Estimate IN and NOT IN selectivity from the listed values #25621

cargo build --profile ci --locked -p datafusion-benchmarks --bin dfbench
repro_dir=$(mktemp -d)
mkdir -p "$repro_dir/data"
curl --fail --location \
  https://raw.githubusercontent.com/apache/datafusion-benchmarks/32f67477f692453616d2fa98a05a37c5eb4cae49/tpcds/data/sf1/date_dim.parquet \
  -o "$repro_dir/data/date_dim.parquet"
cat > "$repro_dir/repro.sql" <<'SQL'
SET datafusion.execution.target_partitions = 1;
SET datafusion.optimizer.enable_dynamic_filter_pushdown = false;
SELECT d_date_sk FROM date_dim WHERE d_moy IN (1, 2, 3);
SELECT d_date_sk FROM date_dim WHERE d_moy BETWEEN 1 AND 3;
SELECT d_date_sk FROM date_dim WHERE d_moy NOT IN (1, 2, 3);
SELECT d_date_sk FROM date_dim
WHERE d_moy IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12);
SELECT d_date_sk FROM date_dim
WHERE d_moy NOT IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12);
SQL
target/ci/dfbench statistics \
  --path "$repro_dir/data" --query_path "$repro_dir/repro.sql"