Add GitHub action to check dbt yaml key sort order

.github/workflows/check_sort_dbt_yaml_files.yaml

@@ -0,0 +1,24 @@
+name: check-sort-dbt-yaml-files
+
+on:
+  pull_request:
+    branches: [master]
+  push:
+    branches: [master]
+
+jobs:
+  check-sort-dbt-yaml-files:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pyyaml
+    - name: Run dbt yaml sort checks
+      run: python scripts/check_sort_dbt_yaml_files.py
+      working-directory: ./dbt

dbt/models/ccbor/schema.yml

@@ -8,44 +8,14 @@ sources:
         columns:
           - name: appeal_id
             description: Appeal ID. Matches the "Complaint" value on the Board of Review Decision Search
-          - name: pin
-            description: '{{ doc("shared_column_pin") }}'
-          - name: class
-            description: '{{ doc("shared_column_class") }}'
-          - name: township_code
-            description: '{{ doc("shared_column_township_code") }}'
-          - name: tax_code
-            description: '{{ doc("shared_column_tax_code") }}'
-          - name: appeal_trk
-            description: First part of the Complaint number
           - name: appeal_seq
             description: Second part of the Complaint number
+          - name: appeal_trk
+            description: First part of the Complaint number
           - name: appeal_type
             description: Appeal type code
           - name: appeal_type_desc
             description: Appeal type description
-          - name: assessor_land_value
-            description: '{{ doc("shared_column_certified_land") }}'
-          - name: assessor_improvement_value
-            description: '{{ doc("shared_column_certified_bldg") }}'
-          - name: assessor_total_value
-            description: '{{ doc("shared_column_certified_tot") }}'
-          - name: bor_land_value
-            description: '{{ doc("shared_column_board_land") }}'
-          - name: bor_improvement_value
-            description: '{{ doc("shared_column_board_bldg") }}'
-          - name: bor_total_value
-            description: '{{ doc("shared_column_board_tot") }}'
-          - name: result
-            description: Board of Review appeal result
-          - name: change_reason
-            description: Reason code for change. This is only populated starting with 2015.
-          - name: change_reason_desc
-            description: Reason description for change. This is only populated starting with 2015.
-          - name: no_change_reason
-            description: Reason code for no change. This is only populated starting with 2015.
-          - name: no_change_reason_desc
-            description: Reason description for no change. This is only populated starting with 2015.
           - name: appellant
             description: Appellant name
           - name: appellant_address
@@ -56,15 +26,45 @@ sources:
             description: Appellant state
           - name: appellant_zip
             description: Appellant zip code
+          - name: assessor_improvement_value
+            description: '{{ doc("shared_column_certified_bldg") }}'
+          - name: assessor_land_value
+            description: '{{ doc("shared_column_certified_land") }}'
+          - name: assessor_total_value
+            description: '{{ doc("shared_column_certified_tot") }}'
           - name: attorney_code
             description: Attorney code; whether an attorney was used. Values are Individual/Pro Se, Exempt, or Attorney.
-          - name: attorney_id
-            description: Attorney ID. This can be used to join to the Attorney list dataset.
+          - name: attorney_firm_name
+            description: Attorney firm name
           - name: attorney_first_name
             description: Attorney first name
+          - name: attorney_id
+            description: Attorney ID. This can be used to join to the Attorney list dataset.
           - name: attorney_last_name
             description: Attorney last name
-          - name: attorney_firm_name
-            description: Attorney firm name
+          - name: bor_improvement_value
+            description: '{{ doc("shared_column_board_bldg") }}'
+          - name: bor_land_value
+            description: '{{ doc("shared_column_board_land") }}'
+          - name: bor_total_value
+            description: '{{ doc("shared_column_board_tot") }}'
+          - name: change_reason
+            description: Reason code for change. This is only populated starting with 2015.
+          - name: change_reason_desc
+            description: Reason description for change. This is only populated starting with 2015.
+          - name: class
+            description: '{{ doc("shared_column_class") }}'
+          - name: no_change_reason
+            description: Reason code for no change. This is only populated starting with 2015.
+          - name: no_change_reason_desc
+            description: Reason description for no change. This is only populated starting with 2015.
+          - name: pin
+            description: '{{ doc("shared_column_pin") }}'
+          - name: result
+            description: Board of Review appeal result
+          - name: tax_code
+            description: '{{ doc("shared_column_tax_code") }}'
           - name: taxyr
-            description: '{{ doc("shared_column_year") }}'
+            description: '{{ doc("shared_column_year") }}'
+          - name: township_code
+            description: '{{ doc("shared_column_township_code") }}'

dbt/models/default/schema/default.vw_card_res_char.yml

@@ -6,18 +6,6 @@ models:
         - type_res
 
     columns:
-      - name: char_air
-        description: '{{ doc("shared_column_char_air") }}'
-      - name: char_attic_fnsh
-        description: '{{ doc("shared_column_char_attic_fnsh") }}'
-      - name: char_attic_type
-        description: '{{ doc("shared_column_char_attic_type") }}'
-      - name: char_bsmt
-        description: '{{ doc("shared_column_char_bsmt") }}'
-      - name: char_bsmt_fin
-        description: '{{ doc("shared_column_char_bsmt_fin") }}'
-      - name: char_ext_wall
-        description: '{{ doc("shared_column_char_ext_wall") }}'
       - name: card
         description: '{{ doc("shared_column_card") }}'
       - name: card_proration_rate
@@ -26,16 +14,28 @@ models:
         description: '{{ doc("shared_column_cdu") }}'
       - name: char_age
         description: '{{ doc("shared_column_char_age") }}'
+      - name: char_air
+        description: '{{ doc("shared_column_char_air") }}'
       - name: char_apts
         description: '{{ doc("shared_column_char_apts") }}'
+      - name: char_attic_fnsh
+        description: '{{ doc("shared_column_char_attic_fnsh") }}'
+      - name: char_attic_type
+        description: '{{ doc("shared_column_char_attic_type") }}'
       - name: char_beds
         description: '{{ doc("shared_column_char_beds") }}'
       - name: char_bldg_sf
         description: '{{ doc("shared_column_char_bldg_sf") }}'
+      - name: char_bsmt
+        description: '{{ doc("shared_column_char_bsmt") }}'
+      - name: char_bsmt_fin
+        description: '{{ doc("shared_column_char_bsmt_fin") }}'
       - name: char_class
         description: '{{ doc("shared_column_char_class") }}'
       - name: char_cnst_qlty
         description: '{{ doc("shared_column_char_cnst_qlty") }}'
+      - name: char_ext_wall
+        description: '{{ doc("shared_column_char_ext_wall") }}'
       - name: char_fbath
         description: '{{ doc("shared_column_char_fbath") }}'
       - name: char_frpl
@@ -48,10 +48,10 @@ models:
         description: '{{ doc("shared_column_char_gar_cnst") }}'
       - name: char_gar1_size
         description: '{{ doc("shared_column_char_gar_size") }}'
-      - name: char_heat
-        description: '{{ doc("shared_column_char_heat") }}'
       - name: char_hbath
         description: '{{ doc("shared_column_char_hbath") }}'
+      - name: char_heat
+        description: '{{ doc("shared_column_char_heat") }}'
       - name: char_land_sf
         description: '{{ doc("shared_column_char_land_sf") }}'
       - name: char_ncu
@@ -84,16 +84,16 @@ models:
         description: '{{ doc("shared_column_class") }}'
       - name: pin
         description: '{{ doc("shared_column_pin") }}'
-      - name: pin_is_multiland
-        description: '{{ doc("shared_column_pin_is_multiland") }}'
+      - name: pin10
+        description: '{{ doc("shared_column_pin10") }}'
       - name: pin_is_multicard
         description: '{{ doc("shared_column_pin_is_multicard") }}'
+      - name: pin_is_multiland
+        description: '{{ doc("shared_column_pin_is_multiland") }}'
       - name: pin_num_cards
         description: '{{ doc("shared_column_pin_num_cards") }}'
       - name: pin_num_landlines
         description: '{{ doc("shared_column_pin_num_landlines") }}'
-      - name: pin10
-        description: '{{ doc("shared_column_pin10") }}'
       - name: seq
         description: '{{ doc("shared_column_seq") }}'
       - name: tieback_key_pin
@@ -110,12 +110,12 @@ models:
         description: '{{ doc("shared_column_year") }}'
 
     data_tests:
+      - row_count:
+          name: default_vw_card_res_char_row_count
+          above: 27347200 # as of 2023-11-29
       - unique_combination_of_columns:
           name: default_vw_card_res_char_unique_by_pin_card_and_year
           combination_of_columns:
             - pin
             - year
             - card
-      - row_count:
-          name: default_vw_card_res_char_row_count
-          above: 27347200 # as of 2023-11-29

dbt/models/default/schema/default.vw_pin_address.yml

@@ -15,12 +15,12 @@ models:
         description: '{{ doc("shared_column_mail_address_zipcode_1") }}'
       - name: mail_address_zipcode_2
         description: '{{ doc("shared_column_mail_address_zipcode_2") }}'
-      - name: prop_address_city_name
-        description: '{{ doc("shared_column_prop_address_city_name") }}'
       - name: pin
         description: '{{ doc("shared_column_pin") }}'
       - name: pin10
         description: '{{ doc("shared_column_pin10") }}'
+      - name: prop_address_city_name
+        description: '{{ doc("shared_column_prop_address_city_name") }}'
       - name: prop_address_full
         description: '{{ doc("shared_column_prop_address_full") }}'
       - name: prop_address_prefix
@@ -37,10 +37,10 @@ models:
         description: '{{ doc("shared_column_prop_address_suffix_1") }}'
       - name: prop_address_suffix_2
         description: '{{ doc("shared_column_prop_address_suffix_2") }}'
-      - name: prop_address_unit_prefix
-        description: '{{ doc("shared_column_prop_address_unit_prefix") }}'
       - name: prop_address_unit_number
         description: '{{ doc("shared_column_prop_address_unit_number") }}'
+      - name: prop_address_unit_prefix
+        description: '{{ doc("shared_column_prop_address_unit_prefix") }}'
       - name: prop_address_zipcode_1
         description: '{{ doc("shared_column_prop_address_zipcode_1") }}'
       - name: prop_address_zipcode_2
@@ -66,18 +66,18 @@ models:
           config:
             where: CAST(year AS int) BETWEEN {{ var('data_test_iasworld_year_start') }} AND {{ var('data_test_iasworld_year_end') }}
             error_if: ">900000"
+      - expression_is_true:
+          name: default_vw_pin_address_numeric_pin
+          expression: REGEXP_COUNT(pin, '[0-9]') = 14 AND LENGTH(pin) = 14
+          additional_select_columns:
+            - pin
+      - row_count:
+          name: default_vw_pin_address_row_count
+          above: 45079937 # as of 2023-11-22
       - unique_combination_of_columns:
           name: default_vw_pin_address_unique_by_14_digit_pin_and_year
           combination_of_columns:
             - pin
             - year
-      - row_count:
-          name: default_vw_pin_address_row_count
-          above: 45079937 # as of 2023-11-22
       # No non-numeric characters in the pin field
-      - expression_is_true:
-          name: default_vw_pin_address_numeric_pin
-          expression: REGEXP_COUNT(pin, '[0-9]') = 14 AND LENGTH(pin) = 14
-          additional_select_columns:
-            - pin
       # TODO: Site addresses are all in Cook County

dbt/models/default/schema/default.vw_pin_appeal.yml

@@ -94,6 +94,10 @@ models:
             where: CAST(year AS int) BETWEEN {{ var('data_test_iasworld_year_start') }} AND {{ var('data_test_iasworld_year_end') }}
             error_if: ">266719"
       # `change` should be an enum
+      - not_accepted_values:
+          name: default_vw_pin_appeal_class_no_hyphens
+          column_name: class
+          values: "2-99"
       - expression_is_true:
           name: default_vw_pin_appeal_no_unexpected_change_values
           expression: change is null or change in ('change', 'no change')
@@ -106,8 +110,4 @@ models:
             where: CAST(year AS int) BETWEEN {{ var('data_test_iasworld_year_start') }} AND {{ var('data_test_iasworld_year_end') }}
       - row_count:
           name: default_vw_pin_appeal_row_count
-          above: 8407667 # as of 2023-11-22
-      - not_accepted_values:
-          name: default_vw_pin_appeal_class_no_hyphens
-          column_name: class
-          values: "2-99"
+          above: 8407667 # as of 2023-11-22

dbt/models/default/schema/default.vw_pin_condo_char.yml

@@ -82,22 +82,22 @@ models:
         description: '{{ doc("shared_column_year") }}'
 
     data_tests:
+      - not_null:
+          name: default_vw_pin_condo_char_bldg_is_mixed_use_not_null
+          column_name: bldg_is_mixed_use
+      - not_null:
+          name: default_vw_pin_condo_char_card_not_null
+          column_name: card
+      - not_null:
+          name: default_vw_pin_condo_char_char_yrblt_not_null
+          column_name: char_yrblt
       - unique_combination_of_columns:
           name: default_vw_pin_condo_char_unique_by_14_digit_pin_and_year
           combination_of_columns:
             - pin
             - year
           config:
             error_if: ">70297"
-      - not_null:
-          name: default_vw_pin_condo_char_card_not_null
-          column_name: card
-      - not_null:
-          name: default_vw_pin_condo_char_char_yrblt_not_null
-          column_name: char_yrblt
-      - not_null:
-          name: default_vw_pin_condo_char_bldg_is_mixed_use_not_null
-          column_name: bldg_is_mixed_use
       # TODO: Non-liveable unit heuristics
       # TODO: Row count matches PARDAT for condo classes
       # TODO: Non-unit and unit parcel count add up to total parcels per

dbt/models/default/schema/default.vw_pin_exempt.yml

@@ -9,12 +9,12 @@ models:
         description: '{{ doc("shared_column_latitude") }}'
       - name: lon
         description: '{{ doc("shared_column_longitude") }}'
-      - name: pin
-        description: '{{ doc("shared_column_pin") }}'
       - name: owner_name
         description: '{{ doc("shared_column_owner_name") }}'
       - name: owner_num
         description: '{{ doc("shared_column_owner_num") }}'
+      - name: pin
+        description: '{{ doc("shared_column_pin") }}'
       - name: property_address
         description: '{{ doc("shared_column_prop_address_full") }}'
       - name: property_city
@@ -26,16 +26,16 @@ models:
       - name: year
         description: '{{ doc("shared_column_year") }}'
     data_tests:
-      - row_count:
-          name: default_vw_pin_exempt_row_count
-          above: 184845 # as of 2023-11-22
+      - not_accepted_values:
+          name: default_vw_pin_exempt_class_no_hyphens
+          column_name: class
+          values: "2-99"
       # No non-numeric characters in the pin field
       - expression_is_true:
           name: default_vw_pin_exempt_numeric_pin
           expression: REGEXP_COUNT(pin, '[0-9]') = 14 AND LENGTH(pin) = 14
           additional_select_columns:
             - pin
-      - not_accepted_values:
-          name: default_vw_pin_exempt_class_no_hyphens
-          column_name: class
-          values: "2-99"
+      - row_count:
+          name: default_vw_pin_exempt_row_count
+          above: 184845 # as of 2023-11-22