Skip to content

Spark: Backport various fixes for SparkFileWriterFactory #15357

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
pvary merged 1 commit into from
Feb 18, 2026
Merged

Spark: Backport various fixes for SparkFileWriterFactory #15357

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 0 additions & 9 deletions spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/SparkParquetWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,15 +77,6 @@ public static <T> ParquetValueWriter<T> buildWriter(
new WriteBuilder(type));
}

public static <T> ParquetValueWriter<T> buildWriter(
StructType dfSchema, MessageType type, Schema icebergSchema) {
return (ParquetValueWriter<T>)
ParquetWithSparkSchemaVisitor.visit(
dfSchema != null ? dfSchema : SparkSchemaUtil.convert(icebergSchema),
type,
new WriteBuilder(type));
}

private static class WriteBuilder extends ParquetWithSparkSchemaVisitor<ParquetValueWriter<?>> {
private final MessageType type;

Expand Down
11 changes: 5 additions & 6 deletions spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkFileWriterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
private StructType positionDeleteSparkType;
private final Schema positionDeleteRowSchema;
private final Table table;
private final FileFormat format;
private final FileFormat deleteFormat;
private final Map<String, String> writeProperties;

/**
Expand Down Expand Up @@ -100,7 +100,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = positionDeleteRowSchema;
this.positionDeleteSparkType = positionDeleteSparkType;
Expand Down Expand Up @@ -138,7 +138,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = null;
this.useDeprecatedPositionDeleteWriter = false;
Expand Down Expand Up @@ -172,7 +172,7 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
: MetricsConfig.forPositionDelete(table);

try {
return switch (format) {
return switch (deleteFormat) {
case AVRO ->
Avro.writeDeletes(file)
.createWriterFunc(
Expand Down Expand Up @@ -215,14 +215,13 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
.metricsConfig(metricsConfig)
.withPartition(partition)
.overwrite()
.metricsConfig(metricsConfig)
.rowSchema(positionDeleteRowSchema)
.withSpec(spec)
.withKeyMetadata(file.keyMetadata())
.buildPositionWriter();
default ->
throw new UnsupportedOperationException(
"Cannot write pos-deletes for unsupported file format: " + format);
"Cannot write pos-deletes for unsupported file format: " + deleteFormat);
};
} catch (IOException e) {
throw new UncheckedIOException("Failed to create new position delete writer", e);
Expand Down
9 changes: 0 additions & 9 deletions spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/data/SparkParquetWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,15 +77,6 @@ public static <T> ParquetValueWriter<T> buildWriter(
new WriteBuilder(type));
}

public static <T> ParquetValueWriter<T> buildWriter(
StructType dfSchema, MessageType type, Schema icebergSchema) {
return (ParquetValueWriter<T>)
ParquetWithSparkSchemaVisitor.visit(
dfSchema != null ? dfSchema : SparkSchemaUtil.convert(icebergSchema),
type,
new WriteBuilder(type));
}

private static class WriteBuilder extends ParquetWithSparkSchemaVisitor<ParquetValueWriter<?>> {
private final MessageType type;

Expand Down
11 changes: 5 additions & 6 deletions spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkFileWriterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
private StructType positionDeleteSparkType;
private final Schema positionDeleteRowSchema;
private final Table table;
private final FileFormat format;
private final FileFormat deleteFormat;
private final Map<String, String> writeProperties;

/**
Expand Down Expand Up @@ -100,7 +100,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = positionDeleteRowSchema;
this.positionDeleteSparkType = positionDeleteSparkType;
Expand Down Expand Up @@ -138,7 +138,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = null;
this.useDeprecatedPositionDeleteWriter = false;
Expand Down Expand Up @@ -172,7 +172,7 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
: MetricsConfig.forPositionDelete(table);

try {
return switch (format) {
return switch (deleteFormat) {
case AVRO ->
Avro.writeDeletes(file)
.createWriterFunc(
Expand Down Expand Up @@ -215,14 +215,13 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
.metricsConfig(metricsConfig)
.withPartition(partition)
.overwrite()
.metricsConfig(metricsConfig)
.rowSchema(positionDeleteRowSchema)
.withSpec(spec)
.withKeyMetadata(file.keyMetadata())
.buildPositionWriter();
default ->
throw new UnsupportedOperationException(
"Cannot write pos-deletes for unsupported file format: " + format);
"Cannot write pos-deletes for unsupported file format: " + deleteFormat);
};
} catch (IOException e) {
throw new UncheckedIOException("Failed to create new position delete writer", e);
Expand Down
9 changes: 0 additions & 9 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/data/SparkParquetWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,15 +91,6 @@ public static <T> ParquetValueWriter<T> buildWriter(
new WriteBuilder(type));
}

public static <T> ParquetValueWriter<T> buildWriter(
StructType dfSchema, MessageType type, Schema icebergSchema) {
return (ParquetValueWriter<T>)
ParquetWithSparkSchemaVisitor.visit(
dfSchema != null ? dfSchema : SparkSchemaUtil.convert(icebergSchema),
type,
new WriteBuilder(type));
}

private static class WriteBuilder extends ParquetWithSparkSchemaVisitor<ParquetValueWriter<?>> {
private final MessageType type;

Expand Down
11 changes: 5 additions & 6 deletions spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkFileWriterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
private StructType positionDeleteSparkType;
private final Schema positionDeleteRowSchema;
private final Table table;
private final FileFormat format;
private final FileFormat deleteFormat;
private final Map<String, String> writeProperties;

/**
Expand Down Expand Up @@ -100,7 +100,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = positionDeleteRowSchema;
this.positionDeleteSparkType = positionDeleteSparkType;
Expand Down Expand Up @@ -138,7 +138,7 @@ class SparkFileWriterFactory extends RegistryBasedFileWriterFactory<InternalRow,
useOrConvert(equalityDeleteSparkType, equalityDeleteRowSchema));

this.table = table;
this.format = dataFileFormat;
this.deleteFormat = deleteFileFormat;
this.writeProperties = writeProperties != null ? writeProperties : ImmutableMap.of();
this.positionDeleteRowSchema = null;
this.useDeprecatedPositionDeleteWriter = false;
Expand Down Expand Up @@ -172,7 +172,7 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
: MetricsConfig.forPositionDelete(table);

try {
return switch (format) {
return switch (deleteFormat) {
case AVRO ->
Avro.writeDeletes(file)
.createWriterFunc(
Expand Down Expand Up @@ -215,14 +215,13 @@ public PositionDeleteWriter<InternalRow> newPositionDeleteWriter(
.metricsConfig(metricsConfig)
.withPartition(partition)
.overwrite()
.metricsConfig(metricsConfig)
.rowSchema(positionDeleteRowSchema)
.withSpec(spec)
.withKeyMetadata(file.keyMetadata())
.buildPositionWriter();
default ->
throw new UnsupportedOperationException(
"Cannot write pos-deletes for unsupported file format: " + format);
"Cannot write pos-deletes for unsupported file format: " + deleteFormat);
};
} catch (IOException e) {
throw new UncheckedIOException("Failed to create new position delete writer", e);
Expand Down