make \minus equivalent to - operator #26193 (#40948)

* make \minus equivalent to - operator #26193

NEWS.md

@@ -22,6 +22,7 @@ Language changes
 
 * `macroexpand`, `@macroexpand`, and `@macroexpand1` no longer wrap errors in a `LoadError`. To reduce breakage, `@test_throws` has been modified so that many affected tests will still pass ([#38379]].
 * The middle dot `·` (`\cdotp` U+00b7) and the Greek interpunct `·` (U+0387) are now treated as equivalent to the dot operator `⋅` (`\cdot` U+22c5) (#25157).
+* The minus sign `−` (`\minus` U+2212) is now treated as equivalent to the hyphen-minus sign `-` (U+002d).
 
 Compiler/Runtime improvements
 -----------------------------

doc/src/manual/variables.md

@@ -143,6 +143,7 @@ are treated as equivalent to the corresponding Greek letters. The middle dot
 `·` (U+00B7) and the Greek
 [interpunct](https://en.wikipedia.org/wiki/Interpunct) `·` (U+0387) are both
 treated as the mathematical dot operator `⋅` (U+22C5).
+The minus sign `−` (U+2212) is treated as equivalent to the hyphen-minus sign `-` (U+002D).
 
 ## Stylistic Conventions
 

src/flisp/julia_charmap.h

@@ -6,4 +6,5 @@ static const uint32_t charmap[][2] = {
     { 0x00B5, 0x03BC }, // micro sign -> greek small letter mu
     { 0x00B7, 0x22C5 }, // middot char -> dot operator (#25098)
     { 0x0387, 0x22C5 }, // Greek interpunct -> dot operator (#25098)
+    { 0x2212, 0x002D }, // minus -> hyphen-minus (#26193)
 };

src/julia-parser.scm

@@ -4,7 +4,7 @@
 (define (add-dots ops) (append! ops (map (lambda (op) (symbol (string "." op))) ops)))
 
 (define prec-assignment
-  (append! (add-dots '(= += -= *= /= //= |\\=| ^= ÷= %= <<= >>= >>>= |\|=| &= ⊻= ≔ ⩴ ≕))
+  (append! (add-dots '(= += -= −= *= /= //= |\\=| ^= ÷= %= <<= >>= >>>= |\|=| &= ⊻= ≔ ⩴ ≕))
            (add-dots '(~))
            '(:= $=)))
 ;; comma - higher than assignment outside parentheses, lower when inside
@@ -20,7 +20,7 @@
 (define prec-pipe>       '(|.\|>| |\|>|))
 (define prec-colon       (append! '(: |..|) (add-dots '(… ⁝ ⋮ ⋱ ⋰ ⋯))))
 (define prec-plus        (append! '($)
-                          (add-dots '(+ - ¦ |\|| ⊕ ⊖ ⊞ ⊟ |++| ∪ ∨ ⊔ ± ∓ ∔ ∸ ≏ ⊎ ⊻ ⊽ ⋎ ⋓ ⧺ ⧻ ⨈ ⨢ ⨣ ⨤ ⨥ ⨦ ⨧ ⨨ ⨩ ⨪ ⨫ ⨬ ⨭ ⨮ ⨹ ⨺ ⩁ ⩂ ⩅ ⩊ ⩌ ⩏ ⩐ ⩒ ⩔ ⩖ ⩗ ⩛ ⩝ ⩡ ⩢ ⩣))))
+                          (add-dots '(+ - − ¦ |\|| ⊕ ⊖ ⊞ ⊟ |++| ∪ ∨ ⊔ ± ∓ ∔ ∸ ≏ ⊎ ⊻ ⊽ ⋎ ⋓ ⧺ ⧻ ⨈ ⨢ ⨣ ⨤ ⨥ ⨦ ⨧ ⨨ ⨩ ⨪ ⨫ ⨬ ⨭ ⨮ ⨹ ⨺ ⩁ ⩂ ⩅ ⩊ ⩌ ⩏ ⩐ ⩒ ⩔ ⩖ ⩗ ⩛ ⩝ ⩡ ⩢ ⩣))))
 (define prec-times       (add-dots '(* / ⌿ ÷ % & · · ⋅ ∘ × |\\| ∩ ∧ ⊗ ⊘ ⊙ ⊚ ⊛ ⊠ ⊡ ⊓ ∗ ∙ ∤ ⅋ ≀ ⊼ ⋄ ⋆ ⋇ ⋉ ⋊ ⋋ ⋌ ⋏ ⋒ ⟑ ⦸ ⦼ ⦾ ⦿ ⧶ ⧷ ⨇ ⨰ ⨱ ⨲ ⨳ ⨴ ⨵ ⨶ ⨷ ⨸ ⨻ ⨼ ⨽ ⩀ ⩃ ⩄ ⩋ ⩍ ⩎ ⩑ ⩓ ⩕ ⩘ ⩚ ⩜ ⩞ ⩟ ⩠ ⫛ ⊍ ▷ ⨝ ⟕ ⟖ ⟗ ⨟)))
 (define prec-rational    (add-dots '(//)))
 (define prec-bitshift    (add-dots '(<< >> >>>)))
@@ -377,13 +377,17 @@
               (and (eq? pred char-hex?) ispP)
               (memv c '(#\e #\E #\f)))
           (begin (read-char port)
-                 (let ((d (peek-char port)))
+                 (let* ((d (peek-char port))
+                        (is-minus-sign (or (eqv? d #\-) (eqv? d #\u2212))))
                    (if (and (not (eof-object? d))
-                            (or (char-numeric? d) (eqv? d #\+) (eqv? d #\-)))
+                            (or (char-numeric? d) (eqv? d #\+) is-minus-sign))
                        (begin (set! is-float32-literal (eqv? c #\f))
                               (set! is-hex-float-literal ispP)
                               (write-char c str)
-                              (write-char (read-char port) str)
+                              (if is-minus-sign
+                                  (begin (read-char port)
+                                         (write-char #\- str))
+                                  (write-char (read-char port) str))
                               (read-digs #t #f)
                               (disallow-dot))
                        (io.ungetc port c)))))

test/syntax.jl

@@ -819,7 +819,7 @@ let f = function (x; kw...)
 end
 
 # normalization of Unicode symbols (#19464)
-let ε=1, μ=2, x=3, î=4, ⋅=5
+let ε=1, μ=2, x=3, î=4, ⋅=5, (-)=6
     # issue #5434 (mu vs micro):
     @test Meta.parse("\u00b5") === Meta.parse("\u03bc")
     @test µ == μ == 2
@@ -832,6 +832,17 @@ let ε=1, μ=2, x=3, î=4, ⋅=5
     # middot char · or · vs math dot operator ⋅ (#25098)
     @test Meta.parse("\u00b7") === Meta.parse("\u0387") === Meta.parse("\u22c5")
     @test (·) == (·) == (⋅) == 5
+    # minus − vs hyphen-minus - (#26193)
+    @test Meta.parse("\u2212") === Meta.parse("-")
+    @test Meta.parse("\u221242") === Meta.parse("-42")
+    @test Meta.parse("\u2212 42") == Meta.parse("- 42")
+    @test Meta.parse("\u2212x") == Meta.parse("-x")
+    @test Meta.parse("x \u2212 42") == Meta.parse("x - 42")
+    @test Meta.parse("x \u2212= 42") == Meta.parse("x -= 42")
+    @test Meta.parse("100.0e\u22122") === Meta.parse("100.0E\u22122") === Meta.parse("100.0e-2")
+    @test Meta.parse("100.0f\u22122") === Meta.parse("100.0f-2")
+    @test Meta.parse("0x100p\u22128") === Meta.parse("0x100P\u22128") === Meta.parse("0x100p-8")
+    @test (−) == (-) == 6
 end
 
 # issue #8925