(parquet-java) branch master updated: PARQUET-2139: set metadata offset to 0 since it is not written at all (#1369)

[gangwu]

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

gangwu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/parquet-java.git


The following commit(s) were added to refs/heads/master by this push:
     new b714b79ab PARQUET-2139: set metadata offset to 0 since it is not 
written at all (#1369)
b714b79ab is described below

commit b714b79ab373691296019199e53404b2664f7f19
Author: Ed Seidl <etse...@users.noreply.github.com>
AuthorDate: Sat Jul 20 07:28:10 2024 -0700

    PARQUET-2139: set metadata offset to 0 since it is not written at all 
(#1369)
---
 .../apache/parquet/format/converter/ParquetMetadataConverter.java    | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git 
a/parquet-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
 
b/parquet-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
index 20dbb0119..194670f2d 100644
--- 
a/parquet-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
+++ 
b/parquet-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
@@ -534,8 +534,9 @@ public class ParquetMetadataConverter {
     int columnOrdinal = -1;
     ByteArrayOutputStream tempOutStream = null;
     for (ColumnChunkMetaData columnMetaData : columns) {
-      ColumnChunk columnChunk =
-          new ColumnChunk(columnMetaData.getFirstDataPageOffset()); // verify 
this is the right offset
+      // There is no ColumnMetaData written after the chunk data, so set the 
ColumnChunk
+      // file_offset to 0
+      ColumnChunk columnChunk = new ColumnChunk(0);
       columnChunk.file_path = block.getPath(); // they are in the same file 
for now
       InternalColumnEncryptionSetup columnSetup = null;
       boolean writeCryptoMetadata = false;