Merge pull request #54800 from Avogar/update-arrow

Update arrow to release-13.0.0

contrib/arrow

@@ -1 +1 @@
-Subproject commit 1d93838f69a802639ca144ea5704a98e2481810d
+Subproject commit ba5c67934e8274d649befcffab56731632dc5253

contrib/arrow-cmake/CMakeLists.txt

@@ -230,6 +230,8 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/array/builder_nested.cc"
         "${LIBRARY_DIR}/array/builder_primitive.cc"
         "${LIBRARY_DIR}/array/builder_union.cc"
+        "${LIBRARY_DIR}/array/builder_run_end.cc"
+        "${LIBRARY_DIR}/array/array_run_end.cc"
         "${LIBRARY_DIR}/array/concatenate.cc"
         "${LIBRARY_DIR}/array/data.cc"
         "${LIBRARY_DIR}/array/diff.cc"
@@ -309,9 +311,12 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/util/debug.cc"
         "${LIBRARY_DIR}/util/tracing.cc"
         "${LIBRARY_DIR}/util/atfork_internal.cc"
+        "${LIBRARY_DIR}/util/crc32.cc"
+        "${LIBRARY_DIR}/util/hashing.cc"
+        "${LIBRARY_DIR}/util/ree_util.cc"
+        "${LIBRARY_DIR}/util/union_util.cc"
         "${LIBRARY_DIR}/vendored/base64.cpp"
         "${LIBRARY_DIR}/vendored/datetime/tz.cpp"
-
         "${LIBRARY_DIR}/vendored/musl/strptime.c"
         "${LIBRARY_DIR}/vendored/uriparser/UriCommon.c"
         "${LIBRARY_DIR}/vendored/uriparser/UriCompare.c"
@@ -328,39 +333,20 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/vendored/uriparser/UriRecompose.c"
         "${LIBRARY_DIR}/vendored/uriparser/UriResolve.c"
         "${LIBRARY_DIR}/vendored/uriparser/UriShorten.c"
+        "${LIBRARY_DIR}/vendored/double-conversion/bignum.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/bignum-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/cached-powers.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/double-to-string.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/fast-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/fixed-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/string-to-double.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/strtod.cc"
 
         "${LIBRARY_DIR}/compute/api_aggregate.cc"
         "${LIBRARY_DIR}/compute/api_scalar.cc"
         "${LIBRARY_DIR}/compute/api_vector.cc"
         "${LIBRARY_DIR}/compute/cast.cc"
         "${LIBRARY_DIR}/compute/exec.cc"
-        "${LIBRARY_DIR}/compute/exec/accumulation_queue.cc"
-        "${LIBRARY_DIR}/compute/exec/accumulation_queue.h"
-        "${LIBRARY_DIR}/compute/exec/aggregate.cc"
-        "${LIBRARY_DIR}/compute/exec/aggregate_node.cc"
-        "${LIBRARY_DIR}/compute/exec/asof_join_node.cc"
-        "${LIBRARY_DIR}/compute/exec/bloom_filter.cc"
-        "${LIBRARY_DIR}/compute/exec/exec_plan.cc"
-        "${LIBRARY_DIR}/compute/exec/expression.cc"
-        "${LIBRARY_DIR}/compute/exec/filter_node.cc"
-        "${LIBRARY_DIR}/compute/exec/hash_join.cc"
-        "${LIBRARY_DIR}/compute/exec/hash_join_dict.cc"
-        "${LIBRARY_DIR}/compute/exec/hash_join_node.cc"
-        "${LIBRARY_DIR}/compute/exec/key_hash.cc"
-        "${LIBRARY_DIR}/compute/exec/key_map.cc"
-        "${LIBRARY_DIR}/compute/exec/map_node.cc"
-        "${LIBRARY_DIR}/compute/exec/options.cc"
-        "${LIBRARY_DIR}/compute/exec/order_by_impl.cc"
-        "${LIBRARY_DIR}/compute/exec/partition_util.cc"
-        "${LIBRARY_DIR}/compute/exec/project_node.cc"
-        "${LIBRARY_DIR}/compute/exec/query_context.cc"
-        "${LIBRARY_DIR}/compute/exec/sink_node.cc"
-        "${LIBRARY_DIR}/compute/exec/source_node.cc"
-        "${LIBRARY_DIR}/compute/exec/swiss_join.cc"
-        "${LIBRARY_DIR}/compute/exec/task_util.cc"
-        "${LIBRARY_DIR}/compute/exec/tpch_node.cc"
-        "${LIBRARY_DIR}/compute/exec/union_node.cc"
-        "${LIBRARY_DIR}/compute/exec/util.cc"
         "${LIBRARY_DIR}/compute/function.cc"
         "${LIBRARY_DIR}/compute/function_internal.cc"
         "${LIBRARY_DIR}/compute/kernel.cc"
@@ -403,8 +389,13 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/compute/kernels/vector_select_k.cc"
         "${LIBRARY_DIR}/compute/kernels/vector_selection.cc"
         "${LIBRARY_DIR}/compute/kernels/vector_sort.cc"
+        "${LIBRARY_DIR}/compute/kernels/vector_selection_internal.cc"
+        "${LIBRARY_DIR}/compute/kernels/vector_selection_filter_internal.cc"
+        "${LIBRARY_DIR}/compute/kernels/vector_selection_take_internal.cc"
         "${LIBRARY_DIR}/compute/light_array.cc"
         "${LIBRARY_DIR}/compute/registry.cc"
+        "${LIBRARY_DIR}/compute/expression.cc"
+        "${LIBRARY_DIR}/compute/ordering.cc"
         "${LIBRARY_DIR}/compute/row/compare_internal.cc"
         "${LIBRARY_DIR}/compute/row/encode_internal.cc"
         "${LIBRARY_DIR}/compute/row/grouper.cc"
@@ -488,10 +479,10 @@ set(PARQUET_SRCS
         "${LIBRARY_DIR}/exception.cc"
         "${LIBRARY_DIR}/file_reader.cc"
         "${LIBRARY_DIR}/file_writer.cc"
+        "${LIBRARY_DIR}/page_index.cc"
         "${LIBRARY_DIR}/level_conversion.cc"
         "${LIBRARY_DIR}/level_comparison.cc"
         "${LIBRARY_DIR}/metadata.cc"
-        "${LIBRARY_DIR}/murmur3.cc"
         "${LIBRARY_DIR}/platform.cc"
         "${LIBRARY_DIR}/printer.cc"
         "${LIBRARY_DIR}/properties.cc"
@@ -500,6 +491,8 @@ set(PARQUET_SRCS
         "${LIBRARY_DIR}/stream_reader.cc"
         "${LIBRARY_DIR}/stream_writer.cc"
         "${LIBRARY_DIR}/types.cc"
+        "${LIBRARY_DIR}/bloom_filter_reader.cc"
+        "${LIBRARY_DIR}/xxhasher.cc"
 
         "${GEN_LIBRARY_DIR}/parquet_constants.cpp"
         "${GEN_LIBRARY_DIR}/parquet_types.cpp"

tests/queries/0_stateless/02735_parquet_encoder.reference

@@ -36,11 +36,11 @@ ipv6	Nullable(FixedString(16))
 1	1000000	1
 3914219105369203805
 4	1000000	1
-(1000000,0,NULL,'100','299')
+(1000000,NULL,NULL,'100','299')
-(1000000,0,NULL,'0','-1294970296')
+(1000000,NULL,NULL,'0','-1294970296')
-(1000000,0,NULL,'-2147483296','2147481000')
+(1000000,NULL,NULL,'-2147483296','2147481000')
 (100000,900000,NULL,'100009','999999')
-[(2,0,NULL,'','[]')]
+[(2,NULL,NULL,'','[]')]
 1	1
 0	1
 5090915589685802007

tests/queries/0_stateless/02884_parquet_new_encodings.reference

@@ -0,0 +1 @@
+SWEEP	SWETT	00459	\N	('20221206100111','+0100')	('20221206100111','+0100')	('20221206100111','+0100')	3	11	T	\N

tests/queries/0_stateless/02884_parquet_new_encodings.sh

@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Tags: no-fasttest
+
+CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CURDIR"/../shell_config.sh
+
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_parquet/delta_length_byte_array_encoding.parquet')"
+