Add once_cell dependency and refactor Arrow array stream capsule name handling

Author: kosiew

Cargo.lock

@@ -26,17 +26,34 @@ readme = "README.md"
 license = "Apache-2.0"
 edition = "2021"
 rust-version = "1.78"
-include = ["/src", "/datafusion", "/LICENSE.txt", "build.rs", "pyproject.toml", "Cargo.toml", "Cargo.lock"]
+include = [
+    "/src",
+    "/datafusion",
+    "/LICENSE.txt",
+    "build.rs",
+    "pyproject.toml",
+    "Cargo.toml",
+    "Cargo.lock",
+]
 
 [features]
 default = ["mimalloc"]
-protoc = [ "datafusion-substrait/protoc" ]
+protoc = ["datafusion-substrait/protoc"]
 substrait = ["dep:datafusion-substrait"]
 
 [dependencies]
-tokio = { version = "1.45", features = ["macros", "rt", "rt-multi-thread", "sync"] }
-pyo3 = { version = "0.24", features = ["extension-module", "abi3", "abi3-py39"] }
-pyo3-async-runtimes = { version = "0.24", features = ["tokio-runtime"]}
+tokio = { version = "1.45", features = [
+    "macros",
+    "rt",
+    "rt-multi-thread",
+    "sync",
+] }
+pyo3 = { version = "0.24", features = [
+    "extension-module",
+    "abi3",
+    "abi3-py39",
+] }
+pyo3-async-runtimes = { version = "0.24", features = ["tokio-runtime"] }
 pyo3-log = "0.12.4"
 arrow = { version = "55.1.0", features = ["pyarrow"] }
 datafusion = { version = "49.0.2", features = ["avro", "unicode_expressions"] }
@@ -45,15 +62,23 @@ datafusion-proto = { version = "49.0.2" }
 datafusion-ffi = { version = "49.0.2" }
 prost = "0.13.1" # keep in line with `datafusion-substrait`
 uuid = { version = "1.18", features = ["v4"] }
-mimalloc = { version = "0.1", optional = true, default-features = false, features = ["local_dynamic_tls"] }
+mimalloc = { version = "0.1", optional = true, default-features = false, features = [
+    "local_dynamic_tls",
+] }
 async-trait = "0.1.89"
+once_cell = "1.18"
 futures = "0.3"
-object_store = { version = "0.12.3", features = ["aws", "gcp", "azure", "http"] }
+object_store = { version = "0.12.3", features = [
+    "aws",
+    "gcp",
+    "azure",
+    "http",
+] }
 url = "2"
 log = "0.4.27"
 
 [build-dependencies]
-prost-types = "0.13.1" # keep in line with `datafusion-substrait`
+prost-types = "0.13.1"     # keep in line with `datafusion-substrait`
 pyo3-build-config = "0.24"
 
 [lib]

Cargo.toml

@@ -15,6 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use once_cell::sync::Lazy;
 use std::collections::HashMap;
 use std::ffi::CString;
 use std::sync::Arc;
@@ -59,6 +60,10 @@ use crate::{
     expr::{sort_expr::PySortExpr, PyExpr},
 };
 
+/// File-level static CString for the Arrow array stream capsule name.
+static ARROW_ARRAY_STREAM_NAME: Lazy<CString> =
+    Lazy::new(|| CString::new("arrow_array_stream").unwrap());
+
 // https://github.com/apache/datafusion-python/pull/1016#discussion_r1983239116
 // - we have not decided on the table_provider approach yet
 // this is an interim implementation
@@ -967,8 +972,7 @@ impl PyDataFrame {
         // destructor provided by PyO3 will drop the stream unless ownership is
         // transferred to PyArrow during import.
         let stream = FFI_ArrowArrayStream::new(reader);
-        let name = CString::new("arrow_array_stream").unwrap();
-        let capsule = PyCapsule::new(py, stream, Some(name))?;
+        let capsule = PyCapsule::new(py, stream, Some(ARROW_ARRAY_STREAM_NAME.clone()))?;
         Ok(capsule)
     }