[orc] branch branch-1.7 updated: ORC-1095: Deprecate `UnknownFormatException` (#1016)

[do...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

dongjoon pushed a commit to branch branch-1.7
in repository https://gitbox.apache.org/repos/asf/orc.git


The following commit(s) were added to refs/heads/branch-1.7 by this push:
     new 5a07dfa  ORC-1095: Deprecate `UnknownFormatException` (#1016)
5a07dfa is described below

commit 5a07dfaf90ca2682f5f6fd295937edc29140da63
Author: Dongjoon Hyun <do...@apache.org>
AuthorDate: Sun Jan 16 13:55:33 2022 -0800

    ORC-1095: Deprecate `UnknownFormatException` (#1016)
    
    ### What changes were proposed in this pull request?
    
    This PR aims to deprecate `UnknownFormatException` at Apache ORC 1.7.3.
    
    ### Why are the changes needed?
    
    This extends `IOException` to expose more data and used once here. However, the downstream projects are not using this information because `checkOrcVersion` returns `IOException`.  The error message is enough.
    
    https://github.com/apache/orc/blob/80b98126cf8a15d9d44c67a9aabfabfdcc7f913e/java/core/src/java/org/apache/orc/impl/ReaderImpl.java#L517-L525
    
    This PR replaces it with `IOException` with the same message generated by `UnknownFormatException` previously.
    
    https://github.com/apache/orc/blob/80b98126cf8a15d9d44c67a9aabfabfdcc7f913e/java/core/src/java/org/apache/orc/UnknownFormatException.java#L33-L35
    
    ### How was this patch tested?
    
    Pass the CIs.
    
    (cherry picked from commit 9a3be32a21aca05ee8ef0d28d74da58f1b23233b)
    Signed-off-by: Dongjoon Hyun <do...@apache.org>
---
 .../src/java/org/apache/orc/UnknownFormatException.java     |  4 ++++
 java/core/src/java/org/apache/orc/impl/ReaderImpl.java      |  7 ++++---
 java/core/src/test/org/apache/orc/TestVectorOrcFile.java    | 13 +++++++------
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/java/core/src/java/org/apache/orc/UnknownFormatException.java b/java/core/src/java/org/apache/orc/UnknownFormatException.java
index 9ebdae7..eb21fe3 100644
--- a/java/core/src/java/org/apache/orc/UnknownFormatException.java
+++ b/java/core/src/java/org/apache/orc/UnknownFormatException.java
@@ -23,6 +23,10 @@ import org.apache.hadoop.fs.Path;
 
 import java.io.IOException;
 
+/**
+ * @deprecated This will be removed in the future releases.
+ */
+@Deprecated
 public class UnknownFormatException extends IOException {
   private final Path path;
   private final String versionString;
diff --git a/java/core/src/java/org/apache/orc/impl/ReaderImpl.java b/java/core/src/java/org/apache/orc/impl/ReaderImpl.java
index 2ddd1ae..73b7927 100644
--- a/java/core/src/java/org/apache/orc/impl/ReaderImpl.java
+++ b/java/core/src/java/org/apache/orc/impl/ReaderImpl.java
@@ -19,6 +19,7 @@
 package org.apache.orc.impl;
 
 import com.google.protobuf.CodedInputStream;
+import com.google.protobuf.TextFormat;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.fs.FileStatus;
@@ -44,7 +45,6 @@ import org.apache.orc.RecordReader;
 import org.apache.orc.StripeInformation;
 import org.apache.orc.StripeStatistics;
 import org.apache.orc.TypeDescription;
-import org.apache.orc.UnknownFormatException;
 import org.apache.orc.impl.reader.ReaderEncryption;
 import org.apache.orc.impl.reader.ReaderEncryptionVariant;
 import org.slf4j.Logger;
@@ -519,8 +519,9 @@ public class ReaderImpl implements Reader {
                                         ) throws IOException {
     List<Integer> version = postscript.getVersionList();
     if (getFileVersion(version) == OrcFile.Version.FUTURE) {
-      throw new UnknownFormatException(path, versionString(version),
-          postscript);
+      throw new IOException(path + " was written by a future ORC version " +
+          versionString(version) + ". This file is not readable by this version of ORC.\n"+
+          "Postscript: " + TextFormat.shortDebugString(postscript));
     }
   }
 
diff --git a/java/core/src/test/org/apache/orc/TestVectorOrcFile.java b/java/core/src/test/org/apache/orc/TestVectorOrcFile.java
index 769d1d2..13fa6b8 100644
--- a/java/core/src/test/org/apache/orc/TestVectorOrcFile.java
+++ b/java/core/src/test/org/apache/orc/TestVectorOrcFile.java
@@ -4145,12 +4145,13 @@ public class TestVectorOrcFile {
     try {
       OrcFile.createReader(zeroFile, OrcFile.readerOptions(conf));
       fail("no exception for bad version");
-    } catch (UnknownFormatException uf) {
-      assertEquals("version1999.orc", uf.getPath().getName(), "path is correct");
-      assertEquals("19.99", uf.getVersionString());
-      OrcProto.PostScript ps = uf.getPostscript();
-      assertEquals("ORC", ps.getMagic());
-      assertEquals(OrcProto.CompressionKind.NONE, ps.getCompression());
+    } catch (IOException e) {
+      String m = e.getMessage();
+      assertTrue(m.contains("version1999.orc was written by a future ORC version 19.99."));
+      assertTrue(m.contains("This file is not readable by this version of ORC."));
+      assertTrue(m.contains("Postscript: footerLength: 19 compression: NONE " +
+          "compressionBlockSize: 65536 version: 19 version: 99 metadataLength: 0 " +
+          "writerVersion: 1"));
     }
   }