6fd854ed9f
# Description
This PR introduces a `ByteStream` type which is a `Read`-able stream of
bytes. Internally, it has an enum over three different byte stream
sources:
```rust
pub enum ByteStreamSource {
Read(Box<dyn Read + Send + 'static>),
File(File),
Child(ChildProcess),
}
```
This is in comparison to the current `RawStream` type, which is an
`Iterator<Item = Vec<u8>>` and has to allocate for each read chunk.
Currently, `PipelineData::ExternalStream` serves a weird dual role where
it is either external command output or a wrapper around `RawStream`.
`ByteStream` makes this distinction more clear (via `ByteStreamSource`)
and replaces `PipelineData::ExternalStream` in this PR:
```rust
pub enum PipelineData {
Empty,
Value(Value, Option<PipelineMetadata>),
ListStream(ListStream, Option<PipelineMetadata>),
ByteStream(ByteStream, Option<PipelineMetadata>),
}
```
The PR is relatively large, but a decent amount of it is just repetitive
changes.
This PR fixes #7017, fixes #10763, and fixes #12369.
This PR also improves performance when piping external commands. Nushell
should, in most cases, have competitive pipeline throughput compared to,
e.g., bash.
| Command | Before (MB/s) | After (MB/s) | Bash (MB/s) |
| -------------------------------------------------- | -------------:|
------------:| -----------:|
| `throughput \| rg 'x'` | 3059 | 3744 | 3739 |
| `throughput \| nu --testbin relay o> /dev/null` | 3508 | 8087 | 8136 |
# User-Facing Changes
- This is a breaking change for the plugin communication protocol,
because the `ExternalStreamInfo` was replaced with `ByteStreamInfo`.
Plugins now only have to deal with a single input stream, as opposed to
the previous three streams: stdout, stderr, and exit code.
- The output of `describe` has been changed for external/byte streams.
- Temporary breaking change: `bytes starts-with` no longer works with
byte streams. This is to keep the PR smaller, and `bytes ends-with`
already does not work on byte streams.
- If a process core dumped, then instead of having a `Value::Error` in
the `exit_code` column of the output returned from `complete`, it now is
a `Value::Int` with the negation of the signal number.
# After Submitting
- Update docs and book as necessary
- Release notes (e.g., plugin protocol changes)
- Adapt/convert commands to work with byte streams (high priority is
`str length`, `bytes starts-with`, and maybe `bytes ends-with`).
- Refactor the `tee` code, Devyn has already done some work on this.
---------
Co-authored-by: Devyn Cairns <devyn.cairns@gmail.com>
253 lines
9.8 KiB
Rust
253 lines
9.8 KiB
Rust
use crate::dataframe::values::{Column, NuDataFrame, NuExpression, NuLazyFrame};
|
|
use nu_engine::command_prelude::*;
|
|
|
|
use polars::prelude::{Expr, JoinType};
|
|
|
|
#[derive(Clone)]
|
|
pub struct LazyJoin;
|
|
|
|
impl Command for LazyJoin {
|
|
fn name(&self) -> &str {
|
|
"dfr join"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Joins a lazy frame with other lazy frame."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.required("other", SyntaxShape::Any, "LazyFrame to join with")
|
|
.required("left_on", SyntaxShape::Any, "Left column(s) to join on")
|
|
.required("right_on", SyntaxShape::Any, "Right column(s) to join on")
|
|
.switch(
|
|
"inner",
|
|
"inner join between lazyframes (default)",
|
|
Some('i'),
|
|
)
|
|
.switch("left", "left join between lazyframes", Some('l'))
|
|
.switch("outer", "outer join between lazyframes", Some('o'))
|
|
.switch("cross", "cross join between lazyframes", Some('c'))
|
|
.named(
|
|
"suffix",
|
|
SyntaxShape::String,
|
|
"Suffix to use on columns with same name",
|
|
Some('s'),
|
|
)
|
|
.input_output_type(
|
|
Type::Custom("dataframe".into()),
|
|
Type::Custom("dataframe".into()),
|
|
)
|
|
.category(Category::Custom("lazyframe".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![
|
|
Example {
|
|
description: "Join two lazy dataframes",
|
|
example: r#"let df_a = ([[a b c];[1 "a" 0] [2 "b" 1] [1 "c" 2] [1 "c" 3]] | dfr into-lazy);
|
|
let df_b = ([["foo" "bar" "ham"];[1 "a" "let"] [2 "c" "var"] [3 "c" "const"]] | dfr into-lazy);
|
|
$df_a | dfr join $df_b a foo | dfr collect"#,
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![
|
|
Column::new(
|
|
"a".to_string(),
|
|
vec![
|
|
Value::test_int(1),
|
|
Value::test_int(2),
|
|
Value::test_int(1),
|
|
Value::test_int(1),
|
|
],
|
|
),
|
|
Column::new(
|
|
"b".to_string(),
|
|
vec![
|
|
Value::test_string("a"),
|
|
Value::test_string("b"),
|
|
Value::test_string("c"),
|
|
Value::test_string("c"),
|
|
],
|
|
),
|
|
Column::new(
|
|
"c".to_string(),
|
|
vec![
|
|
Value::test_int(0),
|
|
Value::test_int(1),
|
|
Value::test_int(2),
|
|
Value::test_int(3),
|
|
],
|
|
),
|
|
Column::new(
|
|
"bar".to_string(),
|
|
vec![
|
|
Value::test_string("a"),
|
|
Value::test_string("c"),
|
|
Value::test_string("a"),
|
|
Value::test_string("a"),
|
|
],
|
|
),
|
|
Column::new(
|
|
"ham".to_string(),
|
|
vec![
|
|
Value::test_string("let"),
|
|
Value::test_string("var"),
|
|
Value::test_string("let"),
|
|
Value::test_string("let"),
|
|
],
|
|
),
|
|
],
|
|
None,
|
|
)
|
|
.expect("simple df for test should not fail")
|
|
.into_value(Span::test_data()),
|
|
),
|
|
},
|
|
Example {
|
|
description: "Join one eager dataframe with a lazy dataframe",
|
|
example: r#"let df_a = ([[a b c];[1 "a" 0] [2 "b" 1] [1 "c" 2] [1 "c" 3]] | dfr into-df);
|
|
let df_b = ([["foo" "bar" "ham"];[1 "a" "let"] [2 "c" "var"] [3 "c" "const"]] | dfr into-lazy);
|
|
$df_a | dfr join $df_b a foo"#,
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![
|
|
Column::new(
|
|
"a".to_string(),
|
|
vec![
|
|
Value::test_int(1),
|
|
Value::test_int(2),
|
|
Value::test_int(1),
|
|
Value::test_int(1),
|
|
],
|
|
),
|
|
Column::new(
|
|
"b".to_string(),
|
|
vec![
|
|
Value::test_string("a"),
|
|
Value::test_string("b"),
|
|
Value::test_string("c"),
|
|
Value::test_string("c"),
|
|
],
|
|
),
|
|
Column::new(
|
|
"c".to_string(),
|
|
vec![
|
|
Value::test_int(0),
|
|
Value::test_int(1),
|
|
Value::test_int(2),
|
|
Value::test_int(3),
|
|
],
|
|
),
|
|
Column::new(
|
|
"bar".to_string(),
|
|
vec![
|
|
Value::test_string("a"),
|
|
Value::test_string("c"),
|
|
Value::test_string("a"),
|
|
Value::test_string("a"),
|
|
],
|
|
),
|
|
Column::new(
|
|
"ham".to_string(),
|
|
vec![
|
|
Value::test_string("let"),
|
|
Value::test_string("var"),
|
|
Value::test_string("let"),
|
|
Value::test_string("let"),
|
|
],
|
|
),
|
|
],
|
|
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> {
|
|
let left = call.has_flag(engine_state, stack, "left")?;
|
|
let outer = call.has_flag(engine_state, stack, "outer")?;
|
|
let cross = call.has_flag(engine_state, stack, "cross")?;
|
|
|
|
let how = if left {
|
|
JoinType::Left
|
|
} else if outer {
|
|
JoinType::Outer { coalesce: true }
|
|
} else if cross {
|
|
JoinType::Cross
|
|
} else {
|
|
JoinType::Inner
|
|
};
|
|
|
|
let other: Value = call.req(engine_state, stack, 0)?;
|
|
let other = NuLazyFrame::try_from_value(other)?;
|
|
let other = other.into_polars();
|
|
|
|
let left_on: Value = call.req(engine_state, stack, 1)?;
|
|
let left_on = NuExpression::extract_exprs(left_on)?;
|
|
|
|
let right_on: Value = call.req(engine_state, stack, 2)?;
|
|
let right_on = NuExpression::extract_exprs(right_on)?;
|
|
|
|
if left_on.len() != right_on.len() {
|
|
let right_on: Value = call.req(engine_state, stack, 2)?;
|
|
return Err(ShellError::IncompatibleParametersSingle {
|
|
msg: "The right column list has a different size to the left column list".into(),
|
|
span: right_on.span(),
|
|
});
|
|
}
|
|
|
|
// Checking that both list of expressions are made out of col expressions or strings
|
|
for (index, list) in &[(1usize, &left_on), (2, &left_on)] {
|
|
if list.iter().any(|expr| !matches!(expr, Expr::Column(..))) {
|
|
let value: Value = call.req(engine_state, stack, *index)?;
|
|
return Err(ShellError::IncompatibleParametersSingle {
|
|
msg: "Expected only a string, col expressions or list of strings".into(),
|
|
span: value.span(),
|
|
});
|
|
}
|
|
}
|
|
|
|
let suffix: Option<String> = call.get_flag(engine_state, stack, "suffix")?;
|
|
let suffix = suffix.unwrap_or_else(|| "_x".into());
|
|
|
|
let value = input.into_value(call.head)?;
|
|
let lazy = NuLazyFrame::try_from_value(value)?;
|
|
let from_eager = lazy.from_eager;
|
|
let lazy = lazy.into_polars();
|
|
|
|
let lazy = lazy
|
|
.join_builder()
|
|
.with(other)
|
|
.left_on(left_on)
|
|
.right_on(right_on)
|
|
.how(how)
|
|
.force_parallel(true)
|
|
.suffix(suffix)
|
|
.finish();
|
|
|
|
let lazy = NuLazyFrame::new(from_eager, lazy);
|
|
|
|
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(LazyJoin {})])
|
|
}
|
|
}
|