optimized textwidth(::Char) for ASCII (#55398)

Author: stevengj

base/strings/unicode.jl

@@ -256,6 +256,15 @@ julia> textwidth('⛵')
 ```
 """
 function textwidth(c::AbstractChar)
+    ismalformed(c) && return 1
+    i = codepoint(c)
+    i < 0x7f && return Int(i >= 0x20) # ASCII fast path
+    Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), i))
+end
+
+function textwidth(c::Char)
+    b = bswap(reinterpret(UInt32, c)) # from isascii(c)
+    b < 0x7f && return Int(b >= 0x20) # ASCII fast path
     ismalformed(c) && return 1
     Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), c))
 end

test/strings/util.jl

@@ -2,6 +2,20 @@
 
 SubStr(s) = SubString("abc$(s)de", firstindex(s) + 3, lastindex(s) + 3)
 
+@testset "textwidth" begin
+    for (c, w) in [('x', 1), ('α', 1), ('🍕', 2), ('\0', 0), ('\u0302', 0), ('\xc0', 1)]
+        @test textwidth(c) == w
+        @test textwidth(c^3) == w*3
+        @test w == @invoke textwidth(c::AbstractChar)
+    end
+    for i in 0x00:0x7f # test all ASCII chars (which have fast path)
+        w = Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), i))
+        c = Char(i)
+        @test textwidth(c) == w
+        @test w == @invoke textwidth(c::AbstractChar)
+    end
+end
+
 @testset "padding (lpad and rpad)" begin
     @test lpad("foo", 2) == "foo"
     @test rpad("foo", 2) == "foo"