Merge branch 'main' into phillip/250509-predicate-fix

Author: phillipleblanc

.github/workflows/ci_typos.yml

@@ -42,4 +42,4 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Check typos
-        uses: crate-ci/typos@v1.31.1
+        uses: crate-ci/typos@v1.32.0

Cargo.lock

@@ -1688,5 +1688,22 @@ mod tests {
             ]));
             assert_eq!(arrow_type, type_to_arrow_type(&iceberg_type).unwrap());
         }
+
+        // test dictionary type
+        {
+            let arrow_type =
+                DataType::Dictionary(Box::new(DataType::Int32), Box::new(DataType::Int8));
+            let iceberg_type = Type::Primitive(PrimitiveType::Int);
+            assert_eq!(
+                iceberg_type,
+                arrow_type_to_type(&arrow_type).unwrap(),
+                "Expected dictionary conversion to use the contained value"
+            );
+
+            let arrow_type =
+                DataType::Dictionary(Box::new(DataType::Utf8), Box::new(DataType::Boolean));
+            let iceberg_type = Type::Primitive(PrimitiveType::Boolean);
+            assert_eq!(iceberg_type, arrow_type_to_type(&arrow_type).unwrap());
+        }
     }
 }

bindings/python/Cargo.lock

@@ -28,6 +28,9 @@ pub type Result<T> = std::result::Result<T, Error>;
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
 #[non_exhaustive]
 pub enum ErrorKind {
+    /// The operation was rejected because the system is not in a state required for the operation’s execution.
+    PreconditionFailed,
+
     /// Iceberg don't know what happened here, and no actions other than
     /// just returning it back. For example, iceberg returns an internal
     /// service error.
@@ -76,6 +79,7 @@ impl From<ErrorKind> for &'static str {
             ErrorKind::TableNotFound => "TableNotFound",
             ErrorKind::NamespaceAlreadyExists => "NamespaceAlreadyExists",
             ErrorKind::NamespaceNotFound => "NamespaceNotFound",
+            ErrorKind::PreconditionFailed => "PreconditionFailed",
         }
     }
 }

crates/iceberg/src/arrow/schema.rs

@@ -19,6 +19,8 @@ use std::collections::HashMap;
 
 /// A serialized form of a "compact" Theta sketch produced by the Apache DataSketches library.
 pub const APACHE_DATASKETCHES_THETA_V1: &str = "apache-datasketches-theta-v1";
+/// A serialized form of a deletion vector.
+pub const DELETION_VECTOR_V1: &str = "deletion-vector-v1";
 
 /// The blob
 #[derive(Debug, PartialEq, Clone)]

crates/iceberg/src/error.rs

@@ -20,7 +20,7 @@
 #![deny(missing_docs)]
 
 mod blob;
-pub use blob::{Blob, APACHE_DATASKETCHES_THETA_V1};
+pub use blob::{Blob, APACHE_DATASKETCHES_THETA_V1, DELETION_VECTOR_V1};
 
 mod compression;
 pub use compression::CompressionCodec;

crates/iceberg/src/puffin/blob.rs

@@ -219,6 +219,15 @@ mod tests {
     use crate::transaction::Transaction;
     use crate::{TableRequirement, TableUpdate};
 
+    #[tokio::test]
+    async fn test_empty_data_append_action() {
+        let table = make_v2_minimal_table();
+        let tx = Transaction::new(&table);
+        let mut action = tx.fast_append(None, vec![]).unwrap();
+        action.add_data_files(vec![]).unwrap();
+        assert!(action.apply().await.is_err());
+    }
+
     #[tokio::test]
     async fn test_fast_append_action() {
         let table = make_v2_minimal_table();

crates/iceberg/src/puffin/mod.rs

@@ -172,6 +172,13 @@ impl<'a> SnapshotProduceAction<'a> {
     // Write manifest file for added data files and return the ManifestFile for ManifestList.
     async fn write_added_manifest(&mut self) -> Result<ManifestFile> {
         let added_data_files = std::mem::take(&mut self.added_data_files);
+        if added_data_files.is_empty() {
+            return Err(Error::new(
+                ErrorKind::PreconditionFailed,
+                "No added data files found when write a manifest file",
+            ));
+        }
+
         let snapshot_id = self.snapshot_id;
         let format_version = self.tx.current_table.metadata().format_version();
         let manifest_entries = added_data_files.into_iter().map(|data_file| {