rdblue commented on code in PR #9695:
URL: https://github.com/apache/iceberg/pull/9695#discussion_r1690623146
##########
open-api/rest-catalog-open-api.yaml:
##########
@@ -3647,6 +3818,176 @@ components:
type: integer
description: "List of equality field IDs"
+ PreplanTableRequest:
+ type: object
+ required:
+ - table-scan-context
+ properties:
+ table-scan-context:
+ $ref: '#/components/schemas/TableScanContext'
+
+ PlanTableRequest:
+ type: object
+ required:
+ - table-scan-context
+ properties:
+ table-scan-context:
+ $ref: '#/components/schemas/TableScanContext'
+ plan-task:
+ $ref: '#/components/schemas/PlanTask'
+ stats-fields:
+ description:
+ A list of fields that the client requests the server to send
statistics
+ in each `FileScanTask` returned in the response
+ type: array
+ items:
+ $ref: '#/components/schemas/FieldName'
+
+ TableScanContext:
+ anyOf:
+ - $ref: '#/components/schemas/SnapshotScanContext'
+ - $ref: '#/components/schemas/IncrementalSnapshotScanContext'
+
+ BaseTableScanContext:
+ discriminator:
+ propertyName: type
+ mapping:
+ snapshot-scan: '#/components/schemas/SnapshotScanContext'
+ incremental-snapshot-scan:
'#/components/schemas/IncrementalSnapshotScanContext'
+ type: object
+ required:
+ - type
+ properties:
+ type:
+ type: string
+
+ SnapshotScanContext:
+ description: context for scanning data in a specific snapshot
+ type: object
+ allOf:
+ - $ref: '#/components/schemas/BaseTableScanContext'
+ required:
+ - type
+ properties:
+ type:
+ type: string
+ enum: ["snapshot-scan"]
+ select:
+ $ref: '#/components/schemas/SelectedFieldNames'
+ filter:
+ $ref: '#/components/schemas/Filter'
+ case-sensitive:
+ description: If field selection and filtering should be case
sensitive
+ type: boolean
+ default: true
+ snapshot-id:
+ description:
+ The ID of the snapshot to use for the table scan.
+ If not specified, the snapshot at the main branch head will be
used.
+ type: integer
+ format: int64
+ use-snapshot-schema:
+ description:
+ If the schema of the specific snapshot should be used instead of
the table schema.
+ type: boolean
+ default: false
+
+ IncrementalSnapshotScanContext:
+ description:
+ Context for scanning data appended in a range of snapshots.
+ The scan always follows the schema of the snapshot at the main branch
head.
+ type: object
+ allOf:
+ - $ref: '#/components/schemas/BaseTableScanContext'
+ required:
+ - type
+ - start-snapshot-id
+ properties:
+ type:
+ type: string
+ enum: ["incremental-snapshot-scan"]
+ select:
+ $ref: '#/components/schemas/SelectedFieldNames'
+ filter:
+ $ref: '#/components/schemas/Filter'
+ case-sensitive:
+ description: If field selection and filtering should be case
sensitive
+ type: boolean
+ default: true
+ start-snapshot-id:
+ description: The ID of the starting snapshot of the incremental scan
+ type: integer
+ format: int64
+ inclusive-start:
+ description: If the data appended in the start snapshot should be
included in the scan
+ type: boolean
+ default: false
+ end-snapshot-id:
+ description:
+ The ID of the inclusive ending snapshot of the incremental scan.
+ If not specified, the snapshot at the main branch head will be
used as the end snapshot.
+ type: integer
+ format: int64
+
+ FieldName:
+ description:
+ A field name that follows the Iceberg naming standard, and can be used
in APIs like
+ Java `Schema#findField(String name)`.
+
+ The nested field name follows these rules
+ - nested struct fields are named by concatenating field names at each
struct level using dot (`.`) delimiter,
+ e.g. employer.contact_info.address.zip_code
+ - nested fields in a map key are named using the keyword `key`, e.g.
employee_address_map.key.first_name
+ - nested fields in a map value are named using the keyword `value`,
e.g. employee_address_map.value.zip_code
+ - nested fields in a list are named using the keyword `element`, e.g.
employees.element.first_name
+ type: string
+
+ SelectedFieldNames:
+ description:
+ A list of fields in schema that are selected in a table scan.
+ When not specified, all columns in the requested schema should be
selected.
+ type: array
+ items:
+ $ref: '#/components/schemas/FieldName'
+
+ Filter:
+ description:
+ an unbounded expression to describe the filters to apply to a table
scan,
+ default to `TrueExpression` meaning that nothing is filtered.
+ allOf:
+ - $ref: '#/components/schemas/Expression'
+ default: { "type": "true" }
+
+ PlanTask:
+ description:
+ An opaque JSON object that contains information provided by the REST
server
+ to be utilized by clients for distributed table scan planning; should
be supplied
+ as input in `PlanTable` operation.
+ type: object
+
+ FileScanTask:
+ type: object
+ required:
+ - data-file
+ - residual-filter
+ properties:
+ data-file:
+ $ref: '#/components/schemas/DataFile'
+ position-delete-files:
Review Comment:
> a client can choose whether or not it can handle that new delete file type.
One small callout: we should make sure that the client is *required* to fail
if it does not support or recognize a delete file type and that delete file is
used by a FileScanTask.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
