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

Move date_part, date_trunc, date_bin functions to datafusion-functions #9435

Merged
merged 13 commits into from
Mar 10, 2024
Merged

Move date_part, date_trunc, date_bin functions to datafusion-functions #9435

Show file tree
Hide file tree
Changes from 11 commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
bcd2bd1
Move date_part, date_trunc, date_bin functions to datafusion-functions
Omega359 Mar 3, 2024
761d873
Merge remote-tracking branch 'upstream/main' into feature/9421
Omega359 Mar 3, 2024
2a41960
I do not understand why the logical plan changed but updating the exp…
Omega359 Mar 3, 2024
35f8e36
Merge remote-tracking branch 'upstream/main' into feature/9421
Omega359 Mar 3, 2024
618cc40
Fix fmt
Omega359 Mar 3, 2024
7ea0527
Merge remote-tracking branch 'upstream/main' into feature/9421
Omega359 Mar 5, 2024
98d5ff7
Improvements to remove datafusion-functions dependency from sq and ph…
Omega359 Mar 5, 2024
42039da
Merge remote-tracking branch 'upstream/main' into feature/9421
Omega359 Mar 5, 2024
9675dcd
Fix function arguments for date_bin, date_trunc and date_part.
Omega359 Mar 6, 2024
444337c
Merge remote-tracking branch 'upstream/main' into feature/9421
Omega359 Mar 6, 2024
c0ce362
Fix projection change. Add new test date_bin monotonicity
mustafasrepo Mar 6, 2024
bb29203
Merge remote-tracking branch 'apache/main' into feature/9421
alamb Mar 9, 2024
173c8b3
Merge remote-tracking branch 'apache/main' into feature/9421
alamb Mar 10, 2024
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
143 changes: 1 addition & 142 deletions datafusion/expr/src/built_in_function.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ use crate::{
conditional_expressions, FuncMonotonicity, Signature, TypeSignature, Volatility,
};

use arrow::datatypes::{DataType, Field, Fields, IntervalUnit, TimeUnit};
use arrow::datatypes::{DataType, Field, Fields, TimeUnit};
use datafusion_common::{exec_err, plan_err, DataFusionError, Result};

use strum::IntoEnumIterator;
Expand Down Expand Up @@ -194,12 +194,6 @@ pub enum BuiltinScalarFunction {
Concat,
/// concat_ws
ConcatWithSeparator,
/// date_part
DatePart,
/// date_trunc
DateTrunc,
/// date_bin
DateBin,
/// ends_with
EndsWith,
/// initcap
Expand Down Expand Up @@ -402,9 +396,6 @@ impl BuiltinScalarFunction {
BuiltinScalarFunction::Chr => Volatility::Immutable,
BuiltinScalarFunction::Concat => Volatility::Immutable,
BuiltinScalarFunction::ConcatWithSeparator => Volatility::Immutable,
BuiltinScalarFunction::DatePart => Volatility::Immutable,
BuiltinScalarFunction::DateTrunc => Volatility::Immutable,
BuiltinScalarFunction::DateBin => Volatility::Immutable,
BuiltinScalarFunction::EndsWith => Volatility::Immutable,
BuiltinScalarFunction::InitCap => Volatility::Immutable,
BuiltinScalarFunction::Left => Volatility::Immutable,
Expand Down Expand Up @@ -631,27 +622,6 @@ impl BuiltinScalarFunction {
}
BuiltinScalarFunction::Concat => Ok(Utf8),
BuiltinScalarFunction::ConcatWithSeparator => Ok(Utf8),
BuiltinScalarFunction::DatePart => Ok(Float64),
BuiltinScalarFunction::DateBin | BuiltinScalarFunction::DateTrunc => {
match &input_expr_types[1] {
Timestamp(Nanosecond, None) | Utf8 | Null => {
Ok(Timestamp(Nanosecond, None))
}
Timestamp(Nanosecond, tz_opt) => {
Ok(Timestamp(Nanosecond, tz_opt.clone()))
}
Timestamp(Microsecond, tz_opt) => {
Ok(Timestamp(Microsecond, tz_opt.clone()))
}
Timestamp(Millisecond, tz_opt) => {
Ok(Timestamp(Millisecond, tz_opt.clone()))
}
Timestamp(Second, tz_opt) => Ok(Timestamp(Second, tz_opt.clone())),
_ => plan_err!(
"The {self} function can only accept timestamp as the second arg."
),
}
}
BuiltinScalarFunction::InitCap => {
utf8_to_str_type(&input_expr_types[0], "initcap")
}
Expand Down Expand Up @@ -823,7 +793,6 @@ impl BuiltinScalarFunction {
/// Return the argument [`Signature`] supported by this function
pub fn signature(&self) -> Signature {
use DataType::*;
use IntervalUnit::*;
use TimeUnit::*;
use TypeSignature::*;
// note: the physical expression must accept the type returned by this function or the execution panics.
Expand Down Expand Up @@ -998,108 +967,6 @@ impl BuiltinScalarFunction {
],
self.volatility(),
),
BuiltinScalarFunction::DateTrunc => Signature::one_of(
vec![
Exact(vec![Utf8, Timestamp(Nanosecond, None)]),
Exact(vec![
Utf8,
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Microsecond, None)]),
Exact(vec![
Utf8,
Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Millisecond, None)]),
Exact(vec![
Utf8,
Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Second, None)]),
Exact(vec![
Utf8,
Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
]),
],
self.volatility(),
),
BuiltinScalarFunction::DateBin => {
let base_sig = |array_type: TimeUnit| {
vec![
Exact(vec![
Interval(MonthDayNano),
Timestamp(array_type.clone(), None),
Timestamp(Nanosecond, None),
]),
Exact(vec![
Interval(MonthDayNano),
Timestamp(array_type.clone(), Some(TIMEZONE_WILDCARD.into())),
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![
Interval(DayTime),
Timestamp(array_type.clone(), None),
Timestamp(Nanosecond, None),
]),
Exact(vec![
Interval(DayTime),
Timestamp(array_type.clone(), Some(TIMEZONE_WILDCARD.into())),
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![
Interval(MonthDayNano),
Timestamp(array_type.clone(), None),
]),
Exact(vec![
Interval(MonthDayNano),
Timestamp(array_type.clone(), Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![
Interval(DayTime),
Timestamp(array_type.clone(), None),
]),
Exact(vec![
Interval(DayTime),
Timestamp(array_type, Some(TIMEZONE_WILDCARD.into())),
]),
]
};

let full_sig = [Nanosecond, Microsecond, Millisecond, Second]
.into_iter()
.map(base_sig)
.collect::<Vec<_>>()
.concat();

Signature::one_of(full_sig, self.volatility())
}
BuiltinScalarFunction::DatePart => Signature::one_of(
vec![
Exact(vec![Utf8, Timestamp(Nanosecond, None)]),
Exact(vec![
Utf8,
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Millisecond, None)]),
Exact(vec![
Utf8,
Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Microsecond, None)]),
Exact(vec![
Utf8,
Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Timestamp(Second, None)]),
Exact(vec![
Utf8,
Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
]),
Exact(vec![Utf8, Date64]),
Exact(vec![Utf8, Date32]),
],
self.volatility(),
),
BuiltinScalarFunction::SplitPart => Signature::one_of(
vec![
Exact(vec![Utf8, Utf8, Int64]),
Expand Down Expand Up @@ -1291,11 +1158,6 @@ impl BuiltinScalarFunction {
| BuiltinScalarFunction::Pi
) {
Some(vec![Some(true)])
} else if matches!(
&self,
BuiltinScalarFunction::DateTrunc | BuiltinScalarFunction::DateBin
) {
Some(vec![None, Some(true)])
} else if *self == BuiltinScalarFunction::Log {
Some(vec![Some(true), Some(false)])
} else {
Expand Down Expand Up @@ -1388,9 +1250,6 @@ impl BuiltinScalarFunction {
BuiltinScalarFunction::CurrentDate => &["current_date", "today"],
BuiltinScalarFunction::CurrentTime => &["current_time"],
BuiltinScalarFunction::MakeDate => &["make_date"],
BuiltinScalarFunction::DateBin => &["date_bin"],
BuiltinScalarFunction::DateTrunc => &["date_trunc", "datetrunc"],
BuiltinScalarFunction::DatePart => &["date_part", "datepart"],
BuiltinScalarFunction::ToChar => &["to_char", "date_format"],
BuiltinScalarFunction::FromUnixtime => &["from_unixtime"],

Expand Down
5 changes: 5 additions & 0 deletions datafusion/expr/src/expr.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -419,6 +419,11 @@ impl ScalarFunction {
args,
}
}

/// Create a new ScalarFunction expression with a user-defined function (UDF)
pub fn new_func_def(func_def: ScalarFunctionDefinition, args: Vec<Expr>) -> Self {
Copy link
Contributor

Choose a reason for hiding this comment

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

Is it better to inline the arguments directly?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Could do that, sure.

Self { func_def, args }
}
}

/// Access a sub field of a nested type, such as `Field` or `List`
Expand Down
6 changes: 0 additions & 6 deletions datafusion/expr/src/expr_fn.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -855,9 +855,6 @@ nary_scalar_expr!(
);

// date functions
scalar_expr!(DatePart, date_part, part date, "extracts a subfield from the date");
scalar_expr!(DateTrunc, date_trunc, part date, "truncates the date to a specified level of precision");
scalar_expr!(DateBin, date_bin, stride source origin, "coerces an arbitrary timestamp to the start of the nearest specified interval");
scalar_expr!(
ToChar,
to_char,
Expand Down Expand Up @@ -1345,9 +1342,6 @@ mod test {
test_scalar_expr!(Trim, trim, string);
test_scalar_expr!(Upper, upper, string);

test_scalar_expr!(DatePart, date_part, part, date);
test_scalar_expr!(DateTrunc, date_trunc, part, date);
test_scalar_expr!(DateBin, date_bin, stride, source, origin);
test_scalar_expr!(FromUnixtime, from_unixtime, unixtime);

test_scalar_expr!(ArrayAppend, array_append, array, element);
Expand Down
Loading
Loading