Skip to content
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.

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

[BugFix] Fix hive text reader can't recognize last empty element #52990

Merged
merged 1 commit into from
Nov 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Fix text reader can't recognize last empty element
Signed-off-by: Smith Cruise <chendingchao1@126.com>
  • Loading branch information
Smith-Cruise committed Nov 19, 2024
commit 257fa23e906d72f5655e345db35e4472948d1e46
2 changes: 1 addition & 1 deletion be/src/formats/csv/array_reader.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ bool HiveTextArrayReader::split_array_elements(const Slice& s, std::vector<Slice
left = right + 1;
}
}
if (right > left) {
if (right >= left) {
elements.emplace_back(s.data + left, right - left);
}

Expand Down
41 changes: 41 additions & 0 deletions be/test/exec/hdfs_scanner_test.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2299,6 +2299,47 @@ TEST_F(HdfsScannerTest, TestCSVWithStructMap) {
}
}

TEST_F(HdfsScannerTest, TestCSVArrayLastElementEmpty) {
TypeDescriptor array_col = TypeDescriptor::from_logical_type(LogicalType::TYPE_ARRAY);
array_col.children.emplace_back(TypeDescriptor::from_logical_type(TYPE_VARCHAR));

SlotDesc csv_descs[] = {{"id", TypeDescriptor::from_logical_type(LogicalType::TYPE_VARCHAR)},
{"array", array_col},
{"sex", TypeDescriptor::from_logical_type(LogicalType::TYPE_VARCHAR)},
{""}};

const std::string small_file = "./be/test/exec/test_data/csv_scanner/array_last_element_is_empty.csv";
Status status;

{
auto* range = _create_scan_range(small_file, 0, 0);
range->text_file_desc.__set_field_delim(DEFAULT_FIELD_DELIM);
range->text_file_desc.__set_collection_delim(DEFAULT_COLLECTION_DELIM);
auto* tuple_desc = _create_tuple_desc(csv_descs);
auto* param = _create_param(small_file, range, tuple_desc);
std::vector<std::string> hive_column_names{"id", "array", "sex"};
param->hive_column_names = &hive_column_names;
auto scanner = std::make_shared<HdfsTextScanner>();

status = scanner->init(_runtime_state, *param);
EXPECT_TRUE(status.ok());

status = scanner->open(_runtime_state);
EXPECT_TRUE(status.ok());

ChunkPtr chunk = ChunkHelper::new_chunk(*tuple_desc, 4096);

status = scanner->get_next(_runtime_state, &chunk);
EXPECT_TRUE(status.ok());
EXPECT_EQ(3, chunk->num_rows());

EXPECT_EQ("['1', ['1','2',''], 'man']", chunk->debug_row(0));
EXPECT_EQ("['2', ['2','3',''], 'female']", chunk->debug_row(1));
EXPECT_EQ("['3', ['3','4','5'], 'man']", chunk->debug_row(2));
scanner->close();
}
}

TEST_F(HdfsScannerTest, TestCSVWithBlankDelimiter) {
const std::string small_file = "./be/test/exec/test_data/csv_scanner/array_struct_map.csv";

Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
112man
223female
3345man
Loading