Snapshot column names

.changes/unreleased/Features-20240903-155618.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Allow configuring of snapshot column names
+time: 2024-09-03T15:56:18.211492-04:00
+custom:
+  Author: gshank
+  Issue: "289"

dbt/adapters/base/impl.py

@@ -82,7 +82,6 @@
     QuoteConfigTypeError,
     RelationReturnedMultipleResultsError,
     RenameToNoneAttemptedError,
-    SnapshotTargetIncompleteError,
     SnapshotTargetNotSnapshotTableError,
     UnexpectedNonTimestampError,
 )
@@ -740,7 +739,9 @@ def get_missing_columns(
         return [col for (col_name, col) in from_columns.items() if col_name in missing_columns]
 
     @available.parse_none
-    def valid_snapshot_target(self, relation: BaseRelation) -> None:
+    def valid_snapshot_target(
+        self, relation: BaseRelation, column_names: Optional[Dict[str, str]] = None
+    ) -> None:
         """Ensure that the target relation is valid, by making sure it has the
         expected columns.
 
@@ -758,21 +759,15 @@ def valid_snapshot_target(self, relation: BaseRelation) -> None:
 
         columns = self.get_columns_in_relation(relation)
         names = set(c.name.lower() for c in columns)
-        expanded_keys = ("scd_id", "valid_from", "valid_to")
-        extra = []
+        columns = ("dbt_scd_id", "dbt_valid_from", "dbt_valid_to")
         missing = []
-        for legacy in expanded_keys:
-            desired = "dbt_" + legacy
+        for column in columns:
+            desired = column_names[column] if column_names else column
             if desired not in names:
                 missing.append(desired)
-                if legacy in names:
-                    extra.append(legacy)
 
         if missing:
-            if extra:
-                raise SnapshotTargetIncompleteError(extra, missing)
-            else:
-                raise SnapshotTargetNotSnapshotTableError(missing)
+            raise SnapshotTargetNotSnapshotTableError(missing)
 
     @available.parse_none
     def expand_target_column_types(

dbt/adapters/exceptions/compilation.py

@@ -150,7 +150,7 @@ def __init__(self, missing: List):
         super().__init__(msg=self.get_message())
 
     def get_message(self) -> str:
-        msg = 'Snapshot target is not a snapshot table (missing "{}")'.format(
+        msg = 'Snapshot target is not a snapshot table or is missing configured columns (missing "{}")'.format(
             '", "'.join(self.missing)
         )
         return msg

dbt/include/global_project/macros/materializations/snapshots/helpers.sql

@@ -35,6 +35,11 @@
 {% endmacro %}
 
 {% macro default__snapshot_staging_table(strategy, source_sql, target_relation) -%}
+    {% set dbt_scd_id = config.get('dbt_scd_id_column_name') or "dbt_scd_id" %}
+    {% set dbt_updated_at = config.get('dbt_updated_at_column_name') or "dbt_updated_at" %}
+    {% set dbt_valid_from = config.get('dbt_valid_from_column_name') or "dbt_valid_from" %}
+    {% set dbt_valid_to = config.get('dbt_valid_to_column_name') or "dbt_valid_to" %}
+
 
     with snapshot_query as (
 
@@ -48,7 +53,7 @@
             {{ strategy.unique_key }} as dbt_unique_key
 
         from {{ target_relation }}
-        where dbt_valid_to is null
+        where {{ dbt_valid_to }} is null
 
     ),
 
@@ -57,10 +62,10 @@
         select
             *,
             {{ strategy.unique_key }} as dbt_unique_key,
-            {{ strategy.updated_at }} as dbt_updated_at,
-            {{ strategy.updated_at }} as dbt_valid_from,
-            nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as dbt_valid_to,
-            {{ strategy.scd_id }} as dbt_scd_id
+            {{ strategy.updated_at }} as {{ dbt_updated_at }},
+            {{ strategy.updated_at }} as {{ dbt_valid_from }},
+            nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ dbt_valid_to }},
+            {{ strategy.scd_id }} as {{ dbt_scd_id }}
 
         from snapshot_query
     ),
@@ -70,9 +75,9 @@
         select
             *,
             {{ strategy.unique_key }} as dbt_unique_key,
-            {{ strategy.updated_at }} as dbt_updated_at,
-            {{ strategy.updated_at }} as dbt_valid_from,
-            {{ strategy.updated_at }} as dbt_valid_to
+            {{ strategy.updated_at }} as {{ dbt_updated_at }},
+            {{ strategy.updated_at }} as {{ dbt_valid_from }},
+            {{ strategy.updated_at }} as {{ dbt_valid_to }}
 
         from snapshot_query
     ),
@@ -111,7 +116,7 @@
         select
             'update' as dbt_change_type,
             source_data.*,
-            snapshotted_data.dbt_scd_id
+            snapshotted_data.{{ dbt_scd_id }}
 
         from updates_source_data as source_data
         join snapshotted_data on snapshotted_data.dbt_unique_key = source_data.dbt_unique_key
@@ -128,10 +133,10 @@
         select
             'delete' as dbt_change_type,
             source_data.*,
-            {{ snapshot_get_time() }} as dbt_valid_from,
-            {{ snapshot_get_time() }} as dbt_updated_at,
-            {{ snapshot_get_time() }} as dbt_valid_to,
-            snapshotted_data.dbt_scd_id
+            {{ snapshot_get_time() }} as {{ dbt_valid_from }},
+            {{ snapshot_get_time() }} as {{ dbt_updated_at }},
+            {{ snapshot_get_time() }} as {{ dbt_valid_to }},
+            snapshotted_data.{{ dbt_scd_id }}
 
         from snapshotted_data
         left join deletes_source_data as source_data on snapshotted_data.dbt_unique_key = source_data.dbt_unique_key
@@ -155,12 +160,16 @@
 {% endmacro %}
 
 {% macro default__build_snapshot_table(strategy, sql) %}
+    {% set dbt_scd_id = config.get('dbt_scd_id_column_name') or "dbt_scd_id" %}
+    {% set dbt_updated_at = config.get('dbt_updated_at_column_name') or "dbt_updated_at" %}
+    {% set dbt_valid_from = config.get('dbt_valid_from_column_name') or "dbt_valid_from" %}
+    {% set dbt_valid_to = config.get('dbt_valid_to_column_name') or "dbt_valid_to" %}
 
     select *,
-        {{ strategy.scd_id }} as dbt_scd_id,
-        {{ strategy.updated_at }} as dbt_updated_at,
-        {{ strategy.updated_at }} as dbt_valid_from,
-        nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as dbt_valid_to
+        {{ strategy.scd_id }} as {{ dbt_scd_id }},
+        {{ strategy.updated_at }} as {{ dbt_updated_at }},
+        {{ strategy.updated_at }} as {{ dbt_valid_from }},
+        nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ dbt_valid_to }}
     from (
         {{ sql }}
     ) sbq

dbt/include/global_project/macros/materializations/snapshots/snapshot.sql

@@ -1,5 +1,4 @@
 {% materialization snapshot, default %}
-  {%- set config = model['config'] -%}
 
   {%- set target_table = model.get('alias', model.get('name')) -%}
 
@@ -24,7 +23,7 @@
   {{ run_hooks(pre_hooks, inside_transaction=True) }}
 
   {% set strategy_macro = strategy_dispatch(strategy_name) %}
-  {% set strategy = strategy_macro(model, "snapshotted_data", "source_data", config, target_relation_exists) %}
+  {% set strategy = strategy_macro(model, "snapshotted_data", "source_data", model['config'], target_relation_exists) %}
 
   {% if not target_relation_exists %}
 
@@ -33,7 +32,10 @@
 
   {% else %}
 
-      {{ adapter.valid_snapshot_target(target_relation) }}
+      {% set snapshot_table_column_names = config.get("snapshot_table_column_names") %}
+      {{ log("stcn: " ~ snapshot_table_column_names, info=true) }}
+
+      {{ adapter.valid_snapshot_target(target_relation, snapshot_table_column_names) }}
 
       {% set staging_table = build_snapshot_staging_table(strategy, sql, target_relation) %}
 

dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql

@@ -7,15 +7,18 @@
 {% macro default__snapshot_merge_sql(target, source, insert_cols) -%}
     {%- set insert_cols_csv = insert_cols | join(', ') -%}
 
+    {%- set dbt_scd_id = config.get("dbt_scd_id_column_name") or "dbt_scd_id" -%}
+    {%- set dbt_valid_to = config.get("dbt_valid_to_column_name") or "dbt_valid_to" -%}
+
     merge into {{ target.render() }} as DBT_INTERNAL_DEST
     using {{ source }} as DBT_INTERNAL_SOURCE
-    on DBT_INTERNAL_SOURCE.dbt_scd_id = DBT_INTERNAL_DEST.dbt_scd_id
+    on DBT_INTERNAL_SOURCE.{{ dbt_scd_id }} = DBT_INTERNAL_DEST.{{ dbt_scd_id }}
 
     when matched
-     and DBT_INTERNAL_DEST.dbt_valid_to is null
+     and DBT_INTERNAL_DEST.{{ dbt_valid_to }} is null
      and DBT_INTERNAL_SOURCE.dbt_change_type in ('update', 'delete')
         then update
-        set dbt_valid_to = DBT_INTERNAL_SOURCE.dbt_valid_to
+        set {{ dbt_valid_to }} = DBT_INTERNAL_SOURCE.{{ dbt_valid_to }}
 
     when not matched
      and DBT_INTERNAL_SOURCE.dbt_change_type = 'insert'

dbt/include/global_project/macros/materializations/snapshots/strategies.sql

@@ -49,10 +49,12 @@
 {#
     Core strategy definitions
 #}
-{% macro snapshot_timestamp_strategy(node, snapshotted_rel, current_rel, config, target_exists) %}
-    {% set primary_key = config['unique_key'] %}
-    {% set updated_at = config['updated_at'] %}
-    {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes', false) %}
+
+{% macro snapshot_timestamp_strategy(node, snapshotted_rel, current_rel, model_config, target_exists) %}
+    {% set primary_key = config.get('unique_key') %}
+    {% set updated_at = config.get('updated_at') %}
+    {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes') or false %}
+    {% set dbt_valid_from = config.get("dbt_valid_from_column_name") or "dbt_valid_from" %}
 
     {#/*
         The snapshot relation might not have an {{ updated_at }} value if the
@@ -64,7 +66,7 @@
         See https://github.com/dbt-labs/dbt-core/issues/2350
     */ #}
     {% set row_changed_expr -%}
-        ({{ snapshotted_rel }}.dbt_valid_from < {{ current_rel }}.{{ updated_at }})
+        ({{ snapshotted_rel }}.{{ dbt_valid_from }} < {{ current_rel }}.{{ updated_at }})
     {%- endset %}
 
     {% set scd_id_expr = snapshot_hash_arguments([primary_key, updated_at]) %}
@@ -133,11 +135,11 @@
 {%- endmacro %}
 
 
-{% macro snapshot_check_strategy(node, snapshotted_rel, current_rel, config, target_exists) %}
-    {% set check_cols_config = config['check_cols'] %}
-    {% set primary_key = config['unique_key'] %}
-    {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes', false) %}
-    {% set updated_at = config.get('updated_at', snapshot_get_time()) %}
+{% macro snapshot_check_strategy(node, snapshotted_rel, current_rel, model_config, target_exists) %}
+    {% set check_cols_config = config.get('check_cols') %}
+    {% set primary_key = config.get('unique_key') %}
+    {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes') or false %}
+    {% set updated_at = config.get('updated_at') or snapshot_get_time() %}
 
     {% set column_added = false %}