(parquet-java) branch master updated: GH-3449: Fix BinaryStats int overflow (#3448)

[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 689547cc9 GH-3449: Fix BinaryStats int overflow (#3448)
689547cc9 is described below

commit 689547cc9f5575b565b60f0b4ba523528d0e4b42
Author: Jiayi-Wang-db <wjyi2...@gmail.com>
AuthorDate: Wed Mar 18 02:56:09 2026 +0100

    GH-3449: Fix BinaryStats int overflow (#3448)
---
 .../apache/parquet/column/statistics/BinaryStatistics.java    |  6 +++---
 .../org/apache/parquet/column/statistics/TestStatistics.java  | 11 +++++++++++
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git 
a/parquet-column/src/main/java/org/apache/parquet/column/statistics/BinaryStatistics.java
 
b/parquet-column/src/main/java/org/apache/parquet/column/statistics/BinaryStatistics.java
index 87d39bf16..9488a3849 100644
--- 
a/parquet-column/src/main/java/org/apache/parquet/column/statistics/BinaryStatistics.java
+++ 
b/parquet-column/src/main/java/org/apache/parquet/column/statistics/BinaryStatistics.java
@@ -105,7 +105,7 @@ public class BinaryStatistics extends Statistics<Binary> {
 
   @Override
   public boolean isSmallerThan(long size) {
-    return !hasNonNullValue() || ((min.length() + max.length()) < size);
+    return !hasNonNullValue() || (((long) min.length() + max.length()) < size);
   }
 
   public boolean isSmallerThanWithTruncation(long size, int truncationLength) {
@@ -113,8 +113,8 @@ public class BinaryStatistics extends Statistics<Binary> {
       return true;
     }
 
-    int minTruncateLength = Math.min(min.length(), truncationLength);
-    int maxTruncateLength = Math.min(max.length(), truncationLength);
+    long minTruncateLength = Math.min(min.length(), truncationLength);
+    long maxTruncateLength = Math.min(max.length(), truncationLength);
 
     return minTruncateLength + maxTruncateLength < size;
   }
diff --git 
a/parquet-column/src/test/java/org/apache/parquet/column/statistics/TestStatistics.java
 
b/parquet-column/src/test/java/org/apache/parquet/column/statistics/TestStatistics.java
index dec244f62..92eaa7a30 100644
--- 
a/parquet-column/src/test/java/org/apache/parquet/column/statistics/TestStatistics.java
+++ 
b/parquet-column/src/test/java/org/apache/parquet/column/statistics/TestStatistics.java
@@ -927,4 +927,15 @@ public class TestStatistics {
     assertThrows(UnsupportedOperationException.class, stats::minAsString);
     assertThrows(UnsupportedOperationException.class, () -> 
stats.isSmallerThan(0));
   }
+
+  @Test
+  public void testBinaryIsSmallerThanNoOverflowForLargeValues() {
+    BinaryStatistics stats = new BinaryStatistics();
+    // Create a Binary whose length() reports 2^30 without allocating 1 GB
+    Binary fakeLarge = Binary.fromConstantByteArray(new byte[0], 0, 1 << 30);
+    stats.updateStats(fakeLarge);
+
+    // min.length() + max.length() = 2^31, must not overflow int to negative
+    assertFalse(stats.isSmallerThan(4096));
+  }
 }