Release/snowplow unified/0.5.0

.github/workflows/pr_tests.yml

@@ -39,13 +39,12 @@ env:
   SNOWFLAKE_TEST_WAREHOUSE: ${{ secrets.SNOWFLAKE_TEST_WAREHOUSE }}
 
   # Postgres Connection
-  POSTGRES_TEST_HOST: ${{ secrets.POSTGRES_TEST_HOST }}
   POSTGRES_TEST_USER: ${{ secrets.POSTGRES_TEST_USER }}
   POSTGRES_TEST_PASS: ${{ secrets.POSTGRES_TEST_PASS }}
-  POSTGRES_TEST_PORT: ${{ secrets.POSTGRES_TEST_PORT }}
   POSTGRES_TEST_DBNAME: ${{ secrets.POSTGRES_TEST_DBNAME }}
+  POSTGRES_TEST_HOST: ${{ secrets.POSTGRES_TEST_HOST }}
+  POSTGRES_TEST_PORT: ${{ secrets.POSTGRES_TEST_PORT }}
 
-  # Databricks Connection
   DATABRICKS_TEST_HOST: ${{ secrets.DATABRICKS_TEST_HOST }}
   DATABRICKS_TEST_HTTP_PATH: ${{ secrets.DATABRICKS_TEST_HTTP_PATH }}
   DATABRICKS_TEST_TOKEN: ${{ secrets.DATABRICKS_TEST_TOKEN }}
@@ -63,8 +62,7 @@ jobs:
       fail-fast: false
       matrix:
         dbt_version: ["1.*"]
-        warehouse: ["postgres", "bigquery", "snowflake", "databricks", "redshift"] # TODO: Add RS self-hosted runner
-
+        warehouse: ["postgres", "bigquery", "snowflake", "databricks", "redshift", "spark_iceberg"] # TODO: Add RS self-hosted runner
     services:
       postgres:
         image: postgres:latest
@@ -88,52 +86,90 @@ jobs:
 
       # Remove '*' and replace '.' with '_' in DBT_VERSION & set as SCHEMA_SUFFIX.
       # SCHEMA_SUFFIX allows us to run multiple versions of dbt in parallel without overwriting the output tables
+      - name: Set SCHEMA_SUFFIX env
+        run: echo "SCHEMA_SUFFIX=$(echo ${DBT_VERSION%.*} | tr . _)" >> $GITHUB_ENV
+        env:
+          DBT_VERSION: ${{ matrix.dbt_version }}
+      - name: Configure Docker credentials
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_SNOWPLOWCI_READ_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_SNOWPLOWCI_READ_PASSWORD }}
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v1
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: eu-west-1
+      - name: Set warehouse variables
+        id: set_warehouse
+        run: |
+          WAREHOUSE_PLATFORM=$(echo ${{ matrix.warehouse }} | cut -d'_' -f1)
+          WAREHOUSE_SPECIFIC=$(echo ${{ matrix.warehouse }} | cut -s -d'_' -f2)
+          echo "WAREHOUSE_PLATFORM=${WAREHOUSE_PLATFORM}" >> $GITHUB_ENV
+          echo "WAREHOUSE_SPECIFIC=${WAREHOUSE_SPECIFIC}" >> $GITHUB_ENV
+          echo "warehouse_platform=${WAREHOUSE_PLATFORM}" >> $GITHUB_OUTPUT
+          echo "warehouse_specific=${WAREHOUSE_SPECIFIC}" >> $GITHUB_OUTPUT
+      # Remove '*' and replace '.' with '_' in DBT_VERSION & set as SCHEMA_SUFFIX.
+      # SCHEMA_SUFFIX allows us to run multiple versions of dbt in parallel without overwriting the output tables
       - name: Set SCHEMA_SUFFIX env
         run: echo "SCHEMA_SUFFIX=$(echo ${DBT_VERSION%.*} | tr . _)" >> $GITHUB_ENV
         env:
           DBT_VERSION: ${{ matrix.dbt_version }}
 
       - name: Set DEFAULT_TARGET env
         run: |
-         echo "DEFAULT_TARGET=${{ matrix.warehouse }}" >> $GITHUB_ENV
+         echo "DEFAULT_TARGET=${{matrix.warehouse}}" >> $GITHUB_ENV
 
       - name: Python setup
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
         with:
          python-version: "3.8.x"
 
       - name: Pip cache
-        uses: actions/cache@v4
+        uses: actions/cache@v3
         with:
           path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ matrix.dbt_version }}-${{ matrix.warehouse }}
+          key: ${{ runner.os }}-pip-${{ matrix.dbt_version }}-${{env.WAREHOUSE_PLATFORM}}
           restore-keys: |
-            ${{ runner.os }}-pip-${{ matrix.dbt_version }}-${{ matrix.warehouse }}
+            ${{ runner.os }}-pip-${{ matrix.dbt_version }}-${{env.WAREHOUSE_PLATFORM}}
 
       # Install latest patch version. Upgrade if cache contains old patch version.
       - name: Install dependencies
         run: |
-          pip install pip wheel setuptools
-          pip install -Iv dbt-${{ matrix.warehouse }}==${{ matrix.dbt_version }} --upgrade
+          pip install wheel setuptools
+          pip install -Iv dbt-${{env.WAREHOUSE_PLATFORM}}==${{ matrix.dbt_version }} --upgrade
           dbt deps
-        if: ${{matrix.warehouse != 'spark'}}
-
+        if: ${{env.WAREHOUSE_PLATFORM != 'spark'}}
 
       - name: Install spark dependencies
         run: |
           pip install --upgrade pip wheel setuptools
-          pip install -Iv "dbt-${{ matrix.warehouse }}[ODBC]"==${{ matrix.dbt_version }} --upgrade
+          pip install -Iv "dbt-${{ env.WAREHOUSE_PLATFORM }}[PyHive]"==${{ matrix.dbt_version }} --upgrade
           dbt deps
-        if: ${{matrix.warehouse == 'spark'}}
+        if: ${{env.WAREHOUSE_PLATFORM == 'spark'}}
+
+      - name: Install Docker Compose
+        run: |
+          sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
+          sudo chmod +x /usr/local/bin/docker-compose
 
+
+      - name: Build and start Spark cluster
+        working-directory: .github/workflows/spark_deployment
+        run: |
+          docker-compose up -d
+          echo "Waiting for Spark services to start..."
+          sleep 90
+        if: ${{env.WAREHOUSE_PLATFORM == 'spark'}}
+
       - name: "Pre-test: Drop ci schemas"
         run: |
-          dbt run-operation post_ci_cleanup --target ${{ matrix.warehouse }}
+          dbt run-operation post_ci_cleanup --target ${{matrix.warehouse}}
 
       - name: Run tests
-        run: ./.scripts/integration_test.sh -d ${{ matrix.warehouse }}
+        run: ./.scripts/integration_test.sh -d ${{matrix.warehouse}}
 
-      # post_ci_cleanup sits in utils package
       - name: "Post-test: Drop ci schemas"
         run: |
-          dbt run-operation post_ci_cleanup --target ${{ matrix.warehouse }}
+          dbt run-operation post_ci_cleanup --target ${{matrix.warehouse}}

.github/workflows/spark_deployment/Dockerfile

@@ -0,0 +1,34 @@
+FROM openjdk:11-jre-slim
+
+# Set environment variables
+ENV SPARK_VERSION=3.5.1
+ENV HADOOP_VERSION=3.3.4
+ENV ICEBERG_VERSION=1.4.2
+ENV AWS_SDK_VERSION=1.12.581
+
+# Install necessary tools
+RUN apt-get update && apt-get install -y curl wget procps rsync ssh
+
+# Download and install Spark
+RUN wget https://downloads.apache.org/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz && \
+    tar -xvzf spark-${SPARK_VERSION}-bin-hadoop3.tgz && \
+    mv spark-${SPARK_VERSION}-bin-hadoop3 /spark && \
+    rm spark-${SPARK_VERSION}-bin-hadoop3.tgz
+
+# Set Spark environment variables
+ENV SPARK_HOME=/spark
+ENV PATH=$PATH:$SPARK_HOME/bin:$SPARK_HOME/sbin
+
+# Download necessary JARs
+RUN mkdir -p /spark/jars && \
+    wget https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/${ICEBERG_VERSION}/iceberg-spark-runtime-3.5_2.12-${ICEBERG_VERSION}.jar -O /spark/jars/iceberg-spark-runtime.jar && \
+    wget https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-aws-bundle/${ICEBERG_VERSION}/iceberg-aws-bundle-${ICEBERG_VERSION}.jar -O /spark/jars/iceberg-aws-bundle.jar && \
+    wget https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/${HADOOP_VERSION}/hadoop-aws-${HADOOP_VERSION}.jar -O /spark/jars/hadoop-aws.jar && \
+    wget https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/${AWS_SDK_VERSION}/aws-java-sdk-bundle-${AWS_SDK_VERSION}.jar -O /spark/jars/aws-java-sdk-bundle.jar
+
+# Create directory for Spark events
+RUN mkdir -p /tmp/spark-events
+
+WORKDIR /spark
+
+CMD ["bash"]

.github/workflows/spark_deployment/build_and_push.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# Set variables
+DOCKER_HUB_ORG="snowplow"
+IMAGE_NAME="spark-s3-iceberg"
+TAG="latest"
+
+# Build the image
+echo "Building Docker image..."
+docker build --platform linux/amd64 -t $DOCKER_HUB_ORG/$IMAGE_NAME:$TAG .
+
+# Log in to Docker Hub
+echo "Logging in to Docker Hub..."
+docker login
+
+# Push the image to Docker Hub
+echo "Pushing image to Docker Hub..."
+docker push $DOCKER_HUB_ORG/$IMAGE_NAME:$TAG
+
+echo "Image successfully built and pushed to Docker Hub"

.github/workflows/spark_deployment/docker-compose.yml

@@ -0,0 +1,66 @@
+version: '3'
+
+networks:
+  spark-network:
+    driver: bridge
+
+services:
+  spark-master:
+    image: snowplow/spark-s3-iceberg:latest
+    command: ["/bin/bash", "-c", "/spark/sbin/start-master.sh -h spark-master --properties-file /spark/conf/spark-defaults.conf && tail -f /spark/logs/spark--org.apache.spark.deploy.master.Master-1-*.out"]
+    hostname: spark-master
+    ports:
+      - '8080:8080'
+      - '7077:7077'
+    environment:
+      - SPARK_LOCAL_IP=spark-master
+      - SPARK_MASTER_HOST=spark-master
+      - SPARK_MASTER_PORT=7077
+      - SPARK_MASTER_OPTS="-Dspark.driver.memory=2g"
+      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
+      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
+      - AWS_REGION=eu-west-1
+      - AWS_DEFAULT_REGION=eu-west-1
+    volumes:
+      - ./spark-defaults.conf:/spark/conf/spark-defaults.conf
+    networks:
+      - spark-network
+
+  spark-worker:
+    image: snowplow/spark-s3-iceberg:latest
+    command: ["/bin/bash", "-c", "sleep 10 && /spark/sbin/start-worker.sh spark://spark-master:7077 --properties-file /spark/conf/spark-defaults.conf && tail -f /spark/logs/spark--org.apache.spark.deploy.worker.Worker-*.out"]
+    depends_on:
+      - spark-master
+    environment:
+      - SPARK_WORKER_CORES=2
+      - SPARK_WORKER_MEMORY=4G
+      - SPARK_EXECUTOR_MEMORY=3G
+      - SPARK_LOCAL_IP=spark-worker
+      - SPARK_MASTER=spark://spark-master:7077
+      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
+      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
+      - AWS_REGION=eu-west-1
+      - AWS_DEFAULT_REGION=eu-west-1
+    volumes:
+      - ./spark-defaults.conf:/spark/conf/spark-defaults.conf
+    networks:
+      - spark-network
+
+  thrift-server:
+    image: snowplow/spark-s3-iceberg:latest
+    command: ["/bin/bash", "-c", "sleep 30 && /spark/sbin/start-thriftserver.sh --master spark://spark-master:7077 --driver-memory 2g --executor-memory 3g --hiveconf hive.server2.thrift.port=10000 --hiveconf hive.server2.thrift.bind.host=0.0.0.0 --conf spark.sql.hive.thriftServer.async=true --conf spark.sql.hive.thriftServer.workerQueue.size=2000 --conf spark.sql.hive.thriftServer.maxWorkerThreads=100 --conf spark.sql.hive.thriftServer.minWorkerThreads=50 && tail -f /spark/logs/spark--org.apache.spark.sql.hive.thriftserver.HiveThriftServer2-*.out"]
+    ports:
+      - '10000:10000'
+    depends_on:
+      - spark-master
+      - spark-worker
+    environment:
+      - SPARK_LOCAL_IP=thrift-server
+      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
+      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
+      - AWS_REGION=eu-west-1
+      - AWS_DEFAULT_REGION=eu-west-1
+    volumes:
+      - ./spark-defaults.conf:/spark/conf/spark-defaults.conf
+    networks:
+      - spark-network

.github/workflows/spark_deployment/spark-defaults.conf

@@ -0,0 +1,44 @@
+spark.master                                   spark://spark-master:7077
+
+spark.sql.warehouse.dir                        s3a://dbt-spark-iceberg/github-integration-testing
+spark.sql.catalog.glue                         org.apache.iceberg.spark.SparkCatalog
+spark.sql.catalog.glue.catalog-impl            org.apache.iceberg.aws.glue.GlueCatalog
+spark.sql.catalog.glue.warehouse               s3a://dbt-spark-iceberg/github-integration-testing
+spark.sql.catalog.glue.io-impl                 org.apache.iceberg.aws.s3.S3FileIO
+spark.sql.defaultCatalog                       glue
+spark.sql.catalog.glue.database                dbt-spark-iceberg
+
+spark.hadoop.fs.s3a.impl                       org.apache.hadoop.fs.s3a.S3AFileSystem
+spark.hadoop.fs.s3a.access.key                 <AWS_ACCESS_KEY_ID>
+spark.hadoop.fs.s3a.secret.key                 <AWS_SECRET_ACCESS_KEY>
+spark.hadoop.fs.s3a.endpoint                   s3.eu-west-1.amazonaws.com
+spark.hadoop.fs.s3a.path.style.access          true
+spark.hadoop.fs.s3a.region                     eu-west-1
+spark.hadoop.fs.s3a.aws.region                 eu-west-1
+
+# Enabling AWS SDK V4 signing (required for regions launched after January 2014)
+spark.hadoop.com.amazonaws.services.s3.enableV4 true
+spark.hadoop.fs.s3a.aws.credentials.provider   org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider
+
+# Hive Metastore Configuration (using AWS Glue)
+spark.hadoop.hive.metastore.client.factory.class com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory
+
+# Thrift Server Configuration for better performance in concurrent environments
+spark.sql.hive.thriftServer.singleSession     false
+spark.sql.hive.thriftServer.async             true
+# spark.sql.hive.thriftServer.maxWorkerThreads  100
+# spark.sql.hive.thriftServer.minWorkerThreads  50
+# spark.sql.hive.thriftServer.workerQueue.size  2000
+
+# Memory and Performance Tuning
+# spark.driver.memory                           2g
+# spark.executor.memory                         3g
+# spark.worker.memory                           4g
+spark.network.timeout                         600s
+spark.sql.broadcastTimeout                    600s
+spark.sql.adaptive.enabled                    true
+spark.serializer                              org.apache.spark.serializer.KryoSerializer
+
+# Logging and Debugging
+spark.eventLog.enabled                        true
+spark.eventLog.dir                            /tmp/spark-events

CHANGELOG

@@ -1,3 +1,21 @@
+snowplow-unified 0.5.0 (2024-10-14)
+---------------------------------------
+## Summary
+This release brings significant updates to support Apache Spark with the Iceberg file format, enhances browser context support, improves documentation, and refines language mapping and column tests.
+
+## Features
+- Add support for Apache Spark with Iceberg file format
+- Introduce support for browser_context_2
+- Implement unified language mapping for Android and iOS to produce a common language name
+- Enhance documentation for previously undocumented fields in derived tables
+
+## Under the hood
+- Modify integration tests to support Spark
+- Adjust column tests for conditional scenarios
+
+## Upgrading
+Update the snowplow-unified version in your `packages.yml` file.
+
 snowplow-unified 0.4.5 (2024-07-30)
 ---------------------------------------
 ## Summary

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'snowplow_unified'
-version: '0.4.5'
+version: '0.5.0'
 config-version: 2
 
 require-dbt-version: [">=1.6.0", "<2.0.0"]
@@ -29,8 +29,8 @@ vars:
 
     # WAREHOUSE & TRACKER
     # See https://docs.snowplow.io/docs/modeling-your-data/modeling-your-data-with-dbt/dbt-configuration/unified/ for more information
-    # snowplow__atomic_schema: 'atomic_data_sample' # Only set if not using 'atomic' schema for Snowplow events data
-    # snowplow__database: # Only set if not using target.database for Snowplow events data -- WILL BE IGNORED FOR DATABRICKS
+    #snowplow__atomic_schema: 'atomic_data_sample' # Only set if not using 'atomic' schema for Snowplow events data
+    #snowplow__database: # Only set if not using target.database for Snowplow events data -- WILL BE IGNORED FOR DATABRICKS
     snowplow__dev_target_name: dev
     snowplow__events: "{{ source('atomic', 'events') }}"
     # snowplow__events_table: "events" # Only set if not using 'events' table for Snowplow events data
@@ -42,8 +42,11 @@ vars:
     snowplow__ga4_categories_seed: snowplow_unified_dim_ga4_source_categories
     snowplow__geo_mapping_seed: snowplow_unified_dim_geo_country_mapping
     snowplow__rfc_5646_seed: snowplow_unified_dim_rfc_5646_language_mapping
+    snowplow__iso_639_2t_seed: snowplow_unified_dim_iso_639_2t
+    snowplow__iso_639_3_seed: snowplow_unified_dim_iso_639_3
     snowplow__grant_select_to: []
     snowplow__grant_schema_usage: true
+
 
     # OPERATION & LOGIC
     snowplow__allow_refresh: false
@@ -86,6 +89,7 @@ vars:
     snowplow__enable_iab: false
     snowplow__enable_ua: false
     snowplow__enable_browser_context: false
+    snowplow__enable_browser_context_2 : false
     # add extra mobile fields:
     snowplow__enable_mobile_context: false
     snowplow__enable_geolocation_context: false
@@ -132,6 +136,7 @@ vars:
     snowplow__yauaa_context: nl_basjes_yauaa_context_1
     snowplow__cwv_events: com_snowplowanalytics_snowplow_web_vitals_1
     snowplow__browser_context: com_snowplowanalytics_snowplow_browser_context_1
+    snowplow__browser_context_2: com_snowplowanalytics_snowplow_browser_context_2
     snowplow__session_context: com_snowplowanalytics_snowplow_client_session_1
     snowplow__mobile_context: com_snowplowanalytics_snowplow_mobile_context_1
     snowplow__geolocation_context: com_snowplowanalytics_snowplow_geolocation_context_1
@@ -142,6 +147,7 @@ vars:
     snowplow__deep_link_context: com_snowplowanalytics_mobile_deep_link_1
     snowplow__screen_summary_context: com_snowplowanalytics_mobile_screen_summary_1
 
+
 # Completely or partially remove models from the manifest during run start.
 on-run-start:
   - "{{ snowplow_utils.snowplow_delete_from_manifest(var('models_to_remove',[]), ref('snowplow_unified_incremental_manifest')) }}"
@@ -160,7 +166,8 @@ on-run-end:
 models:
   snowplow_unified:
     +materialized: table
-    +file_format: delta
+    +file_format:  "{{ 'delta' if target.type not in ['spark'] else 'iceberg'}}"
+    +incremental_strategy: "{{ None if target.type not in ['spark'] else 'merge' }}"
     +bind: false
     base:
       +tags: "base"