nushell/crates/nu-cmd-dataframe/src/dataframe/series/string/concatenate.rs
JT 1e3e034021
Spanned Value step 1: span all value cases (#10042)
# Description

This doesn't really do much that the user could see, but it helps get us
ready to do the steps of the refactor to split the span off of Value, so
that values can be spanless. This allows us to have top-level values
that can hold both a Value and a Span, without requiring that all values
have them.

We expect to see significant memory reduction by removing so many
unnecessary spans from values. For example, a table of 100,000 rows and
5 columns would have a savings of ~8megs in just spans that are almost
always duplicated.

# User-Facing Changes

Nothing yet

# Tests + Formatting
<!--
Don't forget to add tests that cover your changes.

Make sure you've run and fixed any issues with these commands:

- `cargo fmt --all -- --check` to check standard code formatting (`cargo
fmt --all` applies these changes)
- `cargo clippy --workspace -- -D warnings -D clippy::unwrap_used -A
clippy::needless_collect -A clippy::result_large_err` to check that
you're using the standard code style
- `cargo test --workspace` to check that all tests pass
- `cargo run -- -c "use std testing; testing run-tests --path
crates/nu-std"` to run the tests for the standard library

> **Note**
> from `nushell` you can also use the `toolkit` as follows
> ```bash
> use toolkit.nu # or use an `env_change` hook to activate it
automatically
> toolkit check pr
> ```
-->

# After Submitting
<!-- If your PR had any user-facing changes, update [the
documentation](https://github.com/nushell/nushell.github.io) after the
PR is merged, if necessary. This will help us keep the docs up to date.
-->
2023-08-25 08:48:05 +12:00

120 lines
3.3 KiB
Rust

use super::super::super::values::{Column, NuDataFrame};
use nu_engine::CallExt;
use nu_protocol::{
ast::Call,
engine::{Command, EngineState, Stack},
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
};
use polars::prelude::{IntoSeries, Utf8NameSpaceImpl};
#[derive(Clone)]
pub struct Concatenate;
impl Command for Concatenate {
fn name(&self) -> &str {
"dfr concatenate"
}
fn usage(&self) -> &str {
"Concatenates strings with other array."
}
fn signature(&self) -> Signature {
Signature::build(self.name())
.required(
"other",
SyntaxShape::Any,
"Other array with string to be concatenated",
)
.input_output_type(
Type::Custom("dataframe".into()),
Type::Custom("dataframe".into()),
)
.category(Category::Custom("dataframe".into()))
}
fn examples(&self) -> Vec<Example> {
vec![Example {
description: "Concatenate string",
example: r#"let other = ([za xs cd] | dfr into-df);
[abc abc abc] | dfr into-df | dfr concatenate $other"#,
result: Some(
NuDataFrame::try_from_columns(vec![Column::new(
"0".to_string(),
vec![
Value::test_string("abcza"),
Value::test_string("abcxs"),
Value::test_string("abccd"),
],
)])
.expect("simple df for test should not fail")
.into_value(Span::test_data()),
),
}]
}
fn run(
&self,
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
input: PipelineData,
) -> Result<PipelineData, ShellError> {
command(engine_state, stack, call, input)
}
}
fn command(
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
input: PipelineData,
) -> Result<PipelineData, ShellError> {
let df = NuDataFrame::try_from_pipeline(input, call.head)?;
let other: Value = call.req(engine_state, stack, 0)?;
let other_span = other.span();
let other_df = NuDataFrame::try_from_value(other)?;
let other_series = other_df.as_series(other_span)?;
let other_chunked = other_series.utf8().map_err(|e| {
ShellError::GenericError(
"The concatenate only with string columns".into(),
e.to_string(),
Some(other_span),
None,
Vec::new(),
)
})?;
let series = df.as_series(call.head)?;
let chunked = series.utf8().map_err(|e| {
ShellError::GenericError(
"The concatenate only with string columns".into(),
e.to_string(),
Some(call.head),
None,
Vec::new(),
)
})?;
let mut res = chunked.concat(other_chunked);
res.rename(series.name());
NuDataFrame::try_from_series(vec![res.into_series()], call.head)
.map(|df| PipelineData::Value(NuDataFrame::into_value(df, call.head), None))
}
#[cfg(test)]
mod test {
use super::super::super::super::test_dataframe::test_dataframe;
use super::*;
#[test]
fn test_examples() {
test_dataframe(vec![Box::new(Concatenate {})])
}
}