This is an automated email from the ASF dual-hosted git repository.
yihua pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/hudi.git
The following commit(s) were added to refs/heads/asf-site by this push:
new d9e0a47cb8 [DOCS][MINOR] Improve spark quick start doc (#6538)
d9e0a47cb8 is described below
commit d9e0a47cb88649dfdac2a13250737a590e50e5eb
Author: KnightChess <[email protected]>
AuthorDate: Tue Aug 30 10:38:45 2022 +0800
[DOCS][MINOR] Improve spark quick start doc (#6538)
---
website/docs/quick-start-guide.md | 12 ++++++++----
.../versioned_docs/version-0.10.0/quick-start-guide.md | 12 +++++++++---
.../versioned_docs/version-0.10.1/quick-start-guide.md | 16 ++++++++++++----
.../versioned_docs/version-0.11.0/quick-start-guide.md | 12 ++++++++----
.../versioned_docs/version-0.11.1/quick-start-guide.md | 12 ++++++++----
.../versioned_docs/version-0.12.0/quick-start-guide.md | 12 ++++++++----
6 files changed, 53 insertions(+), 23 deletions(-)
diff --git a/website/docs/quick-start-guide.md
b/website/docs/quick-start-guide.md
index 02ebfc74e0..145c17f843 100644
--- a/website/docs/quick-start-guide.md
+++ b/website/docs/quick-start-guide.md
@@ -67,13 +67,15 @@ spark-shell \
# Spark 3.1
spark-shell \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
spark-shell \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -104,14 +106,16 @@ pyspark \
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.10.0/quick-start-guide.md
b/website/versioned_docs/version-0.10.0/quick-start-guide.md
index e3f38448e9..108b1071cd 100644
--- a/website/versioned_docs/version-0.10.0/quick-start-guide.md
+++ b/website/versioned_docs/version-0.10.0/quick-start-guide.md
@@ -41,17 +41,20 @@ From the extracted directory run spark-shell with Hudi as:
// spark-shell for spark 3
spark-shell \
--packages
org.apache.hudi:hudi-spark3-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:3.1.2
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
// spark-shell for spark 2 with scala 2.12
spark-shell \
--packages
org.apache.hudi:hudi-spark-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:2.4.4
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
// spark-shell for spark 2 with scala 2.11
spark-shell \
--packages
org.apache.hudi:hudi-spark-bundle_2.11:0.10.0,org.apache.spark:spark-avro_2.11:2.4.4
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -91,16 +94,19 @@ export PYSPARK_PYTHON=$(which python3)
pyspark
--packages
org.apache.hudi:hudi-spark3-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:3.1.2
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
# for spark2 with scala 2.12
pyspark
--packages
org.apache.hudi:hudi-spark-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:2.4.4
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
# for spark2 with scala 2.11
pyspark
--packages
org.apache.hudi:hudi-spark-bundle_2.11:0.10.0,org.apache.spark:spark-avro_2.11:2.4.4
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.10.1/quick-start-guide.md
b/website/versioned_docs/version-0.10.1/quick-start-guide.md
index d7c70ee510..42ce44162f 100644
--- a/website/versioned_docs/version-0.10.1/quick-start-guide.md
+++ b/website/versioned_docs/version-0.10.1/quick-start-guide.md
@@ -41,22 +41,26 @@ From the extracted directory run spark-shell with Hudi as:
// spark-shell for spark 3.1
spark-shell \
--packages
org.apache.hudi:hudi-spark3.1.2-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:3.1.2
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
// spark-shell for spark 3.2
spark-shell \
--packages
org.apache.hudi:hudi-spark3.0.3-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:3.0.3
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
// spark-shell for spark 2 with scala 2.12
spark-shell \
--packages
org.apache.hudi:hudi-spark-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:2.4.4
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
// spark-shell for spark 2 with scala 2.11
spark-shell \
--packages
org.apache.hudi:hudi-spark-bundle_2.11:0.10.1,org.apache.spark:spark-avro_2.11:2.4.4
\
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -101,21 +105,25 @@ export PYSPARK_PYTHON=$(which python3)
pyspark
--packages
org.apache.hudi:hudi-spark3.1.2-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:3.1.2
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
# for spark3.0
pyspark
--packages
org.apache.hudi:hudi-spark3.0.3-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:3.0.3
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
# for spark2 with scala 2.12
pyspark
--packages
org.apache.hudi:hudi-spark-bundle_2.12:0.10.1,org.apache.spark:spark-avro_2.12:2.4.4
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
# for spark2 with scala 2.11
pyspark
--packages
org.apache.hudi:hudi-spark-bundle_2.11:0.10.1,org.apache.spark:spark-avro_2.11:2.4.4
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.11.0/quick-start-guide.md
b/website/versioned_docs/version-0.11.0/quick-start-guide.md
index 8dace5306e..14166b6fe5 100644
--- a/website/versioned_docs/version-0.11.0/quick-start-guide.md
+++ b/website/versioned_docs/version-0.11.0/quick-start-guide.md
@@ -57,13 +57,15 @@ spark-shell \
# Spark 3.1
spark-shell \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.11.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
spark-shell \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.11.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -85,14 +87,16 @@ pyspark \
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.11.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.11.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.11.1/quick-start-guide.md
b/website/versioned_docs/version-0.11.1/quick-start-guide.md
index bec6545520..b9894a51a7 100644
--- a/website/versioned_docs/version-0.11.1/quick-start-guide.md
+++ b/website/versioned_docs/version-0.11.1/quick-start-guide.md
@@ -57,13 +57,15 @@ spark-shell \
# Spark 3.1
spark-shell \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.11.1 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
spark-shell \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.11.1 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -85,14 +87,16 @@ pyspark \
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.11.1 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.11.1 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.12.0/quick-start-guide.md
b/website/versioned_docs/version-0.12.0/quick-start-guide.md
index 02ebfc74e0..145c17f843 100644
--- a/website/versioned_docs/version-0.12.0/quick-start-guide.md
+++ b/website/versioned_docs/version-0.12.0/quick-start-guide.md
@@ -67,13 +67,15 @@ spark-shell \
# Spark 3.1
spark-shell \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
spark-shell \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.0 \
- --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>
@@ -104,14 +106,16 @@ pyspark \
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```shell
# Spark 2.4
export PYSPARK_PYTHON=$(which python3)
pyspark \
--packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
+--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
</TabItem>