This is an automated email from the ASF dual-hosted git repository.
huaxingao pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg.git
The following commit(s) were added to refs/heads/main by this push:
new 9c3bed6a65 Docs: Fix MERGE INTO example in Getting Started (#14943)
9c3bed6a65 is described below
commit 9c3bed6a651f20fc06b1a4c329e40910bd6eb36a
Author: Varun Lakhyani <[email protected]>
AuthorDate: Wed Dec 31 01:46:19 2025 +0530
Docs: Fix MERGE INTO example in Getting Started (#14943)
* Docs: Fix MERGE INTO example in Getting Started
* Docs: Fix Getting Started Spark SQL example to be runnable
* Apply same documentation fix to Spark 3.4, 4.0, and 4.1 versions
* Retry CI as earlier gave 429
---
docs/docs/spark-getting-started.md | 8 ++++++--
.../integration/java/org/apache/iceberg/spark/TestRoundTrip.java | 2 --
.../integration/java/org/apache/iceberg/spark/TestRoundTrip.java | 2 --
.../integration/java/org/apache/iceberg/spark/TestRoundTrip.java | 2 --
.../integration/java/org/apache/iceberg/spark/TestRoundTrip.java | 2 --
5 files changed, 6 insertions(+), 10 deletions(-)
diff --git a/docs/docs/spark-getting-started.md
b/docs/docs/spark-getting-started.md
index 6813c76937..821bfd022c 100644
--- a/docs/docs/spark-getting-started.md
+++ b/docs/docs/spark-getting-started.md
@@ -61,6 +61,8 @@ To create your first Iceberg table in Spark, use the
`spark-sql` shell or `spark
```sql
-- local is the path-based catalog defined above
CREATE TABLE local.db.table (id bigint, data string) USING iceberg;
+CREATE TABLE source (id bigint, data string) USING parquet;
+CREATE TABLE updates (id bigint, data string) USING parquet;
```
Iceberg catalogs support the full range of SQL DDL commands, including:
@@ -76,14 +78,16 @@ Once your table is created, insert data using [`INSERT
INTO`](spark-writes.md#in
```sql
INSERT INTO local.db.table VALUES (1, 'a'), (2, 'b'), (3, 'c');
+INSERT INTO source VALUES (10, 'd'), (11, 'ee');
+INSERT INTO updates VALUES (1, 'x'), (2, 'x'), (4, 'z');
INSERT INTO local.db.table SELECT id, data FROM source WHERE length(data) = 1;
```
Iceberg also adds row-level SQL updates to Spark, [`MERGE
INTO`](spark-writes.md#merge-into) and [`DELETE
FROM`](spark-writes.md#delete-from):
```sql
-MERGE INTO local.db.target t USING (SELECT * FROM updates) u ON t.id = u.id
-WHEN MATCHED THEN UPDATE SET t.count = t.count + u.count
+MERGE INTO local.db.table t USING (SELECT * FROM updates) u ON t.id = u.id
+WHEN MATCHED THEN UPDATE SET t.data = u.data
WHEN NOT MATCHED THEN INSERT *;
```
diff --git
a/spark/v3.4/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
b/spark/v3.4/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
index 29f725615a..709f626b08 100644
---
a/spark/v3.4/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
+++
b/spark/v3.4/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
@@ -38,8 +38,6 @@ public class TestRoundTrip extends ExtensionsTestBase {
}
// Run through our Doc's Getting Started Example
- // TODO Update doc example so that it can actually be run, modifications
were required for this
- // test suite to run
@TestTemplate
public void testGettingStarted() throws IOException {
// Creating a table
diff --git
a/spark/v3.5/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
b/spark/v3.5/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
index 29f725615a..709f626b08 100644
---
a/spark/v3.5/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
+++
b/spark/v3.5/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
@@ -38,8 +38,6 @@ public class TestRoundTrip extends ExtensionsTestBase {
}
// Run through our Doc's Getting Started Example
- // TODO Update doc example so that it can actually be run, modifications
were required for this
- // test suite to run
@TestTemplate
public void testGettingStarted() throws IOException {
// Creating a table
diff --git
a/spark/v4.0/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
b/spark/v4.0/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
index 29f725615a..709f626b08 100644
---
a/spark/v4.0/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
+++
b/spark/v4.0/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
@@ -38,8 +38,6 @@ public class TestRoundTrip extends ExtensionsTestBase {
}
// Run through our Doc's Getting Started Example
- // TODO Update doc example so that it can actually be run, modifications
were required for this
- // test suite to run
@TestTemplate
public void testGettingStarted() throws IOException {
// Creating a table
diff --git
a/spark/v4.1/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
b/spark/v4.1/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
index 29f725615a..709f626b08 100644
---
a/spark/v4.1/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
+++
b/spark/v4.1/spark-runtime/src/integration/java/org/apache/iceberg/spark/TestRoundTrip.java
@@ -38,8 +38,6 @@ public class TestRoundTrip extends ExtensionsTestBase {
}
// Run through our Doc's Getting Started Example
- // TODO Update doc example so that it can actually be run, modifications
were required for this
- // test suite to run
@TestTemplate
public void testGettingStarted() throws IOException {
// Creating a table
