2019-12-31 04:05:02 +00:00
|
|
|
use nu_test_support::fs::Stub::FileWithContentToBeTrimmed;
|
|
|
|
use nu_test_support::playground::Playground;
|
|
|
|
use nu_test_support::{nu, pipeline};
|
|
|
|
|
|
|
|
#[test]
|
2020-01-10 15:44:24 +00:00
|
|
|
fn removes_duplicate_rows() {
|
2019-12-31 04:05:02 +00:00
|
|
|
Playground::setup("uniq_test_1", |dirs, sandbox| {
|
|
|
|
sandbox.with_files(vec![FileWithContentToBeTrimmed(
|
|
|
|
"los_tres_caballeros.csv",
|
|
|
|
r#"
|
|
|
|
first_name,last_name,rusty_at,type
|
|
|
|
Andrés,Robalino,10/11/2013,A
|
2023-03-15 05:54:55 +00:00
|
|
|
JT,Turner,10/12/2013,B
|
2019-12-31 04:05:02 +00:00
|
|
|
Yehuda,Katz,10/11/2013,A
|
2023-03-15 05:54:55 +00:00
|
|
|
JT,Turner,10/12/2013,B
|
2019-12-31 04:05:02 +00:00
|
|
|
Yehuda,Katz,10/11/2013,A
|
|
|
|
"#,
|
|
|
|
)]);
|
|
|
|
|
|
|
|
let actual = nu!(
|
|
|
|
cwd: dirs.test(), pipeline(
|
|
|
|
r#"
|
|
|
|
open los_tres_caballeros.csv
|
|
|
|
| uniq
|
2021-03-13 21:46:40 +00:00
|
|
|
| length
|
2019-12-31 04:05:02 +00:00
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
2020-05-07 11:03:43 +00:00
|
|
|
assert_eq!(actual.out, "3");
|
2019-12-31 04:05:02 +00:00
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
2020-01-10 15:44:24 +00:00
|
|
|
fn uniq_values() {
|
2019-12-31 04:05:02 +00:00
|
|
|
Playground::setup("uniq_test_2", |dirs, sandbox| {
|
|
|
|
sandbox.with_files(vec![FileWithContentToBeTrimmed(
|
|
|
|
"los_tres_caballeros.csv",
|
|
|
|
r#"
|
|
|
|
first_name,last_name,rusty_at,type
|
|
|
|
Andrés,Robalino,10/11/2013,A
|
2023-03-15 05:54:55 +00:00
|
|
|
JT,Turner,10/12/2013,B
|
2019-12-31 04:05:02 +00:00
|
|
|
Yehuda,Katz,10/11/2013,A
|
2023-03-15 05:54:55 +00:00
|
|
|
JT,Turner,10/12/2013,B
|
2019-12-31 04:05:02 +00:00
|
|
|
Yehuda,Katz,10/11/2013,A
|
|
|
|
"#,
|
|
|
|
)]);
|
|
|
|
|
|
|
|
let actual = nu!(
|
|
|
|
cwd: dirs.test(), pipeline(
|
|
|
|
r#"
|
|
|
|
open los_tres_caballeros.csv
|
2020-05-07 11:03:43 +00:00
|
|
|
| select type
|
2019-12-31 04:05:02 +00:00
|
|
|
| uniq
|
2021-03-13 21:46:40 +00:00
|
|
|
| length
|
2019-12-31 04:05:02 +00:00
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
2020-05-07 11:03:43 +00:00
|
|
|
assert_eq!(actual.out, "2");
|
2019-12-31 04:05:02 +00:00
|
|
|
})
|
|
|
|
}
|
|
|
|
|
Support passing an empty list to sort, uniq, sort-by, and uniq-by (issue #5957) (#8669)
# Description
Currently, all four of these commands return a (rather-confusing)
spanless error when passed an empty list:
```
> [] | sort
Error:
× no values to work with
help: no values to work with
```
This PR changes these commands to always output `[]` if the input is
`[]`.
```
> [] | sort
╭────────────╮
│ empty list │
╰────────────╯
> [] | uniq-by foo
╭────────────╮
│ empty list │
╰────────────╯
```
I'm not sure what the original logic was here, but in the case of `sort`
and `uniq`, I think the current behavior is straightforwardly wrong.
`sort-by` and `uniq-by` are a bit more complicated, since they currently
try to perform some validation that the specified column name is present
in the input (see #8667 for problems with this validation, where a
possible outcome is removing the validation entirely). When passed `[]`,
it's not possible to do any validation because there are no records.
This opens up the possibility for situations like the following:
```
> [[foo]; [5] [6]] | where foo < 3 | sort-by bar
╭────────────╮
│ empty list │
╰────────────╯
```
I think there's a strong argument that `[]` is the best output for these
commands as well, since it makes pipelines like `$table | filter
$condition | sort-by $column` more predictable. Currently, this pipeline
will throw an error if `filter` evaluates to `[]`, but work fine
otherwise. This makes it difficult to write reliable code, especially
since users are not likely to encounter the `filter -> []` case in
testing (issue #5957). The only workaround is to insert manual checks
for an empty result. IMO, this is significantly worse than the "you can
typo a column name without getting an error" problem shown above.
Other commands that take column arguments (`get`, `select`, `rename`,
etc) already have `[] -> []`, so there's existing precedent for this
behavior.
The core question here is "what columns does `[]` have"? The current
behavior of `sort-by` is "no columns", while the current behavior of
`select` is "all possible columns". Both answers lead to accepting some
likely-buggy code without throwing on error, but in order to do better
here we would need something like `Value::Table` that tracks columns on
empty tables.
If other people disagree with this logic, I'm happy to split out the
`sort-by` and `uniq-by` changes into another PR.
# User-Facing Changes
`sort`, `uniq`, `sort-by`, and `uniq-by` now return `[]` instead of
throwing an error when input is `[]`.
# After Submitting
> If your PR had any user-facing changes, update [the
documentation](https://github.com/nushell/nushell.github.io) after the
PR is merged, if necessary. This will help us keep the docs up to date.
The existing behavior was not documented, and the new behavior is what
you would expect by default, so I don't think we need to update
documentation.
---------
Co-authored-by: Reilly Wood <reilly.wood@icloud.com>
2023-03-30 02:55:38 +00:00
|
|
|
#[test]
|
|
|
|
fn uniq_empty() {
|
|
|
|
let actual = nu!("[] | uniq | to nuon");
|
|
|
|
|
|
|
|
assert_eq!(actual.out, "[]");
|
|
|
|
}
|
|
|
|
|
2019-12-31 04:05:02 +00:00
|
|
|
#[test]
|
2020-01-10 15:44:24 +00:00
|
|
|
fn nested_json_structures() {
|
2019-12-31 04:05:02 +00:00
|
|
|
Playground::setup("uniq_test_3", |dirs, sandbox| {
|
|
|
|
sandbox.with_files(vec![FileWithContentToBeTrimmed(
|
2020-01-10 15:44:24 +00:00
|
|
|
"nested_json_structures.json",
|
2019-12-31 04:05:02 +00:00
|
|
|
r#"
|
2020-03-13 17:23:41 +00:00
|
|
|
[
|
2020-01-10 15:44:24 +00:00
|
|
|
{
|
|
|
|
"name": "this is duplicated",
|
|
|
|
"nesting": [ { "a": "a", "b": "b" },
|
|
|
|
{ "c": "c", "d": "d" }
|
|
|
|
],
|
|
|
|
"can_be_ordered_differently": {
|
|
|
|
"array": [1, 2, 3, 4, 5],
|
|
|
|
"something": { "else": "works" }
|
|
|
|
}
|
|
|
|
},
|
|
|
|
{
|
|
|
|
"can_be_ordered_differently": {
|
|
|
|
"something": { "else": "works" },
|
|
|
|
"array": [1, 2, 3, 4, 5]
|
|
|
|
},
|
|
|
|
"nesting": [ { "b": "b", "a": "a" },
|
|
|
|
{ "d": "d", "c": "c" }
|
|
|
|
],
|
|
|
|
"name": "this is duplicated"
|
|
|
|
},
|
|
|
|
{
|
|
|
|
"name": "this is unique",
|
|
|
|
"nesting": [ { "a": "b", "b": "a" },
|
|
|
|
{ "c": "d", "d": "c" }
|
|
|
|
],
|
|
|
|
"can_be_ordered_differently": {
|
|
|
|
"array": [],
|
|
|
|
"something": { "else": "does not work" }
|
|
|
|
}
|
|
|
|
},
|
|
|
|
{
|
|
|
|
"name": "this is unique",
|
|
|
|
"nesting": [ { "a": "a", "b": "b", "c": "c" },
|
|
|
|
{ "d": "d", "e": "e", "f": "f" }
|
|
|
|
],
|
|
|
|
"can_be_ordered_differently": {
|
|
|
|
"array": [],
|
|
|
|
"something": { "else": "works" }
|
|
|
|
}
|
|
|
|
}
|
|
|
|
]
|
2019-12-31 04:05:02 +00:00
|
|
|
"#,
|
|
|
|
)]);
|
|
|
|
|
|
|
|
let actual = nu!(
|
|
|
|
cwd: dirs.test(), pipeline(
|
|
|
|
r#"
|
2020-01-10 15:44:24 +00:00
|
|
|
open nested_json_structures.json
|
2019-12-31 04:05:02 +00:00
|
|
|
| uniq
|
2021-03-13 21:46:40 +00:00
|
|
|
| length
|
2019-12-31 04:05:02 +00:00
|
|
|
"#
|
|
|
|
));
|
2020-05-07 11:03:43 +00:00
|
|
|
assert_eq!(actual.out, "3");
|
2019-12-31 04:05:02 +00:00
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn uniq_when_keys_out_of_order() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!(pipeline(
|
2019-12-31 04:05:02 +00:00
|
|
|
r#"
|
2022-02-04 02:01:45 +00:00
|
|
|
[{"a": "a", "b": [1,2,3]}, {"b": [1,2,3], "a": "a"}]
|
2019-12-31 04:05:02 +00:00
|
|
|
| uniq
|
2021-03-13 21:46:40 +00:00
|
|
|
| length
|
2019-12-31 04:05:02 +00:00
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
2020-05-07 11:03:43 +00:00
|
|
|
assert_eq!(actual.out, "1");
|
2019-12-31 04:05:02 +00:00
|
|
|
}
|
2020-06-21 00:22:06 +00:00
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn uniq_counting() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!(pipeline(
|
2020-06-21 00:22:06 +00:00
|
|
|
r#"
|
2022-02-04 02:01:45 +00:00
|
|
|
["A", "B", "A"]
|
2020-06-21 00:22:06 +00:00
|
|
|
| wrap item
|
|
|
|
| uniq --count
|
2022-02-16 18:24:45 +00:00
|
|
|
| flatten
|
2020-11-22 00:37:16 +00:00
|
|
|
| where item == A
|
|
|
|
| get count
|
2022-02-16 18:24:45 +00:00
|
|
|
| get 0
|
2020-06-21 00:22:06 +00:00
|
|
|
"#
|
|
|
|
));
|
2020-11-22 00:37:16 +00:00
|
|
|
assert_eq!(actual.out, "2");
|
|
|
|
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!(pipeline(
|
2020-06-21 00:22:06 +00:00
|
|
|
r#"
|
2023-04-28 11:25:44 +00:00
|
|
|
["A", "B", "A"]
|
2020-11-22 00:37:16 +00:00
|
|
|
| wrap item
|
|
|
|
| uniq --count
|
2022-02-16 18:24:45 +00:00
|
|
|
| flatten
|
2020-11-22 00:37:16 +00:00
|
|
|
| where item == B
|
|
|
|
| get count
|
2022-02-16 18:24:45 +00:00
|
|
|
| get 0
|
2020-06-21 00:22:06 +00:00
|
|
|
"#
|
|
|
|
));
|
2020-11-22 00:37:16 +00:00
|
|
|
assert_eq!(actual.out, "1");
|
2020-06-21 00:22:06 +00:00
|
|
|
}
|
2020-07-18 17:19:03 +00:00
|
|
|
|
2021-07-09 19:27:35 +00:00
|
|
|
#[test]
|
|
|
|
fn uniq_unique() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!("[1 2 3 4 1 5] | uniq --unique");
|
|
|
|
let expected = nu!("[2 3 4 5]");
|
2021-07-09 19:27:35 +00:00
|
|
|
assert_eq!(actual.out, expected.out);
|
|
|
|
}
|
|
|
|
|
2020-07-18 17:19:03 +00:00
|
|
|
#[test]
|
|
|
|
fn uniq_simple_vals_ints() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!("[1 2 3 4 1 5] | uniq");
|
|
|
|
let expected = nu!("[1 2 3 4 5]");
|
2020-07-18 17:19:03 +00:00
|
|
|
assert_eq!(actual.out, expected.out);
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn uniq_simple_vals_strs() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!("[A B C A] | uniq");
|
|
|
|
let expected = nu!("[A B C]");
|
2020-07-18 17:19:03 +00:00
|
|
|
assert_eq!(actual.out, expected.out);
|
|
|
|
}
|
2022-11-23 10:18:13 +00:00
|
|
|
|
|
|
|
#[test]
|
`uniq -i` does not convert to lowercase (#7192) (#7209)
# Description
`uniq -i` does not convert output strings to lowercase.
Also, `uniq -i` did not ignore case in strings below the first level of
Tables and Records. Now all strings case are ignored for all children
Values for tables, Records, and List.
Fixes https://github.com/nushell/nushell/issues/7192
# Tests + Formatting
About the issue https://github.com/nushell/nushell/issues/7192, the
output will be:
```
〉[AAA BBB CCC] | uniq -i
╭───┬─────╮
│ 0 │ AAA │
│ 1 │ BBB │
│ 2 │ CCC │
╰───┴─────╯
```
About ignoring case for all children string, I expect this to be true:
```
([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Geremias', {plate: 'Bitoque', carbs: 100}]
]
)],
] | uniq -i
) == ([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)]
])
```
2022-11-23 23:46:20 +00:00
|
|
|
fn table() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!(pipeline(
|
2022-11-23 10:18:13 +00:00
|
|
|
r#"
|
`uniq -i` does not convert to lowercase (#7192) (#7209)
# Description
`uniq -i` does not convert output strings to lowercase.
Also, `uniq -i` did not ignore case in strings below the first level of
Tables and Records. Now all strings case are ignored for all children
Values for tables, Records, and List.
Fixes https://github.com/nushell/nushell/issues/7192
# Tests + Formatting
About the issue https://github.com/nushell/nushell/issues/7192, the
output will be:
```
〉[AAA BBB CCC] | uniq -i
╭───┬─────╮
│ 0 │ AAA │
│ 1 │ BBB │
│ 2 │ CCC │
╰───┴─────╯
```
About ignoring case for all children string, I expect this to be true:
```
([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Geremias', {plate: 'Bitoque', carbs: 100}]
]
)],
] | uniq -i
) == ([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)]
])
```
2022-11-23 23:46:20 +00:00
|
|
|
[[fruit day]; [apple monday] [apple friday] [Apple friday] [apple monday] [pear monday] [orange tuesday]]
|
2022-11-23 10:18:13 +00:00
|
|
|
| uniq
|
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
2023-04-28 11:25:44 +00:00
|
|
|
let expected = nu!("[[fruit day]; [apple monday] [apple friday] [Apple friday] [pear monday] [orange tuesday]]");
|
2022-11-23 10:18:13 +00:00
|
|
|
assert_eq!(actual.out, expected.out);
|
|
|
|
}
|
`uniq -i` does not convert to lowercase (#7192) (#7209)
# Description
`uniq -i` does not convert output strings to lowercase.
Also, `uniq -i` did not ignore case in strings below the first level of
Tables and Records. Now all strings case are ignored for all children
Values for tables, Records, and List.
Fixes https://github.com/nushell/nushell/issues/7192
# Tests + Formatting
About the issue https://github.com/nushell/nushell/issues/7192, the
output will be:
```
〉[AAA BBB CCC] | uniq -i
╭───┬─────╮
│ 0 │ AAA │
│ 1 │ BBB │
│ 2 │ CCC │
╰───┴─────╯
```
About ignoring case for all children string, I expect this to be true:
```
([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Geremias', {plate: 'Bitoque', carbs: 100}]
]
)],
] | uniq -i
) == ([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)]
])
```
2022-11-23 23:46:20 +00:00
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn table_with_ignore_case() {
|
2023-04-28 11:25:44 +00:00
|
|
|
let actual = nu!(pipeline(
|
`uniq -i` does not convert to lowercase (#7192) (#7209)
# Description
`uniq -i` does not convert output strings to lowercase.
Also, `uniq -i` did not ignore case in strings below the first level of
Tables and Records. Now all strings case are ignored for all children
Values for tables, Records, and List.
Fixes https://github.com/nushell/nushell/issues/7192
# Tests + Formatting
About the issue https://github.com/nushell/nushell/issues/7192, the
output will be:
```
〉[AAA BBB CCC] | uniq -i
╭───┬─────╮
│ 0 │ AAA │
│ 1 │ BBB │
│ 2 │ CCC │
╰───┴─────╯
```
About ignoring case for all children string, I expect this to be true:
```
([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Geremias', {plate: 'Bitoque', carbs: 100}]
]
)],
] | uniq -i
) == ([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)]
])
```
2022-11-23 23:46:20 +00:00
|
|
|
r#"
|
|
|
|
[[origin, people];
|
|
|
|
[World, (
|
|
|
|
[[name, meal];
|
|
|
|
['Geremias', {plate: 'bitoque', carbs: 100}]
|
|
|
|
]
|
|
|
|
)],
|
|
|
|
[World, (
|
|
|
|
[[name, meal];
|
|
|
|
['Martin', {plate: 'bitoque', carbs: 100}]
|
|
|
|
]
|
|
|
|
)],
|
|
|
|
[World, (
|
|
|
|
[[name, meal];
|
|
|
|
['Geremias', {plate: 'Bitoque', carbs: 100}]
|
|
|
|
]
|
|
|
|
)],
|
|
|
|
] | uniq -i
|
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
2023-04-28 11:25:44 +00:00
|
|
|
let expected = nu!(pipeline(
|
`uniq -i` does not convert to lowercase (#7192) (#7209)
# Description
`uniq -i` does not convert output strings to lowercase.
Also, `uniq -i` did not ignore case in strings below the first level of
Tables and Records. Now all strings case are ignored for all children
Values for tables, Records, and List.
Fixes https://github.com/nushell/nushell/issues/7192
# Tests + Formatting
About the issue https://github.com/nushell/nushell/issues/7192, the
output will be:
```
〉[AAA BBB CCC] | uniq -i
╭───┬─────╮
│ 0 │ AAA │
│ 1 │ BBB │
│ 2 │ CCC │
╰───┴─────╯
```
About ignoring case for all children string, I expect this to be true:
```
([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Geremias', {plate: 'Bitoque', carbs: 100}]
]
)],
] | uniq -i
) == ([[origin, people];
[World, (
[[name, meal];
['Geremias', {plate: 'bitoque', carbs: 100}]
]
)],
[World, (
[[name, meal];
['Martin', {plate: 'bitoque', carbs: 100}]
]
)]
])
```
2022-11-23 23:46:20 +00:00
|
|
|
r#"
|
|
|
|
echo [[origin, people];
|
|
|
|
[World, (
|
|
|
|
[[name, meal];
|
|
|
|
['Geremias', {plate: 'bitoque', carbs: 100}]
|
|
|
|
]
|
|
|
|
)],
|
|
|
|
[World, (
|
|
|
|
[[name, meal];
|
|
|
|
['Martin', {plate: 'bitoque', carbs: 100}]
|
|
|
|
]
|
|
|
|
)],
|
|
|
|
]
|
|
|
|
"#
|
|
|
|
));
|
|
|
|
|
|
|
|
assert_eq!(actual.out, expected.out);
|
|
|
|
}
|