Merge Dev to Main

.github/workflows/build.yml

@@ -0,0 +1,80 @@
+name: build
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+  workflow_dispatch:
+
+jobs:
+  build:
+    env:
+      REGISTRY: us-west1-docker.pkg.dev
+      IMAGE: ${{ vars.ARTIFACT_REGISTRY_REPO }}/tide
+      BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
+
+    permissions:
+      contents: 'read'
+      id-token: 'write'
+
+    runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false && !contains(github.event.head_commit.message, '!ignore')
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Get version from pom.xml
+        id: version
+        run: |
+          VERSION=$(grep -m1 '<version>' pom.xml | sed 's/[^>]*>\([^<]*\).*/\1/')
+          echo "VERSION=${VERSION}" >> $GITHUB_OUTPUT
+          echo "Detected version: ${VERSION}"
+
+      - name: Authenticate with Google Cloud
+        id: auth
+        uses: google-github-actions/auth@v2
+        with:
+          project_id: 'som-rit-infrastructure-prod'
+          workload_identity_provider: 'projects/294515190965/locations/global/workloadIdentityPools/github/providers/susom-github'
+
+      - name: Set up Cloud SDK
+        uses: 'google-github-actions/setup-gcloud@v2'
+        with:
+          version: '>= 363.0.0'
+
+      - name: Authenticate to GAR, get timestamp
+        id: docker
+        run: |
+          gcloud auth configure-docker ${{ env.REGISTRY }}
+          ts=$(date +%Y%m%d%H%M%S)
+          echo "BUILD_ID=build-${ts}" >> $GITHUB_OUTPUT
+          SAFE_BRANCH=$(echo "${{ env.BRANCH_NAME }}" | sed 's/\//-/g')
+          echo "SAFE_BRANCH=${SAFE_BRANCH}" >> $GITHUB_OUTPUT
+
+      - name: Build and push image
+        run: |
+          FULL_IMAGE=${{ env.IMAGE }}                      
+
+          docker build \
+            --build-arg DOCKER_TAG=${{ steps.docker.outputs.BUILD_ID }} \
+            --build-arg GITHUB_REF_NAME=${{ env.BRANCH_NAME }} \
+            --build-arg GITHUB_REF_TYPE=${{ github.ref_type }} \
+            -t ${FULL_IMAGE}:${{ steps.version.outputs.VERSION }} \
+            -t ${FULL_IMAGE}:${{ steps.docker.outputs.BUILD_ID }} \
+            -t ${FULL_IMAGE}:${{ steps.docker.outputs.SAFE_BRANCH }} \
+            -t ${FULL_IMAGE}:latest \
+            .
+
+          docker push --all-tags ${FULL_IMAGE}
+
+      - name: Create Build Summary
+        run: |
+          echo "## Docker Build Summary" >> $GITHUB_STEP_SUMMARY
+          echo "| Key | Value |" >> $GITHUB_STEP_SUMMARY
+          echo "|-----|-------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Image | \`${{ env.REGISTRY }}/${{ env.IMAGE }}:${{ steps.version.outputs.VERSION }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Version | \`${{ steps.version.outputs.VERSION }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Build ID | \`${{ steps.docker.outputs.BUILD_ID }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Branch | \`${{ steps.docker.outputs.SAFE_BRANCH }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Commit | \`${{ github.sha }}\` |" >> $GITHUB_STEP_SUMMARY

.gitignore

@@ -5,3 +5,6 @@ target
 local_deid
 stanford-test-project-1-fa1533111732.json
 output/
+
+# Make sure .github is NOT ignored
+!.github/

Dockerfile

@@ -1,12 +1,14 @@
-FROM maven:3.9.0-eclipse-temurin-17-focal
+FROM maven:3.9-eclipse-temurin-17-focal
 # Do not replace Maven with a generic JRE or JDK since TiDE can be called by Maven
 
 RUN apt update && apt -y install zip unzip curl
+
 RUN mkdir /opt/deid
 WORKDIR /opt/deid
 COPY ./ /opt/deid
 
-RUN mvn clean install -DskipTests
+RUN mvn clean install -DskipTests \
+    -s maven/settings-docker.xml
 #RUN mv target/deid-3.0.30-SNAPSHOT-jar-with-dependencies.jar /opt/deid/deid.jar
 
 #CMD [ "java","-jar","/opt/deid/deid.jar" ]

maven/settings-docker.xml

@@ -0,0 +1,24 @@
+<settings>
+  <profiles>
+    <profile>
+      <id>docker</id>
+      <repositories>
+        <repository>
+          <id>artifact-registry</id>
+          <url>artifactregistry://us-west1-maven.pkg.dev/som-rit-infrastructure-prod/starr-maven</url>
+          <releases><enabled>false</enabled></releases>
+          <snapshots><enabled>false</enabled></snapshots>
+        </repository>
+        <repository>
+          <id>artifact-registry-snapshot</id>
+          <url>artifactregistry://us-west1-maven.pkg.dev/som-rit-infrastructure-prod/starr-maven-snapshot</url>
+          <releases><enabled>false</enabled></releases>
+          <snapshots><enabled>false</enabled></snapshots>
+        </repository>
+      </repositories>
+    </profile>
+  </profiles>
+  <activeProfiles>
+    <activeProfile>docker</activeProfile>
+  </activeProfiles>
+</settings>

pom.xml

@@ -6,19 +6,19 @@
   <name>Starr Core DeId Pipeline</name>
   <groupId>com.github.susom</groupId>
   <artifactId>deid</artifactId>
-  <version>3.0.36-SNAPSHOT</version>
+  <version>3.0.40-SNAPSHOT</version>
   <packaging>jar</packaging>
 
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
-    <java.version>1.8</java.version>
+    <java.version>17</java.version>
 
     <main.class>com.github.susom.starr.deid.Main</main.class>
 
-    <beam.version>2.56.0</beam.version>
-    <jackson.version>2.10.4</jackson.version>
-    <junit-jupiter.version>5.1.0</junit-jupiter.version>
+    <beam.version>2.71.0</beam.version>
+    <jackson.version>2.15.3</jackson.version>
+    <junit-jupiter.version>5.8.2</junit-jupiter.version>
     <version.jopt.simple>5.0.4</version.jopt.simple>
     <version.gcp.bigquery>1.135.4</version.gcp.bigquery>
   </properties>
@@ -92,7 +92,7 @@
     <dependency>
       <groupId>com.fasterxml.jackson.dataformat</groupId>
       <artifactId>jackson-dataformat-csv</artifactId>
-      <version>2.12.4</version>
+      <version>${jackson.version}</version>
     </dependency>
 
     <dependency>
@@ -101,6 +101,29 @@
       <version>1.2</version>
     </dependency>
 
+    <dependency>
+      <groupId>com.fasterxml.jackson.core</groupId>
+      <artifactId>jackson-core</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>com.fasterxml.jackson.core</groupId>
+      <artifactId>jackson-databind</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+
+    <dependency>
+      <groupId>com.fasterxml.jackson.core</groupId>
+      <artifactId>jackson-annotations</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+
+    <dependency>
+      <groupId>com.fasterxml.jackson.dataformat</groupId>
+      <artifactId>jackson-dataformat-yaml</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+
     <dependency>
       <groupId>com.google.cloud</groupId>
       <artifactId>google-cloud-dlp</artifactId>
@@ -131,10 +154,6 @@
           <groupId>com.google.http-client</groupId>
           <artifactId>google-http-client</artifactId>
         </exclusion>
-        <exclusion>
-          <groupId>com.fasterxml.jackson.core</groupId>
-          <artifactId>jackson-core</artifactId>
-        </exclusion>
         <exclusion>
           <groupId>io.grpc</groupId>
           <artifactId>grpc-netty-shaded</artifactId>
@@ -244,7 +263,7 @@
     <dependency>
       <groupId>org.xerial.snappy</groupId>
       <artifactId>snappy-java</artifactId>
-      <version>1.1.10.1</version>
+      <version>1.1.10.4</version>
       <type>jar</type>
       <scope>compile</scope>
     </dependency>
@@ -299,10 +318,11 @@
 
       <plugin>
         <artifactId>maven-compiler-plugin</artifactId>
-        <version>3.1</version>
+        <version>3.10.1</version>
         <configuration>
           <source>${java.version}</source>
           <target>${java.version}</target>
+          <release>17</release>
         </configuration>
       </plugin>