Add argument to get_column_values allow for alternate sorting of column values

CHANGELOG.md

@@ -1,3 +1,8 @@
+# dbt-utils v0.6.3
+
+## Features
+- Adds ability to specify a `sort_column` and `sort_direction` in `get_column_values.
+
 # dbt-utils v0.6.2
 
 ## Fixes

README.md

@@ -442,6 +442,8 @@ group by 1
 This macro returns the unique values for a column in a given [relation](https://docs.getdbt.com/docs/writing-code-in-dbt/class-reference/#relation).
 It takes an options `default` argument for compiling when the relation does not already exist.
 
+The `order_by` argument allows for sorting of values. The default is highest to lowest frequency of values. You can also specify a `sort_direction`.
+
 Usage:
 ```
 -- Returns a list of the top 50 states in the `users` table
@@ -453,6 +455,41 @@ Usage:
 
 ...
 ```
+
+```
+-- Returns a list of user names sorted by name from the `users` table
+{% set names = dbt_utils.get_column_values(table=ref('users'), column='name', default=[], order_by='name') %}
+
+{% for name in names %}
+    ...
+{% endfor %}
+
+...
+```
+
+```
+-- Returns a list of user cities sorted by name from the `users` table
+{% set cities = dbt_utils.get_column_values(table=ref('users'), column='city_name', default=[], order_by='city_name') %}
+
+{% for city in cities %}
+    ...
+{% endfor %}
+
+...
+```
+
+
+```
+-- Returns a list of user cities sorted by name from the `users` table
+{% set cities = dbt_utils.get_column_values(table=ref('users'), column='city_name', default=[], order_by='max(created_at)') %}
+
+{% for city in cities %}
+    ...
+{% endfor %}
+
+...
+```
+
 #### get_relations_by_prefix
 Returns a list of [Relations](https://docs.getdbt.com/docs/writing-code-in-dbt/class-reference/#relation)
 that match a given prefix, with an optional exclusion pattern. It's particularly

integration_tests/models/sql/test_get_column_values.sql

@@ -1,5 +1,5 @@
 
-{% set columns = dbt_utils.get_column_values(ref('data_get_column_values'), 'field', default = []) %}
+{% set columns = dbt_utils.get_column_values(ref('data_get_column_values'), 'field', default = [],  order_by="field", sort_direction="desc") %}
 
 
 {% if target.type == 'snowflake' %}

macros/sql/get_column_values.sql

@@ -10,18 +10,29 @@ Returns:
     A list of distinct values for the specified columns
 #}
 
-{% macro get_column_values(table, column, max_records=none, default=none) -%}
+{% macro get_column_values(table, column, max_records=none, default=none, order_by=none, sort_direction=none) -%}
 
 {#-- Prevent querying of db in parsing mode. This works because this macro does not create any new refs. #}
     {%- if not execute -%}
         {{ return('') }}
     {% endif %}
 {#--  #}
 
+    {%- set order_by = order_by if order_by else 'count(*)' -%}
+    {%- set order_by = 'max(' ~ order_by ~ ')' if order_by == column else order_by -%}
+    {%- set sort_direction -%}
+        {%- if order_by == column -%}
+        {{ sort_direction or 'asc' }} 
+        {%- else -%}
+        {{ sort_direction or 'desc' }}
+        {%- endif -%}
+    {%- endset -%}
+
     {%- set target_relation = adapter.get_relation(database=table.database,
                                           schema=table.schema,
                                          identifier=table.identifier) -%}
 
+    {# If no sort column is supplied, we use the default descending frequency count. #}
     {%- call statement('get_column_values', fetch_result=true) %}
 
         {%- if not target_relation and default is none -%}
@@ -36,16 +47,21 @@ Returns:
 
         {%- else -%}
 
-            select
-                {{ column }} as value
-
-            from {{ target_relation }}
-            group by 1
-            order by count(*) desc
-
-            {% if max_records is not none %}
-            limit {{ max_records }}
-            {% endif %}
+            with sorted_column_values as (
+
+                select
+                    {{ column }} as value,
+                    {{ order_by }} as sort_column
+                from {{ target_relation }}
+                group by 1
+                order by {{ order_by }} {{ sort_direction }}
+                {% if max_records is not none %}
+
+                limit {{ max_records }}
+                {% endif %}
+
+            )
+            select value from sorted_column_values
 
         {% endif %}