Skip to content

Unify temporal field parsing with DatePart #24906

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

Merged
kumarUjjawal merged 1 commit into from
Sep 4, 2026
Merged

Unify temporal field parsing with DatePart #24906

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
56 changes: 16 additions & 40 deletions datafusion/functions/src/datetime/date_part.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ use std::sync::Arc;

use arrow::array::timezone::Tz;
use arrow::array::{Array, ArrayRef, Float64Array, Int32Array, Int64Array};
use arrow::compute::kernels::cast_utils::IntervalUnit;
use arrow::compute::{DatePart, binary, date_part};
use arrow::datatypes::DataType::{
Date32, Date64, Duration, Interval, Time32, Time64, Timestamp,
Expand Down Expand Up @@ -216,37 +215,14 @@ impl ScalarUDFImpl for DatePartFunc {

let part_trim = part_normalization(&part);

// using IntervalUnit here means we hand off all the work of supporting plurals (like "seconds")
// and synonyms ( like "ms,msec,msecond,millisecond") to Arrow
let arr = if let Ok(interval_unit) = IntervalUnit::from_str(part_trim) {
match interval_unit {
IntervalUnit::Year => date_part(array.as_ref(), DatePart::Year)?,
IntervalUnit::Month => date_part(array.as_ref(), DatePart::Month)?,
IntervalUnit::Week => date_part(array.as_ref(), DatePart::Week)?,
IntervalUnit::Day => date_part(array.as_ref(), DatePart::Day)?,
IntervalUnit::Hour => date_part(array.as_ref(), DatePart::Hour)?,
IntervalUnit::Minute => date_part(array.as_ref(), DatePart::Minute)?,
IntervalUnit::Second => seconds_as_i32(array.as_ref(), Second)?,
IntervalUnit::Millisecond => seconds_as_i32(array.as_ref(), Millisecond)?,
IntervalUnit::Microsecond => seconds_as_i32(array.as_ref(), Microsecond)?,
IntervalUnit::Nanosecond => seconds_ns(array.as_ref())?,
// century and decade are not supported by `DatePart`, although they are supported in postgres
_ => return exec_err!("Date part '{part}' not supported"),
}
} else {
// special cases that can be extracted (in postgres) but are not interval units
match part_trim.to_lowercase().as_str() {
"isoyear" => date_part(array.as_ref(), DatePart::YearISO)?,
"qtr" | "quarter" => date_part(array.as_ref(), DatePart::Quarter)?,
"doy" => date_part(array.as_ref(), DatePart::DayOfYear)?,
"dow" => date_part(array.as_ref(), DatePart::DayOfWeekSunday0)?,
"isodow" => {
// Postgres `isodow` is 1..=7 with Mon=1
date_part(array.as_ref(), DatePart::DayOfWeekMonday1)?
}
"epoch" => epoch(array.as_ref())?,
_ => return exec_err!("Date part '{part}' not supported"),
}
let arr = match DatePart::from_str(part_trim) {
Ok(DatePart::Second) => seconds_as_i32(array.as_ref(), Second)?,
Ok(DatePart::Millisecond) => seconds_as_i32(array.as_ref(), Millisecond)?,
Ok(DatePart::Microsecond) => seconds_as_i32(array.as_ref(), Microsecond)?,
Ok(DatePart::Nanosecond) => seconds_ns(array.as_ref())?,
Ok(part) => date_part(array.as_ref(), part)?,
Err(_) if is_epoch(part_trim) => epoch(array.as_ref())?,
Err(_) => return exec_err!("Date part '{part}' not supported"),
};

Ok(if is_scalar {
Expand All @@ -256,7 +232,7 @@ impl ScalarUDFImpl for DatePartFunc {
})
}

// Only casting the year is supported since pruning other IntervalUnit is not possible
// Only casting the year is supported since pruning other date parts is not possible
// date_part(col, YEAR) = 2024 => col >= '2024-01-01' and col < '2025-01-01'
// But for anything less than YEAR simplifying is not possible without specifying the bigger interval
// date_part(col, MONTH) = 1 => col = '2023-01-01' or col = '2024-01-01' or ... or col = '3000-01-01'
Expand All @@ -268,16 +244,16 @@ impl ScalarUDFImpl for DatePartFunc {
) -> Result<PreimageResult> {
let [part, col_expr] = take_function_args(self.name(), args)?;

// Get the interval unit from the part argument
let interval_unit = part
// Get the date part from the part argument
let date_part = part
.as_literal()
.and_then(|sv| sv.try_as_str().flatten())
.map(part_normalization)
.and_then(|s| IntervalUnit::from_str(s).ok());
.and_then(|s| DatePart::from_str(s).ok());

// only support extracting year
match interval_unit {
Some(IntervalUnit::Year) => (),
match date_part {
Some(DatePart::Year) => (),
_ => return Ok(PreimageResult::None),
}

Expand Down Expand Up @@ -336,8 +312,8 @@ fn is_epoch(part: &str) -> bool {
}

fn is_nanosecond(part: &str) -> bool {
IntervalUnit::from_str(part_normalization(part))
.map(|p| matches!(p, IntervalUnit::Nanosecond))
DatePart::from_str(part_normalization(part))
.map(|p| matches!(p, DatePart::Nanosecond))
.unwrap_or(false)
}

Expand Down
Loading