mirror of
https://github.com/nushell/nushell.git
synced 2025-05-01 08:34:26 +02:00
8da27a1a09
# Description
This PR creates a new `Record` type to reduce duplicate code and
possibly bugs as well. (This is an edited version of #9648.)
- `Record` implements `FromIterator` and `IntoIterator` and so can be
iterated over or collected into. For example, this helps with
conversions to and from (hash)maps. (Also, no more
`cols.iter().zip(vals)`!)
- `Record` has a `push(col, val)` function to help insure that the
number of columns is equal to the number of values. I caught a few
potential bugs thanks to this (e.g. in the `ls` command).
- Finally, this PR also adds a `record!` macro that helps simplify
record creation. It is used like so:
```rust
record! {
"key1" => some_value,
"key2" => Value::string("text", span),
"key3" => Value::int(optional_int.unwrap_or(0), span),
"key4" => Value::bool(config.setting, span),
}
```
Since macros hinder formatting, etc., the right hand side values should
be relatively short and sweet like the examples above.
Where possible, prefer `record!` or `.collect()` on an iterator instead
of multiple `Record::push`s, since the first two automatically set the
record capacity and do less work overall.
# User-Facing Changes
Besides the changes in `nu-protocol` the only other breaking changes are
to `nu-table::{ExpandedTable::build_map, JustTable::kv_table}`.
355 lines
14 KiB
Rust
355 lines
14 KiB
Rust
use indexmap::indexmap;
|
||
use indexmap::map::IndexMap;
|
||
use nu_engine::CallExt;
|
||
use nu_protocol::engine::{EngineState, Stack};
|
||
use nu_protocol::record;
|
||
use nu_protocol::{
|
||
ast::Call, engine::Command, Category, Example, IntoInterruptiblePipelineData, IntoPipelineData,
|
||
PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
|
||
};
|
||
use once_cell::sync::Lazy;
|
||
|
||
// Character used to separate directories in a Path Environment variable on windows is ";"
|
||
#[cfg(target_family = "windows")]
|
||
const ENV_PATH_SEPARATOR_CHAR: char = ';';
|
||
// Character used to separate directories in a Path Environment variable on linux/mac/unix is ":"
|
||
#[cfg(not(target_family = "windows"))]
|
||
const ENV_PATH_SEPARATOR_CHAR: char = ':';
|
||
|
||
#[derive(Clone)]
|
||
pub struct Char;
|
||
|
||
static CHAR_MAP: Lazy<IndexMap<&'static str, String>> = Lazy::new(|| {
|
||
indexmap! {
|
||
// These are some regular characters that either can't be used or
|
||
// it's just easier to use them like this.
|
||
|
||
// This are the "normal" characters section
|
||
"newline" => '\n'.to_string(),
|
||
"enter" => '\n'.to_string(),
|
||
"nl" => '\n'.to_string(),
|
||
"line_feed" => '\n'.to_string(),
|
||
"lf" => '\n'.to_string(),
|
||
"carriage_return" => '\r'.to_string(),
|
||
"cr" => '\r'.to_string(),
|
||
"crlf" => "\r\n".to_string(),
|
||
"tab" => '\t'.to_string(),
|
||
"sp" => ' '.to_string(),
|
||
"space" => ' '.to_string(),
|
||
"pipe" => '|'.to_string(),
|
||
"left_brace" => '{'.to_string(),
|
||
"lbrace" => '{'.to_string(),
|
||
"right_brace" => '}'.to_string(),
|
||
"rbrace" => '}'.to_string(),
|
||
"left_paren" => '('.to_string(),
|
||
"lp" => '('.to_string(),
|
||
"lparen" => '('.to_string(),
|
||
"right_paren" => ')'.to_string(),
|
||
"rparen" => ')'.to_string(),
|
||
"rp" => ')'.to_string(),
|
||
"left_bracket" => '['.to_string(),
|
||
"lbracket" => '['.to_string(),
|
||
"right_bracket" => ']'.to_string(),
|
||
"rbracket" => ']'.to_string(),
|
||
"single_quote" => '\''.to_string(),
|
||
"squote" => '\''.to_string(),
|
||
"sq" => '\''.to_string(),
|
||
"double_quote" => '\"'.to_string(),
|
||
"dquote" => '\"'.to_string(),
|
||
"dq" => '\"'.to_string(),
|
||
"path_sep" => std::path::MAIN_SEPARATOR.to_string(),
|
||
"psep" => std::path::MAIN_SEPARATOR.to_string(),
|
||
"separator" => std::path::MAIN_SEPARATOR.to_string(),
|
||
"esep" => ENV_PATH_SEPARATOR_CHAR.to_string(),
|
||
"env_sep" => ENV_PATH_SEPARATOR_CHAR.to_string(),
|
||
"tilde" => '~'.to_string(), // ~
|
||
"twiddle" => '~'.to_string(), // ~
|
||
"squiggly" => '~'.to_string(), // ~
|
||
"home" => '~'.to_string(), // ~
|
||
"hash" => '#'.to_string(), // #
|
||
"hashtag" => '#'.to_string(), // #
|
||
"pound_sign" => '#'.to_string(), // #
|
||
"sharp" => '#'.to_string(), // #
|
||
"root" => '#'.to_string(), // #
|
||
|
||
// This is the unicode section
|
||
// Unicode names came from https://www.compart.com/en/unicode
|
||
// Private Use Area (U+E000-U+F8FF)
|
||
// Unicode can't be mixed with Ansi or it will break width calculation
|
||
"nf_branch" => '\u{e0a0}'.to_string(), //
|
||
"nf_segment" => '\u{e0b0}'.to_string(), //
|
||
"nf_left_segment" => '\u{e0b0}'.to_string(), //
|
||
"nf_left_segment_thin" => '\u{e0b1}'.to_string(), //
|
||
"nf_right_segment" => '\u{e0b2}'.to_string(), //
|
||
"nf_right_segment_thin" => '\u{e0b3}'.to_string(), //
|
||
"nf_git" => '\u{f1d3}'.to_string(), //
|
||
"nf_git_branch" => "\u{e709}\u{e0a0}".to_string(), //
|
||
"nf_folder1" => '\u{f07c}'.to_string(), //
|
||
"nf_folder2" => '\u{f115}'.to_string(), //
|
||
"nf_house1" => '\u{f015}'.to_string(), //
|
||
"nf_house2" => '\u{f7db}'.to_string(), //
|
||
|
||
"identical_to" => '\u{2261}'.to_string(), // ≡
|
||
"hamburger" => '\u{2261}'.to_string(), // ≡
|
||
"not_identical_to" => '\u{2262}'.to_string(), // ≢
|
||
"branch_untracked" => '\u{2262}'.to_string(), // ≢
|
||
"strictly_equivalent_to" => '\u{2263}'.to_string(), // ≣
|
||
"branch_identical" => '\u{2263}'.to_string(), // ≣
|
||
|
||
"upwards_arrow" => '\u{2191}'.to_string(), // ↑
|
||
"branch_ahead" => '\u{2191}'.to_string(), // ↑
|
||
"downwards_arrow" => '\u{2193}'.to_string(), // ↓
|
||
"branch_behind" => '\u{2193}'.to_string(), // ↓
|
||
"up_down_arrow" => '\u{2195}'.to_string(), // ↕
|
||
"branch_ahead_behind" => '\u{2195}'.to_string(), // ↕
|
||
|
||
"black_right_pointing_triangle" => '\u{25b6}'.to_string(), // ▶
|
||
"prompt" => '\u{25b6}'.to_string(), // ▶
|
||
"vector_or_cross_product" => '\u{2a2f}'.to_string(), // ⨯
|
||
"failed" => '\u{2a2f}'.to_string(), // ⨯
|
||
"high_voltage_sign" => '\u{26a1}'.to_string(), // ⚡
|
||
"elevated" => '\u{26a1}'.to_string(), // ⚡
|
||
|
||
// This is the emoji section
|
||
// Weather symbols
|
||
// https://www.babelstone.co.uk/Unicode/whatisit.html
|
||
"sun" => "☀️".to_string(), //2600 + fe0f
|
||
"sunny" => "☀️".to_string(), //2600 + fe0f
|
||
"sunrise" => "☀️".to_string(), //2600 + fe0f
|
||
"moon" => "🌛".to_string(), //1f31b
|
||
"cloudy" => "☁️".to_string(), //2601 + fe0f
|
||
"cloud" => "☁️".to_string(), //2601 + fe0f
|
||
"clouds" => "☁️".to_string(), //2601 + fe0f
|
||
"rainy" => "🌦️".to_string(), //1f326 + fe0f
|
||
"rain" => "🌦️".to_string(), //1f326 + fe0f
|
||
"foggy" => "🌫️".to_string(), //1f32b + fe0f
|
||
"fog" => "🌫️".to_string(), //1f32b + fe0f
|
||
"mist" => '\u{2591}'.to_string(), //2591
|
||
"haze" => '\u{2591}'.to_string(), //2591
|
||
"snowy" => "❄️".to_string(), //2744 + fe0f
|
||
"snow" => "❄️".to_string(), //2744 + fe0f
|
||
"thunderstorm" => "🌩️".to_string(),//1f329 + fe0f
|
||
"thunder" => "🌩️".to_string(), //1f329 + fe0f
|
||
|
||
// This is the "other" section
|
||
"bel" => '\x07'.to_string(), // Terminal Bell
|
||
"backspace" => '\x08'.to_string(), // Backspace
|
||
|
||
// separators
|
||
"file_separator" => '\x1c'.to_string(),
|
||
"file_sep" => '\x1c'.to_string(),
|
||
"fs" => '\x1c'.to_string(),
|
||
"group_separator" => '\x1d'.to_string(),
|
||
"group_sep" => '\x1d'.to_string(),
|
||
"gs" => '\x1d'.to_string(),
|
||
"record_separator" => '\x1e'.to_string(),
|
||
"record_sep" => '\x1e'.to_string(),
|
||
"rs" => '\x1e'.to_string(),
|
||
"unit_separator" => '\x1f'.to_string(),
|
||
"unit_sep" => '\x1f'.to_string(),
|
||
"us" => '\x1f'.to_string(),
|
||
}
|
||
});
|
||
|
||
impl Command for Char {
|
||
fn name(&self) -> &str {
|
||
"char"
|
||
}
|
||
|
||
fn signature(&self) -> Signature {
|
||
Signature::build("char")
|
||
.input_output_types(vec![
|
||
(Type::Nothing, Type::String),
|
||
(Type::Nothing, Type::Table(vec![])),
|
||
])
|
||
.optional(
|
||
"character",
|
||
SyntaxShape::Any,
|
||
"the name of the character to output",
|
||
)
|
||
.rest("rest", SyntaxShape::Any, "multiple Unicode bytes")
|
||
.switch("list", "List all supported character names", Some('l'))
|
||
.switch("unicode", "Unicode string i.e. 1f378", Some('u'))
|
||
.switch("integer", "Create a codepoint from an integer", Some('i'))
|
||
.allow_variants_without_examples(true)
|
||
.category(Category::Strings)
|
||
}
|
||
|
||
fn usage(&self) -> &str {
|
||
"Output special characters (e.g., 'newline')."
|
||
}
|
||
|
||
fn search_terms(&self) -> Vec<&str> {
|
||
vec!["line break", "newline", "Unicode"]
|
||
}
|
||
|
||
fn examples(&self) -> Vec<Example> {
|
||
vec![
|
||
Example {
|
||
description: "Output newline",
|
||
example: r#"char newline"#,
|
||
result: Some(Value::test_string("\n")),
|
||
},
|
||
Example {
|
||
description: "List available characters",
|
||
example: r#"char --list"#,
|
||
result: None,
|
||
},
|
||
Example {
|
||
description: "Output prompt character, newline and a hamburger menu character",
|
||
example: r#"(char prompt) + (char newline) + (char hamburger)"#,
|
||
result: Some(Value::test_string("\u{25b6}\n\u{2261}")),
|
||
},
|
||
Example {
|
||
description: "Output Unicode character",
|
||
example: r#"char -u 1f378"#,
|
||
result: Some(Value::test_string("\u{1f378}")),
|
||
},
|
||
Example {
|
||
description: "Create Unicode from integer codepoint values",
|
||
example: r#"char -i (0x60 + 1) (0x60 + 2)"#,
|
||
result: Some(Value::test_string("ab")),
|
||
},
|
||
Example {
|
||
description: "Output multi-byte Unicode character",
|
||
example: r#"char -u 1F468 200D 1F466 200D 1F466"#,
|
||
result: Some(Value::test_string(
|
||
"\u{1F468}\u{200D}\u{1F466}\u{200D}\u{1F466}",
|
||
)),
|
||
},
|
||
]
|
||
}
|
||
|
||
fn run(
|
||
&self,
|
||
engine_state: &EngineState,
|
||
stack: &mut Stack,
|
||
call: &Call,
|
||
_input: PipelineData,
|
||
) -> Result<PipelineData, ShellError> {
|
||
let call_span = call.head;
|
||
// handle -l flag
|
||
if call.has_flag("list") {
|
||
return Ok(CHAR_MAP
|
||
.iter()
|
||
.map(move |(name, s)| {
|
||
let unicode = Value::string(
|
||
s.chars()
|
||
.map(|c| format!("{:x}", c as u32))
|
||
.collect::<Vec<String>>()
|
||
.join(" "),
|
||
call_span,
|
||
);
|
||
let record = record! {
|
||
"name" => Value::string(*name, call_span),
|
||
"character" => Value::string(s, call_span),
|
||
"unicode" => unicode,
|
||
};
|
||
|
||
Value::record(record, call_span)
|
||
})
|
||
.into_pipeline_data(engine_state.ctrlc.clone()));
|
||
}
|
||
// handle -u flag
|
||
if call.has_flag("integer") {
|
||
let args: Vec<i64> = call.rest(engine_state, stack, 0)?;
|
||
if args.is_empty() {
|
||
return Err(ShellError::MissingParameter {
|
||
param_name: "missing at least one unicode character".into(),
|
||
span: call_span,
|
||
});
|
||
}
|
||
let mut multi_byte = String::new();
|
||
for (i, &arg) in args.iter().enumerate() {
|
||
let span = call
|
||
.positional_nth(i)
|
||
.expect("Unexpected missing argument")
|
||
.span;
|
||
multi_byte.push(integer_to_unicode_char(arg, span)?)
|
||
}
|
||
Ok(Value::string(multi_byte, call_span).into_pipeline_data())
|
||
} else if call.has_flag("unicode") {
|
||
let args: Vec<String> = call.rest(engine_state, stack, 0)?;
|
||
if args.is_empty() {
|
||
return Err(ShellError::MissingParameter {
|
||
param_name: "missing at least one unicode character".into(),
|
||
span: call_span,
|
||
});
|
||
}
|
||
let mut multi_byte = String::new();
|
||
for (i, arg) in args.iter().enumerate() {
|
||
let span = call
|
||
.positional_nth(i)
|
||
.expect("Unexpected missing argument")
|
||
.span;
|
||
multi_byte.push(string_to_unicode_char(arg, span)?)
|
||
}
|
||
Ok(Value::string(multi_byte, call_span).into_pipeline_data())
|
||
} else {
|
||
let args: Vec<String> = call.rest(engine_state, stack, 0)?;
|
||
if args.is_empty() {
|
||
return Err(ShellError::MissingParameter {
|
||
param_name: "missing name of the character".into(),
|
||
span: call_span,
|
||
});
|
||
}
|
||
let special_character = str_to_character(&args[0]);
|
||
if let Some(output) = special_character {
|
||
Ok(Value::string(output, call_span).into_pipeline_data())
|
||
} else {
|
||
Err(ShellError::TypeMismatch {
|
||
err_message: "error finding named character".into(),
|
||
span: call
|
||
.positional_nth(0)
|
||
.expect("Unexpected missing argument")
|
||
.span,
|
||
})
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
fn integer_to_unicode_char(value: i64, t: Span) -> Result<char, ShellError> {
|
||
let decoded_char = value.try_into().ok().and_then(std::char::from_u32);
|
||
|
||
if let Some(ch) = decoded_char {
|
||
Ok(ch)
|
||
} else {
|
||
Err(ShellError::TypeMismatch {
|
||
err_message: "not a valid Unicode codepoint".into(),
|
||
span: t,
|
||
})
|
||
}
|
||
}
|
||
|
||
fn string_to_unicode_char(s: &str, t: Span) -> Result<char, ShellError> {
|
||
let decoded_char = u32::from_str_radix(s, 16)
|
||
.ok()
|
||
.and_then(std::char::from_u32);
|
||
|
||
if let Some(ch) = decoded_char {
|
||
Ok(ch)
|
||
} else {
|
||
Err(ShellError::TypeMismatch {
|
||
err_message: "error decoding Unicode character".into(),
|
||
span: t,
|
||
})
|
||
}
|
||
}
|
||
|
||
fn str_to_character(s: &str) -> Option<String> {
|
||
CHAR_MAP.get(s).map(|s| s.into())
|
||
}
|
||
|
||
#[cfg(test)]
|
||
mod tests {
|
||
use super::Char;
|
||
|
||
#[test]
|
||
fn examples_work_as_expected() {
|
||
use crate::test_examples;
|
||
|
||
test_examples(Char {})
|
||
}
|
||
}
|