Make regex dependency optional in datafusion-functions, add CI checks for function packages (#9473)

* Make regex dependency optional in datafusion-functions

* Add missing cargo-check tests in CI

* make it optional

* remove uncessary core expressions

* add missing dependency

* format toml

Author: alamb

.github/workflows/rust.yml

@@ -79,17 +79,20 @@ jobs:
 
       # Ensure that the datafusion crate can be built with only a subset of the function
       # packages enabled.
+      - 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 function packages (encoding_expressions)
         run: cargo check --no-default-features --features=encoding_expressions -p datafusion
 
       - name: Check function packages (math_expressions)
         run: cargo check --no-default-features --features=math_expressions -p datafusion
 
-      - 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 function packages (regex_expressions)
+        run: cargo check --no-default-features --features=regex_expressions -p datafusion
 
       - name: Check Cargo.lock for datafusion-cli
         run: |

datafusion/core/Cargo.toml

@@ -60,7 +60,11 @@ force_hash_collisions = []
 math_expressions = ["datafusion-functions/math_expressions"]
 parquet = ["datafusion-common/parquet", "dep:parquet"]
 pyarrow = ["datafusion-common/pyarrow", "parquet"]
-regex_expressions = ["datafusion-physical-expr/regex_expressions", "datafusion-optimizer/regex_expressions"]
+regex_expressions = [
+    "datafusion-physical-expr/regex_expressions",
+    "datafusion-optimizer/regex_expressions",
+    "datafusion-functions/regex_expressions",
+]
 serde = ["arrow-schema/serde"]
 unicode_expressions = [
     "datafusion-physical-expr/unicode_expressions",

datafusion/functions/Cargo.toml

@@ -39,7 +39,8 @@ default = ["core_expressions", "datetime_expressions", "encoding_expressions", "
 encoding_expressions = ["base64", "hex"]
 # enable math functions
 math_expressions = []
-regex_expressions = []
+# enable regular expressions
+regex_expressions = ["regex"]
 
 [lib]
 name = "datafusion_functions"
@@ -59,7 +60,8 @@ datafusion-physical-expr = { workspace = true, default-features = true }
 hex = { version = "0.4", optional = true }
 itertools = { workspace = true }
 log = { workspace = true }
-regex = { version = "1.8" }
+regex = { version = "1.8", optional = true }
+
 [dev-dependencies]
 criterion = "0.5"
 rand = { workspace = true }