Merge pull request #105 from data-catering/feature/sample-api

Update to 0.16.8

Author: pflooky

README.md

@@ -38,7 +38,7 @@ and deep dive into issues [from the generated report](https://data.catering/late
 
 1. Docker
    ```shell
-   docker run -d -i -p 9898:9898 -e DEPLOY_MODE=standalone --name datacaterer datacatering/data-caterer:0.16.7
+   docker run -d -i -p 9898:9898 -e DEPLOY_MODE=standalone --name datacaterer datacatering/data-caterer:0.16.8
    ```
    [Open localhost:9898](http://localhost:9898).
 1. [Run Scala/Java examples](#run-scalajava-examples)

api/build.gradle.kts

@@ -7,8 +7,6 @@
  * This project uses @Incubating APIs which are subject to change.
  */
 val apiArtifactId: String by project
-val scalaVersion: String by project
-val scalaSpecificVersion: String by project
 
 project.base.archivesName.set(apiArtifactId)
 

app/build.gradle.kts

@@ -6,11 +6,6 @@
  * User Manual available at https://docs.gradle.org/7.5.1/userguide/building_java_projects.html
  * This project uses @Incubating APIs which are subject to change.
  */
-val scalaVersion: String by project
-val scalaSpecificVersion: String by project
-val sparkVersion: String by project
-val sparkMajorVersion: String by project
-
 plugins {
     scala
     application

docker-action.sh

@@ -1,7 +1,6 @@
 #!/usr/bin/env bash
 
 version=$(grep version gradle.properties | cut -d= -f2)
-sparkVersion=$(grep sparkVersion gradle.properties | cut -d= -f2)
 platforms="linux/amd64,linux/arm64"
 
 echo "Creating API jars and publishing, version=$version"

docs/get-started/quick-start.md

@@ -85,7 +85,7 @@ cd data-caterer-example && ./run.sh simple-json.yaml
 
 1. Docker
    ```shell
-   docker run -d -i -p 9898:9898 -e DEPLOY_MODE=standalone --name datacaterer datacatering/data-caterer:0.16.7
+   docker run -d -i -p 9898:9898 -e DEPLOY_MODE=standalone --name datacaterer datacatering/data-caterer:0.16.8
    ```
 2. [Open localhost:9898](http://localhost:9898)
 

example/build.gradle.kts

@@ -1,6 +1,3 @@
-val scalaVersion: String by project
-val scalaSpecificVersion: String by project
-
 plugins {
     scala
 }
@@ -10,7 +7,7 @@ repositories {
 }
 
 dependencies {
-    compileOnly("org.scala-lang:scala-library:$scalaSpecificVersion")
+    compileOnly(libs.scala.library)
 
     compileOnly(project(":api"))
 }

gradle.properties

@@ -1,10 +1,5 @@
 group=io.github.data-catering
-version=0.16.7
-
-scalaVersion=2.12
-scalaSpecificVersion=2.12.19
-sparkVersion=3.5.6
-sparkMajorVersion=3.5
+version=0.16.8
 
 org.gradle.parallel=true
 org.gradle.caching=true

misc/CHANGELOG.md

@@ -1,5 +1,26 @@
 # Changelog
 
+## 0.16.8
+
+Introduce sample-data generation APIs with docs, new Gradle run tasks, improved logging, and stricter sink format validation with accompanying tests.
+
+- API/UI:
+  - New endpoints: POST /sample/task-file, POST /sample/task-yaml (supports raw YAML and JSON), POST /sample/schema in PlanRoutes.
+  - Request models & unmarshaller: Add SampleModels and custom TaskYamlUnmarshaller.
+  - Repository wiring: PlanRepository adds GenerateFromTaskFile/TaskYaml/Schema commands using FastSampleGenerator; Spark warm-up on startup.
+- Core/Generation:
+  - Add FastSampleGenerator for lightweight sample data from schema/task YAML/file.
+  - Enhance BatchDataProcessor with debug logging and per-step try/catch.
+- Sink:
+  - SinkFactory: require FORMAT option (throws helpful error); cleanup noisy logs; JSON array unwrap preserved.
+- Build/Run:
+  - Gradle: add runUI and runSpark tasks with JVM args.
+- Docs/Tooling:
+  - Add comprehensive API doc docs/docs/api.md.
+  - Add misc/api/validate_api_docs.py and ignore api_validation_report.txt.
+- Tests:
+  - New tests for sample generation and YAML unmarshal; add sink format error test; update sample YAMLs.
+
 ## 0.16.7
 
 - Fix bug when there are multiple tasks and the number of records generated is not correct