Merge pull request #9 from kgmcquate/develop

Added string length tests and sampling

.vscode/settings.json

@@ -0,0 +1,14 @@
+{
+    "sqltools.connections": [
+        {
+            "previewLimit": 50,
+            "server": "lake-freeze-db.cu0bcthnum69.us-east-1.rds.amazonaws.com",
+            "port": 5432,
+            "driver": "PostgreSQL",
+            "name": "weather",
+            "database": "postgres",
+            "username": "postgres",
+            "password": "8bF6G!Wy"
+        }
+    ]
+}

README.md

@@ -3,7 +3,9 @@
 ## About
 `dbt-testgen` is a [dbt](https://github.com/dbt-labs/dbt) package that autogenerates dbt test YAML based on real data.
 
-Inspired by [dbt-codegen](https://github.com/dbt-labs/dbt-codegen) and [deequ Constraint Suggestion](https://github.com/awslabs/deequ/blob/master/src/main/scala/com/amazon/deequ/examples/constraint_suggestion_example.md)
+Code documentation available at [here](https://kgmcquate.github.io/dbt-testgen/)
+
+Inspired by [dbt-codegen](https://github.com/dbt-labs/dbt-codegen) and [deequ Constraint Suggestion](https://github.com/awslabs/deequ/blob/master/src/main/scala/com/amazon/deequ/examples/constraint_suggestion_example.md).
 
 ## Install
 `dbt-testgen` currently supports `dbt 1.2.x` or higher.

docs/catalog.json

@@ -1 +1 @@
-{"metadata": {"dbt_schema_version": "https://schemas.getdbt.com/dbt/catalog/v1.json", "dbt_version": "1.7.4", "generated_at": "2024-01-03T04:59:27.467159Z", "invocation_id": "9da1e8ba-623e-4944-bd70-71b4be14443b", "env": {}}, "nodes": {"seed.testgen_integration_tests.colnames_with_spaces": {"metadata": {"type": "BASE TABLE", "schema": "main_integration_test_data", "name": "colnames_with_spaces", "database": "integration_test_data", "comment": null, "owner": null}, "columns": {"first name": {"type": "VARCHAR", "index": 1, "name": "first name", "comment": null}, "age (years)": {"type": "INTEGER", "index": 2, "name": "age (years)", "comment": null}, "current city": {"type": "VARCHAR", "index": 3, "name": "current city", "comment": null}}, "stats": {"has_stats": {"id": "has_stats", "label": "Has Stats?", "value": false, "include": false, "description": "Indicates whether there are statistics for this table"}}, "unique_id": "seed.testgen_integration_tests.colnames_with_spaces"}, "seed.testgen_integration_tests.users": {"metadata": {"type": "BASE TABLE", "schema": "main_integration_test_data", "name": "users", "database": "integration_test_data", "comment": null, "owner": null}, "columns": {"user_id": {"type": "INTEGER", "index": 1, "name": "user_id", "comment": null}, "username": {"type": "VARCHAR", "index": 2, "name": "username", "comment": null}, "email": {"type": "VARCHAR", "index": 3, "name": "email", "comment": null}, "age": {"type": "INTEGER", "index": 4, "name": "age", "comment": null}, "user_status": {"type": "VARCHAR", "index": 5, "name": "user_status", "comment": null}}, "stats": {"has_stats": {"id": "has_stats", "label": "Has Stats?", "value": false, "include": false, "description": "Indicates whether there are statistics for this table"}}, "unique_id": "seed.testgen_integration_tests.users"}}, "sources": {}, "errors": null}
+{"metadata": {"dbt_schema_version": "https://schemas.getdbt.com/dbt/catalog/v1.json", "dbt_version": "1.7.4", "generated_at": "2024-01-03T06:03:44.780433Z", "invocation_id": "40a950e0-7023-41e7-bb8d-8483b6e8e8c4", "env": {}}, "nodes": {"seed.testgen_integration_tests.colnames_with_spaces": {"metadata": {"type": "BASE TABLE", "schema": "main_integration_test_data", "name": "colnames_with_spaces", "database": "integration_test_data", "comment": null, "owner": null}, "columns": {"first name": {"type": "VARCHAR", "index": 1, "name": "first name", "comment": null}, "age (years)": {"type": "INTEGER", "index": 2, "name": "age (years)", "comment": null}, "current city": {"type": "VARCHAR", "index": 3, "name": "current city", "comment": null}}, "stats": {"has_stats": {"id": "has_stats", "label": "Has Stats?", "value": false, "include": false, "description": "Indicates whether there are statistics for this table"}}, "unique_id": "seed.testgen_integration_tests.colnames_with_spaces"}, "seed.testgen_integration_tests.users": {"metadata": {"type": "BASE TABLE", "schema": "main_integration_test_data", "name": "users", "database": "integration_test_data", "comment": null, "owner": null}, "columns": {"user_id": {"type": "INTEGER", "index": 1, "name": "user_id", "comment": null}, "username": {"type": "VARCHAR", "index": 2, "name": "username", "comment": null}, "email": {"type": "VARCHAR", "index": 3, "name": "email", "comment": null}, "age": {"type": "INTEGER", "index": 4, "name": "age", "comment": null}, "user_status": {"type": "VARCHAR", "index": 5, "name": "user_status", "comment": null}}, "stats": {"has_stats": {"id": "has_stats", "label": "Has Stats?", "value": false, "include": false, "description": "Indicates whether there are statistics for this table"}}, "unique_id": "seed.testgen_integration_tests.users"}}, "sources": {}, "errors": null}

integration_tests/generate_docs.sh

@@ -1,6 +1,6 @@
 dbt docs generate
 
-mkdir ../docs
+mkdir -p ../docs
 cp target/catalog.json ../docs
 cp target/index.html ../docs
 cp target/manifest.json ../docs

integration_tests/packages.yml

@@ -1,4 +1,6 @@
 packages:
     - local: ../
     - package: dbt-labs/dbt_utils
-      version: 1.1.1
+      version: 1.1.1
+    - package: calogica/dbt_expectations
+      version: 0.10.1

integration_tests/tests/generate_string_length_tests/string_length_colnames_with_spaces.sql

@@ -0,0 +1,32 @@
+
+
+{% set actual_yaml = testgen.to_yaml(
+        testgen.get_string_length_test_suggestions(
+            ref('colnames_with_spaces'),
+            sample=true,
+            limit=100
+        )
+    )
+%}
+
+{% set expected_yaml %}
+models:
+- name: colnames_with_spaces
+  columns:
+  - name: first name
+    description: String length test generated by dbt-testgen
+    tests:
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 3
+        max_value: 5
+        row_condition: '"first name" is not null'
+  - name: current city
+    description: String length test generated by dbt-testgen
+    tests:
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 7
+        max_value: 13
+        row_condition: '"current city" is not null'
+{% endset %}
+
+{{ assert_equal (actual_yaml | trim, expected_yaml | trim) }}

integration_tests/tests/generate_string_length_tests/string_length_users.sql

@@ -0,0 +1,39 @@
+
+
+{% set actual_yaml = testgen.to_yaml(
+        testgen.get_string_length_test_suggestions(
+            ref('users'),
+            sample=true,
+            limit=100
+        )
+    )
+%}
+
+{% set expected_yaml %}
+models:
+- name: users
+  columns:
+  - name: username
+    description: String length test generated by dbt-testgen
+    tests:
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 8
+        max_value: 15
+        row_condition: '"username" is not null'
+  - name: email
+    description: String length test generated by dbt-testgen
+    tests:
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 18
+        max_value: 25
+        row_condition: '"email" is not null'
+  - name: user_status
+    description: String length test generated by dbt-testgen
+    tests:
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 6
+        max_value: 8
+        row_condition: '"user_status" is not null'
+{% endset %}
+
+{{ assert_equal (actual_yaml | trim, expected_yaml | trim) }}

integration_tests/tests/test_test_selection/test_selection_users.sql

@@ -21,22 +21,34 @@ models:
         min_value: 1
         max_value: 30
   - name: username
-    description: Uniqueness test generated by dbt-testgen
+    description: String length test generated by dbt-testgen
     tests:
     - unique
     - not_null
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 8
+        max_value: 15
+        row_condition: '"username" is not null'
   - name: email
-    description: Uniqueness test generated by dbt-testgen
+    description: String length test generated by dbt-testgen
     tests:
     - unique
     - not_null
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 18
+        max_value: 25
+        row_condition: '"email" is not null'
   - name: user_status
-    description: Accepted values test generated by dbt-testgen
+    description: String length test generated by dbt-testgen
     tests:
     - accepted_values:
         values:
         - active
         - inactive
+    - dbt_expectations.expect_column_value_lengths_to_be_between:
+        min_value: 6
+        max_value: 8
+        row_condition: '"user_status" is not null'
   - name: age
     description: Numeric range test generated by dbt-testgen
     tests:

macros/helpers/sql_functions.sql

@@ -0,0 +1,8 @@
+
+{% macro get_random_function() %}
+    {{ return(adapter.dispatch('get_random_function', 'testgen')()) }}
+{% endmacro %}
+
+{% macro default__get_random_function(colname) %}
+    {{ return("RANDOM") }}
+{% endmacro %}

macros/schema.yml

@@ -0,0 +1,52 @@
+version: 2
+
+macros:
+  - name: get_test_suggestions
+    description: Generates YAML schema file that includes tests for your data
+    arguments:
+      - name: column_name
+        type: string
+        description: The name of the column you want to convert
+      - name: precision
+        type: integer
+        description: Number of decimal places. Defaults to 2.
+
+      - name: table_relation
+        type: Relation
+        description: |
+            The [dbt Relation](https://docs.getdbt.com/reference/dbt-classes#relation) 
+            you wish to generate tests for.
+            Example: ref("mymodel")
+      - name: sample
+        type: bool
+        description: Take a random sample when using the `limit` argument
+      - name: limit
+        type: integer
+        description: Use only this number of records to generate tests.
+      - name: resource_type
+        type: string
+        description: The type of resource that `table_relation` is - 'models', 'seeds', or 'sources'
+      - name: column_config
+        type: dict
+        description: "Configurations to set on columns. Example - {'quote': true}"
+      - name: exclude_types
+        type: list
+        description: Column types to exclude from tests.
+      - name: exclude_cols
+        type: list
+        description: Columns to exclude from tests.
+      - name: tags
+        type: list
+        description: Tags to put on the tests.
+      - name: tests
+        type: list
+        description: "Types of tests to generate. Example: ['uniqueness', 'accepted_values', 'range']"
+      - name: composite_key_length
+        type: integer
+        description: Max length of the composite key for uniqueness tests.
+      - name: dbt_config
+        type: dict
+        description: Existing parsed DBT Schema file to add tests onto.
+      - name: return_object
+        type: bool
+        description: Return the DBT Schema file as a dict object instead of printing YAML.

macros/test_aggregation/get_test_suggestions.sql

@@ -8,7 +8,7 @@
         exclude_types = [],
         exclude_cols = [],
         tags = [],
-        tests = ["uniqueness", "accepted_values", "range"],
+        tests = ["uniqueness", "accepted_values", "range", "string_length"],
         composite_key_length = 1,
         dbt_config = None,
         return_object = false
@@ -58,6 +58,20 @@
             ) %}
         {% endif %}
 
+        {% if "string_length" in tests %}
+            {% set dbt_config = testgen.get_string_length_test_suggestions(
+                table_relation=table_relation,
+                sample=sample,
+                limit=limit,
+                resource_type=resource_type,
+                column_config=column_config,
+                exclude_types=exclude_types,
+                exclude_cols=exclude_cols,
+                tags=tags,
+                dbt_config=dbt_config
+            ) %}
+        {% endif %}
+
         {% if return_object %}
             {{ return(dbt_config) }}
         {% else %}

macros/test_generation/get_accepted_values_test_suggestions.sql

@@ -79,14 +79,28 @@
                 testgen.array_agg(column.column) ~ " AS UNIQUE_VALUES
             from (
                 select " ~ adapter.quote(column.column) ~ "
-                from " ~ table_relation ~ "
+                from base
                 group by " ~ adapter.quote(column.column) ~ "
             ) t1
             "
         ) %}
     {% endfor %}
 
+    {% if limit != None %}
+        {% if sample == true %}
+            {% set limit_stmt = "ORDER BY " ~ testgen.get_random_function() ~ "() LIMIT " ~ limit %}
+        {% else %}
+            {% set limit_stmt = "LIMIT " ~ limit %}
+        {% endif %}
+    {% else %}
+        {% set limit_stmt = "" %}
+    {% endif %}
+
     {% set count_distinct_sql %}
+        WITH base AS (
+            SELECT * FROM {{ table_relation }}
+            {{ limit_stmt }}
+        )
         SELECT * FROM (
             {{ count_distinct_exprs | join("\nUNION ALL\n") }}
         ) t2

macros/test_generation/get_range_test_suggestions.sql

@@ -45,19 +45,33 @@
         {% endif %}
     {% endfor %}
 
+    {% if limit != None %}
+        {% if sample == true %}
+            {% set limit_stmt = "ORDER BY " ~ testgen.get_random_function() ~ "() LIMIT " ~ limit %}
+        {% else %}
+            {% set limit_stmt = "LIMIT " ~ limit %}
+        {% endif %}
+    {% else %}
+        {% set limit_stmt = "" %}
+    {% endif %}
+
     {% set min_max_exprs = [] %}
     {% for column in number_cols %}
         {% do min_max_exprs.append(
             "SELECT '" ~ column.column ~ "' AS COLNAME, " ~ 
                 "MIN(" ~ adapter.quote(column.column) ~ ") as COL_MIN, " ~ 
                 "MAX(" ~ adapter.quote(column.column) ~ ") as COL_MAX, " ~ 
                 loop.index ~ " AS ORDERING " ~ 
-            "FROM " ~ table_relation
+            "FROM base"
         ) %}
     {% endfor %}
 
 
     {% set min_max_sql %}
+        WITH base AS (
+            SELECT * FROM {{ table_relation }}
+            {{ limit_stmt }}
+        )
         SELECT * FROM (
             {{ min_max_exprs | join("\nUNION ALL\n") }}
         ) t1