mirror of
https://github.com/nushell/nushell.git
synced 2025-05-28 10:31:23 +00:00
# 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>
133 lines
4.4 KiB
Rust
133 lines
4.4 KiB
Rust
use chrono_humanize::HumanTime;
|
|
use nu_engine::command_prelude::*;
|
|
use nu_protocol::{format_duration, format_filesize_from_conf, ByteStream, Config};
|
|
|
|
const LINE_ENDING: &str = if cfg!(target_os = "windows") {
|
|
"\r\n"
|
|
} else {
|
|
"\n"
|
|
};
|
|
|
|
#[derive(Clone)]
|
|
pub struct ToText;
|
|
|
|
impl Command for ToText {
|
|
fn name(&self) -> &str {
|
|
"to text"
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build("to text")
|
|
.input_output_types(vec![(Type::Any, Type::String)])
|
|
.category(Category::Formats)
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Converts data into simple text."
|
|
}
|
|
|
|
fn run(
|
|
&self,
|
|
engine_state: &EngineState,
|
|
_stack: &mut Stack,
|
|
call: &Call,
|
|
input: PipelineData,
|
|
) -> Result<PipelineData, ShellError> {
|
|
let span = call.head;
|
|
let input = input.try_expand_range()?;
|
|
|
|
match input {
|
|
PipelineData::Empty => Ok(Value::string(String::new(), span).into_pipeline_data()),
|
|
PipelineData::Value(value, ..) => {
|
|
let str = local_into_string(value, LINE_ENDING, engine_state.get_config());
|
|
Ok(Value::string(str, span).into_pipeline_data())
|
|
}
|
|
PipelineData::ListStream(stream, meta) => {
|
|
let span = stream.span();
|
|
let config = engine_state.get_config().clone();
|
|
let iter = stream.into_inner().map(move |value| {
|
|
let mut str = local_into_string(value, LINE_ENDING, &config);
|
|
str.push_str(LINE_ENDING);
|
|
str
|
|
});
|
|
Ok(PipelineData::ByteStream(
|
|
ByteStream::from_iter(iter, span, engine_state.ctrlc.clone()),
|
|
meta,
|
|
))
|
|
}
|
|
PipelineData::ByteStream(stream, meta) => Ok(PipelineData::ByteStream(stream, meta)),
|
|
}
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![
|
|
Example {
|
|
description: "Outputs data as simple text",
|
|
example: "1 | to text",
|
|
result: Some(Value::test_string("1")),
|
|
},
|
|
Example {
|
|
description: "Outputs external data as simple text",
|
|
example: "git help -a | lines | find -r '^ ' | to text",
|
|
result: None,
|
|
},
|
|
Example {
|
|
description: "Outputs records as simple text",
|
|
example: "ls | to text",
|
|
result: None,
|
|
},
|
|
]
|
|
}
|
|
}
|
|
|
|
fn local_into_string(value: Value, separator: &str, config: &Config) -> String {
|
|
let span = value.span();
|
|
match value {
|
|
Value::Bool { val, .. } => val.to_string(),
|
|
Value::Int { val, .. } => val.to_string(),
|
|
Value::Float { val, .. } => val.to_string(),
|
|
Value::Filesize { val, .. } => format_filesize_from_conf(val, config),
|
|
Value::Duration { val, .. } => format_duration(val),
|
|
Value::Date { val, .. } => {
|
|
format!("{} ({})", val.to_rfc2822(), HumanTime::from(val))
|
|
}
|
|
Value::Range { val, .. } => val.to_string(),
|
|
Value::String { val, .. } => val,
|
|
Value::Glob { val, .. } => val,
|
|
Value::List { vals: val, .. } => val
|
|
.into_iter()
|
|
.map(|x| local_into_string(x, ", ", config))
|
|
.collect::<Vec<_>>()
|
|
.join(separator),
|
|
Value::Record { val, .. } => val
|
|
.into_owned()
|
|
.into_iter()
|
|
.map(|(x, y)| format!("{}: {}", x, local_into_string(y, ", ", config)))
|
|
.collect::<Vec<_>>()
|
|
.join(separator),
|
|
Value::Closure { val, .. } => format!("<Closure {}>", val.block_id),
|
|
Value::Nothing { .. } => String::new(),
|
|
Value::Error { error, .. } => format!("{error:?}"),
|
|
Value::Binary { val, .. } => format!("{val:?}"),
|
|
Value::CellPath { val, .. } => val.to_string(),
|
|
// If we fail to collapse the custom value, just print <{type_name}> - failure is not
|
|
// that critical here
|
|
Value::Custom { val, .. } => val
|
|
.to_base_value(span)
|
|
.map(|val| local_into_string(val, separator, config))
|
|
.unwrap_or_else(|_| format!("<{}>", val.type_name())),
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod test {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn test_examples() {
|
|
use crate::test_examples;
|
|
|
|
test_examples(ToText {})
|
|
}
|
|
}
|