Chore/monorepo import docs examples (#94)

* Move docs and examples repo into here

* Update gitignore

---------

Signed-off-by: Peter Flook <pflooky@hotmail.com>
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: pflooky <26299147+pflooky@users.noreply.github.com>

Author: pflooky

.github/workflows/benchmark.yml

@@ -0,0 +1,46 @@
+name: Run performance benchmark tests
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: example
+    steps:
+      - name: Checkout monorepo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+      - name: Check if benchmark has already run
+        run: |
+          version=$(grep dataCatererVersion gradle.properties | cut -d= -f2)
+          if [ ! -f benchmark/results/benchmark_results_${version}.txt ]; then
+              echo "No benchmark results for version: $version, starting to run benchmarks"
+          else
+              echo "Benchmarks already run!"
+              exit 1
+          fi
+      - name: Checkout datafusion-comet repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+          repository: apache/datafusion-comet
+          path: example/benchmark/build/datafusion-comet
+      - name: Get Spark query engine jars
+        run: bash benchmark/setup_query_engine_jars.sh
+      - name: Run benchmark script
+        env:
+          DATA_CATERER_MANAGEMENT_TRACK: ${{ secrets.DATA_CATERER_MANAGEMENT_TRACK }}
+        run: |
+          version=$(grep dataCatererVersion gradle.properties | cut -d= -f2)
+          bash benchmark/run_benchmark.sh
+          bash benchmark/compare_benchmark_results.sh "$version"
+      - name: Create pull request
+        uses: peter-evans/create-pull-request@v6
+        with:
+          title: Add benchmark results

.github/workflows/docs-ci.yml

@@ -0,0 +1,40 @@
+name: docs
+
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: write
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.x'
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - name: Set cache key
+        run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: sudo apt-get update && sudo apt-get install -y pngquant
+      - run: pip install mkdocs-material mkdocs-open-in-new-tab "mkdocs-material[imaging]" mike
+      - name: Deploy docs with mike
+        run: |
+          latest_tag=$(git describe --tags --abbrev=0)
+          mike deploy --push --update-aliases "$latest_tag" latest
+    env:
+      GH_TOKEN: ${{ secrets.GH_TOKEN }}

.gitignore

@@ -15,6 +15,12 @@ tmp
 .bloop
 .metals
 .vscode
+site
+.cache
+
+# Python/virtualenvs used by docs
+.venv
+.python-version
 
 app/out
 app/src/test/resources/sample/parquet
@@ -30,8 +36,21 @@ app/src/test/resources/sample/plan-gen
 api/out
 api/src/test/resources/sample/documentation
 
+# UI
 ui/node_modules
 ui/coverage
 
+# Docs build caches
+.docs
+docs/site
+docs/.cache
+docs/.venv
+
+# Example module
+example/build
+example/.gradle
+example/benchmark/build
+example/benchmark/jars
+
 *.class
 *.log

buildSrc/build.gradle.kts

@@ -0,0 +1,18 @@
+plugins {
+    kotlin("jvm") version "1.9.0"
+}
+
+repositories {
+    mavenCentral()
+}
+
+dependencies {
+    implementation("com.fasterxml.jackson.module:jackson-module-kotlin:2.18.2")
+    implementation("com.fasterxml.jackson.dataformat:jackson-dataformat-yaml:2.18.2")
+    implementation("com.networknt:json-schema-validator:1.0.87")
+    implementation(kotlin("stdlib-jdk8"))
+}
+
+kotlin {
+    jvmToolchain(17)
+}

buildSrc/src/main/kotlin/ValidateYamlAgainstSchema.kt

@@ -0,0 +1,61 @@
+import com.fasterxml.jackson.databind.JsonNode
+import com.fasterxml.jackson.databind.ObjectMapper
+import com.fasterxml.jackson.dataformat.yaml.YAMLFactory
+import com.networknt.schema.JsonSchema
+import com.networknt.schema.JsonSchemaFactory
+import com.networknt.schema.SpecVersion
+import com.networknt.schema.ValidationMessage
+import org.gradle.api.DefaultTask
+import org.gradle.api.file.DirectoryProperty
+import org.gradle.api.file.RegularFileProperty
+import org.gradle.api.tasks.InputDirectory
+import org.gradle.api.tasks.InputFile
+import org.gradle.api.tasks.TaskAction
+import org.gradle.api.GradleException
+
+abstract class ValidateYamlAgainstSchema : DefaultTask() {
+
+    @get:InputDirectory
+    abstract val yamlDirectory: DirectoryProperty
+
+    @get:InputFile
+    abstract val schemaFile: RegularFileProperty
+
+    @TaskAction
+    fun validateYaml() {
+        val objectMapper = ObjectMapper(YAMLFactory())
+        objectMapper.readTree(schemaFile.get().asFile.readText())
+        val schemaFactory = JsonSchemaFactory.getInstance(SpecVersion.VersionFlag.V201909)
+        val schemaNode: JsonNode = objectMapper.readTree(schemaFile.asFile.get())
+        val schema: JsonSchema = schemaFactory.getSchema(schemaNode)
+
+        val validationResults = yamlDirectory.asFile.get().walk()
+            .filter { it.isFile && (it.extension == "yaml" || it.extension == "yml") }
+            .map { file ->
+                try {
+                    val yamlNode: JsonNode = objectMapper.readTree(file)
+                    val validationResult: Set<ValidationMessage> = schema.validate(yamlNode)
+                    file to validationResult
+                } catch (e: Exception) {
+                    println("Fail read or validation failed, path: ${file.absolutePath}, message: ${e.message}")
+                    file to setOf()
+                }
+            }
+            .toList()
+
+        val failedValidations = validationResults.filter { it.second.isNotEmpty() }
+
+        if (failedValidations.isNotEmpty()) {
+            val errorMessage = StringBuilder("YAML validation failed for the following files:\n")
+            failedValidations.forEach { (file, errors) ->
+                errorMessage.append("  - file://${file}:\n")
+                errors.forEach { message ->
+                    errorMessage.append("    - ${message.message} (path: ${message.schemaPath})\n")
+                }
+            }
+            throw GradleException(errorMessage.toString())
+        } else {
+            println("All YAML files validated successfully.")
+        }
+    }
+}

docs/.DS_Store

@@ -0,0 +1 @@
+data.catering

docs/CNAME

@@ -0,0 +1,18 @@
+# About
+
+Hi, my name is Peter. I am a Software Developer, mainly focussing on data related services. My experience
+can be found on my [LinkedIn](https://www.linkedin.com/in/peter-flook/).
+
+I have created Data Caterer to help serve individuals and companies with data generation and data testing. It is a
+complex area that has many edge cases or intricacies that are hard to summarise or turn into something actionable and
+repeatable. Through the use of metadata, Data Caterer can help simplify your data testing, simulating production
+environment data, aid in data debugging, or whatever your data use case may be.
+
+Given that it is going to save you and your team time and money, please help in considering financial support. This will
+help the product grow into a sustainable and feature-full service.
+
+## Contact
+
+Please contact us
+via [Slack](https://join.slack.com/t/data-catering/shared_invite/zt-2664ylbpi-w3n7lWAO~PHeOG9Ujpm~~w)
+or via email `hello@data.catering` if you have any questions or queries.