From 3e2dfc4f0db99ba107683577968b60844909c458 Mon Sep 17 00:00:00 2001
From: Fokko Driesprong <fokko@apache.org>
Date: Sun, 26 Jul 2026 21:31:35 +0200
Subject: [PATCH] Revert "GH-3574: Statistics.toParquetStatistics always set
 null_count(#3575)"

This reverts commit 63aebcc0cf3684ba6c9dc2b7243c6007d3a1269f.
---
 .../format/converter/ParquetMetadataConverter.java    | 10 ++++------
 .../converter/TestParquetMetadataConverter.java       | 11 +++++------
 2 files changed, 9 insertions(+), 12 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 8600b2ced4..465516e48f 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
@@ -815,17 +815,15 @@ public static Statistics toParquetStatistics(org.apache.parquet.column.statistic
   public static Statistics toParquetStatistics(
       org.apache.parquet.column.statistics.Statistics stats, int truncateLength) {
     Statistics formatStats = new Statistics();
-    if (!stats.isEmpty()) {
-      formatStats.setNull_count(stats.getNumNulls());
-      if (stats.isNanCountSet()) {
-        formatStats.setNan_count(stats.getNanCount());
-      }
-    }
     // Don't write stats larger than the max size rather than truncating. The
     // rationale is that some engines may use the minimum value in the page as
     // the true minimum for aggregations and there is no way to mark that a
     // value has been truncated and is a lower bound and not in the page.
     if (!stats.isEmpty() && withinLimit(stats, truncateLength)) {
+      formatStats.setNull_count(stats.getNumNulls());
+      if (stats.isNanCountSet()) {
+        formatStats.setNan_count(stats.getNanCount());
+      }
       if (stats.hasNonNullValue()) {
         byte[] min;
         byte[] max;
diff --git a/parquet-hadoop/src/test/java/org/apache/parquet/format/converter/TestParquetMetadataConverter.java b/parquet-hadoop/src/test/java/org/apache/parquet/format/converter/TestParquetMetadataConverter.java
index c6deee2855..4d361d6aa0 100644
--- a/parquet-hadoop/src/test/java/org/apache/parquet/format/converter/TestParquetMetadataConverter.java
+++ b/parquet-hadoop/src/test/java/org/apache/parquet/format/converter/TestParquetMetadataConverter.java
@@ -878,7 +878,7 @@ private void testBinaryStats(StatsHelper helper) {
     }
     assertThat(formatStats.getNull_count()).as("Num nulls should match").isEqualTo(3004);
 
-    // min/max are not written because the values are too large, but null count is always written
+    // convert to empty stats because the values are too large
     stats.setMinMaxFromBytes(max, max);
 
     formatStats = helper.toParquetStatistics(stats);
@@ -891,7 +891,9 @@ private void testBinaryStats(StatsHelper helper) {
     assertThat(formatStats.isSetMax_value())
         .as("Max_value should not be set")
         .isFalse();
-    assertThat(formatStats.getNull_count()).as("Num nulls should match").isEqualTo(3004);
+    assertThat(formatStats.isSetNull_count())
+        .as("Num nulls should not be set")
+        .isFalse();
 
     Statistics roundTripStats = ParquetMetadataConverter.fromParquetStatisticsInternal(
         Version.FULL_VERSION,
@@ -901,10 +903,7 @@ private void testBinaryStats(StatsHelper helper) {
 
     assertThat(roundTripStats.isEmpty())
         .as("Round-trip stats should not be empty (null count is set)")
-        .isFalse();
-    assertThat(roundTripStats.getNumNulls())
-        .as("Round-trip null count should match")
-        .isEqualTo(3004);
+        .isTrue();
   }
 
   @Test