first commit

.gitignore

@@ -0,0 +1,3 @@
+node_modules
+.env
+databases.txt

README.md

@@ -0,0 +1,42 @@
+# Database S3 backups
+This script provides a simple and automated way to back up your essential databases to AWS S3, ensuring that your data is always safe and retrievable.
+
+The script provides the capability to initiate backups either upon its startup or on a scheduled basis using Cron expressions. Backups are compressed to reduce file size.
+
+## How it works 
+1. Define database connection URI strings for each database you want backed up and the backup schedule 
+2. The script will connect to the database(s) and do a dump
+3. The dump is compressed and uploaded to your defined AWS S3 Bucket
+4. Finally, the dumps are cleaned up on the local file system
+
+Supported databases:
+- `postgres`
+- `mysql`
+- `mongodb`.
+
+## Configuration
+Create a `.env` file in the root directory with the following variables:
+
+```
+RUN_ON_STARTUP=true
+CRON=0 0 * * *
+AWS_ACCESS_KEY_ID=<ACCESS_KEY_ID>
+AWS_SECRET_ACCESS_KEY=<SECRET_ACCESS_KEY>
+AWS_S3_BUCKET=<S3_BUCKET>
+AWS_S3_REGION=<S3_REGION>
+AWS_S3_ENDPOINT=<S3_ENDPOINT>
+DATABASES="mysql://user:password@host:port/database,postgresql://user:password@host:port/database,mongodb://user:password@host:port"
+```
+
+### Environment variables
+
+| Key                     | Description              | Optional | Default Value |
+|-------------------------|--------------------------|----------|---------------|
+| `DATABASES`             | Comma-separated string list of database URIs that should be backed up. | No | `[]`|
+| `RUN_ON_STARTUP`        | Boolean value that indicates if the script should run immediately on startup. | Yes | `false` |
+| `CRON`                  | Cron expression for scheduling when the backup job will run for all databases. See [Crontab.guru](https://crontab.guru/) for help setting up schedules. | Yes | |
+| `AWS_ACCESS_KEY_ID`     | [AWS access key ID](https://docs.aws.amazon.com/general/latest/gr/aws-sec-cred-types.html#access-keys-and-secret-access-keys). | No | |
+| `AWS_SECRET_ACCESS_KEY` | [AWS secret access key](https://docs.aws.amazon.com/general/latest/gr/aws-sec-cred-types.html#access-keys-and-secret-access-keys). | No | |
+| `AWS_S3_BUCKET`         | [Name of the S3 bucket](https://docs.aws.amazon.com/AmazonS3/latest/dev/Welcome.html). | No | |
+| `AWS_S3_REGION`         | [Region of the S3 bucket](https://docs.aws.amazon.com/general/latest/gr/rande.html). | No | |
+| `AWS_S3_ENDPOINT`       | [Endpoint for the S3 service](https://docs.aws.amazon.com/general/latest/gr/s3.html). | No | |

index.js

@@ -0,0 +1,126 @@
+require('dotenv').config();
+const util = require('util');
+const exec = util.promisify(require('child_process').exec);
+const s3 = require("@aws-sdk/client-s3");
+const fs = require('fs');
+const cron = require("cron");
+
+function loadConfig() {
+  const requiredEnvars = [
+    'AWS_ACCESS_KEY_ID',
+    'AWS_SECRET_ACCESS_KEY',
+    'AWS_S3_REGION',
+    'AWS_S3_ENDPOINT',
+    'AWS_S3_BUCKET'
+  ];
+
+  for (const key of requiredEnvars) {
+    if (!process.env[key]) {
+      throw new Error(`Environment variable ${key} is required`);
+    }
+  }
+
+  return {
+    aws: {
+      accessKeyId: process.env.AWS_ACCESS_KEY_ID,
+      secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY,
+      region: process.env.AWS_S3_REGION,
+      endpoint: process.env.AWS_S3_ENDPOINT,
+      s3_bucket: process.env.AWS_S3_BUCKET
+    },
+    databases: process.env.DATABASES ? process.env.DATABASES.split(",") : [],
+    run_on_startup: process.env.RUN_ON_STARTUP === 'true' ? true : false,
+    cron: process.env.CRON,
+  };
+}
+
+const config = loadConfig();
+
+const s3Client = new s3.S3Client(config.aws);
+
+async function processBackup() {
+  if (config.databases.length === 0) {
+    console.log("No databases defined.");
+    return;
+  }
+
+  for (const [index, databaseURI] of config.databases.entries()) {
+    const databaseIteration = index + 1;
+    const totalDatabases = config.databases.length;
+
+    const url = new URL(databaseURI);
+    const dbType = url.protocol.slice(0, -1); // remove trailing colon
+    const dbName = url.pathname.substring(1); // extract db name from URL
+    const dbHostname = url.hostname;
+    const dbUser = url.username;
+    const dbPassword = url.password;
+    const dbPort = url.port;
+
+    const date = new Date();
+    const yyyy = date.getFullYear();
+    const mm = String(date.getMonth() + 1).padStart(2, '0');
+    const dd = String(date.getDate()).padStart(2, '0');
+    const hh = String(date.getHours()).padStart(2, '0');
+    const min = String(date.getMinutes()).padStart(2, '0');
+    const ss = String(date.getSeconds()).padStart(2, '0');
+    const timestamp = `${yyyy}-${mm}-${dd}_${hh}:${min}:${ss}`;
+    const filename = `backup-${dbType}-${timestamp}-${dbName}-${dbHostname}.tar.gz`;
+    const filepath = `/tmp/${filename}`;
+
+    console.log(`\n[${databaseIteration}/${totalDatabases}] ${dbType}/${dbName} Backup in progress...`);
+
+    let dumpCommand;
+    switch (dbType) {
+      case 'postgresql':
+        dumpCommand = `pg_dump "${databaseURI}" -F c > "${filepath}.dump"`;
+        break;
+      case 'mongodb':
+        dumpCommand = `mongodump --uri="${databaseURI}" --archive="${filepath}.dump"`;
+        break;
+      case 'mysql':
+        dumpCommand = `mysqldump -u ${dbUser} -p${dbPassword} -h ${dbHostname} -P ${dbPort} ${dbName} > "${filepath}.dump"`;
+        break;
+      default:
+        console.log(`Unknown database type: ${dbType}`);
+        return;
+    }
+
+    try {
+      // 1. Execute the dump command
+      await exec(dumpCommand);
+
+      // 2. Compress the dump file
+      await exec(`tar -czvf ${filepath} ${filepath}.dump`);
+
+      // 3. Read the compressed file
+      const data = fs.readFileSync(filepath);
+
+      // 4. Upload to S3
+      const params = {
+        Bucket: config.aws.s3_bucket,
+        Key: filename,
+        Body: data
+      };
+
+      const putCommand = new s3.PutObjectCommand(params);
+      await s3Client.send(putCommand);
+
+      console.log(`✓ Successfully uploaded db backup for database ${dbType} ${dbName} ${dbHostname}.`);
+    } catch (error) {
+      console.error(`An error occurred while processing the database ${dbType} ${dbName}, host: ${dbHostname}): ${error}`);
+    }
+  }
+}
+
+if (config.cron) {
+  const CronJob = cron.CronJob;
+  const job = new CronJob(config.cron, processBackup);
+  job.start();
+
+  console.log(`Backups configured on Cron job schedule: ${config.cron}`);
+}
+
+if (config.run_on_startup) {
+  console.log("run_on_startup enabled, backing up now...")
+  processBackup();
+}