Merge branch 'main' into fast_sort_with_inlined_fast_key

Author: zhuqi-lucas

Cargo.lock

@@ -89,20 +89,20 @@ ahash = { version = "0.8", default-features = false, features = [
     "runtime-rng",
 ] }
 apache-avro = { version = "0.17", default-features = false }
-arrow = { version = "55.1.0", features = [
+arrow = { version = "55.2.0", features = [
     "prettyprint",
     "chrono-tz",
 ] }
-arrow-buffer = { version = "55.0.0", default-features = false }
-arrow-flight = { version = "55.1.0", features = [
+arrow-buffer = { version = "55.2.0", default-features = false }
+arrow-flight = { version = "55.2.0", features = [
     "flight-sql-experimental",
 ] }
-arrow-ipc = { version = "55.0.0", default-features = false, features = [
+arrow-ipc = { version = "55.2.0", default-features = false, features = [
     "lz4",
     "zstd",
 ] }
-arrow-ord = { version = "55.0.0", default-features = false }
-arrow-schema = { version = "55.0.0", default-features = false }
+arrow-ord = { version = "55.2.0", default-features = false }
+arrow-schema = { version = "55.2.0", default-features = false }
 async-trait = "0.1.88"
 bigdecimal = "0.4.8"
 bytes = "1.10"
@@ -155,7 +155,7 @@ itertools = "0.14"
 log = "^0.4"
 object_store = { version = "0.12.2", default-features = false }
 parking_lot = "0.12"
-parquet = { version = "55.1.0", default-features = false, features = [
+parquet = { version = "55.2.0", default-features = false, features = [
     "arrow",
     "async",
     "object_store",

Cargo.toml

@@ -280,7 +280,7 @@ physical_plan
 06)┌─────────────┴─────────────┐
 07)│       DataSourceExec      │
 08)│    --------------------   │
-09)│        bytes: 1072        │
+09)│        bytes: 1040        │
 10)│       format: memory      │
 11)│          rows: 2          │
 12)└───────────────────────────┘
@@ -360,7 +360,7 @@ physical_plan
 21)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
 22)│       DataSourceExec      ││       ProjectionExec      │
 23)│    --------------------   ││    --------------------   │
-24)│         bytes: 536        ││     date_col: date_col    │
+24)│         bytes: 520        ││     date_col: date_col    │
 25)│       format: memory      ││      int_col: int_col     │
 26)│          rows: 1          ││                           │
 27)│                           ││        string_col:        │
@@ -655,7 +655,7 @@ physical_plan
 13)┌─────────────┴─────────────┐
 14)│       DataSourceExec      │
 15)│    --------------------   │
-16)│         bytes: 536        │
+16)│         bytes: 520        │
 17)│       format: memory      │
 18)│          rows: 1          │
 19)└───────────────────────────┘
@@ -1041,7 +1041,7 @@ physical_plan
 13)┌─────────────┴─────────────┐
 14)│       DataSourceExec      │
 15)│    --------------------   │
-16)│         bytes: 536        │
+16)│         bytes: 520        │
 17)│       format: memory      │
 18)│          rows: 1          │
 19)└───────────────────────────┘

datafusion/sqllogictest/test_files/explain_tree.slt

@@ -61,7 +61,7 @@ logical_plan
 physical_plan
 01)CoalesceBatchesExec: target_batch_size=8192
 02)--FilterExec: column1@0 != 42
-03)----DataSourceExec: 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], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..141], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:141..282], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:282..423], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:423..563]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != 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)----DataSourceExec: 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], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+03)----DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..141], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:141..282], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:282..423], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:423..563]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != 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)--------DataSourceExec: 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], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+05)--------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..280], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:280..554, 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..286], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:286..563]]}, projection=[column1], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != 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)------DataSourceExec: 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], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
+04)------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:0..277], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:0..281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/2.parquet:281..563], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition_scan/parquet_table/1.parquet:277..554]]}, projection=[column1], output_ordering=[column1@0 ASC NULLS LAST], file_type=parquet, predicate=column1@0 != 42, pruning_predicate=column1_null_count@2 != row_count@3 AND (column1_min@0 != 42 OR 42 != column1_max@1), required_guarantees=[column1 not in (42)]
 
 # Cleanup
 statement ok

datafusion/sqllogictest/test_files/repartition_scan.slt

@@ -36,7 +36,7 @@ types of UDFs.
 
 ## Adding a Scalar UDF
 
-A Scalar UDF is a function that takes a row of data and returns a single value. In order for good performance
+A Scalar UDF is a function that takes a row of data and returns a single value. To achieve good performance,
 such functions are "vectorized" in DataFusion, meaning they get one or more Arrow Arrays as input and produce
 an Arrow Array with the same number of rows as output.
 
@@ -48,8 +48,8 @@ To create a Scalar UDF, you
 
 In the following example, we will add a function takes a single i64 and returns a single i64 with 1 added to it:
 
-For brevity, we'll skipped some error handling, but e.g. you may want to check that `args.len()` is the expected number
-of arguments.
+For brevity, we'll skip some error handling.
+For production code, you may want to check, for example, that `args.len()` matches the expected number of arguments.
 
 ### Adding by `impl ScalarUDFImpl`