Unicode input feature

numbat-cli/Cargo.toml

@@ -14,7 +14,7 @@ rust-version = "1.70"
 
 [dependencies]
 anyhow = "1"
-rustyline = { version = "12", features = ["derive"] }
+rustyline = { version = "13", features = ["derive"] }
 dirs = "5"
 numbat = { version = "1.8.0", path = "../numbat" }
 colored = "2"

numbat-cli/src/completer.rs

@@ -1,6 +1,6 @@
 use std::sync::{Arc, Mutex};
 
-use numbat::Context;
+use numbat::{unicode_input::UNICODE_INPUT, Context};
 use rustyline::{
     self,
     completion::{extract_word, Completer, Pair},
@@ -20,6 +20,21 @@ impl Completer for NumbatCompleter {
         pos: usize,
         _: &rustyline::Context<'_>,
     ) -> rustyline::Result<(usize, Vec<Self::Candidate>)> {
+        for (patterns, replacement) in UNICODE_INPUT {
+            for pattern in *patterns {
+                let backslash_pattern = format!("\\{}", pattern);
+                if line[..pos].ends_with(&backslash_pattern) {
+                    return Ok((
+                        pos - (1 + pattern.len()),
+                        vec![Pair {
+                            display: backslash_pattern.to_string(),
+                            replacement: replacement.to_string(),
+                        }],
+                    ));
+                }
+            }
+        }
+
         if line.starts_with("use ") {
             return Ok((
                 0,

numbat/modules/units/misc.nbt

@@ -10,7 +10,7 @@ unit bar: Pressure = 100 kPa
 
 @name("Ångström")
 @url("https://en.wikipedia.org/wiki/Angstrom")
-@aliases(angstroms, Å: short)
+@aliases(angstroms, Å: short, Å: short)
 unit angstrom: Length = 1e-10 meter
 
 @name("Barn")

numbat/src/lib.rs

@@ -30,6 +30,7 @@ mod suggestion;
 mod tokenizer;
 mod typechecker;
 mod typed_ast;
+pub mod unicode_input;
 mod unit;
 mod unit_registry;
 pub mod value;
@@ -68,6 +69,7 @@ use unit::BaseUnitAndFactor;
 use unit_registry::UnitMetadata;
 
 use crate::prefix_parser::PrefixParserResult;
+use crate::unicode_input::UNICODE_INPUT;
 
 #[derive(Debug, Error)]
 pub enum NumbatError {
@@ -215,6 +217,12 @@ impl Context {
 
         let mut words: Vec<_> = KEYWORDS.iter().map(|k| k.to_string()).collect();
 
+        for (patterns, _) in UNICODE_INPUT {
+            for pattern in *patterns {
+                words.push(pattern.to_string());
+            }
+        }
+
         {
             for variable in self.variable_names() {
                 words.push(variable.clone());

numbat/src/unicode_input.rs

@@ -0,0 +1,77 @@
+// We are following Julia here [1], but we only support
+// a small (useful) subset of sequences for now.
+// [1] https://docs.julialang.org/en/v1/manual/unicode-input/
+pub const UNICODE_INPUT: &[(&[&str], &str)] = &[
+    // Superscript symbols
+    (&["^-"], "⁻"),
+    (&["pm"], "±"),
+    (&["^1"], "¹"),
+    (&["^2"], "²"),
+    (&["^3"], "³"),
+    (&["^4"], "⁴"),
+    (&["^5"], "⁵"),
+    (&["^6"], "⁶"),
+    (&["^7"], "⁷"),
+    (&["^8"], "⁸"),
+    (&["^9"], "⁹"),
+    // Numbers
+    (&["1/2"], "½"),
+    // Operators
+    (&["cdot"], "⋅"),
+    (&["cdotp"], "·"),
+    (&["times"], "×"),
+    (&["div"], "÷"),
+    (&["to", "rightarrow"], "→"),
+    (&["ge"], "≥"),
+    (&["le"], "≤"),
+    (&["dots", "ldots"], "…"),
+    // Greek alphabet
+    (&["Gamma"], "Γ"),
+    (&["Delta"], "Δ"),
+    (&["Theta"], "Θ"),
+    (&["Lambda"], "Λ"),
+    (&["Pi"], "Π"),
+    (&["Sigma"], "Σ"),
+    (&["Phi"], "Φ"),
+    (&["Psi"], "Ψ"),
+    (&["Omega"], "Ω"),
+    (&["alpha"], "α"),
+    (&["beta"], "β"),
+    (&["gamma"], "γ"),
+    (&["delta"], "δ"),
+    (&["epsilon"], "ε"),
+    (&["varepsilon"], "ϵ"),
+    (&["zeta"], "ζ"),
+    (&["eta"], "η"),
+    (&["theta"], "θ"),
+    (&["vartheta"], "ϑ"),
+    (&["iota"], "ι"),
+    (&["kappa"], "κ"),
+    (&["lambda"], "λ"),
+    (&["mu"], "μ"),
+    (&["nu"], "ν"),
+    (&["xi"], "ξ"),
+    (&["pi"], "π"),
+    (&["rho"], "ρ"),
+    (&["sigma"], "σ"),
+    (&["tau"], "τ"),
+    (&["upsilon"], "υ"),
+    (&["phi"], "ϕ"),
+    (&["varphi"], "φ"),
+    (&["chi"], "χ"),
+    (&["psi"], "ψ"),
+    (&["omega"], "ω"),
+    // Units
+    (&["sterling"], "£"),
+    (&["yen"], "¥"),
+    (&["euro"], "€"),
+    (&["degree"], "°"),
+    (&["ohm"], "Ω"),
+    (&["Angstrom"], "Å"),
+    (&["percent"], "%"),
+    (&["perthousand"], "‰"),
+    (&["pertenthousand"], "‱"),
+    // Constants
+    (&["hbar"], "ℏ"),
+    (&["planck"], "ℎ"),
+];