lexer: add seven more unicode operators (#26074)

closes nim-lang/RFCs#571

Adds `⟑ ⟇ ⩓ ⩔ ■ □ ☆` with the same priority as `*`.

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Andreas Rumpf <rumpf_a@web.de>

changelog.md

@@ -137,6 +137,11 @@ parameter and result types, not just their source-level shape. Use
   See the [experimental manual](https://nim-lang.github.io/Nim/manual_experimental.html#typeminusbound-overloads)
   for more information.
 
+- Seven more Unicode characters are now parsed as operators, implementing the RFC
+  https://github.com/nim-lang/RFCs/issues/571: `⟑ ⟇ ⩓ ⩔ ■ □ ☆`. They all have the
+  same priority as `*` (multiplication). As with the other Unicode operators, Nim
+  only lexes them; their meaning is up to user code.
+
 ## Compiler changes
 
 - Fixed a bug where `sizeof(T)` inside a `typedesc` template called from a generic type's

compiler/lexer.nim

@@ -845,8 +845,8 @@ proc getCharacter(L: var Lexer; tok: var Token) =
 
 const
   UnicodeOperatorStartChars = {'\226', '\194', '\195'}
-    # the allowed unicode characters ("∙ ∘ × ★ ⊗ ⊘ ⊙ ⊛ ⊠ ⊡ ∩ ∧ ⊓ ± ⊕ ⊖ ⊞ ⊟ ∪ ∨ ⊔")
-    # all start with one of these.
+    # the allowed unicode characters ("∙ ∘ × ★ ☆ ⊗ ⊘ ⊙ ⊛ ⊠ ⊡ ∩ ∧ ⊓ ⟑ ⟇ ⩓ ⩔ ■ □
+    # ± ⊕ ⊖ ⊞ ⊟ ∪ ∨ ⊔") all start with one of these.
 
 type
   UnicodeOprPred = enum
@@ -878,7 +878,18 @@ proc unicodeOprLen(buf: cstring; pos: int): (int8, UnicodeOprPred) =
       elif buf[pos+2] == '\159': result = 3.a # ⊟
       elif buf[pos+2] == '\160': result = 3.m # ⊠
       elif buf[pos+2] == '\161': result = 3.m # ⊡
-    elif buf[pos+1] == '\152' and buf[pos+2] == '\133': result = 3.m # ★
+    elif buf[pos+1] == '\150':
+      if buf[pos+2] == '\160': result = 3.m # ■
+      elif buf[pos+2] == '\161': result = 3.m # □
+    elif buf[pos+1] == '\152':
+      if buf[pos+2] == '\133': result = 3.m # ★
+      elif buf[pos+2] == '\134': result = 3.m # ☆
+    elif buf[pos+1] == '\159':
+      if buf[pos+2] == '\135': result = 3.m # ⟇
+      elif buf[pos+2] == '\145': result = 3.m # ⟑
+    elif buf[pos+1] == '\169':
+      if buf[pos+2] == '\147': result = 3.m # ⩓
+      elif buf[pos+2] == '\148': result = 3.m # ⩔
   of '\194':
     if buf[pos+1] == '\177': result = 2.a # ±
   of '\195':

doc/manual.md

@@ -712,8 +712,8 @@ Unicode Operators
 
 These Unicode operators are also parsed as operators:
 
-    ∙ ∘ × ★ ⊗ ⊘ ⊙ ⊛ ⊠ ⊡ ∩ ∧ ⊓   # same priority as * (multiplication)
-    ± ⊕ ⊖ ⊞ ⊟ ∪ ∨ ⊔             # same priority as + (addition)
+    ∙ ∘ × ★ ☆ ⊗ ⊘ ⊙ ⊛ ⊠ ⊡ ∩ ∧ ⊓ ⟑ ⟇ ⩓ ⩔ ■ □   # same priority as * (multiplication)
+    ± ⊕ ⊖ ⊞ ⊟ ∪ ∨ ⊔                           # same priority as + (addition)
 
 
 Unicode operators can be combined with non-Unicode operator

tests/lexer/tunicode_operators.nim

@@ -14,3 +14,26 @@ var y = 45
 y *= 9 + 4 * 3
 
 assert x == y
+
+proc `⟑`(x, y: int): int = x * y
+proc `⟇`(x, y: int): int = x * y
+proc `⩓`(x, y: int): int = x * y
+proc `⩔`(x, y: int): int = x * y
+proc `■`(x, y: int): int = x * y
+proc `□`(x, y: int): int = x * y
+proc `☆`(x, y: int): int = x * y
+proc `★`(x, y: int): int = x * y
+
+assert 2 + 3 ⟑ 4 ⟇ 5 ⩓ 6 ⩔ 7 ■ 8 □ 9 ☆ 10 ★ 11 == 2 + 3 * 4 * 5 * 6 * 7 * 8 * 9 * 10 * 11
+
+proc `⟑=`(x: var int, y: int) = x *= y
+
+proc `⩓++`(x, y: int): int = x * y
+
+var z = 45
+z ⟑= a⩓++4⟑3
+
+var w = 45
+w *= 9 * 4 * 3
+
+assert z == w