I ran across a challenge today. What I want to do is an automatic achievement system for my website. I want to check daily if users meet the requirements to get new achievements. Those requirements would not be stocked in the database, to add new achievements, I want to be able to only define a new javascript object/prototype, something along those lines.
I am working with sails and I don't know if my approach is right. I am making a service with a method "checkForAchievements" and I want it to check for all users and if they meet the requirements for every achievement defined. If they do, I would add a record in my table user_achievement. Here is what I tried so far :
exports.checkForAchievements = function(callback) {
var AchievementsValidator = function(achievement, user) {
this.achievement = achievement;
this.user = user;
this.validation = function() {
return true;
};
this.giveAchievement = function() {
UserAchievement.findOrCreate({ user: this.user, achievement: this.achievement}, { user: this.user, achievement: this.achievement })
.exec(function(err, userAchievment) {});
}
};
//Example badge code, validation returns true if the user has at least 50 posts on the website
var FiftyPosts = function() {
this.validation = function() {
Post.count({ user: this.user }).exec(function(err, count) {
if (count >= 50) {
return true;
}
else {
return false;
}
})
};
};
//Loop in users and execute this code for each
FiftyPosts.prototype = new AchievementsValidator(22, user); // 22 would be the achivement in database
if (FiftyPosts.validation) {
FiftyPosts.giveAchievement();
}
callback();
};
Is it possible to get somewhere with this code? I feel like it would messy because I would need to write down each achivement in my final loop. Also, the code above is not working properly I can't get the validation to execute on the badge.
Note: Performance is not an issue as this code will not run often. I only want this to be scalable, so that I can add new achievements without too much hassle.
Thank you.
EDIT: It seems like the questions weren't clear enough so here you go :
How can I get FiftyPosts.validation to use the right method in the above code? It is not using any of the above (AchievementsValidator, FiftyPosts).
If you know sails.js enough can you tell me if doing this in a service is a good idea?
Related
I am using TranscriptLoggerMiddleware and CosmosDB to log my chatbot transcripts. We are trying to capture the user state information (user name, account number, account type, etc) as top level attributes in the transcript so that specific customers can easily be queried in the DB (if that information is just in the individual timestamp attributes of the document, they can't be queried).
Ideally I would just add the user state when I'm building the file, but I can't figure any way to access it since the logger is defined in index.js and TranscriptLoggerMiddleware only provides the activity to my function, not the full context. If anyone has a way to get the user state data via TranscriptLoggerMiddleware, let me know, that would solve this issue. Here is the customLogger code. Note that due to the function receiving both the user query and bot response, I couldn't get retrieving and resaving the transcript to work, so I'm overwriting the transcript from a local log object. Not trying to come up with a new approach here but if one would solve the overall issue I'd like to hear it.
// Copyright (c) Microsoft Corporation. All rights reserved.
// Licensed under the MIT License.
const { CosmosDbPartitionedStorage } = require('botbuilder-azure');
const path = require('path');
/**
* CustomLogger, takes in an activity and saves it for the duration of the conversation, writing to an emulator compatible transcript file in the transcriptsPath folder.
*/
class CustomLogger {
/**
* Log an activity to the log file.
* #param activity Activity being logged.
*/
// Set up Cosmos Storage
constructor(appInsightsClient) {
this.transcriptStorage = new CosmosDbPartitionedStorage({
cosmosDbEndpoint: process.env.COSMOS_SERVICE_ENDPOINT,
authKey: process.env.COSMOS_AUTH_KEY,
databaseId: process.env.DATABASE,
containerId: 'bot-transcripts'
});
this.conversationLogger = {};
this.appInsightsClient = appInsightsClient;
this.msDelay = 250;
}
async logActivity(activity) {
if (!activity) {
throw new Error('Activity is required.');
}
// Log only if this is type message
if (activity.type === 'message') {
if (activity.attachments) {
try {
var logTextDb = `${activity.from.name}: ${activity.attachments[0].content.text}`;
} catch (err) {
var logTextDb = `${activity.from.name}: ${activity.text}`;
}
} else {
var logTextDb = `${activity.from.name}: ${activity.text}`;
}
if (activity.conversation) {
var id = activity.conversation.id;
if (id.indexOf('|') !== -1) {
id = activity.conversation.id.replace(/\|.*/, '');
}
// Get today's date for datestamp
var currentDate = new Date();
var day = currentDate.getDate();
var month = currentDate.getMonth()+1;
var year = currentDate.getFullYear();
var datestamp = year + '-' + month + '-' + day;
var fileName = `${datestamp}_${id}`;
var timestamp = Math.floor(Date.now()/1);
// CosmosDB logging (JK)
if (!(fileName in this.conversationLogger)) {
this.conversationLogger[fileName] = {};
this.conversationLogger[fileName]['userData'] = {};
this.conversationLogger[fileName]['botName'] = process.env.BOTNAME;
}
this.conversationLogger[fileName][timestamp] = logTextDb;
let updateObj = {
[fileName]:{
...this.conversationLogger[fileName]
}
}
// Add delay to ensure messages logged sequentially
await this.wait(this.msDelay);
try {
let result = await this.transcriptStorage.write(updateObj);
} catch(err) {
console.log(err);
this.appInsightsClient.trackTrace({message: `Logger Error ${err.code} - ${path.basename(__filename)}`,severity: 3,properties: {'botName': process.env.BOTNAME, 'error':err.body}});
}
}
}
}
async wait(milliseconds) {
var start = new Date().getTime();
for (var i = 0; i < 1e7; i++) {
if ((new Date().getTime() - start) > milliseconds) {
break;
}
}
}
}
exports.CustomLogger = CustomLogger;
Not being able to get user state in this function, I decided to try a few other approaches. The most promising was creating a separate "updateTranscript" function to grab the transcript, add user state, and save it back. But I think it was catching it only on user request and getting overidden again by local object on bot response. I added a delay to try to combat this, but it still didn't work. On my very first prompt of providing customer number user state data is getting stored on transcript, but at the next activity it is gone and never comes back (even though I can see it is supposedly getting written to DB). Here is that update function.
const { CosmosDbStorage } = require('botbuilder-azure');
var updateTranscript = async (context, userData, appInsightsClient) => {
const transcriptStorage = new CosmosDbStorage({
serviceEndpoint: process.env.COSMOS_SERVICE_ENDPOINT,
authKey: process.env.COSMOS_AUTH_KEY,
databaseId: process.env.DATABASE,
collectionId: 'bot-transcripts',
partitionKey: process.env.BOTNAME
});
var id = context.activity.conversation.id;
if (id.indexOf('|') !== -1) {
id = context.activity.conversation.id.replace(/\|.*/, '');
}
// Get today's date for datestamp
var currentDate = new Date();
var day = currentDate.getDate();
var month = currentDate.getMonth()+1;
var year = currentDate.getFullYear();
var datestamp = year + '-' + month + '-' + day;
var filename = `${datestamp}_${id}`;
var msDelay = 500;
await new Promise(resolve => setTimeout(resolve, msDelay));
var transcript = await transcriptStorage.read([filename]);
transcript[filename]['userData'] = userData
try {
await transcriptStorage.write(transcript);
console.log('User data added to transcript');
} catch(err) {
console.log(err);
appInsightsClient.trackTrace({message: `Log Updater Error ${err.code} - ${path.basename(__filename)}`,severity: 3,properties: {'botName': process.env.BOTNAME, 'error':err.body}});
}
return;
}
module.exports.updateTranscript = updateTranscript
I realize this approach is a bit of a cluster but I've been unable to find anything better. I know the Microsoft COVID-19 bot has a really nice transcript retrieval function, but I haven't been able to get any input from them on how that was accomplished. That aside, I'm quite happy to continue with this implementation if someone can help me figure out how to get that user state into the transcript without being overwritten or running into concurrency issues.
As to why I can't query an account number even via substring() function, here's an example of the documents data object. I have no idea which string to check for a substring, in this case 122809. I don't know what that timestamp could be. If this is stored at the top level (e.g. userData/accountNumber) I know exactly where to look for the value. For further context, I've displayed what I see after the first prompt for account number, where userData is populated. But it gets overidden on subsequent writes and I can't seem to get it back even with a delay in my updateTranscript function.
"document": {
"userData": {},
"botName": "AveryCreek_OEM_CSC_Bot_QA",
"1594745997562": "AveryCreek_OEM_CSC_Bot_QA: Hi! I'm the OEM CSC Support Bot! Before we get started, can you please provide me with your 6-digit Vista number? If you don't have one, just type \"Skip\".",
"1594746003973": "You: 122809",
"1594746004241": "AveryCreek_OEM_CSC_Bot_QA: Thank you. What can I help you with today? \r\nYou can say **Menu** for a list of common commands, **Help** for chatbot tips, or choose one of the frequent actions below. \r\n \r\n I'm still being tested, so please use our [Feedback Form](https://forms.office.com/Pages/ResponsePage.aspx?id=lVxS1ga5GkO5Jum1G6Q8xHnUJxcBMMdAqVUeyOmrhgBUNFI3VEhMU1laV1YwMUdFTkhYVzcwWk9DMiQlQCN0PWcu) to let us know how well I'm doing and how I can be improved!",
"1594746011384": "You: what is my account number?",
"1594746011652": "AveryCreek_OEM_CSC_Bot_QA: Here is the informaiton I have stored: \n \n**Account Number:** 122809 \n\n I will forget everything except your account number after the end of this conversation.",
"1594746011920": "AveryCreek_OEM_CSC_Bot_QA: I can clear your information if you don't want me to store it or if you want to reneter it. Would you like me to clear your information now?",
"1594746016034": "You: no",
"1594746016301": "AveryCreek_OEM_CSC_Bot_QA: OK, I won't clear your information. You can ask again at any time."
},
"document": {
"userData": {
"accountNumber": "122809"
},
"botName": "AveryCreek_OEM_CSC_Bot_QA",
"1594746019952": "AveryCreek_OEM_CSC_Bot_QA: Hi! I'm the OEM CSC Support Bot! What can I help you with today? \r\nYou can say **Menu** for a list of common commands, **Help** for chatbot tips, or choose one of the frequent actions below. \r\n \r\n I'm still being tested, so please use our [Feedback Form](https://forms.office.com/Pages/ResponsePage.aspx?id=lVxS1ga5GkO5Jum1G6Q8xHnUJxcBMMdAqVUeyOmrhgBUNFI3VEhMU1laV1YwMUdFTkhYVzcwWk9DMiQlQCN0PWcu) to let us know how well I'm doing and how I can be improved!"
},
You had said you were encountering concurrency issues even though JavaScript is single-threaded. As strange as that sounds, I think you're right on some level. TranscriptLoggerMiddleware does have its own buffer that it uses to store activities throughout the turn and then it tries to log all of them all at once. It could easily have provided a way to get that whole buffer in your own logger function, but instead it just loops through the buffer so that you still only get to log them each individually. Also, it allows logActivity to return a promise but it never awaits it, so each activity will get logged "simultaneously" (it's not really simultaneous but the code will likely jump between function calls before waiting for them to complete). This is a problem for any operation that isn't atomic, because you'll be modifying state without knowing about its latest modifications.
while (transcript.length > 0) {
try {
const activity: Activity = transcript.shift();
// If the implementation of this.logger.logActivity() is asynchronous, we don't
// await it as to not block processing of activities.
// Because TranscriptLogger.logActivity() returns void or Promise<void>, we capture
// the result and see if it is a Promise.
const logActivityResult = this.logger.logActivity(activity);
// If this.logger.logActivity() returns a Promise, a catch is added in case there
// is no innate error handling in the method. This catch prevents
// UnhandledPromiseRejectionWarnings from being thrown and prints the error to the
// console.
if (logActivityResult instanceof Promise) {
logActivityResult.catch(err => {
this.transcriptLoggerErrorHandler(err);
});
}
} catch (err) {
this.transcriptLoggerErrorHandler(err);
}
}
All in all, I don't think transcript logger middleware is the way to go here. While it may purport to serve your purposes, there are just too many problems with it. I would either write my own middleware or just put the middleware code directly in my bot logic like this:
async onTurn(turnContext) {
const activity = turnContext.activity;
await this.logActivity(turnContext, activity);
turnContext.onSendActivities(async (ctx, activities, next) => {
for (const activity of activities) {
await this.logActivity(ctx, activity);
}
return await next();
});
// Bot code here
// Save state changes
await this.userState.saveChanges(turnContext);
}
async logActivity(turnContext, activity) {
var transcript = await this.transcriptProperty.get(turnContext, []);
transcript.push(activity);
await this.transcriptProperty.set(turnContext, transcript);
console.log('Activities saved: ' + transcript.length);
}
Since your transcript would be stored in your user state, that user state would also have the account number you need and hopefully you'd be able to query for it.
Kyle's answer did help me solve the issue, and I think that will be the most reusable piece for anyone experiencing similar issues. The key takeaway is that, if you're using nodejs, you should not be using TranscriptLoggerMiddleware and instead use Kyle's function in your onTurn handler (repeated here for reference):
// Function provided by Kyle Delaney
async onTurn(turnContext) {
const activity = turnContext.activity;
await this.logActivity(turnContext, activity);
turnContext.onSendActivities(async (ctx, activities, next) => {
for (const activity of activities) {
await this.logActivity(ctx, activity);
}
return await next();
});
// Bot code here
// Save state changes
await this.userState.saveChanges(turnContext);
}
You need to note, though, that his logActivity function is just storing the raw activities to the user state using a custom transcriptProperty. As of yet I haven't found a good method to give business/admin users access to this data in a way that is easily readable and searchable, nor construct some sort of file out output to send to a customer requesting a transcript of their conversation. As such, I continued using my CustomLogger instead. Here is how I accomplished that.
First, you must create the transcriptLogger in the constructor. If you create it inside your turn handler, you will lose the cache/buffer and it will only have the latest activity instead of the full history. May be common sense but this tripped me up briefly. I do this in the constructor via this.transcriptLogger = new CustomerLogger(appInsightsClient);. I also modified my logActivity function to accept the userData (my state object) as a second, optional parameter. I have successfully been able to use that userData object to add the required customer information to the bot transcript. To modify Kyle's function above you just need to replace this.logActivity with your function call, in my case this.transcriptLogger.logActivity(context, userData);.
While there are still some other issues with this approach, it does solve the title question of how to get user state data into the transcript.
I've followed every step of this walkthrough, but when I try to create a new row, I get a 403:
code: 119
message: "This user is not allowed to perform the create
operation on Messages. You can change this setting in the Data Browser."
My code:
Messages = Parse.Object.extend("Messages")
var message = new Messages();
message.set("sender", Parse.User.current());
message.set("receiver", *anotherUser*);
message.set("subject", "foo")
message.set("body", "bar")
message.save()
.then(
function(message){
console.log("success!")
},function(error){
console.log("error: ", error);
});
My CLPs are set as follows:
It looks like someone else posted the same issue in a google group. What are we missing?
I've submitted this as a bug to Parse (Facebook), and they replied:
We have managed to reproduce this issue and it appears to be a valid bug. We are assigning this to the appropriate team.
I will update this answer once the issue has been resolved. If this issue is impacting you, please subscribe to the bug, as this will help prioritize the fix.
UPDATE
Facebook replied:
Turns out that this is actually by design. To create an object, the class should have public create permissions on it
Unfortunately, with this solution, I can create a message "from" any other user (another user set as the sender). This is unacceptable and unusable IMHO.
That has been a bug since the launch of Pointer Permissions, which effectively makes them useless. My impression is they built this with the idea of letting developers secure existing schemas in one go, but of course you need it to work for future creation.
One workaround would involve combining the older Class Level Permissions and per-row ACL's while being careful to not disable your Data Browser. Let's assume you have classes "Puppy" and "Cat" and both have a field called "owner".
In your Data Browser, for each class where it makes sense to have an owner field, you set its Class Level Permissions for Puppy and Cat each to:
Public - Read: Yes or No, depends on your use case, Write: Yes
Add a Pointer Permission for "owner" - Read: Yes, Write: Yes (can skip this for now, see below)
Then in your cloud/main.js, you can use the following as a starting point (which I often call "types" below, sorry).
When Parse fixes the creation issue, you remove the Public Write Class Level permission (above), leave the Pointer Permission one, and get rid of the workaround code below.
--
var validateAndUpdateOwnerWritePerms = function(request){
var object = request.object;
var error = null;
var owner = object.get('owner');
if (!Parse.User.current()) {
error = 'User session required to create or modify object.';
} else if (!owner) {
error = 'Owner expected, but not found.';
} else if (owner && owner.id != Parse.User.current().id && !object.existed()) {
error = 'User session must match the owner field in the new object.';
}
if (request.master) {
error = null;
}
if (error) {
return error;
}
if (object.existed()) {
return null;
}
var acl = new Parse.ACL();
acl.setReadAccess(owner, true);
acl.setWriteAccess(owner, true);
object.setACL(acl);
return null;
}
// Wrapper that makes beforeSave, beforeDelete, etc. respect master-key calls.
// If you use one of those hooks directly, your tests or admin
// console may not work.
var adminWriteHook = function(cloudHook, dataType, callback) {
cloudHook(dataType, function(request, response) {
if (request.master) {
Parse.Cloud.useMasterKey();
} else {
var noUserAllowed = false;
if (cloudHook == Parse.Cloud.beforeSave &&
(dataType == Parse.Installation || dataType == Parse.User)) {
noUserAllowed = true;
}
if (!noUserAllowed && !Parse.User.current()) {
response.error('Neither user session, nor master key was found.');
return null;
}
}
return callback(request, response);
});
};
// Set hooks for permission checks to run on delete and save.
var beforeOwnedTypeWriteHook = function(type) {
var callback = function (request, response) {
var error = validateAndUpdateOwnerWritePerms(request);
if (error) {
response.error(error);
return;
}
response.success();
};
return adminWriteHook(Parse.Cloud.beforeSave, type, callback);
return adminWriteHook(Parse.Cloud.beforeDelete, type, callback);
};
beforeOwnedTypeWriteHook('Puppy');
beforeOwnedTypeWriteHook('Cat');
Unfortunately it seems that Parse Pointer Permissions do not work as you expect it on Create. The quick fix would be to allow Create permission to Public. Then to ensure that the user who is creating a record is the same as the sender. So you need to perform a manual check in the beforeSave trigger for Messages class in cloud code and if that check fails, reject the record being created.
UPDATE: In a nutshell, I would like to use the Master key, because I need to write an other user object with my current user, but I don't want to override all security, I just wanna use it in one function. The accepted answer in this question gave a very nice starting point, however I couldn't make it to work. It's the last code block in this question.
I have two separated functions. The first is pure objective-c, it deletes users from the currentUser's firstRelation. It worked well without any problems until i added a different CloudCode function into a different view controller. The CloudCode function uses the master key and adds currentUser to otherUser's sampleRelation & adds otherUser to currentUser's sampleRelation (firstRelation and sampleRelation is two different column inside the User class).
So the problem is when I delete a user from currentUser's firstRelation (with current user) my app crashes, because the user must be authenticated via logIn or signUp. Actually i don't understand this, because in this case I'm writing the currentUser with the currentUser instead of another user, so it must work without any problems (and worked before the CloudCode).
I'm almost sure that it's because I'm using the master key with the CloudCode, but have no idea how can I avoid it. Everything else is still working, for example I can upload images with currentUser.
Here is the code that I'm using for the CloudCode, JavaScript is totally unknown for me, maybe somebody will see what causes the problem.
Parse.Cloud.define('editUser', function(request, response) {
Parse.Cloud.useMasterKey();
var userQuery = new Parse.Query(Parse.User);
userQuery.get(request.params.userId)
.then(function (user) {
var relation = user.relation("sampleRelation");
relation.add(request.user);
// chain the promise
return user.save();
}).then(function (user) {
var currentUser = request.user;
var relation = currentUser.relation("sampleRelation");
relation.add(user);
// chain the new promise
return currentUser.save();
}).then(function () {
response.success();
}, function (error) {
response.error(error);
});
});
It crashes when i try to remove the object:
PFUser *user = [self.friends objectAtIndex:indexPath.row];
PFRelation *myFriendsRel = [self.currentUser relationForKey:#"simpleRelation"];
if ([self isFriend:user]) {
for (PFUser *friendName in self.friends) {
if ([friendName.objectId isEqualToString:user.objectId]){
[self.friends removeObject:friendName];
break; // to exit a loop
}
}
// remove from parse
[myFriendsRel removeObject:user];
NSLog(#"deleted: %#", user.username);
}
[self.currentUser saveInBackgroundWithBlock:^(BOOL succeeded, NSError *error) {
if (error){
NSLog(#"Error %# %#", error, [error userInfo]);
}
}];
This is the newest attempt, that based Fosco's answer from the other question. It works, but the same way as the earlier versions.
Parse.Cloud.define('editUser', function(request, response) {
var userId = request.params.userId;
var User = Parse.Object.extend('_User'),
user = new User({ objectId: userId });
var currentUser = request.user;
var relation = user.relation("friendsRelation");
relation.add(currentUser);
user.save(null, { useMasterKey:true}).then(function(user) {
response.success(user);
}, function(error) {
response.error(error)
});
});
At a quick glance it looks like its failing because you're trying to remove an object from an array whilst it is being iterated. I know this causes a crash in Objective C regardless of whether you're using Parse objects or not.
Try re-writing this segment:
for (PFUser *friendName in self.friends) {
if ([friendName.objectId isEqualToString:user.objectId]){
[self.friends removeObject:friendName];
break; // to exit a loop
}
}
To something like this:
NSMutableArray *tempArray = [[NSMutableArray alloc]init];
for (PFUser *friendName in self.friends) {
if (![friendName.objectId isEqualToString:user.objectId]) {
[tempArray addObject:friendName];
}
self.friends = [NSArray arrayWithArray:tempArray];
Again, only had a quick glance so not 100% if that is your problem but it looks like it, let me know if it helps
Imagine I have two models:
var Movie = sequelize.define('movies', {
/* model definition */
})
var Genre = sequelize.define('genres', {
/* model definition */
});
Movie.hasMany(Genre);
Genre.hasMany(Movie);
If I wanted to stipulate that a Movie MUST have at least one Genre, how would I go about doing that?
I've looked in the obvious places. My initial idea was to build(), validate() and save(), however looking at the source .validate() only accommodates fields defined in the model definition.
e.g.
Genre.find({where:{'name':'horror})
.success(function (horrorGenre) {
var movie = Movie.build({..});
movie.addGenre(horrorGenre);
if (! movie.validate()) { // This doesn't consider related data
movie.save();
}
});
So I figure I need to implement some kind of custom validation mechanism, but I'm not entirely sure where to start.
NOTE I'm maintaining my own fork of Sequelize, so this is more of a question of how I might go about modifying the Sequelize source to do what I want it to do versus throwing together a hacky solid implementation.
you can try to search for genre objects in database and call addGenre for movie
Genre.findall({where:{'name':["genre1","genre1"]})
.success(function (genres) {
if(genres.length==0){
console.log("Genres were not found!");
// exit somehow maybe res.json(200,{"msg","not ok"});
}
var movie = Movie.build({..});
var queryChainer = new Sequelize.Utils.QueryChainer;
for(var i = 0 ; i != genres.length ; i++){
queryChainer.add(movie.addGenre(genres[i].id));
}
queryChainer.run().success(function(){}).error(function(){});
});
this way you will know that at least 1 genre will be added to submitted movie!
I'm not experienced in Javascript but I've read a ton of articles about Meteor reactivity but still can't figure out why it is not working in my case.
When a new product is added, I want to be recalculated total cost and use it in the totalCost helper so it's almost real time visible in the browser.
Can someone please take a look at my code and try to figure out some logic error? Everything except the reactivity is working on my computer.
I have got this method in /models/Product.js :
Meteor.methods({
totalProductCost: function() {
var pipeline = [
{$match: {owner: Meteor.userId()}},
{$group: {_id: null, cost: {$sum: "$cost"}}}
];
var data = Products.aggregate(pipeline)["0"].cost;
return (data === undefined) ? 0 : data;
}
});
Then I've got layout.js in client folder:
if (Meteor.isClient) {
var handle = Meteor.subscribe("Products", Meteor.userId());
ProductManager = {
_productItems: null,
_dep: new Tracker.Dependency(),
getProducts: function () {
this._dep.depend();
return this._productItems;
},
setProducts: function (value) {
if (value !== this._productItems) {
this._productItems = value;
this._dep.changed();
}
},
getTotalCost: function () {
return ReactiveMethod.call('totalProductCost');
}
}
// TRACKER
Tracker.autorun(function () {
if (handle.ready()) {
ProductManager.setProducts(Products.find().fetch());
}
});
// HELPERS
Template.boxOverview.helpers({
"totalCost" : function () {
return ProductManager.getTotalCost();
},
});
}
It seems that you used a collection.aggregate in a method. If you need reactivity, you need to use a publication rather than a method (or you need to call the method each time you want to refresh). However, if you use your aggregation inside your publication (I assume you use a package for it) you will loose reactivity as well.
What I would advise you is to use a publication without aggregate function. You calculate your product cost by creating a new field and adding it to your cursor. Once, you do that, if you want to keep reactivity, it is necessary to use to use cursor.observeChanges() or just cursor.observe().
Have a look at this example:
var self = this;
// Modify the document we are sending to the client.
function filter(doc) {
var length = doc.item.length;
// White list the fields you want to publish.
var docToPublish = _.pick(doc, [
'someOtherField'
]);
// Add your custom fields.
docToPublish.itemLength = length;
return docToPublish;
}
var handle = myCollection.find({}, {fields: {item:1, someOtherField:1}})
// Use observe since it gives us the the old and new document when something is changing.
// If this becomes a performance issue then consider using observeChanges,
// but its usually a lot simpler to use observe in cases like this.
.observe({
added: function(doc) {
self.added("myCollection", doc._id, filter(doc));
},
changed: function(newDocument, oldDocument)
// When the item count is changing, send update to client.
if (newDocument.item.length !== oldDocument.item.length)
self.changed("myCollection", newDocument._id, filter(newDocument));
},
removed: function(doc) {
self.removed("myCollection", doc._id);
});
self.ready();
self.onStop(function () {
handle.stop();
});
This is taken from here.