Commit 65fbf0e8 authored by Agniva De Sarker's avatar Agniva De Sarker Committed by Joe Tsai

strings: optimize ToLower

Handling the ASCII case inline and call unicode.ToLower only
for non-ASCII cases.

Gives good improvements for the ASCII case and minor perf
degrade for non-ASCII case

name                                     old time/op    new time/op    delta
ToLower/#00                                10.8ns ± 1%     9.0ns ± 1%  -16.83%  (p=0.008 n=5+5)
ToLower/abc                                23.3ns ± 4%    12.6ns ± 1%  -46.01%  (p=0.008 n=5+5)
ToLower/AbC123                             91.0ns ± 2%    70.4ns ± 0%  -22.59%  (p=0.008 n=5+5)
ToLower/azAZ09_                             104ns ± 3%      75ns ± 1%  -28.35%  (p=0.008 n=5+5)
ToLower/longStrinGwitHmixofsmaLLandcAps     254ns ± 4%     157ns ± 0%  -38.19%  (p=0.016 n=5+4)
ToLower/LONGⱯSTRINGⱯWITHⱯNONASCIIⱯCHARS     446ns ± 1%     451ns ± 1%     ~     (p=0.056 n=5+5)
ToLower/ⱭⱭⱭⱭⱭ                               345ns ± 1%     348ns ± 0%   +0.93%  (p=0.016 n=5+5)

name                                     old alloc/op   new alloc/op   delta
ToLower/#00                                 0.00B          0.00B          ~     (all equal)
ToLower/abc                                 0.00B          0.00B          ~     (all equal)
ToLower/AbC123                              16.0B ± 0%     16.0B ± 0%     ~     (all equal)
ToLower/azAZ09_                             24.0B ± 0%     16.0B ± 0%  -33.33%  (p=0.008 n=5+5)
ToLower/longStrinGwitHmixofsmaLLandcAps     80.0B ± 0%     64.0B ± 0%  -20.00%  (p=0.008 n=5+5)
ToLower/LONGⱯSTRINGⱯWITHⱯNONASCIIⱯCHARS     96.0B ± 0%     96.0B ± 0%     ~     (all equal)
ToLower/ⱭⱭⱭⱭⱭ                               48.0B ± 0%     48.0B ± 0%     ~     (all equal)

Ran on a machine with Intel(R) Core(TM) i5-5200U CPU @ 2.20GHz

Fixes #17859

Change-Id: Iacc1e6b77e1aedba9447a6e94352606f131ea597
Reviewed-on: https://go-review.googlesource.com/76470Reviewed-by: 's avatarMarvin Stenger <marvin.stenger94@gmail.com>
Reviewed-by: 's avatarJoe Tsai <thebrokentoaster@gmail.com>
parent 506386fd
......@@ -571,7 +571,33 @@ func ToUpper(s string) string {
}
// ToLower returns a copy of the string s with all Unicode letters mapped to their lower case.
func ToLower(s string) string { return Map(unicode.ToLower, s) }
func ToLower(s string) string {
isASCII, hasUpper := true, false
for i := 0; i < len(s); i++ {
c := s[i]
if c >= utf8.RuneSelf {
isASCII = false
break
}
hasUpper = hasUpper || (c >= 'A' && c <= 'Z')
}
if isASCII { // optimize for ASCII-only strings.
if !hasUpper {
return s
}
b := make([]byte, len(s))
for i := 0; i < len(s); i++ {
c := s[i]
if c >= 'A' && c <= 'Z' {
c += 'a' - 'A'
}
b[i] = c
}
return string(b)
}
return Map(unicode.ToLower, s)
}
// ToTitle returns a copy of the string s with all Unicode letters mapped to their title case.
func ToTitle(s string) string { return Map(unicode.ToTitle, s) }
......
......@@ -532,6 +532,8 @@ var lowerTests = []StringTest{
{"abc", "abc"},
{"AbC123", "abc123"},
{"azAZ09_", "azaz09_"},
{"longStrinGwitHmixofsmaLLandcAps", "longstringwithmixofsmallandcaps"},
{"LONG\u2C6FSTRING\u2C6FWITH\u2C6FNONASCII\u2C6FCHARS", "long\u0250string\u0250with\u0250nonascii\u0250chars"},
{"\u2C6D\u2C6D\u2C6D\u2C6D\u2C6D", "\u0251\u0251\u0251\u0251\u0251"}, // shrinks one byte per char
}
......@@ -664,6 +666,19 @@ func BenchmarkToUpper(b *testing.B) {
}
}
func BenchmarkToLower(b *testing.B) {
for _, tc := range lowerTests {
b.Run(tc.in, func(b *testing.B) {
for i := 0; i < b.N; i++ {
actual := ToLower(tc.in)
if actual != tc.out {
b.Errorf("ToLower(%q) = %q; want %q", tc.in, actual, tc.out)
}
}
})
}
}
func BenchmarkMapNoChanges(b *testing.B) {
identity := func(r rune) rune {
return r
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment