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

feat: add rounding logic and scale zero fix fro parse_decimal to match parse_string_to_decimal_native behavior #7179

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add rounding logic and scale zero fix fro parse_decimal to match parse_string_to_decimal_native behavior #7179

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
53 changes: 53 additions & 0 deletions arrow-cast/src/cast/decimal.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -590,6 +590,7 @@ where
#[cfg(test)]
mod tests {
use super::*;
use crate::parse::parse_decimal;

#[test]
fn test_parse_string_to_decimal_native() -> Result<(), ArrowError> {
Expand All @@ -598,7 +599,20 @@ mod tests {
0_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("0", 38, 0)?,
parse_string_to_decimal_native::<Decimal128Type>("0", 0)?,
"value is {}",
0_i128
);

assert_eq!(
parse_string_to_decimal_native::<Decimal128Type>("0", 5)?,
0_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("0", 38, 5)?,
parse_string_to_decimal_native::<Decimal128Type>("0", 5)?,
"value is {}",
0_i128
);

Expand All @@ -607,7 +621,20 @@ mod tests {
123_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123", 38, 0)?,
parse_string_to_decimal_native::<Decimal128Type>("123", 0)?,
"value is {}",
123_i128
);

assert_eq!(
parse_string_to_decimal_native::<Decimal128Type>("123", 5)?,
12300000_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123", 38, 5)?,
parse_string_to_decimal_native::<Decimal128Type>("123", 5)?,
"value is {}",
12300000_i128
);

Expand All @@ -616,7 +643,20 @@ mod tests {
123_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123.45", 38, 0)?,
parse_string_to_decimal_native::<Decimal128Type>("123.45", 0)?,
"value is {}",
123_i128
);

assert_eq!(
parse_string_to_decimal_native::<Decimal128Type>("123.45", 5)?,
12345000_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123.45", 38, 5)?,
parse_string_to_decimal_native::<Decimal128Type>("123.45", 5)?,
"value is {}",
12345000_i128
);

Expand All @@ -625,7 +665,20 @@ mod tests {
123_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123.4567891", 38, 0)?,
parse_string_to_decimal_native::<Decimal128Type>("123.4567891", 0)?,
"value is {}",
123_i128
);

assert_eq!(
parse_string_to_decimal_native::<Decimal128Type>("123.4567891", 5)?,
12345679_i128
);
assert_eq!(
parse_decimal::<Decimal128Type>("123.4567891", 38, 5)?,
parse_string_to_decimal_native::<Decimal128Type>("123.4567891", 5)?,
"value is {}",
12345679_i128
);
Ok(())
Expand Down
36 changes: 33 additions & 3 deletions arrow-cast/src/parse.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -850,7 +850,16 @@ fn parse_e_notation<T: DecimalType>(
}

if exp < 0 {
result = result.div_wrapping(base.pow_wrapping(-exp as _));
let result_with_scale = result.div_wrapping(base.pow_wrapping(-exp as _));
let result_with_one_scale_up =
result.div_wrapping(base.pow_wrapping(-exp.add_wrapping(1) as _));
let rounding_digit =
result_with_one_scale_up.sub_wrapping(result_with_scale.mul_wrapping(base));
if rounding_digit >= T::Native::usize_as(5) {
result = result_with_scale.add_wrapping(T::Native::usize_as(1));
} else {
result = result_with_scale;
}
} else {
result = result.mul_wrapping(base.pow_wrapping(exp as _));
}
Expand All @@ -868,6 +877,7 @@ pub fn parse_decimal<T: DecimalType>(
let mut result = T::Native::usize_as(0);
let mut fractionals: i8 = 0;
let mut digits: u8 = 0;
let mut rounding_digit = -1; // to store digit after the scale for rounding
let base = T::Native::usize_as(10);

let bs = s.as_bytes();
Expand Down Expand Up @@ -897,6 +907,13 @@ pub fn parse_decimal<T: DecimalType>(
// Ignore leading zeros.
continue;
}
if fractionals == scale && scale != 0 {
// Capture the rounding digit once
if rounding_digit < 0 {
rounding_digit = (b - b'0') as i8;
}
continue;
}
digits += 1;
result = result.mul_wrapping(base);
result = result.add_wrapping(T::Native::usize_as((b - b'0') as usize));
Expand Down Expand Up @@ -925,11 +942,17 @@ pub fn parse_decimal<T: DecimalType>(
"can't parse the string value {s} to decimal"
)));
}
if fractionals == scale && scale != 0 {
if fractionals == scale {
// Capture the rounding digit once
if rounding_digit < 0 {
rounding_digit = (b - b'0') as i8;
}
// We have processed all the digits that we need. All that
// is left is to validate that the rest of the string contains
// valid digits.
continue;
if scale != 0 {
continue;
}
}
fractionals += 1;
digits += 1;
Expand Down Expand Up @@ -986,6 +1009,13 @@ pub fn parse_decimal<T: DecimalType>(
"parse decimal overflow ({s})"
)));
}
if scale == 0 {
result = result.div_wrapping(base.pow_wrapping(fractionals as u32))
}
//add one if >=5
if rounding_digit >= 5 {
result = result.add_wrapping(T::Native::usize_as(1));
}
}

Ok(if negative {
Expand Down
2 changes: 1 addition & 1 deletion arrow-csv/src/reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1286,7 +1286,7 @@ mod tests {
assert_eq!("53.002666", lat.value_as_string(1));
assert_eq!("52.412811", lat.value_as_string(2));
assert_eq!("51.481583", lat.value_as_string(3));
assert_eq!("12.123456", lat.value_as_string(4));
assert_eq!("12.123457", lat.value_as_string(4));
assert_eq!("50.760000", lat.value_as_string(5));
assert_eq!("0.123000", lat.value_as_string(6));
assert_eq!("123.000000", lat.value_as_string(7));
Expand Down
4 changes: 2 additions & 2 deletions arrow-json/src/reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1181,7 +1181,7 @@ mod tests {
assert!(col1.is_null(5));
assert_eq!(
col1.values(),
&[100, 200, 204, 1103420, 0, 0].map(T::Native::usize_as)
&[100, 200, 205, 1103420, 0, 0].map(T::Native::usize_as)
);

let col2 = batches[0].column(1).as_primitive::<T>();
Expand All @@ -1201,7 +1201,7 @@ mod tests {
assert!(col3.is_null(5));
assert_eq!(
col3.values(),
&[3830, 12345, 0, 0, 0, 0].map(T::Native::usize_as)
&[3830, 12346, 0, 0, 0, 0].map(T::Native::usize_as)
);
}

Expand Down
Loading