Skip to content

[SPARK-11970] [SQL] Add function SHOW to Dataset APIs #9955

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
gatorsmile wants to merge 2 commits into from
Closed

[SPARK-11970] [SQL] Add function SHOW to Dataset APIs #9955

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1fb34ba
Add show into dataset API
gatorsmile Nov 25, 2015
a4428c3
Merge remote-tracking branch 'upstream/master' into show
gatorsmile Nov 25, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
107 changes: 2 additions & 105 deletions sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,13 +164,11 @@ class DataFrame private[sql](
* @param _numRows Number of rows to show
* @param truncate Whether truncate long strings and align cells right
*/
private[sql] def showString(_numRows: Int, truncate: Boolean = true): String = {
override private[sql] def showString(_numRows: Int, truncate: Boolean = true): String = {
val numRows = _numRows.max(0)
val sb = new StringBuilder
val takeResult = take(numRows + 1)
val hasMoreData = takeResult.length > numRows
val data = takeResult.take(numRows)
val numCols = schema.fieldNames.length

// For array values, replace Seq and Array with square brackets
// For cells that are beyond 20 characters, replace it with the first 17 and "..."
Expand All @@ -186,50 +184,7 @@ class DataFrame private[sql](
}: Seq[String]
}

// Initialise the width of each column to a minimum value of '3'
val colWidths = Array.fill(numCols)(3)

// Compute the width of each column
for (row <- rows) {
for ((cell, i) <- row.zipWithIndex) {
colWidths(i) = math.max(colWidths(i), cell.length)
}
}

// Create SeparateLine
val sep: String = colWidths.map("-" * _).addString(sb, "+", "+", "+\n").toString()

// column names
rows.head.zipWithIndex.map { case (cell, i) =>
if (truncate) {
StringUtils.leftPad(cell, colWidths(i))
} else {
StringUtils.rightPad(cell, colWidths(i))
}
}.addString(sb, "|", "|", "|\n")

sb.append(sep)

// data
rows.tail.map {
_.zipWithIndex.map { case (cell, i) =>
if (truncate) {
StringUtils.leftPad(cell.toString, colWidths(i))
} else {
StringUtils.rightPad(cell.toString, colWidths(i))
}
}.addString(sb, "|", "|", "|\n")
}

sb.append(sep)

// For Data that has more than "numRows" records
if (hasMoreData) {
val rowsString = if (numRows == 1) "row" else "rows"
sb.append(s"only showing top $numRows $rowsString\n")
}

sb.toString()
formatString ( rows, numRows, hasMoreData, truncate )
}

/**
Expand Down Expand Up @@ -306,64 +261,6 @@ class DataFrame private[sql](
*/
def isLocal: Boolean = logicalPlan.isInstanceOf[LocalRelation]

/**
* Displays the [[DataFrame]] in a tabular form. Strings more than 20 characters will be
* truncated, and all cells will be aligned right. For example:
* {{{
* year month AVG('Adj Close) MAX('Adj Close)
* 1980 12 0.503218 0.595103
* 1981 01 0.523289 0.570307
* 1982 02 0.436504 0.475256
* 1983 03 0.410516 0.442194
* 1984 04 0.450090 0.483521
* }}}
* @param numRows Number of rows to show
*
* @group action
* @since 1.3.0
*/
def show(numRows: Int): Unit = show(numRows, truncate = true)

/**
* Displays the top 20 rows of [[DataFrame]] in a tabular form. Strings more than 20 characters
* will be truncated, and all cells will be aligned right.
* @group action
* @since 1.3.0
*/
def show(): Unit = show(20)

/**
* Displays the top 20 rows of [[DataFrame]] in a tabular form.
*
* @param truncate Whether truncate long strings. If true, strings more than 20 characters will
* be truncated and all cells will be aligned right
*
* @group action
* @since 1.5.0
*/
def show(truncate: Boolean): Unit = show(20, truncate)

/**
* Displays the [[DataFrame]] in a tabular form. For example:
* {{{
* year month AVG('Adj Close) MAX('Adj Close)
* 1980 12 0.503218 0.595103
* 1981 01 0.523289 0.570307
* 1982 02 0.436504 0.475256
* 1983 03 0.410516 0.442194
* 1984 04 0.450090 0.483521
* }}}
* @param numRows Number of rows to show
* @param truncate Whether truncate long strings. If true, strings more than 20 characters will
* be truncated and all cells will be aligned right
*
* @group action
* @since 1.5.0
*/
// scalastyle:off println
def show(numRows: Int, truncate: Boolean): Unit = println(showString(numRows, truncate))
// scalastyle:on println

/**
* Returns a [[DataFrameNaFunctions]] for working with missing data.
* {{{
Expand Down
32 changes: 32 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -599,6 +599,38 @@ class Dataset[T] private[sql](
*/
def takeAsList(num: Int): java.util.List[T] = java.util.Arrays.asList(take(num) : _*)

/**
* Compose the string representing rows for output
* @param _numRows Number of rows to show
* @param truncate Whether truncate long strings and align cells right
*/
override private[sql] def showString(_numRows: Int, truncate: Boolean = true): String = {
Copy link
Contributor

@rxin rxin Nov 25, 2015

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can't we share the code between dataset and dataframe?

Copy link
Member Author

@gatorsmile gatorsmile Nov 25, 2015

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

When merging them into the same one, I hit a problem when calling the function take. The Dataset API take returns type Array[T], but Dataframe API take has a different return type Array[Row].

Do you have a better idea how to integrate them into the same function?

val numRows = _numRows.max(0)
val takeResult = take(numRows + 1)
val hasMoreData = takeResult.length > numRows
val data = takeResult.take(numRows)

// For array values, replace Seq and Array with square brackets
// For cells that are beyond 20 characters, replace it with the first 17 and "..."
val rows: Seq[Seq[String]] = schema.fieldNames.toSeq +: (data.map {
case r: Row => r
case tuple: Product => Row.fromTuple(tuple)
case o => Row(o)
} map { row =>
row.toSeq.map { cell =>
val str = cell match {
case null => "null"
case array: Array[_] => array.mkString("[", ", ", "]")
case seq: Seq[_] => seq.mkString("[", ", ", "]")
case _ => cell.toString
}
if (truncate && str.length > 20) str.substring(0, 17) + "..." else str
}: Seq[String]
})

formatString ( rows, numRows, hasMoreData, truncate )
}

/* ******************** *
* Internal Functions *
* ******************** */
Expand Down
128 changes: 128 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/Queryable.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

package org.apache.spark.sql.execution

import org.apache.commons.lang3.StringUtils
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.types.StructType

Expand Down Expand Up @@ -64,4 +65,131 @@ private[sql] trait Queryable {
* @since 1.3.0
*/
def explain(): Unit = explain(extended = false)

/**
* Displays the [[Queryable]] in a tabular form. Strings more than 20 characters
* will be truncated, and all cells will be aligned right. For example:
* {{{
* year month AVG('Adj Close) MAX('Adj Close)
* 1980 12 0.503218 0.595103
* 1981 01 0.523289 0.570307
* 1982 02 0.436504 0.475256
* 1983 03 0.410516 0.442194
* 1984 04 0.450090 0.483521
* }}}
* @param numRows Number of rows to show
*
* @group action
* @since 1.3.0
*/
def show(numRows: Int): Unit = show(numRows, truncate = true)

/**
* Displays the top 20 rows of [[Queryable]] in a tabular form. Strings more than 20 characters
* will be truncated, and all cells will be aligned right.
*
* @group action
* @since 1.3.0
*/
def show(): Unit = show(20)

/**
* Displays the top 20 rows of [[Queryable]] in a tabular form.
*
* @param truncate Whether truncate long strings. If true, strings more than 20 characters will
* be truncated and all cells will be aligned right
*
* @group action
* @since 1.5.0
*/
def show(truncate: Boolean): Unit = show(20, truncate)

/**
* Displays the [[Queryable]] in a tabular form. For example:
* {{{
* year month AVG('Adj Close) MAX('Adj Close)
* 1980 12 0.503218 0.595103
* 1981 01 0.523289 0.570307
* 1982 02 0.436504 0.475256
* 1983 03 0.410516 0.442194
* 1984 04 0.450090 0.483521
* }}}
* @param numRows Number of rows to show
* @param truncate Whether truncate long strings. If true, strings more than 20 characters will
* be truncated and all cells will be aligned right
*
* @group action
* @since 1.5.0
*/
// scalastyle:off println
def show(numRows: Int, truncate: Boolean): Unit = println(showString(numRows, truncate))
// scalastyle:on println

/**
* Compose the string representing rows for output
* @param _numRows The max limit of rows to show
* @param truncate Whether truncate long strings and align cells right
*/
private[sql] def showString(_numRows: Int, truncate: Boolean = true): String

/**
* Format the string representing rows for output
* @param rows The rows to show
* @param numRows Number of rows to show
* @param hasMoreData Whether some rows are not shown due to the limit
* @param truncate Whether truncate long strings and align cells right
*
*/
private[sql] def formatString (rows: Seq[Seq[String]],
numRows: Int,
hasMoreData : Boolean,
truncate: Boolean = true): String = {
val sb = new StringBuilder
val numCols = schema.fieldNames.length

// Initialise the width of each column to a minimum value of '3'
val colWidths = Array.fill(numCols)(3)

// Compute the width of each column
for (row <- rows) {
for ((cell, i) <- row.zipWithIndex) {
colWidths(i) = math.max(colWidths(i), cell.length)
}
}

// Create SeparateLine
val sep: String = colWidths.map("-" * _).addString(sb, "+", "+", "+\n").toString()

// column names
rows.head.zipWithIndex.map { case (cell, i) =>
if (truncate) {
StringUtils.leftPad(cell, colWidths(i))
} else {
StringUtils.rightPad(cell, colWidths(i))
}
}.addString(sb, "|", "|", "|\n")

sb.append(sep)

// data
rows.tail.map {
_.zipWithIndex.map { case (cell, i) =>
if (truncate) {
StringUtils.leftPad(cell.toString, colWidths(i))
} else {
StringUtils.rightPad(cell.toString, colWidths(i))
}
}.addString(sb, "|", "|", "|\n")
}

sb.append(sep)

// For Data that has more than "numRows" records
if (hasMoreData) {
val rowsString = if (numRows == 1) "row" else "rows"
sb.append(s"only showing top $numRows $rowsString\n")
}

sb.toString()
}
}