allow identifiers to start with category No (Number, other)

NEWS.md

@@ -35,6 +35,10 @@ New language features
   which can be overloaded to customize its behavior for different collection types
   ([#37410]).
 
+  * Identifiers can now start with numeric symbols in category
+    [No: Number, other](http://www.fileformat.info/info/unicode/category/No/list.htm),
+    allowing you to have variables with names like `⅓x` or `¹x₂` ([#20278]).
+
 Language changes
 ----------------
 

doc/src/manual/variables.md

@@ -94,9 +94,9 @@ ERROR: cannot assign a value to variable Base.sqrt from module Main
 
 Variable names must begin with a letter (A-Z or a-z), underscore, or a subset of Unicode code
 points greater than 00A0; in particular, [Unicode character categories](http://www.fileformat.info/info/unicode/category/index.htm)
-Lu/Ll/Lt/Lm/Lo/Nl (letters), Sc/So (currency and other symbols), and a few other letter-like characters
+Lu/Ll/Lt/Lm/Lo/Nl/No (letters and certain numeric symbols), Sc/So (currency and other symbols), and a few other letter-like characters
 (e.g. a subset of the Sm math symbols) are allowed. Subsequent characters may also include ! and
-digits (0-9 and other characters in categories Nd/No), as well as other Unicode code points: diacritics
+digits (0-9 and other decimal digits in category Nd), as well as other Unicode code points: diacritics
 and other modifying marks (categories Mn/Mc/Me/Sk), some punctuation connectors (category Pc),
 primes, and a few other characters.
 

src/flisp/julia_extensions.c

@@ -68,7 +68,8 @@ static int is_wc_cat_id_start(uint32_t wc, utf8proc_category_t cat)
 {
     return (cat == UTF8PROC_CATEGORY_LU || cat == UTF8PROC_CATEGORY_LL ||
             cat == UTF8PROC_CATEGORY_LT || cat == UTF8PROC_CATEGORY_LM ||
-            cat == UTF8PROC_CATEGORY_LO || cat == UTF8PROC_CATEGORY_NL ||
+            cat == UTF8PROC_CATEGORY_LO ||
+            cat == UTF8PROC_CATEGORY_NL || cat == UTF8PROC_CATEGORY_NO ||
             cat == UTF8PROC_CATEGORY_SC ||  // allow currency symbols
             // other symbols, but not arrows or replacement characters
             (cat == UTF8PROC_CATEGORY_SO && !(wc >= 0x2190 && wc <= 0x21FF) &&
@@ -144,7 +145,6 @@ JL_DLLEXPORT int jl_id_char(uint32_t wc)
     if (cat == UTF8PROC_CATEGORY_MN || cat == UTF8PROC_CATEGORY_MC ||
         cat == UTF8PROC_CATEGORY_ND || cat == UTF8PROC_CATEGORY_PC ||
         cat == UTF8PROC_CATEGORY_SK || cat == UTF8PROC_CATEGORY_ME ||
-        cat == UTF8PROC_CATEGORY_NO ||
         // primes (single, double, triple, their reverses, and quadruple)
         (wc >= 0x2032 && wc <= 0x2037) || (wc == 0x2057))
         return 1;
@@ -329,10 +329,11 @@ value_t fl_accum_julia_symbol(fl_context_t *fl_ctx, value_t *args, uint32_t narg
         type_error(fl_ctx, "accum-julia-symbol", "wchar", args[0]);
     uint32_t wc = *(uint32_t*)cp_data((cprim_t*)ptr(args[0]));
     ios_t str;
-    int allascii = 1;
+    int allascii = 1, allNo = 1;
     ios_mem(&str, 0);
     do {
         allascii &= (wc <= 0x7f);
+        allNo = allNo && UTF8PROC_CATEGORY_NO == utf8proc_category((utf8proc_int32_t) wc);
         ios_getutf8(s, &wc);
         if (wc == '!') {
             uint32_t nwc = 0;
@@ -348,6 +349,8 @@ value_t fl_accum_julia_symbol(fl_context_t *fl_ctx, value_t *args, uint32_t narg
             break;
     } while (jl_id_char(wc));
     ios_pututf8(&str, 0);
+    if (allNo) /* identifiers cannot consist only of category-No */
+        lerrorf(fl_ctx, symbol(fl_ctx, "error"), "invalid identifier %s", str.buf);
     return symbol(fl_ctx, allascii ? str.buf : normalize(fl_ctx, str.buf));
 }
 

test/parse.jl

@@ -281,6 +281,21 @@ end
     @test_throws ArgumentError parse(Complex{Int}, "3 + 4.2im")
 end
 
+# identifiers starting with category No:
+let ½x = 1/2, ¹x = 12
+    @test ½x === 1/2
+    @test ¹x === 12
+    Meta.parse("½ = 0.5",raise=false) == Expr(:error, "invalid identifier ½")
+end
+
+# added ⟂ to operator precedence (#24404)
+@test Meta.parse("a ⟂ b ⟂ c") == Expr(:comparison, :a, :⟂, :b, :⟂, :c)
+@test Meta.parse("a ⟂ b ∥ c") == Expr(:comparison, :a, :⟂, :b, :∥, :c)
+
+# only allow certain characters after interpolated vars (#25231)
+@test Meta.parse("\"\$x෴  \"",raise=false) == Expr(:error, "interpolated variable \$x ends with invalid character \"෴\"; use \"\$(x)\" instead.")
+@test Base.incomplete_tag(Meta.parse("\"\$foo", raise=false)) == :string
+
 @testset "parse and tryparse type inference" begin
     @inferred parse(Int, "12")
     @inferred parse(Float64, "12")