Merge branch 'main' into issue-10668

.asf.yaml

@@ -49,12 +49,12 @@ github:
     - jun-he
     - marton-bod
     - samarthjain
-    - findepi
     - SreeramGarlapati
     - samredai
     - gaborkaszab
     - bitsondatadev
     - ajantha-bhat
+    - jbonofre
   ghp_branch: gh-pages
   ghp_path: /
 

.baseline/checkstyle/checkstyle.xml

@@ -159,7 +159,6 @@
         </module>
         <module name="ClassTypeParameterName"> <!-- Java Style Guide: Type variable names -->
             <property name="format" value="(^[A-Z][0-9]?)$|([A-Z][a-zA-Z0-9]*[T]$)"/>
-            <message key="name.invalidPattern" value="Class type name ''{0}'' must match pattern ''{1}''."/>
         </module>
         <module name="CovariantEquals"/> <!-- Java Coding Guidelines: Override ``Object#equals`` consistently -->
         <module name="DefaultComesLast"/> <!-- Java Style Guide: The default case is present -->
@@ -281,12 +280,13 @@
         </module>
         <module name="InnerAssignment"/> <!-- Java Coding Guidelines: Inner assignments: Not used -->
         <module name="MemberName"> <!-- Java Style Guide: Non-constant field names -->
-            <property name="format" value="^[a-z][a-zA-Z0-9]+$"/>
-            <message key="name.invalidPattern" value="Member name ''{0}'' must match pattern ''{1}''."/>
+            <property name="format" value="^[a-z][a-zA-Z0-9]++$"/>
+        </module>
+        <module name="ConstantName">
+            <property name="format" value="^[A-Z][A-Z0-9]*+(_[A-Z0-9]++)*+$"/>
         </module>
         <module name="MethodName"> <!-- Java Style Guide: Method names -->
-            <property name="format" value="^[a-z][a-zA-Z0-9_]+$"/>
-            <message key="name.invalidPattern" value="Method name ''{0}'' must match pattern ''{1}''."/>
+            <property name="format" value="^[a-z][a-zA-Z0-9_]++$"/>
         </module>
         <module name="MethodParamPad"/> <!-- Java Style Guide: Horizontal whitespace -->
         <module name="MissingDeprecated"/> <!-- Java Coding Guide: Deprecate per annotation and Javadoc -->
@@ -304,8 +304,7 @@
         <module name="PackageAnnotation"/> <!-- Java Style Guide: Package statement -->
         <module name="PackageDeclaration"/> <!-- Java Style Guide: Package statement -->
         <module name="PackageName"> <!-- Java Style Guide: Package names -->
-            <property name="format" value="^[a-z]+(\.[a-z][a-z0-9]*)*$"/>
-            <message key="name.invalidPattern" value="Package name ''{0}'' must match pattern ''{1}''."/>
+            <property name="format" value="^[a-z]++(\.[a-z][a-z0-9]*+)*+$"/>
         </module>
         <module name="ParameterAssignment"/> <!-- Java Coding Guidelines: Final variables and parameters -->
         <module name="ParenPad"/> <!-- Java Style Guide: Horizontal whitespace -->
@@ -444,7 +443,6 @@
             <message key="todo.match" value="There must be whitespace at the beginning of all comments."/>
         </module>
         <module name="TypeName"> <!-- Java Style Guide: Class names -->
-            <message key="name.invalidPattern" value="Type name ''{0}'' must match pattern ''{1}''."/>
         </module>
         <module name="TypecastParenPad"/> <!-- Java Style Guide: Horizontal whitespace -->
         <module name="UnusedImports"> <!-- Java Style Guide: No unused imports -->
@@ -480,23 +478,20 @@
         <module name="LocalFinalVariableName"/> <!-- Java Style Guide: Local variable names -->
         <module name="LocalVariableName"> <!-- Java Style Guide: Local variable names -->
             <property name="tokens" value="VARIABLE_DEF"/>
-            <property name="format" value="^[a-z][a-zA-Z0-9]+$"/>
+            <property name="format" value="^[a-z][a-zA-Z0-9]++$"/>
             <property name="allowOneCharVarInForLoop" value="true"/>
-            <message key="name.invalidPattern" value="Local variable name ''{0}'' must match pattern ''{1}''."/>
         </module>
         <module name="MethodLength"/> <!-- Java Coding Guide: Methods and functions: focused, crisp, concise -->
         <module name="MethodTypeParameterName"> <!-- Java Style Guide: Type variable names -->
             <property name="format" value="(^[A-Z][0-9]?)$|([A-Z][a-zA-Z0-9]*[T]$)"/>
-            <message key="name.invalidPattern" value="Method type name ''{0}'' must match pattern ''{1}''."/>
         </module>
         <module name="NestedForDepth">
             <property name="max" value="2"/>
         </module>
         <module name="NestedTryDepth"/> <!-- Java Coding Guide: Try/catch blocks: never nested -->
         <module name="NonEmptyAtclauseDescription"/> <!-- Java Style Guide: At-clauses -->
         <module name="ParameterName"> <!-- Java Style Guide: Parameter names -->
-            <property name="format" value="^[a-z][a-zA-Z0-9]+$"/>
-            <message key="name.invalidPattern" value="Parameter name ''{0}'' must match pattern ''{1}''."/>
+            <property name="format" value="^[a-z][a-zA-Z0-9]++$"/>
             <property name="ignoreOverridden" value="true"/>
         </module>
 

.github/ISSUE_TEMPLATE/iceberg_bug_report.yml

@@ -28,7 +28,8 @@ body:
       description: What Apache Iceberg version are you using?
       multiple: false
       options:
-        - "1.5.2 (latest release)"
+        - "1.6.0 (latest release)"
+        - "1.5.2"
         - "1.5.1"
         - "1.5.0"
         - "1.4.3"
@@ -76,3 +77,11 @@ body:
         You can include files by dragging and dropping them here.
     validations:
       required: true
+  - type: checkboxes
+    attributes:
+      label: Willingness to contribute
+      description: The Apache Iceberg community encourages bug fix contributions. Would you or another member of your organization be willing to contribute a fix for this bug to the Apache Iceberg codebase?
+      options:
+        - label: I can contribute a fix for this bug independently
+        - label: I would be willing to contribute a fix for this bug with guidance from the Iceberg community
+        - label: I cannot contribute a fix for this bug at this time

.github/workflows/delta-conversion-ci.yml

@@ -71,7 +71,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     env:
       SPARK_LOCAL_IP: localhost
     steps:
@@ -100,7 +100,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     env:
       SPARK_LOCAL_IP: localhost
     steps:

.github/workflows/flink-ci.yml

@@ -73,12 +73,15 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
         flink: ['1.17', '1.18', '1.19']
         exclude:
           # Flink 1.17 does not support Java 17.
           - jvm: 17
             flink: '1.17'
+          # Flink 1.17 does not support Java 21.
+          - jvm: 21
+            flink: '1.17'
     env:
       SPARK_LOCAL_IP: localhost
     steps:

.github/workflows/hive-ci.yml

@@ -69,7 +69,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     env:
       SPARK_LOCAL_IP: localhost
     steps:
@@ -98,7 +98,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     env:
       SPARK_LOCAL_IP: localhost
     steps:

.github/workflows/java-ci.yml

@@ -65,7 +65,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     env:
       SPARK_LOCAL_IP: localhost
     steps:
@@ -94,7 +94,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     steps:
     - uses: actions/checkout@v4
     - uses: actions/setup-java@v4
@@ -107,7 +107,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
     steps:
     - uses: actions/checkout@v4
     - uses: actions/setup-java@v4

.github/workflows/spark-ci.yml

@@ -71,9 +71,16 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        jvm: [8, 11, 17]
+        jvm: [8, 11, 17, 21]
         spark: ['3.3', '3.4', '3.5']
         scala: ['2.12', '2.13']
+        exclude:
+          # Spark 3.5 is the first version not failing on Java 21 (https://issues.apache.org/jira/browse/SPARK-42369)
+          # Full Java 21 support is coming in Spark 4 (https://issues.apache.org/jira/browse/SPARK-43831)
+          - jvm: 21
+            spark: '3.3'
+          - jvm: 21
+            spark: '3.4'
     env:
       SPARK_LOCAL_IP: localhost
     steps:

.github/workflows/stale.yml

@@ -25,6 +25,7 @@ on:
 permissions:
   # All other permissions are set to none
   issues: write
+  pull-requests: write
 
 jobs:
   stale:
@@ -54,4 +55,4 @@ jobs:
           days-before-pr-stale: 30
           days-before-pr-close: 7
           ascending: true
-          operations-per-run: 100
+          operations-per-run: 200

README.md

@@ -51,7 +51,7 @@ Community discussions happen primarily on the [dev mailing list][dev-list] or on
 
 ### Building
 
-Iceberg is built using Gradle with Java 8, 11, or 17.
+Iceberg is built using Gradle with Java 8, 11, 17, or 21.
 
 * To invoke a build and run tests: `./gradlew build`
 * To skip tests: `./gradlew build -x test -x integrationTest`

aliyun/src/test/java/org/apache/iceberg/aliyun/oss/TestOSSOutputStream.java

@@ -50,7 +50,7 @@ public class TestOSSOutputStream extends AliyunOSSTestBase {
   private final OSS ossMock = mock(OSS.class, delegatesTo(ossClient));
 
   private final Path tmpDir = Files.createTempDirectory("oss-file-io-test-");
-  private static final Random random = ThreadLocalRandom.current();
+  private static final Random RANDOM = ThreadLocalRandom.current();
 
   private final AliyunProperties props =
       new AliyunProperties(
@@ -127,7 +127,7 @@ private byte[] data256() {
 
   private byte[] randomData(int size) {
     byte[] data = new byte[size];
-    random.nextBytes(data);
+    RANDOM.nextBytes(data);
     return data;
   }
 

api/src/main/java/org/apache/iceberg/RewriteManifests.java

@@ -54,7 +54,7 @@ public interface RewriteManifests extends SnapshotUpdate<RewriteManifests> {
    * then all manifests will be rewritten.
    *
    * @param predicate Predicate used to determine which manifests to rewrite. If true then the
-   *     manifest file will be included for rewrite. If false then then manifest is kept as-is.
+   *     manifest file will be included for rewrite. If false then the manifest is kept as-is.
    * @return this for method chaining
    */
   RewriteManifests rewriteIf(Predicate<ManifestFile> predicate);

api/src/main/java/org/apache/iceberg/StatisticsFile.java

@@ -28,7 +28,7 @@
  * support is not required to read the table correctly.
  */
 public interface StatisticsFile {
-  /** ID of the Iceberg table's snapshot the statistics were computed from. */
+  /** ID of the Iceberg table's snapshot the statistics file is associated with. */
   long snapshotId();
 
   /**

api/src/main/java/org/apache/iceberg/Table.java

@@ -270,7 +270,7 @@ default AppendFiles newFastAppend() {
   ReplacePartitions newReplacePartitions();
 
   /**
-   * Create a new {@link DeleteFiles delete API} to replace files in this table and commit.
+   * Create a new {@link DeleteFiles delete API} to delete files in this table and commit.
    *
    * @return a new {@link DeleteFiles}
    */
@@ -299,7 +299,7 @@ default UpdatePartitionStatistics updatePartitionStatistics() {
   }
 
   /**
-   * Create a new {@link ExpireSnapshots expire API} to manage snapshots in this table and commit.
+   * Create a new {@link ExpireSnapshots expire API} to expire snapshots in this table and commit.
    *
    * @return a new {@link ExpireSnapshots}
    */

api/src/main/java/org/apache/iceberg/events/Listeners.java

@@ -28,19 +28,19 @@
 public class Listeners {
   private Listeners() {}
 
-  private static final Map<Class<?>, Queue<Listener<?>>> listeners = Maps.newConcurrentMap();
+  private static final Map<Class<?>, Queue<Listener<?>>> LISTENERS = Maps.newConcurrentMap();
 
   public static <E> void register(Listener<E> listener, Class<E> eventType) {
     Queue<Listener<?>> list =
-        listeners.computeIfAbsent(eventType, k -> new ConcurrentLinkedQueue<>());
+        LISTENERS.computeIfAbsent(eventType, k -> new ConcurrentLinkedQueue<>());
     list.add(listener);
   }
 
   @SuppressWarnings("unchecked")
   public static <E> void notifyAll(E event) {
     Preconditions.checkNotNull(event, "Cannot notify listeners for a null event.");
 
-    Queue<Listener<?>> list = listeners.get(event.getClass());
+    Queue<Listener<?>> list = LISTENERS.get(event.getClass());
     if (list != null) {
       for (Listener<?> value : list) {
         Listener<E> listener = (Listener<E>) value;

api/src/main/java/org/apache/iceberg/util/CharSequenceSet.java

@@ -30,7 +30,7 @@
 import org.apache.iceberg.relocated.com.google.common.collect.Streams;
 
 public class CharSequenceSet implements Set<CharSequence>, Serializable {
-  private static final ThreadLocal<CharSequenceWrapper> wrappers =
+  private static final ThreadLocal<CharSequenceWrapper> WRAPPERS =
       ThreadLocal.withInitial(() -> CharSequenceWrapper.wrap(null));
 
   public static CharSequenceSet of(Iterable<CharSequence> charSequences) {
@@ -61,7 +61,7 @@ public boolean isEmpty() {
   @Override
   public boolean contains(Object obj) {
     if (obj instanceof CharSequence) {
-      CharSequenceWrapper wrapper = wrappers.get();
+      CharSequenceWrapper wrapper = WRAPPERS.get();
       boolean result = wrapperSet.contains(wrapper.set((CharSequence) obj));
       wrapper.set(null); // don't hold a reference to the value
       return result;
@@ -109,7 +109,7 @@ public boolean add(CharSequence charSequence) {
   @Override
   public boolean remove(Object obj) {
     if (obj instanceof CharSequence) {
-      CharSequenceWrapper wrapper = wrappers.get();
+      CharSequenceWrapper wrapper = WRAPPERS.get();
       boolean result = wrapperSet.remove(wrapper.set((CharSequence) obj));
       wrapper.set(null); // don't hold a reference to the value
       return result;

api/src/test/java/org/apache/iceberg/expressions/TestAggregateBinding.java

@@ -29,15 +29,15 @@
 import org.junit.jupiter.api.Test;
 
 public class TestAggregateBinding {
-  private static final List<UnboundAggregate<Integer>> list =
+  private static final List<UnboundAggregate<Integer>> LIST =
       ImmutableList.of(Expressions.count("x"), Expressions.max("x"), Expressions.min("x"));
-  private static final StructType struct =
+  private static final StructType STRUCT =
       StructType.of(Types.NestedField.required(10, "x", Types.IntegerType.get()));
 
   @Test
   public void testAggregateBinding() {
-    for (UnboundAggregate<Integer> unbound : list) {
-      Expression expr = unbound.bind(struct, true);
+    for (UnboundAggregate<Integer> unbound : LIST) {
+      Expression expr = unbound.bind(STRUCT, true);
       BoundAggregate<Integer, ?> bound = assertAndUnwrapAggregate(expr);
       assertThat(bound.ref().fieldId()).as("Should reference correct field ID").isEqualTo(10);
       assertThat(bound.op())
@@ -60,15 +60,15 @@ public void testCountStarBinding() {
   @Test
   public void testBoundAggregateFails() {
     Expression unbound = Expressions.count("x");
-    assertThatThrownBy(() -> Binder.bind(struct, Binder.bind(struct, unbound)))
+    assertThatThrownBy(() -> Binder.bind(STRUCT, Binder.bind(STRUCT, unbound)))
         .isInstanceOf(IllegalStateException.class)
         .hasMessageContaining("Found already bound aggregate");
   }
 
   @Test
   public void testCaseInsensitiveReference() {
     Expression expr = Expressions.max("X");
-    Expression boundExpr = Binder.bind(struct, expr, false);
+    Expression boundExpr = Binder.bind(STRUCT, expr, false);
     BoundAggregate<Integer, Integer> bound = assertAndUnwrapAggregate(boundExpr);
     assertThat(bound.ref().fieldId()).as("Should reference correct field ID").isEqualTo(10);
     assertThat(bound.op())
@@ -79,15 +79,15 @@ public void testCaseInsensitiveReference() {
   @Test
   public void testCaseSensitiveReference() {
     Expression expr = Expressions.max("X");
-    assertThatThrownBy(() -> Binder.bind(struct, expr, true))
+    assertThatThrownBy(() -> Binder.bind(STRUCT, expr, true))
         .isInstanceOf(ValidationException.class)
         .hasMessageContaining("Cannot find field 'X' in struct");
   }
 
   @Test
   public void testMissingField() {
     UnboundAggregate<?> unbound = Expressions.count("missing");
-    assertThatThrownBy(() -> unbound.bind(struct, false))
+    assertThatThrownBy(() -> unbound.bind(STRUCT, false))
         .isInstanceOf(ValidationException.class)
         .hasMessageContaining("Cannot find field 'missing' in struct:");
   }