create tests & update docs

sjrusso8 · Apr 19, 2024 · 5343ae3 · 5343ae3
1 parent e050d9f
commit 5343ae3
Show file tree

Hide file tree

Showing 3 changed files with 246 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -62,7 +62,6 @@ The following section outlines some of the larger functionality that are not yet
 
 - ![done] TLS authentication & Databricks compatability via the feature flag `feature = 'tls'`
 - ![open] StreamingQueryManager
-- ![open] Window and ~~Pivot~~ functions
 - ![open] UDFs or any type of functionality that takes a closure (foreach, foreachBatch, etc.)
 
 ### SparkSession
@@ -282,6 +281,7 @@ Spark [Column](https://spark.apache.org/docs/latest/api/python/reference/pyspark
 | like             | ![done] |                                                                              |
 | name             | ![done] |                                                                              |
 | otherwise        | ![open] |                                                                              |
+| over             | ![done] | Refer to **Window** for creating window specifications                       |
 | rlike            | ![done] |                                                                              |
 | startswith       | ![done] |                                                                              |
 | substr           | ![open] |                                                                              |
@@ -612,5 +612,24 @@ An array can be made like `lit([1_i16,2_i16,3_i16])` would result in an `ArrayTy
 | Struct             |                     | ![open] |
 
 
+### Window & WindowSpec
+
+For ease of use it's recommended to use `Window` to create the `WindowSpec`.
+
+| Window                  | API     | Comment |
+|-------------------------|---------|---------|
+| currentRow              | ![done] |         |
+| orderBy                 | ![done] |         |
+| partitionBy             | ![done] |         |
+| rangeBetween            | ![done] |         |
+| rowsBetween             | ![done] |         |
+| unboundedFollowing      | ![done] |         |
+| unboundedPreceding      | ![done] |         |
+| WindowSpec.orderBy      | ![done] |         |
+| WindowSpec.partitionBy  | ![done] |         |
+| WindowSpec.rangeBetween | ![done] |         |
+| WindowSpec.rowsBetween  | ![done] |         |
+
+
 [open]: https://cdn.jsdelivr.net/gh/Readme-Workflows/Readme-Icons@main/icons/octicons/IssueNeutral.svg
 [done]: https://cdn.jsdelivr.net/gh/Readme-Workflows/Readme-Icons@main/icons/octicons/ApprovedChanges.svg
diff --git a/src/column.rs b/src/column.rs
@@ -326,12 +326,28 @@ impl Column {
         invoke_func("isNaN", self)
     }
 
+    /// Defines a windowing column
+    /// # Arguments:
+    ///
+    /// * `window`: a [WindowSpec]
+    ///
+    /// # Example
+    ///
+    /// ```
+    /// let window = Window::new()
+    ///     .partitionBy(col("name"))
+    ///     .orderBy([col("age")])
+    ///     .rangeBetween(Window::unboundedPreceding(), Window::currentRow());
+    ///
+    /// let df = df.withColumn("rank", rank().over(window.clone()))
+    ///     .withColumn("min", min("age").over(window));
+    /// ```
     pub fn over(self, window: WindowSpec) -> Column {
         let window_expr = spark::expression::Window {
             window_function: Some(Box::new(self.expression)),
             partition_spec: window.partition_spec,
             order_spec: window.order_spec,
-            frame_spec: window.frame,
+            frame_spec: window.frame_spec,
         };
 
         let expression = spark::Expression {