Skip to content

[IcebergIO] Spec aware file reserialization #39973

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ahmedabu98 merged 3 commits into from
Sep 3, 2026
+347 −39
Merged

[IcebergIO] Spec aware file reserialization #39973

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3344178
spec-aware
Sep 2, 2026
d83adef
fix(iceberg): drop the Logger orphaned by the fallback-warning removal
ahmedabu98 Sep 2, 2026
4eb3a04
Merge branch 'master' of https://github.com/ahmedabu98/beam into spec…
ahmedabu98 Sep 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 80 additions & 5 deletions .../java/io/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/SerializableDeleteFile.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import java.util.List;
import java.util.Map;
import java.util.Objects;
import org.apache.beam.sdk.annotations.Internal;
import org.apache.beam.sdk.schemas.AutoValueSchema;
import org.apache.beam.sdk.schemas.annotations.DefaultSchema;
import org.apache.beam.sdk.schemas.annotations.SchemaFieldNumber;
Expand All @@ -37,11 +38,14 @@
import org.apache.iceberg.FileMetadata;
import org.apache.iceberg.Metrics;
import org.apache.iceberg.PartitionSpec;
import org.apache.iceberg.SingleValueParser;
import org.apache.iceberg.SortOrder;
import org.apache.iceberg.StructLike;
import org.checkerframework.checker.nullness.qual.Nullable;

@DefaultSchema(AutoValueSchema.class)
@AutoValue
@Internal
public abstract class SerializableDeleteFile {
public static SerializableDeleteFile.Builder builder() {
return new AutoValue_SerializableDeleteFile.Builder();
Expand All @@ -62,7 +66,11 @@ public static SerializableDeleteFile.Builder builder() {
@SchemaFieldNumber("4")
public abstract long getFileSizeInBytes();

/**
* @deprecated Use {@link #getJsonPartition()} instead.
Comment thread
ahmedabu98 marked this conversation as resolved.
*/
@SchemaFieldNumber("5")
@Deprecated
public abstract String getPartitionPath();

@SchemaFieldNumber("6")
Expand Down Expand Up @@ -113,6 +121,9 @@ public static SerializableDeleteFile.Builder builder() {
@SchemaFieldNumber("21")
public abstract @Nullable Long getFileSequenceNumber();

@SchemaFieldNumber("22")
abstract @Nullable String getJsonPartition();

@AutoValue.Builder
abstract static class Builder {
abstract Builder setContentType(FileContent content);
Expand All @@ -127,6 +138,8 @@ abstract static class Builder {

abstract Builder setPartitionPath(String partitionPath);

abstract Builder setJsonPartition(String jsonPartition);

abstract Builder setPartitionSpecId(int partitionSpec);

abstract Builder setSortOrderId(@Nullable Integer sortOrderId);
Expand Down Expand Up @@ -163,14 +176,55 @@ abstract static class Builder {
}

public static SerializableDeleteFile from(
DeleteFile deleteFile, String partitionPath, boolean includeMetrics) {
DeleteFile deleteFile, Map<Integer, PartitionSpec> specs) {
return from(deleteFile, specs, true);
}

/**
* Creates a {@link SerializableDeleteFile}, resolving the file's {@link PartitionSpec} by its own
* spec id.
*
* <p>Delete files reached from a scan task may carry a spec id that differs from the spec of the
* data file they apply to, so the lookup has to be per delete file rather than against a single
* "current" spec.
*/
public static SerializableDeleteFile from(
DeleteFile deleteFile, Map<Integer, PartitionSpec> specs, boolean includeMetrics) {
return from(
deleteFile,
checkStateNotNull(
specs.get(deleteFile.specId()),
"Could not create a SerializableDeleteFile because DeleteFile is written using a partition spec id '%s' that is not found in the provided specs: %s",
deleteFile.specId(),
specs.keySet()),
includeMetrics);
}

public static SerializableDeleteFile from(DeleteFile deleteFile, PartitionSpec spec) {
return from(deleteFile, spec, true);
}

public static SerializableDeleteFile from(
DeleteFile deleteFile, PartitionSpec spec, boolean includeMetrics) {
if (spec.specId() != deleteFile.specId()) {
throw new IllegalArgumentException(
String.format(
"Cannot serialize DeleteFile: its partition spec id %s does not match the provided "
+ "spec id %s.",
deleteFile.specId(), spec.specId()));
}
// jsonPartition is the primary (handles evolved specs, special characters).
// partitionPath is the fallback for values that don't round-trip through JSON.
String jsonPartition = SingleValueParser.toJson(spec.partitionType(), deleteFile.partition());
String partitionPath = spec.partitionToPath(deleteFile.partition());

SerializableDeleteFile.Builder builder =
SerializableDeleteFile.builder()
.setLocation(deleteFile.location())
.setFileFormat(deleteFile.format().name())
.setFileSizeInBytes(deleteFile.fileSizeInBytes())
.setPartitionPath(partitionPath)
.setJsonPartition(jsonPartition)
.setPartitionSpecId(deleteFile.specId())
.setRecordCount(deleteFile.recordCount())
.setColumnSizes(deleteFile.columnSizes())
Expand Down Expand Up @@ -228,7 +282,21 @@ public DeleteFile createDeleteFile(
.withMetrics(metrics)
.withSplitOffsets(getSplitOffsets())
.withEncryptionKeyMetadata(getKeyMetadata())
.withPartitionPath(getPartitionPath());
.withReferencedDataFile(getReferencedDataFile());

@Nullable String jsonPartition = getJsonPartition();
if (jsonPartition != null) {
try {
deleteFileBuilder = deleteFileBuilder.withPartition(partition(partitionSpec));
} catch (RuntimeException e) {

@chamikaramj chamikaramj Sep 3, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: seems like this catch might be too broad ? Should we either catch a Exception that is less broad or rethrow ?

@ahmedabu98 ahmedabu98 Sep 3, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Underlying utils throw different types of RuntimeExceptions (see similar comment here(#39705 (comment)))

// Some partition values (e.g. NaN / Infinity floating-point) don't round-trip through the
// JSON representation; fall back to the partition-path string
deleteFileBuilder = deleteFileBuilder.withPartitionPath(getPartitionPath());
}
} else {
// Elements decoded from a pre-jsonPartition release carry only the partition path.
deleteFileBuilder = deleteFileBuilder.withPartitionPath(getPartitionPath());
}

switch (getContentType()) {
case POSITION_DELETES:
Expand Down Expand Up @@ -260,17 +328,22 @@ public DeleteFile createDeleteFile(
"Unexpected content type for DeleteFile: " + getContentType());
}

// needed for puffin files
// contentOffset / contentSizeInBytes really are Puffin-only: build() rejects a non-null value
// for either on any other format, and requires both (plus referencedDataFile) on Puffin.
if (getFileFormat().equalsIgnoreCase(FileFormat.PUFFIN.name())) {
deleteFileBuilder =
deleteFileBuilder
.withContentOffset(checkStateNotNull(getContentOffset()))
.withContentSizeInBytes(checkStateNotNull(getContentSizeInBytes()))
.withReferencedDataFile(checkStateNotNull(getReferencedDataFile()));
.withContentSizeInBytes(checkStateNotNull(getContentSizeInBytes()));
}
return deleteFileBuilder.build();
}

private StructLike partition(PartitionSpec spec) {
return (StructLike)
SingleValueParser.fromJson(spec.partitionType(), checkStateNotNull(getJsonPartition()));
}

@Override
public final boolean equals(@Nullable Object o) {
if (this == o) {
Expand All @@ -287,6 +360,7 @@ && getRecordCount() == that.getRecordCount()
&& getFileSizeInBytes() == that.getFileSizeInBytes()
&& getPartitionPath().equals(that.getPartitionPath())
&& getPartitionSpecId() == that.getPartitionSpecId()
&& Objects.equals(getJsonPartition(), that.getJsonPartition())
&& Objects.equals(getSortOrderId(), that.getSortOrderId())
&& Objects.equals(getEqualityFieldIds(), that.getEqualityFieldIds())
&& Objects.equals(getKeyMetadata(), that.getKeyMetadata())
Expand Down Expand Up @@ -314,6 +388,7 @@ public final int hashCode() {
getRecordCount(),
getFileSizeInBytes(),
getPartitionPath(),
getJsonPartition(),
getPartitionSpecId(),
getSortOrderId(),
getEqualityFieldIds(),
Expand Down
10 changes: 3 additions & 7 deletions ...o/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/cdc/SerializableChangelogTask.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@
*/
package org.apache.beam.sdk.io.iceberg.cdc;

import static org.apache.beam.sdk.util.Preconditions.checkStateNotNull;
import static org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.Preconditions.checkState;

import com.google.auto.value.AutoValue;
Expand Down Expand Up @@ -267,13 +266,10 @@ static List<DeleteFile> getAddedDeleteFiles(ChangelogScanTask task) {

private static List<SerializableDeleteFile> toSerializableDeletes(
List<DeleteFile> dfs, Map<Integer, PartitionSpec> specs, boolean includeMetrics) {
// Serialize each delete file against its own spec (looked up by its spec id): a delete file may
// carry a different spec id than the data file it applies to.
return dfs.stream()
.map(
df ->
SerializableDeleteFile.from(
df,
checkStateNotNull(specs.get(df.specId())).partitionToPath(df.partition()),
includeMetrics))
.map(df -> SerializableDeleteFile.from(df, specs, includeMetrics))
.collect(Collectors.toList());
}
}
Loading
Loading