I am trying to setup push notifications with PubNub on a react-native project. However calling the push.addChannels() method gives me the error 403 with "PNAccessDeniedCategory".
I have tried turning off the access manager but still get the same result. Not to sure if I am passing the correct params though.
I have setup push notifications with apple and uploaded the cert.pem file to PubNub.
pubnub.push.addChannels({
channels: ['ch.staff'],
device: 'ECID-OF-DEVICE-HERE',
pushGateway: 'apns' // apns, gcm, mpns
}, function(status) {
if (status.error) {
console.log("operation failed w/ error:", status);
} else {
console.log("operation done!")
}
});
I can send and receive standard messages without issue, it is just this which doesn't work.
I am following the docs here:
https://www.pubnub.com/docs/javascript/mobile-gateway-sdk-v4#Provisioning_devices_with_channel_names_per_lang_Examples
My main questions are.
Do I need to grant access to use this method and how do I do that?
Is the device field supposed to be the ECID?
PubNub Mobile Push + Access Manager
Access Manager is denying access because the client device's auth-key does not have read permissions (or it doesn't have an auth-key at all).
Either disable Access Manager until you are ready to implement permission granting to auth-keys for your clients by your server, or grant read permission for the client's auth-key for the channels it needs to register for push on (and optionally subscribe to).
For full details see the PubNub Nub operations/permissions mapping in the PubNub JavaScript SDK docs Access Manager tutorial.
The grant permissions would look something like this:
pubnub.grant(
{
channels: ['ch.staff'],
authKeys: ['clientAuthKey'],
read: true, // false to disallow
write: true, // false to disallow
},
function (status) {
// handle state setting response
console.log('Status', status)
}
);
Related
I have a web application and I want to track its crashing reports.
Can I use Firebase crashlytics or Fabric for this purpose. In their site its mentioned its only for Android or ios.
Regards,
Makrand
There is feature request: https://github.com/firebase/firebase-js-sdk/issues/710
Looks like it's not supported at all, fabric didn't supported crashlytics on web either so it looks like there are maybe some alternatives like https://www.bugsnag.com but I would like to have it too in one place. Don't see difference between web, android or iOS clients at all, don't know why this is not supported.
But for some possible solution for Vue framework is to catch errors and send it to google analytics where you can connect also your firebase mobile apps. I think to try it this way for now. I didnt tested it yet so don't know if I have to catch window errors too.
Vue.config.errorHandler = function (error) {
//Toast.error(error.message)
console.warn(error.message)
//send error as event to google analytcs...
if (error) message = error.stack;
ga('send', 'event', 'Vue.config.errorHandler', message, navigator.userAgent);
}
window.onerror = function(message, source, lineno, colno, error) {
// maybe we need to also catch errors here and send to GA
}
But I found something like this too for typescript https://github.com/enkot/catch-decorator
While there is still no firebase crashlytics for web, google offers Stackdriver with error reporting functionality - it keeps track of all errors with ability to mark them as resolved (it can also send email notifications about new errors):
You can access it using the below url (make sure to put your firebase {project_id} in the link before clicking it):
https://console.cloud.google.com/errors?project={project_id}
There are two ways on how to use it:
Easy way, limited flexibility.
Every console.error(new Error(...)) reported from your firebase function is automatically tracked in the Stackdriver error logging platform.
So you just need to send an error report from your web app to your firebase function and log it using console.error inside that function.
Note, only an instances of Error object will be sent to the Stackdriver platform. For example console.error("{field1: 'text'}") won't be sent to Stackdriver. More info on that in this doc
More comprehensive way that provides an additional control (you can also report userId, your custom platform name, it's version, user agent, etc):
Here is a quick snippet on how it can be used (in our case we first send the error log from web app to our server and then report the error to Stackdriver):
in firebase nodejs:
const {ErrorReporting} = require('#google-cloud/error-reporting');
let serviceAccount = {...} //service account is your firebase credetials that holds your secret keys etc. See below for more details.
let config = {
projectId: serviceAccount.project_id,
reportMode: "always",
credentials: serviceAccount
}
let errors = new ErrorReporting(config);
Report error to Stackdriver from nodejs:
async function reportError(message){
//message is a string that contains the error name with an optional
//stacktrace as a string representing each stack frame separated using "\n".
//For example:
//message = "Error: Oh-hoh\n at MyClass.myMethod (filename.js:12:23)\n etc.etc."
const errorEvent = this.errors.event()
.setMessage(message)
.setUser(userId)
.setServiceContext("web-app", "1.0.0")
await errors.report(errorEvent)
}
More info about the Stackdriver library is available in this doc. And more info about the stacktrace and it's format can be found in the docs here
A few notes on setting it up:
You need to enable two things:
Enable Stackdrive api for your project using the link below (make sure to set your firebase {project_id} in the url below before clicking it)
https://console.developers.google.com/apis/library/clouderrorreporting.googleapis.com?project={project_id}
Make sure to also grant "Error writer" permission to the firebase service account so Stackdriver can receive the error logs (service account is a sort of representation of a "user" for your firebase project who accesses the services)
To grant the premission, follow the below steps:
first locate the "Firebase service account" using your firebase dashboard link (you can find it below) and remember it's value - it looks something like firebase-adminsdk-{random_symbols}#{project_id}.iam.gserviceaccount.com
Then open gcloud console under "Access"->"IAM". Or use the following link:
https://console.cloud.google.com/access/iam?project={project_id} <- put your firebase project id here
Locate your Firebase service account from the step 1.
Press edit for that account and add "Errors writer" permission:
Where to find the serviceAccount.json:
Regarding the serviceAccount - this is a universal credentials that can be used to authenticate many google services including the Stackdriver. You can obtain yours from your firebase dashboard using the url below (just put your firebase project_id in the link before using it):
https://console.firebase.google.com/u/0/project/{project_id}/settings/serviceaccounts/adminsdk
Open it and click "generate new credentials". This will generate a new service account and download the serviceAccount.json that you need to keep safe (you won't be able to get it again unless you generate a new one).
Apparently Sentry now supports several web frameworks out of the box.
I have recently integrated Sentry crashlytics for Django App.
see here:
https://sentry.io/platforms/
I'm using googleapis npm package ("apis/drive/v3.js") for Google Drive service. On backend I'm using NodeJS and ngrok for local testing. My problem is that I can't get notifications.
The following code:
drive.changes.watch({
pageToken: startPageToken,
resource: {
id: uuid.v1(),
type: 'web_hook',
address: 'https://7def94f6.ngrok.io/notifications'
}
}, function(err, result) {
console.log(result)
});
returns some like:
{
kind: 'api#channel',
id: '8c9d74f0-fe7b-11e5-a764-fd0d7465593e',
resourceId: '9amJTbMCYabCkFvn8ssPrtzWvAM',
resourceUri: 'https://www.googleapis.com/drive/v3/changes?includeRemoved=true&pageSize=100&pageToken=6051&restrictToMyDrive=false&spaces=drive&alt=json',
expiration: '1460227829000'
}
When I try to change any files in Google Drive, the notifications do not comes. Dear colleges, what is wrong?
This should be a comment but i do not have enough (50points) experience to post one. Sorry if this is not a real answer but might help.
I learned this today. I'm doing practically the same thing like you - only not with Drive but Gmail api.
I see you have this error:
"push.webhookUrlUnauthorized", "message": "Unauthorized WebHook etc..."
I think this is because one of the 2 reasons:
you didn't give the Drive-api publisher permissions to your topic.
Second if you want to receive notifications, the authorized webHooks Url must be set both on the server( your project) and in your pub/sub service(Google Cloud).
See below - for me this setup works:
1. Create a topic
2. Give the Drive publish permissions to your topic. This is done by adding the Drive scope in the box and following steps 2 and 3.
3. Configure authorized WebHooks. Form the Create Topic page - click on add subscriptions. Not rely vizible here but once you are there you can manage.
I'm using Web push notifications with Chrome, and they work great. But now I want to deliver a custom message in my notifications. I can have my Service Worker call out to my site to get content, as is done at https://simple-push-demo.appspot.com/—which is fine if I want every recipient to see the same message.
Is there any way to get either the recipient’s registration_id or the message_id that GCM returns? If I could get either of these and include them in the callback to the service, I could customize the response.
Also, any info on when we might be able to include a payload in the call to GCM?
The registration_id and message_id fields aren't exposed, but if the user is previously authenticated to your app, any fetch() to the server from your Service Worker will include credentials (and session information) which you can use to identify them.
If that doesn't work for your case, you can store user/session information in IndexedDB.
Payloads are coming soon—likely Chrome 50 or 51—based on the Web Push protocol. It's a bit of extra overhead and work to configure the (required) encryption.
It's possible, but I wouldn't do it since it's specific to GCM, while other browsers use other services.
You can either create a unique ID for each user (like we're doing in Mercurius) and store it in IndexedDB, or you can use the entire endpoint URL as an ID.
Here's the snippet to get the registration_id:
self.registration.pushManager.getSubscription()
.then(function(subscription) {
if (subscription) {
var endpoint = subscription.endpoint;
var endpointParts = endpoint.split('/');
var gcmRegistrationID = endpointParts[endpointParts.length - 1];
console.log(gcmRegistrationID);
}
});
P.S.: It returns a promise, so make sure your service worker waits for the promise to be resolved.
Well I am able to upload video on Youtube but i didn't find a way or relevant code to delete video/videos from Youtube.
Here is my code which i tried to delete the youtube video.
private async Task Run()
{
UserCredential credential;
using (var stream = new FileStream("client_secret.json", FileMode.Open, FileAccess.Read))
{
credential = await GoogleWebAuthorizationBroker.AuthorizeAsync(
GoogleClientSecrets.Load(stream).Secrets,
new[] { YouTubeService.Scope.Youtube },
"user",
CancellationToken.None
);
}
var youtubeService = new YouTubeService(new BaseClientService.Initializer()
{
HttpClientInitializer = credential,
ApplicationName = Assembly.GetExecutingAssembly().GetName().Name
});
var videosDeleteRequest = youtubeService.Videos.Delete("Video ID");
await videosDeleteRequest.ExecuteAsync();
}
But getting 403 response
Error: Google.Apis.Requests.RequestError
Insufficient Permission [403]
Errors [
Message[Insufficient Permission] Location[ - ] Reason[insufficientPermis
sions] Domain[global]
]
A little help or any possible solution will be highly appreciable.
The error translates to:
The video that you are trying to delete cannot be deleted. The request
might not be properly authorized.
https://developers.google.com/youtube/v3/docs/videos/delete
Have you successfully acquired the token of the user that owns the video?
The videos.delete method is preformed on private user data. In order to delete the data you must have permission or consent of the user to access their account. They must have granted you permission in one of the following scopes.
The error message
Message[Insufficient Permission] Location[ - ] Reason[insufficientPermis
sions] Domain[global]
Means that the user did not grant you permission with a hig enough scope. If for example you asked for authorization with only a read only scope you would then not have enough permissions to delete a video.
However if we check your code we can see that you are in fact using YouTubeService.Scope.Youtube. However if you have previously run your application then the client library stored the consent of the user. If you then have changed the scope and not forced the user to consent to authorization again. Then you are still running on the old consent.
The solution in this case is to change "user" to something else which will force it to request authorization again.
Community:
ServiceWorker is a great advance technology in terms of cache managment, but I have some questions associated with other operations such as:
Push Notification: I made a GCM integration (Google Clud Message) and NodeJS, following this article, the problem is that when GCM sends the information to the client (Chorme), the payload of the message generated by GCM is not accessible in the Notification in ServiceWorker Listener, which would be great for making decisions.
Any Idea when data payload in notifications will be enabled?
Registration: Since ES6 is very mature, it would be good to register a ServiceWorker in other ways, for example:
import sw from './sw.js'
navigator.serviceWorker.register(sw, {scope: '/'}).then(function (registration) {
// Registration was successful
console.log('ServiceWorker registration successful with scope: ', registration.scope);
}).catch(function (err) {
// registration failed :(
console.log('ServiceWorker registration failed: ', err);
});
Is this possible or make sense?
Thanks!!!!
The "Support encrypted payloads for push messages" bug tracks progress on getting payloads exposed in notifications. That bug is Chrome-specific, but other browser vendors are likely to follow the same approach.
The service worker upgrade flow is very much tied to the idea of there being a specific JavaScript file which represents the service worker's code, and that file can then be periodically checked, byte-by-byte, to see if there are any updates. If it were an in-memory JavaScript object that was registered, detached from the file, the upgrade flow wouldn't work as specified. I don't think you'll see the change you're proposing added to the specification.