I'm trying to Stream JSON from MongoDB to S3 with the new version of @aws-sdk/lib-storage:
"@aws-sdk/client-s3": "^3.17.0"
"@aws-sdk/lib-storage": "^3.34.0"
"JSONStream": "^1.3.5",
Try #1: It seems that I'm not using JSONStream.stringify() correctly:
import { MongoClient } from 'mongodb';
import { S3Client } from '@aws-sdk/client-s3';
import { Upload } from '@aws-sdk/lib-storage';
const s3Client = new S3Client({ region: env.AWS_REGION });
export const uploadMongoStreamToS3 = async (connectionString, collectionName) => {
let client;
try {
client = await MongoClient.connect(connectionString);
const db = client.db();
const readStream = db.collection(collectionName).find('{}').limit(5).stream();
readStream.pipe(JSONStream.stringify());
const upload = new Upload({
client: s3Client,
params: {
Bucket: 'test-bucket',
Key: 'extracted-data/benda_mongo.json',
Body: readStream,
},
});
await upload.done();
}
catch (err) {
log.error(err);
throw err.name;
}
finally {
if (client) {
client.close();
}
}
};
Error #1:
TypeError [ERR_INVALID_ARG_TYPE]: The first argument must be one of type string, Buffer, ArrayBuffer, Array, or Array-like Object. Received type object at Function.from (buffer.js:305:9) at getDataReadable (/.../node_modules/@aws-sdk/lib-storage/src/chunks/getDataReadable.ts:6:18) at processTicksAndRejections (internal/process/task_queues.js:94:5) at Object.getChunkStream (/.../node_modules/@aws-sdk/lib-storage/src/chunks/getChunkStream.ts:17:20) at Upload.__doConcurrentUpload (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:121:22) at async Promise.all (index 0) at Upload.__doMultipartUpload (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:196:5) at Upload.done (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:88:12)
Try #2, using the variable jsonStream:
const readStream = db.collection(collectionName).find('{}').limit(5).stream();
const jsonStream = readStream.pipe(JSONStream.stringify());
const upload = new Upload({
client: s3Client,
params: {
Bucket: 'test-bucket',
Key: 'extracted-data/benda_mongo.json',
Body: jsonStream,
},
});
Error #2:
ReferenceError: ReadableStream is not defined at Object.getChunk (/.../node_modules/@aws-sdk/lib-storage/src/chunker.ts:22:30) at Upload.__doMultipartUpload (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:187:24) at Upload.done (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:88:37)
Try #3: use stream.PassThrough:
client = await MongoClient.connect(connectionString);
const db = client.db();
const readStream = db.collection(collectionName).find('{}').limit(5).stream();
readStream.pipe(JSONStream.stringify()).pipe(uploadStreamFile('benda_mongo.json'));
...
const stream = require('stream');
export const uploadStreamFile = async(fileName) => {
try{
const pass = new stream.PassThrough();
const upload = new Upload({
client: s3Client,
params: {
Bucket: 'test-bucket',
Key: 'extracted-data/benda_mongo.json',
Body: pass,
},
});
const res = await upload.done();
log.info('finished uploading file', fileName);
return res;
}
catch(err){
return;
}
};
Error #3:
'dest.on is not a function at Stream.pipe (internal/streams/legacy.js:30:8'
Try #4: mongodb.stream({transform: doc => JSON.stringify...}) instead of JSONStream:
import { S3Client } from '@aws-sdk/client-s3';
import { Upload } from '@aws-sdk/lib-storage';
import { env } from '../../../env';
const s3Client = new S3Client({ region: env.AWS_REGION });
export const uploadMongoStreamToS3 = async (connectionString, collectionName) => {
let client;
try {
client = await MongoClient.connect(connectionString);
const db = client.db();
const readStream = db.collection(collectionName)
.find('{}')
.limit(5)
.stream({ transform: doc => JSON.stringify(doc) + '\n' });
const upload = new Upload({
client: s3Client,
params: {
Bucket: 'test-bucket',
Key: 'extracted-data/benda_mongo.json',
Body: readStream,
},
});
await upload.done();
}
catch (err) {
log.error('waaaaa', err);
throw err.name;
}
finally {
if (client) {
client.close();
}
}
};
Error: #4:
TypeError [ERR_INVALID_ARG_TYPE]: The first argument must be one of type string, Buffer, ArrayBuffer, Array, or Array-like Object. Received type object at Function.from (buffer.js:305:9) at getDataReadable (/.../node_modules/@aws-sdk/lib-storage/src/chunks/getDataReadable.ts:6:18) at processTicksAndRejections (internal/process/task_queues.js:94:5) at Object.getChunkStream (/.../node_modules/@aws-sdk/lib-storage/src/chunks/getChunkStream.ts:17:20) at Upload.__doConcurrentUpload (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:121:22) at async Promise.all (index 0) at Upload.__doMultipartUpload (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:196:5) at Upload.done (/.../node_modules/@aws-sdk/lib-storage/src/Upload.ts:88:12)
Try #5: using stream.PassThrough() and return pass to pipe:
export const uploadMongoStreamToS3 = async (connectionString, collectionName) => {
let client;
try {
client = await MongoClient.connect(connectionString);
const db = client.db();
const readStream = db.collection(collectionName).find('{}').limit(5).stream({ transform: doc => JSON.stringify(doc) + '\n' });
readStream.pipe(uploadStreamFile());
}
catch (err) {
log.error('waaaaa', err);
throw err.name;
}
finally {
if (client) {
client.close();
}
}
};
const stream = require('stream');
export const uploadStreamFile = async() => {
try{
const pass = new stream.PassThrough();
const upload = new Upload({
client: s3Client,
params: {
Bucket: 'test-bucket',
Key: 'extracted-data/benda_mongo.json',
Body: pass,
},
});
await upload.done();
return pass;
}
catch(err){
log.error('pawoooooo', err);
return;
}
};
Error #5:
TypeError: dest.on is not a function at Cursor.pipe (_stream_readable.js:680:8)