From 18d88145809723212de441be144e548b3cdd92fd Mon Sep 17 00:00:00 2001
From: Alexander Alexandrov <alexander.s.alexandrov@gmail.com>
Date: Sun, 22 Mar 2026 23:28:32 +0200
Subject: [PATCH] fix: support total_size=0 in byte_range_to_row_range

In certain cases DataFusion might decide to create a ranges for empty
files that have zero rows. In order to avoid hitting a division by zero
error in the

```rust
let average_row = total_size / row_count;
```

line, add an early exit check to `VortexOpener::open` to immediately
return an empty stream if the file contains  zero rows:

```rust
if vxf.row_count() == 0 {
    let empty_stream = stream::iter(vec![]).boxed();
    return Ok(empty_stream);
}
```

The enforced `row_count > 0` invariant for the `byte_range_to_row_range`
call is now also called out with a `debug_assert!` macro.

Add a new `test_open_empty_file` test case.

Signed-off-by: Alexander Alexandrov <alexander.s.alexandrov@gmail.com>
---
 vortex-datafusion/src/persistent/opener.rs | 35 ++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/vortex-datafusion/src/persistent/opener.rs b/vortex-datafusion/src/persistent/opener.rs
index 1eefb4f0ae1..deb67a908d5 100644
--- a/vortex-datafusion/src/persistent/opener.rs
+++ b/vortex-datafusion/src/persistent/opener.rs
@@ -198,6 +198,12 @@ impl FileOpener for VortexOpener {
                 .await
                 .map_err(|e| exec_datafusion_err!("Failed to open Vortex file {e}"))?;
 
+            // Check if there are rows in this file. If not, we can save
+            // ourselves some work and return an empty stream.
+            if vxf.row_count() == 0 {
+                return Ok(stream::empty().boxed());
+            }
+
             // This is the expected arrow types of the actual columns in the file, which might have different types
             // from the unified logical schema or miss
             let this_file_schema = Arc::new(calculate_physical_schema(
@@ -430,6 +436,8 @@ fn apply_byte_range(
 }
 
 fn byte_range_to_row_range(byte_range: Range<u64>, row_count: u64, total_size: u64) -> Range<u64> {
+    debug_assert!(row_count > 0); // Asserted by an early exit check in VortexOpener::open
+
     let average_row = total_size / row_count;
     assert!(average_row > 0, "A row must always have at least one byte");
 
@@ -619,6 +627,33 @@ mod tests {
         Ok(())
     }
 
+    #[tokio::test]
+    async fn test_open_empty_file() -> anyhow::Result<()> {
+        use futures::TryStreamExt;
+
+        let object_store = Arc::new(InMemory::new()) as Arc<dyn ObjectStore>;
+        let data_batch = record_batch!(("a", Int32, Vec::<i32>::new())).unwrap();
+        let file_path = "part=1/empty.vortex";
+        let file_size =
+            write_arrow_to_vortex(object_store.clone(), file_path, data_batch.clone()).await?;
+
+        let file_schema = data_batch.schema();
+        // Parallel scans may attach a byte range even for empty files; the
+        // opener must not call byte_range_to_row_range when the row_count is 0.
+        let file =
+            PartitionedFile::new_with_range(file_path.to_string(), file_size, 0, file_size as i64);
+
+        let table_schema = TableSchema::from_file_schema(file_schema.clone());
+
+        let opener = make_opener(object_store, table_schema, None);
+        let stream = opener.open(file)?.await?;
+        let data = stream.try_collect::<Vec<_>>().await?;
+
+        assert_eq!(data.len(), 0);
+
+        Ok(())
+    }
+
     #[rstest]
     #[tokio::test]
     async fn test_open_files_different_table_schema() -> anyhow::Result<()> {