mirror of
https://github.com/nushell/nushell.git
synced 2024-11-25 18:03:51 +01:00
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>
296 lines
8.0 KiB
Rust
296 lines
8.0 KiB
Rust
use nu_test_support::fs::Stub::FileWithContentToBeTrimmed;
|
|
use nu_test_support::playground::Playground;
|
|
use nu_test_support::{nu, pipeline};
|
|
|
|
#[test]
|
|
fn table_to_tsv_text_and_from_tsv_text_back_into_table() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open caco3_plastics.tsv | to tsv | from tsv | first | get origin"
|
|
);
|
|
|
|
assert_eq!(actual.out, "SPAIN");
|
|
}
|
|
|
|
#[test]
|
|
fn table_to_tsv_text_and_from_tsv_text_back_into_table_using_csv_separator() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
r#"open caco3_plastics.tsv | to tsv | from csv --separator "\t" | first | get origin"#
|
|
);
|
|
|
|
assert_eq!(actual.out, "SPAIN");
|
|
}
|
|
|
|
#[test]
|
|
fn table_to_tsv_text() {
|
|
Playground::setup("filter_to_tsv_test_1", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"tsv_text_sample.txt",
|
|
r#"
|
|
importer shipper tariff_item name origin
|
|
Plasticos Rival Reverte 2509000000 Calcium carbonate Spain
|
|
Tigre Ecuador OMYA Andina 3824909999 Calcium carbonate Colombia
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open tsv_text_sample.txt
|
|
| lines
|
|
| split column "\t" a b c d origin
|
|
| last 1
|
|
| to tsv
|
|
| lines
|
|
| select 1
|
|
"#
|
|
));
|
|
|
|
assert!(actual.out.contains("Colombia"));
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn table_to_tsv_text_skipping_headers_after_conversion() {
|
|
Playground::setup("filter_to_tsv_test_2", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"tsv_text_sample.txt",
|
|
r#"
|
|
importer shipper tariff_item name origin
|
|
Plasticos Rival Reverte 2509000000 Calcium carbonate Spain
|
|
Tigre Ecuador OMYA Andina 3824909999 Calcium carbonate Colombia
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open tsv_text_sample.txt
|
|
| lines
|
|
| split column "\t" a b c d origin
|
|
| last 1
|
|
| to tsv --noheaders
|
|
"#
|
|
));
|
|
|
|
assert!(actual.out.contains("Colombia"));
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_to_table() {
|
|
Playground::setup("filter_from_tsv_test_1", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_amigos.txt",
|
|
r#"
|
|
first Name Last Name rusty_luck
|
|
Andrés Robalino 1
|
|
JT Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_amigos.txt
|
|
| from tsv
|
|
| get rusty_luck
|
|
| length
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "3");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
#[ignore = "csv crate has a bug when the last line is a comment: https://github.com/BurntSushi/rust-csv/issues/363"]
|
|
fn from_tsv_text_with_comments_to_table() {
|
|
Playground::setup("filter_from_tsv_test_2", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
# This is a comment
|
|
first_name last_name rusty_luck
|
|
# This one too
|
|
Andrés Robalino 1
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
# This one also
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r##"
|
|
open los_tres_caballeros.txt
|
|
| from tsv --comment "#"
|
|
| get rusty_luck
|
|
| length
|
|
"##
|
|
));
|
|
|
|
assert_eq!(actual.out, "3");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_with_custom_quotes_to_table() {
|
|
Playground::setup("filter_from_tsv_test_3", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
first_name last_name rusty_luck
|
|
'And''rés' Robalino 1
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_caballeros.txt
|
|
| from tsv --quote "'"
|
|
| first
|
|
| get first_name
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "And'rés");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_with_custom_escapes_to_table() {
|
|
Playground::setup("filter_from_tsv_test_4", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
first_name last_name rusty_luck
|
|
"And\"rés" Robalino 1
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r"
|
|
open los_tres_caballeros.txt
|
|
| from tsv --escape '\'
|
|
| first
|
|
| get first_name
|
|
"
|
|
));
|
|
|
|
assert_eq!(actual.out, "And\"rés");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_skipping_headers_to_table() {
|
|
Playground::setup("filter_from_tsv_test_5", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_amigos.txt",
|
|
r#"
|
|
Andrés Robalino 1
|
|
JT Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_amigos.txt
|
|
| from tsv --noheaders
|
|
| get column3
|
|
| length
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "3");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_with_missing_columns_to_table() {
|
|
Playground::setup("filter_from_tsv_test_6", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
first_name last_name rusty_luck
|
|
Andrés Robalino
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_caballeros.txt
|
|
| from tsv --flexible
|
|
| get -i rusty_luck
|
|
| compact
|
|
| length
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "2");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_with_multiple_char_comment() {
|
|
Playground::setup("filter_from_tsv_test_7", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
first_name last_name rusty_luck
|
|
Andrés Robalino 1
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_caballeros.txt
|
|
| from csv --comment "li"
|
|
"#
|
|
));
|
|
|
|
assert!(actual.err.contains("single character separator"));
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn from_tsv_text_with_wrong_type_comment() {
|
|
Playground::setup("filter_from_csv_test_8", |dirs, sandbox| {
|
|
sandbox.with_files(&[FileWithContentToBeTrimmed(
|
|
"los_tres_caballeros.txt",
|
|
r#"
|
|
first_name last_name rusty_luck
|
|
Andrés Robalino 1
|
|
Jonathan Turner 1
|
|
Yehuda Katz 1
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open los_tres_caballeros.txt
|
|
| from csv --comment ('123' | into int)
|
|
"#
|
|
));
|
|
|
|
assert!(actual.err.contains("can't convert int to char"));
|
|
})
|
|
}
|