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

Support multiple alternative syntaxes in the user_doc macro, port trim to use new macro #13952

Merged
merged 1 commit into from
Dec 31, 2024
Merged

Support multiple alternative syntaxes in the user_doc macro, port trim to use new macro #13952

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: 24 additions & 29 deletions datafusion/functions/src/string/btrim.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,11 @@ use arrow::array::{ArrayRef, OffsetSizeTrait};
use arrow::datatypes::DataType;
use datafusion_common::{exec_err, Result};
use datafusion_expr::function::Hint;
use datafusion_expr::scalar_doc_sections::DOC_SECTION_STRING;
use datafusion_expr::{
ColumnarValue, Documentation, ScalarUDFImpl, Signature, TypeSignature, Volatility,
};
use datafusion_macros::user_doc;
use std::any::Any;
use std::sync::OnceLock;

/// Returns the longest string with leading and trailing characters removed. If the characters are not specified, whitespace is removed.
/// btrim('xyxtrimyyx', 'xyz') = 'trim'
Expand All @@ -35,6 +34,28 @@ fn btrim<T: OffsetSizeTrait>(args: &[ArrayRef]) -> Result<ArrayRef> {
general_trim::<T>(args, TrimType::Both, use_string_view)
}

#[user_doc(
doc_section(label = "String Functions"),
description = "Trims the specified trim string from the start and end of a string. If no trim string is provided, all whitespace is removed from the start and end of the input string.",
syntax_example = "btrim(str[, trim_str])",
sql_example = r#"```sql
> select btrim('__datafusion____', '_');
+-------------------------------------------+
| btrim(Utf8("__datafusion____"),Utf8("_")) |
+-------------------------------------------+
| datafusion |
+-------------------------------------------+
```"#,
standard_argument(name = "str", prefix = "String"),
argument(
name = "trim_str",
description = r"String expression to operate on. Can be a constant, column, or function, and any combination of operators. _Default is whitespace characters._"
),
alternative_syntax = "trim(BOTH trim_str FROM str)",
alternative_syntax = "trim(trim_str FROM str)",
related_udf(name = "ltrim"),
related_udf(name = "rtrim")
)]
#[derive(Debug)]
pub struct BTrimFunc {
signature: Signature,
Expand Down Expand Up @@ -106,36 +127,10 @@ impl ScalarUDFImpl for BTrimFunc {
}

fn documentation(&self) -> Option<&Documentation> {
Some(get_btrim_doc())
self.doc()
}
}

static DOCUMENTATION: OnceLock<Documentation> = OnceLock::new();

fn get_btrim_doc() -> &'static Documentation {
DOCUMENTATION.get_or_init(|| {
Documentation::builder(
DOC_SECTION_STRING,
"Trims the specified trim string from the start and end of a string. If no trim string is provided, all whitespace is removed from the start and end of the input string.",
"btrim(str[, trim_str])")
.with_sql_example(r#"```sql
> select btrim('__datafusion____', '_');
+-------------------------------------------+
| btrim(Utf8("__datafusion____"),Utf8("_")) |
+-------------------------------------------+
| datafusion |
+-------------------------------------------+
```"#)
.with_standard_argument("str", Some("String"))
.with_argument("trim_str", "String expression to operate on. Can be a constant, column, or function, and any combination of operators. _Default is whitespace characters._")
.with_alternative_syntax("trim(BOTH trim_str FROM str)")
.with_alternative_syntax("trim(trim_str FROM str)")
.with_related_udf("ltrim")
.with_related_udf("rtrim")
.build()
})
}

#[cfg(test)]
mod tests {
use arrow::array::{Array, StringArray, StringViewArray};
Expand Down
8 changes: 4 additions & 4 deletions datafusion/macros/src/user_doc.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ pub fn user_doc(args: TokenStream, input: TokenStream) -> TokenStream {

let mut description: Option<LitStr> = None;
let mut syntax_example: Option<LitStr> = None;
let mut alt_syntax_example: Option<LitStr> = None;
let mut alt_syntax_example: Vec<Option<LitStr>> = vec![];
let mut sql_example: Option<LitStr> = None;
let mut standard_args: Vec<(Option<LitStr>, Option<LitStr>)> = vec![];
let mut udf_args: Vec<(Option<LitStr>, Option<LitStr>)> = vec![];
Expand Down Expand Up @@ -131,7 +131,7 @@ pub fn user_doc(args: TokenStream, input: TokenStream) -> TokenStream {
syntax_example = Some(meta.value()?.parse()?);
Ok(())
} else if meta.path.is_ident("alternative_syntax") {
alt_syntax_example = Some(meta.value()?.parse()?);
alt_syntax_example.push(Some(meta.value()?.parse()?));
Ok(())
} else if meta.path.is_ident("sql_example") {
sql_example = Some(meta.value()?.parse()?);
Expand Down Expand Up @@ -242,7 +242,7 @@ pub fn user_doc(args: TokenStream, input: TokenStream) -> TokenStream {
})
.collect::<Vec<_>>();

let alt_syntax_example = alt_syntax_example.map(|syn| {
let alt_syntax_example = alt_syntax_example.iter().map(|syn| {
quote! {
.with_alternative_syntax(#syn)
}
Expand All @@ -258,7 +258,7 @@ pub fn user_doc(args: TokenStream, input: TokenStream) -> TokenStream {
datafusion_doc::Documentation::builder(datafusion_doc::DocSection { include: #doc_section_include, label: #doc_section_lbl, description: #doc_section_description },
#description.to_string(), #syntax_example.to_string())
#sql_example
#alt_syntax_example
#(#alt_syntax_example)*
Copy link
Contributor

Choose a reason for hiding this comment

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

🤯 -- very nice @delamarch3

Thank you

#(#standard_args)*
#(#udf_args)*
#(#related_udfs)*
Expand Down
Loading