chore: Upgrade to datafusion 47.0.0-rc1 and arrow-rs 55.0.0 (#1563)

Author: andygrove

native/Cargo.lock

@@ -34,11 +34,11 @@ edition = "2021"
 rust-version = "1.85"
 
 [workspace.dependencies]
-arrow = { version = "54.2.0", features = ["prettyprint", "ffi", "chrono-tz"] }
+arrow = { version = "55.0.0", features = ["prettyprint", "ffi", "chrono-tz"] }
 async-trait = { version = "0.1" }
 bytes = { version = "1.10.0" }
-parquet = { version = "54.2.0", default-features = false, features = ["experimental"] }
-datafusion = { version = "46.0.0", default-features = false, features = ["unicode_expressions", "crypto_expressions", "nested_expressions", "parquet"] }
+parquet = { version = "55.0.0", default-features = false, features = ["experimental"] }
+datafusion = { git = "https://github.com/apache/datafusion", rev = "47.0.0-rc1", default-features = false, features = ["unicode_expressions", "crypto_expressions", "nested_expressions", "parquet"] }
 datafusion-comet-spark-expr = { path = "spark-expr", version = "0.8.0" }
 datafusion-comet-proto = { path = "proto", version = "0.8.0" }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
@@ -48,7 +48,7 @@ num = "0.4"
 rand = "0.8"
 regex = "1.9.6"
 thiserror = "1"
-object_store = { version = "0.11.0", features = ["gcp", "azure", "aws", "http"] }
+object_store = { version = "0.12.0", features = ["gcp", "azure", "aws", "http"] }
 url = "2.2"
 
 [profile.release]

native/Cargo.toml

@@ -77,7 +77,7 @@ jni = { version = "0.21", features = ["invocation"] }
 lazy_static = "1.4"
 assertables = "7"
 hex = "0.4.3"
-datafusion-functions-nested = "46.0.0"
+datafusion-functions-nested = { git = "https://github.com/apache/datafusion", rev = "47.0.0-rc1" }
 
 [features]
 default = []

native/core/Cargo.toml

@@ -22,6 +22,7 @@ use arrow::record_batch::RecordBatch;
 use datafusion::common::{internal_err, Result, ScalarValue};
 use datafusion::physical_expr::PhysicalExpr;
 use datafusion::physical_plan::ColumnarValue;
+use std::fmt::Formatter;
 use std::hash::Hash;
 use std::{any::Any, fmt::Display, sync::Arc};
 
@@ -140,4 +141,8 @@ impl PhysicalExpr for BloomFilterMightContain {
             Arc::clone(&children[1]),
         )?))
     }
+
+    fn fmt_sql(&self, _: &mut Formatter<'_>) -> std::fmt::Result {
+        unimplemented!()
+    }
 }

native/core/src/execution/expressions/bloom_filter_might_contain.rs

@@ -67,6 +67,10 @@ impl PhysicalExpr for Subquery {
         self
     }
 
+    fn fmt_sql(&self, _: &mut Formatter<'_>) -> std::fmt::Result {
+        unimplemented!()
+    }
+
     fn data_type(&self, _: &Schema) -> datafusion::common::Result<DataType> {
         Ok(self.data_type.clone())
     }

native/core/src/execution/expressions/subquery.rs

@@ -99,6 +99,7 @@ impl DisplayAs for CopyExec {
             DisplayFormatType::Default | DisplayFormatType::Verbose => {
                 write!(f, "CopyExec [{:?}]", self.mode)
             }
+            DisplayFormatType::TreeRender => unimplemented!(),
         }
     }
 }

native/core/src/execution/operators/copy.rs

@@ -85,6 +85,7 @@ impl DisplayAs for ExpandExec {
 
                 Ok(())
             }
+            DisplayFormatType::TreeRender => unimplemented!(),
         }
     }
 }

native/core/src/execution/operators/expand.rs

@@ -312,6 +312,7 @@ impl DisplayAs for FilterExec {
                     self.predicate, display_projections
                 )
             }
+            DisplayFormatType::TreeRender => unimplemented!(),
         }
     }
 }

native/core/src/execution/operators/filter.rs

@@ -384,6 +384,7 @@ impl DisplayAs for ScanExec {
                     .collect();
                 write!(f, "schema=[{}]", fields.join(", "))?;
             }
+            DisplayFormatType::TreeRender => unimplemented!(),
         }
         Ok(())
     }

native/core/src/execution/operators/scan.rs

@@ -120,6 +120,7 @@ impl DisplayAs for ShuffleWriterExec {
                     self.partitioning, self.enable_fast_encoding, self.codec
                 )
             }
+            DisplayFormatType::TreeRender => unimplemented!(),
         }
     }
 }