update pipeline to run on GH with configurable deployment repository

.gitattributes

@@ -1,14 +1,10 @@
 ############################
 # Common settings that generally should always be used with your language specific settings
-############################
 
 # Auto detect text files and perform LF normalization
 *          text=auto
-
 #
 # The above will handle all files NOT found below
-#
-
 # Documents
 *.bibtex   text diff=bibtex
 *.doc      diff=astextplain
@@ -33,7 +29,6 @@
 *.txt      text
 *.sql      text
 *.epub     diff=astextplain
-
 # Graphics
 *.png      binary
 *.jpg      binary
@@ -48,7 +43,6 @@
 # use the following line instead.
 # *.svg    binary
 *.eps      binary
-
 # Scripts
 *.bash     text eol=lf
 *.fish     text eol=lf
@@ -58,35 +52,25 @@
 *.bat      text eol=crlf
 *.cmd      text eol=crlf
 *.ps1      text eol=crlf
-
 # Serialisation
 *.json     text
 *.toml     text
 *.xml      text
 *.yaml     text
 *.yml      text
-
 # Archives
 *.7z       binary
 *.gz       binary
 *.tar      binary
 *.tgz      binary
 *.zip      binary
-
 # Text files where line endings should be preserved
 *.patch    -text
-
-#
 # Exclude files from exporting
-#
 .gitattributes export-ignore
 .gitignore     export-ignore
 .gitkeep       export-ignore
-
-############################
 # Web
-############################
-
 # These files are text and should be normalized (Convert crlf => lf)
 *.css           text diff=css
 *.scss          text diff=css
@@ -103,22 +87,16 @@
 *.tag           text
 *.tagx          text
 *.xml           text
-
-
 # Common build-tool wrapper scripts ('.cmd' versions are handled by 'Common.gitattributes')
 mvnw            text eol=lf
 gradlew         text eol=lf
-
-############################
 # Java sources
-############################
 *.java          text diff=java
 *.kt            text diff=kotlin
 *.groovy        text diff=java
 *.scala         text diff=java
 *.gradle        text diff=java
 *.gradle.kts    text diff=kotlin
-
 # These files are binary and should be left untouched (and ideally not checked in)
 # (binary is a macro for -text -diff)
 *.class         binary
@@ -128,10 +106,3 @@ gradlew         text eol=lf
 *.so            binary
 *.war           binary
 *.jks           binary
-
-
-############################
-# Custom Binaries
-############################
-**/*.zip filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text

.github/workflows/build.yaml

@@ -0,0 +1,54 @@
+name: Build Workflow
+
+run-name: 'Build Workflow -- ${{ github.head_ref || github.ref_name }}'
+
+# Pipeline/Workflow Triggers
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+
+jobs:
+  pr-verification:
+    name: Pull Request Validation
+    runs-on: ubuntu-24.04
+    if: github.event_name == 'pull_request'
+    steps:
+      - name: Pull Request Version Validation
+        uses: ikmdev/maven-pull-request-version-validation-action@v2.1.0
+
+  build-job:
+    name: Build Job
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Maven Settings File
+        uses: whelk-io/maven-settings-xml-action@v22
+        with:
+          servers: '[{"id": "tinkar-nexus", "username": "${{secrets.NEXUS_USER}}", "password": "${{secrets.NEXUS_PASSWORD}}"}]'
+          mirrors: '[{"id": "tinkar-nexus", "mirrorOf": "*", "url": "${{secrets.NEXUS_URL}}/repository/maven-public/"}]'
+          repositories: '
+            [
+              {
+                "id": "tinkar-nexus",
+                "name": "tinkar-nexus",
+                "url": "${{secrets.NEXUS_URL}}/repository/maven-public/",
+                "releases": {
+                  "enabled": "true",
+                  "updatePolicy": "always",
+                  "checksumPolicy": "fail"
+                },
+                "snapshots": {
+                  "enabled": "true",
+                  "updatePolicy": "always",
+                  "checksumPolicy": "fail"
+                }
+              }
+            ]'
+          output_file: ../.m2/tinkar-settings.xml
+
+      - name: Build Data Pipeline
+        uses: ikmdev/maven-clean-install-build-action@v3.5.0
+        with:
+          branch_name: ${{github.ref_name}}
+          mvn_additional_args: " -s '/home/runner/work/${{github.event.repository.name}}/.m2/tinkar-settings.xml'"

.github/workflows/post_build.yaml

@@ -0,0 +1,58 @@
+name: Post Build Action
+
+run-name: 'Post Build Action -- ${{github.event.workflow_run.head_branch}}'
+
+on:
+   workflow_run:
+    workflows:
+      - Build Workflow
+    types:
+      - completed
+
+permissions:
+  contents: write 
+
+jobs:
+  post-build:
+    name: Post Build Actions
+    runs-on: ubuntu-24.04
+    if: github.event.workflow_run.conclusion == 'success' && github.repository_owner == 'ikmdev'
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+        with:
+          repository: ${{github.event.workflow_run.head_repository.full_name}}
+          ref: ${{github.event.workflow_run.head_branch}}
+          fetch-depth: 0
+
+      - name: Maven Settings File
+        uses: whelk-io/maven-settings-xml-action@v22
+        with:
+          servers: '
+          [
+            {"id": "tinkar-nexus-private", "username": "admin", "password": "${{secrets.EC2_NEXUS_PASSWORD}}"},
+            {"id": "maven-snapshots", "username": "admin", "password": "${{secrets.EC2_NEXUS_PASSWORD}}"}
+          ]'
+          mirrors: '[{"id": "tinkar-nexus-private", "mirrorOf": "*", "url": "https://nexus.tinkarbuild.com/repository/maven-private/"}]'
+          output_file: ../.m2/tinkar-settings.xml
+
+      - name: Build Plugins
+        uses: ikmdev/maven-clean-install-build-action@v3.5.0
+        with:
+          branch_name: ${{github.ref_name}}
+          mvn_additional_args: " -f plugin"
+
+      - name: Deploy To Nexus
+        shell: bash
+        run: |
+          ./mvnw clean deploy \
+            --batch-mode \
+            -U \
+            -e \
+            -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn \
+            -DskipTests \
+            -DskipITs \
+            -s '/home/runner/work/${{github.event.repository.name}}/.m2/tinkar-settings.xml'\
+            -DaltDeploymentRepository='maven-snapshots::https://nexus.tinkarbuild.com/repository/maven-snapshots/' \
+            -Dmaven.build.cache.enabled=false \
+            -PgenerateData

.mvn/jvm.config

@@ -1,4 +1,3 @@
---enable-preview
 --enable-native-access=ALL-UNNAMED
 --add-modules jdk.incubator.vector
 -Xmx12g

.mvn/wrapper/maven-wrapper.properties

@@ -14,5 +14,6 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.9.9/apache-maven-3.9.9-bin.zip
-wrapperUrl=https://repo.maven.apache.org/maven2/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar
+wrapperVersion=3.3.2
+distributionType=only-script
+distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.9.11/apache-maven-3.9.11-bin.zip

README.md

@@ -1,42 +1,64 @@
-# rxnorm-data
+# RxNorm Pipeline
 
-### Team Ownership - Product Owner
-Data Team
+**Prerequisites**
 
-## Getting Started
-
-Follow these instructions to generate a rxnorm dataset:
+* JDK 24+
+* Maven 3.9.9+
+* Nexus Repository (optional)
+* SnomedCt Pipeline Artifact (see [snomed-ct-data repository](https://github.com/ikmdev/snomed-ct-data))
+
+**Clone Project and Configure Maven Settings**
 
 1. Clone the [rxnorm-data repository](https://github.com/ikmdev/rxnorm-data)
 
-```bash
-git clone [Rep URL]
-```
+   ```
+   git clone https://github.com/ikmdev/rxnorm-data.git
+   ```
+
+2. Configure Maven settings.xml based on the [provided sample](https://ikmdev.atlassian.net/wiki/spaces/IKDT/pages/1036648449/Centralized+Documentation+for+Maven+Settings+File+Configuration).
+
+3. Change local directory to `rxnorm-data`
+
+**Run Origin Packaging**
+
+The following source data is required for this pipeline:
 
-2. Change local directory to `rxnorm-data`
+* Pilot-Defined-RxNorm-with-SNCT-classes-2024-04-10-with-custom-annotations.owl
 
-3. Download RxNorm File from National Library of Medicine (RxNorm-in-OWL/RxNorm Files): https://www.nlm.nih.gov/research/umls/rxnorm/index.html
+More information can be found on National Library of Medicine (RxNorm-in-OWL/RxNorm Files): https://www.nlm.nih.gov/research/umls/rxnorm/index.html
 
-4. Place the downloaded Pilot-Defined-RxNorm_*_.owl in your local Downloads directory.
+1. Place the downloaded file in your ~/Downloads directory.
 
-5. Ensure the rxnorm-data/pom.xml contains the proper tags containing source filename for the downloaded files such as:
-   <source.zip>, <source.version>, <snomed.source.zip>, <starterSet>, etc.
+2. Ensure the properties defined in rxnorm-data/pom.xml are set to the correct file names:
+   - <rxnormOwl>
+   - <source.zip>
 
-6. Create a ~/Solor directory and ensure ~/Solor/generated-data does not exist or is empty.
+3. Run origin packaging and deployment.
 
-7. You can create a reasoned or unreasoned dataset by either including or commenting out the rxnorm-data/pom.xml <module>rxnorm-reasoner</module>
+   To deploy origin artifact to a shared Nexus repository, run the following command, specifying the repository ID and URL in `-DaltDeploymentRepository`
+   ```
+   mvn clean deploy --projects rxnorm-origin --also-make -Ptinkarbuild -DaltDeploymentRepository=tinkar-snapshot::https://nexus.tinkar.org/repository/maven-snapshots/ -Dmaven.build.cache.enabled=false
+   ```
 
-8. Enter the following command to build the dataset:
+   To install origin artifact to a local M2 repository, run the following command:
+   ```
+   mvn clean install --projects rxnorm-origin --also-make -Ptinkarbuild,generateDataLocal -Dmaven.build.cache.enabled=false
+   ```
 
-```bash
-mvn clean install -U "-DMaven.build.cache.enable=false"
-```
+**Run Transformation Pipeline**
 
-9. Enter the following command to deploy the dataset:
+The transformation pipeline can be built after origin data is available in Nexus or a local M2 repository.
 
-```bash
-mvn deploy -f rxnorm-export "-DdeployToNexus=true" "-Dmaven.deploy.skip=true" "-Dmaven.build.cache.enabled=false"
-```
+1. Ensure the rxnorm-data/pom.xml contains the proper tags containing source filename for the downloaded files such as:
+   <source.zip>, <source.version>, <snomedct.version>, <starterSet>, etc.
 
-- NOTE. This repo is built on top of an unreasoned spined array DB from snomed-ct-data. Therefore, make sure you have it built before running step #8.
+2. Build the pipeline with the following command:
+   ```
+   mvn clean install -U -Ptinkarbuild -Dmaven.build.cache.enabled=false
+   ```
 
+3. Deploy transformed data artifacts to Nexus, run the following command:
+   ```
+   mvn deploy --projects rxnorm-export --also-make -Ptinkarbuild -DaltDeploymentRepository=tinkar-snapshot::https://nexus.tinkar.org/repository/maven-snapshots/ -Dmaven.build.cache.enabled=false
+   ```
+

plugin/rxnorm-transformation-maven-plugin/pom.xml

@@ -18,7 +18,6 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-plugin-plugin</artifactId>
-                <version>${maven-plugin-plugin.version}</version>
                 <executions>
                     <execution>
                         <id>mojo-descriptor</id>