Files
nushell/crates/nu-command/src/strings/char_.rs
Darren Schroeder 366348dea0 make char command const (#11771)
# Description

This PR makes the `char` command a `const` command. The only real
changes are to get the arguments different and I extracted code into
functions so they could be called via run and run_cost. No algorithms
were harmed in the making of this PR.

# 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` to
check that you're using the standard code style
- `cargo test --workspace` to check that all tests pass (on Windows make
sure to [enable developer
mode](https://learn.microsoft.com/en-us/windows/apps/get-started/developer-mode-features-and-debugging))
- `cargo run -- -c "use std testing; testing run-tests --path
crates/nu-std"` 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.
-->
2024-02-07 16:29:00 -06:00

432 lines
16 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

use indexmap::indexmap;
use indexmap::map::IndexMap;
use nu_engine::CallExt;
use nu_protocol::engine::{EngineState, Stack, StateWorkingSet};
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;
use std::sync::{atomic::AtomicBool, Arc};
// 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::Any)])
.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 is_const(&self) -> bool {
true
}
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 --unicode 1f378"#,
result: Some(Value::test_string("\u{1f378}")),
},
Example {
description: "Create Unicode from integer codepoint values",
example: r#"char --integer (0x60 + 1) (0x60 + 2)"#,
result: Some(Value::test_string("ab")),
},
Example {
description: "Output multi-byte Unicode character",
example: r#"char --unicode 1F468 200D 1F466 200D 1F466"#,
result: Some(Value::test_string(
"\u{1F468}\u{200D}\u{1F466}\u{200D}\u{1F466}",
)),
},
]
}
fn run_const(
&self,
working_set: &StateWorkingSet,
call: &Call,
_input: PipelineData,
) -> Result<PipelineData, ShellError> {
let call_span = call.head;
let list = call.has_flag_const(working_set, "list")?;
let integer = call.has_flag_const(working_set, "integer")?;
let unicode = call.has_flag_const(working_set, "unicode")?;
let ctrlc = working_set.permanent().ctrlc.clone();
// handle -l flag
if list {
return generate_character_list(ctrlc, call.head);
}
// handle -i flag
if integer {
let int_args: Vec<i64> = call.rest_const(working_set, 0)?;
handle_integer_flag(int_args, call, call_span)
}
// handle -u flag
else if unicode {
let string_args: Vec<String> = call.rest_const(working_set, 0)?;
handle_unicode_flag(string_args, call, call_span)
}
// handle the rest
else {
let string_args: Vec<String> = call.rest_const(working_set, 0)?;
handle_the_rest(string_args, call, call_span)
}
}
fn run(
&self,
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
_input: PipelineData,
) -> Result<PipelineData, ShellError> {
let call_span = call.head;
let list = call.has_flag(engine_state, stack, "list")?;
let integer = call.has_flag(engine_state, stack, "integer")?;
let unicode = call.has_flag(engine_state, stack, "unicode")?;
let ctrlc = engine_state.ctrlc.clone();
// handle -l flag
if list {
return generate_character_list(ctrlc, call_span);
}
// handle -i flag
if integer {
let int_args: Vec<i64> = call.rest(engine_state, stack, 0)?;
handle_integer_flag(int_args, call, call_span)
}
// handle -u flag
else if unicode {
let string_args: Vec<String> = call.rest(engine_state, stack, 0)?;
handle_unicode_flag(string_args, call, call_span)
}
// handle the rest
else {
let string_args: Vec<String> = call.rest(engine_state, stack, 0)?;
handle_the_rest(string_args, call, call_span)
}
}
}
fn generate_character_list(
ctrlc: Option<Arc<AtomicBool>>,
call_span: Span,
) -> Result<PipelineData, ShellError> {
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(ctrlc))
}
fn handle_integer_flag(
int_args: Vec<i64>,
call: &Call,
call_span: Span,
) -> Result<PipelineData, ShellError> {
if int_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 int_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())
}
fn handle_unicode_flag(
string_args: Vec<String>,
call: &Call,
call_span: Span,
) -> Result<PipelineData, ShellError> {
if string_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 string_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())
}
fn handle_the_rest(
string_args: Vec<String>,
call: &Call,
call_span: Span,
) -> Result<PipelineData, ShellError> {
if string_args.is_empty() {
return Err(ShellError::MissingParameter {
param_name: "missing name of the character".into(),
span: call_span,
});
}
let special_character = str_to_character(&string_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 {})
}
}