Custom command input/output types (#9690)

# Description

This adds input/output types to custom commands. These are input/output
pairs that related an input type to an output type.

For example (a single int-to-int input/output pair):

```
def foo []: int -> int { ... }
```

You can also have multiple input/output pairs:
```
def bar []: [int -> string, string -> list<string>] { ... }
```

These types are checked during definition time in the parser. If the
block does not match the type, the user will get a parser error.

This `:` to begin the input/output signatures should immediately follow
the argument signature as shown above.

The PR also improves type parsing by re-using the shape parser. The
shape parser is now the canonical way to parse types/shapes in user
code.

This PR also splits `extern` into `extern`/`extern-wrapped` because of
the parser limitation that a multi-span argument (which Signature now
is) can't precede an optional argument. `extern-wrapped` now takes the
required block that was previously optional.

# User-Facing Changes

The change to `extern` to split into `extern` and `extern-wrapped` is a
breaking change.

# 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 -- -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.
-->

crates/nu-parser/src/parser.rs

@@ -682,6 +682,14 @@ pub fn parse_multispan_value(
 
             arg
         }
+        SyntaxShape::Signature => {
+            trace!("parsing: signature");
+
+            let sig = parse_full_signature(working_set, &spans[*spans_idx..]);
+            *spans_idx = spans.len() - 1;
+
+            sig
+        }
         SyntaxShape::Keyword(keyword, arg) => {
             trace!(
                 "parsing: keyword({}) {:?}",
@@ -2932,36 +2940,7 @@ fn prepare_inner_span(
 }
 
 pub fn parse_type(working_set: &mut StateWorkingSet, bytes: &[u8], span: Span) -> Type {
-    match bytes {
-        b"binary" => Type::Binary,
-        b"block" => {
-            working_set.error(ParseError::LabeledErrorWithHelp {
-                error: "Blocks are not support as first-class values".into(),
-                label: "blocks are not supported as values".into(),
-                help: "Use 'closure' instead of 'block'".into(),
-                span,
-            });
-
-            Type::Any
-        }
-        b"bool" => Type::Bool,
-        b"cellpath" => Type::CellPath,
-        b"closure" => Type::Closure,
-        b"date" => Type::Date,
-        b"duration" => Type::Duration,
-        b"error" => Type::Error,
-        b"filesize" => Type::Filesize,
-        b"float" | b"decimal" => Type::Float,
-        b"int" => Type::Int,
-        b"list" => Type::List(Box::new(Type::Any)),
-        b"number" => Type::Number,
-        b"range" => Type::Range,
-        b"record" => Type::Record(vec![]),
-        b"string" => Type::String,
-        b"table" => Type::Table(vec![]), //FIXME
-
-        _ => Type::Any,
-    }
+    parse_shape_name(working_set, bytes, span).to_type()
 }
 
 pub fn parse_import_pattern(working_set: &mut StateWorkingSet, spans: &[Span]) -> Expression {
@@ -3199,6 +3178,95 @@ pub fn expand_to_cell_path(
     }
 }
 
+pub fn parse_input_output_types(
+    working_set: &mut StateWorkingSet,
+    spans: &[Span],
+) -> Vec<(Type, Type)> {
+    let mut full_span = span(spans);
+
+    let mut bytes = working_set.get_span_contents(full_span);
+
+    if bytes.starts_with(b"[") {
+        bytes = &bytes[1..];
+        full_span.start += 1;
+    }
+
+    if bytes.ends_with(b"]") {
+        bytes = &bytes[..(bytes.len() - 1)];
+        full_span.end -= 1;
+    }
+
+    let (tokens, parse_error) = lex(bytes, full_span.start, &[b','], &[], true);
+
+    if let Some(parse_error) = parse_error {
+        working_set.parse_errors.push(parse_error);
+    }
+
+    let mut output = vec![];
+
+    let mut idx = 0;
+    while idx < tokens.len() {
+        let type_bytes = working_set.get_span_contents(tokens[idx].span).to_vec();
+        let input_type = parse_type(working_set, &type_bytes, tokens[idx].span);
+
+        idx += 1;
+        if idx >= tokens.len() {
+            working_set.error(ParseError::Expected(
+                "arrow (->)",
+                Span::new(tokens[idx - 1].span.end, tokens[idx - 1].span.end),
+            ));
+            break;
+        }
+
+        let arrow = working_set.get_span_contents(tokens[idx].span);
+        if arrow != b"->" {
+            working_set.error(ParseError::Expected("arrow (->)", tokens[idx].span));
+        }
+
+        idx += 1;
+        if idx >= tokens.len() {
+            working_set.error(ParseError::MissingType(Span::new(
+                tokens[idx - 1].span.end,
+                tokens[idx - 1].span.end,
+            )));
+            break;
+        }
+
+        let type_bytes = working_set.get_span_contents(tokens[idx].span).to_vec();
+        let output_type = parse_type(working_set, &type_bytes, tokens[idx].span);
+
+        output.push((input_type, output_type));
+
+        idx += 1;
+    }
+
+    output
+}
+
+pub fn parse_full_signature(working_set: &mut StateWorkingSet, spans: &[Span]) -> Expression {
+    let arg_signature = working_set.get_span_contents(spans[0]);
+
+    if arg_signature.ends_with(b":") {
+        let mut arg_signature =
+            parse_signature(working_set, Span::new(spans[0].start, spans[0].end - 1));
+
+        let input_output_types = parse_input_output_types(working_set, &spans[1..]);
+
+        if let Expression {
+            expr: Expr::Signature(sig),
+            span: expr_span,
+            ..
+        } = &mut arg_signature
+        {
+            sig.input_output_types = input_output_types;
+            expr_span.end = span(&spans[1..]).end;
+        }
+        arg_signature
+    } else {
+        parse_signature(working_set, spans[0])
+    }
+}
+
 pub fn parse_row_condition(working_set: &mut StateWorkingSet, spans: &[Span]) -> Expression {
     let var_id = working_set.add_variable(b"$it".to_vec(), span(spans), Type::Any, false);
     let expression = parse_math_expression(working_set, spans, Some(var_id));
@@ -5026,8 +5094,8 @@ pub fn parse_expression(
 
         // For now, check for special parses of certain keywords
         match bytes.as_slice() {
-            b"def" | b"extern" | b"for" | b"module" | b"use" | b"source" | b"alias" | b"export"
-            | b"hide" => {
+            b"def" | b"extern" | b"extern-wrapped" | b"for" | b"module" | b"use" | b"source"
+            | b"alias" | b"export" | b"hide" => {
                 working_set.error(ParseError::BuiltinCommandInPipeline(
                     String::from_utf8(bytes)
                         .expect("builtin commands bytes should be able to convert to string"),
@@ -5194,7 +5262,7 @@ pub fn parse_builtin_commands(
 
     match name {
         b"def" | b"def-env" => parse_def(working_set, lite_command, None),
-        b"extern" => parse_extern(working_set, lite_command, None),
+        b"extern" | b"extern-wrapped" => parse_extern(working_set, lite_command, None),
         b"let" => parse_let(working_set, &lite_command.parts),
         b"const" => parse_const(working_set, &lite_command.parts),
         b"mut" => parse_mut(working_set, &lite_command.parts),
@@ -5582,7 +5650,10 @@ pub fn parse_block(
 
     block.span = Some(span);
 
-    type_check::check_block_input_output(working_set, &block);
+    let errors = type_check::check_block_input_output(working_set, &block);
+    if !errors.is_empty() {
+        working_set.parse_errors.extend_from_slice(&errors);
+    }
 
     block
 }