fix: harden legacy update filter barrier

rust/lancedb/src/table/update.rs

@@ -3,6 +3,7 @@
 
 use std::sync::Arc;
 
+use arrow_schema::DataType;
 use lance::dataset::UpdateBuilder as LanceUpdateBuilder;
 use serde::{Deserialize, Serialize};
 
@@ -84,10 +85,11 @@ pub(crate) async fn execute_update(
     let dataset = table.dataset.get().await?;
 
     // 2. Initialize the Lance Core builder
-    let mut builder = LanceUpdateBuilder::new(dataset);
+    let mut builder = LanceUpdateBuilder::new(dataset.clone());
 
     // 3. Apply the filter (WHERE clause)
     if let Some(predicate) = update.filter {
+        let predicate = safe_update_filter(&predicate, dataset.as_ref());
         builder = builder.update_where(&predicate)?;
     }
 
@@ -109,9 +111,61 @@ pub(crate) async fn execute_update(
     })
 }
 
+/// Keep vulnerable legacy updates on the early-materialization scan path.
+///
+/// Late materialization uses `TakeExec` to concatenate values read from multiple
+/// fragments. That can overflow a single 32-bit-offset array. Lance's update
+/// builder does not currently expose its scanner's materialization controls, so
+/// cast the predicate to an integer before comparing it with `1`. Lance's
+/// scalar-index extractor does not unwrap non-literal casts, keeping every
+/// supported predicate out of the vulnerable late-materialization plan.
+///
+/// Keep the original SQL verbatim instead of parsing and serializing it. Newlines
+/// isolate the generated syntax from a trailing line comment in the predicate.
+///
+/// This compatibility fallback is intentionally limited to legacy storage. V2
+/// readers do not use the affected materialization path and keep their original
+/// filter expression and indexed plan.
+fn safe_update_filter(predicate: &str, dataset: &lance::Dataset) -> String {
+    let has_offset_columns = dataset
+        .schema()
+        .fields
+        .iter()
+        .any(|field| has_32_bit_offsets(&field.data_type()));
+
+    if !dataset.manifest().should_use_legacy_format() || !has_offset_columns {
+        return predicate.to_owned();
+    }
+
+    format!("CAST((\n{predicate}\n) AS INT) = 1")
+}
+
+fn has_32_bit_offsets(data_type: &DataType) -> bool {
+    match data_type {
+        DataType::Binary
+        | DataType::Utf8
+        | DataType::List(_)
+        | DataType::ListView(_)
+        | DataType::Map(_, _)
+        | DataType::Union(_, _) => true,
+        DataType::FixedSizeList(field, _)
+        | DataType::LargeList(field)
+        | DataType::LargeListView(field) => has_32_bit_offsets(field.data_type()),
+        DataType::Struct(fields) => fields
+            .iter()
+            .any(|field| has_32_bit_offsets(field.data_type())),
+        DataType::Dictionary(_, values) => has_32_bit_offsets(values),
+        DataType::RunEndEncoded(_, values) => has_32_bit_offsets(values.data_type()),
+        _ => false,
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use crate::connect;
+    use crate::connection::LanceFileVersion;
+    use crate::database::listing::{ListingDatabaseOptions, NewTableConfig};
+    use crate::index::{Index, scalar::BTreeIndexBuilder};
     use crate::query::QueryBase;
     use crate::query::{ExecutableQuery, Select};
     use arrow_array::{
@@ -122,9 +176,18 @@ mod tests {
     use arrow_data::ArrayDataBuilder;
     use arrow_schema::{ArrowError, DataType, Field, Schema, TimeUnit};
     use futures::TryStreamExt;
+    use lance::io::exec::Planner;
     use std::sync::Arc;
     use std::time::Duration;
 
+    fn contains_take(plan: &dyn datafusion_physical_plan::ExecutionPlan) -> bool {
+        plan.name() == "TakeExec"
+            || plan
+                .children()
+                .iter()
+                .any(|child| contains_take(child.as_ref()))
+    }
+
     #[tokio::test]
     async fn test_update_all_types() {
         let conn = connect("memory://")
@@ -409,6 +472,301 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn test_update_materializes_offset_columns_before_filter() {
+        let batch = record_batch!(
+            ("id", Int32, [0, 1, 2, 3]),
+            (
+                "split",
+                Utf8,
+                [Some("test"), None, Some("test"), Some("train")]
+            ),
+            ("payload", Utf8, ["a", "b", "c", "d"])
+        )
+        .unwrap();
+        let conn = connect("memory://")
+            .database_options(&ListingDatabaseOptions {
+                new_table_config: NewTableConfig {
+                    data_storage_version: Some(LanceFileVersion::Legacy),
+                    ..Default::default()
+                },
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        let table = conn
+            .create_table("offset_table", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        table.add(batch).execute().await.unwrap();
+        table
+            .create_index(&["split"], Index::BTree(BTreeIndexBuilder::default()))
+            .execute()
+            .await
+            .unwrap();
+
+        let dataset = table.dataset().unwrap().get().await.unwrap();
+        let planner = Planner::new(Arc::new(dataset.schema().into()));
+
+        let filter = planner.parse_filter("split = 'test'").unwrap();
+        let filter = planner.optimize_expr(filter).unwrap();
+        let mut scanner = dataset.scan();
+        scanner.with_row_id().filter_expr(filter);
+        let explanation = scanner.explain_plan(false).await.unwrap();
+        let plan = scanner.create_plan().await.unwrap();
+        assert!(
+            contains_take(plan.as_ref()),
+            "test setup must late-materialize payload:\n{explanation}"
+        );
+
+        let guarded_filter = super::safe_update_filter("split = 'test'", dataset.as_ref());
+        let filter = planner.parse_filter(&guarded_filter).unwrap();
+        let filter = planner.optimize_expr(filter).unwrap();
+        let mut scanner = dataset.scan();
+        scanner.with_row_id().filter_expr(filter);
+        let explanation = scanner.explain_plan(false).await.unwrap();
+        let plan = scanner.create_plan().await.unwrap();
+
+        // Regression test for #1291: the payload must be read by the scan, not
+        // concatenated across fragments by a late-materializing TakeExec.
+        assert!(
+            !contains_take(plan.as_ref()),
+            "unexpected late materialization:\n{explanation}"
+        );
+
+        let result = table
+            .update()
+            .only_if("split = 'test'")
+            .column("split", "'TEST'")
+            .execute()
+            .await
+            .unwrap();
+
+        assert_eq!(result.rows_updated, 4);
+        assert_eq!(
+            table
+                .count_rows(Some("split = 'TEST'".to_string()))
+                .await
+                .unwrap(),
+            4
+        );
+        assert_eq!(
+            table
+                .count_rows(Some("payload IN ('a', 'b', 'c', 'd')".to_string()))
+                .await
+                .unwrap(),
+            8
+        );
+    }
+
+    #[tokio::test]
+    async fn test_update_v2_keeps_indexed_plan() {
+        let batch = record_batch!(
+            ("id", Int32, [0, 1, 2, 3]),
+            ("split", Utf8, ["test", "train", "test", "train"]),
+            ("payload", Utf8, ["a", "b", "c", "d"])
+        )
+        .unwrap();
+        let conn = connect("memory://")
+            .database_options(&ListingDatabaseOptions {
+                new_table_config: NewTableConfig {
+                    data_storage_version: Some(LanceFileVersion::V2_0),
+                    ..Default::default()
+                },
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        let table = conn
+            .create_table("v2_offset_table", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        table.add(batch).execute().await.unwrap();
+        table
+            .create_index(&["split"], Index::BTree(BTreeIndexBuilder::default()))
+            .execute()
+            .await
+            .unwrap();
+
+        let dataset = table.dataset().unwrap().get().await.unwrap();
+        let predicate = "split = 'test'";
+        let update_filter = super::safe_update_filter(predicate, dataset.as_ref());
+        assert_eq!(update_filter, predicate);
+
+        let planner = Planner::new(Arc::new(dataset.schema().into()));
+        let filter = planner.parse_filter(&update_filter).unwrap();
+        let filter = planner.optimize_expr(filter).unwrap();
+        let mut scanner = dataset.scan();
+        scanner.with_row_id().filter_expr(filter);
+        let explanation = scanner.explain_plan(false).await.unwrap();
+        let plan = scanner.create_plan().await.unwrap();
+        assert!(
+            explanation.contains("ScalarIndexQuery"),
+            "v2 plan unexpectedly lost its scalar index:\n{explanation}"
+        );
+        assert!(
+            !contains_take(plan.as_ref()),
+            "v2 plan unexpectedly used the legacy TakeExec path:\n{explanation}"
+        );
+
+        let result = table
+            .update()
+            .only_if(predicate)
+            .column("split", "'TEST'")
+            .execute()
+            .await
+            .unwrap();
+        assert_eq!(result.rows_updated, 4);
+    }
+
+    #[tokio::test]
+    async fn test_update_accepts_trailing_comment_filter() {
+        let conn = connect("memory://")
+            .database_options(&ListingDatabaseOptions {
+                new_table_config: NewTableConfig {
+                    data_storage_version: Some(LanceFileVersion::Legacy),
+                    ..Default::default()
+                },
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        let batch = record_batch!(("id", Int32, [1, 2]), ("payload", Utf8, ["a", "b"])).unwrap();
+        let table = conn
+            .create_table("trailing_comment", batch)
+            .execute()
+            .await
+            .unwrap();
+
+        let predicate = "id = 1 -- valid trailing comment";
+        assert_eq!(table.count_rows(Some(predicate.into())).await.unwrap(), 1);
+        let result = table
+            .update()
+            .only_if(predicate)
+            .column("payload", "'updated'")
+            .execute()
+            .await
+            .unwrap();
+
+        assert_eq!(result.rows_updated, 1);
+        assert_eq!(
+            table
+                .count_rows(Some("payload = 'updated'".into()))
+                .await
+                .unwrap(),
+            1
+        );
+    }
+
+    #[tokio::test]
+    async fn test_update_boolean_index_uses_early_materialization() {
+        let conn = connect("memory://")
+            .database_options(&ListingDatabaseOptions {
+                new_table_config: NewTableConfig {
+                    data_storage_version: Some(LanceFileVersion::Legacy),
+                    ..Default::default()
+                },
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        let batch = record_batch!(
+            ("flag", Boolean, [true, false]),
+            ("payload", Utf8, ["a", "b"])
+        )
+        .unwrap();
+        let table = conn
+            .create_table("boolean_index", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        table.add(batch).execute().await.unwrap();
+        table
+            .create_index(&["flag"], Index::BTree(BTreeIndexBuilder::default()))
+            .execute()
+            .await
+            .unwrap();
+
+        let dataset = table.dataset().unwrap().get().await.unwrap();
+        let guarded_filter = super::safe_update_filter("flag", dataset.as_ref());
+        let mut scanner = dataset.scan();
+        scanner.with_row_id().filter(&guarded_filter).unwrap();
+        let explanation = scanner.explain_plan(false).await.unwrap();
+        let plan = scanner.create_plan().await.unwrap();
+        assert!(
+            !contains_take(plan.as_ref()),
+            "Boolean predicate retained late materialization:\n{explanation}"
+        );
+        assert!(
+            !explanation.contains("MaterializeIndex"),
+            "Boolean predicate retained scalar-index extraction:\n{explanation}"
+        );
+
+        let result = table
+            .update()
+            .only_if("flag")
+            .column("payload", "'updated'")
+            .execute()
+            .await
+            .unwrap();
+        assert_eq!(result.rows_updated, 2);
+        assert_eq!(
+            table
+                .count_rows(Some("payload = 'updated'".into()))
+                .await
+                .unwrap(),
+            2
+        );
+    }
+
+    #[tokio::test]
+    async fn test_update_accepts_quoted_reserved_identifier() {
+        let conn = connect("memory://")
+            .database_options(&ListingDatabaseOptions {
+                new_table_config: NewTableConfig {
+                    data_storage_version: Some(LanceFileVersion::Legacy),
+                    ..Default::default()
+                },
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        let batch =
+            record_batch!(("select", Int32, [1, 2]), ("payload", Utf8, ["a", "b"])).unwrap();
+        let table = conn
+            .create_table("reserved_identifier", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        table.add(batch).execute().await.unwrap();
+
+        let predicate = "`select` = 1";
+        assert_eq!(table.count_rows(Some(predicate.into())).await.unwrap(), 2);
+        let result = table
+            .update()
+            .only_if(predicate)
+            .column("payload", "'updated'")
+            .execute()
+            .await
+            .unwrap();
+
+        assert_eq!(result.rows_updated, 2);
+        assert_eq!(
+            table
+                .count_rows(Some("payload = 'updated'".into()))
+                .await
+                .unwrap(),
+            2
+        );
+    }
+
     #[tokio::test]
     async fn test_update_via_expr() {
         let conn = connect("memory://")