hubgeter commented on code in PR #65851:
URL: https://github.com/apache/doris/pull/65851#discussion_r3657804372
##########
fe/fe-core/src/main/java/org/apache/doris/datasource/iceberg/source/IcebergScanNode.java:
##########
@@ -524,30 +578,504 @@ void enableCurrentIcebergScanSemantics() {
params.setIcebergScanSemanticsVersion(ICEBERG_SCAN_SEMANTICS_VERSION);
}
+ /**
+ * Build the schema metadata carrier used by both scanners and
equality-delete readers.
+ *
+ * <p>Batch-mode delete files are planned asynchronously after scan
parameters are sent to BE.
+ * The authenticated manifest preflight therefore supplies the live
equality field IDs before
+ * the schema carrier is serialized. Only historical fields referenced by
those delete files are
+ * added, so an unrelated dropped type cannot make an otherwise supported
scan fail.
+ */
+ @VisibleForTesting
+ List<NestedField> getSchemaFieldsForScan(
+ Schema scanSchema, Set<Integer> equalityDeleteFieldIds) throws
UserException {
+ List<NestedField> fields = new ArrayList<>(scanSchema.columns());
+ if (isSystemTable || equalityDeleteFieldIds.isEmpty()) {
+ return fields;
+ }
+
+ Set<Integer> missingFieldIds = new HashSet<>(equalityDeleteFieldIds);
+
missingFieldIds.removeAll(TypeUtil.indexById(scanSchema.asStruct()).keySet());
+ if (missingFieldIds.isEmpty()) {
+ return fields;
+ }
+
+ List<Schema> schemaHistory = getMetadataSchemaHistory();
+ // Schema IDs may be reused when evolution returns to an earlier
schema, while the metadata
+ // list may also contain schemas committed after a time-travel or
branch target. Follow the
+ // actual scan snapshot's parent chain first so the field definition
active on that lineage
+ // wins. Then use the complete metadata list as a fallback for
schema-only changes and
+ // expired ancestors. A fallback definition may come from a later
rename, so BE resolves an
+ // ID-less equality key through the target mapping first and the
delete file's original key
+ // name second. Initial-default and field identity remain bound to the
stable field ID.
+ Snapshot snapshot = createTableScan().snapshot();
+ while (snapshot != null) {
+ Integer schemaId = snapshot.schemaId();
+ if (schemaId != null) {
+ Schema historicalSchema = icebergTable.schemas().get(schemaId);
+ Preconditions.checkState(historicalSchema != null,
+ "Iceberg snapshot schema %s is absent from table
metadata", schemaId);
+ addHistoricalEqualityFields(fields, missingFieldIds,
historicalSchema);
+ }
+ Long parentId = snapshot.parentId();
+ snapshot = parentId == null ? null :
icebergTable.snapshot(parentId);
+ }
+ for (int index = schemaHistory.size() - 1; index >= 0; index--) {
+ addHistoricalEqualityFields(fields, missingFieldIds,
schemaHistory.get(index));
+ }
+ Preconditions.checkState(missingFieldIds.isEmpty(),
+ "Iceberg equality-delete fields are absent from schema
history: %s",
+ missingFieldIds);
+ return fields;
+ }
+
+ private List<Schema> getMetadataSchemaHistory() {
+ Preconditions.checkState(icebergTable instanceof HasTableOperations,
+ "Iceberg table does not expose metadata schema history: %s",
icebergTable.name());
+ return ((HasTableOperations)
icebergTable).operations().current().schemas();
+ }
+
+ private static void addHistoricalEqualityFields(List<NestedField> fields,
+ Set<Integer> missingFieldIds, Schema historicalSchema) {
+ for (NestedField field :
TypeUtil.indexById(historicalSchema.asStruct()).values()) {
+ if (missingFieldIds.remove(field.fieldId())) {
+ Preconditions.checkState(field.type().isPrimitiveType(),
+ "Iceberg equality-delete field %s must be primitive",
field.fieldId());
+ fields.add(field);
+ }
+ }
+ }
+
+ @VisibleForTesting
+ static boolean requiresRecursiveInitialDefaultMaterialization(
+ Schema scanSchema, List<SlotDescriptor> projectedSlots) {
+ return requiresProjectedIcebergField(scanSchema, projectedSlots,
+ (field, isTopLevel) -> field.initialDefault() != null
+ && (!isTopLevel || field.type().isNestedType()));
+ }
+
+ @VisibleForTesting
+ static boolean requiresMissingRequiredFieldRejection(
+ Schema scanSchema, List<SlotDescriptor> projectedSlots,
+ List<Schema> historicalSchemas) {
+ Map<Integer, NestedField> fieldById =
TypeUtil.indexById(scanSchema.asStruct());
+ Map<Integer, Integer> parentById =
TypeUtil.indexParents(scanSchema.asStruct());
+ Set<Integer> collectionWrapperFieldIds = new HashSet<>();
+ collectCollectionWrapperFieldIds(scanSchema.asStruct(),
collectionWrapperFieldIds);
+ Set<Integer> potentiallyMissingRequiredFieldIds = new HashSet<>();
+ for (Schema historicalSchema : historicalSchemas) {
+ Map<Integer, NestedField> historicalFieldById =
+ TypeUtil.indexById(historicalSchema.asStruct());
+ for (NestedField field : fieldById.values()) {
+ NestedField historicalField =
historicalFieldById.get(field.fieldId());
+ if (historicalField != null) {
+ if (!collectionWrapperFieldIds.contains(field.fieldId())
+ && field.isRequired() && field.initialDefault() ==
null
+ && historicalField.isOptional()) {
+
potentiallyMissingRequiredFieldIds.add(field.fieldId());
+ }
+ continue;
+ }
+ NestedField highestMissingField = field;
+ Integer parentId = parentById.get(field.fieldId());
+ while (parentId != null &&
!historicalFieldById.containsKey(parentId)) {
+ highestMissingField =
Preconditions.checkNotNull(fieldById.get(parentId),
+ "Iceberg parent field %s is absent from scan
schema", parentId);
+ parentId = parentById.get(parentId);
+ }
+ // If the highest missing ancestor is optional, the old
physical subtree is NULL
+ // and no required descendant is materialized. A non-null
initial default is
+ // already covered by
requiresRecursiveInitialDefaultMaterialization().
+ if
(!collectionWrapperFieldIds.contains(highestMissingField.fieldId())
+ && highestMissingField.isRequired()
+ && highestMissingField.initialDefault() == null) {
+
potentiallyMissingRequiredFieldIds.add(highestMissingField.fieldId());
+ }
+ }
+ }
+ return requiresProjectedIcebergField(scanSchema, projectedSlots,
+ (field, isTopLevel) ->
potentiallyMissingRequiredFieldIds.contains(
+ field.fieldId()));
+ }
+
+ private static void collectCollectionWrapperFieldIds(
+ Type type, Set<Integer> collectionWrapperFieldIds) {
+ switch (type.typeId()) {
+ case STRUCT:
+ for (NestedField field : type.asStructType().fields()) {
+ collectCollectionWrapperFieldIds(field.type(),
collectionWrapperFieldIds);
+ }
+ break;
+ case LIST:
+ Types.ListType listType = (Types.ListType) type;
+ collectionWrapperFieldIds.add(listType.elementId());
+ collectCollectionWrapperFieldIds(
+ listType.elementType(), collectionWrapperFieldIds);
+ break;
+ case MAP:
+ Types.MapType mapType = (Types.MapType) type;
+ collectionWrapperFieldIds.add(mapType.keyId());
+ collectionWrapperFieldIds.add(mapType.valueId());
+ collectCollectionWrapperFieldIds(mapType.keyType(),
collectionWrapperFieldIds);
+ collectCollectionWrapperFieldIds(mapType.valueType(),
collectionWrapperFieldIds);
+ break;
+ default:
+ break;
+ }
+ }
+
+ private static boolean requiresProjectedIcebergField(
+ Schema scanSchema, List<SlotDescriptor> projectedSlots,
+ ProjectedFieldRequirement requirement) {
+ Map<Integer, NestedField> fieldById =
TypeUtil.indexById(scanSchema.asStruct());
+ Set<Integer> topLevelFieldIds = new HashSet<>();
+ for (NestedField field : scanSchema.columns()) {
+ topLevelFieldIds.add(field.fieldId());
+ }
+ for (SlotDescriptor slot : projectedSlots) {
+ Column column = slot.getColumn();
+ List<ColumnAccessPath> accessPaths = slot.getAllAccessPaths();
+ if (accessPaths != null && !accessPaths.isEmpty()) {
+ for (ColumnAccessPath accessPath : accessPaths) {
+ List<String> path = accessPath.getPath();
+ Preconditions.checkState(!path.isEmpty(),
+ "Iceberg column access path must not be empty");
+
Preconditions.checkState(matchesAccessPathComponent(column, path.get(0)),
+ "Iceberg access path root %s does not match column
%s", path.get(0),
+ column.getName());
+ if (requiresProjectedIcebergField(
+ column, path, 1, fieldById,
+ topLevelFieldIds.contains(column.getUniqueId()),
requirement)) {
+ return true;
+ }
+ }
+ } else if (requiresProjectedIcebergField(
+ column, slot.getType(), fieldById,
+ topLevelFieldIds.contains(column.getUniqueId()),
requirement)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ private static boolean requiresProjectedIcebergField(
+ Column column, org.apache.doris.catalog.Type projectedType,
+ Map<Integer, NestedField> fieldById, boolean isTopLevel,
+ ProjectedFieldRequirement requirement) {
+ if (requiresIcebergField(column, fieldById, isTopLevel, requirement)) {
+ return true;
+ }
+ if (column.getChildren() == null) {
+ return false;
+ }
+ if (projectedType.isStructType()) {
+ for (StructField projectedField : ((StructType)
projectedType).getFields()) {
+ Column child = findChildByName(column,
projectedField.getName());
+ Preconditions.checkState(child != null,
+ "Projected Iceberg child %s is absent from column %s",
+ projectedField.getName(), column.getName());
+ if (requiresProjectedIcebergField(
+ child, projectedField.getType(), fieldById, false,
requirement)) {
+ return true;
+ }
+ }
+ } else if (projectedType.isArrayType()) {
+ Preconditions.checkState(column.getChildren().size() == 1,
+ "Iceberg array column %s must have one child",
column.getName());
+ if (requiresProjectedIcebergField(
+ column.getChildren().get(0), ((ArrayType)
projectedType).getItemType(),
+ fieldById, false, requirement)) {
+ return true;
+ }
+ } else if (projectedType.isMapType()) {
+ Preconditions.checkState(column.getChildren().size() == 2,
+ "Iceberg map column %s must have two children",
column.getName());
+ MapType mapType = (MapType) projectedType;
+ if (requiresProjectedIcebergField(
+ column.getChildren().get(0), mapType.getKeyType(),
fieldById, false,
+ requirement)
+ || requiresProjectedIcebergField(
+ column.getChildren().get(1),
mapType.getValueType(), fieldById, false,
+ requirement)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ private static boolean requiresProjectedIcebergField(
+ Column column, List<String> path, int pathIndex,
+ Map<Integer, NestedField> fieldById, boolean isTopLevel,
+ ProjectedFieldRequirement requirement) {
+ if (requiresIcebergField(column, fieldById, isTopLevel, requirement)) {
+ return true;
+ }
+ if (pathIndex == path.size()) {
+ return requiresProjectedIcebergField(column, fieldById,
requirement);
+ }
+
+ String component = path.get(pathIndex);
+ if (AccessPathInfo.ACCESS_NULL.equals(component)
+ || AccessPathInfo.ACCESS_OFFSET.equals(component)) {
+ return false;
+ }
+ Preconditions.checkState(column.getChildren() != null,
+ "Iceberg access path continues below primitive column %s",
column.getName());
+
+ if (AccessPathInfo.ACCESS_ALL.equals(component)) {
+ if (column.getType().isArrayType()) {
+ Preconditions.checkState(column.getChildren().size() == 1,
+ "Iceberg array column %s must have one child",
column.getName());
+ return requiresProjectedIcebergField(
+ column.getChildren().get(0), path, pathIndex + 1,
fieldById, false,
+ requirement);
+ }
+ Preconditions.checkState(column.getType().isMapType(),
+ "Unexpected Iceberg access-all path below column %s",
column.getName());
+ Preconditions.checkState(column.getChildren().size() == 2,
+ "Iceberg map column %s must have two children",
column.getName());
+ Column key = column.getChildren().get(0);
+ // element_at(map, key) reads the complete key subtree, while any
path after '*'
+ // describes only the selected value subtree.
+ if (requiresIcebergField(key, fieldById, false, requirement)
+ || requiresProjectedIcebergField(key, fieldById,
requirement)) {
+ return true;
+ }
+ return requiresProjectedIcebergField(
+ column.getChildren().get(1), path, pathIndex + 1,
fieldById, false,
+ requirement);
+ }
+ if (column.getType().isMapType()) {
+ Preconditions.checkState(column.getChildren().size() == 2,
+ "Iceberg map column %s must have two children",
column.getName());
+ int childIndex;
+ if (AccessPathInfo.ACCESS_MAP_KEYS.equals(component)) {
+ childIndex = 0;
+ } else {
+
Preconditions.checkState(AccessPathInfo.ACCESS_MAP_VALUES.equals(component),
+ "Unexpected Iceberg map access path component %s",
component);
+ childIndex = 1;
+ }
+ return requiresProjectedIcebergField(
+ column.getChildren().get(childIndex), path, pathIndex + 1,
fieldById, false,
+ requirement);
+ }
+
+ Column child = findAccessPathChild(column, component);
+ Preconditions.checkState(child != null,
+ "Iceberg access path child %s is absent from column %s",
component,
+ column.getName());
+ return requiresProjectedIcebergField(
+ child, path, pathIndex + 1, fieldById, false, requirement);
+ }
+
+ private static boolean requiresProjectedIcebergField(
+ Column column, Map<Integer, NestedField> fieldById,
+ ProjectedFieldRequirement requirement) {
+ if (column.getChildren() == null) {
+ return false;
+ }
+ for (Column child : column.getChildren()) {
+ if (requiresIcebergField(child, fieldById, false, requirement)
+ || requiresProjectedIcebergField(child, fieldById,
requirement)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ private static boolean requiresIcebergField(
+ Column column, Map<Integer, NestedField> fieldById, boolean
isTopLevel,
+ ProjectedFieldRequirement requirement) {
+ NestedField field = fieldById.get(column.getUniqueId());
+ return field != null && requirement.requires(field, isTopLevel);
+ }
+
+ private interface ProjectedFieldRequirement {
+ boolean requires(NestedField field, boolean isTopLevel);
+ }
+
+ private static boolean matchesAccessPathComponent(Column column, String
component) {
+ return Integer.toString(column.getUniqueId()).equals(component)
+ || column.getName().equalsIgnoreCase(component);
+ }
+
+ private static Column findAccessPathChild(Column column, String component)
{
+ for (Column child : column.getChildren()) {
+ if (matchesAccessPathComponent(child, component)) {
+ return child;
+ }
+ }
+ return null;
+ }
+
+ private static Column findChildByName(Column column, String childName) {
+ for (Column child : column.getChildren()) {
+ if (child.getName().equalsIgnoreCase(childName)) {
+ return child;
+ }
+ }
+ return null;
+ }
+
+ @VisibleForTesting
+ Set<Integer> getEqualityDeleteFieldIdsForScan() throws UserException {
+ Snapshot snapshot = createTableScan().snapshot();
+ if (snapshot == null) {
+ return Collections.emptySet();
+ }
+ try {
+ // deleteManifests() can lazily read the manifest list. Keep both
that call and the
+ // manifest-entry cache load inside the catalog's authentication
context.
+ return preExecutionAuthenticator.execute(
+ () -> loadEqualityDeleteFieldIds(snapshot));
+ } catch (Exception e) {
+ Optional<NotSupportedException> opt =
checkNotSupportedException(e);
+ if (opt.isPresent()) {
+ throw opt.get();
+ }
+ throw new UserException(ExceptionUtils.getRootCauseMessage(e), e);
+ }
+ }
+
+ @VisibleForTesting
+ Set<Integer> loadEqualityDeleteFieldIds(Snapshot snapshot) {
+ IcebergExternalMetaCache cache =
Env.getCurrentEnv().getExtMetaCacheMgr()
+ .iceberg(source.getCatalog().getId());
+ Preconditions.checkState(source.getTargetTable() instanceof
ExternalTable,
+ "Iceberg scan target table is not an external table");
+ ExternalTable targetExternalTable = (ExternalTable)
source.getTargetTable();
+ Set<Integer> equalityDeleteFieldIds = new HashSet<>();
+ for (ManifestFile manifest :
snapshot.deleteManifests(icebergTable.io())) {
+ Preconditions.checkState(manifest.content() ==
ManifestContent.DELETES,
+ "Iceberg delete manifest %s has content %s",
manifest.path(),
+ manifest.content());
+ ManifestCacheValue value =
IcebergManifestCacheLoader.loadDeleteFilesWithCache(
+ cache, targetExternalTable, manifest, icebergTable,
+ this::recordManifestCacheAccess);
+ equalityDeleteFieldIds.addAll(
Review Comment:
Fixed in 0dd1a86a681. Equality field IDs are now collected only from delete
files attached to the applicable FileScanTasks produced by the same filtered
TableScan. Rewrite planning reuses the retained task list without consuming it;
other scans make a bounded second planning pass. IcebergScanNodeTest adds a
cross-partition historical unsupported-field case. Focused FE tests passed
113/113 and the partition-evolution equality-delete regression passed.
##########
docs/iceberg-v3-default-values-agent-handoff.md:
##########
@@ -0,0 +1,1066 @@
+# Iceberg V3 Default Values 全权处理交接
+
+> 状态日期：2026-07-24
+>
+> 当前 PR：[apache/doris#65851](https://github.com/apache/doris/pull/65851)
+>
+> 唯一工作目录：`/mnt/disk1/changyuwei/doris-worktrees/iceberg-v3-defaults`
Review Comment:
Fixed in 0dd1a86a681. The contributor-local handoff document has been
removed. Durable semantics remain in docs/iceberg-v3-default-values-design.md
without environment-specific operational state.
--
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]
