Upgrade arrow parquet and arrow-flight to 24.0.0 (#3691)

* Update to arrow 24.0.0

* Update pyo3 interface

* Update datafusion-cli lockfile

Author: alamb

datafusion-cli/Cargo.lock

@@ -29,7 +29,7 @@ rust-version = "1.62"
 readme = "README.md"
 
 [dependencies]
-arrow = "23.0.0"
+arrow = "24.0.0"
 clap = { version = "3", features = ["derive", "cargo"] }
 datafusion = { path = "../datafusion/core", version = "12.0.0" }
 dirs = "4.0.0"

datafusion-cli/Cargo.toml

@@ -34,7 +34,7 @@ path = "examples/avro_sql.rs"
 required-features = ["datafusion/avro"]
 
 [dev-dependencies]
-arrow-flight = "23.0.0"
+arrow-flight = "24.0.0"
 async-trait = "0.1.41"
 datafusion = { path = "../datafusion/core" }
 futures = "0.3"

datafusion-examples/Cargo.toml

@@ -40,10 +40,10 @@ pyarrow = ["pyo3", "arrow/pyarrow"]
 
 [dependencies]
 apache-avro = { version = "0.14", default-features = false, features = ["snappy"], optional = true }
-arrow = { version = "23.0.0", default-features = false }
+arrow = { version = "24.0.0", default-features = false }
 cranelift-module = { version = "0.88.0", optional = true }
 object_store = { version = "0.5.0", default-features = false, optional = true }
 ordered-float = "3.0"
-parquet = { version = "23.0.0", default-features = false, optional = true }
+parquet = { version = "24.0.0", default-features = false, optional = true }
 pyo3 = { version = "0.17.1", optional = true }
 sqlparser = "0.24"

datafusion/common/Cargo.toml

@@ -43,16 +43,16 @@ impl PyArrowConvert for ScalarValue {
         let array = factory.call1((args, typ))?;
 
         // convert the pyarrow array to rust array using C data interface
-        let array = array.extract::<ArrayData>()?;
-        let scalar = ScalarValue::try_from_array(&array.into(), 0)?;
+        let array = arrow::array::make_array(ArrayData::from_pyarrow(array)?);
+        let scalar = ScalarValue::try_from_array(&array, 0)?;
 
         Ok(scalar)
     }
 
     fn to_pyarrow(&self, py: Python) -> PyResult<PyObject> {
         let array = self.to_array();
         // convert to pyarrow array using C data interface
-        let pyarray = array.data_ref().clone().into_py(py);
+        let pyarray = array.data().to_pyarrow(py)?;
         let pyscalar = pyarray.call_method1(py, "__getitem__", (0,))?;
 
         Ok(pyscalar)

datafusion/common/src/pyarrow.rs

@@ -56,7 +56,7 @@ unicode_expressions = ["datafusion-physical-expr/regex_expressions", "datafusion
 [dependencies]
 ahash = { version = "0.8", default-features = false, features = ["runtime-rng"] }
 apache-avro = { version = "0.14", optional = true }
-arrow = { version = "23.0.0", features = ["prettyprint"] }
+arrow = { version = "24.0.0", features = ["prettyprint"] }
 async-trait = "0.1.41"
 bytes = "1.1"
 chrono = { version = "0.4", default-features = false }
@@ -78,7 +78,7 @@ num_cpus = "1.13.0"
 object_store = "0.5.0"
 ordered-float = "3.0"
 parking_lot = "0.12"
-parquet = { version = "23.0.0", features = ["arrow", "async"] }
+parquet = { version = "24.0.0", features = ["arrow", "async"] }
 paste = "^1.0"
 pin-project-lite = "^0.2.7"
 pyo3 = { version = "0.17.1", optional = true }
@@ -93,7 +93,7 @@ url = "2.2"
 uuid = { version = "1.0", features = ["v4"] }
 
 [dev-dependencies]
-arrow = { version = "23.0.0", features = ["prettyprint", "dyn_cmp_dict"] }
+arrow = { version = "24.0.0", features = ["prettyprint", "dyn_cmp_dict"] }
 async-trait = "0.1.53"
 criterion = "0.4"
 csv = "1.1.6"

datafusion/core/Cargo.toml

@@ -23,6 +23,6 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-arrow = { version = "23.0.0", features = ["prettyprint"] }
+arrow = { version = "24.0.0", features = ["prettyprint"] }
 env_logger = "0.9.0"
 rand = "0.8"

datafusion/core/fuzz-utils/Cargo.toml

@@ -36,6 +36,6 @@ path = "src/lib.rs"
 
 [dependencies]
 ahash = { version = "0.8", default-features = false, features = ["runtime-rng"] }
-arrow = { version = "23.0.0", default-features = false }
+arrow = { version = "24.0.0", default-features = false }
 datafusion-common = { path = "../common", version = "12.0.0" }
 sqlparser = "0.24"

datafusion/expr/Cargo.toml

@@ -36,7 +36,7 @@ path = "src/lib.rs"
 jit = []
 
 [dependencies]
-arrow = { version = "23.0.0", default-features = false }
+arrow = { version = "24.0.0", default-features = false }
 cranelift = "0.88.0"
 cranelift-jit = "0.88.0"
 cranelift-module = "0.88.0"

datafusion/jit/Cargo.toml

@@ -37,7 +37,7 @@ default = ["unicode_expressions"]
 unicode_expressions = []
 
 [dependencies]
-arrow = { version = "23.0.0", features = ["prettyprint"] }
+arrow = { version = "24.0.0", features = ["prettyprint"] }
 async-trait = "0.1.41"
 chrono = { version = "0.4", default-features = false }
 datafusion-common = { path = "../common", version = "12.0.0" }

datafusion/optimizer/Cargo.toml

@@ -40,7 +40,7 @@ unicode_expressions = ["unicode-segmentation"]
 
 [dependencies]
 ahash = { version = "0.8", default-features = false, features = ["runtime-rng"] }
-arrow = { version = "23.0.0", features = ["prettyprint"] }
+arrow = { version = "24.0.0", features = ["prettyprint"] }
 blake2 = { version = "^0.10.2", optional = true }
 blake3 = { version = "1.0", optional = true }
 chrono = { version = "0.4", default-features = false }

datafusion/physical-expr/Cargo.toml

@@ -40,7 +40,7 @@ default = []
 json = ["pbjson", "pbjson-build", "serde", "serde_json"]
 
 [dependencies]
-arrow = "23.0.0"
+arrow = "24.0.0"
 datafusion = { path = "../core", version = "12.0.0" }
 datafusion-common = { path = "../common", version = "12.0.0" }
 datafusion-expr = { path = "../expr", version = "12.0.0" }