Fixed repo config for Maven and add docker build (#62)

* Configure cache directly in actions/setup-java
* Remove build config for Azure Pipelines and Cloud Build
* Fixed documentation since targetUri option and export endpoint is removed
* Set up docker build

.github/workflows/build.yml

@@ -4,9 +4,22 @@ on:
   push:
     branches:
       - master
+    paths:
+      - src/**
+      - conf/**
+      - Dockerfile
   pull_request:
     branches:
       - master
+    paths:
+      - src/**
+      - conf/**
+      - Dockerfile
+
+env:
+  REGISTRY: europe-north1-docker.pkg.dev/artifact-registry-5n/dapla-pseudo-docker/ssb/dapla
+  IMAGE: dapla-dlp-pseudo-service
+  TAG: ${{ github.ref_name }}-${{ github.sha }}
 
 jobs:
   build:
@@ -23,6 +36,7 @@ jobs:
         with:
           java-version: 21
           distribution: zulu
+          cache: maven
 
       - name: Authenticate to Google Cloud
         id: auth
@@ -32,13 +46,51 @@ jobs:
           service_account: "gh-actions-dapla-pseudo@artifact-registry-5n.iam.gserviceaccount.com"
           token_format: access_token
 
-      - name: Cache Maven packages
-        uses: actions/cache@v3
-        with:
-          path: ~/.m2
-          key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
-          restore-keys: ${{ runner.os }}-m2
-
       - name: Build with Maven and deploy to Artifact Registry
         run: mvn --batch-mode -P ssb-bip deploy
 
+      - name: Clean up artifacts that are no longer needed
+        run: |
+          rm -f target/dapla-dlp-pseudo-service-*-sources.jar
+          rm -f target/dapla-dlp-pseudo-service-*-javadoc.jar
+          ls -al target/dapla-dlp-pseudo-service-*.jar
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to Artifact Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: "oauth2accesstoken"
+          password: "${{ steps.auth.outputs.access_token }}"
+
+      - name: Docker meta
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE }}
+          # Docker tags based on the following events/attributes
+          tags: |
+            type=ref,event=branch
+            type=ref,event=pr
+            type=raw,value=latest,enable={{is_default_branch}}
+            type=semver,pattern=v{{version}}
+            type=semver,pattern=v{{major}}.{{minor}}
+            type=semver,pattern=v{{major}}
+            type=raw,value=${{ env.TAG }}, enable=true
+
+      - name: Build and push
+        id: docker_build
+        uses: docker/build-push-action@v4
+        with:
+          file: Dockerfile
+          push: true
+          context: .
+          tags: |
+            ${{ steps.metadata.outputs.tags }}
+          labels: ${{ steps.metadata.outputs.labels }}
+
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}

Dockerfile

@@ -1,4 +1,4 @@
-FROM azul/zulu-openjdk:17
+FROM azul/zulu-openjdk:21
 RUN apt-get -qq update && apt-get -y dist-upgrade && apt-get -y --no-install-recommends install curl
 COPY target/dapla-dlp-pseudo-service-*.jar dapla-dlp-pseudo-service.jar
 COPY target/classes/logback*.xml /conf/

README.md

@@ -11,49 +11,6 @@ Browse the API docs as:
 
 ## Examples
 
-### Export a dataset
-```sh
-curl "${root_url}/export" -i -H "Authorization: Bearer ${dapla_auth_token}" --data @export-request.json
-```
-Where `root_url` points to an instance of the pseudo-service, `dapla_auth_token` is a JWT token and
-`export-request.json` is a file containing the request. E.g:
-
-```json
-{
-  "sourceDataset": {
-    "root": "gs://ssb-dev-demo-enhjoern-a-data-produkt",
-    "path": "/path/to/data",
-    "version": "123"
-  },
-  "targetContentName": "test",
-  "targetContentType":  "application/json",
-  "targetPassword": "kensentme",
-  "depseudonymize": true,
-  "pseudoRules": [
-    {
-      "name": "kontonummer",
-      "pattern": "**/kontonummer",
-      "func": "fpe-anychar(secret1)"
-    }
-  ]
-}
-```
-
-This example exports all columns matching either `**/foedsel` or `**/kontonummer` from a dataset located in a GCS
-bucket at `gs://ssb-dev-demo-enhjoern-a-data-produkt/path/to/data/123`.
-Columns matching `**/kontonummer` will be depseudonymized using the function `fpe-anychar(secret1)` and then compressed,
-encrypted and uploaded (as json) to the preconfigured data export bucket (see config).      
-
-Note that the above will export all data. If you only need a subset of fields, you can specify this with column selector
-glob expressions, like so:
-```
-  "columnSelectors": [
-    "**/foedsel*",
-    "**/kontonummer"
-  ]
-```
-
-
 ### Pseudonymize JSON file and stream back the result 
 
 ```sh
@@ -94,13 +51,12 @@ curl "${root_url}/depseudonymize/file" \
 }'
 ```
 
-### Depseudonymize JSON file and upload to google cloud storage as zipped CSV-file
+### Depseudonymize JSON file and download a zipped CSV-file
 ```sh
 curl "${root_url}/depseudonymize/file" \
 --header "Authorization: Bearer ${dapla_auth_token}" \
 --form 'data=@src/test/resources/data/15k-pseudonymized.json' \
 --form 'request={
-  "targetUri": "gs://ssb-dev-demo-enhjoern-a-data-export/path/to/depseudonymized-csv.zip",
   "targetContentType": "text/csv",
   "pseudoConfig": {
     "rules": [