test: update tests for new config prop, as well as the new file parti…

…tion offsets based upon larger metadata

datafusion/sqllogictest/test_files/information_schema.slt

@@ -215,6 +215,7 @@ datafusion.execution.parquet.pruning true
 datafusion.execution.parquet.pushdown_filters false
 datafusion.execution.parquet.reorder_filters false
 datafusion.execution.parquet.schema_force_view_types true
+datafusion.execution.parquet.skip_arrow_metadata false
 datafusion.execution.parquet.skip_metadata true
 datafusion.execution.parquet.statistics_enabled page
 datafusion.execution.parquet.write_batch_size 1024
@@ -308,6 +309,7 @@ datafusion.execution.parquet.pruning true (reading) If true, the parquet reader
 datafusion.execution.parquet.pushdown_filters false (reading) If true, filter expressions are be applied during the parquet decoding operation to reduce the number of rows decoded. This optimization is sometimes called "late materialization".
 datafusion.execution.parquet.reorder_filters false (reading) If true, filter expressions evaluated during the parquet decoding operation will be reordered heuristically to minimize the cost of evaluation. If false, the filters are applied in the same order as written in the query
 datafusion.execution.parquet.schema_force_view_types true (reading) If true, parquet reader will read columns of `Utf8/Utf8Large` with `Utf8View`, and `Binary/BinaryLarge` with `BinaryView`.
+datafusion.execution.parquet.skip_arrow_metadata false (writing) Skip encoding the embedded arrow metadata in the KV_meta This is analogous to the `ArrowWriterOptions::with_skip_arrow_metadata`. Refer to <https://docs.rs/parquet/53.3.0/parquet/arrow/arrow_writer/struct.ArrowWriterOptions.html#method.with_skip_arrow_metadata>
 datafusion.execution.parquet.skip_metadata true (reading) If true, the parquet reader skip the optional embedded metadata that may be in the file Schema. This setting can help avoid schema conflicts when querying multiple parquet files with schemas containing compatible types but different metadata
 datafusion.execution.parquet.statistics_enabled page (writing) Sets if statistics are enabled for any column Valid values are: "none", "chunk", and "page" These values are not case sensitive. If NULL, uses default parquet writer setting
 datafusion.execution.parquet.write_batch_size 1024 (writing) Sets write_batch_size in bytes

datafusion/sqllogictest/test_files/repartition_scan.slt

@@ -61,7 +61,7 @@ logical_plan
 physical_plan
 01)CoalesceBatchesExec: target_batch_size=8192
 02)--FilterExec: column1@0 != 42
-03)----ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..88], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:88..176], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:176..264], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:264..351]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+03)----ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..137], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:137..274], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:274..411], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:411..547]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
 
 # disable round robin repartitioning
 statement ok
@@ -77,7 +77,7 @@ logical_plan
 physical_plan
 01)CoalesceBatchesExec: target_batch_size=8192
 02)--FilterExec: column1@0 != 42
-03)----ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..88], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:88..176], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:176..264], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:264..351]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+03)----ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..137], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:137..274], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:274..411], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:411..547]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
 
 # enable round robin repartitioning again
 statement ok
@@ -102,7 +102,7 @@ physical_plan
 02)--SortExec: expr=[column1@0 ASC NULLS LAST], preserve_partitioning=[true]
 03)----CoalesceBatchesExec: target_batch_size=8192
 04)------FilterExec: column1@0 != 42
-05)--------ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..174], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:174..342, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..6], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:6..180], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:180..351]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+05)--------ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..272], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:272..538, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..6], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:6..278], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:278..547]]}, projection=[column1], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
 
 
 ## Read the files as though they are ordered
@@ -138,7 +138,7 @@ physical_plan
 01)SortPreservingMergeExec: [column1@0 ASC NULLS LAST]
 02)--CoalesceBatchesExec: target_batch_size=8192
 03)----FilterExec: column1@0 != 42
-04)------ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..171], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..175], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:175..351], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:171..342]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+04)------ParquetExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..269], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..273], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:273..547], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:269..538]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != column1_row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
 
 # Cleanup
 statement ok