chore: Deprecate H1SeekableInputStream

parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/HadoopStreams.java

@@ -19,24 +19,16 @@
 
 package org.apache.parquet.hadoop.util;
 
-import java.io.InputStream;
 import java.util.Objects;
-import java.util.function.Function;
-import org.apache.hadoop.fs.ByteBufferReadable;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.fs.FSDataOutputStream;
 import org.apache.parquet.io.PositionOutputStream;
 import org.apache.parquet.io.SeekableInputStream;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
 
 /**
  * Convenience methods to get Parquet abstractions for Hadoop data streams.
  */
 public class HadoopStreams {
-
-  private static final Logger LOG = LoggerFactory.getLogger(HadoopStreams.class);
-
   /**
    * Wraps a {@link FSDataInputStream} in a {@link SeekableInputStream}
    * implementation for Parquet readers.
@@ -46,79 +38,7 @@ public class HadoopStreams {
    */
   public static SeekableInputStream wrap(FSDataInputStream stream) {
     Objects.requireNonNull(stream, "Cannot wrap a null input stream");
-
-    // Try to check using hasCapabilities(str)
-    Boolean hasCapabilitiesResult = isWrappedStreamByteBufferReadable(stream);
-
-    // If it is null, then fall back to the old method
-    if (hasCapabilitiesResult != null) {
-      if (hasCapabilitiesResult) {
-        return new H2SeekableInputStream(stream);
-      } else {
-        return new H1SeekableInputStream(stream);
-      }
-    }
-
-    return unwrapByteBufferReadableLegacy(stream).apply(stream);
-  }
-
-  /**
-   * Is the inner stream byte buffer readable?
-   * The test is 'the stream is not FSDataInputStream
-   * and implements ByteBufferReadable'
-   * <p>
-   * This logic is only used for Hadoop <2.9.x, and <3.x.x
-   *
-   * @param stream stream to probe
-   * @return A H2SeekableInputStream to access, or H1SeekableInputStream if the stream is not seekable
-   */
-  private static Function<FSDataInputStream, SeekableInputStream> unwrapByteBufferReadableLegacy(
-      FSDataInputStream stream) {
-    InputStream wrapped = stream.getWrappedStream();
-    if (wrapped instanceof FSDataInputStream) {
-      LOG.debug("Checking on wrapped stream {} of {} whether is ByteBufferReadable", wrapped, stream);
-      return unwrapByteBufferReadableLegacy(((FSDataInputStream) wrapped));
-    }
-    if (stream.getWrappedStream() instanceof ByteBufferReadable) {
-      return H2SeekableInputStream::new;
-    } else {
-      return H1SeekableInputStream::new;
-    }
-  }
-
-  /**
-   * Is the inner stream byte buffer readable?
-   * The test is 'the stream is not FSDataInputStream
-   * and implements ByteBufferReadable'
-   * <p>
-   * That is: all streams which implement ByteBufferReadable
-   * other than FSDataInputStream successfully support read(ByteBuffer).
-   * This is true for all filesystem clients the hadoop codebase.
-   * <p>
-   * In hadoop 3.3.0+, the StreamCapabilities probe can be used to
-   * check this: only those streams which provide the read(ByteBuffer)
-   * semantics MAY return true for the probe "in:readbytebuffer";
-   * FSDataInputStream will pass the probe down to the underlying stream.
-   *
-   * @param stream stream to probe
-   * @return true if it is safe to a H2SeekableInputStream to access
-   * the data, null when it cannot be determined because of missing hasCapabilities
-   */
-  private static Boolean isWrappedStreamByteBufferReadable(FSDataInputStream stream) {
-    boolean isByteBufferReadable = stream.hasCapability("in:readbytebuffer");
-
-    if (isByteBufferReadable) {
-      // stream is issuing the guarantee that it implements the
-      // API. Holds for all implementations in hadoop-*
-      // since Hadoop 3.3.0 (HDFS-14111).
-      return true;
-    }
-    InputStream wrapped = stream.getWrappedStream();
-    if (wrapped instanceof FSDataInputStream) {
-      LOG.debug("Checking on wrapped stream {} of {} whether is ByteBufferReadable", wrapped, stream);
-      return isWrappedStreamByteBufferReadable(((FSDataInputStream) wrapped));
-    }
-    return wrapped instanceof ByteBufferReadable;
+    return new H2SeekableInputStream(stream);
   }
 
   /**

parquet-hadoop/src/test/java/org/apache/parquet/hadoop/util/TestHadoop2ByteBufferReads.java

@@ -381,18 +381,6 @@ public void testDirectReadFullyPositionAndLimit() throws Exception {
     Assert.assertEquals("Buffer contents should match", ByteBuffer.wrap(TEST_ARRAY, 0, 7), readBuffer);
   }
 
-  @Test
-  public void testCreateStreamNoByteBufferReadable() {
-    final SeekableInputStream s = wrap(new FSDataInputStream(new MockHadoopInputStream()));
-    Assert.assertTrue("Wrong wrapper: " + s, s instanceof H1SeekableInputStream);
-  }
-
-  @Test
-  public void testDoubleWrapNoByteBufferReadable() {
-    final SeekableInputStream s = wrap(new FSDataInputStream(new FSDataInputStream(new MockHadoopInputStream())));
-    Assert.assertTrue("Wrong wrapper: " + s, s instanceof H1SeekableInputStream);
-  }
-
   @Test
   public void testCreateStreamWithByteBufferReadable() {
     final SeekableInputStream s = wrap(new FSDataInputStream(new MockByteBufferInputStream()));