[apacheGH-3035][ParquetRewriter] removed ColumnChunkMetaData.get(path…

…, type)
MaxNevermind · Nov 11, 2024 · a5b48e2 · a5b48e2
1 parent 1565d73
commit a5b48e2
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 27 deletions.
diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/metadata/ColumnChunkMetaData.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/metadata/ColumnChunkMetaData.java
@@ -504,29 +504,6 @@ public boolean hasDictionaryPage() {
   public boolean isEncrypted() {
     return false;
   }
-
-  /**
-   * Copies this ColumnChunkMetaData with path and type changed to provided ones.
-   *
-   * @param path a new ColumnPath of a chunk
-   * @param type a new PrimitiveType of a chunk
-   * @return resulting chunk
-   */
-  public ColumnChunkMetaData copy(ColumnPath path, PrimitiveType type) {
-    return ColumnChunkMetaData.get(
-        path,
-        type,
-        this.getCodec(),
-        this.getEncodingStats(),
-        this.getEncodings(),
-        this.getStatistics(),
-        this.getFirstDataPageOffset(),
-        this.getDictionaryPageOffset(),
-        this.getValueCount(),
-        this.getTotalSize(),
-        this.getTotalUncompressedSize(),
-        this.getSizeStatistics());
-  }
 }
 
 class IntColumnChunkMetaData extends ColumnChunkMetaData {

diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/ParquetRewriter.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/ParquetRewriter.java
@@ -155,7 +155,7 @@ public ParquetRewriter(RewriteOptions options) throws IOException {
     this.newCodecName = options.getNewCodecName();
     this.indexCacheStrategy = options.getIndexCacheStrategy();
     this.overwriteInputWithJoinColumns = options.getOverwriteInputWithJoinColumns();
-    this.renamedColumns = options.gerRenameColumns();
+    this.renamedColumns = options.getRenameColumns();
     ParquetConfiguration conf = options.getParquetConfiguration();
     this.inputFiles.addAll(getFileReaders(options.getParquetInputFiles(), conf));
     this.inputFilesToJoin.addAll(getFileReaders(options.getParquetInputFilesToJoin(), conf));
@@ -495,8 +495,19 @@ private void processBlock(
 
     ColumnChunkMetaData chunkNormalized = chunk;
     if (!renamedColumns.isEmpty()) {
-      chunkNormalized =
-          chunk.copy(normalizeFieldsInPath(chunk.getPath()), normalizeNameInType(chunk.getPrimitiveType()));
+      chunkNormalized = ColumnChunkMetaData.get(
+          normalizeFieldsInPath(chunk.getPath()),
+          normalizeNameInType(chunk.getPrimitiveType()),
+          chunk.getCodec(),
+          chunk.getEncodingStats(),
+          chunk.getEncodings(),
+          chunk.getStatistics(),
+          chunk.getFirstDataPageOffset(),
+          chunk.getDictionaryPageOffset(),
+          chunk.getValueCount(),
+          chunk.getTotalSize(),
+          chunk.getTotalUncompressedSize(),
+          chunk.getSizeStatistics());
     }
 
     ColumnDescriptor descriptorOriginal = outSchema.getColumns().get(outColumnIdx);

diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/RewriteOptions.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/RewriteOptions.java
@@ -198,7 +198,7 @@ public Map<String, MaskMode> getMaskColumns() {
     return maskColumns;
   }
 
-  public Map<String, String> gerRenameColumns() {
+  public Map<String, String> getRenameColumns() {
     return renameColumns;
   }