forked from extern/nushell
add the ability to combine columns with detect columns (#9511)
# Description
This PR adds the ability to manually combine columns in the `detect
columns` command. This is useful when items are close together but want
them to be in one column.
For example, if you want to parse the output of bash's `ls` command, the
output passed into `detect columns` would look similar to this.
```
❯ ^ls -lh
total 242K
-rw-r--r-- 1 dschroeder 197121 3.5K Mar 30 10:10 CODE_OF_CONDUCT.md
-rw-r--r-- 1 dschroeder 197121 11K Jun 21 14:16 CONTRIBUTING.md
-rw-r--r-- 1 dschroeder 197121 153K Jun 21 14:16 Cargo.lock
-rw-r--r-- 1 dschroeder 197121 5.7K Jun 21 08:47 Cargo.toml
-rw-r--r-- 1 dschroeder 197121 371 Mar 30 10:10 Cross.toml
-rw-r--r-- 1 dschroeder 197121 1.1K Apr 3 08:37 LICENSE
-rw-r--r-- 1 dschroeder 197121 13K Jun 21 14:16 README.md
drwxr-xr-x 1 dschroeder 197121 0 May 24 08:06 assets
drwxr-xr-x 1 dschroeder 197121 0 Jun 21 14:16 benches
-rw-r--r-- 1 dschroeder 197121 310 Mar 30 10:10 codecov.yml
drwxr-xr-x 1 dschroeder 197121 0 Jun 1 15:30 crates
drwxr-xr-x 1 dschroeder 197121 0 May 4 07:55 dict
drwxr-xr-x 1 dschroeder 197121 0 Mar 30 10:10 docker
-rw-r--r-- 1 dschroeder 197121 1.1K Jun 12 07:03 rust-toolchain.toml
drwxr-xr-x 1 dschroeder 197121 0 May 26 07:11 scripts
drwxr-xr-x 1 dschroeder 197121 0 Jun 15 07:14 src
drwxr-xr-x 1 dschroeder 197121 0 Jun 21 09:48 target
drwxr-xr-x 1 dschroeder 197121 0 Jun 21 12:30 tests
-rw-r--r-- 1 dschroeder 197121 16K Jun 21 14:16 toolkit.nu
drwxr-xr-x 1 dschroeder 197121 0 Jun 1 15:30 wix
```
Running it through `detect columns` is helpful but notice how the Month,
Day, and Time are in their own columns.
```
❯ ^ls -lh | detect columns --no-headers --skip 1
╭────┬────────────┬─────────┬────────────┬─────────┬─────────┬─────────┬─────────┬─────────┬─────────────────────╮
│ # │ column0 │ column1 │ column2 │ column3 │ column4 │ column5 │ column6 │ column7 │ column8 │
├────┼────────────┼─────────┼────────────┼─────────┼─────────┼─────────┼─────────┼─────────┼─────────────────────┤
│ 0 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 3.5K │ Mar │ 30 │ 10:10 │ CODE_OF_CONDUCT.md │
│ 1 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 11K │ Jun │ 21 │ 14:16 │ CONTRIBUTING.md │
│ 2 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 153K │ Jun │ 21 │ 14:16 │ Cargo.lock │
│ 3 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 5.7K │ Jun │ 21 │ 08:47 │ Cargo.toml │
│ 4 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 371 │ Mar │ 30 │ 10:10 │ Cross.toml │
│ 5 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1K │ Apr │ 3 │ 08:37 │ LICENSE │
│ 6 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 13K │ Jun │ 21 │ 14:16 │ README.md │
│ 7 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May │ 24 │ 08:06 │ assets │
│ 8 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 21 │ 14:16 │ benches │
│ 9 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 310 │ Mar │ 30 │ 10:10 │ codecov.yml │
│ 10 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 1 │ 15:30 │ crates │
│ 11 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May │ 4 │ 07:55 │ dict │
│ 12 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Mar │ 30 │ 10:10 │ docker │
│ 13 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1K │ Jun │ 12 │ 07:03 │ rust-toolchain.toml │
│ 14 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May │ 26 │ 07:11 │ scripts │
│ 15 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 15 │ 07:14 │ src │
│ 16 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 21 │ 09:48 │ target │
│ 17 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 21 │ 12:30 │ tests │
│ 18 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 16K │ Jun │ 21 │ 14:16 │ toolkit.nu │
│ 19 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun │ 1 │ 15:30 │ wix │
├────┼────────────┼─────────┼────────────┼─────────┼─────────┼─────────┼─────────┼─────────┼─────────────────────┤
│ # │ column0 │ column1 │ column2 │ column3 │ column4 │ column5 │ column6 │ column7 │ column8 │
╰────┴────────────┴─────────┴────────────┴─────────┴─────────┴─────────┴─────────┴─────────┴─────────────────────╯
```
Now you can add `--combine-columns <range>` and get something like this.
```
❯ ^ls -lh | detect columns --no-headers --skip 1 --combine-columns 5..7
╭────┬────────────┬─────────┬────────────┬─────────┬─────────┬──────────────┬─────────────────────╮
│ # │ column0 │ column1 │ column2 │ column3 │ column4 │ column5 │ column6 │
├────┼────────────┼─────────┼────────────┼─────────┼─────────┼──────────────┼─────────────────────┤
│ 0 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 3.5K │ Mar 30 10:10 │ CODE_OF_CONDUCT.md │
│ 1 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 11K │ Jun 21 14:16 │ CONTRIBUTING.md │
│ 2 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 153K │ Jun 21 14:16 │ Cargo.lock │
│ 3 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 5.7K │ Jun 21 08:47 │ Cargo.toml │
│ 4 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 371 │ Mar 30 10:10 │ Cross.toml │
│ 5 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1K │ Apr 3 08:37 │ LICENSE │
│ 6 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 13K │ Jun 21 14:16 │ README.md │
│ 7 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May 24 08:06 │ assets │
│ 8 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 21 14:16 │ benches │
│ 9 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 310 │ Mar 30 10:10 │ codecov.yml │
│ 10 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 1 15:30 │ crates │
│ 11 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May 4 07:55 │ dict │
│ 12 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Mar 30 10:10 │ docker │
│ 13 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1K │ Jun 12 07:03 │ rust-toolchain.toml │
│ 14 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ May 26 07:11 │ scripts │
│ 15 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 15 07:14 │ src │
│ 16 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 21 09:48 │ target │
│ 17 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 21 12:30 │ tests │
│ 18 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 16K │ Jun 21 14:16 │ toolkit.nu │
│ 19 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 │ Jun 1 15:30 │ wix │
├────┼────────────┼─────────┼────────────┼─────────┼─────────┼──────────────┼─────────────────────┤
│ # │ column0 │ column1 │ column2 │ column3 │ column4 │ column5 │ column6 │
╰────┴────────────┴─────────┴────────────┴─────────┴─────────┴──────────────┴─────────────────────╯
```
Then you can fancy-it-up by tweaking the other columns and renaming
columns.
```
❯ ^ls -lh | detect columns --no-headers --skip 1 --combine-columns 5..7 | update column5 {|r| $r.column5 | into datetime} | into int column1 column3 | into filesize column4 | rename perms links user inode filesize datetime name
╭────┬────────────┬───────┬────────────┬────────┬──────────┬──────────────┬─────────────────────╮
│ # │ perms │ links │ user │ inode │ filesize │ datetime │ name │
├────┼────────────┼───────┼────────────┼────────┼──────────┼──────────────┼─────────────────────┤
│ 0 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 3.5 KB │ 2 months ago │ CODE_OF_CONDUCT.md │
│ 1 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 11.0 KB │ 2 days ago │ CONTRIBUTING.md │
│ 2 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 153.0 KB │ 2 days ago │ Cargo.lock │
│ 3 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 5.7 KB │ 2 days ago │ Cargo.toml │
│ 4 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 371 B │ 2 months ago │ Cross.toml │
│ 5 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1 KB │ 2 months ago │ LICENSE │
│ 6 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 13.0 KB │ 2 days ago │ README.md │
│ 7 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ a month ago │ assets │
│ 8 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 2 days ago │ benches │
│ 9 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 310 B │ 2 months ago │ codecov.yml │
│ 10 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 3 weeks ago │ crates │
│ 11 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 2 months ago │ dict │
│ 12 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 2 months ago │ docker │
│ 13 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 1.1 KB │ 2 weeks ago │ rust-toolchain.toml │
│ 14 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 4 weeks ago │ scripts │
│ 15 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ a week ago │ src │
│ 16 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 2 days ago │ target │
│ 17 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 2 days ago │ tests │
│ 18 │ -rw-r--r-- │ 1 │ dschroeder │ 197121 │ 16.0 KB │ 2 days ago │ toolkit.nu │
│ 19 │ drwxr-xr-x │ 1 │ dschroeder │ 197121 │ 0 B │ 3 weeks ago │ wix │
├────┼────────────┼───────┼────────────┼────────┼──────────┼──────────────┼─────────────────────┤
│ # │ perms │ links │ user │ inode │ filesize │ datetime │ name │
╰────┴────────────┴───────┴────────────┴────────┴──────────┴──────────────┴─────────────────────╯
```
# User-Facing Changes
<!-- List of all changes that impact the user experience here. This
helps us keep track of breaking changes. -->
# Tests + Formatting
<!--
Don't forget to add tests that cover your changes.
Make sure you've run and fixed any issues with these commands:
- `cargo fmt --all -- --check` to check standard code formatting (`cargo
fmt --all` applies these changes)
- `cargo clippy --workspace -- -D warnings -D clippy::unwrap_used -A
clippy::needless_collect -A clippy::result_large_err` to check that
you're using the standard code style
- `cargo test --workspace` to check that all tests pass
- `cargo run -- crates/nu-std/tests/run.nu` to run the tests for the
standard library
> **Note**
> from `nushell` you can also use the `toolkit` as follows
> ```bash
> use toolkit.nu # or use an `env_change` hook to activate it
automatically
> toolkit check pr
> ```
-->
# 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.
-->
This commit is contained in:
Darren Schroeder
GitHub
parent
0c888486c9
commit
761946c522
@ -1,12 +1,13 @@
|
||||
use std::iter::Peekable;
|
||||
use std::str::CharIndices;
|
||||
|
||||
use itertools::Itertools;
|
||||
use nu_engine::CallExt;
|
||||
use nu_protocol::ast::Call;
|
||||
use nu_protocol::engine::{Command, EngineState, Stack};
|
||||
use nu_protocol::{
|
||||
Category, Example, IntoInterruptiblePipelineData, PipelineData, ShellError, Signature, Span,
|
||||
Spanned, SyntaxShape, Type, Value,
|
||||
Category, Example, IntoInterruptiblePipelineData, PipelineData, Range, ShellError, Signature,
|
||||
Span, Spanned, SyntaxShape, Type, Value,
|
||||
};
|
||||
|
||||
type Input<'t> = Peekable<CharIndices<'t>>;
|
||||
@ -29,6 +30,12 @@ impl Command for DetectColumns {
|
||||
)
|
||||
.input_output_types(vec![(Type::String, Type::Table(vec![]))])
|
||||
.switch("no-headers", "don't detect headers", Some('n'))
|
||||
.named(
|
||||
"combine-columns",
|
||||
SyntaxShape::Range,
|
||||
"columns to be combined; listed as a range",
|
||||
Some('c'),
|
||||
)
|
||||
.category(Category::Strings)
|
||||
}
|
||||
|
||||
@ -37,7 +44,7 @@ impl Command for DetectColumns {
|
||||
}
|
||||
|
||||
fn search_terms(&self) -> Vec<&str> {
|
||||
vec!["split"]
|
||||
vec!["split", "tabular"]
|
||||
}
|
||||
|
||||
fn run(
|
||||
@ -78,6 +85,11 @@ impl Command for DetectColumns {
|
||||
example: "$'c1 c2 c3(char nl)a b c' | detect columns",
|
||||
result: None,
|
||||
},
|
||||
Example {
|
||||
description: "Parse external ls command and combine columns for datetime",
|
||||
example: "^ls -lh | detect columns --no-headers --skip 1 --combine-columns 5..7",
|
||||
result: None,
|
||||
},
|
||||
]
|
||||
}
|
||||
}
|
||||
@ -91,6 +103,7 @@ fn detect_columns(
|
||||
let name_span = call.head;
|
||||
let num_rows_to_skip: Option<usize> = call.get_flag(engine_state, stack, "skip")?;
|
||||
let noheader = call.has_flag("no-headers");
|
||||
let range: Option<Range> = call.get_flag(engine_state, stack, "combine-columns")?;
|
||||
let ctrlc = engine_state.ctrlc.clone();
|
||||
let config = engine_state.get_config();
|
||||
let input = input.collect_string("", config)?;
|
||||
@ -172,10 +185,70 @@ fn detect_columns(
|
||||
}
|
||||
}
|
||||
|
||||
Value::Record {
|
||||
cols,
|
||||
vals,
|
||||
span: name_span,
|
||||
if range.is_some() {
|
||||
// Destructure the range parameter
|
||||
let (start_index, end_index) = if let Some(range) = &range {
|
||||
match nu_cmd_base::util::process_range(range) {
|
||||
Ok(r) => {
|
||||
// `process_range()` returns `isize::MAX` if the range is open-ended,
|
||||
// which is not ideal for us
|
||||
let end = if r.1 as usize > cols.len() {
|
||||
cols.len()
|
||||
} else {
|
||||
r.1 as usize
|
||||
};
|
||||
(r.0 as usize, end)
|
||||
}
|
||||
Err(processing_error) => {
|
||||
let err = processing_error("could not find range index", name_span);
|
||||
return Value::Error {
|
||||
error: Box::new(err),
|
||||
};
|
||||
}
|
||||
}
|
||||
} else {
|
||||
(0usize, cols.len())
|
||||
};
|
||||
|
||||
// Merge Columns
|
||||
let part1 = &cols.clone()[0..start_index];
|
||||
let combined = &cols.clone()[start_index..=end_index];
|
||||
let binding = combined.join("");
|
||||
let part3 = &cols.clone()[end_index + 1..];
|
||||
let new_cols = [part1, &[binding], part3].concat();
|
||||
// Now renumber columns since we merged some
|
||||
let mut renum_cols = vec![];
|
||||
for (idx, _acol) in new_cols.iter().enumerate() {
|
||||
renum_cols.push(format!("column{idx}"));
|
||||
}
|
||||
|
||||
// Merge Values
|
||||
let part1 = &vals.clone()[0..start_index];
|
||||
let combined = &vals.clone()[start_index..=end_index];
|
||||
let binding = Value::string(
|
||||
combined
|
||||
.iter()
|
||||
.map(|f| match f.as_string() {
|
||||
Ok(s) => s,
|
||||
_ => "".to_string(),
|
||||
})
|
||||
.join(" "), // add a space between items
|
||||
Span::unknown(),
|
||||
);
|
||||
let part3 = &vals.clone()[end_index + 1..];
|
||||
let new_vals = [part1, &[binding], part3].concat();
|
||||
|
||||
Value::Record {
|
||||
cols: renum_cols,
|
||||
vals: new_vals,
|
||||
span: name_span,
|
||||
}
|
||||
} else {
|
||||
Value::Record {
|
||||
cols,
|
||||
vals,
|
||||
span: name_span,
|
||||
}
|
||||
}
|
||||
})
|
||||
.into_pipeline_data(ctrlc))
|
||||
@ -207,9 +280,9 @@ pub fn find_columns(input: &str) -> Vec<Spanned<String>> {
|
||||
|
||||
#[derive(Clone, Copy)]
|
||||
enum BlockKind {
|
||||
Paren,
|
||||
CurlyBracket,
|
||||
SquareBracket,
|
||||
Parenthesis,
|
||||
Brace,
|
||||
Bracket,
|
||||
}
|
||||
|
||||
fn baseline(src: &mut Input) -> Spanned<String> {
|
||||
@ -265,27 +338,27 @@ fn baseline(src: &mut Input) -> Spanned<String> {
|
||||
quote_start = Some(c);
|
||||
} else if c == '[' {
|
||||
// We encountered an opening `[` delimiter.
|
||||
block_level.push(BlockKind::SquareBracket);
|
||||
block_level.push(BlockKind::Bracket);
|
||||
} else if c == ']' {
|
||||
// We encountered a closing `]` delimiter. Pop off the opening `[`
|
||||
// delimiter.
|
||||
if let Some(BlockKind::SquareBracket) = block_level.last() {
|
||||
if let Some(BlockKind::Bracket) = block_level.last() {
|
||||
let _ = block_level.pop();
|
||||
}
|
||||
} else if c == '{' {
|
||||
// We encountered an opening `{` delimiter.
|
||||
block_level.push(BlockKind::CurlyBracket);
|
||||
block_level.push(BlockKind::Brace);
|
||||
} else if c == '}' {
|
||||
// We encountered a closing `}` delimiter. Pop off the opening `{`.
|
||||
if let Some(BlockKind::CurlyBracket) = block_level.last() {
|
||||
if let Some(BlockKind::Brace) = block_level.last() {
|
||||
let _ = block_level.pop();
|
||||
}
|
||||
} else if c == '(' {
|
||||
// We enceountered an opening `(` delimiter.
|
||||
block_level.push(BlockKind::Paren);
|
||||
block_level.push(BlockKind::Parenthesis);
|
||||
} else if c == ')' {
|
||||
// We encountered a closing `)` delimiter. Pop off the opening `(`.
|
||||
if let Some(BlockKind::Paren) = block_level.last() {
|
||||
if let Some(BlockKind::Parenthesis) = block_level.last() {
|
||||
let _ = block_level.pop();
|
||||
}
|
||||
} else if is_termination(&block_level, c) {
|
||||
|
||||
Loading…
Reference in New Issue
Block a user