Skip to content

FIX: Update time handling in Arrow integration to include fractional seconds #499

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

Open
ffelixg wants to merge 1 commit into
base: main
Choose a base branch
from
+16 −24
Open

FIX: Update time handling in Arrow integration to include fractional seconds #499

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 9 additions & 14 deletions mssql_python/pybind/ddbc_bindings.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,7 +247,7 @@ struct ArrowArrayPrivateData {
std::unique_ptr<uint64_t[]> varVal;
std::unique_ptr<int32_t[]> dateVal;
std::unique_ptr<int64_t[]> tsMicroVal;
std::unique_ptr<int32_t[]> timeSecondVal;
std::unique_ptr<int64_t[]> timeNanoVal;
std::unique_ptr<Int128_t[]> decimalVal;

std::vector<uint8_t> varData;
Expand Down Expand Up @@ -4691,12 +4691,10 @@ SQLRETURN FetchArrowBatch_wrap(
arrowColumnProducer->dateVal = std::make_unique<int32_t[]>(arrowBatchSize);
arrowColumnProducer->ptrValueBuffer = arrowColumnProducer->dateVal.get();
break;
case SQL_TIME:
case SQL_TYPE_TIME:
case SQL_SS_TIME2:
format = "tts";
arrowColumnProducer->timeSecondVal = std::make_unique<int32_t[]>(arrowBatchSize);
arrowColumnProducer->ptrValueBuffer = arrowColumnProducer->timeSecondVal.get();
format = "ttn";
arrowColumnProducer->timeNanoVal = std::make_unique<int64_t[]>(arrowBatchSize);
arrowColumnProducer->ptrValueBuffer = arrowColumnProducer->timeNanoVal.get();
break;
case SQL_BIT:
format = "b";
Expand Down Expand Up @@ -4965,8 +4963,6 @@ SQLRETURN FetchArrowBatch_wrap(
}
break;
}
case SQL_TIME:
case SQL_TYPE_TIME:
case SQL_SS_TIME2: {
buffers.timeBuffers[idxCol].resize(1);
ret = SQLGetData_ptr(
Expand Down Expand Up @@ -5226,14 +5222,13 @@ SQLRETURN FetchArrowBatch_wrap(
buffers.dateBuffers[idxCol][idxRowSql].day
);
break;
case SQL_TIME:
case SQL_TYPE_TIME:
case SQL_SS_TIME2: {
const SQL_SS_TIME2_STRUCT& timeValue = buffers.timeBuffers[idxCol][idxRowSql];
arrowColumnProducer->timeSecondVal[idxRowArrow] =
static_cast<int32_t>(timeValue.hour) * 3600 +
static_cast<int32_t>(timeValue.minute) * 60 +
static_cast<int32_t>(timeValue.second);
arrowColumnProducer->timeNanoVal[idxRowArrow] =
static_cast<int64_t>(timeValue.hour) * 3600 * 1000000000 +
static_cast<int64_t>(timeValue.minute) * 60 * 1000000000 +
static_cast<int64_t>(timeValue.second) * 1000000000 +
static_cast<int64_t>(timeValue.fraction);
break;
}
case SQL_BIT: {
Expand Down
17 changes: 7 additions & 10 deletions tests/test_004_cursor_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,15 +89,20 @@ def get_arrow_test_data(include_lobs: bool, batch_length: int):
],
),
(
pa.time32("s"),
pa.time64("ns"),
"time(0)",
[time(12, 0, 5, 0), None, time(23, 59, 59, 0), time(0, 0, 0, 0)],
),
(
pa.time32("s"),
pa.time64("ns"),
"time(7)",
[time(12, 0, 5, 0), None, time(23, 59, 59, 0), time(0, 0, 0, 0)],
),
(
pa.time64("ns"),
"time(7)",
[time(12, 0, 5, 123456), None, time(23, 59, 59, 123456), time(0, 0, 0, 0)],
),
(
pa.timestamp("us"),
"datetime2(0)",
Expand Down Expand Up @@ -187,14 +192,6 @@ def _test_arrow_test_data(cursor: mssql_python.Cursor, arrow_test_data, fetch_le

# Validate that Parquet serialization/deserialization does not detect any issues
tbl = pa.Table.from_batches([ret])
# for some reason parquet converts seconds to milliseconds in time32
for i_col, col in enumerate(tbl.columns):
if col.type == pa.time32("s"):
tbl = tbl.set_column(
i_col,
tbl.schema.field(i_col).name,
col.cast(pa.time32("ms")),
)
buffer = io.BytesIO()
pq.write_table(tbl, buffer)
buffer.seek(0)
Expand Down
Loading