mirror of
https://github.com/nushell/nushell.git
synced 2025-07-08 02:17:22 +02:00
c747ec75c9
# Description
When implementing a `Command`, one must also import all the types
present in the function signatures for `Command`. This makes it so that
we often import the same set of types in each command implementation
file. E.g., something like this:
```rust
use nu_protocol::ast::Call;
use nu_protocol::engine::{Command, EngineState, Stack};
use nu_protocol::{
record, Category, Example, IntoInterruptiblePipelineData, IntoPipelineData, PipelineData,
ShellError, Signature, Span, Type, Value,
};
```
This PR adds the `nu_engine::command_prelude` module which contains the
necessary and commonly used types to implement a `Command`:
```rust
// command_prelude.rs
pub use crate::CallExt;
pub use nu_protocol::{
ast::{Call, CellPath},
engine::{Command, EngineState, Stack},
record, Category, Example, IntoInterruptiblePipelineData, IntoPipelineData, IntoSpanned,
PipelineData, Record, ShellError, Signature, Span, Spanned, SyntaxShape, Type, Value,
};
```
This should reduce the boilerplate needed to implement a command and
also gives us a place to track the breadth of the `Command` API. I tried
to be conservative with what went into the prelude modules, since it
might be hard/annoying to remove items from the prelude in the future.
Let me know if something should be included or excluded.
120 lines
3.5 KiB
Rust
120 lines
3.5 KiB
Rust
use crate::dataframe::values::{utils::convert_columns_string, Column, NuDataFrame};
|
|
use nu_engine::command_prelude::*;
|
|
|
|
use polars::prelude::UniqueKeepStrategy;
|
|
|
|
#[derive(Clone)]
|
|
pub struct DropDuplicates;
|
|
|
|
impl Command for DropDuplicates {
|
|
fn name(&self) -> &str {
|
|
"dfr drop-duplicates"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Drops duplicate values in dataframe."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.optional(
|
|
"subset",
|
|
SyntaxShape::Table(vec![]),
|
|
"subset of columns to drop duplicates",
|
|
)
|
|
.switch("maintain", "maintain order", Some('m'))
|
|
.switch(
|
|
"last",
|
|
"keeps last duplicate value (by default keeps first)",
|
|
Some('l'),
|
|
)
|
|
.input_output_type(
|
|
Type::Custom("dataframe".into()),
|
|
Type::Custom("dataframe".into()),
|
|
)
|
|
.category(Category::Custom("dataframe".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![Example {
|
|
description: "drop duplicates",
|
|
example: "[[a b]; [1 2] [3 4] [1 2]] | dfr into-df | dfr drop-duplicates",
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![
|
|
Column::new(
|
|
"a".to_string(),
|
|
vec![Value::test_int(3), Value::test_int(1)],
|
|
),
|
|
Column::new(
|
|
"b".to_string(),
|
|
vec![Value::test_int(4), Value::test_int(2)],
|
|
),
|
|
],
|
|
None,
|
|
)
|
|
.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 columns: Option<Vec<Value>> = call.opt(engine_state, stack, 0)?;
|
|
let (subset, col_span) = match columns {
|
|
Some(cols) => {
|
|
let (agg_string, col_span) = convert_columns_string(cols, call.head)?;
|
|
(Some(agg_string), col_span)
|
|
}
|
|
None => (None, call.head),
|
|
};
|
|
|
|
let df = NuDataFrame::try_from_pipeline(input, call.head)?;
|
|
|
|
let subset_slice = subset.as_ref().map(|cols| &cols[..]);
|
|
|
|
let keep_strategy = if call.has_flag(engine_state, stack, "last")? {
|
|
UniqueKeepStrategy::Last
|
|
} else {
|
|
UniqueKeepStrategy::First
|
|
};
|
|
|
|
df.as_ref()
|
|
.unique(subset_slice, keep_strategy, None)
|
|
.map_err(|e| ShellError::GenericError {
|
|
error: "Error dropping duplicates".into(),
|
|
msg: e.to_string(),
|
|
span: Some(col_span),
|
|
help: None,
|
|
inner: vec![],
|
|
})
|
|
.map(|df| PipelineData::Value(NuDataFrame::dataframe_into_value(df, 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(DropDuplicates {})])
|
|
}
|
|
}
|