feat: Add Spark-compatible implementation of SchemaAdapterFactory (#1169)

* Add Spark-compatible SchemaAdapterFactory implementation

* remove prototype code

* fix

* refactor

* implement more cast logic

* implement more cast logic

* add basic test

* improve test

* cleanup

* fmt

* add support for casting unsigned int to signed int

* clippy

* address feedback

* fix test

Author: andygrove

native/Cargo.lock

@@ -39,8 +39,8 @@ arrow-buffer = { version = "53.2.0" }
 arrow-data = { version = "53.2.0" }
 arrow-schema = { version = "53.2.0" }
 parquet = { version = "53.2.0", default-features = false, features = ["experimental"] }
-datafusion-common = { version = "43.0.0" }
 datafusion = { version = "43.0.0", default-features = false, features = ["unicode_expressions", "crypto_expressions"] }
+datafusion-common = { version = "43.0.0" }
 datafusion-functions = { version = "43.0.0", features = ["crypto_expressions"] }
 datafusion-functions-nested = { version = "43.0.0", default-features = false }
 datafusion-expr = { version = "43.0.0", default-features = false }

native/Cargo.toml

@@ -15,10 +15,9 @@
 // specific language governing permissions and limitations
 // under the License.
 
-pub mod file_util;
 pub mod page_util;
 pub mod rand_gen;
 
 pub use self::rand_gen::{random_bools, random_bytes, random_numbers, random_numbers_range};
 
-pub use self::file_util::{get_temp_file, get_temp_filename};
+pub use datafusion_comet_spark_expr::test_common::file_util::{get_temp_file, get_temp_filename};

native/core/src/parquet/util/test_common/mod.rs

@@ -33,7 +33,7 @@ arrow-buffer = { workspace = true }
 arrow-data = { workspace = true }
 arrow-schema = { workspace = true }
 chrono = { workspace = true }
-datafusion = { workspace = true }
+datafusion = { workspace = true, features = ["parquet"] }
 datafusion-common = { workspace = true }
 datafusion-expr = { workspace = true }
 datafusion-physical-expr = { workspace = true }
@@ -43,9 +43,11 @@ regex = { workspace = true }
 thiserror = { workspace = true }
 futures = { workspace = true }
 twox-hash = "2.0.0"
+rand = { workspace = true }
 
 [dev-dependencies]
 arrow-data = {workspace = true}
+parquet = { workspace = true, features = ["arrow"] }
 criterion = "0.5.1"
 rand = { workspace = true}
 tokio = { version = "1", features = ["rt-multi-thread"] }