danny0405 commented on code in PR #17562: URL: https://github.com/apache/hudi/pull/17562#discussion_r2625629601
########## hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/source/split/HoodieContinuousSplitBatch.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.hudi.source.split; + +import org.apache.hudi.common.util.ValidationUtils; +import org.apache.hudi.source.IncrementalInputSplits; + +import java.util.Collection; +import java.util.Collections; +import java.util.List; +import java.util.stream.Collectors; + +/** + * Result from continuous enumerator. It has the same semantic to the {@link org.apache.hudi.source.IncrementalInputSplits.Result}. + */ +public class HoodieContinuousSplitBatch { + public static final HoodieContinuousSplitBatch EMPTY = new HoodieContinuousSplitBatch(Collections.emptyList(), "", ""); + private final Collection<HoodieSourceSplit> splits; + private final String endInstant; // end instant to consume to + private final String offset; // monotonic increasing consumption offset + + /** + * @param splits should never be null. But it can be an empty collection + * @param endInstant could be null, end instant to consume to + * @param offset should never be null. monotonic increasing consumption offset + */ + public HoodieContinuousSplitBatch( + Collection<HoodieSourceSplit> splits, + String endInstant, + String offset) { + + ValidationUtils.checkArgument(splits != null, "Invalid to splits collection: null"); + ValidationUtils.checkArgument(offset != null, "Invalid end instant: null"); + this.splits = splits; + this.endInstant = endInstant; + this.offset = offset; + } + + public static HoodieContinuousSplitBatch fromResult(IncrementalInputSplits.Result result) { + List<HoodieSourceSplit> splits = result.getInputSplits().stream().map(split -> + new HoodieSourceSplit( + HoodieSourceSplit.SPLIT_COUNTER.incrementAndGet(), + split.getBasePath().orElse(null), + split.getLogPaths(), split.getTablePath(), + split.getMergeType(), split.getFileId() + ) + ).collect(Collectors.toList()); + + return new HoodieContinuousSplitBatch(splits, result.getEndInstant(), result.getOffset() == null ? result.getEndInstant() : result.getOffset()); Review Comment: should be just `result.getOffset()`? -- 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]
