Files
nushell/crates/nu-cmd-dataframe/src/dataframe/eager/rename.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

183 lines
5.8 KiB
Rust

use nu_engine::CallExt;
use nu_protocol::{
ast::Call,
engine::{Command, EngineState, Stack},
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
};
use crate::dataframe::{utils::extract_strings, values::NuLazyFrame};
use super::super::values::{Column, NuDataFrame};
#[derive(Clone)]
pub struct RenameDF;
impl Command for RenameDF {
fn name(&self) -> &str {
"dfr rename"
}
fn usage(&self) -> &str {
"Rename a dataframe column."
}
fn signature(&self) -> Signature {
Signature::build(self.name())
.required(
"columns",
SyntaxShape::Any,
"Column(s) to be renamed. A string or list of strings",
)
.required(
"new names",
SyntaxShape::Any,
"New names for the selected column(s). A string or list of strings",
)
.input_output_type(
Type::Custom("dataframe".into()),
Type::Custom("dataframe".into()),
)
.category(Category::Custom("dataframe or lazyframe".into()))
}
fn examples(&self) -> Vec<Example> {
vec![
Example {
description: "Renames a series",
example: "[5 6 7 8] | dfr into-df | dfr rename '0' new_name",
result: Some(
NuDataFrame::try_from_columns(vec![Column::new(
"new_name".to_string(),
vec![
Value::test_int(5),
Value::test_int(6),
Value::test_int(7),
Value::test_int(8),
],
)])
.expect("simple df for test should not fail")
.into_value(Span::test_data()),
),
},
Example {
description: "Renames a dataframe column",
example: "[[a b]; [1 2] [3 4]] | dfr into-df | dfr rename a a_new",
result: Some(
NuDataFrame::try_from_columns(vec![
Column::new(
"a_new".to_string(),
vec![Value::test_int(1), Value::test_int(3)],
),
Column::new(
"b".to_string(),
vec![Value::test_int(2), Value::test_int(4)],
),
])
.expect("simple df for test should not fail")
.into_value(Span::test_data()),
),
},
Example {
description: "Renames two dataframe columns",
example: "[[a b]; [1 2] [3 4]] | dfr into-df | dfr rename [a b] [a_new b_new]",
result: Some(
NuDataFrame::try_from_columns(vec![
Column::new(
"a_new".to_string(),
vec![Value::test_int(1), Value::test_int(3)],
),
Column::new(
"b_new".to_string(),
vec![Value::test_int(2), Value::test_int(4)],
),
])
.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> {
let value = input.into_value(call.head);
if NuLazyFrame::can_downcast(&value) {
let df = NuLazyFrame::try_from_value(value)?;
command_lazy(engine_state, stack, call, df)
} else {
let df = NuDataFrame::try_from_value(value)?;
command_eager(engine_state, stack, call, df)
}
}
}
fn command_eager(
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
mut df: NuDataFrame,
) -> Result<PipelineData, ShellError> {
let columns: Value = call.req(engine_state, stack, 0)?;
let columns = extract_strings(columns)?;
let new_names: Value = call.req(engine_state, stack, 1)?;
let new_names = extract_strings(new_names)?;
for (from, to) in columns.iter().zip(new_names.iter()) {
df.as_mut().rename(from, to).map_err(|e| {
ShellError::GenericError(
"Error renaming".into(),
e.to_string(),
Some(call.head),
None,
Vec::new(),
)
})?;
}
Ok(PipelineData::Value(df.into_value(call.head), None))
}
fn command_lazy(
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
lazy: NuLazyFrame,
) -> Result<PipelineData, ShellError> {
let columns: Value = call.req(engine_state, stack, 0)?;
let columns = extract_strings(columns)?;
let new_names: Value = call.req(engine_state, stack, 1)?;
let new_names = extract_strings(new_names)?;
if columns.len() != new_names.len() {
let value: Value = call.req(engine_state, stack, 1)?;
return Err(ShellError::IncompatibleParametersSingle {
msg: "New name list has different size to column list".into(),
span: value.span(),
});
}
let lazy = lazy.into_polars();
let lazy: NuLazyFrame = lazy.rename(&columns, &new_names).into();
Ok(PipelineData::Value(lazy.into_value(call.head)?, None))
}
#[cfg(test)]
mod test {
use super::super::super::test_dataframe::test_dataframe;
use super::*;
#[test]
fn test_examples() {
test_dataframe(vec![Box::new(RenameDF {})])
}
}