nastra commented on code in PR #13400: URL: https://github.com/apache/iceberg/pull/13400#discussion_r2559818171
########## core/src/main/java/org/apache/iceberg/RESTTableScan.java: ########## @@ -0,0 +1,285 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ +package org.apache.iceberg; + +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.Set; +import java.util.function.Supplier; +import java.util.stream.Collectors; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.rest.Endpoint; +import org.apache.iceberg.rest.ErrorHandlers; +import org.apache.iceberg.rest.ParserContext; +import org.apache.iceberg.rest.PlanStatus; +import org.apache.iceberg.rest.RESTClient; +import org.apache.iceberg.rest.ResourcePaths; +import org.apache.iceberg.rest.requests.PlanTableScanRequest; +import org.apache.iceberg.rest.responses.FetchPlanningResultResponse; +import org.apache.iceberg.rest.responses.PlanTableScanResponse; +import org.apache.iceberg.types.Types; + +public class RESTTableScan extends DataTableScan { + private final RESTClient client; + private final String path; + private final Supplier<Map<String, String>> headers; + private final TableOperations operations; + private final Table table; + private final ResourcePaths resourcePaths; + private final TableIdentifier tableIdentifier; + private final Set<Endpoint> supportedEndpoints; + private final ParserContext parserContext; + + // Track the current plan ID for cancellation + private volatile String currentPlanId = null; + + // TODO revisit if this property should be configurable + // Sleep duration between polling attempts for plan completion + private static final int FETCH_PLANNING_SLEEP_DURATION_MS = 1000; + // Maximum time to wait for scan planning to complete (5 minutes) + // This prevents indefinite blocking on server-side planning issues + private static final long MAX_WAIT_TIME_MS = 5 * 60 * 1000L; + + RESTTableScan( + Table table, + Schema schema, + TableScanContext context, + RESTClient client, + String path, + Supplier<Map<String, String>> headers, + TableOperations operations, + TableIdentifier tableIdentifier, + ResourcePaths resourcePaths, + Set<Endpoint> supportedEndpoints) { + super(table, schema, context); + this.table = table; + this.client = client; + this.headers = headers; + this.path = path; + this.operations = operations; + this.tableIdentifier = tableIdentifier; + this.resourcePaths = resourcePaths; + this.supportedEndpoints = supportedEndpoints; + this.parserContext = + ParserContext.builder() + .add("specsById", table.specs()) + .add("caseSensitive", context().caseSensitive()) + .build(); + } + + @Override + protected TableScan newRefinedScan( + Table refinedTable, Schema refinedSchema, TableScanContext refinedContext) { + return new RESTTableScan( + refinedTable, + refinedSchema, + refinedContext, + client, + path, + headers, + operations, + tableIdentifier, + resourcePaths, + supportedEndpoints); + } + + @Override + public CloseableIterable<FileScanTask> planFiles() { + Long startSnapshotId = context().fromSnapshotId(); + Long endSnapshotId = context().toSnapshotId(); + Long snapshotId = snapshotId(); + List<String> selectedColumns = + schema().columns().stream().map(Types.NestedField::name).collect(Collectors.toList()); + + List<String> statsFields = null; + if (columnsToKeepStats() != null) { + statsFields = + columnsToKeepStats().stream() + .map(columnId -> schema().findColumnName(columnId)) + .collect(Collectors.toList()); + } + + PlanTableScanRequest.Builder planTableScanRequestBuilder = + PlanTableScanRequest.builder() + .withSelect(selectedColumns) + .withFilter(filter()) + .withCaseSensitive(isCaseSensitive()) + .withStatsFields(statsFields); + + if (startSnapshotId != null && endSnapshotId != null) { + planTableScanRequestBuilder + .withStartSnapshotId(startSnapshotId) + .withEndSnapshotId(endSnapshotId) + .withUseSnapshotSchema(true); + + } else if (snapshotId != null) { + boolean useSnapShotSchema = snapshotId != table.currentSnapshot().snapshotId(); + planTableScanRequestBuilder + .withSnapshotId(snapshotId) + .withUseSnapshotSchema(useSnapShotSchema); + } + + return planTableScan(planTableScanRequestBuilder.build()); + } + + private CloseableIterable<FileScanTask> planTableScan(PlanTableScanRequest planTableScanRequest) { + + PlanTableScanResponse response = + client.post( + resourcePaths.planTableScan(tableIdentifier), + planTableScanRequest, + PlanTableScanResponse.class, + headers.get(), + ErrorHandlers.defaultErrorHandler(), + stringStringMap -> {}, + parserContext); + + PlanStatus planStatus = response.planStatus(); + switch (planStatus) { + case COMPLETED: + currentPlanId = response.planId(); + return getScanTasksIterable(response.planTasks(), response.fileScanTasks()); + case SUBMITTED: + Preconditions.checkState( Review Comment: I believe this should use `Endpoint.check()` to be consistent with other error messaging around unsupported endpoints. Also can we add a test that verifies the error messages on the 3 endpoints when we run with a server that doesn't support them? -- 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]
