perf: factor common guards out of pruning predicates

datafusion/sqllogictest/test_files/limit_pruning.slt

@@ -120,7 +120,7 @@ explain analyze select * from tracking_data where species > 'M' AND s >= 50 orde
 ----
 Plan with Metrics
 01)SortExec: TopK(fetch=3), expr=[species@0 ASC NULLS LAST], preserve_partitioning=[false], filter=[species@0 < Nlpine Sheep], metrics=[output_rows=3, elapsed_compute=<slt:ignore>, output_bytes=<slt:ignore>]
-02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/limit_pruning/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_null_count@1 != row_count@2 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=<slt:ignore>, output_bytes=<slt:ignore>, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, row_groups_pruned_bloom_filter=3 total → 3 matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, bytes_processed=<slt:ignore>, bytes_scanned=<slt:ignore>, row_groups_pruned_dynamic_filter=0, metadata_load_time=<slt:ignore>, scan_efficiency_ratio=<slt:ignore> (<slt:ignore>/<slt:ignore>)]
+02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/limit_pruning/data.parquet]]}, projection=[species, s], file_type=parquet, predicate=species@0 > M AND s@1 >= 50 AND DynamicFilter [ species@0 < Nlpine Sheep ], sort_order_for_reorder=[species@0 ASC NULLS LAST], dynamic_rg_pruning=eligible, pruning_predicate=species_null_count@1 != row_count@2 AND species_max@0 > M AND s_null_count@4 != row_count@2 AND s_max@3 >= 50 AND species_min@5 < Nlpine Sheep, required_guarantees=[], metrics=[output_rows=3, elapsed_compute=<slt:ignore>, output_bytes=<slt:ignore>, files_ranges_pruned_statistics=1 total → 1 matched, row_groups_pruned_statistics=4 total → 3 matched -> 1 fully matched, row_groups_pruned_bloom_filter=3 total → 3 matched, page_index_pages_pruned=2 total → 2 matched, page_index_pages_skipped_by_fully_matched=1, limit_pruned_row_groups=0 total → 0 matched, bytes_processed=<slt:ignore>, bytes_scanned=<slt:ignore>, row_groups_pruned_dynamic_filter=0, metadata_load_time=<slt:ignore>, scan_efficiency_ratio=<slt:ignore> (<slt:ignore>/<slt:ignore>)]
 
 statement ok
 drop table tracking_data;

datafusion/sqllogictest/test_files/parquet_filter_pushdown.slt

@@ -494,7 +494,7 @@ EXPLAIN select * from t_pushdown where val != 'd' AND val != 'c' AND part = 'a'
 logical_plan
 01)Filter: t_pushdown.val != Utf8View("d") AND t_pushdown.val != Utf8View("c") AND t_pushdown.val != t_pushdown.part
 02)--TableScan: t_pushdown projection=[val, part], full_filters=[t_pushdown.part = Utf8View("a")], partial_filters=[t_pushdown.val != Utf8View("d"), t_pushdown.val != Utf8View("c"), t_pushdown.val != t_pushdown.part]
-physical_plan DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/parquet_filter_pushdown/parquet_part_test/part=a/file.parquet]]}, projection=[val, part], file_type=parquet, predicate=val@0 != d AND val@0 != c AND val@0 != part@1, pruning_predicate=val_null_count@2 != row_count@3 AND (val_min@0 != d OR d != val_max@1) AND val_null_count@2 != row_count@3 AND (val_min@0 != c OR c != val_max@1), required_guarantees=[val not in (c, d)]
+physical_plan DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/parquet_filter_pushdown/parquet_part_test/part=a/file.parquet]]}, projection=[val, part], file_type=parquet, predicate=val@0 != d AND val@0 != c AND val@0 != part@1, pruning_predicate=val_null_count@2 != row_count@3 AND (val_min@0 != d OR d != val_max@1) AND (val_min@0 != c OR c != val_max@1), required_guarantees=[val not in (c, d)]
 
 # The order of filters should not matter
 query TT

datafusion/sqllogictest/test_files/projection_pushdown.slt

@@ -1163,7 +1163,7 @@ logical_plan
 physical_plan
 01)ProjectionExec: expr=[__datafusion_extracted_1@0 as simple_struct.s[value]]
 02)--FilterExec: id@1 > 1 AND (id@1 < 4 OR id@1 = 5), projection=[__datafusion_extracted_1@0]
-03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/projection_pushdown/simple.parquet]]}, projection=[get_field(s@1, value) as __datafusion_extracted_1, id], file_type=parquet, predicate=id@0 > 1 AND (id@0 < 4 OR id@0 = 5), pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 > 1 AND (id_null_count@1 != row_count@2 AND id_min@3 < 4 OR id_null_count@1 != row_count@2 AND id_min@3 <= 5 AND 5 <= id_max@0), required_guarantees=[]
+03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/projection_pushdown/simple.parquet]]}, projection=[get_field(s@1, value) as __datafusion_extracted_1, id], file_type=parquet, predicate=id@0 > 1 AND (id@0 < 4 OR id@0 = 5), pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 > 1 AND (id_min@3 < 4 OR id_min@3 <= 5 AND 5 <= id_max@0), required_guarantees=[]
 
 # Verify correctness - should return rows where (id > 1) AND ((id < 4) OR (id = 5))
 # That's: id=2,3 (1<id<4) and id=5 (id=5 from second branch)
@@ -1185,7 +1185,7 @@ logical_plan
 physical_plan
 01)ProjectionExec: expr=[__datafusion_extracted_1@0 as simple_struct.s[value]]
 02)--FilterExec: id@1 > 1 AND id@1 < 5, projection=[__datafusion_extracted_1@0]
-03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/projection_pushdown/simple.parquet]]}, projection=[get_field(s@1, value) as __datafusion_extracted_1, id], file_type=parquet, predicate=id@0 > 1 AND id@0 < 5, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 > 1 AND id_null_count@1 != row_count@2 AND id_min@3 < 5, required_guarantees=[]
+03)----DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/projection_pushdown/simple.parquet]]}, projection=[get_field(s@1, value) as __datafusion_extracted_1, id], file_type=parquet, predicate=id@0 > 1 AND id@0 < 5, pruning_predicate=id_null_count@1 != row_count@2 AND id_max@0 > 1 AND id_min@3 < 5, required_guarantees=[]
 
 # Verify correctness - should return rows where 1 < id < 5 (id=2,3,4)
 query I