[SPARK-6007][SQL] Add numRows param in DataFrame.show()

It is useful to let the user decide the number of rows to show in DataFrame.show

Author: Jacky Li <jacky.likun@huawei.com>

Closes #4767 from jackylk/show and squashes the following commits:

a0e0f4b [Jacky Li] fix testcase
7cdbe91 [Jacky Li] modify according to comment
bb54537 [Jacky Li] for Java compatibility
d7acc18 [Jacky Li] modify according to comments
981be52 [Jacky Li] add numRows param in DataFrame.show()

python/pyspark/sql/dataframe.py

@@ -272,9 +272,9 @@ class DataFrame(object):
         """
         return self._jdf.isLocal()
 
-    def show(self):
+    def show(self, n=20):
         """
-        Print the first 20 rows.
+        Print the first n rows.
 
         >>> df
         DataFrame[age: int, name: string]
@@ -283,7 +283,7 @@ class DataFrame(object):
         2   Alice
         5   Bob
         """
-        print self._jdf.showString().encode('utf8', 'ignore')
+        print self._jdf.showString(n).encode('utf8', 'ignore')
 
     def __repr__(self):
         return "DataFrame[%s]" % (", ".join("%s: %s" % c for c in self.dtypes))

sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala

@@ -159,9 +159,10 @@ class DataFrame protected[sql](
 
   /**
    * Internal API for Python
+   * @param numRows Number of rows to show
    */
-  private[sql] def showString(): String = {
-    val data = take(20)
+  private[sql] def showString(numRows: Int): String = {
+    val data = take(numRows)
     val numCols = schema.fieldNames.length
 
     // For cells that are beyond 20 characters, replace it with the first 17 and "..."
@@ -293,9 +294,15 @@ class DataFrame protected[sql](
    *   1983  03    0.410516        0.442194
    *   1984  04    0.450090        0.483521
    * }}}
+   * @param numRows Number of rows to show
    * @group basic
    */
-  def show(): Unit = println(showString())
+  def show(numRows: Int): Unit = println(showString(numRows))
+
+  /**
+   * Displays the top 20 rows of [[DataFrame]] in a tabular form.
+   */
+  def show(): Unit = show(20)
 
   /**
    * Cartesian join with another [[DataFrame]].

sql/core/src/test/java/test/org/apache/spark/sql/JavaDataFrameSuite.java

@@ -20,6 +20,7 @@ package test.org.apache.spark.sql;
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
+import org.junit.Ignore;
 import org.junit.Test;
 
 import org.apache.spark.sql.*;
@@ -81,4 +82,12 @@ public class JavaDataFrameSuite {
     df.groupBy().agg(countDistinct(col("key"), col("value")));
     df.select(coalesce(col("key")));
   }
+
+  @Ignore
+  public void testShow() {
+    // This test case is intended ignored, but to make sure it compiles correctly
+    DataFrame df = context.table("testData");
+    df.show();
+    df.show(1000);
+  }
 }

sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala

@@ -441,4 +441,9 @@ class DataFrameSuite extends QueryTest {
     checkAnswer(df.select(df("key")), testData.select('key).collect().toSeq)
   }
 
+  ignore("show") {
+    // This test case is intended ignored, but to make sure it compiles correctly
+    testData.select($"*").show()
+    testData.select($"*").show(1000)
+  }
 }