Skip to content

Fix scan of array type #320

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

Merged
merged 3 commits into from
Jun 29, 2023
Merged

Fix scan of array type #320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b9b100a
array
rui-mo Jun 19, 2023
f1e4d7f
Thrift ENUM values are converted to Parquet binaries containing UTF-8…
rui-mo Jun 26, 2023
3f2cbc0
add test
rui-mo Jun 28, 2023
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
6 changes: 4 additions & 2 deletions velox/dwio/parquet/reader/ParquetReader.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,7 +283,7 @@ std::shared_ptr<const ParquetTypeWithId> ReaderBase::getParquetColumnInfo(
schemaElement.name,
std::nullopt,
maxRepeat,
maxDefine);
maxDefine - 1);
}
return leafTypePtr;
}
Expand Down Expand Up @@ -381,6 +381,9 @@ TypePtr ReaderBase::convertType(
}

case thrift::ConvertedType::UTF8:
// Thrift ENUM values are converted to Parquet binaries containing UTF-8
// strings.
case thrift::ConvertedType::ENUM:
switch (schemaElement.type) {
case thrift::Type::BYTE_ARRAY:
case thrift::Type::FIXED_LEN_BYTE_ARRAY:
Expand All @@ -392,7 +395,6 @@ TypePtr ReaderBase::convertType(
case thrift::ConvertedType::MAP:
case thrift::ConvertedType::MAP_KEY_VALUE:
case thrift::ConvertedType::LIST:
case thrift::ConvertedType::ENUM:
case thrift::ConvertedType::TIME_MILLIS:
case thrift::ConvertedType::TIME_MICROS:
case thrift::ConvertedType::JSON:
Expand Down
Binary file added velox/dwio/parquet/tests/examples/part-r-0.parquet
View file
Open in desktop
Binary file not shown.
36 changes: 29 additions & 7 deletions velox/dwio/parquet/tests/reader/ParquetTableScanTest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,20 +225,42 @@ TEST_F(ParquetTableScanTest, map) {
}

// Array reader result has missing result.
// TEST_F(ParquetTableScanTest, array) {
// auto vector = makeArrayVector<int32_t>({{1, 2, 3}});
TEST_F(ParquetTableScanTest, array) {
auto vector = makeArrayVector<int32_t>({{1, 2, 3}});

loadData(
getExampleFilePath("old-repeated-int.parquet"),
ROW({"repeatedInt"}, {ARRAY(INTEGER())}),
makeRowVector(
{"repeatedInt"},
{
vector,
}));

assertSelectWithFilter(
{"repeatedInt"}, {}, "", "SELECT repeatedInt FROM tmp");
}

// Failed unit test on Velox array reader.
// Optional array with required elements.
// TEST_F(ParquetTableScanTest, optionalArray) {
// auto vector = makeArrayVector<StringView>({
// {"a", "b"},
// {"c", "d"},
// {"e", "f"},
// });

// loadData(
// getExampleFilePath("old-repeated-int.parquet"),
// ROW({"repeatedInt"}, {ARRAY(INTEGER())}),
// getExampleFilePath("part-r-0.parquet"),
// ROW({"_1"}, {ARRAY(VARCHAR())}),
// makeRowVector(
// {"repeatedInt"},
// {"_1"},
// {
// vector,
// }));

// assertSelectWithFilter({"repeatedInt"}, {}, "", "SELECT repeatedInt FROM
// tmp");
// assertSelectWithFilter(
// {"_1"}, {}, "", "SELECT _1 FROM tmp");
// }

// Failed unit test on Velox map reader.
Expand Down