Flesh out the target example and add it to CI.

.github/workflows/ci.yml

@@ -64,6 +64,27 @@ jobs:
     - name: Run sql examples
       run:
         ./run_sql_examples.sh
+  run-target-examples:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+    - name: Cache Spark and friends
+      uses: actions/cache@v3
+      with:
+        path: |
+          spark*.tgz
+          iceberg*.jar
+        key: spark-artifacts
+    - name: Cache Data
+      uses: actions/cache@v3
+      with:
+        path: |
+          data/fetched/*
+        key: data-fetched
+    - name: Run sql examples
+      run:
+        cd target-validator; ./runme.sh
   run-pyspark-examples:
     runs-on: ubuntu-latest
     steps:

target-validator/ex.yaml

@@ -1,4 +1,5 @@
 detailedErrors: true
+numKeyCols: 4
 # We might have a large number of errors so just show the first 5
 numErrorsToReport: 5
 
@@ -10,8 +11,8 @@ email:
     - [email protected]
 
 tables:
-  - db: uk_data
-    table: adult
+  - db: gender_paygaps
+    table: uk
     # Columns that taken together uniquely specifies each row (think of groupBy)
     keyColumns:
       - CompanyNumber

target-validator/runme.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+source ../env_setup.sh 
+set -ex
+export SPARK_VERSION=${SPARK_VERSION:-3.4.1}
+git clone [email protected]:holdenk/data-validator.git
+cd data-validator
+git checkout upgrade-to-modern-spark
+sbt -Dspark=${SPARK_VERSION} clean assembly
+export JAR_PATH="$(pwd)/target/scala-2.12/data-validator-assembly-${SPARK_VERSION}_0.15.0.jar"
+cd ..
+spark-submit --master local  $JAR_PATH --config ex.yaml || echo "Failed as expected."