rdblue commented on a change in pull request #2092: URL: https://github.com/apache/iceberg/pull/2092#discussion_r559784905
########## File path: spark/src/main/java/org/apache/iceberg/spark/source/StreamingOffset.java ########## @@ -0,0 +1,149 @@ +/* + * 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.spark.source; + +import com.fasterxml.jackson.core.JsonGenerator; +import com.fasterxml.jackson.databind.JsonNode; +import java.io.IOException; +import java.io.StringWriter; +import java.io.UncheckedIOException; +import org.apache.iceberg.relocated.com.google.common.base.Objects; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.util.JsonUtil; +import org.apache.spark.sql.sources.v2.reader.streaming.Offset; + +class StreamingOffset extends Offset { + static final StreamingOffset START_OFFSET = new StreamingOffset(-1L, -1, false, true); + + private static final int CURR_VERSION = 1; + private static final String VERSION = "version"; + private static final String SNAPSHOT_ID = "snapshot_id"; + private static final String INDEX = "index"; + private static final String SCAN_ALL_FILES = "scan_all_files"; + private static final String SNAPSHOT_FULLY_PROCESSED = "snapshot_fully_processed"; + + private final long snapshotId; + private final int index; + private final boolean scanAllFiles; + private final boolean snapshotFullyProcessed; + + /** + * An implementation of Spark Structured Streaming Offset, to track the current processed files of + * Iceberg table. + * + * @param snapshotId The current processed snapshot id. + * @param index The index of last scanned file in snapshot. + * @param scanAllFiles Denote whether to scan all files in a snapshot, currently we only + * scan all files in the starting snapshot. + * @param snapshotFullyProcessed Denote whether the current snapshot is fully processed, to avoid + * revisiting the processed snapshot. + */ + StreamingOffset(long snapshotId, int index, boolean scanAllFiles, + boolean snapshotFullyProcessed) { + this.snapshotId = snapshotId; + this.index = index; + this.scanAllFiles = scanAllFiles; + this.snapshotFullyProcessed = snapshotFullyProcessed; + } + + static StreamingOffset fromJson(String json) { + Preconditions.checkNotNull(json, "The input JSON string representation of a StreamingOffset cannot be null"); Review comment: Error messages typically follow the pattern "Invalid ..." or "Cannot (action): (reason) [suggestion]". Here, there is no suggestion for fixing it, so it would be something like "Cannot parse offset JSON: null". ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
