Skip to content

Fixes for working with functions in dataframes, additional documentation #1430

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
alamb merged 7 commits into from
Dec 15, 2021
Merged

Fixes for working with functions in dataframes, additional documentation #1430

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2ccd20f
Fixes for working with functions in dataframes
tobyhede Nov 28, 2021
c1074c5
clippy fix
tobyhede Dec 15, 2021
a7dc3bf
Update datafusion/src/logical_plan/expr.rs
tobyhede Dec 15, 2021
56e4e44
Update datafusion/src/logical_plan/expr.rs
tobyhede Dec 15, 2021
c36e68a
remove broken regex test
tobyhede Dec 15, 2021
4f21740
remove uneeded comments
tobyhede Dec 15, 2021
253153f
fix: cargo fmt
alamb Dec 15, 2021
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
213 changes: 137 additions & 76 deletions datafusion/src/logical_plan/expr.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1564,7 +1564,7 @@ pub fn approx_distinct(expr: Expr) -> Expr {
/// Create an convenience function representing a unary scalar function
macro_rules! unary_scalar_expr {
($ENUM:ident, $FUNC:ident) => {
#[doc = "this scalar function is not documented yet"]
#[doc = concat!("Unary scalar function definition for ", stringify!($FUNC) ) ]
Copy link
Contributor

@alamb alamb Dec 13, 2021

Choose a reason for hiding this comment

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

👍

pub fn $FUNC(e: Expr) -> Expr {
Expr::ScalarFunction {
fun: functions::BuiltinScalarFunction::$ENUM,
Expand All @@ -1574,17 +1574,28 @@ macro_rules! unary_scalar_expr {
};
}

/// Create an convenience function representing a binary scalar function
macro_rules! binary_scalar_expr {
macro_rules! scalar_expr {
($ENUM:ident, $FUNC:ident, $($arg:ident),*) => {
#[doc = concat!("Scalar function definition for ", stringify!($FUNC) ) ]
pub fn $FUNC($($arg: Expr),*) -> Expr {
Expr::ScalarFunction {
fun: functions::BuiltinScalarFunction::$ENUM,
args: vec![$($arg),*],
}
}
};
}

macro_rules! nary_scalar_expr {
($ENUM:ident, $FUNC:ident) => {
#[doc = "this scalar function is not documented yet"]
pub fn $FUNC(arg1: Expr, arg2: Expr) -> Expr {
#[doc = concat!("Scalar function definition for ", stringify!($FUNC) ) ]
pub fn $FUNC(args: Vec<Expr>) -> Expr {
Expr::ScalarFunction {
fun: functions::BuiltinScalarFunction::$ENUM,
args: vec![arg1, arg2],
args: args,
}
}
};
};
}

// generate methods for creating the supported unary/binary expressions
Expand All @@ -1610,44 +1621,46 @@ unary_scalar_expr!(Log10, log10);
unary_scalar_expr!(Ln, ln);

// string functions
unary_scalar_expr!(Ascii, ascii);
unary_scalar_expr!(BitLength, bit_length);
unary_scalar_expr!(Btrim, btrim);
unary_scalar_expr!(CharacterLength, character_length);
unary_scalar_expr!(CharacterLength, length);
unary_scalar_expr!(Chr, chr);
unary_scalar_expr!(InitCap, initcap);
unary_scalar_expr!(Left, left);
unary_scalar_expr!(Lower, lower);
unary_scalar_expr!(Lpad, lpad);
unary_scalar_expr!(Ltrim, ltrim);
unary_scalar_expr!(MD5, md5);
unary_scalar_expr!(OctetLength, octet_length);
unary_scalar_expr!(RegexpMatch, regexp_match);
unary_scalar_expr!(RegexpReplace, regexp_replace);
unary_scalar_expr!(Replace, replace);
unary_scalar_expr!(Repeat, repeat);
unary_scalar_expr!(Reverse, reverse);
unary_scalar_expr!(Right, right);
unary_scalar_expr!(Rpad, rpad);
unary_scalar_expr!(Rtrim, rtrim);
unary_scalar_expr!(SHA224, sha224);
unary_scalar_expr!(SHA256, sha256);
unary_scalar_expr!(SHA384, sha384);
unary_scalar_expr!(SHA512, sha512);
unary_scalar_expr!(SplitPart, split_part);
unary_scalar_expr!(StartsWith, starts_with);
unary_scalar_expr!(Strpos, strpos);
unary_scalar_expr!(Substr, substr);
unary_scalar_expr!(ToHex, to_hex);
unary_scalar_expr!(Translate, translate);
unary_scalar_expr!(Trim, trim);
unary_scalar_expr!(Upper, upper);
scalar_expr!(Ascii, ascii, string);
scalar_expr!(BitLength, bit_length, string);
nary_scalar_expr!(Btrim, btrim);
// scalar_expr!(Btrim, btrim, string);
// scalar_expr!(Btrim, btrim_chars, string, characters);
Copy link
Contributor

@alamb alamb Dec 13, 2021

Choose a reason for hiding this comment

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

What happened to these two functions (as in do you mean to leave them commented out)?

Copy link
Contributor Author

@tobyhede tobyhede Dec 13, 2021

Choose a reason for hiding this comment

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

@alamb Left these in to demonstrate the alternative approach to handling the differnt function arities with different functions. Will clean up.

scalar_expr!(CharacterLength, character_length, string);
scalar_expr!(CharacterLength, length, string);
scalar_expr!(Chr, chr, string);
scalar_expr!(Digest, digest, string, algorithm);
scalar_expr!(InitCap, initcap, string);
scalar_expr!(Left, left, string, count);
scalar_expr!(Lower, lower, string);
nary_scalar_expr!(Lpad, lpad);
scalar_expr!(Ltrim, ltrim, string);
scalar_expr!(MD5, md5, string);
scalar_expr!(OctetLength, octet_length, string);
nary_scalar_expr!(RegexpMatch, regexp_match);
nary_scalar_expr!(RegexpReplace, regexp_replace);
scalar_expr!(Replace, replace, string, from, to);
scalar_expr!(Repeat, repeat, string, count);
scalar_expr!(Reverse, reverse, string);
scalar_expr!(Right, right, string, count);
nary_scalar_expr!(Rpad, rpad);
scalar_expr!(Rtrim, rtrim, string);
scalar_expr!(SHA224, sha224, string);
scalar_expr!(SHA256, sha256, string);
scalar_expr!(SHA384, sha384, string);
scalar_expr!(SHA512, sha512, string);
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!(ToHex, to_hex, string);
scalar_expr!(Translate, translate, string, from, to);
scalar_expr!(Trim, trim, string);
scalar_expr!(Upper, upper, string);

// date functions
binary_scalar_expr!(DatePart, date_part);
binary_scalar_expr!(DateTrunc, date_trunc);
binary_scalar_expr!(Digest, digest);
scalar_expr!(DatePart, date_part, part, date);
scalar_expr!(DateTrunc, date_trunc, part, date);
Copy link
Contributor

@alamb alamb Dec 13, 2021

Choose a reason for hiding this comment

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

for other reviewers, digest was moved above

Copy link
Contributor Author

@tobyhede tobyhede Dec 13, 2021

Choose a reason for hiding this comment

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

Yeah, digest was with date functions but is arguably string function or could be a section with some of the other hashes


/// returns an array of fixed size with each argument on it.
pub fn array(args: Vec<Expr>) -> Expr {
Expand Down Expand Up @@ -2217,6 +2230,44 @@ mod tests {
}};
}

macro_rules! test_scalar_expr {
($ENUM:ident, $FUNC:ident, $($arg:ident),*) => {
let expected = vec![$(stringify!($arg)),*];
let result = $FUNC(
$(
col(stringify!($arg.to_string()))
),*
);
if let Expr::ScalarFunction { fun, args } = result {
let name = functions::BuiltinScalarFunction::$ENUM;
assert_eq!(name, fun);
assert_eq!(expected.len(), args.len());
} else {
assert!(false, "unexpected");
}
};
}

macro_rules! test_nary_scalar_expr {
($ENUM:ident, $FUNC:ident, $($arg:ident),*) => {
let expected = vec![$(stringify!($arg)),*];
let result = $FUNC(
vec![
$(
col(stringify!($arg.to_string()))
),*
]
);
if let Expr::ScalarFunction { fun, args } = result {
let name = functions::BuiltinScalarFunction::$ENUM;
assert_eq!(name, fun);
assert_eq!(expected.len(), args.len());
} else {
assert!(false, "unexpected");
}
};
}

#[test]
fn digest_function_definitions() {
if let Expr::ScalarFunction { fun, args } = digest(col("tableA.a"), lit("md5")) {
Expand Down Expand Up @@ -2248,39 +2299,49 @@ mod tests {
test_unary_scalar_expr!(Log2, log2);
test_unary_scalar_expr!(Log10, log10);
test_unary_scalar_expr!(Ln, ln);
test_unary_scalar_expr!(Ascii, ascii);
test_unary_scalar_expr!(BitLength, bit_length);
test_unary_scalar_expr!(Btrim, btrim);
test_unary_scalar_expr!(CharacterLength, character_length);
test_unary_scalar_expr!(CharacterLength, length);
test_unary_scalar_expr!(Chr, chr);
test_unary_scalar_expr!(InitCap, initcap);
test_unary_scalar_expr!(Left, left);
test_unary_scalar_expr!(Lower, lower);
test_unary_scalar_expr!(Lpad, lpad);
test_unary_scalar_expr!(Ltrim, ltrim);
test_unary_scalar_expr!(MD5, md5);
test_unary_scalar_expr!(OctetLength, octet_length);
test_unary_scalar_expr!(RegexpMatch, regexp_match);
test_unary_scalar_expr!(RegexpReplace, regexp_replace);
test_unary_scalar_expr!(Replace, replace);
test_unary_scalar_expr!(Repeat, repeat);
test_unary_scalar_expr!(Reverse, reverse);
test_unary_scalar_expr!(Right, right);
test_unary_scalar_expr!(Rpad, rpad);
test_unary_scalar_expr!(Rtrim, rtrim);
test_unary_scalar_expr!(SHA224, sha224);
test_unary_scalar_expr!(SHA256, sha256);
test_unary_scalar_expr!(SHA384, sha384);
test_unary_scalar_expr!(SHA512, sha512);
test_unary_scalar_expr!(SplitPart, split_part);
test_unary_scalar_expr!(StartsWith, starts_with);
test_unary_scalar_expr!(Strpos, strpos);
test_unary_scalar_expr!(Substr, substr);
test_unary_scalar_expr!(ToHex, to_hex);
test_unary_scalar_expr!(Translate, translate);
test_unary_scalar_expr!(Trim, trim);
test_unary_scalar_expr!(Upper, upper);

test_scalar_expr!(Ascii, ascii, input);
test_scalar_expr!(BitLength, bit_length, string);
test_nary_scalar_expr!(Btrim, btrim, string);
test_nary_scalar_expr!(Btrim, btrim, string, characters);
test_scalar_expr!(CharacterLength, character_length, string);
test_scalar_expr!(CharacterLength, length, string);
test_scalar_expr!(Chr, chr, string);
test_scalar_expr!(Digest, digest, string, algorithm);
test_scalar_expr!(InitCap, initcap, string);
test_scalar_expr!(Left, left, string, count);
test_scalar_expr!(Lower, lower, string);
test_nary_scalar_expr!(Lpad, lpad, string, count);
test_nary_scalar_expr!(Lpad, lpad, string, count, characters);
test_scalar_expr!(Ltrim, ltrim, string);
test_scalar_expr!(MD5, md5, string);
test_scalar_expr!(OctetLength, octet_length, string);
test_nary_scalar_expr!(RegexpMatch, regexp_match, string, pattern);
test_nary_scalar_expr!(RegexpMatch, regexp_match, string, pattern, flags);
test_nary_scalar_expr!(RegexpReplace, regexp_replace, string, pattern, replacement);
test_nary_scalar_expr!(RegexpReplace, regexp_replace, string, pattern, replacement, flags);
test_scalar_expr!(Replace, replace, string, from, to);
test_scalar_expr!(Repeat, repeat, string, count);
test_scalar_expr!(Reverse, reverse, string);
test_scalar_expr!(Right, right, string, count);
test_nary_scalar_expr!(Rpad, rpad, string, count);
test_nary_scalar_expr!(Rpad, rpad, string, count, characters);
test_scalar_expr!(Rtrim, rtrim, string);
test_scalar_expr!(SHA224, sha224, string);
test_scalar_expr!(SHA256, sha256, string);
test_scalar_expr!(SHA384, sha384, string);
test_scalar_expr!(SHA512, sha512, string);
test_scalar_expr!(SplitPart, split_part, expr, delimiter, index);
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!(ToHex, to_hex, string);
test_scalar_expr!(Translate, translate, string, from, to);
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]
Expand Down
13 changes: 13 additions & 0 deletions datafusion/src/physical_plan/functions.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2575,6 +2575,19 @@ mod tests {
Int32,
Int32Array
);
// #[cfg(feature = "regex_expressions")]
Copy link
Contributor

@alamb alamb Dec 13, 2021

Choose a reason for hiding this comment

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

Did you intend to fix this case?

Copy link
Contributor Author

@tobyhede tobyhede Dec 15, 2021

Choose a reason for hiding this comment

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

Ah, this one doesn't work and I have removed.

There is a bug in the regex handling #1429
I might pick up that one next.

// test_function!(
// RegexpMatch,
// &[
// lit(ScalarValue::Utf8(Some("abc".to_string()))),
// lit(ScalarValue::Utf8(Some("a..".to_string()))),
// lit(ScalarValue::Utf8(Some("g".to_string()))),
// ],
// Ok(Some("abc")),
// &str,
// Utf8,
// StringArray
// );
#[cfg(feature = "regex_expressions")]
test_function!(
RegexpReplace,
Expand Down
2 changes: 1 addition & 1 deletion datafusion/src/prelude.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ pub use crate::execution::options::{CsvReadOptions, NdJsonReadOptions};
pub use crate::logical_plan::{
array, ascii, avg, bit_length, btrim, character_length, chr, col, concat, concat_ws,
count, create_udf, date_part, date_trunc, digest, in_list, initcap, left, length,
lit, lower, lpad, ltrim, max, md5, min, now, octet_length, random, regexp_replace,
lit, lower, lpad, ltrim, max, md5, min, now, octet_length, random, regexp_match, regexp_replace,
repeat, replace, reverse, right, rpad, rtrim, sha224, sha256, sha384, sha512,
split_part, starts_with, strpos, substr, sum, to_hex, translate, trim, upper, Column,
JoinType, Partitioning,
Expand Down
Loading