Job ${JobRun.JobRunState}. Waiting ${waitTimeInSeconds} more seconds...`,
  );
  await wait(waitTimeInSeconds);
  return waitForJobRun(getJobRun, jobName, jobRunId);
};

/**
 * @param {{ prompter: { prompt: () => Promise<{ shouldOpen: boolean }>} }} context
 */
const promptToOpen = async (context) => {
  const { shouldOpen } = await context.prompter.prompt({
    name: "shouldOpen",
    type: "confirm",
    message: "Open the output bucket in your browser?",
  });

  if (shouldOpen) {
    return open(
      `https://s3.console.aws.amazon.com/s3/buckets/${process.env.BUCKET_NAME} to view the output.`,
    );
  }
};

const makeStartJobRunStep =
  ({ startJobRun, getJobRun }) =>
  async (context) => {
    log("Starting job.");
    const { JobRunId } = await startJobRun(
      process.env.JOB_NAME,
      process.env.DATABASE_NAME,
      process.env.TABLE_NAME,
      process.env.BUCKET_NAME,
    );
    log("Job started.", { type: "success" });

    log("Waiting for job to finish running. This can take a while.");
    await waitForJobRun(getJobRun, process.env.JOB_NAME, JobRunId);
    log("Job run succeeded.", { type: "success" });

    await promptToOpen(context);

    return { ...context };
  };

Liste informações sobre execuções de tarefas e visualize alguns dos dados transformados.

const getJobRuns = (jobName) => {
  const client = new GlueClient({});
  const command = new GetJobRunsCommand({
    JobName: jobName,
  });

  return client.send(command);
};

const getJobRun = (jobName, jobRunId) => {
  const client = new GlueClient({});
  const command = new GetJobRunCommand({
    JobName: jobName,
    RunId: jobRunId,
  });

  return client.send(command);
};

/**
 * @typedef {{ prompter: { prompt: () => Promise<{jobName: string}> } }} Context
 */

/**
 * @typedef {() => Promise<import('@aws-sdk/client-glue').GetJobRunCommandOutput>} getJobRun
 */

/**
 * @typedef {() => Promise<import('@aws-sdk/client-glue').GetJobRunsCommandOutput} getJobRuns
 */

/**
 *
 * @param {getJobRun} getJobRun
 * @param {string} jobName
 * @param {string} jobRunId
 */
const logJobRunDetails = async (getJobRun, jobName, jobRunId) => {
  const { JobRun } = await getJobRun(jobName, jobRunId);
  log(JobRun, { type: "object" });
};

/**
 *
 * @param {{getJobRuns: getJobRuns, getJobRun: getJobRun }} funcs
 */
const makePickJobRunStep =
  ({ getJobRuns, getJobRun }) =>
  async (/** @type { Context } */ context) => {
    if (context.selectedJobName) {
      const { JobRuns } = await getJobRuns(context.selectedJobName);

      const { jobRunId } = await context.prompter.prompt({
        name: "jobRunId",
        type: "list",
        message: "Select a job run to see details.",
        choices: JobRuns.map((run) => run.Id),
      });

      logJobRunDetails(getJobRun, context.selectedJobName, jobRunId);
    }

    return { ...context };
  };

Exclua todos os recursos criados pela demonstração.

const deleteJob = (jobName) => {
  const client = new GlueClient({});

  const command = new DeleteJobCommand({
    JobName: jobName,
  });

  return client.send(command);
};

const deleteTable = (databaseName, tableName) => {
  const client = new GlueClient({});

  const command = new DeleteTableCommand({
    DatabaseName: databaseName,
    Name: tableName,
  });

  return client.send(command);
};

const deleteDatabase = (databaseName) => {
  const client = new GlueClient({});

  const command = new DeleteDatabaseCommand({
    Name: databaseName,
  });

  return client.send(command);
};

const deleteCrawler = (crawlerName) => {
  const client = new GlueClient({});

  const command = new DeleteCrawlerCommand({
    Name: crawlerName,
  });

  return client.send(command);
};

/**
 *
 * @param {import('../../../actions/delete-job.js').deleteJob} deleteJobFn
 * @param {string[]} jobNames
 * @param {{ prompter: { prompt: () => Promise<any> }}} context
 */
const handleDeleteJobs = async (deleteJobFn, jobNames, context) => {
  /**
   * @type {{ selectedJobNames: string[] }}
   */
  const { selectedJobNames } = await context.prompter.prompt({
    name: "selectedJobNames",
    type: "checkbox",
    message: "Let's clean up jobs. Select jobs to delete.",
    choices: jobNames,
  });

  if (selectedJobNames.length === 0) {
    log("No jobs selected.");
  } else {
    log("Deleting jobs.");
    await Promise.all(
      selectedJobNames.map((n) => deleteJobFn(n).catch(console.error)),
    );
    log("Jobs deleted.", { type: "success" });
  }
};

/**
 * @param {{
 *   listJobs: import('../../../actions/list-jobs.js').listJobs,
 *   deleteJob: import('../../../actions/delete-job.js').deleteJob
 * }} config
 */
const makeCleanUpJobsStep =
  ({ listJobs, deleteJob }) =>
  async (context) => {
    const { JobNames } = await listJobs();
    if (JobNames.length > 0) {
      await handleDeleteJobs(deleteJob, JobNames, context);
    }

    return { ...context };
  };

/**
 * @param {import('../../../actions/delete-table.js').deleteTable} deleteTable
 * @param {string} databaseName
 * @param {string[]} tableNames
 */
const deleteTables = (deleteTable, databaseName, tableNames) =>
  Promise.all(
    tableNames.map((tableName) =>
      deleteTable(databaseName, tableName).catch(console.error),
    ),
  );

/**
 * @param {{
 *  getTables: import('../../../actions/get-tables.js').getTables,
 *  deleteTable: import('../../../actions/delete-table.js').deleteTable
 * }} config
 */
const makeCleanUpTablesStep =
  ({ getTables, deleteTable }) =>
  /**
   * @param {{ prompter: { prompt: () => Promise<any>}}} context
   */
  async (context) => {
    const { TableList } = await getTables(process.env.DATABASE_NAME).catch(
      () => ({ TableList: null }),
    );

    if (TableList && TableList.length > 0) {
      /**
       * @type {{ tableNames: string[] }}
       */
      const { tableNames } = await context.prompter.prompt({
        name: "tableNames",
        type: "checkbox",
        message: "Let's clean up tables. Select tables to delete.",
        choices: TableList.map((t) => t.Name),
      });

      if (tableNames.length === 0) {
        log("No tables selected.");
      } else {
        log("Deleting tables.");
        await deleteTables(deleteTable, process.env.DATABASE_NAME, tableNames);
        log("Tables deleted.", { type: "success" });
      }
    }

    return { ...context };
  };

/**
 * @param {import('../../../actions/delete-database.js').deleteDatabase} deleteDatabase
 * @param {string[]} databaseNames
 */
const deleteDatabases = (deleteDatabase, databaseNames) =>
  Promise.all(
    databaseNames.map((dbName) => deleteDatabase(dbName).catch(console.error)),
  );

/**
 * @param {{
 *   getDatabases: import('../../../actions/get-databases.js').getDatabases
 *   deleteDatabase: import('../../../actions/delete-database.js').deleteDatabase
 * }} config
 */
const makeCleanUpDatabasesStep =
  ({ getDatabases, deleteDatabase }) =>
  /**
   * @param {{ prompter: { prompt: () => Promise<any>}} context
   */
  async (context) => {
    const { DatabaseList } = await getDatabases();

    if (DatabaseList.length > 0) {
      /** @type {{ dbNames: string[] }} */
      const { dbNames } = await context.prompter.prompt({
        name: "dbNames",
        type: "checkbox",
        message: "Let's clean up databases. Select databases to delete.",
        choices: DatabaseList.map((db) => db.Name),
      });

      if (dbNames.length === 0) {
        log("No databases selected.");
      } else {
        log("Deleting databases.");
        await deleteDatabases(deleteDatabase, dbNames);
        log("Databases deleted.", { type: "success" });
      }
    }

    return { ...context };
  };

const cleanUpCrawlerStep = async (context) => {
  log("Deleting crawler.");

  try {
    await deleteCrawler(process.env.CRAWLER_NAME);
    log("Crawler deleted.", { type: "success" });
  } catch (err) {
    if (err.name === "EntityNotFoundException") {
      log("Crawler is already deleted.");
    } else {
      throw err;
    }
  }

  return { ...context };
};

const createCrawler = (name, role, dbName, tablePrefix, s3TargetPath) => {
  const client = new GlueClient({});

  const command = new CreateCrawlerCommand({
    Name: name,
    Role: role,
    DatabaseName: dbName,
    TablePrefix: tablePrefix,
    Targets: {
      S3Targets: [{ Path: s3TargetPath }],
    },
  });

  return client.send(command);
};

const createJob = (name, role, scriptBucketName, scriptKey) => {
  const client = new GlueClient({});

  const command = new CreateJobCommand({
    Name: name,
    Role: role,
    Command: {
      Name: "glueetl",
      PythonVersion: "3",
      ScriptLocation: `s3://${scriptBucketName}/${scriptKey}`,
    },
    GlueVersion: "3.0",
  });

  return client.send(command);
};

const deleteCrawler = (crawlerName) => {
  const client = new GlueClient({});

  const command = new DeleteCrawlerCommand({
    Name: crawlerName,
  });

  return client.send(command);
};

const deleteDatabase = (databaseName) => {
  const client = new GlueClient({});

  const command = new DeleteDatabaseCommand({
    Name: databaseName,
  });

  return client.send(command);
};

const deleteJob = (jobName) => {
  const client = new GlueClient({});

  const command = new DeleteJobCommand({
    JobName: jobName,
  });

  return client.send(command);
};

const deleteTable = (databaseName, tableName) => {
  const client = new GlueClient({});

  const command = new DeleteTableCommand({
    DatabaseName: databaseName,
    Name: tableName,
  });

  return client.send(command);
};

const getCrawler = (name) => {
  const client = new GlueClient({});

  const command = new GetCrawlerCommand({
    Name: name,
  });

  return client.send(command);
};

const getDatabase = (name) => {
  const client = new GlueClient({});

  const command = new GetDatabaseCommand({
    Name: name,
  });

  return client.send(command);
};

const getDatabases = () => {
  const client = new GlueClient({});

  const command = new GetDatabasesCommand({});

  return client.send(command);
};

const getJob = (jobName) => {
  const client = new GlueClient({});

  const command = new GetJobCommand({
    JobName: jobName,
  });

  return client.send(command);
};

const getJobRun = (jobName, jobRunId) => {
  const client = new GlueClient({});
  const command = new GetJobRunCommand({
    JobName: jobName,
    RunId: jobRunId,
  });

  return client.send(command);
};

const getJobRuns = (jobName) => {
  const client = new GlueClient({});
  const command = new GetJobRunsCommand({
    JobName: jobName,
  });

  return client.send(command);
};

const getTables = (databaseName) => {
  const client = new GlueClient({});

  const command = new GetTablesCommand({
    DatabaseName: databaseName,
  });

  return client.send(command);
};

const listJobs = () => {
  const client = new GlueClient({});

  const command = new ListJobsCommand({});

  return client.send(command);
};

const startCrawler = (name) => {
  const client = new GlueClient({});

  const command = new StartCrawlerCommand({
    Name: name,
  });

  return client.send(command);
};

const startJobRun = (jobName, dbName, tableName, bucketName) => {
  const client = new GlueClient({});

  const command = new StartJobRunCommand({
    JobName: jobName,
    Arguments: {
      "--input_database": dbName,
      "--input_table": tableName,
      "--output_bucket_url": `s3://${bucketName}/`,
    },
  });

  return client.send(command);
};