Add maildat columns to default.vw_pin_address

dbt/models/default/default.vw_pin_address.sql

@@ -1,4 +1,30 @@
 -- Source of truth view for PIN address, both legal and mailing
+
+-- We need a CTE here since MAILDAT is not unique by PIN and TAXYR - it tracks
+-- changes to mailing addresses within a year for a given PIN using MAILSEQ.
+-- For now, we're chosing to use the final address for a pin in any year where
+-- it has more than one since this seems to align with which addresses surface
+-- on the Treasurer's website.
+WITH mail AS (
+    SELECT
+        parid,
+        taxyr,
+        NULLIF(
+            REGEXP_REPLACE(CONCAT_WS(' ', mail1, mail2), '\s+', ' '), ''
+        ) AS mail_address_name,
+        NULLIF(
+            REGEXP_REPLACE(CONCAT_WS(' ', maddr1, maddr2), '\s+', ' '), ''
+        ) AS mail_address_full,
+        mcityname AS mail_address_city_name,
+        mstatecode AS mail_address_state,
+        NULLIF(mzip1, '00000') AS mail_address_zipcode_1,
+        NULLIF(mzip2, '0000') AS mail_address_zipcode_2,
+        mailseq = MAX(mailseq) OVER (PARTITION BY parid, taxyr) AS newest
+    FROM {{ source('iasworld', 'maildat') }}
+    WHERE cur = 'Y'
+        AND deactivat IS NULL
+)
+
 SELECT
     -- Main PIN-level attribute data from iasWorld
     par.parid AS pin,
@@ -29,11 +55,11 @@ SELECT
     NULLIF(leg.zip1, '00000') AS prop_address_zipcode_1,
     NULLIF(leg.zip2, '0000') AS prop_address_zipcode_2,
 
-    -- PIN mailing address from OWNDAT
+    -- PIN owner address from OWNDAT
     NULLIF(CONCAT_WS(
         ' ',
         own.own1, own.own2
-    ), '') AS mail_address_name,
+    ), '') AS owner_address_name,
     CASE WHEN NULLIF(own.addr1, '') IS NOT NULL THEN own.addr1
         WHEN NULLIF(own.addr2, '') IS NOT NULL THEN own.addr2
         ELSE NULLIF(CONCAT_WS(
@@ -42,11 +68,19 @@ SELECT
                 own.adrdir, own.adrstr, own.adrsuf,
                 own.unitdesc, own.unitno
             ), '')
-    END AS mail_address_full,
-    own.cityname AS mail_address_city_name,
-    own.statecode AS mail_address_state,
-    NULLIF(own.zip1, '00000') AS mail_address_zipcode_1,
-    NULLIF(own.zip2, '0000') AS mail_address_zipcode_2
+    END AS owner_address_full,
+    own.cityname AS owner_address_city_name,
+    own.statecode AS owner_address_state,
+    NULLIF(own.zip1, '00000') AS owner_address_zipcode_1,
+    NULLIF(own.zip2, '0000') AS owner_address_zipcode_2,
+
+    -- PIN mailing address from MAILDAT
+    mail.mail_address_name,
+    mail.mail_address_full,
+    mail.mail_address_city_name,
+    mail.mail_address_state,
+    mail.mail_address_zipcode_1,
+    mail.mail_address_zipcode_2
 
 FROM {{ source('iasworld', 'pardat') }} AS par
 LEFT JOIN {{ source('iasworld', 'legdat') }} AS leg
@@ -59,6 +93,10 @@ LEFT JOIN {{ source('iasworld', 'owndat') }} AS own
     AND par.taxyr = own.taxyr
     AND own.cur = 'Y'
     AND own.deactivat IS NULL
+LEFT JOIN mail
+    ON par.parid = mail.parid
+    AND par.taxyr = mail.taxyr
+    AND mail.newest
 WHERE par.cur = 'Y'
     AND par.deactivat IS NULL
     -- Remove any parcels with non-numeric characters

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

@@ -15,6 +15,18 @@ models:
         description: '{{ doc("shared_column_mail_address_zipcode_1") }}'
       - name: mail_address_zipcode_2
         description: '{{ doc("shared_column_mail_address_zipcode_2") }}'
+      - name: owner_address_city_name
+        description: '{{ doc("shared_column_owner_address_city_name") }}'
+      - name: owner_address_full
+        description: '{{ doc("shared_column_owner_address_full") }}'
+      - name: owner_address_name
+        description: '{{ doc("shared_column_owner_address_name") }}'
+      - name: owner_address_state
+        description: '{{ doc("shared_column_owner_address_state") }}'
+      - name: owner_address_zipcode_1
+        description: '{{ doc("shared_column_owner_address_zipcode_1") }}'
+      - name: owner_address_zipcode_2
+        description: '{{ doc("shared_column_owner_address_zipcode_2") }}'
       - name: pin
         description: '{{ doc("shared_column_pin") }}'
       - name: pin10

dbt/models/iasworld/columns.md

@@ -665,6 +665,12 @@ Owner 2 suffix
 Owner number
 {% enddocs %}
 
+## ownseq
+
+{% docs column_ownseq %}
+Owner sequence number
+{% enddocs %}
+
 ## page
 
 {% docs column_page %}
@@ -836,7 +842,10 @@ Split/combination tracking number
 ## ssn
 
 {% docs column_ssn %}
-Social security number
+Social security number.
+
+The CCAO Data Team does not store sensitive data in our data lake, so this
+field is always null.
 {% enddocs %}
 
 ## ssn2
@@ -851,6 +860,12 @@ Social security number 2
 State or province (2 digit)
 {% enddocs %}
 
+## stateid
+
+{% docs column_stateid %}
+State tax ID number
+{% enddocs %}
+
 ## status
 
 {% docs column_status %}
@@ -983,6 +998,12 @@ Sketch vector notes
 Calculation table version
 {% enddocs %}
 
+## vldrsc
+
+{% docs column_vldrsc %}
+No validation reason code
+{% enddocs %}
+
 ## wallhgt
 
 {% docs column_wallhgt %}

dbt/models/iasworld/docs.md

@@ -279,6 +279,19 @@ Neighborhood parameter table for calp, valuation models, etc.
 **Primary Key**: `jur`, `ver`, `nbhd`
 {% enddocs %}
 
+# maildat
+
+{% docs table_maildat %}
+Taxpayer information such as name and mailing address.
+
+### Nuance
+
+- Taxpayer mailing addresses are not necessarily the same as property owner
+  mailing addresses. For property owner addresses, see `iasworld.owndat`.
+
+**Primary Key**: `jur`, `taxyr`, `parid`
+{% enddocs %}
+
 # oby
 
 {% docs table_oby %}
@@ -296,6 +309,8 @@ Property owner information such as name and mailing address.
 ### Nuance
 
 - Mailing addresses and owner names have not been regularly updated since 2017.
+- Property owner mailing addresses are not necessarily the same as taxpayer
+  mailing addresses. For taxpayer addresses, see `iasworld.maildat`.
 
 **Primary Key**: `jur`, `taxyr`, `parid`
 {% enddocs %}

dbt/models/iasworld/schema/iasworld.cname.yml

@@ -142,7 +142,7 @@ sources:
           - name: upd_status
             description: '{{ doc("column_upd_status") }}'
           - name: vldrsc
-            description: No validation reason code
+            description: '{{ doc("column_vldrsc") }}'
           - name: wen
             description: '{{ doc("shared_column_updated_at") }}'
           - name: who