lidavidm commented on code in PR #38266: URL: https://github.com/apache/arrow/pull/38266#discussion_r1367004599
########## java/memory/memory-core/src/main/java/org/apache/arrow/memory/ReusableBuffer.java: ########## @@ -0,0 +1,47 @@ +/* + * 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.arrow.memory; + +/** + * A lightweight, automatically expanding container for holding byte data. + * @param <T> The type of the underlying buffer. + */ +public interface ReusableBuffer<T> { + /** + * Get the number of valid bytes in the data. + * + * @return the number of valid bytes in the data + */ + int getLength(); Review Comment: Should we use `long` for future compatibility? ########## java/vector/src/main/java/org/apache/arrow/vector/LargeVarBinaryVector.java: ########## @@ -112,6 +113,20 @@ public byte[] get(int index) { return result; } + /** + * Read the value at the given position to the given output buffer. + * The caller is responsible for checking for nullity first. + * + * @param index position of element. + * @param outputBuffer the buffer to write into. + */ + public void readBytes(int index, ReusableBuffer<?> outputBuffer) { + final long startOffset = getStartOffset(index); + final int dataLength = Review Comment: And I think that it's not possible for the current implementation to exceed `int`. However a Java 21+ memory module should actually be able to. @danepitkin we should probably file some follow-up work for after your PR lands to shake out all the problems that are about to crop up. ########## java/memory/memory-core/src/main/java/org/apache/arrow/memory/ReusableBuffer.java: ########## @@ -0,0 +1,47 @@ +/* + * 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.arrow.memory; + +/** + * A lightweight, automatically expanding container for holding byte data. + * @param <T> The type of the underlying buffer. + */ +public interface ReusableBuffer<T> { + /** + * Get the number of valid bytes in the data. + * + * @return the number of valid bytes in the data + */ + int getLength(); + + /** + * Get the buffer backing this ReusableBuffer. + */ + T getBuffer(); + + /** + * Set the buffer to the contents of the given ArrowBuf. + * The internal buffer must resize if it cannot fit the contents + * of the data. + * + * @param srcBytes the data to copy from + * @param start the first position of the new data + * @param len the number of bytes of the new data + */ + void set(ArrowBuf srcBytes, long start, int len); Review Comment: Ditto here (for `len`) ########## java/vector/src/main/java/org/apache/arrow/vector/util/ReusableByteArray.java: ########## @@ -0,0 +1,80 @@ +/* + * 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.arrow.vector.util; + +import java.util.Arrays; + +import org.apache.arrow.memory.ArrowBuf; +import org.apache.arrow.memory.ReusableBuffer; + +/** + * A wrapper around byte arrays for repeated writing. + */ +public class ReusableByteArray implements ReusableBuffer<byte[]> { + + protected static final byte[] EMPTY_BYTES = new byte[0]; + + protected byte[] bytes; + protected int length; + + public ReusableByteArray() { + bytes = EMPTY_BYTES; + } + + /** + * Get the number of bytes in the byte array. + * + * @return the number of bytes in the byte array + */ + @Override + public int getLength() { + return length; + } + + @Override + public byte[] getBuffer() { + return bytes; + } + + @Override + public void set(ArrowBuf srcBytes, long start, int len) { + setCapacity(len, false); + srcBytes.getBytes(start, bytes, 0, len); + length = len; + } + + /** + * Sets the capacity of this object to <em>at least</em> <code>len</code> bytes. If the + * current buffer is longer, then the capacity and existing content of the buffer are unchanged. + * If <code>len</code> is larger than the current capacity, the Text object's capacity is + * increased to match. + * + * @param len the number of bytes we need + * @param keepData should the old data be kept + */ + protected void setCapacity(int len, boolean keepData) { + if (bytes == null || bytes.length < len) { + if (bytes != null && keepData) { + bytes = Arrays.copyOf(bytes, Math.max(len, length << 1)); + } else { + bytes = new byte[len]; + } + } + } + Review Comment: Does it make sense to have equals, toString, hashCode, etc. here? ########## java/vector/src/main/java/org/apache/arrow/vector/LargeVarBinaryVector.java: ########## @@ -112,6 +113,20 @@ public byte[] get(int index) { return result; } + /** + * Read the value at the given position to the given output buffer. + * The caller is responsible for checking for nullity first. + * + * @param index position of element. + * @param outputBuffer the buffer to write into. + */ + public void readBytes(int index, ReusableBuffer<?> outputBuffer) { + final long startOffset = getStartOffset(index); + final int dataLength = Review Comment: I suppose they don't inherit because of the different integer types. The `long` vs `int` problem is baked heavily into the library (and I guess ByteBuffer), so I don't think it's a concern here, but new interfaces should probably use `long` to be forward-looking (e.g., [MemorySegment uses `long` now](https://docs.oracle.com/en/java/javase/21/docs//api/java.base/java/lang/foreign/MemorySegment.html)) -- 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]
