mirror of
https://github.com/golang/go.git
synced 2025-05-05 15:43:04 +00:00
f9ce1dddc2
Add benchmarks for ParseMediaType.
Eschew UTF-8 decoding and strings.IndexFunc where possible, and rely
on 128-bit bitmaps instead. Eliminate some bounds checks.
Some benchmark results (no changes to allocations):
goos: darwin
goarch: amd64
pkg: mime
cpu: Intel(R) Core(TM) i7-6700HQ CPU @ 2.60GHz
│ old │ new │
│ sec/op │ sec/op vs base │
ParseMediaType-8 71.75µ ± 0% 55.53µ ± 0% -22.60% (p=0.000 n=20)
ParseMediaTypeBogus-8 5.330µ ± 0% 3.603µ ± 0% -32.41% (p=0.000 n=20)
geomean 19.56µ 14.14µ -27.67%
Change-Id: I324c9990fe43581484916ecff61ca6c708467a89
GitHub-Last-Rev: e2293d64b3852722bef920169eaa44e7ded3111c
GitHub-Pull-Request: golang/go#73436
Reviewed-on: https://go-review.googlesource.com/c/go/+/666655
Reviewed-by: Jorropo <jorropo.pgm@gmail.com>
Reviewed-by: Junyang Shao <shaojunyang@google.com>
Reviewed-by: Sean Liao <sean@liao.dev>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Auto-Submit: Sean Liao <sean@liao.dev>
84 lines
1.9 KiB
Go
84 lines
1.9 KiB
Go
// Copyright 2010 The Go Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
package mime
|
|
|
|
// isTSpecial reports whether c is in 'tspecials' as defined by RFC
|
|
// 1521 and RFC 2045.
|
|
func isTSpecial(c byte) bool {
|
|
// tspecials := "(" / ")" / "<" / ">" / "@" /
|
|
// "," / ";" / ":" / "\" / <">
|
|
// "/" / "[" / "]" / "?" / "="
|
|
//
|
|
// mask is a 128-bit bitmap with 1s for allowed bytes,
|
|
// so that the byte c can be tested with a shift and an and.
|
|
// If c >= 128, then 1<<c and 1<<(c-64) will both be zero,
|
|
// and this function will return false.
|
|
const mask = 0 |
|
|
1<<'(' |
|
|
1<<')' |
|
|
1<<'<' |
|
|
1<<'>' |
|
|
1<<'@' |
|
|
1<<',' |
|
|
1<<';' |
|
|
1<<':' |
|
|
1<<'\\' |
|
|
1<<'"' |
|
|
1<<'/' |
|
|
1<<'[' |
|
|
1<<']' |
|
|
1<<'?' |
|
|
1<<'='
|
|
return ((uint64(1)<<c)&(mask&(1<<64-1)) |
|
|
(uint64(1)<<(c-64))&(mask>>64)) != 0
|
|
}
|
|
|
|
// isTokenChar reports whether c is in 'token' as defined by RFC
|
|
// 1521 and RFC 2045.
|
|
func isTokenChar(c byte) bool {
|
|
// token := 1*<any (US-ASCII) CHAR except SPACE, CTLs,
|
|
// or tspecials>
|
|
//
|
|
// mask is a 128-bit bitmap with 1s for allowed bytes,
|
|
// so that the byte c can be tested with a shift and an and.
|
|
// If c >= 128, then 1<<c and 1<<(c-64) will both be zero,
|
|
// and this function will return false.
|
|
const mask = 0 |
|
|
(1<<(10)-1)<<'0' |
|
|
(1<<(26)-1)<<'a' |
|
|
(1<<(26)-1)<<'A' |
|
|
1<<'!' |
|
|
1<<'#' |
|
|
1<<'$' |
|
|
1<<'%' |
|
|
1<<'&' |
|
|
1<<'\'' |
|
|
1<<'*' |
|
|
1<<'+' |
|
|
1<<'-' |
|
|
1<<'.' |
|
|
1<<'^' |
|
|
1<<'_' |
|
|
1<<'`' |
|
|
1<<'|' |
|
|
1<<'~'
|
|
return ((uint64(1)<<c)&(mask&(1<<64-1)) |
|
|
(uint64(1)<<(c-64))&(mask>>64)) != 0
|
|
}
|
|
|
|
// isToken reports whether s is a 'token' as defined by RFC 1521
|
|
// and RFC 2045.
|
|
func isToken(s string) bool {
|
|
if s == "" {
|
|
return false
|
|
}
|
|
for _, c := range []byte(s) {
|
|
if !isTokenChar(c) {
|
|
return false
|
|
}
|
|
}
|
|
return true
|
|
}
|