mirror of
https://github.com/nushell/nushell.git
synced 2025-07-07 18:07:02 +02:00
Replace ExternalStream
with new ByteStream
type (#12774)
# 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>
This commit is contained in:
@ -1,5 +1,6 @@
|
||||
use miette::Diagnostic;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::io;
|
||||
use thiserror::Error;
|
||||
|
||||
use crate::{
|
||||
@ -1374,42 +1375,79 @@ impl ShellError {
|
||||
}
|
||||
}
|
||||
|
||||
impl From<std::io::Error> for ShellError {
|
||||
fn from(input: std::io::Error) -> ShellError {
|
||||
ShellError::IOError {
|
||||
msg: format!("{input:?}"),
|
||||
impl From<io::Error> for ShellError {
|
||||
fn from(error: io::Error) -> ShellError {
|
||||
if error.kind() == io::ErrorKind::Other {
|
||||
match error.into_inner() {
|
||||
Some(err) => match err.downcast() {
|
||||
Ok(err) => *err,
|
||||
Err(err) => Self::IOError {
|
||||
msg: err.to_string(),
|
||||
},
|
||||
},
|
||||
None => Self::IOError {
|
||||
msg: "unknown error".into(),
|
||||
},
|
||||
}
|
||||
} else {
|
||||
Self::IOError {
|
||||
msg: error.to_string(),
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Spanned<std::io::Error>> for ShellError {
|
||||
fn from(error: Spanned<std::io::Error>) -> Self {
|
||||
ShellError::IOErrorSpanned {
|
||||
msg: error.item.to_string(),
|
||||
span: error.span,
|
||||
impl From<Spanned<io::Error>> for ShellError {
|
||||
fn from(error: Spanned<io::Error>) -> Self {
|
||||
let Spanned { item: error, span } = error;
|
||||
if error.kind() == io::ErrorKind::Other {
|
||||
match error.into_inner() {
|
||||
Some(err) => match err.downcast() {
|
||||
Ok(err) => *err,
|
||||
Err(err) => Self::IOErrorSpanned {
|
||||
msg: err.to_string(),
|
||||
span,
|
||||
},
|
||||
},
|
||||
None => Self::IOErrorSpanned {
|
||||
msg: "unknown error".into(),
|
||||
span,
|
||||
},
|
||||
}
|
||||
} else {
|
||||
Self::IOErrorSpanned {
|
||||
msg: error.to_string(),
|
||||
span,
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl std::convert::From<Box<dyn std::error::Error>> for ShellError {
|
||||
fn from(input: Box<dyn std::error::Error>) -> ShellError {
|
||||
impl From<ShellError> for io::Error {
|
||||
fn from(error: ShellError) -> Self {
|
||||
io::Error::new(io::ErrorKind::Other, error)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Box<dyn std::error::Error>> for ShellError {
|
||||
fn from(error: Box<dyn std::error::Error>) -> ShellError {
|
||||
ShellError::IOError {
|
||||
msg: input.to_string(),
|
||||
msg: error.to_string(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Box<dyn std::error::Error + Send + Sync>> for ShellError {
|
||||
fn from(input: Box<dyn std::error::Error + Send + Sync>) -> ShellError {
|
||||
fn from(error: Box<dyn std::error::Error + Send + Sync>) -> ShellError {
|
||||
ShellError::IOError {
|
||||
msg: format!("{input:?}"),
|
||||
msg: format!("{error:?}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<super::LabeledError> for ShellError {
|
||||
fn from(value: super::LabeledError) -> Self {
|
||||
ShellError::LabeledError(Box::new(value))
|
||||
fn from(error: super::LabeledError) -> Self {
|
||||
ShellError::LabeledError(Box::new(error))
|
||||
}
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user