Skip to content

Add Substring(str [from int] [for int]) support in datafusion-proto #3902

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
merged 2 commits into from
Oct 21, 2022
Merged

Add Substring(str [from int] [for int]) support in datafusion-proto #3902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aa7c9a2
Add Substring(str [from int] [for int]) support in datafusion-proto
r4ntix Oct 20, 2022
0b63624
Add assert for Substr
r4ntix Oct 21, 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
2 changes: 2 additions & 0 deletions datafusion/expr/src/expr_fn.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -403,6 +403,7 @@ scalar_expr!(SplitPart, split_part, expr, delimiter, index);
scalar_expr!(StartsWith, starts_with, string, characters);
scalar_expr!(Strpos, strpos, string, substring);
scalar_expr!(Substr, substr, string, position);
scalar_expr!(Substr, substring, string, position, count);
scalar_expr!(ToHex, to_hex, string);
scalar_expr!(Translate, translate, string, from, to);
scalar_expr!(Trim, trim, string);
Expand Down Expand Up @@ -656,6 +657,7 @@ mod test {
test_scalar_expr!(StartsWith, starts_with, string, characters);
test_scalar_expr!(Strpos, strpos, string, substring);
test_scalar_expr!(Substr, substr, string, position);
test_scalar_expr!(Substr, substring, string, position, count);
test_scalar_expr!(ToHex, to_hex, string);
test_scalar_expr!(Translate, translate, string, from, to);
test_scalar_expr!(Trim, trim, string);
Expand Down
28 changes: 20 additions & 8 deletions datafusion/proto/src/from_proto.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,10 +39,11 @@ use datafusion_expr::{
logical_plan::{PlanType, StringifiedPlan},
lower, lpad, ltrim, md5, now, nullif, octet_length, power, random, regexp_match,
regexp_replace, repeat, replace, reverse, right, round, rpad, rtrim, sha224, sha256,
sha384, sha512, signum, sin, split_part, sqrt, starts_with, strpos, substr, tan,
to_hex, to_timestamp_micros, to_timestamp_millis, to_timestamp_seconds, translate,
trim, trunc, upper, AggregateFunction, Between, BuiltInWindowFunction,
BuiltinScalarFunction, Case, Expr, GetIndexedField, GroupingSet,
sha384, sha512, signum, sin, split_part, sqrt, starts_with, strpos, substr,
substring, tan, to_hex, to_timestamp_micros, to_timestamp_millis,
to_timestamp_seconds, translate, trim, trunc, upper, AggregateFunction, Between,
BuiltInWindowFunction, BuiltinScalarFunction, Case, Expr, GetIndexedField,
GroupingSet,
GroupingSet::GroupingSets,
Like, Operator, WindowFrame, WindowFrameBound, WindowFrameUnits,
};
Expand Down Expand Up @@ -1137,10 +1138,21 @@ pub fn parse_expr(
parse_expr(&args[0], registry)?,
parse_expr(&args[1], registry)?,
)),
ScalarFunction::Substr => Ok(substr(
parse_expr(&args[0], registry)?,
parse_expr(&args[1], registry)?,
)),
ScalarFunction::Substr => {
if args.len() > 2 {
Copy link
Contributor

@alamb alamb Oct 20, 2022

Choose a reason for hiding this comment

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

I recommend adding an assert assert_eq!(args.len(), 3) in this case so that we don't get another silent failure if we add additional argument support to substr

Copy link
Contributor Author

@r4ntix r4ntix Oct 21, 2022

Choose a reason for hiding this comment

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

Thanks for the feedback, I've added the assert in the new commit :)

assert_eq!(args.len(), 3);
Ok(substring(
parse_expr(&args[0], registry)?,
parse_expr(&args[1], registry)?,
parse_expr(&args[2], registry)?,
))
} else {
Ok(substr(
parse_expr(&args[0], registry)?,
parse_expr(&args[1], registry)?,
))
}
}
ScalarFunction::ToHex => Ok(to_hex(parse_expr(&args[0], registry)?)),
ScalarFunction::ToTimestampMillis => {
Ok(to_timestamp_millis(parse_expr(&args[0], registry)?))
Expand Down
22 changes: 21 additions & 1 deletion datafusion/proto/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,8 @@ mod roundtrip_tests {
use datafusion_expr::logical_plan::{Extension, UserDefinedLogicalNode};
use datafusion_expr::{
col, lit, Accumulator, AggregateFunction, AggregateState,
BuiltinScalarFunction::Sqrt, Expr, LogicalPlan, Operator, Volatility,
BuiltinScalarFunction::{Sqrt, Substr},
Expr, LogicalPlan, Operator, Volatility,
};
use prost::Message;
use std::any::Any;
Expand Down Expand Up @@ -1149,4 +1150,23 @@ mod roundtrip_tests {
let ctx = SessionContext::new();
roundtrip_expr_test(test_expr, ctx);
}

#[test]
fn roundtrip_substr() {
// substr(string, position)
let test_expr = Expr::ScalarFunction {
fun: Substr,
args: vec![col("col"), lit(1_i64)],
};

// substr(string, position, count)
let test_expr_with_count = Expr::ScalarFunction {
fun: Substr,
args: vec![col("col"), lit(1_i64), lit(1_i64)],
};

let ctx = SessionContext::new();
roundtrip_expr_test(test_expr, ctx.clone());
roundtrip_expr_test(test_expr_with_count, ctx);
}
}