From 89737b89003ea38f7eb79b1734a6a32bdc5b062d Mon Sep 17 00:00:00 2001
From: arnavb <arnavb@uber.com>
Date: Sun, 17 Aug 2025 08:46:20 +0000
Subject: [PATCH 1/3] update

---
 .../parquet/hadoop/ParquetFileWriter.java     | 66 +++++++++++++++++--
 1 file changed, 60 insertions(+), 6 deletions(-)

diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
index 4d17a1d6e4..0886fa2f25 100644
--- a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
+++ b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
@@ -1804,14 +1804,27 @@ private static void copy(SeekableInputStream from, PositionOutputStream to, long
    * @throws IOException if there is an error while writing
    */
   public void end(Map<String, String> extraMetaData) throws IOException {
+    final long footerStart = out.getPos();
+
+    // Build the footer metadata) in memory using the helper stream
+    InMemoryPositionOutputStream buffer = new InMemoryPositionOutputStream(footerStart);
+
+    serializeColumnIndexes(columnIndexes, blocks, buffer, fileEncryptor);
+    serializeOffsetIndexes(offsetIndexes, blocks, buffer, fileEncryptor);
+    serializeBloomFilters(bloomFilters, blocks, buffer, fileEncryptor);
+
+    ParquetMetadata localFooter =
+        new ParquetMetadata(new FileMetaData(schema, extraMetaData, Version.FULL_VERSION), blocks);
+    serializeFooter(localFooter, buffer, fileEncryptor, metadataConverter);
+
+    byte[] footerBytes = buffer.toByteArray();
+
     try {
+      out.write(footerBytes);
+      out.flush();
+
       state = state.end();
-      serializeColumnIndexes(columnIndexes, blocks, out, fileEncryptor);
-      serializeOffsetIndexes(offsetIndexes, blocks, out, fileEncryptor);
-      serializeBloomFilters(bloomFilters, blocks, out, fileEncryptor);
-      LOG.debug("{}: end", out.getPos());
-      this.footer = new ParquetMetadata(new FileMetaData(schema, extraMetaData, Version.FULL_VERSION), blocks);
-      serializeFooter(footer, out, fileEncryptor, metadataConverter);
+      this.footer = localFooter;
     } finally {
       close();
     }
@@ -2441,4 +2454,45 @@ protected boolean isPaddingNeeded(long remaining) {
       return (remaining <= maxPaddingSize);
     }
   }
+
+  /**
+   * Lightweight {@link PositionOutputStream} that writes into a byte buffer while
+   * keeping a virtual position that can be initialised to an arbitrary offset.
+   * The position offset lets us build the footer in memory but still record the
+   * *final* absolute offsets that will appear once the buffer is flushed to the
+   * underlying file.
+   */
+  private static final class InMemoryPositionOutputStream extends PositionOutputStream {
+    private final java.io.ByteArrayOutputStream buffer = new java.io.ByteArrayOutputStream();
+    private long pos;
+
+    InMemoryPositionOutputStream(long startPos) {
+      this.pos = startPos;
+    }
+
+    @Override
+    public long getPos() {
+      return pos;
+    }
+
+    @Override
+    public void write(int b) {
+      buffer.write(b);
+      pos++;
+    }
+
+    @Override
+    public void write(byte[] b, int off, int len) {
+      buffer.write(b, off, len);
+      pos += len;
+    }
+
+    @Override
+    public void flush() {
+    }
+
+    byte[] toByteArray() {
+      return buffer.toByteArray();
+    }
+  }
 }

From 0943a33d3765a662275b11d6c66c60302aa32465 Mon Sep 17 00:00:00 2001
From: arnavb <arnavb@uber.com>
Date: Sun, 17 Aug 2025 13:16:12 +0000
Subject: [PATCH 2/3] update

---
 .../main/java/org/apache/parquet/hadoop/ParquetFileWriter.java | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
index 0886fa2f25..26a543777a 100644
--- a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
+++ b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
@@ -2488,8 +2488,7 @@ public void write(byte[] b, int off, int len) {
     }
 
     @Override
-    public void flush() {
-    }
+    public void flush() {}
 
     byte[] toByteArray() {
       return buffer.toByteArray();

From 258ee14f1fa431ebf6df2a5fd696337a5c20e31e Mon Sep 17 00:00:00 2001
From: arnavb <arnavb@uber.com>
Date: Mon, 25 Aug 2025 07:20:02 +0000
Subject: [PATCH 3/3] update

---
 .../java/org/apache/parquet/hadoop/ParquetFileWriter.java     | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
index 26a543777a..c8d8bf7534 100644
--- a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
+++ b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileWriter.java
@@ -1820,10 +1820,10 @@ public void end(Map<String, String> extraMetaData) throws IOException {
     byte[] footerBytes = buffer.toByteArray();
 
     try {
+      state = state.end();
+
       out.write(footerBytes);
       out.flush();
-
-      state = state.end();
       this.footer = localFooter;
     } finally {
       close();