apache · andygrove · Apr 1, 2026
diff --git a/.claude/skills/review-comet-pr/SKILL.md b/.claude/skills/review-comet-pr/SKILL.md
@@ -149,8 +149,6 @@ Categories include: `aggregate/`, `array/`, `string/`, `math/`, `struct/`, `map/
 **SQL file structure:**
 
 ```sql
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 -- Create test data
 statement
 CREATE TABLE test_crc32(col string, a int, b float) USING parquet

diff --git a/docs/source/contributor-guide/adding_a_new_expression.md b/docs/source/contributor-guide/adding_a_new_expression.md
@@ -217,8 +217,6 @@ It is important to verify that the new expression is correctly recognized by the
 Create a `.sql` file under the appropriate subdirectory in `spark/src/test/resources/sql-tests/expressions/` (e.g., `string/`, `math/`, `array/`). The file should create a table with test data, then run queries that exercise the expression. Here is an example for the `unhex` expression:
 
 ```sql
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_unhex(col string) USING parquet
 

diff --git a/docs/source/contributor-guide/sql-file-tests.md b/docs/source/contributor-guide/sql-file-tests.md
@@ -76,8 +76,6 @@ A test file consists of SQL comments, directives, statements, and queries separa
 lines. Here is a minimal example:
 
 ```sql
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_abs(v double) USING parquet
 
@@ -106,16 +104,19 @@ Runs the entire file once per combination of values. Multiple `ConfigMatrix` lin
 cross product of all combinations.
 
 ```sql
--- ConfigMatrix: parquet.enable.dictionary=false,true
+-- ConfigMatrix: spark.sql.optimizer.inSetConversionThreshold=100,0
 ```
 
 This generates two test cases:
 
 ```
-sql-file: expressions/cast/cast.sql [parquet.enable.dictionary=false]
-sql-file: expressions/cast/cast.sql [parquet.enable.dictionary=true]
+sql-file: expressions/conditional/in_set.sql [spark.sql.optimizer.inSetConversionThreshold=100]
+sql-file: expressions/conditional/in_set.sql [spark.sql.optimizer.inSetConversionThreshold=0]
 ```
 
+Only add a `ConfigMatrix` directive when there is a real reason to run the test under
+multiple configurations. Do not add `ConfigMatrix` directives speculatively.
+
 #### `MinSparkVersion`
 
 Skips the file when running on a Spark version older than the specified version.
@@ -223,12 +224,9 @@ SELECT array(1, 2, 3)[10]
 
 2. Add the Apache license header as a SQL comment.
 
-3. Add a `ConfigMatrix` directive if the test should run with multiple Parquet configurations.
-   Most expression tests use:
-
-   ```sql
-   -- ConfigMatrix: parquet.enable.dictionary=false,true
-   ```
+3. Add a `ConfigMatrix` directive only if the test needs to run under multiple configurations
+   (e.g., testing behavior that varies with a specific Spark config). Do not add `ConfigMatrix`
+   directives speculatively.
 
 4. Create tables and insert test data using `statement` blocks. Include edge cases such as
    `NULL`, boundary values, and negative numbers.

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/aggregate_filter.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/aggregate_filter.sql
@@ -83,4 +83,3 @@ SELECT AVG(d) FILTER (WHERE flag = true) FROM test_agg_filter
 
 query spark_answer_only
 SELECT grp, AVG(d) FILTER (WHERE flag = true) FROM test_agg_filter GROUP BY grp ORDER BY grp
-
diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/avg.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/avg.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_avg(i int, l long, f float, d double, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/bit_agg.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/bit_agg.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_bit_agg(i int, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/corr.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/corr.sql
@@ -16,7 +16,6 @@
 -- under the License.
 
 -- Config: spark.comet.expression.Corr.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_corr(x double, y double, grp string) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/count.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/count.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_count(i int, s string, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/covariance.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/covariance.sql
@@ -1,3 +1,4 @@
+
 -- Licensed to the Apache Software Foundation (ASF) under one
 -- or more contributor license agreements.  See the NOTICE file
 -- distributed with this work for additional information
@@ -15,8 +16,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_covar(x double, y double, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/first_last.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/first_last.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_first_last(i int, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/min_max.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/min_max.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_min_max(i int, d double, s string, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/stddev.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/stddev.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_stddev(d double, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/sum.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/sum.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_sum(i int, l long, f float, d double, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/aggregate/variance.sql b/spark/src/test/resources/sql-tests/expressions/aggregate/variance.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_variance(d double, grp string) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_append.sql b/spark/src/test/resources/sql-tests/expressions/array/array_append.sql
@@ -18,7 +18,6 @@
 -- On Spark 4.0, array_append is a RuntimeReplaceable that rewrites to array_insert(-1),
 -- so we need to allow the incompatible array_insert to run natively there.
 -- Config: spark.comet.expression.ArrayInsert.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_array_append(arr array<int>, val int) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_compact.sql b/spark/src/test/resources/sql-tests/expressions/array/array_compact.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_compact(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_concat.sql b/spark/src/test/resources/sql-tests/expressions/array/array_concat.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 -- migrated from CometExpressionSuite "test concat function - arrays"
 -- https://github.com/apache/datafusion-comet/issues/2647
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_contains.sql b/spark/src/test/resources/sql-tests/expressions/array/array_contains.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_contains(arr array<int>, val int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_distinct.sql b/spark/src/test/resources/sql-tests/expressions/array/array_distinct.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_distinct(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_except.sql b/spark/src/test/resources/sql-tests/expressions/array/array_except.sql
@@ -14,8 +14,8 @@
 -- KIND, either express or implied.  See the License for the
 -- specific language governing permissions and limitations
 -- under the License.
+
 -- Config: spark.comet.expression.ArrayExcept.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_array_except(a array<int>, b array<int>) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_filter.sql b/spark/src/test/resources/sql-tests/expressions/array/array_filter.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_filter(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_insert.sql b/spark/src/test/resources/sql-tests/expressions/array/array_insert.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_insert(arr array<int>, pos int, val int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_intersect.sql b/spark/src/test/resources/sql-tests/expressions/array/array_intersect.sql
@@ -16,7 +16,6 @@
 -- under the License.
 
 -- Config: spark.comet.expression.ArrayIntersect.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_array_intersect(a array<int>, b array<int>) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_join.sql b/spark/src/test/resources/sql-tests/expressions/array/array_join.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_join(arr array<string>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_max.sql b/spark/src/test/resources/sql-tests/expressions/array/array_max.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_max(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_min.sql b/spark/src/test/resources/sql-tests/expressions/array/array_min.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_min(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_remove.sql b/spark/src/test/resources/sql-tests/expressions/array/array_remove.sql
@@ -16,7 +16,6 @@
 -- under the License.
 
 -- Config: spark.comet.expression.ArrayRemove.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_array_remove(arr array<int>, val int) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_repeat.sql b/spark/src/test/resources/sql-tests/expressions/array/array_repeat.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_array_repeat(val int, cnt int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/array_union.sql b/spark/src/test/resources/sql-tests/expressions/array/array_union.sql
@@ -16,7 +16,6 @@
 -- under the License.
 
 -- Config: spark.comet.expression.ArrayUnion.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_array_union(a array<int>, b array<int>) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/arrays_overlap.sql b/spark/src/test/resources/sql-tests/expressions/array/arrays_overlap.sql
@@ -16,7 +16,6 @@
 -- under the License.
 
 -- Config: spark.comet.expression.ArraysOverlap.allowIncompatible=true
--- ConfigMatrix: parquet.enable.dictionary=false,true
 
 statement
 CREATE TABLE test_arrays_overlap(a array<int>, b array<int>) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/array/create_array.sql b/spark/src/test/resources/sql-tests/expressions/array/create_array.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_create_array(a int, b int, c int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/element_at.sql b/spark/src/test/resources/sql-tests/expressions/array/element_at.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_element_at(arr array<int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/flatten.sql b/spark/src/test/resources/sql-tests/expressions/array/flatten.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_flatten(arr array<array<int>>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/get_array_item.sql b/spark/src/test/resources/sql-tests/expressions/array/get_array_item.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_get_array_item(arr array<int>, idx int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/get_array_struct_fields.sql b/spark/src/test/resources/sql-tests/expressions/array/get_array_struct_fields.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_arr_struct(arr array<struct<name: string, value: int>>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/array/size.sql b/spark/src/test/resources/sql-tests/expressions/array/size.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_size(arr array<int>, m map<string, int>) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/bitwise/bitwise.sql b/spark/src/test/resources/sql-tests/expressions/bitwise/bitwise.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 -- Setup
 statement
 CREATE TABLE test(col1 int, col2 int) USING parquet

diff --git a/spark/src/test/resources/sql-tests/expressions/cast/cast.sql b/spark/src/test/resources/sql-tests/expressions/cast/cast.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_cast(i int, l long, f float, d double, s string, b boolean) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/cast/cast_double_to_string.sql b/spark/src/test/resources/sql-tests/expressions/cast/cast_double_to_string.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 statement
 CREATE TABLE test_double_to_string(d double, id int) USING parquet
 

diff --git a/spark/src/test/resources/sql-tests/expressions/conditional/boolean.sql b/spark/src/test/resources/sql-tests/expressions/conditional/boolean.sql
@@ -15,8 +15,6 @@
 -- specific language governing permissions and limitations
 -- under the License.
 
--- ConfigMatrix: parquet.enable.dictionary=false,true
-
 -- compare true/false to negative zero
 statement
 CREATE TABLE test(col1 boolean, col2 float) USING parquet
Original file line number	Diff line number	Diff line change
Expand Up		@@ -83,4 +83,3 @@ SELECT AVG(d) FILTER (WHERE flag = true) FROM test_agg_filter

		query spark_answer_only
		SELECT grp, AVG(d) FILTER (WHERE flag = true) FROM test_agg_filter GROUP BY grp ORDER BY grp