This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 4cf9d14d84c0 [SPARK-49806][SQL][CONNECT] Remove redundant `blank
space` after `show` in `Scala` and `Connect` clients
4cf9d14d84c0 is described below
commit 4cf9d14d84c0061ae2476d97256daf0b2062ed54
Author: panbingkun <[email protected]>
AuthorDate: Fri Oct 4 10:08:18 2024 -0700
[SPARK-49806][SQL][CONNECT] Remove redundant `blank space` after `show` in
`Scala` and `Connect` clients
### What changes were proposed in this pull request?
The pr aims to remove redundant `blank space` after `show` in `Scala` and
`Connect` clients.
### Why are the changes needed?
Make the output of `show` in `scala` and `connect` both end with `1 blank
space`, making it look more `consistent` in style.
#### A.Scala (`spark-shell`)
- Before:
<img width="1400" alt="image"
src="https://github.com/user-attachments/assets/cccd947d-176e-49d1-a6e2-9553c267837a";>
**Note: Other command end with `1 blank space`, while `show` end with `2
blank spaces`.**
- After:
<img width="1397" alt="image"
src="https://github.com/user-attachments/assets/83253433-5339-458f-9f14-5ae7c442e7a3";>
#### B.Connect (`spark-connect-scala-client`)
- Before:
<img width="911" alt="image"
src="https://github.com/user-attachments/assets/fc625539-d14c-499f-95cc-7e545a8a1bbe";>
<img width="908" alt="image"
src="https://github.com/user-attachments/assets/7fb93845-bbef-4001-9a0c-97a771852c4a";>
**Note: Other command end with `1 blank space`, while `show` end with `3
blank spaces`.**
- After:
<img width="914" alt="image"
src="https://github.com/user-attachments/assets/c31aa97e-03a1-467e-abb2-5d1c07dcc156";>
<img width="911" alt="image"
src="https://github.com/user-attachments/assets/7144a4e1-7552-4700-9b0e-658774236ab4";>
### Does this PR introduce _any_ user-facing change?
Yes, command are separated by `1 blank space` between them, and 'show' is
no longer abrupt.
### How was this patch tested?
Manually check.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #48277 from panbingkun/SPARK-49806.
Authored-by: panbingkun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
---
.../src/main/scala/org/apache/spark/sql/Dataset.scala | 4 +---
python/pyspark/ml/fpm.py | 2 --
python/pyspark/sql/tests/test_dataframe.py | 3 +--
.../src/main/scala/org/apache/spark/sql/Dataset.scala | 4 ++--
.../scala/org/apache/spark/sql/DataFrameShowSuite.scala | 17 +++++++----------
.../streaming/sources/ConsoleWriteSupportSuite.scala | 1 -
6 files changed, 11 insertions(+), 20 deletions(-)
diff --git
a/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala
b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala
index 6bae04ef8023..a368da2aaee6 100644
---
a/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala
+++
b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -274,9 +274,7 @@ class Dataset[T] private[sql] (
df.withResult { result =>
assert(result.length == 1)
assert(result.schema.size == 1)
- // scalastyle:off println
- println(result.toArray.head)
- // scalastyle:on println
+ print(result.toArray.head)
}
}
diff --git a/python/pyspark/ml/fpm.py b/python/pyspark/ml/fpm.py
index cba4219a0694..72fcfccf19e4 100644
--- a/python/pyspark/ml/fpm.py
+++ b/python/pyspark/ml/fpm.py
@@ -213,7 +213,6 @@ class FPGrowth(
| [q]| 2|
+---------+----+
only showing top 5 rows
- ...
>>> fpm.associationRules.sort("antecedent", "consequent").show(5)
+----------+----------+----------+----+------------------+
|antecedent|consequent|confidence|lift| support|
@@ -225,7 +224,6 @@ class FPGrowth(
| [q]| [t]| 1.0| 2.0|0.3333333333333333|
+----------+----------+----------+----+------------------+
only showing top 5 rows
- ...
>>> new_data = spark.createDataFrame([(["t", "s"], )], ["items"])
>>> sorted(fpm.transform(new_data).first().newPrediction)
['x', 'y', 'z']
diff --git a/python/pyspark/sql/tests/test_dataframe.py
b/python/pyspark/sql/tests/test_dataframe.py
index 8ec0839ec1fe..b5af00a4e7b7 100644
--- a/python/pyspark/sql/tests/test_dataframe.py
+++ b/python/pyspark/sql/tests/test_dataframe.py
@@ -671,8 +671,7 @@ class DataFrameTestsMixin:
|+---+-----+
|| 1| 1|
|+---+-----+
- |only showing top 1 row
- |"""
+ |only showing top 1 row"""
self.assertEqual(re.sub(pattern, "", expected3),
df.__repr__())
# test when eager evaluation is enabled and _repr_html_ will be called
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index 18fc5787a158..58006837a3a6 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -412,11 +412,11 @@ class Dataset[T] private[sql](
// Print a footer
if (vertical && rows.tail.isEmpty) {
// In a vertical mode, print an empty row set explicitly
- sb.append("(0 rows)\n")
+ sb.append("(0 rows)")
} else if (hasMoreData) {
// For Data that has more than "numRows" records
val rowsString = if (numRows == 1) "row" else "rows"
- sb.append(s"only showing top $numRows $rowsString\n")
+ sb.append(s"only showing top $numRows $rowsString")
}
sb.toString()
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala
index d728cc5810a2..86d3ca45fd08 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala
@@ -112,13 +112,12 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
||key|value|
|+---+-----+
|+---+-----+
- |only showing top 0 rows
- |""".stripMargin
+ |only showing top 0 rows""".stripMargin
assert(testData.select($"*").showString(-1) === expectedAnswer)
}
test("showString(negative), vertical = true") {
- val expectedAnswer = "(0 rows)\n"
+ val expectedAnswer = "(0 rows)"
assert(testData.select($"*").showString(-1, vertical = true) ===
expectedAnswer)
}
@@ -127,8 +126,7 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
||key|value|
|+---+-----+
|+---+-----+
- |only showing top 0 rows
- |""".stripMargin
+ |only showing top 0 rows""".stripMargin
assert(testData.select($"*").showString(0) === expectedAnswer)
}
@@ -145,7 +143,7 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
}
test("showString(0), vertical = true") {
- val expectedAnswer = "(0 rows)\n"
+ val expectedAnswer = "(0 rows)"
assert(testData.select($"*").showString(0, vertical = true) ===
expectedAnswer)
}
@@ -286,8 +284,7 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
|+---+-----+
|| 1| 1|
|+---+-----+
- |only showing top 1 row
- |""".stripMargin
+ |only showing top 1 row""".stripMargin
assert(testData.select($"*").showString(1) === expectedAnswer)
}
@@ -295,7 +292,7 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
val expectedAnswer = "-RECORD 0----\n" +
" key | 1 \n" +
" value | 1 \n" +
- "only showing top 1 row\n"
+ "only showing top 1 row"
assert(testData.select($"*").showString(1, vertical = true) ===
expectedAnswer)
}
@@ -337,7 +334,7 @@ class DataFrameShowSuite extends QueryTest with
SharedSparkSession {
}
test("SPARK-7327 show with empty dataFrame, vertical = true") {
- assert(testData.select($"*").filter($"key" < 0).showString(1, vertical =
true) === "(0 rows)\n")
+ assert(testData.select($"*").filter($"key" < 0).showString(1, vertical =
true) === "(0 rows)")
}
test("SPARK-18350 show with session local timezone") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/sources/ConsoleWriteSupportSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/sources/ConsoleWriteSupportSuite.scala
index 97b95eb402b7..b5f23853fd5b 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/sources/ConsoleWriteSupportSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/sources/ConsoleWriteSupportSuite.scala
@@ -102,7 +102,6 @@ class ConsoleWriteSupportSuite extends StreamTest {
|| 2|
|+-----+
|only showing top 2 rows
- |
|""".stripMargin)
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
