Merge pull request #23787 from JuliaLang/sk/repeatchar

more efficient repeat(Char, n)
JuliaLang · Sep 20, 2017 · 9202df2 · 9202df2
2 parents 2562263 + 14253b9
commit 9202df2
Show file tree

Hide file tree

Showing 2 changed files with 52 additions and 4 deletions.
diff --git a/base/strings/string.jl b/base/strings/string.jl
@@ -455,12 +455,43 @@ julia> repeat('A', 3)
 ```
 """
 function repeat(c::Char, r::Integer)
-    if isascii(c)
-        r < 0 && throw(ArgumentError("can't repeat a character $r times"))
+    r < 0 && throw(ArgumentError("can't repeat a character $r times"))
+    r == 0 && return ""
+    ch = UInt(c)
+    if ch < 0x80
         out = _string_n(r)
         ccall(:memset, Ptr{Void}, (Ptr{UInt8}, Cint, Csize_t), out, c, r)
-        return out
+    elseif ch < 0x800
+        out = _string_n(2r)
+        p16 = reinterpret(Ptr{UInt16}, pointer(out))
+        u16 = ((ch >> 0x6) | (ch & 0x3f) << 0x8) % UInt16 | 0x80c0
+        @inbounds for i = 1:r
+            unsafe_store!(p16, u16, i)
+        end
+    elseif ch < 0x10000
+        (0xd800 ≥ ch ≤ 0xdfff) || throw(ArgumentError("invalid character 0x$(hex(ch))"))
+        out = _string_n(3r)
+        p = pointer(out)
+        b1 = (ch >> 0xc) % UInt8 | 0xe0
+        b2 = ((ch >> 0x6) & 0x3f) % UInt8 | 0x80
+        b3 = (ch & 0x3f) % UInt8 | 0x80
+        @inbounds for i = 1:r
+            unsafe_store!(p, b1)
+            unsafe_store!(p, b2, 2)
+            unsafe_store!(p, b3, 3)
+            p += 3
+        end
+    elseif ch < 0x110000
+        out = _string_n(4r)
+        p32 = reinterpret(Ptr{UInt32}, pointer(out))
+        u32 = ((ch >> 0x12) | ((ch >> 0x4) & 0x03f00) |
+            ((ch << 0xa) & 0x3f0000) | ((ch & 0x3f) << 0x18)) % UInt32 | 0x808080f0
+        @inbounds for i = 1:r
+            unsafe_store!(p32, u32)
+            p32 += 4
+        end
     else
-        return repeat(string(c), r)
+        throw(ArgumentError("invalid character 0x$(hex(ch))"))
     end
+    return out
 end
diff --git a/test/strings/basic.jl b/test/strings/basic.jl
@@ -497,6 +497,23 @@ Base.endof(x::CharStr) = endof(x.chars)
 @test repeat("x",1) == repeat('x',1) == "x"^1 == 'x'^1 == GenericString("x")^1 == "x"
 @test repeat("x",0) == repeat('x',0) == "x"^0 == 'x'^0 == GenericString("x")^0 == ""
 
+for S in ["xxx", "ååå", "∀∀∀", "🍕🍕🍕"]
+    c = S[1]
+    s = string(c)
+    @test_throws ArgumentError repeat(c, -1)
+    @test_throws ArgumentError repeat(s, -1)
+    @test_throws ArgumentError repeat(S, -1)
+    @test repeat(c, 0) == ""
+    @test repeat(s, 0) == ""
+    @test repeat(S, 0) == ""
+    @test repeat(c, 1) == s
+    @test repeat(s, 1) == s
+    @test repeat(S, 1) == S
+    @test repeat(c, 3) == S
+    @test repeat(s, 3) == S
+    @test repeat(S, 3) == S*S*S
+end
+
 # issue #12495: check that logical indexing attempt raises ArgumentError
 @test_throws ArgumentError "abc"[[true, false, true]]
 @test_throws ArgumentError "abc"[BitArray([true, false, true])]