Merge branch 'main' of https://github.com/zeotuan/spark-fast-tests in…

…to AssertApproximateSmallDf

.github/workflows/docs.yml

@@ -0,0 +1,17 @@
+name: Docs
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - uses: olafurpg/setup-scala@v10
+      - name: Build docs
+        run: sbt laikaSite
+      - name: Deploy to GH Pages
+        uses: peaceiris/actions-gh-pages@v4
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./target/docs/site

README.md

@@ -1,4 +1,4 @@
-# spark-fast-tests
+# Spark Fast Tests
 
 [![CI](https://github.com/MrPowers/spark-fast-tests/actions/workflows/ci.yml/badge.svg)](https://github.com/MrPowers/spark-fast-tests/actions/workflows/ci.yml)
 
@@ -64,7 +64,7 @@ val expectedDS = Seq(
 ).toDS
 ```
 
-![assert_small_dataset_equality_error_message](https://github.com/MrPowers/spark-fast-tests/blob/master/images/assertSmallDatasetEquality_error_message.png)
+![assert_small_dataset_equality_error_message](https://raw.githubusercontent.com/mrpowers-io/spark-fast-tests/main/images/assertSmallDatasetEquality_error_message.png)
 
 The colors in the error message make it easy to identify the rows that aren't equal.
 
@@ -89,12 +89,14 @@ def myLowerClean(col: Column): Column = {
 
 Here's how long the tests take to execute:
 
-|test method|runtime|
-|-------|--------------------|
-|`assertLargeDataFrameEquality`|709 milliseconds|
-|`assertSmallDataFrameEquality`|166 milliseconds|
-|`assertColumnEquality`|108 milliseconds|
-|`evalString`|26 milliseconds|
+
+| test method                    | runtime          |
+|--------------------------------|------------------|
+| `assertLargeDataFrameEquality` | 709 milliseconds |
+| `assertSmallDataFrameEquality` | 166 milliseconds |
+| `assertColumnEquality`         | 108 milliseconds |
+| `evalString`                   | 26 milliseconds  |
+
 
 `evalString` isn't as robust, but is the fastest.  `assertColumnEquality` is robust and saves a lot of time.
 
@@ -192,7 +194,7 @@ The following code will throw a `ColumnMismatch` error message:
 assertColumnEquality(df, "name", "expected_name")
 ```
 
-![assert_column_equality_error_message](https://github.com/MrPowers/spark-fast-tests/blob/master/images/assertColumnEquality_error_message.png)
+![assert_column_equality_error_message](https://raw.githubusercontent.com/mrpowers-io/spark-fast-tests/main/images/assertColumnEquality_error_message.png)
 
 Mix in the `ColumnComparer` trait to your test class to access the `assertColumnEquality` method:
 

build.sbt

@@ -1,31 +1,31 @@
 enablePlugins(GitVersioning)
-Compile / scalafmtOnCompile:= true
+Compile / scalafmtOnCompile := true
 
 organization := "com.github.mrpowers"
-name := "spark-fast-tests"
+name         := "spark-fast-tests"
 
 version := "1.10.1"
 
-val versionRegex      = """^(.*)\.(.*)\.(.*)$""".r
+val versionRegex = """^(.*)\.(.*)\.(.*)$""".r
 
 val sparkVersion = settingKey[String]("Spark version")
 
-val scala2_13= "2.13.13"
-val scala2_12= "2.12.15"
-val scala2_11= "2.11.17"
+val scala2_13 = "2.13.13"
+val scala2_12 = "2.12.15"
+val scala2_11 = "2.11.17"
 
 sparkVersion := System.getProperty("spark.testVersion", "3.5.1")
 crossScalaVersions := {
   sparkVersion.value match {
     case versionRegex("3", m, _) if m.toInt >= 2 => Seq(scala2_12, scala2_13)
-    case versionRegex("3", _ , _)                => Seq(scala2_12)
+    case versionRegex("3", _, _)                 => Seq(scala2_12)
   }
 }
 
 scalaVersion := crossScalaVersions.value.head
 
 libraryDependencies += "org.apache.spark" %% "spark-sql" % sparkVersion.value % "provided"
-libraryDependencies += "org.scalatest" %% "scalatest" % "3.2.18" % "test"
+libraryDependencies += "org.scalatest"    %% "scalatest" % "3.2.18"           % "test"
 
 credentials += Credentials(Path.userHome / ".sbt" / "sonatype_credentials")
 
@@ -45,4 +45,49 @@ publishMavenStyle := true
 
 publishTo := sonatypePublishToBundle.value
 
-Global / useGpgPinentry := true
+Global / useGpgPinentry := true
+
+enablePlugins(LaikaPlugin)
+
+import laika.format.Markdown
+import laika.config.SyntaxHighlighting
+import laika.ast.Path.Root
+import laika.ast.{Image, ExternalTarget}
+import laika.helium.config._
+import laika.helium.Helium
+
+laikaTheme := Helium.defaults.site
+  .landingPage(
+    title = Some("Spark Fast Tests"),
+    subtitle = Some("Unit testing your Apache Spark application"),
+    latestReleases = Seq(
+      ReleaseInfo("Latest Stable Release", "1.0.0")
+    ),
+    license = Some("Apache 2-0"),
+    titleLinks = Seq(
+      VersionMenu.create(unversionedLabel = "Getting Started"),
+      LinkGroup.create(
+        IconLink.external("https://github.com/mrpowers-io/spark-fast-tests", HeliumIcon.github)
+      )
+    ),
+    linkPanel = Some(
+      LinkPanel(
+        "Documentation",
+        TextLink.internal(Root / "about" / "README.md", "Spark Fast Tests")
+      )
+    ),
+    projectLinks = Seq(
+      LinkGroup.create(
+        TextLink.internal(Root / "api" / "com" / "github" / "mrpowers" / "spark" / "fast" / "tests" / "index.html", "API (Scaladoc)")
+      )
+    ),
+    teasers = Seq(
+      Teaser("Fast", "Handle small dataframes effectively and provide column assertions"),
+      Teaser("Flexible", "Works fine with scalatest, uTest, munit")
+    )
+  )
+  .build
+
+laikaIncludeAPI := true
+laikaExtensions ++= Seq(Markdown.GitHubFlavor, SyntaxHighlighting)
+Laika / sourceDirectories := Seq((ThisBuild / baseDirectory).value / "docs")

docs/about/README.md

@@ -0,0 +1 @@
+../../README.md

project/plugins.sbt

@@ -8,4 +8,6 @@ addSbtPlugin("org.scalameta" % "sbt-scalafmt" % "2.5.2")
 
 addSbtPlugin("com.github.sbt" % "sbt-ci-release" % "1.5.12")
 
-addSbtPlugin("com.github.sbt" % "sbt-pgp" % "2.2.1")
+addSbtPlugin("com.github.sbt" % "sbt-pgp" % "2.2.1")
+
+addSbtPlugin("org.typelevel" % "laika-sbt" % "1.2.0")