2020-12-09 12:00:14 +03:00
|
|
|
defmodule Plausible.Workers.SpikeNotifier do
|
|
|
|
use Plausible.Repo
|
|
|
|
alias Plausible.Stats.Query
|
2020-12-09 12:16:16 +03:00
|
|
|
alias Plausible.Site.SpikeNotification
|
2020-12-09 12:00:14 +03:00
|
|
|
use Oban.Worker, queue: :spike_notifications
|
|
|
|
@at_most_every "12 hours"
|
|
|
|
|
|
|
|
@impl Oban.Worker
|
2021-04-26 11:32:18 +03:00
|
|
|
def perform(_job, clickhouse \\ Plausible.Stats.Clickhouse) do
|
2020-12-29 16:17:27 +03:00
|
|
|
notifications =
|
|
|
|
Repo.all(
|
|
|
|
from sn in SpikeNotification,
|
|
|
|
where: is_nil(sn.last_sent),
|
|
|
|
or_where: sn.last_sent < fragment("now() - INTERVAL ?", @at_most_every),
|
2021-06-17 10:20:54 +03:00
|
|
|
join: s in Plausible.Site,
|
|
|
|
on: sn.site_id == s.id,
|
|
|
|
where: not s.locked,
|
|
|
|
preload: [site: s]
|
2020-12-29 16:17:27 +03:00
|
|
|
)
|
2020-12-09 12:00:14 +03:00
|
|
|
|
|
|
|
for notification <- notifications do
|
[Continued] Google Analytics import (#1753)
* Add has_imported_stats boolean to Site
* Add Google Analytics import panel to general settings
* Get GA profiles to display in import settings panel
* Add import_from_google method as entrypoint to import data
* Add imported_visitors table
* Remove conflicting code from migration
* Import visitors data into clickhouse database
* Pass another dataset to main graph for rendering in red
This adds another entry to the JSON data returned via the main graph API
called `imported_plot`, which is similar to `plot` in form but will be
completed with previously imported data. Currently it simply returns
the values from `plot` / 2. The data is rendered in the main graph in
red without fill, and without an indicator for the present. Rationale:
imported data will not continue to grow so there is no projection
forward, only backwards.
* Hook imported GA data to dashboard timeseries plot
* Add settings option to forget imported data
* Import sources from google analytics
* Merge imported sources when queried
* Merge imported source data native data when querying sources
* Start converting metrics to atoms so they can be subqueried
This changes "visitors" and in some places "sources" to atoms. This does
not change the behaviour of the functions - the tests all pass unchanged
following this commit. This is necessary as joining subqueries requires
that the keys in `select` statements be atoms and not strings.
* Convery GA (direct) source to empty string
* Import utm campaign and utm medium from GA
* format
* Import all data types from GA into new tables
* Handle large amounts of more data more safely
* Fix some mistakes in tables
* Make GA requests in chunks of 5 queries
* Only display imported timeseries when there is no filter
* Correctly show last 30 minutes timeseries when 'realtime'
* Add with_imported key to Query struct
* Account for injected :is_not filter on sources from dashboard
* Also add tentative imported_utm_sources table
This needs a bit more work on the google import side, as GA do not
report sources and utm sources as distinct things.
* Return imported data to dashboard for rest of Sources panel
This extends the merge_imported function definition for sources to
utm_sources, utm_mediums and utm_campaigns too. This appears to be
working on the DB side but something is incomplete on the client side.
* Clear imported stats from all tables when requested
* Merge entry pages and exit pages from imported data into unfiltered dashboard view
This requires converting the `"visits"` and `"visit_duration"` metrics
to atoms so that they can be used in ecto subqueries.
* Display imported devices, browsers and OSs on dashboard
* Display imported country data on dashboard
* Add more metrics to entries/exits for modals
* make sure data is returned via API with correct keys
* Import regions and cities from GA
* Capitalize device upon import to match native data
* Leave query limits/offsets until after possibly joining with imported data
* Also import timeOnPage and pageviews for pages from GA
* imported_countries -> imported_locations
* Get timeOnPage and pageviews for pages from GA
These are needed for the pages modal, and for calculating exit rates for
exit pages.
* Add indicator to dashboard when imported data is being used
* Don't show imported data as separately line on main graph
* "bounce_rate" -> :bounce_rate, so it works in subqueries
* Drop imported browser and OS versions
These are not needed.
* Toggle displaying imported data by clicking indicator
* Parse referrers with RefInspector
- Use 'ga:fullReferrer' instead of 'ga:source'. This provides the actual
referrer host + path, whereas 'ga:source' includes utm_mediums and
other values when relevant.
- 'ga:fullReferror' does however include search engine names directly,
so they are manually checked for as RefInspector won't pick up on
these.
* Keep imported data indicator on dashboard and strikethrough when hidden
* Add unlink google button to import panel
* Rename some GA browsers and OSes to plausible versions
* Get main top pages and exit pages panels working correctly with imported data
* mix format
* Fetch time_on_pages for imported data when needed
* entry pages need to fetch bounces from GA
* "sample_percent" -> :sample_percent as only atoms can be used in subqueries
* Calculate bounce_rate for joined native and imported data for top pages modal
* Flip some query bindings around to be less misleading
* Fixup entry page modal visit durations
* mix format
* Fetch bounces and visit_duration for sources from GA
* add more source metrics used for data in modals
* Make sources modals display correct values
* imported_visitors: bounce_rate -> bounces, avg_visit_duration -> visit_duration
* Merge imported data into aggregate stats
* Reformat top graph side icons
* Ensure sample_percent is yielded from aggregate data
* filter event_props should be strings
* Hide imported data from frontend when using filter
* Fix existing tests
* fix tests
* Fix imported indicator appearing when filtering
* comma needed, lost when rebasing
* Import utm_terms and utm_content from GA
* Merge imported utm_term and utm_content
* Rename imported Countries data as Locations
* Set imported city schema field to int
* Remove utm_terms and utm_content when clearing imported
* Clean locations import from Google Analytics
- Country and region should be set to "" when GA provides "(not set)"
- City should be set to 0 for "unknown", as we cannot reliably import
city data from GA.
* Display imported region and city in dashboard
* os -> operating_system in some parts of code
The inconsistency of using os in some places and operating_system in
others causes trouble with subqueries and joins for the native and
imported data, which would require additional logic to account for. The
simplest solution is the just use a consistent word for all uses. This
doesn't make any user-facing or database changes.
* to_atom -> to_existing_atom
* format
* "events" metric -> :events
* ignore imported data when "events" in metrics
* update "bounce_rate"
* atomise some more metrics from new city and region api
* atomise some more metrics for email handlers
* "conversion_rate" -> :conversion_rate during csv export
* Move imported data stats code to own module
* Move imported timeseries function to Stats.Imported
* Use Timex.parse to import dates from GA
* has_imported_stats -> imported_source
* "time_on_page" -> :time_on_page
* Convert imported GA data to UTC
* Clean up GA request code a bit
There was some weird logic here with two separate lists that really
ought to be together, so this merges those.
* Fail sooner if GA timezone can't be identified
* Link imported tables to site by id
* imported_utm_content -> imported_utm_contents
* Imported GA from all of time
* Reorganise GA data fetch logic
- Fetch data from the start of time (2005)
- Check whether no data was fetched, and if so, inform user and don't
consider data to be imported.
* Clarify removal of "visits" data when it isn't in metrics
* Apply location filters from API
This makes it consistent with the sources etc which filter out 'Direct /
None' on the API side. These filters are used by both the native and
imported data handling code, which would otherwise both duplicate the
filters in their `where` clauses.
* Do not use changeset for setting site.imported_source
* Add all metrics to all dimensions
* Run GA import in the background
* Send email when GA import completes
* Add handler to insert imported data into tests and imported_browsers_factory
* Add remaining import data test factories
* Add imported location data to test
* Test main graph with imported data
* Add imported data to operating systems tests
* Add imported data to pages tests
* Add imported data to entry pages tests
* Add imported data to exit pages tests
* Add imported data to devices tests
* Add imported data to sources tests
* Add imported data to UTM tests
* Add new test module for the data import step
* Test import of sources GA data
* Test import of utm_mediums GA data
* Test import of utm_campaigns GA data
* Add tests for UTM terms
* Add tests for UTM contents
* Add test for importing pages and entry pages data from GA
* Add test for importing exit page data
* Fix module file name typo
* Add test for importing location data from GA
* Add test for importing devices data from GA
* Add test for importing browsers data from GA
* Add test for importing OS data from GA
* Paginate GA requests to download all data
* Bump clickhouse_ecto version
* Move RefInspector wrapper function into module
* Drop timezone transform on import
* Order imported by side_id then date
* More strings -> atoms
Also changes a conditional to be a bit nicer
* Remove parallelisation of data import
* Split sources and UTM sources from fetched GA data
GA has only a "source" dimension and no "UTM source" dimension. Instead
it returns these combined. The logic herein to tease these apart is:
1. "(direct)" -> it's a direct source
2. if the source is a domain -> it's a source
3. "google" -> it's from adwords; let's make this a UTM source "adwords"
4. else -> just a UTM source
* Keep prop names in queries as strings
* fix typo
* Fix import
* Insert data to clickhouse in batches
* Fix link when removing imported data
* Merge source tables
* Import hostname as well as pathname
* Record start and end time of imported data
* Track import progress
* Fix month interval with imported data
* Do not JOIN when imported date range has no overlap
* Fix time on page using exits
Co-authored-by: mcol <mcol@posteo.net>
2022-03-11 00:04:59 +03:00
|
|
|
query = Query.from(notification.site, %{"period" => "realtime"})
|
2020-12-09 12:00:14 +03:00
|
|
|
current_visitors = clickhouse.current_visitors(notification.site, query)
|
2021-11-08 16:38:37 +03:00
|
|
|
|
|
|
|
if current_visitors >= notification.threshold do
|
|
|
|
sources = clickhouse.top_sources(notification.site, query, 3, 1, true)
|
|
|
|
notify(notification, current_visitors, sources)
|
|
|
|
end
|
2020-12-09 12:00:14 +03:00
|
|
|
end
|
2020-12-29 16:23:24 +03:00
|
|
|
|
|
|
|
:ok
|
2020-12-09 12:00:14 +03:00
|
|
|
end
|
|
|
|
|
2022-11-03 12:20:29 +03:00
|
|
|
defp notify(notification, current_visitors, sources) do
|
2021-11-08 16:38:37 +03:00
|
|
|
for recipient <- notification.recipients do
|
|
|
|
send_notification(recipient, notification.site, current_visitors, sources)
|
2020-12-09 12:00:14 +03:00
|
|
|
end
|
2021-11-08 16:38:37 +03:00
|
|
|
|
|
|
|
notification
|
|
|
|
|> SpikeNotification.was_sent()
|
|
|
|
|> Repo.update()
|
2020-12-09 12:00:14 +03:00
|
|
|
end
|
|
|
|
|
2020-12-11 12:50:44 +03:00
|
|
|
defp send_notification(recipient, site, current_visitors, sources) do
|
|
|
|
site = Repo.preload(site, :members)
|
|
|
|
|
2020-12-29 16:17:27 +03:00
|
|
|
dashboard_link =
|
2022-11-03 12:20:29 +03:00
|
|
|
if Enum.any?(site.members, &(&1.email == recipient)) do
|
2020-12-29 16:17:27 +03:00
|
|
|
PlausibleWeb.Endpoint.url() <> "/" <> URI.encode_www_form(site.domain)
|
|
|
|
end
|
|
|
|
|
|
|
|
template =
|
|
|
|
PlausibleWeb.Email.spike_notification(
|
|
|
|
recipient,
|
|
|
|
site,
|
|
|
|
current_visitors,
|
|
|
|
sources,
|
|
|
|
dashboard_link
|
|
|
|
)
|
2020-12-11 12:50:44 +03:00
|
|
|
|
2022-10-24 13:13:23 +03:00
|
|
|
Plausible.Mailer.send(template)
|
2020-12-09 12:00:14 +03:00
|
|
|
end
|
|
|
|
end
|