Merge remote-tracking branch 'apache/main' into simply-udf

Author: alamb

.github/workflows/rust.yml

@@ -88,6 +88,9 @@ jobs:
       - name: Check function packages (array_expressions)
         run: cargo check --no-default-features --features=array_expressions -p datafusion
 
+      - name: Check function packages (datetime_expressions)
+        run: cargo check --no-default-features --features=datetime_expressions -p datafusion
+
       - name: Check Cargo.lock for datafusion-cli
         run: |
           # If this test fails, try running `cargo update` in the `datafusion-cli` directory

Cargo.toml

@@ -51,6 +51,11 @@ rust-version = "1.72"
 version = "36.0.0"
 
 [workspace.dependencies]
+# We turn off default-features for some dependencies here so the workspaces which inherit them can
+# selectively turn them on if needed, since we can override default-features = true (from false)
+# for the inherited dependency but cannot do the reverse (override from true to false).
+#
+# See for more detaiils: https://github.com/rust-lang/cargo/issues/11329
 arrow = { version = "50.0.0", features = ["prettyprint"] }
 arrow-array = { version = "50.0.0", default-features = false, features = ["chrono-tz"] }
 arrow-buffer = { version = "50.0.0", default-features = false }
@@ -65,14 +70,14 @@ bytes = "1.4"
 chrono = { version = "0.4.34", default-features = false }
 ctor = "0.2.0"
 dashmap = "5.4.0"
-datafusion = { path = "datafusion/core", version = "36.0.0" }
-datafusion-common = { path = "datafusion/common", version = "36.0.0" }
+datafusion = { path = "datafusion/core", version = "36.0.0", default-features = false }
+datafusion-common = { path = "datafusion/common", version = "36.0.0", default-features = false }
 datafusion-execution = { path = "datafusion/execution", version = "36.0.0" }
 datafusion-expr = { path = "datafusion/expr", version = "36.0.0" }
 datafusion-functions = { path = "datafusion/functions", version = "36.0.0" }
 datafusion-functions-array = { path = "datafusion/functions-array", version = "36.0.0" }
-datafusion-optimizer = { path = "datafusion/optimizer", version = "36.0.0" }
-datafusion-physical-expr = { path = "datafusion/physical-expr", version = "36.0.0" }
+datafusion-optimizer = { path = "datafusion/optimizer", version = "36.0.0", default-features = false }
+datafusion-physical-expr = { path = "datafusion/physical-expr", version = "36.0.0", default-features = false }
 datafusion-physical-plan = { path = "datafusion/physical-plan", version = "36.0.0" }
 datafusion-proto = { path = "datafusion/proto", version = "36.0.0" }
 datafusion-sql = { path = "datafusion/sql", version = "36.0.0" }
@@ -81,7 +86,7 @@ datafusion-substrait = { path = "datafusion/substrait", version = "36.0.0" }
 doc-comment = "0.3"
 env_logger = "0.11"
 futures = "0.3"
-half = "2.2.1"
+half = { version = "2.2.1", default-features = false }
 indexmap = "2.0.0"
 itertools = "0.12"
 log = "^0.4"

README.md

@@ -78,6 +78,7 @@ Default features:
 - `array_expressions`: functions for working with arrays such as `array_to_string`
 - `compression`: reading files compressed with `xz2`, `bzip2`, `flate2`, and `zstd`
 - `crypto_expressions`: cryptographic functions such as `md5` and `sha256`
+- `datetime_expressions`: date and time functions such as `to_timestamp`
 - `encoding_expressions`: `encode` and `decode` functions
 - `parquet`: support for reading the [Apache Parquet] format
 - `regex_expressions`: regular expression functions, such as `regexp_match`

benchmarks/Cargo.toml

@@ -18,12 +18,12 @@
 [package]
 name = "datafusion-benchmarks"
 description = "DataFusion Benchmarks"
-version = "36.0.0"
+version = { workspace = true }
 edition = { workspace = true }
-authors = ["Apache Arrow <dev@arrow.apache.org>"]
-homepage = "https://github.com/apache/arrow-datafusion"
-repository = "https://github.com/apache/arrow-datafusion"
-license = "Apache-2.0"
+authors = { workspace = true }
+homepage = { workspace = true }
+repository = { workspace = true }
+license = { workspace = true }
 rust-version = { workspace = true }
 
 [features]
@@ -33,8 +33,8 @@ snmalloc = ["snmalloc-rs"]
 
 [dependencies]
 arrow = { workspace = true }
-datafusion = { path = "../datafusion/core", version = "36.0.0" }
-datafusion-common = { path = "../datafusion/common", version = "36.0.0" }
+datafusion = { workspace = true, default-features = true }
+datafusion-common = { workspace = true, default-features = true }
 env_logger = { workspace = true }
 futures = { workspace = true }
 log = { workspace = true }
@@ -49,4 +49,4 @@ test-utils = { path = "../test-utils/", version = "0.1.0" }
 tokio = { workspace = true, features = ["rt-multi-thread", "parking_lot"] }
 
 [dev-dependencies]
-datafusion-proto = { path = "../datafusion/proto", version = "36.0.0" }
+datafusion-proto = { workspace = true }

benchmarks/src/clickbench.rs

@@ -16,13 +16,14 @@
 // under the License.
 
 use std::path::Path;
-use std::{path::PathBuf, time::Instant};
+use std::path::PathBuf;
 
 use datafusion::{
     error::{DataFusionError, Result},
     prelude::SessionContext,
 };
 use datafusion_common::exec_datafusion_err;
+use datafusion_common::instant::Instant;
 use structopt::StructOpt;
 
 use crate::{BenchmarkRun, CommonOpt};

benchmarks/src/parquet_filter.rs

@@ -24,8 +24,8 @@ use datafusion::logical_expr::{lit, or, Expr};
 use datafusion::physical_plan::collect;
 use datafusion::prelude::{col, SessionContext};
 use datafusion::test_util::parquet::{ParquetScanOptions, TestParquetFile};
+use datafusion_common::instant::Instant;
 use std::path::PathBuf;
-use std::time::Instant;
 use structopt::StructOpt;
 
 /// Test performance of parquet filter pushdown

benchmarks/src/sort.rs

@@ -25,9 +25,9 @@ use datafusion::physical_plan::collect;
 use datafusion::physical_plan::sorts::sort::SortExec;
 use datafusion::prelude::{SessionConfig, SessionContext};
 use datafusion::test_util::parquet::TestParquetFile;
+use datafusion_common::instant::Instant;
 use std::path::PathBuf;
 use std::sync::Arc;
-use std::time::Instant;
 use structopt::StructOpt;
 
 /// Test performance of sorting large datasets

benchmarks/src/tpch/convert.rs

@@ -15,12 +15,12 @@
 // specific language governing permissions and limitations
 // under the License.
 
+use datafusion_common::instant::Instant;
 use std::fs;
 use std::path::{Path, PathBuf};
-use std::time::Instant;
 
 use datafusion::common::not_impl_err;
-use datafusion::error::DataFusionError;
+
 use datafusion::error::Result;
 use datafusion::prelude::*;
 use parquet::basic::Compression;

benchmarks/src/tpch/mod.rs

@@ -21,7 +21,7 @@ use arrow::datatypes::SchemaBuilder;
 use datafusion::{
     arrow::datatypes::{DataType, Field, Schema},
     common::plan_err,
-    error::{DataFusionError, Result},
+    error::Result,
 };
 use std::fs;
 mod run;

benchmarks/src/tpch/run.rs

@@ -31,9 +31,9 @@ use datafusion::physical_plan::{collect, displayable};
 use datafusion_common::{DEFAULT_CSV_EXTENSION, DEFAULT_PARQUET_EXTENSION};
 use log::info;
 
+use datafusion_common::instant::Instant;
 use std::path::PathBuf;
 use std::sync::Arc;
-use std::time::Instant;
 
 use datafusion::error::Result;
 use datafusion::prelude::*;