2019-10-20 23:42:07 +00:00
|
|
|
use crate::commands::WholeStreamCommand;
|
|
|
|
use crate::prelude::*;
|
2020-05-18 12:56:01 +00:00
|
|
|
use indexmap::indexmap;
|
Extract core stuff into own crates
This commit extracts five new crates:
- nu-source, which contains the core source-code handling logic in Nu,
including Text, Span, and also the pretty.rs-based debug logic
- nu-parser, which is the parser and expander logic
- nu-protocol, which is the bulk of the types and basic conveniences
used by plugins
- nu-errors, which contains ShellError, ParseError and error handling
conveniences
- nu-textview, which is the textview plugin extracted into a crate
One of the major consequences of this refactor is that it's no longer
possible to `impl X for Spanned<Y>` outside of the `nu-source` crate, so
a lot of types became more concrete (Value became a concrete type
instead of Spanned<Value>, for example).
This also turned a number of inherent methods in the main nu crate into
plain functions (impl Value {} became a bunch of functions in the
`value` namespace in `crate::data::value`).
2019-11-26 02:30:48 +00:00
|
|
|
use nu_errors::ShellError;
|
2020-05-18 12:56:01 +00:00
|
|
|
use nu_protocol::{ReturnSuccess, Signature, SyntaxShape, UntaggedValue, Value};
|
2019-11-21 14:33:14 +00:00
|
|
|
use nu_source::Tagged;
|
2019-10-20 23:42:07 +00:00
|
|
|
|
|
|
|
pub struct GroupBy;
|
|
|
|
|
|
|
|
#[derive(Deserialize)]
|
|
|
|
pub struct GroupByArgs {
|
2020-05-15 09:16:09 +00:00
|
|
|
column_name: Option<Tagged<String>>,
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
impl WholeStreamCommand for GroupBy {
|
|
|
|
fn name(&self) -> &str {
|
|
|
|
"group-by"
|
|
|
|
}
|
|
|
|
|
|
|
|
fn signature(&self) -> Signature {
|
2020-05-15 09:16:09 +00:00
|
|
|
Signature::build("group-by").optional(
|
|
|
|
"column_name",
|
|
|
|
SyntaxShape::String,
|
|
|
|
"the name of the column to group by",
|
|
|
|
)
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
fn usage(&self) -> &str {
|
|
|
|
"Creates a new table with the data from the table rows grouped by the column given."
|
|
|
|
}
|
|
|
|
|
|
|
|
fn run(
|
|
|
|
&self,
|
|
|
|
args: CommandArgs,
|
|
|
|
registry: &CommandRegistry,
|
|
|
|
) -> Result<OutputStream, ShellError> {
|
2020-05-16 03:18:24 +00:00
|
|
|
group_by(args, registry)
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|
2020-05-12 15:54:29 +00:00
|
|
|
|
2020-05-18 12:56:01 +00:00
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
|
|
vec![
|
|
|
|
Example {
|
|
|
|
description: "Group items by type",
|
|
|
|
example: r#"ls | group-by type"#,
|
|
|
|
result: None,
|
|
|
|
},
|
|
|
|
Example {
|
|
|
|
description: "Group items by their value",
|
|
|
|
example: "echo [1 3 1 3 2 1 1] | group-by",
|
|
|
|
result: Some(vec![UntaggedValue::row(indexmap! {
|
|
|
|
"1".to_string() => UntaggedValue::Table(vec![
|
|
|
|
UntaggedValue::int(1).into(),
|
|
|
|
UntaggedValue::int(1).into(),
|
|
|
|
UntaggedValue::int(1).into(),
|
|
|
|
UntaggedValue::int(1).into(),
|
|
|
|
]).into(),
|
|
|
|
|
|
|
|
"3".to_string() => UntaggedValue::Table(vec![
|
|
|
|
UntaggedValue::int(3).into(),
|
|
|
|
UntaggedValue::int(3).into(),
|
|
|
|
]).into(),
|
|
|
|
|
|
|
|
"2".to_string() => UntaggedValue::Table(vec![
|
|
|
|
UntaggedValue::int(2).into(),
|
|
|
|
]).into(),
|
|
|
|
})
|
|
|
|
.into()]),
|
|
|
|
},
|
|
|
|
]
|
2020-05-12 15:54:29 +00:00
|
|
|
}
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|
|
|
|
|
2020-05-16 03:18:24 +00:00
|
|
|
pub fn group_by(args: CommandArgs, registry: &CommandRegistry) -> Result<OutputStream, ShellError> {
|
|
|
|
let registry = registry.clone();
|
|
|
|
let name = args.call_info.name_tag.clone();
|
2019-10-20 23:42:07 +00:00
|
|
|
let stream = async_stream! {
|
2020-05-16 03:18:24 +00:00
|
|
|
let (GroupByArgs { column_name }, mut input) = args.process(®istry).await?;
|
Move external closer to internal (#1611)
* Refactor InputStream and affected commands.
First, making `values` private and leaning on the `Stream` implementation makes
consumes of `InputStream` less likely to have to change in the future, if we
change what an `InputStream` is internally.
Second, we're dropping `Option<InputStream>` as the input to pipelines,
internals, and externals. Instead, `InputStream.is_empty` can be used to check
for "emptiness". Empty streams are typically only ever used as the first input
to a pipeline.
* Add run_external internal command.
We want to push external commands closer to internal commands, eventually
eliminating the concept of "external" completely. This means we can consolidate
a couple of things:
- Variable evaluation (for example, `$it`, `$nu`, alias vars)
- Behaviour of whole stream vs per-item external execution
It should also make it easier for us to start introducing argument signatures
for external commands,
* Update run_external.rs
* Update run_external.rs
* Update run_external.rs
* Update run_external.rs
Co-authored-by: Jonathan Turner <jonathandturner@users.noreply.github.com>
2020-04-20 03:30:44 +00:00
|
|
|
let values: Vec<Value> = input.collect().await;
|
2019-10-29 21:04:31 +00:00
|
|
|
|
|
|
|
if values.is_empty() {
|
|
|
|
yield Err(ShellError::labeled_error(
|
|
|
|
"Expected table from pipeline",
|
|
|
|
"requires a table input",
|
2020-05-15 09:16:09 +00:00
|
|
|
name
|
2019-10-29 21:04:31 +00:00
|
|
|
))
|
|
|
|
} else {
|
2020-05-09 17:15:47 +00:00
|
|
|
|
2020-05-15 09:16:09 +00:00
|
|
|
match crate::utils::data::group(column_name, &values, None, &name) {
|
|
|
|
Ok(grouped) => yield ReturnSuccess::value(grouped),
|
|
|
|
Err(err) => yield Err(err),
|
2019-10-22 05:00:06 +00:00
|
|
|
}
|
2020-05-15 09:16:09 +00:00
|
|
|
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|
2019-10-29 21:04:31 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
Ok(stream.to_output_stream())
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn group(
|
|
|
|
column_name: &Tagged<String>,
|
2019-11-21 14:33:14 +00:00
|
|
|
values: Vec<Value>,
|
2019-10-29 21:04:31 +00:00
|
|
|
tag: impl Into<Tag>,
|
2019-11-21 14:33:14 +00:00
|
|
|
) -> Result<Value, ShellError> {
|
2020-05-15 09:16:09 +00:00
|
|
|
crate::utils::data::group(Some(column_name.clone()), &values, None, tag)
|
2019-10-29 21:04:31 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
#[cfg(test)]
|
|
|
|
mod tests {
|
|
|
|
use crate::commands::group_by::group;
|
|
|
|
use indexmap::IndexMap;
|
2020-01-02 04:02:46 +00:00
|
|
|
use nu_errors::ShellError;
|
2019-12-04 19:52:31 +00:00
|
|
|
use nu_protocol::{UntaggedValue, Value};
|
2019-11-21 14:33:14 +00:00
|
|
|
use nu_source::*;
|
2019-10-29 21:04:31 +00:00
|
|
|
|
2019-11-21 14:33:14 +00:00
|
|
|
fn string(input: impl Into<String>) -> Value {
|
2019-12-04 19:52:31 +00:00
|
|
|
UntaggedValue::string(input.into()).into_untagged_value()
|
2019-10-29 21:04:31 +00:00
|
|
|
}
|
|
|
|
|
2019-11-21 14:33:14 +00:00
|
|
|
fn row(entries: IndexMap<String, Value>) -> Value {
|
2019-12-04 19:52:31 +00:00
|
|
|
UntaggedValue::row(entries).into_untagged_value()
|
2019-10-29 21:04:31 +00:00
|
|
|
}
|
|
|
|
|
2019-12-31 07:36:08 +00:00
|
|
|
fn table(list: &[Value]) -> Value {
|
2019-12-04 19:52:31 +00:00
|
|
|
UntaggedValue::table(list).into_untagged_value()
|
2019-10-29 21:04:31 +00:00
|
|
|
}
|
|
|
|
|
2019-11-21 14:33:14 +00:00
|
|
|
fn nu_releases_commiters() -> Vec<Value> {
|
2019-11-12 07:07:43 +00:00
|
|
|
vec![
|
2019-10-29 21:04:31 +00:00
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("August 23-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("August 23-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("October 10-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("Sept 24-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("October 10-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("Sept 24-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("October 10-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("Sept 24-2019")},
|
|
|
|
),
|
|
|
|
row(
|
|
|
|
indexmap! {"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("August 23-2019")},
|
|
|
|
),
|
2019-11-12 07:07:43 +00:00
|
|
|
]
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
2020-01-02 04:02:46 +00:00
|
|
|
fn groups_table_by_date_column() -> Result<(), ShellError> {
|
2019-11-12 07:07:43 +00:00
|
|
|
let for_key = String::from("date").tagged_unknown();
|
2019-10-29 21:04:31 +00:00
|
|
|
|
|
|
|
assert_eq!(
|
2020-01-02 04:02:46 +00:00
|
|
|
group(&for_key, nu_releases_commiters(), Tag::unknown())?,
|
2019-10-29 21:04:31 +00:00
|
|
|
row(indexmap! {
|
2019-12-31 07:36:08 +00:00
|
|
|
"August 23-2019".into() => table(&[
|
2019-10-29 21:04:31 +00:00
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("August 23-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("August 23-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("August 23-2019")})
|
|
|
|
]),
|
2019-12-31 07:36:08 +00:00
|
|
|
"October 10-2019".into() => table(&[
|
2019-10-29 21:04:31 +00:00
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("October 10-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("October 10-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("October 10-2019")})
|
|
|
|
]),
|
2019-12-31 07:36:08 +00:00
|
|
|
"Sept 24-2019".into() => table(&[
|
2019-10-29 21:04:31 +00:00
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("Sept 24-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("Sept 24-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("Sept 24-2019")})
|
|
|
|
]),
|
|
|
|
})
|
|
|
|
);
|
2020-01-02 04:02:46 +00:00
|
|
|
|
|
|
|
Ok(())
|
2019-10-29 21:04:31 +00:00
|
|
|
}
|
2019-11-12 07:07:43 +00:00
|
|
|
|
|
|
|
#[test]
|
2020-01-02 04:02:46 +00:00
|
|
|
fn groups_table_by_country_column() -> Result<(), ShellError> {
|
2019-11-12 07:07:43 +00:00
|
|
|
let for_key = String::from("country").tagged_unknown();
|
|
|
|
|
|
|
|
assert_eq!(
|
2020-01-02 04:02:46 +00:00
|
|
|
group(&for_key, nu_releases_commiters(), Tag::unknown())?,
|
2019-11-12 07:07:43 +00:00
|
|
|
row(indexmap! {
|
2019-12-31 07:36:08 +00:00
|
|
|
"EC".into() => table(&[
|
2019-11-12 07:07:43 +00:00
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("August 23-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("Sept 24-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("AR"), "country".into() => string("EC"), "date".into() => string("October 10-2019")})
|
|
|
|
]),
|
2019-12-31 07:36:08 +00:00
|
|
|
"NZ".into() => table(&[
|
2019-11-12 07:07:43 +00:00
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("August 23-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("October 10-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("JT"), "country".into() => string("NZ"), "date".into() => string("Sept 24-2019")})
|
|
|
|
]),
|
2019-12-31 07:36:08 +00:00
|
|
|
"US".into() => table(&[
|
2019-11-12 07:07:43 +00:00
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("October 10-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("Sept 24-2019")}),
|
|
|
|
row(indexmap!{"name".into() => string("YK"), "country".into() => string("US"), "date".into() => string("August 23-2019")}),
|
|
|
|
]),
|
|
|
|
})
|
|
|
|
);
|
2020-01-02 04:02:46 +00:00
|
|
|
|
|
|
|
Ok(())
|
2019-11-12 07:07:43 +00:00
|
|
|
}
|
2020-05-18 12:56:01 +00:00
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn examples_work_as_expected() {
|
|
|
|
use super::GroupBy;
|
|
|
|
use crate::examples::test as test_examples;
|
|
|
|
|
|
|
|
test_examples(GroupBy {})
|
|
|
|
}
|
2019-10-20 23:42:07 +00:00
|
|
|
}
|