Update orc and arrow

.gitmodules

@@ -103,7 +103,7 @@
 	url = https://github.com/ClickHouse-Extras/fastops
 [submodule "contrib/orc"]
 	path = contrib/orc
-	url = https://github.com/apache/orc
+	url = https://github.com/ClickHouse-Extras/orc
 [submodule "contrib/sparsehash-c11"]
 	path = contrib/sparsehash-c11
 	url = https://github.com/sparsehash/sparsehash-c11.git

contrib/arrow

@@ -1 +1 @@
-Subproject commit 616b3dc76a0c8450b4027ded8a78e9619d7c845f
+Subproject commit debf751a129bdda9ff4d1e895e08957ff77000a1

contrib/arrow-cmake/CMakeLists.txt

@@ -188,6 +188,7 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/array/util.cc"
         "${LIBRARY_DIR}/array/validate.cc"
 
+        "${LIBRARY_DIR}/compute/api_aggregate.cc"
         "${LIBRARY_DIR}/compute/api_scalar.cc"
         "${LIBRARY_DIR}/compute/api_vector.cc"
         "${LIBRARY_DIR}/compute/cast.cc"
@@ -198,8 +199,11 @@ set(ARROW_SRCS
 
         "${LIBRARY_DIR}/compute/kernels/aggregate_basic.cc"
         "${LIBRARY_DIR}/compute/kernels/aggregate_mode.cc"
+        "${LIBRARY_DIR}/compute/kernels/aggregate_quantile.cc"
+        "${LIBRARY_DIR}/compute/kernels/aggregate_tdigest.cc"
         "${LIBRARY_DIR}/compute/kernels/aggregate_var_std.cc"
         "${LIBRARY_DIR}/compute/kernels/codegen_internal.cc"
+        "${LIBRARY_DIR}/compute/kernels/hash_aggregate.cc"
         "${LIBRARY_DIR}/compute/kernels/scalar_arithmetic.cc"
         "${LIBRARY_DIR}/compute/kernels/scalar_boolean.cc"
         "${LIBRARY_DIR}/compute/kernels/scalar_cast_boolean.cc"
@@ -243,6 +247,7 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/io/interfaces.cc"
         "${LIBRARY_DIR}/io/memory.cc"
         "${LIBRARY_DIR}/io/slow.cc"
+        "${LIBRARY_DIR}/io/transform.cc"
 
         "${LIBRARY_DIR}/tensor/coo_converter.cc"
         "${LIBRARY_DIR}/tensor/csf_converter.cc"
@@ -256,11 +261,8 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/util/bitmap_builders.cc"
         "${LIBRARY_DIR}/util/bitmap_ops.cc"
         "${LIBRARY_DIR}/util/bpacking.cc"
+        "${LIBRARY_DIR}/util/cancel.cc"
         "${LIBRARY_DIR}/util/compression.cc"
-        "${LIBRARY_DIR}/util/compression_lz4.cc"
-        "${LIBRARY_DIR}/util/compression_snappy.cc"
-        "${LIBRARY_DIR}/util/compression_zlib.cc"
-        "${LIBRARY_DIR}/util/compression_zstd.cc"
         "${LIBRARY_DIR}/util/cpu_info.cc"
         "${LIBRARY_DIR}/util/decimal.cc"
         "${LIBRARY_DIR}/util/delimiting.cc"
@@ -268,20 +270,33 @@ set(ARROW_SRCS
         "${LIBRARY_DIR}/util/future.cc"
         "${LIBRARY_DIR}/util/int_util.cc"
         "${LIBRARY_DIR}/util/io_util.cc"
-        "${LIBRARY_DIR}/util/iterator.cc"
         "${LIBRARY_DIR}/util/key_value_metadata.cc"
         "${LIBRARY_DIR}/util/logging.cc"
         "${LIBRARY_DIR}/util/memory.cc"
+        "${LIBRARY_DIR}/util/mutex.cc"
         "${LIBRARY_DIR}/util/string_builder.cc"
         "${LIBRARY_DIR}/util/string.cc"
         "${LIBRARY_DIR}/util/task_group.cc"
+        "${LIBRARY_DIR}/util/tdigest.cc"
         "${LIBRARY_DIR}/util/thread_pool.cc"
         "${LIBRARY_DIR}/util/time.cc"
         "${LIBRARY_DIR}/util/trie.cc"
+        "${LIBRARY_DIR}/util/uri.cc"
         "${LIBRARY_DIR}/util/utf8.cc"
         "${LIBRARY_DIR}/util/value_parsing.cc"
 
         "${LIBRARY_DIR}/vendored/base64.cpp"
+        "${LIBRARY_DIR}/vendored/datetime/tz.cpp"
+        "${LIBRARY_DIR}/vendored/double-conversion/bignum.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/double-conversion.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/bignum-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/fast-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/cached-powers.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/fixed-dtoa.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/diy-fp.cc"
+        "${LIBRARY_DIR}/vendored/double-conversion/strtod.cc"
+
+        "${LIBRARY_DIR}/c/bridge.cc"
         ${ORC_SRCS}
         )
 
@@ -368,14 +383,14 @@ set(PARQUET_SRCS
         "${LIBRARY_DIR}/column_reader.cc"
         "${LIBRARY_DIR}/column_scanner.cc"
         "${LIBRARY_DIR}/column_writer.cc"
-        "${LIBRARY_DIR}/deprecated_io.cc"
         "${LIBRARY_DIR}/encoding.cc"
-        "${LIBRARY_DIR}/encryption.cc"
+        "${LIBRARY_DIR}/encryption/encryption.cc"
-        "${LIBRARY_DIR}/encryption_internal.cc"
+        "${LIBRARY_DIR}/encryption/encryption_internal.cc"
+        "${LIBRARY_DIR}/encryption/internal_file_decryptor.cc"
+        "${LIBRARY_DIR}/encryption/internal_file_encryptor.cc"
+        "${LIBRARY_DIR}/exception.cc"
         "${LIBRARY_DIR}/file_reader.cc"
         "${LIBRARY_DIR}/file_writer.cc"
-        "${LIBRARY_DIR}/internal_file_decryptor.cc"
-        "${LIBRARY_DIR}/internal_file_encryptor.cc"
         "${LIBRARY_DIR}/level_conversion.cc"
         "${LIBRARY_DIR}/level_comparison.cc"
         "${LIBRARY_DIR}/metadata.cc"
@@ -385,6 +400,8 @@ set(PARQUET_SRCS
         "${LIBRARY_DIR}/properties.cc"
         "${LIBRARY_DIR}/schema.cc"
         "${LIBRARY_DIR}/statistics.cc"
+        "${LIBRARY_DIR}/stream_reader.cc"
+        "${LIBRARY_DIR}/stream_writer.cc"
         "${LIBRARY_DIR}/types.cc"
 
         "${GEN_LIBRARY_DIR}/parquet_constants.cpp"

contrib/orc

@@ -1 +1 @@
-Subproject commit 5981208e39447df84827f6a961d1da76bacb6078
+Subproject commit 0a936f6bbdb9303308973073f8623b5a8d82eae1