使用 GitLab CI/CD 和 Terraform 實作 Lambda 以進行 SFTP 整合、Go 中的 S Databricks

透過 Databricks 中的流程自動化降低成本

我的客戶需要降低在 Databricks 上運行的流程的成本。 Databricks 負責的功能之一是從各種 SFTP 收集文件，解壓縮它們並將它們放入資料湖中。

自動化資料工作流程是現代資料工程的重要組成部分。在本文中，我們將探討如何使用 GitLab CI/CD 和 Terraform 建立 AWS Lambda 函數，該函數允許 Go 應用程式連接到 SFTP 伺服器、收集檔案、將其儲存在 Amazon S3 中，並最終在 Databricks 上觸發作業。這種端到端的流程對於依賴高效能資料整合和自動化的系統至關重要。

閱讀本文需要什麼

• 具有專案儲存庫的 GitLab 帳戶。
• 有權建立 Lambda、S3 和 IAM 資源的 AWS 帳戶。
• 具有建立和執行作業權限的 Databricks 帳戶。
• Go、Terraform 和 GitLab CI/CD 的基礎知識。

第 1 步：準備 Go 應用程式

首先建立一個 Go 應用程序，該應用程式將連接到 SFTP 伺服器來收集檔案。使用 github.com/pkg/sftp 等軟體包建立 SFTP 連接，使用 github.com/aws/aws-sdk-go 與 AWS S3 服務互動。

package main

import (
 "fmt"
 "log"
 "os"
 "path/filepath"

 "github.com/pkg/sftp"
 "golang.org/x/crypto/ssh"
 "github.com/aws/aws-sdk-go/aws"
 "github.com/aws/aws-sdk-go/aws/session"
 "github.com/aws/aws-sdk-go/service/s3/s3manager"
)

func main() {
 // Configuração do cliente SFTP
 user := "seu_usuario_sftp"
 pass := "sua_senha_sftp"
 host := "endereco_sftp:22"
 config := &ssh.ClientConfig{
  User: user,
  Auth: []ssh.AuthMethod{
   ssh.Password(pass),
  },
  HostKeyCallback: ssh.InsecureIgnoreHostKey(),
 }

 // Conectar ao servidor SFTP
 conn, err := ssh.Dial("tcp", host, config)
 if err != nil {
  log.Fatal(err)
 }
 client, err := sftp.NewClient(conn)
 if err != nil {
  log.Fatal(err)
 }
 defer client.Close()

 // Baixar arquivos do SFTP
 remoteFilePath := "/path/to/remote/file"
 localDir := "/path/to/local/dir"
 localFilePath := filepath.Join(localDir, filepath.Base(remoteFilePath))
 dstFile, err := os.Create(localFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer dstFile.Close()

 srcFile, err := client.Open(remoteFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer srcFile.Close()

 if _, err := srcFile.WriteTo(dstFile); err != nil {
  log.Fatal(err)
 }

 fmt.Println("Arquivo baixado com sucesso:", localFilePath)

 // Configuração do cliente S3
 sess := session.Must(session.NewSession(&aws.Config{
  Region: aws.String("us-west-2"),
 }))
 uploader := s3manager.NewUploader(sess)

 // Carregar arquivo para o S3
 file, err := os.Open(localFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer file.Close()

 _, err = uploader.Upload(&s3manager.UploadInput{
  Bucket: aws.String("seu-bucket-s3"),
  Key:    aws.String(filepath.Base(localFilePath)),
  Body:   file,
 })
 if err != nil {
  log.Fatal("Falha ao carregar arquivo para o S3:", err)
 }

 fmt.Println("Arquivo carregado com sucesso no S3")
}

步驟 2：配置 Terraform

Terraform 將用於在 AWS 上配置 Lambda 函數和所需資源。使用建立 Lambda 函數、IAM 策略和 S3 儲存桶所需的配置來建立 main.tf 檔案。

provider "aws" {
  region = "us-east-1"
}

resource "aws_iam_role" "lambda_execution_role" {
  name = "lambda_execution_role"

  assume_role_policy = jsonencode({
    Version = "2012-10-17",
    Statement = [
      {
        Action = "sts:AssumeRole",
        Effect = "Allow",
        Principal = {
          Service = "lambda.amazonaws.com"
        },
      },
    ]
  })
}

resource "aws_iam_policy" "lambda_policy" {
  name        = "lambda_policy"
  description = "A policy that allows a lambda function to access S3 and SFTP resources"

  policy = jsonencode({
    Version = "2012-10-17",
    Statement = [
      {
        Action = [
          "s3:ListBucket",
          "s3:GetObject",
          "s3:PutObject",
        ],
        Effect = "Allow",
        Resource = [
          "arn:aws:s3:::seu-bucket-s3",
          "arn:aws:s3:::seu-bucket-s3/*",
        ],
      },
    ]
  })
}

resource "aws_iam_role_policy_attachment" "lambda_policy_attachment" {
  role       = aws_iam_role.lambda_execution_role.name
  policy_arn = aws_iam_policy.lambda_policy.arn
}

resource "aws_lambda_function" "sftp_lambda" {
  function_name = "sftp_lambda_function"

  s3_bucket = "seu-bucket-s3-com-codigo-lambda"
  s3_key    = "sftp-lambda.zip"

  handler = "main"
  runtime = "go1.x"

  role = aws_iam_role.lambda_execution_role.arn

  environment {
    variables = {
      SFTP_HOST     = "endereco_sftp",
      SFTP_USER     = "seu_usuario_sftp",
      SFTP_PASSWORD = "sua_senha_sftp",
      S3_BUCKET     = "seu-bucket-s3",
    }
  }
}

resource "aws_s3_bucket" "s3_bucket" {
  bucket = "seu-bucket-s3"
  acl    = "private"
}

步驟 3：設定 GitLab CI/CD

在 GitLab 中，在 .gitlab-ci.yml 檔案中定義 CI/CD 管道。該管道應包括測試 Go 應用程式的步驟、運行 Terraform 來配置基礎設施以及必要時的清理步驟。

stages:
  - test
  - build
  - deploy

variables:
  S3_BUCKET: "seu-bucket-s3"
  AWS_DEFAULT_REGION: "us-east-1"
  TF_VERSION: "1.0.0"

before_script:
  - 'which ssh-agent || ( apt-get update -y && apt-get install openssh-client -y )'
  - eval $(ssh-agent -s)
  - echo "$PRIVATE_KEY" | tr -d '\r' | ssh-add -
  - mkdir -p ~/.ssh
  - chmod 700 ~/.ssh
  - ssh-keyscan -H 'endereco_sftp' >> ~/.ssh/known_hosts

test:
  stage: test
  image: golang:1.18
  script:
    - go test -v ./...

build:
  stage: build
  image: golang:1.18
  script:
    - go build -o myapp
    - zip -r sftp-lambda.zip myapp
  artifacts:
    paths:
      - sftp-lambda.zip
  only:
    - master

deploy:
  stage: deploy
  image: hashicorp/terraform:$TF_VERSION
  script:
    - terraform init
    - terraform apply -auto-approve
  only:
    - master
  environment:
    name: production

第 4 步：與 Databricks 集成

將檔案上傳到 S3 後，Lambda 函數必須觸發 Databricks 中的作業。這可以使用 Databricks API 啟動現有作業來完成。

package main

import (
 "bytes"
 "encoding/json"
 "fmt"
 "net/http"
)

// Estrutura para a requisição de iniciar um job no Databricks
type DatabricksJobRequest struct {
 JobID int `json:"job_id"`
}

// Função para acionar um job no Databricks
func triggerDatabricksJob(databricksInstance string, token string, jobID int) error {
 url := fmt.Sprintf("https://%s/api/2.0/jobs/run-now", databricksInstance)
 requestBody, _ := json.Marshal(DatabricksJobRequest{JobID: jobID})
 req, err := http.NewRequest("POST", url, bytes.NewBuffer(requestBody))
 if err != nil {
  return err
 }

 req.Header.Set("Content-Type", "application/json")
 req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", token))

 client := &http.Client{}
 resp, err := client.Do(req)
 if err != nil {
  return err
 }
 defer resp.Body.Close()

 if resp.StatusCode != http.StatusOK {
  return fmt.Errorf("Failed to trigger Databricks job, status code: %d", resp.StatusCode)
 }

 return nil
}

func main() {
 // ... (código existente para conectar ao SFTP e carregar no S3)

 // Substitua pelos seus valores reais
 databricksInstance := "your-databricks-instance"
 databricksToken := "your-databricks-token"
 databricksJobID := 123 // ID do job que você deseja acionar

 // Acionar o job no Databricks após o upload para o S3
 err := triggerDatabricksJob(databricksInstance, databricksToken, databricksJobID)
 if err != nil {
  log.Fatal("Erro ao acionar o job do Databricks:", err)
 }

 fmt.Println("Job do Databricks acionado com sucesso")
}

第 5 步：運行管道

將程式碼推送到 GitLab 儲存庫以供管道運行。檢查所有步驟是否已成功完成，Lambda 函數是否正常運作並與 S3 和 Databricks 正確互動。

一旦您擁有完整的程式碼並配置了 .gitlab-ci.yml 文件，您就可以按照以下步驟運行管道：

• 將您的程式碼推送到 GitLab 儲存庫：

package main

import (
 "fmt"
 "log"
 "os"
 "path/filepath"

 "github.com/pkg/sftp"
 "golang.org/x/crypto/ssh"
 "github.com/aws/aws-sdk-go/aws"
 "github.com/aws/aws-sdk-go/aws/session"
 "github.com/aws/aws-sdk-go/service/s3/s3manager"
)

func main() {
 // Configuração do cliente SFTP
 user := "seu_usuario_sftp"
 pass := "sua_senha_sftp"
 host := "endereco_sftp:22"
 config := &ssh.ClientConfig{
  User: user,
  Auth: []ssh.AuthMethod{
   ssh.Password(pass),
  },
  HostKeyCallback: ssh.InsecureIgnoreHostKey(),
 }

 // Conectar ao servidor SFTP
 conn, err := ssh.Dial("tcp", host, config)
 if err != nil {
  log.Fatal(err)
 }
 client, err := sftp.NewClient(conn)
 if err != nil {
  log.Fatal(err)
 }
 defer client.Close()

 // Baixar arquivos do SFTP
 remoteFilePath := "/path/to/remote/file"
 localDir := "/path/to/local/dir"
 localFilePath := filepath.Join(localDir, filepath.Base(remoteFilePath))
 dstFile, err := os.Create(localFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer dstFile.Close()

 srcFile, err := client.Open(remoteFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer srcFile.Close()

 if _, err := srcFile.WriteTo(dstFile); err != nil {
  log.Fatal(err)
 }

 fmt.Println("Arquivo baixado com sucesso:", localFilePath)

 // Configuração do cliente S3
 sess := session.Must(session.NewSession(&aws.Config{
  Region: aws.String("us-west-2"),
 }))
 uploader := s3manager.NewUploader(sess)

 // Carregar arquivo para o S3
 file, err := os.Open(localFilePath)
 if err != nil {
  log.Fatal(err)
 }
 defer file.Close()

 _, err = uploader.Upload(&s3manager.UploadInput{
  Bucket: aws.String("seu-bucket-s3"),
  Key:    aws.String(filepath.Base(localFilePath)),
  Body:   file,
 })
 if err != nil {
  log.Fatal("Falha ao carregar arquivo para o S3:", err)
 }

 fmt.Println("Arquivo carregado com sucesso no S3")
}

provider "aws" {
  region = "us-east-1"
}

resource "aws_iam_role" "lambda_execution_role" {
  name = "lambda_execution_role"

  assume_role_policy = jsonencode({
    Version = "2012-10-17",
    Statement = [
      {
        Action = "sts:AssumeRole",
        Effect = "Allow",
        Principal = {
          Service = "lambda.amazonaws.com"
        },
      },
    ]
  })
}

resource "aws_iam_policy" "lambda_policy" {
  name        = "lambda_policy"
  description = "A policy that allows a lambda function to access S3 and SFTP resources"

  policy = jsonencode({
    Version = "2012-10-17",
    Statement = [
      {
        Action = [
          "s3:ListBucket",
          "s3:GetObject",
          "s3:PutObject",
        ],
        Effect = "Allow",
        Resource = [
          "arn:aws:s3:::seu-bucket-s3",
          "arn:aws:s3:::seu-bucket-s3/*",
        ],
      },
    ]
  })
}

resource "aws_iam_role_policy_attachment" "lambda_policy_attachment" {
  role       = aws_iam_role.lambda_execution_role.name
  policy_arn = aws_iam_policy.lambda_policy.arn
}

resource "aws_lambda_function" "sftp_lambda" {
  function_name = "sftp_lambda_function"

  s3_bucket = "seu-bucket-s3-com-codigo-lambda"
  s3_key    = "sftp-lambda.zip"

  handler = "main"
  runtime = "go1.x"

  role = aws_iam_role.lambda_execution_role.arn

  environment {
    variables = {
      SFTP_HOST     = "endereco_sftp",
      SFTP_USER     = "seu_usuario_sftp",
      SFTP_PASSWORD = "sua_senha_sftp",
      S3_BUCKET     = "seu-bucket-s3",
    }
  }
}

resource "aws_s3_bucket" "s3_bucket" {
  bucket = "seu-bucket-s3"
  acl    = "private"
}

• GitLab CI/CD 將偵測新的提交並自動啟動管道。
• 透過存取儲存庫的 CI/CD 部分來追蹤 GitLab 中管道的執行。
• 如果所有階段都成功，您的 Lambda 函數將被部署並可供使用。

請記住，您需要在 GitLab CI/CD 中配置環境變數來儲存敏感訊息，例如存取權杖和私鑰。這可以在“設定”>“設定”中完成。 ‘CI/CD’>來自 GitLab 專案的「變數」。

此外，請確保 Databricks 令牌具有觸發作業所需的權限，並且該作業具有提供的 ID。

結論

使用 GitLab CI/CD、Terraform 和 AWS Lambda 等工具可以顯著簡化自動化資料工程任務。透過遵循本文中概述的步驟，您可以創建一個強大的系統，自動執行 SFTP、S3 和 Databricks 之間的資料收集和集成，所有這些都具有 Go 的效率和簡單性。透過這種方法，您將有能力解決以下問題。大規模資料整合的挑戰。

我的聯絡人：

領英 - Airton Lira Junior

iMasters - Airton Lira Junior

aws #lambda #terraform #gitlab #ci_cd #go #databricks #dataengineering #automation

stages:
  - test
  - build
  - deploy

variables:
  S3_BUCKET: "seu-bucket-s3"
  AWS_DEFAULT_REGION: "us-east-1"
  TF_VERSION: "1.0.0"

before_script:
  - 'which ssh-agent || ( apt-get update -y && apt-get install openssh-client -y )'
  - eval $(ssh-agent -s)
  - echo "$PRIVATE_KEY" | tr -d '\r' | ssh-add -
  - mkdir -p ~/.ssh
  - chmod 700 ~/.ssh
  - ssh-keyscan -H 'endereco_sftp' >> ~/.ssh/known_hosts

test:
  stage: test
  image: golang:1.18
  script:
    - go test -v ./...

build:
  stage: build
  image: golang:1.18
  script:
    - go build -o myapp
    - zip -r sftp-lambda.zip myapp
  artifacts:
    paths:
      - sftp-lambda.zip
  only:
    - master

deploy:
  stage: deploy
  image: hashicorp/terraform:$TF_VERSION
  script:
    - terraform init
    - terraform apply -auto-approve
  only:
    - master
  environment:
    name: production

以上是使用 GitLab CI/CD 和 Terraform 實作 Lambda 以進行 SFTP 整合、Go 中的 S Databricks的詳細內容。更多資訊請關注PHP中文網其他相關文章！