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.

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

Jump to bottom

feat: Add support for TIME literal values #3010

Merged
merged 3 commits into from
Aug 15, 2022
Merged

feat: Add support for TIME literal values #3010

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
8062885
feat: Initial work to add TIME literal value support
stuartcarnie Aug 2, 2022
b750319
chore: Improve unit test coverage
stuartcarnie Aug 15, 2022
cc8caad
chore: Improve test names and simplify test
stuartcarnie Aug 15, 2022
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
32 changes: 32 additions & 0 deletions datafusion/common/src/scalar.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,8 @@ pub enum ScalarValue {
Date32(Option<i32>),
/// Date stored as a signed 64bit int milliseconds since UNIX epoch 1970-01-01
Date64(Option<i64>),
/// Time stored as a signed 64bit int as nanoseconds since midnight
Time64(Option<i64>),
/// Timestamp Second
TimestampSecond(Option<i64>, Option<String>),
/// Timestamp Milliseconds
Expand Down Expand Up @@ -163,6 +165,8 @@ impl PartialEq for ScalarValue {
(Date32(_), _) => false,
(Date64(v1), Date64(v2)) => v1.eq(v2),
(Date64(_), _) => false,
(Time64(v1), Time64(v2)) => v1.eq(v2),
(Time64(_), _) => false,
(TimestampSecond(v1, _), TimestampSecond(v2, _)) => v1.eq(v2),
(TimestampSecond(_, _), _) => false,
(TimestampMillisecond(v1, _), TimestampMillisecond(v2, _)) => v1.eq(v2),
Expand Down Expand Up @@ -255,6 +259,8 @@ impl PartialOrd for ScalarValue {
(Date32(_), _) => None,
(Date64(v1), Date64(v2)) => v1.partial_cmp(v2),
(Date64(_), _) => None,
(Time64(v1), Time64(v2)) => v1.partial_cmp(v2),
(Time64(_), _) => None,
(TimestampSecond(v1, _), TimestampSecond(v2, _)) => v1.partial_cmp(v2),
(TimestampSecond(_, _), _) => None,
(TimestampMillisecond(v1, _), TimestampMillisecond(v2, _)) => {
Expand Down Expand Up @@ -338,6 +344,7 @@ impl std::hash::Hash for ScalarValue {
}
Date32(v) => v.hash(state),
Date64(v) => v.hash(state),
Time64(v) => v.hash(state),
TimestampSecond(v, _) => v.hash(state),
TimestampMillisecond(v, _) => v.hash(state),
TimestampMicrosecond(v, _) => v.hash(state),
Expand Down Expand Up @@ -681,6 +688,7 @@ impl ScalarValue {
))),
ScalarValue::Date32(_) => DataType::Date32,
ScalarValue::Date64(_) => DataType::Date64,
ScalarValue::Time64(_) => DataType::Time64(TimeUnit::Nanosecond),
ScalarValue::IntervalYearMonth(_) => {
DataType::Interval(IntervalUnit::YearMonth)
}
Expand Down Expand Up @@ -741,6 +749,7 @@ impl ScalarValue {
ScalarValue::List(v, _) => v.is_none(),
ScalarValue::Date32(v) => v.is_none(),
ScalarValue::Date64(v) => v.is_none(),
ScalarValue::Time64(v) => v.is_none(),
ScalarValue::TimestampSecond(v, _) => v.is_none(),
ScalarValue::TimestampMillisecond(v, _) => v.is_none(),
ScalarValue::TimestampMicrosecond(v, _) => v.is_none(),
Expand Down Expand Up @@ -963,6 +972,9 @@ impl ScalarValue {
DataType::LargeBinary => build_array_string!(LargeBinaryArray, LargeBinary),
DataType::Date32 => build_array_primitive!(Date32Array, Date32),
DataType::Date64 => build_array_primitive!(Date64Array, Date64),
DataType::Time64(TimeUnit::Nanosecond) => {
build_array_primitive!(Time64NanosecondArray, Time64)
}
DataType::Timestamp(TimeUnit::Second, _) => {
build_array_primitive_tz!(TimestampSecondArray, TimestampSecond)
}
Expand Down Expand Up @@ -1357,6 +1369,15 @@ impl ScalarValue {
ScalarValue::Date64(e) => {
build_array_from_option!(Date64, Date64Array, e, size)
}
ScalarValue::Time64(e) => {
build_array_from_option!(
Time64,
TimeUnit::Nanosecond,
Time64NanosecondArray,
e,
size
)
}
ScalarValue::IntervalDayTime(e) => build_array_from_option!(
Interval,
IntervalUnit::DayTime,
Expand Down Expand Up @@ -1496,6 +1517,9 @@ impl ScalarValue {
DataType::Date64 => {
typed_cast!(array, index, Date64Array, Date64)
}
DataType::Time64(TimeUnit::Nanosecond) => {
typed_cast!(array, index, Time64NanosecondArray, Time64)
}
DataType::Timestamp(TimeUnit::Second, tz_opt) => {
typed_cast_tz!(
array,
Expand Down Expand Up @@ -1691,6 +1715,9 @@ impl ScalarValue {
ScalarValue::Date64(val) => {
eq_array_primitive!(array, index, Date64Array, val)
}
ScalarValue::Time64(val) => {
eq_array_primitive!(array, index, Time64NanosecondArray, val)
}
ScalarValue::TimestampSecond(val, _) => {
eq_array_primitive!(array, index, TimestampSecondArray, val)
}
Expand Down Expand Up @@ -1845,6 +1872,7 @@ impl TryFrom<ScalarValue> for i64 {
match value {
ScalarValue::Int64(Some(inner_value))
| ScalarValue::Date64(Some(inner_value))
| ScalarValue::Time64(Some(inner_value))
| ScalarValue::TimestampNanosecond(Some(inner_value), _)
| ScalarValue::TimestampMicrosecond(Some(inner_value), _)
| ScalarValue::TimestampMillisecond(Some(inner_value), _)
Expand Down Expand Up @@ -1906,6 +1934,7 @@ impl TryFrom<&DataType> for ScalarValue {
DataType::LargeUtf8 => ScalarValue::LargeUtf8(None),
DataType::Date32 => ScalarValue::Date32(None),
DataType::Date64 => ScalarValue::Date64(None),
DataType::Time64(TimeUnit::Nanosecond) => ScalarValue::Time64(None),
DataType::Timestamp(TimeUnit::Second, tz_opt) => {
ScalarValue::TimestampSecond(None, tz_opt.clone())
}
Expand Down Expand Up @@ -2007,6 +2036,7 @@ impl fmt::Display for ScalarValue {
},
ScalarValue::Date32(e) => format_option!(f, e)?,
ScalarValue::Date64(e) => format_option!(f, e)?,
ScalarValue::Time64(e) => format_option!(f, e)?,
ScalarValue::IntervalDayTime(e) => format_option!(f, e)?,
ScalarValue::IntervalYearMonth(e) => format_option!(f, e)?,
ScalarValue::IntervalMonthDayNano(e) => format_option!(f, e)?,
Expand Down Expand Up @@ -2067,6 +2097,7 @@ impl fmt::Debug for ScalarValue {
ScalarValue::List(_, _) => write!(f, "List([{}])", self),
ScalarValue::Date32(_) => write!(f, "Date32(\"{}\")", self),
ScalarValue::Date64(_) => write!(f, "Date64(\"{}\")", self),
ScalarValue::Time64(_) => write!(f, "Time64(\"{}\")", self),
ScalarValue::IntervalDayTime(_) => {
write!(f, "IntervalDayTime(\"{}\")", self)
}
Expand Down Expand Up @@ -2665,6 +2696,7 @@ mod tests {
make_binary_test_case!(str_vals, LargeBinaryArray, LargeBinary),
make_test_case!(i32_vals, Date32Array, Date32),
make_test_case!(i64_vals, Date64Array, Date64),
make_test_case!(i64_vals, Time64NanosecondArray, Time64),
make_test_case!(i64_vals, TimestampSecondArray, TimestampSecond, None),
make_test_case!(
i64_vals,
Expand Down
38 changes: 38 additions & 0 deletions datafusion/core/tests/sql/timestamp.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -985,6 +985,44 @@ async fn sub_interval_day() -> Result<()> {
Ok(())
}

#[tokio::test]
async fn cast_string_to_time() {
let ctx = SessionContext::new();

let sql = "select \
time '08:09:10.123456789' as time_nano, \
time '13:14:15.123456' as time_micro,\
time '13:14:15.123' as time_milli,\
time '13:14:15' as time;";
let results = execute_to_batches(&ctx, sql).await;

let expected = vec![
"+--------------------+-----------------+--------------+----------+",
"| time_nano | time_micro | time_milli | time |",
"+--------------------+-----------------+--------------+----------+",
"| 08:09:10.123456789 | 13:14:15.123456 | 13:14:15.123 | 13:14:15 |",
"+--------------------+-----------------+--------------+----------+",
];
assert_batches_eq!(expected, &results);

// Fallible cases

let sql = "SELECT TIME 'not a time' as time;";
let result = try_execute_to_batches(&ctx, sql).await;
assert_eq!(
result.err().unwrap().to_string(),
"Arrow error: Cast error: Cannot cast string 'not a time' to value of Time64(Nanosecond) type"
);

// An invalid time
let sql = "SELECT TIME '24:01:02' as time;";
let result = try_execute_to_batches(&ctx, sql).await;
assert_eq!(
result.err().unwrap().to_string(),
"Arrow error: Cast error: Cannot cast string '24:01:02' to value of Time64(Nanosecond) type"
);
}

#[tokio::test]
async fn cast_to_timestamp_twice() -> Result<()> {
let ctx = SessionContext::new();
Expand Down
18 changes: 14 additions & 4 deletions datafusion/sql/src/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -496,7 +496,7 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
SQLDataType::Double => Ok(DataType::Float64),
SQLDataType::Boolean => Ok(DataType::Boolean),
SQLDataType::Date => Ok(DataType::Date32),
SQLDataType::Time => Ok(DataType::Time64(TimeUnit::Millisecond)),
SQLDataType::Time => Ok(DataType::Time64(TimeUnit::Nanosecond)),
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This change constitutes a fix as Time64(Millisecond) is invalid. Rather that switch to Time32(Millisecond), I moved to Time64(Nanosecond) as PostgreSQL requires at least microsecond precision per the documentation. Given Nanosecond comes at no additional cost, it seems reasonable to support the increase in precision.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think that is 👍

SQLDataType::Timestamp => Ok(DataType::Timestamp(TimeUnit::Nanosecond, None)),
_ => Err(DataFusionError::NotImplemented(format!(
"The SQL data type {:?} is not implemented",
Expand Down Expand Up @@ -2561,6 +2561,7 @@ pub fn convert_simple_data_type(sql_type: &SQLDataType) -> Result<DataType> {
| SQLDataType::String => Ok(DataType::Utf8),
SQLDataType::Timestamp => Ok(DataType::Timestamp(TimeUnit::Nanosecond, None)),
SQLDataType::Date => Ok(DataType::Date32),
SQLDataType::Time => Ok(DataType::Time64(TimeUnit::Nanosecond)),
SQLDataType::Decimal(precision, scale) => make_decimal_type(*precision, *scale),
SQLDataType::Binary(_) => Ok(DataType::Binary),
SQLDataType::Bytea => Ok(DataType::Binary),
Expand Down Expand Up @@ -4358,10 +4359,19 @@ mod tests {
}

#[test]
fn select_typedstring() {
let sql = "SELECT date '2020-12-10' AS date FROM person";
fn select_typed_date_string() {
let sql = "SELECT date '2020-12-10' AS date";
let expected = "Projection: CAST(Utf8(\"2020-12-10\") AS Date32) AS date\
\n TableScan: person";
\n EmptyRelation";
quick_test(sql, expected);
}

#[test]
fn select_typed_time_string() {
let sql = "SELECT TIME '08:09:10.123' AS time";
let expected =
"Projection: CAST(Utf8(\"08:09:10.123\") AS Time64(Nanosecond)) AS time\
\n EmptyRelation";
quick_test(sql, expected);
}

Expand Down