[spark] Add paimon spark4.2 module

.github/workflows/publish-snapshot-spark4.yml

@@ -67,8 +67,8 @@ jobs:
           echo "<password>$ASF_PASSWORD</password>" >> $tmp_settings
           echo "</server></servers></settings>" >> $tmp_settings
 
-          mvn --settings $tmp_settings -ntp clean install -Dgpg.skip -Drat.skip -DskipTests -Papache-release,spark4,flink1 -pl org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13 -am
+          mvn --settings $tmp_settings -ntp clean install -Dgpg.skip -Drat.skip -DskipTests -Papache-release,spark4,flink1 -pl org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13,org.apache.paimon:paimon-spark-4.2_2.13 -am
           # skip deploy paimon-spark-common_2.13 since they are already deployed in publish-snapshot.yml
-          mvn --settings $tmp_settings -ntp clean deploy -Dgpg.skip -Drat.skip -DskipTests -Papache-release,spark4,flink1 -pl org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-ut_2.13,org.apache.paimon:paimon-spark-ut-4.0_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13
+          mvn --settings $tmp_settings -ntp clean deploy -Dgpg.skip -Drat.skip -DskipTests -Papache-release,spark4,flink1 -pl org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-ut_2.13,org.apache.paimon:paimon-spark-ut-4.0_2.13,org.apache.paimon:paimon-spark-ut-4.1_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13,org.apache.paimon:paimon-spark-4.2_2.13
 
           rm $tmp_settings

.github/workflows/release-java.yml

@@ -121,7 +121,7 @@ jobs:
               mvn -ntp -B "${enforcer_goal}" \
                 -Denforcer.rules="${enforcer_rules}" \
                 -Papache-release,docs-and-source,spark4 \
-                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13 \
+                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13,org.apache.paimon:paimon-spark-4.2_2.13 \
                 -am
               ;;
             *)
@@ -186,22 +186,22 @@ jobs:
             jdk17)
               capture_expected_projects \
                 -Papache-release,docs-and-source,spark4 \
-                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13
+                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13,org.apache.paimon:paimon-spark-4.2_2.13
               # This install only supplies reactor dependencies for the deploy
               # below. Their Javadocs are built by the owning release lane.
               mvn clean install -ntp -B \
                 -Pdocs-and-source,spark4 \
                 -DskipTests -Dmaven.javadoc.skip=true \
                 -Dstyle.color=never \
-                -pl paimon-spark/paimon-spark-4.0,paimon-spark/paimon-spark-4.1 \
+                -pl paimon-spark/paimon-spark-4.0,paimon-spark/paimon-spark-4.1,paimon-spark/paimon-spark-4.2 \
                 -am \
                 2>&1 | tee "${log}"
               mvn deploy -ntp -B \
                 -Papache-release,docs-and-source,spark4 \
                 -DskipTests -Dgpg.skip=true -Dstyle.color=never \
                 -DdeployAtEnd=true \
                 -DaltDeploymentRepository="${alt_repository}" \
-                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13 \
+                -pl org.apache.paimon:paimon-spark-common_2.13,org.apache.paimon:paimon-spark4-common_2.13,org.apache.paimon:paimon-spark-4.0_2.13,org.apache.paimon:paimon-spark-4.1_2.13,org.apache.paimon:paimon-spark-4.2_2.13 \
                 2>&1 | tee -a "${log}"
               ;;
             *)

docs/docs/ecosystem/index.md

@@ -52,7 +52,7 @@ release cycle, embedded Paimon version, and feature limits.
 | Integration | Version selection | Access to Paimon tables |
 | --- | --- | --- |
 | [Flink](../flink/installation) | 1.16–1.20 and 2.0–2.2 | Batch and streaming reads/writes; [DDL](../flink/sql-ddl) and [row changes](../flink/sql-write) have version-specific requirements. |
-| [Spark](../spark/quick-start) | 3.2–3.5, 4.0, and 4.1; match the Scala binary version | Batch reads/writes, [DDL](../spark/sql-ddl), and [row changes](../spark/sql-write); [streaming](../spark/structured-streaming) requires Spark 3.3+. |
+| [Spark](../spark/quick-start) | 3.2–3.5, 4.0, 4.1, and 4.2; match the Scala binary version | Batch reads/writes, [DDL](../spark/sql-ddl), and [row changes](../spark/sql-write); [streaming](../spark/structured-streaming) requires Spark 3.3+. |
 | [Hive](./hive#version) | 2.1, 2.2, 2.3, 3.1, and 2.1-cdh-6.3 | Batch reads, table creation, and `INSERT INTO`; writes require MapReduce. |
 | [Trino](./trino#version) | Match the independently released Paimon connector to Trino | Batch reads; supported connectors also provide DDL, inserts, and time travel. See the guide's table-layout limits. |
 | [Presto](https://github.com/apache/paimon-presto) | Follow the separate connector's version requirements | See the connector repository for installation and supported operations. |

docs/docs/iceberg/data-types.md

@@ -68,7 +68,7 @@ compatibility publishes only millisecond time values.
 **Note on Geospatial Types:**
 - `GEOMETRY` and `GEOGRAPHY` values use OGC Well-Known Binary (WKB). The default CRS is `OGC:CRS84`, and the default geography edge algorithm is `spherical`.
 - Geospatial columns require Parquet for data, per-level, and changelog files. When Iceberg metadata is enabled, set `metadata.iceberg.format-version` to `3`.
-- Spark SQL supports geospatial columns in Spark 4.1 when `spark.sql.geospatial.enabled=true`, for CRSs recognized by Spark, with the `spherical` geography edge algorithm. Spark 3.x, Spark 4.0, and Flink SQL reject these columns instead of exposing them as binary and losing the CRS or edge algorithm.
+- Spark SQL supports geospatial columns in Spark 4.1 and later, for CRSs recognized by Spark, with the `spherical` geography edge algorithm. Spark 4.1 keeps them behind `spark.sql.geospatial.enabled=true` outside its own test environment; Spark 4.2 enables them by default. Spark 3.x, Spark 4.0, and Flink SQL reject these columns instead of exposing them as binary and losing the CRS or edge algorithm.
 - When Iceberg metadata is enabled, a `GEOGRAPHY` CRS cannot contain a comma, including in nested columns, because Iceberg's geospatial type grammar uses commas to separate parameters.
 - Iceberg REST catalog publication does not yet support geospatial columns. Use `table-location`, `hadoop-catalog`, or `hive-catalog` metadata storage instead.
 

docs/docs/project/download.mdx

@@ -75,6 +75,7 @@ signed Apache release.
 | Flink 1.17       | [paimon-flink-1.17-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-flink-1.17/@@VERSION@@/)                                 |
 | Flink 1.16       | [paimon-flink-1.16-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-flink-1.16/@@VERSION@@/)                                 |
 | Flink Action     | [paimon-flink-action-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-flink-action/@@VERSION@@/)                             |
+| Spark 4.2        | [paimon-spark-4.2_2.13-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.2_2.13/@@VERSION@@/)                         |
 | Spark 4.1        | [paimon-spark-4.1_2.13-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.1_2.13/@@VERSION@@/)                         |
 | Spark 4.0        | [paimon-spark-4.0_2.13-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.0_2.13/@@VERSION@@/)                         |
 | Spark 3.5        | [paimon-spark-3.5_2.12-@@VERSION@@.jar](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-3.5_2.12/@@VERSION@@/)                         |
@@ -103,6 +104,7 @@ signed Apache release.
 | Flink 1.17       | [paimon-flink-1.17-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-flink-1.17/@@VERSION@@/paimon-flink-1.17-@@VERSION@@.jar)                                                 |
 | Flink 1.16       | [paimon-flink-1.16-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-flink-1.16/@@VERSION@@/paimon-flink-1.16-@@VERSION@@.jar)                                                 |
 | Flink Action     | [paimon-flink-action-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-flink-action/@@VERSION@@/paimon-flink-action-@@VERSION@@.jar)                                           |
+| Spark 4.2        | [paimon-spark-4.2_2.13-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.2_2.13/@@VERSION@@/paimon-spark-4.2_2.13-@@VERSION@@.jar)                                     |
 | Spark 4.1        | [paimon-spark-4.1_2.13-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.1_2.13/@@VERSION@@/paimon-spark-4.1_2.13-@@VERSION@@.jar)                                     |
 | Spark 4.0        | [paimon-spark-4.0_2.13-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.0_2.13/@@VERSION@@/paimon-spark-4.0_2.13-@@VERSION@@.jar)                                     |
 | Spark 3.5        | [paimon-spark-3.5_2.12-@@VERSION@@.jar](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-3.5_2.12/@@VERSION@@/paimon-spark-3.5_2.12-@@VERSION@@.jar)                                     |

docs/docs/project/verifying-a-release-candidate.md

@@ -264,7 +264,7 @@ the packaging-equivalent build without reproducing the full JDK 17 test lane:
 (
   cd "paimon-${PAIMON_VERSION}"
   mvn -ntp clean install -DskipTests -Pdocs-and-source,spark4 \
-    -pl paimon-spark/paimon-spark-4.0,paimon-spark/paimon-spark-4.1 \
+    -pl paimon-spark/paimon-spark-4.0,paimon-spark/paimon-spark-4.1,paimon-spark/paimon-spark-4.2 \
     -am
 )
 ```

docs/docs/spark/data-types.md

@@ -50,8 +50,8 @@ types Spark can read as `BinaryType`; it does not imply a unique mapping in both
 | `TimestampNTZType (Spark 3.4+)` | `TimestampType` | true |
 | `DecimalType(precision, scale)` | `DecimalType(precision, scale)` | true |
 | `BinaryType` | `VarBinaryType`, `BinaryType` | true |
-| `GeometryType (Spark 4.1)` | `GeometryType` | true |
-| `GeographyType (Spark 4.1)` | `GeographyType` | true |
+| `GeometryType (Spark 4.1+)` | `GeometryType` | true |
+| `GeographyType (Spark 4.1+)` | `GeographyType` | true |
 | `VariantType (Spark 4.0+)` | `VariantType` | true |
 
 ## Timestamps
@@ -66,4 +66,4 @@ Spark 3.4 and later distinguish the two timestamp types.
 
 ## Geospatial Types
 
-Native `GeometryType` and `GeographyType` conversion is supported only in Spark 4.1 and only for CRSs recognized by Spark. Enable it explicitly in production with `--conf spark.sql.geospatial.enabled=true`; Spark enables it automatically only in its test environment. Spark 4.1 supports only the `spherical` geography edge algorithm, so Paimon geography types using `vincenty`, `thomas`, `andoyer`, or `karney` cannot be converted. Spark 3.x and Spark 4.0 reject Paimon geospatial columns instead of exposing them as `BinaryType`, which would lose the CRS or edge algorithm. Paimon does not support Spark geospatial types with mixed SRIDs.
+Native `GeometryType` and `GeographyType` conversion is supported only in Spark 4.1 and later, and only for CRSs recognized by Spark. Spark 4.1 keeps the types behind `--conf spark.sql.geospatial.enabled=true` outside its own test environment; Spark 4.2 enables them by default. Spark 4.1 and 4.2 define `spherical` as their only geography edge algorithm, so Paimon geography types using `vincenty`, `thomas`, `andoyer`, or `karney` cannot be converted. Spark 3.x and Spark 4.0 reject Paimon geospatial columns instead of exposing them as `BinaryType`, which would lose the CRS or edge algorithm. Paimon does not support Spark geospatial types with mixed SRIDs.

docs/docs/spark/installation.mdx

@@ -30,7 +30,7 @@ Match the connector to the Spark minor version and Scala binary version of your
 The Java versions below describe how the connector artifacts are built; your Spark distribution
 may require a newer Java runtime. Check its runtime requirements before starting Spark.
 
-- Spark 4.x (including 4.1, 4.0) : Pre-built with Java 17 and Scala 2.13
+- Spark 4.x (including 4.2, 4.1, 4.0) : Pre-built with Java 17 and Scala 2.13
 
 - Spark 3.x (including 3.5, 3.4, 3.3, 3.2) : Pre-built with Java 8 and Scala 2.12/2.13
 
@@ -42,6 +42,7 @@ Choose the JAR matching your Spark and Scala versions:
 
 | Version   | Jar (Scala 2.12)                                                                                                                                                                    | Jar (Scala 2.13)                                                                                                                                                                    |
 |-----------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| Spark 4.2 | -                                                                                                                                                                                   | [JAR](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.2_2.13/@@VERSION@@/paimon-spark-4.2_2.13-@@VERSION@@.jar) |
 | Spark 4.1 | -                                                                                                                                                                                   | [JAR](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.1_2.13/@@VERSION@@/paimon-spark-4.1_2.13-@@VERSION@@.jar) |
 | Spark 4.0 | -                                                                                                                                                                                   | [JAR](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-4.0_2.13/@@VERSION@@/paimon-spark-4.0_2.13-@@VERSION@@.jar) |
 | Spark 3.5 | [JAR](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-3.5_2.12/@@VERSION@@/paimon-spark-3.5_2.12-@@VERSION@@.jar) | [JAR](https://repo.maven.apache.org/maven2/org/apache/paimon/paimon-spark-3.5_2.13/@@VERSION@@/paimon-spark-3.5_2.13-@@VERSION@@.jar) |
@@ -55,6 +56,7 @@ Choose the JAR matching your Spark and Scala versions:
 
 | Version   | Jar (Scala 2.12)                                                                                                                              | Jar (Scala 2.13)                                                                                                                              |
 |-----------|-----------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|
+| Spark 4.2 | -                                                                                                                                             | [JAR](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.2_2.13/@@VERSION@@/) |
 | Spark 4.1 | -                                                                                                                                             | [JAR](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.1_2.13/@@VERSION@@/) |
 | Spark 4.0 | -                                                                                                                                             | [JAR](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-4.0_2.13/@@VERSION@@/) |
 | Spark 3.5 | [JAR](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-3.5_2.12/@@VERSION@@/) | [JAR](https://repository.apache.org/snapshots/org/apache/paimon/paimon-spark-3.5_2.13/@@VERSION@@/) |
@@ -82,6 +84,9 @@ mvn clean package -DskipTests -pl paimon-spark/paimon-spark-4.0 -am -Pspark4
 
 # build paimon spark 4.1
 mvn clean package -DskipTests -pl paimon-spark/paimon-spark-4.1 -am -Pspark4
+
+# build paimon spark 4.2
+mvn clean package -DskipTests -pl paimon-spark/paimon-spark-4.2 -am -Pspark4
 ```
 
 For Spark 3.5, you can find the bundled jar in `./paimon-spark/paimon-spark-3.5/target/paimon-spark-3.5_2.12-@@VERSION@@.jar`.

paimon-spark/paimon-spark-4.0/pom.xml

@@ -33,10 +33,12 @@ under the License.
 
     <properties>
         <spark.version>4.0.3</spark.version>
-        <!-- Spark 4.x uses SLF4J 2.x (`org.slf4j.spi.LoggingEventBuilder` is 2.x-only). Override
-             the Paimon parent pom's default `slf4j.version=1.7.32` so the classpath is uniformly
-             2.x; otherwise `log4j-slf4j2-impl` + `slf4j-api:1.7.32` mix produces
-             `NoClassDefFoundError: org/slf4j/spi/LoggingEventBuilder` at test startup. -->
+        <!-- This module resolves `log4j-slf4j2-impl` onto the test classpath, and that binding
+             needs SLF4J 2.x (`org.slf4j.spi.LoggingEventBuilder` is 2.x-only). Override the Paimon
+             parent pom's default `slf4j.version=1.7.32` so the classpath is uniformly 2.x;
+             otherwise the mix produces `NoClassDefFoundError:
+             org/slf4j/spi/LoggingEventBuilder` at test startup. `paimon-spark-4.2` resolves no
+             `log4j-slf4j2-impl` and needs no override. -->
         <slf4j.version>2.0.16</slf4j.version>
         <!-- Spark 4 only supports Scala 2.13. Pin it locally so this _2.13 module resolves its
              dependencies to _2.13 even when the spark4 profile is inactive (see issue #6682);
@@ -64,7 +66,7 @@ under the License.
 
         <!--
           `paimon-spark4-common` transitively pulls in `spark-sql-api` at the version set by
-          `paimon-spark-common.spark.version` (4.1.2 under the `spark4` profile). Spark 4.1's
+          `paimon-spark-common.spark.version` (4.2.0 under the `spark4` profile). Spark 4.1's
           `SqlApiConf` added abstract `manageParserCaches()`, which Spark 4.0's concrete
           anonymous subclasses (e.g. `WithTestConf$$anon$4`) don't implement. Mixing those
           jars produces `AbstractMethodError` at parser configuration time. Pin
@@ -124,10 +126,10 @@ under the License.
 
         <!-- test -->
 
-        <!-- The 4.0-compiled build of `paimon-spark-ut`'s test sources. The baseline build cannot be
-             used here: it is compiled against the `spark4` profile baseline, so its classfiles can
-             reference Spark symbols that a 4.0 runtime does not have. See
-             `paimon-spark-ut-4.0/pom.xml`. -->
+        <!-- The 4.0-compiled build of `paimon-spark-ut`'s test sources. The baseline build cannot
+             be used here: Spark 4.2 turned `QueryTest` into a trait (SPARK-55910), so a
+             4.2-compiled `PaimonSparkTestBase` carries it as an interface and fails to load on a
+             4.0/4.1 runtime. See `paimon-spark-ut-4.0/pom.xml`. -->
         <dependency>
             <groupId>org.apache.paimon</groupId>
             <artifactId>paimon-spark-ut-4.0_${scala.binary.version}</artifactId>