feat: add showDeltaFileSizes function (MrPowers#43)

README.md

@@ -483,6 +483,24 @@ Map("size_in_bytes" -> 1320,
   "number_of_files" -> 2,
   "average_file_size_in_bytes" -> 660)
 ```
+## Show Delta File Sizes
+
+The function `showDeltaFileSizes` displays the size, average size and amount of files of a Delta table in a human readable fashion.
+
+Suppose you have the following table, partitioned by `col1`:
+
+```
++----+----+----+
+|col1|col2|col3|
++----+----+----+
+|   1|   A|   A|
+|   2|   A|   B|
++----+----+----+
+```
+
+Running `DeltaHelpers.showDeltaFileSizes` will display the following into the console:
+
+`"The delta table contains 2 files with a size of 1.32 kB.The average file size is 660 B"`
 
 ## Humanize Bytes
 

src/main/scala/mrpowers/jodie/DeltaHelpers.scala

@@ -535,4 +535,19 @@ object DeltaHelpers {
     val result: String = resultOption.getOrElse(f"$n%.0f" + " B")
     result
   }
+
+  def showDeltaFileSizes(deltaTable: DeltaTable) = {
+    val details: Row = deltaTable.detail().select("numFiles", "sizeInBytes").collect()(0)
+    val (sizeInBytes, numberOfFiles) = 
+      (details.getAs[Long]("sizeInBytes"), details.getAs[Long]("numFiles"))
+    val avgFileSizeInBytes = if (numberOfFiles == 0) 0 else Math.round(sizeInBytes / numberOfFiles)
+    val formatter = java.text.NumberFormat.getIntegerInstance
+
+    val humanized_number_of_files = numberOfFiles.toInt
+    val humanized_size_in_bytes = humanizeBytes(sizeInBytes)
+    val humanized_average_file_size = humanizeBytes(avgFileSizeInBytes)
+
+    println( s"The delta table contains ${humanized_number_of_files} files with a size of ${humanized_size_in_bytes}."
+        + s" The average file size is ${humanized_average_file_size}")
+  }
 }

src/test/scala/mrpowers/jodie/DeltaHelperSpec.scala

@@ -77,6 +77,13 @@ class DeltaHelperSpec
       actual("humanized_number_of_files") == "1"
       actual("humanized_average_file_size_in_bytes") == "1.088 kB"
     }
+
+    it("should display delta file sizes in a human readable fashion") {
+      val path = (os.pwd / "tmp" / "delta-table").toString()
+      createBaseDeltaTable(path, rows)
+      val deltaTable = DeltaTable.forPath(path)
+      DeltaHelpers.showDeltaFileSizes(deltaTable)
+    }
   }
   describe("remove duplicate records from delta table") {
     it("should remove duplicates successful") {