dbt seed truncate tables

.changes/unreleased/Fixes-20231013-120628.yaml

@@ -0,0 +1,7 @@
+kind: Fixes
+body: Overwrite existing rows on existing seed tables. For unmanaged databases (no location specified), the current seed command in
+  dbt-spark appends to existing seeded tables instead overwriting.
+time: 2023-10-13T12:06:28.078483-06:00
+custom:
+  Author: mv1742
+  Issue: "112"

dbt/include/spark/macros/adapters.sql

@@ -342,6 +342,13 @@
   {%- endcall %}
 {% endmacro %}
 
+
+{% macro spark__truncate_relation(relation) -%}
+  {% call statement('truncate_relation', auto_begin=False) -%}
+    truncate {{ relation.type }} if exists {{ relation }}
+  {%- endcall %}
+{% endmacro %}
+
 {% macro spark__drop_relation(relation) -%}
   {% call statement('drop_relation', auto_begin=False) -%}
     drop {{ relation.type }} if exists {{ relation }}

dbt/include/spark/macros/materializations/incremental/incremental.sql

@@ -66,6 +66,10 @@
       re: python models and temporary views.
 
       Also, why do neither drop_relation or adapter.drop_relation work here?!
+      'unmanaged' tables in spark need to manually delete the database
+      otherwise drop statement does not delete the underlying data.
+      TODO:add warning that this feature does not work for Unmanaged tables.
+      Managed tables are fine.
       --#}
       {% call statement('drop_relation') -%}
         drop table if exists {{ tmp_relation }}

dbt/include/spark/macros/materializations/seed.sql

@@ -1,16 +1,22 @@
+<<<<<<< HEAD
+=======
 {% macro spark__get_binding_char() %}
   {{ return('?' if target.method == 'odbc' else '%s') }}
 {% endmacro %}
 
 
+>>>>>>> ab7c116 (Update seed.sql)
 {% macro spark__reset_csv_table(model, full_refresh, old_relation, agate_table) %}
     {% if old_relation %}
+        {{ adapter.truncate_relation(old_relation) }}
         {{ adapter.drop_relation(old_relation) }}
+
+        {{ return(sql) }}
     {% endif %}
     {% set sql = create_csv_table(model, agate_table) %}
     {{ return(sql) }}
 {% endmacro %}
-
+    
 
 {% macro spark__load_csv_rows(model, agate_table) %}
 
@@ -27,7 +33,7 @@
       {% endfor %}
 
       {% set sql %}
-          insert into {{ this.render() }} values
+          insert {% if loop.index0 == 0 -%} overwrite {% else -%} into {% endif -%} {{ this.render() }} values
           {% for row in chunk -%}
               ({%- for col_name in agate_table.column_names -%}
                   {%- set inferred_type = adapter.convert_type(agate_table, loop.index0) -%}
@@ -77,3 +83,4 @@
 
   {{ return(sql) }}
 {% endmacro %}
+