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 csv parse error #29286

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open
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
8 changes: 8 additions & 0 deletions be/src/formats/csv/csv_reader.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,14 @@ Status CSVReader::more_rows() {
break;

case ENCLOSE_ESCAPE:
if (UNLIKELY(is_row_delimiter(notGetLine))) {
curState = NEWROW;
break;
}
if (UNLIKELY(is_column_delimiter(notGetLine))) {
curState = COLUMN_DELIMITER;
break;
}
curState = preState;
_buff.skip(1);
break;
Expand Down
82 changes: 54 additions & 28 deletions be/test/exec/csv_scanner_test.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,58 @@ class CSVScannerTest : public TestWithParam<bool> {
ObjectPool _obj_pool;
};

class CSVScannerTrimSpaceTest : public CSVScannerTest {};
class CSVScannerV2Test : public CSVScannerTest {};

TEST_P(CSVScannerV2Test, test_trim_space) {
std::vector<TypeDescriptor> types{TypeDescriptor(TYPE_INT), TypeDescriptor(TYPE_VARCHAR)};

std::vector<TBrokerRangeDesc> ranges;
TBrokerRangeDesc range;
range.__set_num_of_columns_from_file(2);
range.__set_path("./be/test/exec/test_data/csv_scanner/csv_file16");
ranges.push_back(range);

auto scanner = create_csv_scanner(types, ranges, "\n", "|", 0, true, '"');
Status st = scanner->open();
ASSERT_TRUE(st.ok()) << st.to_string();

scanner->use_v2(_use_v2);

ChunkPtr chunk = scanner->get_next().value();
EXPECT_EQ(2, chunk->num_rows());

EXPECT_EQ(1, chunk->get(0)[0].get_int32());
EXPECT_EQ(3, chunk->get(1)[0].get_int32());

EXPECT_EQ("aa ", chunk->get(0)[1].get_slice());
EXPECT_EQ(" bb", chunk->get(1)[1].get_slice());
}

TEST_P(CSVScannerV2Test, test_enclose) {
std::vector<TypeDescriptor> types{TypeDescriptor(TYPE_VARCHAR), TypeDescriptor(TYPE_VARCHAR),
TypeDescriptor(TYPE_VARCHAR), TypeDescriptor(TYPE_VARCHAR)};

std::vector<TBrokerRangeDesc> ranges;
TBrokerRangeDesc range;
range.__set_num_of_columns_from_file(types.size());
range.__set_path("./be/test/exec/test_data/csv_scanner/csv_file22");
ranges.push_back(range);

auto scanner = create_csv_scanner(types, ranges, "\n", ",", 0, false, '"');
Status st = scanner->open();
ASSERT_TRUE(st.ok()) << st.to_string();

scanner->use_v2(_use_v2);

ChunkPtr chunk = scanner->get_next().value();
EXPECT_EQ(1, chunk->num_rows());

EXPECT_EQ("118,99", chunk->get(0)[0].get_slice());
EXPECT_EQ("143", chunk->get(0)[1].get_slice());
EXPECT_EQ("4.0", chunk->get(0)[2].get_slice());
EXPECT_EQ("\"21.03.2016\"", chunk->get(0)[3].get_slice());
std::cout << "yyyy: " << chunk->get(0)[3].get_slice() << "aa" << std::endl;
}

TEST_P(CSVScannerTest, test_scalar_types) {
std::vector<TypeDescriptor> types;
Expand Down Expand Up @@ -694,32 +745,7 @@ TEST_P(CSVScannerTest, test_skip_header) {
EXPECT_EQ(0, chunk->get(4)[1].get_int32());
}

TEST_P(CSVScannerTrimSpaceTest, test_trim_space) {
std::vector<TypeDescriptor> types{TypeDescriptor(TYPE_INT), TypeDescriptor(TYPE_VARCHAR)};

std::vector<TBrokerRangeDesc> ranges;
TBrokerRangeDesc range;
range.__set_num_of_columns_from_file(2);
range.__set_path("./be/test/exec/test_data/csv_scanner/csv_file16");
ranges.push_back(range);

auto scanner = create_csv_scanner(types, ranges, "\n", "|", 0, true, '"');
Status st = scanner->open();
ASSERT_TRUE(st.ok()) << st.to_string();

scanner->use_v2(_use_v2);

ChunkPtr chunk = scanner->get_next().value();
EXPECT_EQ(2, chunk->num_rows());

EXPECT_EQ(1, chunk->get(0)[0].get_int32());
EXPECT_EQ(3, chunk->get(1)[0].get_int32());

EXPECT_EQ("aa ", chunk->get(0)[1].get_slice());
EXPECT_EQ(" bb", chunk->get(1)[1].get_slice());
}

TEST_P(CSVScannerTrimSpaceTest, test_trim_space_with_ENCLOSE) {
TEST_P(CSVScannerV2Test, test_trim_space_with_ENCLOSE) {
std::vector<TypeDescriptor> types{TypeDescriptor(TYPE_INT), TypeDescriptor(TYPE_VARCHAR), TypeDescriptor(TYPE_INT)};

std::vector<TBrokerRangeDesc> ranges;
Expand Down Expand Up @@ -985,6 +1011,6 @@ TEST_P(CSVScannerTest, test_empty) {
}

INSTANTIATE_TEST_CASE_P(CSVScannerTestParams, CSVScannerTest, Values(true, false));
INSTANTIATE_TEST_CASE_P(CSVScannerTestParams, CSVScannerTrimSpaceTest, Values(true));
INSTANTIATE_TEST_CASE_P(CSVScannerTestParams, CSVScannerV2Test, Values(true));

} // namespace starrocks
1 change: 1 addition & 0 deletions be/test/exec/test_data/csv_scanner/csv_file22
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
"118,99","143","4.0","""21.03.2016"""