cloud-fan commented on code in PR #57238: URL: https://github.com/apache/spark/pull/57238#discussion_r3580025391
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SupportsArchiveFormat.scala: ########## @@ -0,0 +1,363 @@ +/* + * 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.spark.sql.execution.datasources + +import java.io.{Closeable, File, FileOutputStream, InputStream} +import java.util.Locale +import java.util.regex.Pattern +import java.util.zip.GZIPInputStream + +import scala.util.control.NonFatal + +import org.apache.commons.compress.archivers.{ArchiveEntry, ArchiveInputStream} +import org.apache.commons.compress.archivers.tar.TarArchiveInputStream +import org.apache.commons.compress.archivers.zip.ZipArchiveInputStream +import org.apache.commons.io.ByteOrderMark +import org.apache.commons.io.input.{BOMInputStream, CloseShieldInputStream} +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.Path +import org.apache.hadoop.io.Text +import org.apache.hadoop.util.LineReader + +import org.apache.spark.{SparkEnv, TaskContext} +import org.apache.spark.internal.Logging +import org.apache.spark.paths.SparkPath +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.util.{HadoopFSUtils, Utils} + +/** + * Mixed into a file-based data source to let it read tar/zip archives of its files, treating an + * archive like a directory of the entries it contains. Schema inference is left to each format. + */ +trait SupportsArchiveFormat extends Logging { + + /** + * Splits one already-decompressed archive entry's bytes into lines (`None` separator = detect + * line breaks), yielding each line as [[Text]] without the trailing separator. Does not close the + * entry stream (the reader owns it). + */ + protected def lineIterator( + in: InputStream, + lineSeparatorInRead: Option[Array[Byte]]): Iterator[Text] = { + // Strip a leading BOM (LineReader does not) so lines match the non-archive read path. + val bomInputStream = BOMInputStream.builder() + .setInputStream(in) + .setByteOrderMarks( + ByteOrderMark.UTF_8, + ByteOrderMark.UTF_16LE, + ByteOrderMark.UTF_16BE, + ByteOrderMark.UTF_32LE, + ByteOrderMark.UTF_32BE) + .setInclude(false) + .get() + val reader = lineSeparatorInRead match { + case Some(sep) => new LineReader(bomInputStream, sep) + case _ => new LineReader(bomInputStream) + } + new Iterator[Text] { + private val text = new Text() + private var finished = false + private var hasValue = false + + override def hasNext: Boolean = { + if (!finished && !hasValue) { + finished = reader.readLine(text) == 0 + hasValue = !finished + } + !finished + } + + override def next(): Text = { + if (!hasNext) throw new NoSuchElementException + hasValue = false + text + } + } + } + + /** Which archive entries are data files of this format; others are skipped. */ + protected def archiveEntryFilter(name: String): Boolean = + throw new UnsupportedOperationException( + s"${getClass.getName} does not support random-access archive reads") + + /** + * Materializes each kept entry (those passing [[archiveEntryFilter]]) to a temp file under + * `localDir`, lazily one at a time, so only one entry occupies disk at once. + * + * @param path the archive path + * @param conf Hadoop configuration used to open the archive + * @param localDir directory the per-entry temp files are created under + * @return an iterator of `(entryName, localFile)` for the kept entries, in archive order + */ + private def localizeEntries( + path: Path, + conf: Configuration, + localDir: File): Iterator[(String, File)] = + SupportsArchiveFormat.readArchiveEntries(path, conf) { (name, in) => + if (archiveEntryFilter(name)) { + Iterator.single((name, SupportsArchiveFormat.copyEntryToLocalFile(in, localDir, name))) + } else { + Iterator.empty + } + } + + /** + * Reads an archive by unpacking each entry to a temp file and applying `readEntry`, for a + * format that needs a complete file on disk (random access). + * + * @param file the archive as a [[PartitionedFile]] + * @param conf Hadoop configuration used to open the archive + * @param tempPrefix prefix for the per-task temp dir the entries are unpacked into + * @param readEntry reads one unpacked entry file into rows + * @return iterator of rows across all entries + */ + protected def readLocalizedEntries( Review Comment: This random-access localization surface — `readLocalizedEntries` here plus `localizeEntries`, `copyEntryToLocalFile`, and the `archiveEntryFilter` hook (which defaults to throwing `UnsupportedOperationException`) — has no counterpart in the removed `ArchiveReader` (which was purely streaming) and no caller anywhere in the tree (grep across `sql/`, including tests, finds only the definitions). The PR description motivates it as "for random-access formats that need a complete file on disk (Parquet/ORC footers)", but neither Parquet nor ORC mixes in this trait, so nothing exercises this path. Since this PR is framed as a behavior-preserving refactor, consider dropping this surface and landing it with the PR that adds the first random-access archive consumer — there it can be exercised and tested, rather than sitting as ~95 lines of untested, uncalled API that has to be maintained (and can rot) before its first use. -- 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]
