eliminate copy for Unicode.normalize of substring (JuliaLang#38381)

eliminate copy for Unicode.normalize of substring
inkydragon · Nov 11, 2020 · af3cd59 · af3cd59
1 parent 9c498bf
commit af3cd59
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/base/strings/unicode.jl b/base/strings/unicode.jl
@@ -145,7 +145,7 @@ const UTF8PROC_STRIPMARK = (1<<13)
 
 utf8proc_error(result) = error(unsafe_string(ccall(:utf8proc_errmsg, Cstring, (Cssize_t,), result)))
 
-function utf8proc_map(str::String, options::Integer)
+function utf8proc_map(str::Union{String,SubString{String}}, options::Integer)
  nwords = ccall(:utf8proc_decompose, Int, (Ptr{UInt8}, Int, Ptr{UInt8}, Int, Cint),
  str, sizeof(str), C_NULL, 0, options)
  nwords < 0 && utf8proc_error(nwords)

diff --git a/stdlib/Unicode/test/runtests.jl b/stdlib/Unicode/test/runtests.jl
@@ -6,7 +6,7 @@ using Unicode: normalize, isassigned
 
 @testset "string normalization" begin
  # normalize (Unicode normalization etc.):
- @test normalize("\u006e\u0303", :NFC) == "\u00f1"
+ @test normalize("\u006e\u0303", :NFC) == "\u00f1" == normalize(SubString("ab\u006e\u0303cd",3,4), :NFC)
  @test "\u006e\u0303" == normalize("\u00f1", :NFD)
  @test normalize("\ufb00", :NFC) != "ff"
  @test normalize("\ufb00", :NFKC) == "ff"