add str deunicode command (#13270)

# Description

Sometimes it's helpful to deal with only ASCII. This command will take a
unicode string as input and convert it to ASCII using the deunicode
crate.

```nushell
❯ "A…B" | str deunicode
A...B
```

# 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 toolkit.nu; toolkit test stdlib"` 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.
-->

Cargo.lock

@@ -377,7 +377,7 @@ dependencies = [
  "bitflags 2.5.0",
  "cexpr",
  "clang-sys",
- "itertools 0.11.0",
+ "itertools 0.12.1",
  "lazy_static",
  "lazycell",
  "proc-macro2",
@@ -1148,6 +1148,12 @@ dependencies = [
  "syn 1.0.109",
 ]
 
+[[package]]
+name = "deunicode"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "339544cc9e2c4dc3fc7149fd630c5f22263a4fdf18a98afd0075784968b5cf00"
+
 [[package]]
 name = "dialoguer"
 version = "0.11.0"
@@ -2967,6 +2973,7 @@ dependencies = [
  "chrono-tz 0.8.6",
  "crossterm",
  "csv",
+ "deunicode",
  "dialoguer",
  "digest",
  "dirs-next",

Cargo.toml

@@ -80,6 +80,7 @@ crossbeam-channel = "0.5.8"
 crossterm = "0.27"
 csv = "1.3"
 ctrlc = "3.4"
+deunicode = "1.6.0"
 dialoguer = { default-features = false, version = "0.11" }
 digest = { default-features = false, version = "0.10" }
 dirs-next = "2.0"

crates/nu-command/Cargo.toml

@@ -42,6 +42,7 @@ chrono-humanize = { workspace = true }
 chrono-tz = { workspace = true }
 crossterm = { workspace = true }
 csv = { workspace = true }
+deunicode = { workspace = true }
 dialoguer = { workspace = true, default-features = false, features = ["fuzzy-select"] }
 digest = { workspace = true, default-features = false }
 dtparse = { workspace = true }

crates/nu-command/src/default_context.rs

@@ -189,6 +189,7 @@ pub fn add_shell_command_context(mut engine_state: EngineState) -> EngineState {
             Str,
             StrCapitalize,
             StrContains,
+            StrDeunicode,
             StrDistance,
             StrDowncase,
             StrEndswith,

crates/nu-command/src/strings/str_/deunicode.rs

@@ -0,0 +1,98 @@
+use deunicode::deunicode;
+use nu_cmd_base::input_handler::{operate, CellPathOnlyArgs};
+use nu_engine::command_prelude::*;
+use nu_protocol::engine::StateWorkingSet;
+
+#[derive(Clone)]
+pub struct SubCommand;
+
+impl Command for SubCommand {
+    fn name(&self) -> &str {
+        "str deunicode"
+    }
+
+    fn signature(&self) -> Signature {
+        Signature::build("str deunicode")
+            .input_output_types(vec![(Type::String, Type::String)])
+            .category(Category::Strings)
+    }
+
+    fn usage(&self) -> &str {
+        "Convert Unicode string to pure ASCII."
+    }
+
+    fn search_terms(&self) -> Vec<&str> {
+        vec!["convert", "ascii"]
+    }
+
+    fn is_const(&self) -> bool {
+        true
+    }
+
+    fn run(
+        &self,
+        engine_state: &EngineState,
+        stack: &mut Stack,
+        call: &Call,
+        input: PipelineData,
+    ) -> Result<PipelineData, ShellError> {
+        let cell_paths: Vec<CellPath> = call.rest(engine_state, stack, 0)?;
+        let args = CellPathOnlyArgs::from(cell_paths);
+
+        operate(action, args, input, call.head, engine_state.ctrlc.clone())
+    }
+
+    fn run_const(
+        &self,
+        working_set: &StateWorkingSet,
+        call: &Call,
+        input: PipelineData,
+    ) -> Result<PipelineData, ShellError> {
+        let cell_paths: Vec<CellPath> = call.rest_const(working_set, 0)?;
+        let args = CellPathOnlyArgs::from(cell_paths);
+
+        operate(
+            action,
+            args,
+            input,
+            call.head,
+            working_set.permanent().ctrlc.clone(),
+        )
+    }
+
+    fn examples(&self) -> Vec<Example> {
+        vec![Example {
+            description: "deunicode a string",
+            example: "'A…B' | str deunicode",
+            result: Some(Value::test_string("A...B")),
+        }]
+    }
+}
+
+fn action(input: &Value, _args: &CellPathOnlyArgs, head: Span) -> Value {
+    match input {
+        Value::String { val, .. } => Value::string(deunicode(val), head),
+        Value::Error { .. } => input.clone(),
+        _ => Value::error(
+            ShellError::OnlySupportsThisInputType {
+                exp_input_type: "string".into(),
+                wrong_type: input.get_type().to_string(),
+                dst_span: head,
+                src_span: input.span(),
+            },
+            head,
+        ),
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_examples() {
+        use crate::test_examples;
+
+        test_examples(SubCommand {})
+    }
+}

crates/nu-command/src/strings/str_/mod.rs

@@ -1,5 +1,6 @@
 mod case;
 mod contains;
+mod deunicode;
 mod distance;
 mod ends_with;
 mod expand;
@@ -15,6 +16,7 @@ mod trim;
 
 pub use case::*;
 pub use contains::SubCommand as StrContains;
+pub use deunicode::SubCommand as StrDeunicode;
 pub use distance::SubCommand as StrDistance;
 pub use ends_with::SubCommand as StrEndswith;
 pub use expand::SubCommand as StrExpand;