hudi-agent commented on code in PR #19083: URL: https://github.com/apache/hudi/pull/19083#discussion_r3731051552
########## hudi-io/src/test/java/org/apache/hudi/io/hfile/TestHFileDataBlock.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.io.hfile; + +import org.junit.jupiter.api.Test; + +import java.io.IOException; +import java.nio.ByteBuffer; +import java.nio.charset.StandardCharsets; + +import static org.junit.jupiter.api.Assertions.assertEquals; + +/** + * Validates the exact on-disk bytes the data block writer emits for each record. A data entry is a + * full HBase KeyValue: {@code [4-byte keyLen][4-byte valueLen][2-byte rowLen][row][1-byte cfLen=0] + * [8-byte ts=LATEST][1-byte type=Put][value][1-byte MVCC=0]}. An HBase reader relies on this exact + * framing, so the test asserts every field rather than a single opaque blob. + */ +class TestHFileDataBlock { + private static final long LATEST_TIMESTAMP = Long.MAX_VALUE; + private static final byte KEY_TYPE_PUT = (byte) 4; Review Comment: 🤖 nit: `KEY_SUFFIX_AND_PREFIX_LENGTH = 12` duplicates the layout knowledge already encoded in `HFileBlock.keyValueKeyLength`. Since both test classes are in the same package, could you use `HFileBlock.keyValueKeyLength(0)` directly instead of the magic constant? That way a layout change in one place stays in sync automatically. <sub><i>⚠️ AI-generated; verify before applying. React 👍/👎 to flag quality.</i></sub> ########## hudi-io/src/test/java/org/apache/hudi/io/hfile/TestHFileWriter.java: ########## @@ -339,6 +751,32 @@ private static void assertArrayEquals(byte[] expected, byte[] actual) { } } + private static int indexOf(byte[] haystack, byte[] needle) { + outer: + for (int i = 0; i + needle.length <= haystack.length; i++) { + for (int j = 0; j < needle.length; j++) { + if (haystack[i + j] != needle[j]) { + continue outer; + } + } + return i; + } + return -1; Review Comment: 🤖 nit: `readIntBE` looks like a hand-rolled reimplementation of `IOUtils.readInt(byte[], int)`, which is already available and imported elsewhere in the test suite — could you swap it out? <sub><i>⚠️ AI-generated; verify before applying. React 👍/👎 to flag quality.</i></sub> -- 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]
