synchronous execution of database function in node.js - node.js

There are two collections products and stock in my database.Each product have multipple stock with different supplier and attributes of products.
I have selected the products from products collection and run a loop for each product. I need to append price and offer price from the stock collection to products i have selected already.
I think the for loop compleated its execution before executiong the find method on stock collection.I need to execute everything in the loop in serial manner(not asynchronous). Please check the code below and help me to solve this. I'm new in node.js and mongodb
collection = db.collection('products');
collection.find().toArray(function(err, abc) {
var finalout = [];
for( var listProducts in abc){
var subfinal = {
'_id' :abc[listProducts]['_id'],
'min_price' :abc[listProducts]['value']['price'],
'stock' :abc[listProducts]['value']['stock'],
'name' :abc[listProducts]['value']['name'],
'price' :'',
'offer_price' :'',
};
collection = db.collection('stock');
collection.find({"product":abc[listProducts]['_id'] ,"supplier":abc[listProducts]['value']['def_supplier']}).toArray(function(err, newprod) {
for( var row in newprod){
subfinal['price'] = newprod[row]['price'];
subfinal.offer_price = newprod[row]['offer_price'];
}
finalout.push(subfinal);
});
}
console.log(finalout);
});

Yes, the loop is running and starting the get requests on the database all at the same time. It is possible, like you said, to run them all sequentially, however it's probably not what you're looking for. Doing it this way will take more time, since each request to Mongo would need to wait for the previous one to finish.
Considering that each iteration of the loop doesn't depend on the previous ones, all you're really looking for is a way to know once ALL of the operations are finished. Keep in mind that these can end in any order, not necessarily the order in which they were initiated in the loop.
There's was also an issue in the creation of the subfinal variable. Since the same variable name is being used for all iterations, when they all come back they'll be using the final assignment of the variable (all results will be written on the same subfinal, which will have been pushed multiple times into the result). To fix that, I've wrapped the entire item processing iteration into another function to give each subfinal variable it's own scope.
There are plenty of modules to ease this kind of management, however here is one way to run some code only after all the Mongo calls are finished using a counter and callback that doesn't require any additional installs:
var finished = 0; // incremented every time an iteration is done
var total = Object.keys(abc).length; // number of keys in the hash table
collection = db.collection('products');
collection.find().toArray(function(err, abc) {
var finalout = [];
for( var listProducts in abc){
processItem(listProducts);
}
});
function processItem(listProducts) {
var subfinal = {
'_id' :abc[listProducts]['_id'],
'min_price' :abc[listProducts]['value']['price'],
'stock' :abc[listProducts]['value']['stock'],
'name' :abc[listProducts]['value']['name'],
'price' :'',
'offer_price' :'',
};
collection = db.collection('stock');
collection.find({"product":abc[listProducts]['_id'] ,"supplier":abc[listProducts]['value']['def_supplier']}).toArray(function(err, newprod) {
for( var row in newprod){
subfinal['price'] = newprod[row]['price'];
subfinal.offer_price = newprod[row]['offer_price'];
}
finalout.push(subfinal);
finished++;
if (finished === total) { // if this is the last one to finish.
allFinished(finalout);
}
});
}
function allFinished(finalout) {
console.log(finalout);
}
It could be written more concisely with less variables, but it should be easier to understand this way.

Related

Queries being run twice on sql.js

I'm using SQLite with sql.js on my project and I have been having some trouble with my implementation. Seems like the queries are being run on the database twice because for the for the INSERT statements I get 2 records in the DB.
The way I do it, I create the SQL and then pass it on to this method (the opts variable contains all of the data being put into the database):
prepareStatementAndCompileResults(db, sql, opts){
const stmt = db.prepare(sql);
const result = stmt.getAsObject(opts);
var rows = [];
if(!this.isEmpty(result)){ // isEmpty is a simple method that checks for empty objects
rows.push(result);
}
while(stmt.step()) {
var row = stmt.getAsObject();
rows.push(row);
}
this.saveToFile(db);
stmt.free();
return rows;
},
Here is a sample SQL INSERT that is being run twice
INSERT OR IGNORE INTO tag_event (tag_id, event_id, unique_string)
VALUES (:tag_id,:event_id, :unique);
Here is what the opts variable would look like for this query:
var opts = {
[':tag_id']: 1,
[':event_id']:1,
[':unique']: '1-1'
}
Because you're pushing it into row 2 time.
// if not empty will add to row
if(!this.isEmpty(result)){ // isEmpty is a simple method that checks for empty objects
rows.push(result);
}
// not sure what step() does but I'm assuming this will also run
while(stmt.step()) {
var row = stmt.getAsObject();
rows.push(row);
}
Verify by using a debugger or just console.log(rows) after the while loop before the save
So, what it turns out I needed to do was bind the variables to the prepared statement before getting the rather than binding them through getAsObject. This is much more efficient. My API response time on a local test went from 785ms to 14.5ms
prepareStatementAndCompileResults(db, sql, opts){
const rows = [];
const stmt = db.prepare(sql);
stmt.bind(opts);
while(stmt.step()) {
var row = stmt.getAsObject();
rows.push(row);
}
this.saveToFile(db);
stmt.free();
return rows;
},

How to bind data to html in angular 2/4 by using thread or async

I have a Component, which have child component. at ngOnInit() I'm calling Web API and get list of data.
Initial point length of the list is 10, But it will have more.
Need to execute some method (task|process|job) in background to take rest of the data 10 by 10 in a loop which would run parallel to other task in background no matter what the user is currently doing, which component he/she is interacting with. And execute that method so that it doesn't block others.
What is the correct way to do this?
Seems like a recursive call to me !
firstResults: any[] = []; // First 10 results to show to your user
results: any[] = []; // All results
currentPosition = 0; // The current position of your last result fetched
getData() {
this.myService.getResults().subscribe(results => {
if(!this.firstResults.length) {
this.firstResults = results
}
this.results.push(...results);
this.currentPosition += results.length;
this.getData();
});
}
I don't imagine you're trying to do. But if the list is not so largger, you can get all the data and "paginate" the array
allData:any[];
page:number=0; //page is 0,1,2,3,4....
paginateData:any[]
this.httpClient.get("url").subscribe(res=>{
allData=res;
paginateData=allData.slice(10*this.page,10*(this.page+1));
}

how to check if any of given queries return any result in knex

I have two queries:
a) select id from ingredietns where name = my_param;
b) select word_id from synonyms where name = my_param;
Both return 0 or 1 row. I can also add limit 1 if needed (or in knex first()).
I can translate each into knex like this:
knex("ingredients").select('id').where('name', my_param) //do we need first()?
knex("synonyms").select('word_id').where('name', my_param) //do we need first()?
I need function called "ingredientGetOrCreate(my_param)". This function would
a) check if any of above queries return result
b) if any of these return, then return ingredients.id or synonyms.word_id - only one could be returned
c) if record doesn't eixst in any of tables, I need to do knex inesrt aand return newly added id from function
d) later I am not sure I also understand how to call this newly create function.
Function ingredientGetOrCreate would be used later as seperate function or in the following scenario (like "loop") that doesn't work for me either:
knex("products") // for each product
.select("id", "name")
.map(function (row) {
var descriptionSplitByCommas = row.desc.split(",");
Promise.all(descriptionSplitByCommas
.map(function (my_param) {
// here it comes - call method for each param and do insert
ingredientGetOrCreate(my_param)
.then(function (id_of_ingredient) {
knex('ingredients_products').insert({ id_of_ingredient });
});
...
I am stuck with knex and Promise queries because of asynchronouse part. Any clues, please?
I though I can somehow use Promise.all or Promise.some to call both queries.
P.S. This is my first day with nodejs, Promise and knex.
As far as I decode your question, it consists of two parts:
(1) You need to implement upsert logic (get-or-create logic).
(2) Your get part requires to query not a single table, but a pair of tables in specific order. Table names imply that this is some sort of aliasing engine inside of your application.
Let's start with (2). This could definitely be solved with two queries, just like you sense it.
function pick_name (rows)
{
if (! rows.length) return null
return rows[0].name
}
// you can sequence queries
function ingredient_get (name)
{
return knex('ingredients')
.select('id').where('name', name)
.then(pick_name)
.then(name =>
{
if (name) return name
return knex('synonyms')
.select('word_id').where('name', name)
.then(pick_name)
})
}
// or run em parallel
function ingredient_get (name)
{
var q_ingredients = knex('ingredients')
.select('id').where('name', name)
.then(pick_name)
var q_synonyms = knex('synonyms')
.select('word_id').where('name', name)
.then(pick_name)
return Promise.all([ q_ingredients, q_synonyms ])
.then(([name1, name2]) =>
{
return name1 || name2
})
}
Important notions here:
Both forms works well and return first occurence or JS' null.
First form optimizes count of queries to DB.
Second form optimizes answer time.
However, you can go deeper and use more SQL. There's a special tool for such task called COALESCE. You can consult your SQL documentation, here's COLASCE of PostgreSQL 9. The main idea of COALESCE is to return first non-NULL argument or NULL otherwise. So, you can leverage this to optimize both queries and answer time.
function ingredient_get (name)
{
// preparing but not executing both queries
var q_ingredients = knex('ingredients')
.select('id').where('name', name)
var q_synonyms = knex('synonyms')
.select('word_id').where('name', name)
// put them in COALESCE
return knex.raw('SELECT COALESCE(?, ?) AS name', [ q_ingredients, q_synonyms ])
.then(pick_name)
This solution guarantees single query and furthermore DB engine can optimize execution in any way it sees appropriate.
Now let's solve (1): We now got ingredient_get(name) which returns Promise<string | null>. We can use its output to activate create logic or return our value.
function ingredient_get_or_create (name, data)
{
return ingredient_get(name)
.then(name =>
{
if (name) return name
// …do your insert logic here
return knex('ingredients').insert({ name, ...data })
// guarantee homohenic output across get/create calls:
.then(() => name)
})
}
Now ingredient_get_or_create do your desired upsert logic.
UPD1:
We already got ingredient_get_or_create which returns Promise<name> in any scenario (both get or create).
a) If you need to do any specific logic after that you can just use then:
ingredient_get_or_create(…)
.then(() => knex('another_table').insert(…))
.then(/* another logic after all */)
In promise language that means «do that action (then) if previous was OK (ingredient_get_or_create)». In most of the cases that is what you need.
b) To implement for-loop in promises you got multiple different idioms:
// use some form of parallelism
var qs = [ 'name1', 'name2', 'name3' ]
.map(name =>
{
return ingredient_get_or_create(name, data)
})
var q = Promise.all(qs)
Please, note, that this is an agressive parallelism and you'll get maximum of parallel queries as your input array provides.
If it's not desired, you need to limit parallelism or even run tasks sequentially. Bluebird's Promise.map is a way to run map which analogous to example above but with concurrency option available. Consider the docs for details.
There's also Bluebird's Promise.mapSeries which conceptually is an analogue to for-loop but with promises. It's like map which runs sequentially. Look the docs for details.
Promise.mapSeries([ 'name1', 'name2', 'name3' ],
(name) => ingredient_get_or_create(name, data))
.then(/* logic after all mapSeries are OK */)
I believe the last is what you need.

How to tell if a record exists in Mongo collection (C#)

Given a collection of items { url: 'http://blah' }. How can I tell if a record exists where the url is "http://stackoverflow.com"?
P.s. I am communicating with the c# driver
For any of the previous suggestions to be efficient you should be sure that there is an index on the url element. Otherwise a full collection scan will be required.
If you only expect the answer to be 0 or 1, count is probably the most efficient approach. If you think the count will be very large and all you really care about is whether there is one or more, FindOne is the most efficient approach.
It probably doesn't matter that FindOne returns the whole document unless the document is actually rather large. In that case you could tell the server to only return one field (the _id seems the most likely candidate):
var query = Query.EQ("url", "http://stackoverflow.com");
var fields = Fields.Include("_id");
var res = collection.Find(query).SetFields(fields).SetLimit(1).FirstOrDefault();
if (res == null) {
// no match found
}
you simply need check count of items returned by the query:
int count = collection.FindAs<Item>(Query.EQ("url", "http://stackoverflow.com")).Count();
if(count > 0)
{
//do some stuff
}
IMongoQuery query = Query.EQ("url", "http://stackoverflow.com");
var res = collection.FindOne(query);
if(res == null)//don't exist
{
}
Existence of Key in MongoDB can check by using Exists and second parameter as true or false
var filter = builder.Exists("style", false);
var RetrievedData = collection.Find(filter).ToList()
Refference Link

Select top/latest 10 in couchdb?

How would I execute a query equivalent to "select top 10" in couch db?
For example I have a "schema" like so:
title body modified
and I want to select the last 10 modified documents.
As an added bonus if anyone can come up with a way to do the same only per category. So for:
title category body modified
return a list of latest 10 documents in each category.
I am just wondering if such a query is possible in couchdb.
To get the first 10 documents from your db you can use the limit query option.
E.g. calling
http://localhost:5984/yourdb/_design/design_doc/_view/view_name?limit=10
You get the first 10 documents.
View rows are sorted by the key; adding descending=true in the querystring will reverse their order. You can also emit only the documents you are interested using again the querystring to select the keys you are interested.
So in your view you write your map function like:
function(doc) {
emit([doc.category, doc.modified], doc);
}
And you query it like this:
http://localhost:5984/yourdb/_design/design_doc/_view/view_name?startkey=["youcategory"]&endkey=["youcategory", date_in_the_future]&limit=10&descending=true
here is what you need to do.
Map function
function(doc)
{
if (doc.category)
{
emit(['category', doc.category], doc.modified);
}
}
then you need a list function that groups them, you might be temped to abuse a reduce and do this, but it will probably throw errors because of not reducing fast enough with large sets of data.
function(head, req)
{
% this sort function assumes that modifed is a number
% and it sorts in descending order
function sortCategory(a,b) { b.value - a.value; }
var categories = {};
var category;
var id;
var row;
while (row = getRow())
{
if (!categories[row.key[0]])
{
categories[row.key[0]] = [];
}
categories[row.key[0]].push(row);
}
for (var cat in categories)
{
categories[cat].sort(sortCategory);
categories[cat] = categories[cat].slice(0,10);
}
send(toJSON(categories));
}
you can get all categories top 10 now with
http://localhost:5984/database/_design/doc/_list/top_ten/by_categories
and get the docs with
http://localhost:5984/database/_design/doc/_list/top_ten/by_categories?include_docs=true
now you can query this with a multiple range POST and limit which categories
curl -X POST http://localhost:5984/database/_design/doc/_list/top_ten/by_categories -d '{"keys":[["category1"],["category2",["category3"]]}'
you could also not hard code the 10 and pass the number in through the req variable.
Here is some more View/List trickery.
slight correction. it was not sorting untill I added the "return" keyword in your sortCategory function. It should be like this:
function sortCategory(a,b) { return b.value - a.value; }

Resources