2 methods AutoIndexer

Qbeast-io · Dec 7, 2023 · b48074e · b48074e
1 parent 80629c5
commit b48074e
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 2 deletions.
diff --git a/core/src/main/scala/io/qbeast/core/model/AutoIndexer.scala b/core/src/main/scala/io/qbeast/core/model/AutoIndexer.scala
@@ -13,6 +13,14 @@ trait AutoIndexer[DATA] {
    */
   def MAX_COLUMNS_TO_INDEX: Int
 
+  /**
+   * Chooses the columns to index without limiting the number of columns.
+   * @param data
+   *   the data to index
+   * @return
+   */
+  def chooseColumnsToIndex(data: DATA): Seq[String]
+
   /**
    * Chooses the columns to index.
    * @param data
@@ -23,6 +31,6 @@ trait AutoIndexer[DATA] {
    * @return
    *   A sequence with the names of the columns to index
    */
-  def chooseColumnsToIndex(data: DATA, numColumnsToIndex: Int = MAX_COLUMNS_TO_INDEX): Seq[String]
+  def chooseColumnsToIndex(data: DATA, numColumnsToIndex: Int): Seq[String]
 
 }
diff --git a/src/main/scala/io/qbeast/spark/index/SparkAutoIndexer.scala b/src/main/scala/io/qbeast/spark/index/SparkAutoIndexer.scala
@@ -17,11 +17,26 @@ import org.apache.spark.sql.DataFrame
 
 object SparkAutoIndexer extends AutoIndexer[DataFrame] with Serializable {
 
+  /**
+   * The maximum number of columns to index.
+   *
+   * @return
+   */
   override def MAX_COLUMNS_TO_INDEX: Int = MAX_NUM_COLUMNS_TO_INDEX
 
+  /**
+   * Chooses the columns to index without limiting the number of columns.
+   *
+   * @param data
+   *   the data to index
+   * @return
+   */
+  override def chooseColumnsToIndex(data: DataFrame): Seq[String] =
+    chooseColumnsToIndex(data, MAX_COLUMNS_TO_INDEX)
+
   override def chooseColumnsToIndex(
       data: DataFrame,
-      numColumnsToIndex: Int = MAX_COLUMNS_TO_INDEX): Seq[String] = {
+      numColumnsToIndex: Int = MAX_NUM_COLUMNS_TO_INDEX): Seq[String] = {
 
     // IF there's no data to write, we return all the columns to index
     if (data.isEmpty) {