[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

5 files changed, 112 insertions, 44 deletions

diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index b59b700af5..841e77e55e 100644
--- a/R/pkg/R/DataFrame.R
+++ b/R/pkg/R/DataFrame.R
@@ -167,7 +167,7 @@ setMethod("isLocal",
 setMethod("showDF",
           signature(x = "DataFrame"),
           function(x, numRows = 20) {
-            cat(callJMethod(x@sdf, "showString", numToInt(numRows)), "\n")
+            callJMethod(x@sdf, "showString", numToInt(numRows))
           })
 
 #' show
diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R
index af7a6c5820..f82e56fdd8 100644
--- a/R/pkg/inst/tests/test_sparkSQL.R
+++ b/R/pkg/inst/tests/test_sparkSQL.R
@@ -641,7 +641,7 @@ test_that("toJSON() returns an RDD of the correct values", {
 
 test_that("showDF()", {
   df <- jsonFile(sqlCtx, jsonPath)
-  expect_output(showDF(df), "age  name   \nnull Michael\n30   Andy   \n19   Justin ")
+  expect_output(showDF(df), "+----+-------+\n| age|   name|\n+----+-------+\n|null|Michael|\n|  30|   Andy|\n|  19| Justin|\n+----+-------+\n")
 })
 
 test_that("isLocal()", {
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index aac5b8c4c5..22762c5bbb 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -275,9 +275,12 @@ class DataFrame(object):
         >>> df
         DataFrame[age: int, name: string]
         >>> df.show()
-        age name
-        2   Alice
-        5   Bob
+        +---+-----+
+        |age| name|
+        +---+-----+
+        |  2|Alice|
+        |  5|  Bob|
+        +---+-----+
         """
         print(self._jdf.showString(n))
 
@@ -591,12 +594,15 @@ class DataFrame(object):
         given, this function computes statistics for all numerical columns.
 
         >>> df.describe().show()
-        summary age
-        count   2
-        mean    3.5
-        stddev  1.5
-        min     2
-        max     5
+        +-------+---+
+        |summary|age|
+        +-------+---+
+        |  count|  2|
+        |   mean|3.5|
+        | stddev|1.5|
+        |    min|  2|
+        |    max|  5|
+        +-------+---+
         """
         jdf = self._jdf.describe(self._jseq(cols))
         return DataFrame(jdf, self.sql_ctx)
@@ -801,12 +807,18 @@ class DataFrame(object):
         :param subset: optional list of column names to consider.
 
         >>> df4.dropna().show()
-        age height name
-        10  80     Alice
+        +---+------+-----+
+        |age|height| name|
+        +---+------+-----+
+        | 10|    80|Alice|
+        +---+------+-----+
 
         >>> df4.na.drop().show()
-        age height name
-        10  80     Alice
+        +---+------+-----+
+        |age|height| name|
+        +---+------+-----+
+        | 10|    80|Alice|
+        +---+------+-----+
         """
         if how is not None and how not in ['any', 'all']:
             raise ValueError("how ('" + how + "') should be 'any' or 'all'")
@@ -837,25 +849,34 @@ class DataFrame(object):
             then the non-string column is simply ignored.
 
         >>> df4.fillna(50).show()
-        age height name
-        10  80     Alice
-        5   50     Bob
-        50  50     Tom
-        50  50     null
+        +---+------+-----+
+        |age|height| name|
+        +---+------+-----+
+        | 10|    80|Alice|
+        |  5|    50|  Bob|
+        | 50|    50|  Tom|
+        | 50|    50| null|
+        +---+------+-----+
 
         >>> df4.fillna({'age': 50, 'name': 'unknown'}).show()
-        age height name
-        10  80     Alice
-        5   null   Bob
-        50  null   Tom
-        50  null   unknown
+        +---+------+-------+
+        |age|height|   name|
+        +---+------+-------+
+        | 10|    80|  Alice|
+        |  5|  null|    Bob|
+        | 50|  null|    Tom|
+        | 50|  null|unknown|
+        +---+------+-------+
 
         >>> df4.na.fill({'age': 50, 'name': 'unknown'}).show()
-        age height name
-        10  80     Alice
-        5   null   Bob
-        50  null   Tom
-        50  null   unknown
+        +---+------+-------+
+        |age|height|   name|
+        +---+------+-------+
+        | 10|    80|  Alice|
+        |  5|  null|    Bob|
+        | 50|  null|    Tom|
+        | 50|  null|unknown|
+        +---+------+-------+
         """
         if not isinstance(value, (float, int, long, basestring, dict)):
             raise ValueError("value should be a float, int, long, string, or dict")
@@ -1241,11 +1262,17 @@ class Column(object):
 
         >>> df = sc.parallelize([([1, 2], {"key": "value"})]).toDF(["l", "d"])
         >>> df.select(df.l.getItem(0), df.d.getItem("key")).show()
-        l[0] d[key]
-        1    value
+        +----+------+
+        |l[0]|d[key]|
+        +----+------+
+        |   1| value|
+        +----+------+
         >>> df.select(df.l[0], df.d["key"]).show()
-        l[0] d[key]
-        1    value
+        +----+------+
+        |l[0]|d[key]|
+        +----+------+
+        |   1| value|
+        +----+------+
         """
         return self[key]
 
@@ -1255,11 +1282,17 @@ class Column(object):
         >>> from pyspark.sql import Row
         >>> df = sc.parallelize([Row(r=Row(a=1, b="b"))]).toDF()
         >>> df.select(df.r.getField("b")).show()
-        r.b
-        b
+        +---+
+        |r.b|
+        +---+
+        |  b|
+        +---+
         >>> df.select(df.r.a).show()
-        r.a
-        1
+        +---+
+        |r.a|
+        +---+
+        |  1|
+        +---+
         """
         return Column(self._jc.getField(name))
 
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)))