Develop Reference

Read csv and write to mongodb using NodeJS

I have a large csv and I need to read t and insert to mongodb
Csv contains user name, category name and policy name.
Need to insert Users into User collection with category id and policy id. Csv provides only the category name and policy name. So I need to fetch category id from collection using its name.
If category name not exist, create a new one and returns its id. Same case for policy.
So I tried
fs.createReadStream('./data_sheet.csv')
.pipe(csv())
.on('data', async (row) => {
// console.log(row)
let res = await Category.findOneOrCreate({ name: row.cat.trim() });
console.log(res)
})
.on('end', () => {
console.log('CSV file successfully processed');
});
categorySchema.statics.findOneOrCreate = async function findOneOrCreate(condition) {
try {
const self = this
let agent = await self.findOne(condition)
console.log("condition")
console.log(condition)
console.log("agent")
console.log(agent)
if (agent) return agent._id
else {
agent = await self.create(condition)
return agent._id
}
} catch (e) {
console.log(e)
}
}
This is not working in proper manner. What is the proper way to do this?

If by not working you mean, the data is not coming up for category then make sure you follow the right async approach or else provide more info.
There are several things to keep in mind,
You might need to create a cronjob for recursive process
Import the csv file into an array of Object
Loop over the object to match with category Id
If not then create a category Id
Return to the main function
update the document [here you can either update all or update one at a time using the step 2 looping we did]

Unable to log user state information to transcript

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.

DiscordJS Database Not Storing Information Ideally

I'm trying to get the Discord bot to create a database that is basically the user map (a row for each user and columns for ID, nick name, avatar URL, etc) when it receives a !getdata command.
I've gotten to the point where the database successfully takes data, in this case the username and user ID, but it displays all the unique values in two columns as long comma separated values (i.e. the username column displays 'user1,user2,user3').
I'm sure this is by design, but I'm really struggling with restructuring. I'd like to either have it take all the data from an object map (client.users or message.guild.members) but I cannot figure it out.
The other option, which is what I'm trying now, is to create a row for each user and then fill in the values that I want to store, but I'm getting nowhere fast.
I'm very new with SQLite (and node/DiscordJS/JS for that matter), so any advice is greatly appreciated.
Index.js
const Discord = require('discord.js');
const client = new Discord.Client();
const sql = require('sqlite3');
let db = new sql.Database("users.sqlite", (err) => {
if (err) {
console.log('Error connecting to the database', err)
} else {
console.log('Database connected.')
}
})
let token = process.env.CLIENT_TOKEN;
let prefix = process.env.PREFIX ;
client.on('ready', () => {
console.log(`Logged in as ${client.user.tag}!`);
db.run(`CREATE TABLE IF NOT EXISTS users(username TEXT, id TEXT)`);
})
client.on('message', function(message) {
if (!message.content.startsWith(prefix));
const args = message.content.slice(prefix.length).split(/ +/);
const command = args.shift().toLowerCase();
if (command === 'getdata') {
let username = message.guild.members.map(m=>m.user.username);
let userid = message.guild.members.map(m=>m.user.id);
db.run(`INSERT OR REPLACE INTO users(username, id) VALUES(?,?)`, [`${username}`,`${userid}`]);
return message.channel.send(`User database updated.`);
}
});
client.login(token);
If you're curious as to the formatting or way things are written, the answer is two fold:
I'm pretty new at this
This was the only way I could get the values in the database to return something other than null
Thanks in advance,

First off, welcome to the site.
I hope that I can shine some light here without diving into refactoring your code or making you change anything major.
One thing sticks out to me as to why you are storing an array instead of a single value.
let username = message.guild.members.map(m=>m.user.username);
let userid = message.guild.members.map(m=>m.user.id);
The .map call returns an array, not a single value.
Each user that issues a command is part of the message object. If I remember correctly, you would want this to be something like...
(simplified version)
const { username, id } = message.member.user;
db.run(`INSERT OR REPLACE INTO users(username, id) VALUES(?,?)`, [username, id]);
// ...
User documentation can be found here
Edit:
If you wanted to build the database for all users in that one command you could do something like the following with a bulk insert... (quick and dirty)
db.serialize(() => {
db.run('BEGIN TRANSACTION;');
// execute inserts in transaction
for (const m of message.guild.members) {
db.run('INSERT OR REPLACE INTO users(username, id) VALUES(?,?);', [m.user.username, m.user.id]);
}
// commit all inserts :)
db.run('COMMIT;')
});
message.channel.send('User database updated.');
Control flow documenation
Hopefully this points you in the right direction :)

MongoDB - Mongoose - TypeError: save is not a function

I am attempting to perform an update to a MongoDB document (using mongoose) by first using .findById to get the document, then updating the fields in that document with new values. I am still a bit new to this so I used a tutorial to figure out how to get it working, then I have been updating my code for my needs. Here is the tutorial: MEAN App Tutorial with Angular 4. The original code had a schema defined, but my requirement is for a generic MongoDB interface that will simply take whatever payload is sent to it and send it along to MongoDB. The original tutorial had something like this:
exports.updateTodo = async function(todo){
var id = todo.id
try{
//Find the old Todo Object by the Id
var oldTodo = await ToDo.findById(id);
}catch(e){
throw Error("Error occured while Finding the Todo")
}
// If no old Todo Object exists return false
if(!oldTodo){
return false;
}
console.log(oldTodo)
//Edit the Todo Object
oldTodo.title = todo.title
oldTodo.description = todo.description
oldTodo.status = todo.status
console.log(oldTodo)
try{
var savedTodo = await oldTodo.save()
return savedTodo;
}catch(e){
throw Error("And Error occured while updating the Todo");
}
}
However, since I don't want a schema and want to allow anything through, I don't want to assign static values to specific field names like, title, description, status, etc. So, I came up with this:
exports.updateData = async function(update){
var id = update.id
// Check the existence of the query parameters, If they don't exist then assign a default value
var dbName = update.dbName ? update.dbName : 'test'
var collection = update.collection ? update.collection : 'testing';
const Test = mongoose.model(dbName, TestSchema, collection);
try{
//Find the existing Test object by the Id
var existingData = await Test.findById(id);
}catch(e){
throw Error("Error occurred while finding the Test document - " + e)
}
// If no existing Test object exists return false
if(!existingData){
return false;
}
console.log("Existing document is " + existingData)
//Edit the Test object
existingData = JSON.parse(JSON.stringify(update))
//This was another way to overwrite existing field values, but
//performs a "shallow copy" so it's not desireable
//existingData = Object.assign({}, existingData, update)
//existingData.title = update.title
//existingData.description = update.description
//existingData.status = update.status
console.log("New data is " + existingData)
try{
var savedOutput = await existingData.save()
return savedOutput;
}catch(e){
throw Error("An error occurred while updating the Test document - " + e);
}
}
My original problem with this was that I had a lot of issues getting the new values to overwrite the old ones. Now that that's been solved, I am getting the error of "TypeError: existingData.save is not a function". I am thinking the data type changed or something, and now it is not being accepted. When I uncomment the static values that were in the old tutorial code, it works. This is further supported by my console logging before and after I join the objects, because the first one prints the actual data and the second one prints [object Object]. However, I can't seem to figure out what it's expecting. Any help would be greatly appreciated.
EDIT: I figured it out. Apparently Mongoose has its own data type of "Model" which gets changed if you do anything crazy to the underlying data by using things like JSON.stringify. I used Object.prototype.constructor to figure out the actual object type like so:
console.log("THIS IS BEFORE: " + existingData.constructor);
existingData = JSON.parse(JSON.stringify(update));
console.log("THIS IS AFTER: " + existingData.constructor);
And I got this:
THIS IS BEFORE: function model(doc, fields, skipId) {
model.hooks.execPreSync('createModel', doc);
if (!(this instanceof model)) {
return new model(doc, fields, skipId);
}
Model.call(this, doc, fields, skipId);
}
THIS IS AFTER: function Object() { [native code] }
Which showed me what was actually going on. I added this to fix it:
existingData = new Test(JSON.parse(JSON.stringify(update)));
On a related note, I should probably just use the native MongoDB driver at this point, but it's working, so I'll just put it on my to do list for now.

You've now found a solution but I would suggest using the MongoDB driver which would make your code look something along the lines of this and would make the origional issue disappear:
// MongoDB Settings
const MongoClient = require(`mongodb`).MongoClient;
const mongodb_uri = `mongodb+srv://${REPLACE_mongodb_username}:${REPLACE_mongodb_password}#url-here.gcp.mongodb.net/test`;
const db_name = `test`;
let db; // allows us to reuse the database connection once it is opened
// Open MongoDB Connection
const open_database_connection = async () => {
try {
client = await MongoClient.connect(mongodb_uri);
} catch (err) { throw new Error(err); }
db = client.db(db_name);
};
exports.updateData = async update => {
// open database connection if it isn't already open
try {
if (!db) await open_database_connection();
} catch (err) { throw new Error(err); }
// update document
let savedOutput;
try {
savedOutput = await db.collection(`testing`).updateOne( // .save() is being depreciated
{ // filter
_id: update.id // the '_id' might need to be 'id' depending on how you have set your collection up, usually it is '_id'
},
$set: { // I've assumed that you are overwriting the fields you are updating hence the '$set' operator
update // update here - this is assuming that the update object only contains fields that should be updated
}
// If you want to add a new document if the id isn't found add the below line
// ,{ upsert: true }
);
} catch (err) { throw new Error(`An error occurred while updating the Test document - ${err}`); }
if (savedOutput.matchedCount !== 1) return false; // if you add in '{ upsert: true }' above, then remove this line as it will create a new document
return savedOutput;
}
The collection testing would need to be created before this code but this is only a one-time thing and is very easy - if you are using MongoDB Atlas then you can use MongoDB Compass / go in your online admin to create the collection without a single line of code...
As far as I can see you should need to duplicate the update object. The above reduces the database calls from 2 to one and allows you to reuse the database connection, potentially anywhere else in the application which would help to speed things up. Also don't store your MongoDB credentials directly in the code.

JS SDK, Thrift error code 12 when getting SharedNotebooksList

It's the first time that I work with evernote,
Like the example given in the JS SDK, I create my client with the token that I get from the OAuth and I get all the notebooks of my current user so it was good for me.
But I'm facing a problem that I can't understand, when I use any method of my shared store it throw an Thrift exception with error code 12 and giving the shard id in the message.
I know that 12 error code is that the shard is temporary unavailable..
But I know that it's another thing because it's not temporary...
I have a full access api key, it work with the note store, did I miss something ?
// This is the example in the JS SDK
var linkedNotebook = noteStore.listLinkedNotebooks()
.then(function(linkedNotebooks) {
// just pick the first LinkedNotebook for this example
return client.getSharedNoteStore(linkedNotebooks[0]);
}).then(function(sharedNoteStore) {
// /!\ There is the problem, throw Thrift exception !
return sharedNoteStore.listNotebooks().then(function(notebooks) {
return sharedNoteStore.listTagsByNotebook(notebooks[0].guid);
}).then(function(tags) {
// tags here is a list of Tag objects
});
});

this seems to be an error with the SDK. I created a PR (https://github.com/evernote/evernote-sdk-js/pull/90).
You can work around this by using authenticateToSharedNotebook yourself.
const client = new Evernote.Client({ token, sandbox });
const noteStore = client.getNoteStore();
const notebooks = await noteStore
.listLinkedNotebooks()
.catch(err => console.error(err));
const notebook = notebooks.find(x => x.guid === guid);
const { authenticationToken } = await client
.getNoteStore(notebook.noteStoreUrl)
.authenticateToSharedNotebook(notebook.sharedNotebookGlobalId);
const client2 = new Evernote.Client({
token: authenticationToken,
sandbox
});
const noteStore2 = client2.getNoteStore();
const [notebook2] = await noteStore2.listNotebooks();
noteStore2.listTagsByNotebook(notebook2.guid)