Skip to content

WIP: Dummy PR to check maint-26.0.0 status #51686

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
raulcd wants to merge 4 commits into
base: main
Choose a base branch
from
+241 −33
Draft

WIP: Dummy PR to check maint-26.0.0 status #51686

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
cca44b5
GH-51638: [CI][C++][Parquet] Update expected JSON output in parquet-r…
tadeja Oct 1, 2026
1deceed
GH-51675: [Python][Packaging] Apply upstream fix to UriParser from vc…
raulcd Oct 1, 2026
12409f8
GH-51682: [CI][C++] Add liburiparser-dev to system dependency image (…
hiroyuki-sato Oct 2, 2026
28e6c67
GH-51687: [C++] Skipt tests that require threads if ARROW_ENABLE_THRE…
raulcd Oct 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .env
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,6 @@ VCPKG="9b965a116838c6cdcd36bca60d1b81b030c8ab8d" # 2026.05.27 (not release, u
# ci/docker/python-*-windows-*.dockerfile or the vcpkg config.
# This is a workaround for our CI problem that "archery docker build" doesn't
# use pulled built images in dev/tasks/python-wheels/github.windows.yml.
PYTHON_WHEEL_WINDOWS_IMAGE_REVISION=2026-09-09
PYTHON_WHEEL_WINDOWS_IMAGE_REVISION=2026-10-01
PYTHON_WHEEL_WINDOWS_TEST_IMAGE_REVISION=2026-09-14

34 changes: 34 additions & 0 deletions ci/vcpkg/ports.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,3 +80,37 @@ index 278bc17a1c..d47d859360 100644
)
file(GLOB modules "${SOURCE_PATH}/cmake_modules/Find*.cmake")
file(REMOVE ${modules} "${SOURCE_PATH}/c++/libs/libhdfspp/libhdfspp.tar.gz")
diff --git a/ports/uriparser/fix-glibc-2.28-reallocarray.diff b/ports/uriparser/fix-glibc-2.28-reallocarray.diff
new file mode 100644
index 0000000..57adef4
--- /dev/null
+++ b/ports/uriparser/fix-glibc-2.28-reallocarray.diff
@@ -0,0 +1,15 @@
+diff --git a/src/UriMemory.c b/src/UriMemory.c
+--- a/src/UriMemory.c
++++ b/src/UriMemory.c
+@@ -50,6 +50,11 @@
+ # define _DEFAULT_SOURCE 1
+ # endif
+
++// For glibc <2.29
++# if !defined(_GNU_SOURCE)
++# define _GNU_SOURCE 1
++# endif
++
+ // For NetBSD (stdlib.h revision 1.122 of 2020-05-26)
+ # if defined(__NetBSD__) && !defined(_OPENBSD_SOURCE)
+ # define _OPENBSD_SOURCE 1
diff --git a/ports/uriparser/portfile.cmake b/ports/uriparser/portfile.cmake
index 5df5e94..225e5fb 100644
--- a/ports/uriparser/portfile.cmake
+++ b/ports/uriparser/portfile.cmake
@@ -4,6 +4,8 @@ vcpkg_from_github(
REF "uriparser-${VERSION}"
SHA512 1e4c397418e71e705b5712de2dc3ea6e95163c9d95bfbaa5f7d2fd2344d34eaf167d7d9389ab9671cfb314af026621b56e632ea34b681c2f4d7951a1b32a98b4
HEAD_REF master
+ PATCHES
+ fix-glibc-2.28-reallocarray.diff
)

if("tool" IN_LIST FEATURES)
1 change: 1 addition & 0 deletions cpp/examples/minimal_build/system_dependency.dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ RUN apt-get update -y -q && \
libre2-dev \
libsnappy-dev \
libthrift-dev \
liburiparser-dev \
libutf8proc-dev \
libzstd-dev \
pkg-config \
Expand Down
9 changes: 9 additions & 0 deletions cpp/src/arrow/util/async_generator_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -976,6 +976,9 @@ TEST_F(MergedGeneratorErrorHookTest, OuterErrorToWaiterNotOvertakenByLaterPull)
// receives the error has completed, even when it is requested while the generator is
// already completing.
TEST_F(MergedGeneratorErrorHookTest, InnerErrorToWaiterNotOvertakenDuringCompletion) {
#ifndef ARROW_ENABLE_THREADING
GTEST_SKIP() << "Test requires threading support";
#endif
auto failing = Future<TestInt>::Make();
AsyncGenerator<TestInt> failing_sub = [failing]() { return failing; };
std::vector<AsyncGenerator<TestInt>> subs = {failing_sub};
Expand All @@ -994,6 +997,9 @@ TEST_F(MergedGeneratorErrorHookTest, InnerErrorToWaiterNotOvertakenDuringComplet
}

TEST_F(MergedGeneratorErrorHookTest, OuterErrorToWaiterNotOvertakenDuringCompletion) {
#ifndef ARROW_ENABLE_THREADING
GTEST_SKIP() << "Test requires threading support";
#endif
auto failing = Future<AsyncGenerator<TestInt>>::Make();
AsyncGenerator<AsyncGenerator<TestInt>> source = [failing]() { return failing; };
MergedGenerator<TestInt> gen(std::move(source), 1);
Expand All @@ -1011,6 +1017,9 @@ TEST_F(MergedGeneratorErrorHookTest, OuterErrorToWaiterNotOvertakenDuringComplet
}

TEST_F(MergedGeneratorErrorHookTest, ClaimedErrorNotOvertakenDuringCompletion) {
#ifndef ARROW_ENABLE_THREADING
GTEST_SKIP() << "Test requires threading support";
#endif
auto failing = Future<TestInt>::Make();
AsyncGenerator<TestInt> failing_sub = [failing]() { return failing; };
std::vector<AsyncGenerator<TestInt>> subs = {MakeVectorGenerator<TestInt>({TestInt(1)}),
Expand Down
228 changes: 196 additions & 32 deletions cpp/src/parquet/reader_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1124,6 +1124,11 @@ class TestJSONWithLocalFile : public ::testing::Test {
};

TEST_F(TestJSONWithLocalFile, JSONOutputWithStatistics) {
// simdjson 5.0 changed the format of fractured_json
if constexpr (simdjson::SIMDJSON_VERSION_MAJOR < 5) {
GTEST_SKIP() << "Test requires simdjson >= 5";
}

std::string json_output = R"###({
"FileName": "nested_lists.snappy.parquet",
"Version": "1.0",
Expand All @@ -1138,15 +1143,9 @@ TEST_F(TestJSONWithLocalFile, JSONOutputWithStatistics) {
"Name": "a.list.element.list.element.list.element",
"PhysicalType": "BYTE_ARRAY",
"ConvertedType": "UTF8",
"LogicalType": { "Type": "String" }
"LogicalType": {"Type": "String"}
},
{
"Id": "1",
"Name": "b",
"PhysicalType": "INT32",
"ConvertedType": "NONE",
"LogicalType": { "Type": "None" }
}
{ "Id": "1", "Name": "b", "PhysicalType": "INT32", "ConvertedType": "NONE", "LogicalType": {"Type": "None"} }
],
"RowGroups": [
{
Expand Down Expand Up @@ -1191,6 +1190,11 @@ TEST_F(TestJSONWithLocalFile, JSONOutputWithStatistics) {
}

TEST_F(TestJSONWithLocalFile, JSONOutput) {
// simdjson 5.0 changed the format of fractured_json
if constexpr (simdjson::SIMDJSON_VERSION_MAJOR < 5) {
GTEST_SKIP() << "Test requires simdjson >= 5";
}

std::string json_output = R"###({
"FileName": "alltypes_plain.parquet",
"Version": "1.0",
Expand All @@ -1200,17 +1204,77 @@ TEST_F(TestJSONWithLocalFile, JSONOutput) {
"NumberOfRealColumns": "11",
"NumberOfColumns": "11",
"Columns": [
{ "ConvertedType": "NONE", "Id": "0" , "LogicalType": { "Type": "None" }, "Name": "id" , "PhysicalType": "INT32" },
{ "ConvertedType": "NONE", "Id": "1" , "LogicalType": { "Type": "None" }, "Name": "bool_col" , "PhysicalType": "BOOLEAN" },
{ "ConvertedType": "NONE", "Id": "2" , "LogicalType": { "Type": "None" }, "Name": "tinyint_col" , "PhysicalType": "INT32" },
{ "ConvertedType": "NONE", "Id": "3" , "LogicalType": { "Type": "None" }, "Name": "smallint_col" , "PhysicalType": "INT32" },
{ "ConvertedType": "NONE", "Id": "4" , "LogicalType": { "Type": "None" }, "Name": "int_col" , "PhysicalType": "INT32" },
{ "ConvertedType": "NONE", "Id": "5" , "LogicalType": { "Type": "None" }, "Name": "bigint_col" , "PhysicalType": "INT64" },
{ "ConvertedType": "NONE", "Id": "6" , "LogicalType": { "Type": "None" }, "Name": "float_col" , "PhysicalType": "FLOAT" },
{ "ConvertedType": "NONE", "Id": "7" , "LogicalType": { "Type": "None" }, "Name": "double_col" , "PhysicalType": "DOUBLE" },
{ "ConvertedType": "NONE", "Id": "8" , "LogicalType": { "Type": "None" }, "Name": "date_string_col", "PhysicalType": "BYTE_ARRAY" },
{ "ConvertedType": "NONE", "Id": "9" , "LogicalType": { "Type": "None" }, "Name": "string_col" , "PhysicalType": "BYTE_ARRAY" },
{ "ConvertedType": "NONE", "Id": "10", "LogicalType": { "Type": "None" }, "Name": "timestamp_col" , "PhysicalType": "INT96" }
{ "Id": "0", "Name": "id", "PhysicalType": "INT32", "ConvertedType": "NONE", "LogicalType": {"Type": "None"} },
{
"Id": "1",
"Name": "bool_col",
"PhysicalType": "BOOLEAN",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "2",
"Name": "tinyint_col",
"PhysicalType": "INT32",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "3",
"Name": "smallint_col",
"PhysicalType": "INT32",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "4",
"Name": "int_col",
"PhysicalType": "INT32",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "5",
"Name": "bigint_col",
"PhysicalType": "INT64",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "6",
"Name": "float_col",
"PhysicalType": "FLOAT",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "7",
"Name": "double_col",
"PhysicalType": "DOUBLE",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "8",
"Name": "date_string_col",
"PhysicalType": "BYTE_ARRAY",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "9",
"Name": "string_col",
"PhysicalType": "BYTE_ARRAY",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
},
{
"Id": "10",
"Name": "timestamp_col",
"PhysicalType": "INT96",
"ConvertedType": "NONE",
"LogicalType": {"Type": "None"}
}
],
"RowGroups": [
{
Expand All @@ -1219,17 +1283,105 @@ TEST_F(TestJSONWithLocalFile, JSONOutput) {
"TotalCompressedBytes": "0",
"Rows": "8",
"ColumnChunks": [
{ "CompressedSize": "73" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "0" , "StatsSet": "False", "UncompressedSize": "73" , "Values": "8" },
{ "CompressedSize": "24" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "1" , "StatsSet": "False", "UncompressedSize": "24" , "Values": "8" },
{ "CompressedSize": "47" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "2" , "StatsSet": "False", "UncompressedSize": "47" , "Values": "8" },
{ "CompressedSize": "47" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "3" , "StatsSet": "False", "UncompressedSize": "47" , "Values": "8" },
{ "CompressedSize": "47" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "4" , "StatsSet": "False", "UncompressedSize": "47" , "Values": "8" },
{ "CompressedSize": "55" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "5" , "StatsSet": "False", "UncompressedSize": "55" , "Values": "8" },
{ "CompressedSize": "47" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "6" , "StatsSet": "False", "UncompressedSize": "47" , "Values": "8" },
{ "CompressedSize": "55" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "7" , "StatsSet": "False", "UncompressedSize": "55" , "Values": "8" },
{ "CompressedSize": "88" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "8" , "StatsSet": "False", "UncompressedSize": "88" , "Values": "8" },
{ "CompressedSize": "49" , "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "9" , "StatsSet": "False", "UncompressedSize": "49" , "Values": "8" },
{ "CompressedSize": "139", "Compression": "UNCOMPRESSED", "Encodings": "RLE PLAIN_DICTIONARY PLAIN ", "Id": "10", "StatsSet": "False", "UncompressedSize": "139", "Values": "8" }
{
"Id": "0",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "73",
"CompressedSize": "73"
},
{
"Id": "1",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "24",
"CompressedSize": "24"
},
{
"Id": "2",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "47",
"CompressedSize": "47"
},
{
"Id": "3",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "47",
"CompressedSize": "47"
},
{
"Id": "4",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "47",
"CompressedSize": "47"
},
{
"Id": "5",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "55",
"CompressedSize": "55"
},
{
"Id": "6",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "47",
"CompressedSize": "47"
},
{
"Id": "7",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "55",
"CompressedSize": "55"
},
{
"Id": "8",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "88",
"CompressedSize": "88"
},
{
"Id": "9",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "49",
"CompressedSize": "49"
},
{
"Id": "10",
"Values": "8",
"StatsSet": "False",
"Compression": "UNCOMPRESSED",
"Encodings": "RLE PLAIN_DICTIONARY PLAIN ",
"UncompressedSize": "139",
"CompressedSize": "139"
}
]
}
]
Expand All @@ -1243,6 +1395,11 @@ TEST_F(TestJSONWithLocalFile, JSONOutput) {
TEST_F(TestJSONWithLocalFile, JSONOutputFLBA) {
// min-max stats for FLBA contains non-utf8 output, so we don't check
// the whole json output.
// simdjson 5.0 changed the format of fractured_json
if constexpr (simdjson::SIMDJSON_VERSION_MAJOR < 5) {
GTEST_SKIP() << "Test requires simdjson >= 5";
}

std::string json_content = ReadFromLocalFile("fixed_length_byte_array.parquet");

std::string json_contains = R"###({
Expand All @@ -1259,19 +1416,26 @@ TEST_F(TestJSONWithLocalFile, JSONOutputFLBA) {
"Name": "flba_field",
"PhysicalType": "FIXED_LEN_BYTE_ARRAY(4)",
"ConvertedType": "NONE",
"LogicalType": { "Type": "None" }
"LogicalType": {"Type": "None"}
}
],)###";

EXPECT_THAT(json_content, testing::HasSubstr(json_contains));
}

TEST_F(TestJSONWithLocalFile, JSONOutputSortColumns) {
// simdjson 5.0 changed the format of fractured_json
if constexpr (simdjson::SIMDJSON_VERSION_MAJOR < 5) {
GTEST_SKIP() << "Test requires simdjson >= 5";
}

std::string json_content = ReadFromLocalFile("sort_columns.parquet");

std::string json_contains = R"###("SortColumns": [
{ "column_idx": 0, "descending": 1, "nulls_first": 1 }, { "column_idx": 1, "descending": 0, "nulls_first": 0 }
{"column_idx": 0, "descending": 1, "nulls_first": 1},
{"column_idx": 1, "descending": 0, "nulls_first": 0}
],)###";

EXPECT_THAT(json_content, testing::HasSubstr(json_contains));
}

Expand Down
Loading