dbt_project.yml

name: 'snowplow_normalize'
version: '0.4.0'
config-version: 2

require-dbt-version: [">=1.4.0", "<2.0.0"]

profile: 'default'

model-paths: ["models"]
docs-paths: ["docs"]
macro-paths: ["macros"]

target-path: "target"
clean-targets:
  - "target"
  - "dbt_packages"

dispatch:
  - macro_namespace: dbt
    search_order: ['snowplow_utils', 'dbt']

vars:
  snowplow_normalize:
    # Sources
    # snowplow__atomic_schema: 'atomic_data_sample' # Only set if not using 'atomic' schema for Snowplow events data
    # snowplow__database:  # Only set if not using target.database for Snowplow events data -- WILL BE IGNORED FOR DATABRICKS
    snowplow__events: "{{ source('atomic', 'events') }}"
    snowplow__grant_select_to: []
    snowplow__grant_schema_usage: true
    # Variables - Standard Config
    snowplow__start_date: '2020-01-01'
    snowplow__backfill_limit_days: 30
    snowplow__app_id: []
    snowplow__derived_tstamp_partitioned: true
    # Variables - Advanced Config
    snowplow__lookback_window_hours: 6
    snowplow__days_late_allowed: 3
    snowplow__upsert_lookback_days: 30
    snowplow__query_tag: "snowplow_dbt"
    snowplow__dev_target_name: 'dev'
    snowplow__allow_refresh: false
    snowplow__session_timestamp: 'collector_tstamp'
    snowplow__partition_tstamp: 'collector_tstamp' # This is the column that will be used to partition the data in the derived tables, it should be a timestamp column that is present in the data
    # Variables - Databricks Only
    # Add the following variable to your dbt project's dbt_project.yml file
    # Depending on the use case it should either be the catalog (for Unity Catalog users from databricks connector 1.1.1 onwards) or the same value as your snowplow__atomic_schema (unless changed it should be 'atomic')
    # snowplow__databricks_catalog: 'hive_metastore'



# Completely or partially remove models from the manifest during run start.
on-run-start:
  - "{{ snowplow_utils.snowplow_delete_from_manifest(var('models_to_remove',[]), ref('snowplow_normalize_incremental_manifest')) }}"

# Update manifest table with last event consumed per sucessfully executed node/model
on-run-end:
  - "{{ snowplow_utils.snowplow_incremental_post_hook('snowplow_normalize', 'snowplow_normalize_incremental_manifest', 'snowplow_normalize_base_events_this_run', var('snowplow__session_timestamp')) }}"
  - "{{ snowplow_utils.grant_usage_on_schemas_built_into(var('snowplow__grant_schemas', true)) }}"


# Tag 'snowplow_normalize_incremental' allows snowplow_incremental_post_hook to identify Snowplow models
# and add their last sucessfull collector_tstamp to the manifest.
models:
  snowplow_normalize:
    +materialized: table
    +file_format:  "{{ 'delta' if target.type not in ['spark'] else 'iceberg'}}"
    +bind: false
    base:
      manifest:
        +schema: "snowplow_manifest"
      scratch:
        +schema: "scratch"
        +tags: "scratch"
        +enabled: "{{ target.type in ['bigquery', 'databricks', 'spark', 'snowflake'] | as_bool() }}"