Merge commit '19356b26f515149f96f9b6296975a77ac7260149' into chunchun…

…/update-df-apr-week-3

.asf.yaml

@@ -26,7 +26,7 @@ notifications:
   pullrequests: [email protected]
   jira_options: link label worklog
 github:
-  description: "Apache Arrow DataFusion SQL Query Engine"
+  description: "Apache DataFusion SQL Query Engine"
   homepage: https://arrow.apache.org/datafusion
   labels:
     - arrow

Cargo.toml

@@ -51,7 +51,7 @@ license = "Apache-2.0"
 readme = "README.md"
 repository = "https://github.com/apache/arrow-datafusion"
 rust-version = "1.73"
-version = "37.0.0"
+version = "37.1.0"
 
 [workspace.dependencies]
 # We turn off default-features for some dependencies here so the workspaces which inherit them can
@@ -73,22 +73,22 @@ bytes = "1.4"
 chrono = { version = "0.4.34", default-features = false }
 ctor = "0.2.0"
 dashmap = "5.4.0"
-datafusion = { path = "datafusion/core", version = "37.0.0", default-features = false }
-datafusion-common = { path = "datafusion/common", version = "37.0.0", default-features = false }
-datafusion-common-runtime = { path = "datafusion/common-runtime", version = "37.0.0" }
-datafusion-execution = { path = "datafusion/execution", version = "37.0.0" }
-datafusion-expr = { path = "datafusion/expr", version = "37.0.0" }
-datafusion-functions = { path = "datafusion/functions", version = "37.0.0" }
-datafusion-functions-aggregate = { path = "datafusion/functions-aggregate", version = "37.0.0" }
-datafusion-functions-array = { path = "datafusion/functions-array", version = "37.0.0" }
-datafusion-optimizer = { path = "datafusion/optimizer", version = "37.0.0", default-features = false }
-datafusion-physical-expr = { path = "datafusion/physical-expr", version = "37.0.0", default-features = false }
-datafusion-physical-expr-common = { path = "datafusion/physical-expr-common", version = "37.0.0", default-features = false }
-datafusion-physical-plan = { path = "datafusion/physical-plan", version = "37.0.0" }
-datafusion-proto = { path = "datafusion/proto", version = "37.0.0" }
-datafusion-sql = { path = "datafusion/sql", version = "37.0.0" }
-datafusion-sqllogictest = { path = "datafusion/sqllogictest", version = "37.0.0" }
-datafusion-substrait = { path = "datafusion/substrait", version = "37.0.0" }
+datafusion = { path = "datafusion/core", version = "37.1.0", default-features = false }
+datafusion-common = { path = "datafusion/common", version = "37.1.0", default-features = false }
+datafusion-common-runtime = { path = "datafusion/common-runtime", version = "37.1.0" }
+datafusion-execution = { path = "datafusion/execution", version = "37.1.0" }
+datafusion-expr = { path = "datafusion/expr", version = "37.1.0" }
+datafusion-functions = { path = "datafusion/functions", version = "37.1.0" }
+datafusion-functions-aggregate = { path = "datafusion/functions-aggregate", version = "37.1.0" }
+datafusion-functions-array = { path = "datafusion/functions-array", version = "37.1.0" }
+datafusion-optimizer = { path = "datafusion/optimizer", version = "37.1.0", default-features = false }
+datafusion-physical-expr = { path = "datafusion/physical-expr", version = "37.1.0", default-features = false }
+datafusion-physical-expr-common = { path = "datafusion/physical-expr-common", version = "37.1.0", default-features = false }
+datafusion-physical-plan = { path = "datafusion/physical-plan", version = "37.1.0" }
+datafusion-proto = { path = "datafusion/proto", version = "37.1.0" }
+datafusion-sql = { path = "datafusion/sql", version = "37.1.0" }
+datafusion-sqllogictest = { path = "datafusion/sqllogictest", version = "37.1.0" }
+datafusion-substrait = { path = "datafusion/substrait", version = "37.1.0" }
 doc-comment = "0.3"
 env_logger = "0.11"
 futures = "0.3"
@@ -126,3 +126,7 @@ opt-level = 3
 overflow-checks = false
 panic = 'unwind'
 rpath = false
+
+[workspace.lints.clippy]
+# Detects large stack-allocated futures that may cause stack overflow crashes (see threshold in clippy.toml)
+large_futures = "warn"

README.md

@@ -17,7 +17,7 @@
   under the License.
 -->
 
-# DataFusion
+# Apache DataFusion
 
 [![Crates.io][crates-badge]][crates-url]
 [![Apache licensed][license-badge]][license-url]
@@ -40,7 +40,7 @@
 
 <img src="./docs/source/_static/images/2x_bgwhite_original.png" width="512" alt="logo"/>
 
-DataFusion is a very fast, extensible query engine for building high-quality data-centric systems in
+Apache DataFusion is a very fast, extensible query engine for building high-quality data-centric systems in
 [Rust](http://rustlang.org), using the [Apache Arrow](https://arrow.apache.org)
 in-memory format. [Python Bindings](https://github.com/apache/arrow-datafusion-python) are also available. DataFusion offers SQL and Dataframe APIs, excellent [performance](https://benchmark.clickhouse.com/), built-in support for CSV, Parquet, JSON, and Avro, extensive customization, and a great community.
 

benchmarks/Cargo.toml

@@ -26,6 +26,9 @@ repository = { workspace = true }
 license = { workspace = true }
 rust-version = { workspace = true }
 
+[lints]
+workspace = true
+
 [features]
 ci = []
 default = ["mimalloc"]

benchmarks/src/bin/parquet.rs

@@ -25,7 +25,7 @@ use structopt::StructOpt;
 static ALLOC: snmalloc_rs::SnMalloc = snmalloc_rs::SnMalloc;
 
 #[derive(Debug, Clone, StructOpt)]
-#[structopt(name = "Benchmarks", about = "Apache Arrow Rust Benchmarks.")]
+#[structopt(name = "Benchmarks", about = "Apache DataFusion Rust Benchmarks.")]
 enum ParquetBenchCmd {
     /// Benchmark sorting parquet files
     Sort(sort::RunOpt),

clippy.toml

@@ -6,3 +6,7 @@ disallowed-methods = [
 disallowed-types = [
     { path = "std::time::Instant", reason = "Use `datafusion_common::instant::Instant` instead for WASM compatibility" },
 ]
+
+# Lowering the threshold to help prevent stack overflows (default is 16384)
+# See: https://rust-lang.github.io/rust-clippy/master/index.html#/large_futures
+future-size-threshold = 10000