diff options
author | 云峤 <chensong.cs@alibaba-inc.com> | 2015-05-04 12:08:38 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-05-04 12:08:38 -0700 |
commit | f32e69ecc333867fc966f65cd0aeaeddd43e0945 (patch) | |
tree | 2dbcc9704acb83d0a7b40f3cee8cc084e29f6dd9 /sql | |
parent | e0833c5958bbd73ff27cfe6865648d7b6e5a99bc (diff) | |
download | spark-f32e69ecc333867fc966f65cd0aeaeddd43e0945.tar.gz spark-f32e69ecc333867fc966f65cd0aeaeddd43e0945.tar.bz2 spark-f32e69ecc333867fc966f65cd0aeaeddd43e0945.zip |
[SPARK-7319][SQL] Improve the output from DataFrame.show()
Author: 云峤 <chensong.cs@alibaba-inc.com>
Closes #5865 from kaka1992/df.show and squashes the following commits:
c79204b [云峤] Update
a1338f6 [云峤] Update python dataFrame show test and add empty df unit test.
734369c [云峤] Update python dataFrame show test and add empty df unit test.
84aec3e [云峤] Update python dataFrame show test and add empty df unit test.
159b3d5 [云峤] update
03ef434 [云峤] update
7394fd5 [云峤] update test show
ced487a [云峤] update pep8
b6e690b [云峤] Merge remote-tracking branch 'upstream/master' into df.show
30ac311 [云峤] [SPARK-7294] ADD BETWEEN
7d62368 [云峤] [SPARK-7294] ADD BETWEEN
baf839b [云峤] [SPARK-7294] ADD BETWEEN
d11d5b9 [云峤] [SPARK-7294] ADD BETWEEN
Diffstat (limited to 'sql')
-rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala | 28 | ||||
-rw-r--r-- | sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala | 19 |
2 files changed, 41 insertions, 6 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala index c421006c8f..cf344710ff 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala @@ -20,6 +20,7 @@ package org.apache.spark.sql import java.io.CharArrayWriter import java.sql.DriverManager + import scala.collection.JavaConversions._ import scala.language.implicitConversions import scala.reflect.ClassTag @@ -28,6 +29,7 @@ import scala.util.control.NonFatal import com.fasterxml.jackson.core.JsonFactory +import org.apache.commons.lang3.StringUtils import org.apache.spark.annotation.{DeveloperApi, Experimental} import org.apache.spark.api.java.JavaRDD import org.apache.spark.api.python.SerDeUtil @@ -175,6 +177,7 @@ class DataFrame private[sql]( * @param numRows Number of rows to show */ private[sql] def showString(numRows: Int): String = { + val sb = new StringBuilder val data = take(numRows) val numCols = schema.fieldNames.length @@ -194,12 +197,25 @@ class DataFrame private[sql]( } } - // Pad the cells - rows.map { row => - row.zipWithIndex.map { case (cell, i) => - String.format(s"%-${colWidths(i)}s", cell) - }.mkString(" ") - }.mkString("\n") + // Create SeparateLine + val sep: String = colWidths.map("-" * _).addString(sb, "+", "+", "+\n").toString() + + // column names + rows.head.zipWithIndex.map { case (cell, i) => + StringUtils.leftPad(cell.toString, colWidths(i)) + }.addString(sb, "|", "|", "|\n") + + sb.append(sep) + + // data + rows.tail.map { + _.zipWithIndex.map { case (cell, i) => + StringUtils.leftPad(cell.toString, colWidths(i)) + }.addString(sb, "|", "|", "|\n") + } + + sb.append(sep) + sb.toString() } override def toString: String = { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala index e286fef23c..ff31e15e2d 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala @@ -598,6 +598,25 @@ class DataFrameSuite extends QueryTest { testData.select($"*").show(1000) } + test("SPARK-7319 showString") { + val expectedAnswer = """+---+-----+ + ||key|value| + |+---+-----+ + || 1| 1| + |+---+-----+ + |""".stripMargin + assert(testData.select($"*").showString(1) === expectedAnswer) + } + + test("SPARK-7327 show with empty dataFrame") { + val expectedAnswer = """+---+-----+ + ||key|value| + |+---+-----+ + |+---+-----+ + |""".stripMargin + assert(testData.select($"*").filter($"key" < 0).showString(1) === expectedAnswer) + } + test("createDataFrame(RDD[Row], StructType) should convert UDTs (SPARK-6672)") { val rowRDD = TestSQLContext.sparkContext.parallelize(Seq(Row(new ExamplePoint(1.0, 2.0)))) val schema = StructType(Array(StructField("point", new ExamplePointUDT(), false))) |