Chore: Added stage tables for portal pageviews

transform/mattermost-analytics/models/intermediate/data_eng/signup/_int_signup__models.yml

@@ -0,0 +1,29 @@
+version: 2
+
+models:
+
+  - name: int_signups_aggregated_to_users
+    description: User signup stages, aggregated by users.
+
+    columns:
+      - name: portal_customer_id
+        description: Customer identifier that joins to customer info coming from stripe.
+        tests:
+          - not_null
+          - unique
+      - name: account_created
+        description: Boolean value indicating if the user created the account.
+      - name: email_verified
+        description: Boolean value indicating if the user verified the email address.
+
+  - name: int_rudder_portal_user_mapping
+    description:  This table provide a list of distinct user and portal customer ID pairs with a non-null value for both IDs.
+
+    columns: 
+      - name: user_id
+        description: User ID coming from rudder events.
+        tests:
+          - unique
+      - name: portal_customer_id
+          - unique
+        description: Customer ID in portal that joins to rudder user ID.

transform/mattermost-analytics/models/intermediate/data_eng/signup/int_rudder_portal_user_mapping.sql

@@ -0,0 +1,20 @@
+{{
+    config({
+        "materialized": "table"
+    })
+}}
+
+SELECT
+    user_id,
+    portal_customer_id,
+    min(timestamp) as first_seen_at,
+    max(timestamp) as last_seen_at
+FROM
+    {{ ref('stg_portal_prod__identifies') }}
+WHERE
+    portal_customer_id IS NOT NULL 
+    -- getting values as `N/A` from portal
+    AND portal_customer_id NOT IN ('N/A')
+    AND user_id IS NOT NULL
+GROUP BY
+    1,2

transform/mattermost-analytics/models/intermediate/data_eng/signup/int_user_signup_stages.sql

@@ -0,0 +1,43 @@
+{{
+    config({
+        "materialized": "table"
+    })
+}}
+WITH rudder_portal_user_mappings as (
+    SELECT
+        user_id,
+        portal_customer_id
+    FROM
+        {{ ref('int_rudder_portal_user_mapping') }} 
+), pageview_create_workspace as (
+    SELECT
+        user_id,
+        pageview_id,
+        timestamp
+    FROM
+        {{ ref('stg_portal_prod__pageview_create_workspace') }}
+), user_signup_stages as ( 
+SELECT
+    portal_customer_id,
+    -- Account is created when portal_customer_id exists
+    true AS account_created, 
+    -- Email is verified and user is redirected to `pageview_create_workspace` screen.
+    CASE 
+        WHEN pageview_create_workspace.pageview_id IS NOT NULL 
+            THEN TRUE 
+        ELSE FALSE 
+    END AS email_verified,
+    timestamp
+FROM
+    rudder_portal_user_mappings
+LEFT JOIN 
+    pageview_create_workspace
+ON pageview_create_workspace.user_id = rudder_portal_user_mappings.user_id
+)
+
+select 
+    portal_customer_id,
+    account_created,
+    email_verified
+from user_signup_stages
+qualify row_number() over (partition by portal_customer_id order by timestamp) = 1

transform/mattermost-analytics/models/staging/portal_prod/_portal_prod__models.yml

@@ -19,3 +19,30 @@ models:
       - name: received_at
         description: Timestamp registered by RudderStack when the event was ingested (received).
 
+  - name: stg_portal_prod__identifies
+    description: |
+      Contains mapping from rudder user_id to portal user_id
+
+    columns:
+      - name: user_id
+        description: The ID of the user that sent the event.
+      - name: portal_customer_id
+        description:  Portal customer id for the user
+      - name: context_traits_portal_customer_id
+        description:  Duplicate of portal_customer_id ingested via context traits, required since sometimes portal_customer_id is null
+      - name: timestamp
+        description:  Timestamp value associated with event.
+
+  - name: stg_portal_prod__pageview_create_workspace
+    description: |
+      Contains rudder data coming from `pageview_create_workspace`.
+
+    columns:
+      - name: pageview_id
+        description:  The pageview ID of the event.
+      - name: user_id
+        description:  The ID of the user that sent the event.
+      - name: event_table
+        description:  The event table that records the event request.
+      - name: timestamp
+        description:  Timestamp value associated with event.

transform/mattermost-analytics/models/staging/portal_prod/_portal_prod__sources.yml

@@ -77,6 +77,7 @@ sources:
       - name: pageview_deployment_selection
       - name: pageview_getting_started
       - name: pageview_verify_email
+        description: Page in the signup flow that user reaches after email is validated.
       - name: password_validation_error
       - name: purchase_complete_create_portal_account
       - name: purchase_fail_clicked_try_again

transform/mattermost-analytics/models/staging/portal_prod/stg_portal_prod__identifies.sql

@@ -0,0 +1,18 @@
+with source as (
+
+    select * from {{ source('portal_prod', 'identifies') }}
+
+),
+
+renamed as (
+
+    select
+        user_id,
+        coalesce(portal_customer_id,context_traits_portal_customer_id) as portal_customer_id,
+        timestamp
+
+    from source
+
+)
+
+select * from renamed

transform/mattermost-analytics/models/staging/portal_prod/stg_portal_prod__pageview_create_workspace.sql

@@ -0,0 +1,19 @@
+with source as (
+
+    select * from {{ source('portal_prod', 'pageview_create_workspace') }}
+
+),
+
+renamed as (
+
+    select
+    id as pageview_id,
+    user_id,
+    event as event_table,
+    timestamp
+
+    from source
+
+)
+
+select * from renamed