aokolnychyi commented on code in PR #5376:
URL: https://github.com/apache/iceberg/pull/5376#discussion_r949550004
##########
core/src/main/java/org/apache/iceberg/BaseFilesTable.java:
##########
@@ -143,33 +177,49 @@ static class ManifestReadTask extends BaseFileScanTask
implements DataTask {
private final FileIO io;
private final Map<Integer, PartitionSpec> specsById;
private final ManifestFile manifest;
- private final Schema schema;
+ private final Schema filesTableSchema;
+ private final Schema dataTableSchema;
+ private final Schema projectedSchema;
+ private final Map<Integer, String> dataTableFields;
+ private final boolean isPartitioned;
ManifestReadTask(
Table table,
ManifestFile manifest,
Schema schema,
+ Schema projectedSchema,
String schemaString,
String specString,
- ResidualEvaluator residuals) {
+ ResidualEvaluator residuals,
+ Map<Integer, String> dataTableFields) {
super(DataFiles.fromManifest(manifest), null, schemaString, specString,
residuals);
this.io = table.io();
this.specsById = Maps.newHashMap(table.specs());
this.manifest = manifest;
- this.schema = schema;
+ this.filesTableSchema = schema;
+ this.dataTableSchema = table.schema();
+ this.dataTableFields = dataTableFields;
+ this.isPartitioned = filesTableSchema.findField(DataFile.PARTITION_ID)
!= null;
+ this.projectedSchema = projectedSchema;
}
@Override
public CloseableIterable<StructLike> rows() {
- return CloseableIterable.transform(manifestEntries(), file ->
(StructLike) file);
+ return CloseableIterable.transform(
+ manifestEntries(),
+ fileEntry ->
+ StaticDataTask.Row.of(
+ projectedFields(fileEntry,
accessors(isPartitioned)).toArray()));
}
private CloseableIterable<? extends ContentFile<?>> manifestEntries() {
+ Schema fileProjection =
+ TypeUtil.selectNot(projectedSchema,
TypeUtil.getProjectedIds(READABLE_METRICS.type()));
Review Comment:
If you define a var to hold the result of `TypeUtil.getProjectedIds()`, this
would fit on one line.
##########
core/src/main/java/org/apache/iceberg/BaseFilesTable.java:
##########
@@ -143,33 +177,49 @@ static class ManifestReadTask extends BaseFileScanTask
implements DataTask {
private final FileIO io;
private final Map<Integer, PartitionSpec> specsById;
private final ManifestFile manifest;
- private final Schema schema;
+ private final Schema filesTableSchema;
+ private final Schema dataTableSchema;
+ private final Schema projectedSchema;
+ private final Map<Integer, String> dataTableFields;
+ private final boolean isPartitioned;
ManifestReadTask(
Table table,
ManifestFile manifest,
Schema schema,
+ Schema projectedSchema,
String schemaString,
String specString,
- ResidualEvaluator residuals) {
+ ResidualEvaluator residuals,
+ Map<Integer, String> dataTableFields) {
super(DataFiles.fromManifest(manifest), null, schemaString, specString,
residuals);
this.io = table.io();
this.specsById = Maps.newHashMap(table.specs());
this.manifest = manifest;
- this.schema = schema;
+ this.filesTableSchema = schema;
+ this.dataTableSchema = table.schema();
+ this.dataTableFields = dataTableFields;
+ this.isPartitioned = filesTableSchema.findField(DataFile.PARTITION_ID)
!= null;
+ this.projectedSchema = projectedSchema;
}
@Override
public CloseableIterable<StructLike> rows() {
- return CloseableIterable.transform(manifestEntries(), file ->
(StructLike) file);
+ return CloseableIterable.transform(
+ manifestEntries(),
+ fileEntry ->
+ StaticDataTask.Row.of(
+ projectedFields(fileEntry,
accessors(isPartitioned)).toArray()));
}
private CloseableIterable<? extends ContentFile<?>> manifestEntries() {
+ Schema fileProjection =
+ TypeUtil.selectNot(projectedSchema,
TypeUtil.getProjectedIds(READABLE_METRICS.type()));
Review Comment:
nit: If you define a var to hold the result of `TypeUtil.getProjectedIds()`,
this would fit on one line.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
