insertMany inside setTimeout and for loop with async functions - javascript

I'm trying to write the following code and make it work synchronously, but the only problem that it works correctly with console.log, which prints me every item in array with delay in 1 second, but don't work with the following structure:
for (let i = 0; i < array.length; i++) {
setTimeout(function () {
1.http request via rp or request.get (I receive a huge data array)
2. .map results
3.insert to Mongo via mongoose
}
}
as for now I have the following code inside:
request.get({url: array[i].url}), function (error, body) {
body.map(element => {
//do stuff, it works fine
});
collection.insertMany(body, function (err, docs) {
//#justloggerthings
}
Or I have almost the same version with rp instead of request.get
By default I have mongoose.Promise = global.Promise;
Why this cause a problem? Because body.length is very huge dataset which eat a lot of RAM. (Now imagine 20+ arrays with insertMany)
So Mongo trying to insertMany all responses from request at once (when they ready, w/o 1000s delay). Actually that's why I choose request instead of rp (request-promise) but it seems look async too. So should I choose another http get module from npm and switch to it. And not to worry about it?
Or should I wrap this operations to promise || made an async function and recall it inside loop every time (1000s for example) when I it's correctly finished. In this case, the only thing which I found actual on StackOverflow is:
How to insert data to mongo synchronously (Nodejs, Express)
Bit it's a bit outdated. So any ideas?

Well, i dont have your actual code so i will write in pseudo code what you can do.
const chunkArray = (array, chunkSize) => {
let i,j,chunks = [];
for (i = 0, j = array.length; i < j; i += chunkSize) {
chunks.push(array.slice(i, i + chunkSize));
}
return chunks;
}
for (let i = 0; i < array.length; i++) {
let bigArray = await request('your data url');
// do some mapping or whatever
// then break your large array into smaller chunks
let chunks = chunkArray(bigArray, 10);
let j;
for (j = 0; j < chunks.length; j++) {
await collection.insertMany(chunks[j]);
}
}

Actual code that solve my problem is:
async function test (name, url, lastModified) {
try {
const response = await rp({uri: url, json: true});
response.map(async (element) => {
if (element.buyout > 0) {
element.price = (element.buyout / element.quantity);
}
element.lastModified = lastModified
});
return collection.insertMany(response);
} catch (err) {
console.error(err)
}
}
async function addAsync() {
const z = await test();
console.log(z);
}
addAsync();

Related

Why promise.all crash an error but not sending promises one by one?

I'm pretty new here and I have a problem on my backend nodejs.
I have a list of object that will help me find a car in the database, and so I prepare promises to get data one by one and send that inside a promise.all to trigger the promises.
the function getCar is working every time with data I sent but When I do the promise.all with the array then it will have an error of pool of connection. What is the probleme ?
function requestData (listOfCar) {
const promiseList = [];
for (let i = 0; i < listOfCar.length; i++) {
promiseList.push(getCar(listOfCar[i]));
}
return Promise.all(promiseList); // crash but sending promises one by one is working
}
function getCar(carFinder) {
// do things and return a query find in sequelize to find a car
// and so it return a promise
}
Promise are always directly trigger, they do not wait to be trigger inside the promise.all.
So your problem is that you are sending I guess way to many request inside the database and so the pool of connection do not accept it anymore
To fix that you can add more pool of connection or you can simply trigger promise little chunk of 5 and await the promise.all
async function requestData (listOfCar) {
const carLists = [];
for (let i = 0; i < listOfCar.length; i++) {
const tmpListOfPromise = [];
for (let j = 0; j < 5 && i < listOfCar; j++) {
const tmpListOfPromise.push(getCar(listOfCar[i]));
i = i + 1;
}
await Promise.all(tmpListOfPromise).then((response) => {
carLists = carLists.concat(response); // this will push every response in the list
});
}
}
function getCar(carFinder) {
// do things and return a query find in sequelize to find a car
// and so it return a promise
}

How to make an API call inside for loop, withour using async await

Having a for loop inside a promise. How can i get response from getData API without using async await. The parameters used inside getData are coming from for loop.
var res = EService.webApi.get.GetActiveData(formModel.project.EID);
res.then(
async function (result) {
//success
var data = result.data;
var eList= data.BodyData;
var jList= [];
for (var i = 0; i < eList.length; i++) {
let entity = await getData(eList[i].EntityID);
if (eList[i].typeID !== 16) {
jList.push({
Name: eList[i].Name + " - " + e[i].typeName + " - " + entity.Name,
EID: eList[i].EntityID,
model: eList[i],
});
}
}
}
If I understand what you're asking, it sounds like you want to invoke all of the async requests right away but have each one await its result, rather than invoking them in serial where each one awaits the previous operation. Maybe something like this:
for (var i = 0; i < eList.length; i++) {
(async (j) => {
// The rest of your logic, but using the passed `j` instead of `i`
})(i);
}
The anonymous async function isn't awaited, but internally each call to that function can await the call to getData to use its result.
Though if you want to do something with jList or any other result/side-effect afterward then you'd need to await the whole thing. Maybe put all of the promises into an array and await the array. Perhaps something like:
let promises = [];
for (var i = 0; i < eList.length; i++) {
promises.push((async (j) => {
// The rest of your logic, but using the passed `j` instead of `i`
})(i));
}
Promise.all(promises).then(() => ...);
The overall goal being that all of the operations run in parallel, rather than in serial like in the original loop.

Javascript await inside a loop

I am trying to work with an api where I have to send a request for each item in a list.
However, I see that the loop doesn't seem to wait for every request, i.e, the loop doesn't work as expected. Here's the code below
getInfo = async () => {
const mylist = ["item1","item2","item3","item4","item5","item6","item7"]
const responses = []
const len = mylist.length
for (let i = 0; i < len; i++) {
//console.log("inside loop")
await axios.get("some_url/"+mylist[i])
.then(res => {
responses.push(res.data)
})
}
When I run the program, all the console.log("inside loop") executes immediately without waiting for the request to be complete.
How can I modify the code so as to wait for each response to be completed before updating the for loop counter variable?
You could try re-arranging the code to something like this. But using a Promise.all with Array.prototype.map would be more idiomatic solution for the problem.
await the async call (remove unnecessary .then call) and then console.log
getInfo = async () => {
const mylist = ["item1","item2","item3","item4","item5","item6","item7"]
const responses = []
const len = mylist.length
for (let i = 0; i < len; i++) {
responses.push((await axios.get("some_url/"+mylist[i])).data)
console.log("inside loop")
}
}
Internally, await is translated into a Promise chain. Since the for loop can't be transformed into a Promise-continuation, you'll need to convert it to a Promise-based construct.
Depending on what you want to achieve there are multiple ways to go about it.
Constructing the responses array could be done with a map statement.
const promises = mylist.map(item => {
return axios.get("some_url/"+item).then(res => { return res.data; })
});
const data = await Promise.all(promises);
No manual pushing items around or fiddling with the array length.

Making a fetch call within a nested for loop

I'm currently converting my local function into a lambda function and am running into a few hardships. In a previous method, I get an array of url fragments that I have to string along programmatically to a prefix to get the data back.
Logically, I figure the best way of doing this is to do a nested for loop. Go through the series of prefixes adding the url fragment and doing the fetch call.
It works fine in local, but lambda throws errors.
function getVariantData(data, cb) {
for (var i = 0; i < chapters.length; i++) {
let source = chapters[i];
// chapters = url prefix
data.forEach(async element => {
let res = await fetch(chapters[i] + element);
//element = url fragment
let body = await res.text();
createVariantsFile(element, source, body, cb);
});
}
}
this code runs fine but i've learned that lambdas are a bit more strict with forEach and async/awaits so I've changed my code to this and I've been dealing with a mess of issues. I havent gone past writing console.log because...well I haven't gotten past the error.
async function getVariantData(data, cb) {
for (var i = 0; i < chapters.length; i++) {
let source = chapters[i];
const promises = data.map((datum, index) => fetch(source+datum))
const chapterData = await Promise.all(promises)
console.log(chapterData)
// await data.map(async element => {
// return await (chapters[i] + element);
// createVariantsFile(element, source, body, cb);
// });
}
}

How to handle async Node.js in a loop

I have such a loop :
var i,j,temparray,chunk = 200;
for (i=0,j=document.mainarray.length; i<j; i+=chunk) {
temparray = document.mainarray.slice(i,i+chunk);
var docs = collection.find({ id: { "$in": temparray}}).toArray();
docs.then(function(singleDoc)
{
if(singleDoc)
{
console.log("single doc length : " + singleDoc.length);
var t;
for(t = 0, len = singleDoc.length; t < len;t++)
{
fs.appendFile("C:/Users/x/Desktop/names.txt", singleDoc[t].name + "\n", function(err) {
if(err) {
return console.log(err);
}
});
}
}
});
}
The loop iterates for two times. In first iteration it gets 200 elements, in second, it gets 130 elements. And when I open the .txt file, I see only 130 names. I guess because of the async nature of Node.js, only second part of the array is processed. What should I do to get all parts of the array to be processed? Thanks in advance.
EDIT : I finally turned the code to this :
var generalArr = [];
var i,j,temparray,chunk = 200;
for (i=0,j=document.mainarray.length; i<j; i+=chunk) {
temparray = document.mainarray.slice(i,i+chunk);
generalArr.push(temparray);
}
async.each(generalArr, function(item, callback)
{
var docs = collection.find({ id: { "$in": item}}).toArray();
docs.then(function(singleDoc)
{
if(singleDoc)
{
console.log("single doc length : " + singleDoc.length);
var t;
for(t = 0, len = singleDoc.length; t < len;t++)
{
fs.appendFile("C:/Users/x/Desktop/names.txt", singleDoc[t].name + "\n", function(err) {
if(err) {
return console.log(err);
}
});
}
}
});
callback(null);
})
When I change this line :
var docs = collection.find({ id: { "$in": item}}).toArray();
To this line :
var docs = collection.find({ id: { "$in": item}}).project({ name: 1 }).toArray();
It works, I'm able to print all names. I guess there is a problem with memory when I try without .project(). How can I make this work without using project? Should I change some memory limits? Thanks in advance.
I think your code is unnecessary complicated and appending file in a loop is very expensive when compared to in-memory computation. A better way would be to write to file just once.
var i, j, temparray, chunk = 200;
for (i = 0, j = document.mainarray.length; i < j; i += chunk) {
temparray = document.mainarray.slice(i, i + chunk);
generalArr.push(temparray);
}
const queryPromises = [];
generalArr.forEach((item, index) => {
queryPromises.push(collection.find({ id: { "$in": item } }).toArray());
});
let stringToWrite = '';
Promise.all(queryPromises).then((result) => {
result.forEach((item) => {
item.forEach((element) => {
//create a single string which you want to write
stringToWrite = stringToWrite + "\n" + element.name;
});
});
fs.appendFile("C:/Users/x/Desktop/names.txt", stringToWrite, function (err) {
if (err) {
return console.log(err);
} else {
// call your callback or return
}
});
});
In the code above, I do the following.
Wait for all the db queries to finish
Lets iterate over this list and create one string that we need to write to the file
Write to the file
Once you go asynchronous you cannot go back - all your code needs to be asynchronous. In node 8 you handle this with async and await keywords. In older versions you can use Promise - async/await are just syntax sugar for it anyway.
However, most of the API in node are older than Promise, and so they use callbacks instead. There is a promisify function to update callback functions to promises.
There are two ways to handle this, you can let all the asynchronous actions happen at the same time, or you can chain them one after another (which preserves order but takes longer).
So, collection.find is asynchronous, it either takes a callback function or returns a Promise. I'm going to assume that the API you're using does the latter, but your problem could be the former (in which case look up promisify).
var findPromise = collection.find({ id: { "$in": item}});
Now, at this point findPromise holds the running find action. We say this is a promise that resolves (completes successfully) or rejects (throws an error). We want to queue up an action to do once it completes, and we do that with then:
// The result of collection.find is the collection of matches
findPromise.then(function(docs) {
// Any code we run here happens asynchronously
});
// Code here will run first
Inside the promise we can return further promises (allowing them to be chained - complete one async, then complete the next, then fire the final resolve once all done) or use Promise.all to let them all happen in parallel and resolve once done:
var p = new Promise(function(resolve, reject) {
var findPromise = collection.find({ id: { "$in": item}});
findPromise.then(function(docs) {
var singleDocNames = [];
for(var i = 0; i < docs.length; i++) {
var singleDoc = docs[i];
if(!singleDoc)
continue;
for(var t = 0; t < singleDoc.length; t++)
singleDocNames.push(singleDoc[t].name);
}
// Resolve the outer promise with the final result
resolve(singleDocNames);
});
});
// When the promise finishes log it to the console
p.then(console.log);
// Code inline here will fire before the promise
This is much easier in node 8 with async/await:
async function p() {
// Await puts the rest of this function in the .then() of the promise
const docs = await collection.find({ id: { "$in": item}});
const singleDocNames = [];
for(var i = 0; i < docs.length; i++) {
// ... synchronous code unchanged ...
}
// Resolve the outer promise with the final result
return singleDocNames;
});
// async functions can be treated like promises
p().then(console.log);
If you need to write the results to a text file asynchronously there are a couple of ways to do it - you can wait until the end and write all of them, or chain a promise to write them after each find, though I find parallel IO operations tend to be at more risk of deadlocks.
Code above have multiple issues about asynchronous control flow. Similar code possible can exists, but only if case of using ES7 async/await operators on all async operation.
Of course, you can easily achieve solution by promises sequence. Solution:
let flowPromise = Promise.resolve();
const chunk = 200;
for (let i=0,j=document.mainarray.length; i<j; i+=chunk) {
flowPromise = flowPromise.then(() => {
const temparray = document.mainarray.slice(i,i+chunk);
const docs = collection.find({ id: { "$in": temparray}}).toArray();
return docs.then((singleDoc) => {
let innerFlowPromise = Promise.resolve();
if(singleDoc) {
console.log("single doc length : " + singleDoc.length);
for(let t = 0, len = singleDoc.length; t < len;t++) {
innerFlowPromise = innerFlowPromise.then(() => new Promise((resolve, reject) =>
fs.appendFile(
"C:/Users/x/Desktop/names.txt", singleDoc[t].name + "\n",
err => (err ? reject(err) : resolve())
)
));
}
}
return innerFlowPromise;
}
});
}
flowPromise.then(() => {
console.log('Done');
}).catch((err) => {
console.log('Error: ', err);
})
When use async-like control flow, based on Promises, always remember that every loop and function call sequence will not pause execution till async operation be done, so include all then sequences manually. Or use async/await syntax.
Which version of nodejs are you using? You should use the native async/await support which is built into newer versions nodejs (no libraries required). Also note, fs.appendFile is asyncronous so you need to either use a library like promisify to transform the callback into a promise or just use the appendFileSync and suffer the blocking IO (but might be okay for you, depending on the use case.)
async function(){
...
for(var item of generalArr) {
var singleDoc = await collection.find({ id: { "$in": item}}).toArray();
// if(singleDoc) { this won't do anything, since collection.find will always return something even if its just an empty array
console.log("single doc length : " + singleDoc.length);
var t;
for(t = 0, len = singleDoc.length; t < len;t++){
fs.appendFileSync("C:/Users/x/Desktop/names.txt", singleDoc[t].name + "\n");
}
};
}
var docs = collection.find({ id: { "$in": document.mainarray}}), // returns a cursor
doc,
names = [],
toInsert;
function saveToFile(cb) {
toInsert = names.splice(0,100);
if(!toInsert.length) return cb();
fs.appendFile("C:/Users/x/Desktop/names.txt", toInsert.join("\n"), cb);
}
(function process() {
if(docs.hasNext()) {
doc = docs.next();
doc.forEach(function(d) {
names.push(d.name);
});
if(names.length === 100) {
// save when we have 100 names in memory and clear the memory
saveToFile(function(err) {
process();
});
} else {
process();
}
} else {
saveToFile(function(){
console.log('All done');
});
}
}()); // invoke the function
If you can't solve your issue using core modules and basic nodejs, there is most likely a lack of understanding of how things work or insufficient knowledge about a library (in this case FileSystem module).
Here is how you can solve your issue, without 3th party libraries and such.
'use strict';
const
fs = require('fs');
let chunk = 200;
// How many rounds of array chunking we expect
let rounds = Math.ceil(mainArray.length/chunk);
// copy to temp (for the counter)
let tempRounds = rounds;
// set file name
let filePath = './names.txt'
// Open writable Stream
let myFileStream = fs.createWriteStream(filePath);
// from round: 0-${rounds}
for (let i = 0; i < rounds; i++) {
// assume array has ${chunk} elements left in this round
let tempChunk = chunk;
// if ${chunk} is to big i.e. i=3 -> chunk = 600 , but mainArray.length = 512
// This way we adjust the last round for "the leftovers"
if (mainArray.length < i*chunk) tempChunk = Math.abs(mainArray.length - i*chunk);
// slice it for this round
let tempArray = mainArray.slice(i*chunk, i*chunk + tempChunk);
// get stuff from DB
let docs = collection.find({ id: { "$in": tempArray}}).toArray();
docs.then(function(singleDoc){
// for each name in the doc
for (let j = 0; j < singleDoc.length; j++) {
// write to stream
myFileStream.write(singleDoc[t].name + "\n");
}
// declare round done (reduce tempRounds) and check if it hits 0
if (!--tempRounds) {
// if all rounds are done, end the stream
myFileStream.end();
// BAM! you done
console.log("Done")
}
});
}
The key is to use fs.WritableStreams :)
link here to docs

Categories

Resources