278 lines
5.1 KiB
Go
Raw Normal View History

package logfmt
import (
"bytes"
"io"
"strconv"
"sync"
"unicode"
"unicode/utf16"
"unicode/utf8"
)
// Taken from Go's encoding/json and modified for use here.
// 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.
var hex = "0123456789abcdef"
var bufferPool = sync.Pool{
New: func() interface{} {
return &bytes.Buffer{}
},
}
func getBuffer() *bytes.Buffer {
return bufferPool.Get().(*bytes.Buffer)
}
func poolBuffer(buf *bytes.Buffer) {
buf.Reset()
bufferPool.Put(buf)
}
// NOTE: keep in sync with writeQuotedBytes below.
func writeQuotedString(w io.Writer, s string) (int, error) {
buf := getBuffer()
buf.WriteByte('"')
start := 0
for i := 0; i < len(s); {
if b := s[i]; b < utf8.RuneSelf {
if 0x20 <= b && b != '\\' && b != '"' {
i++
continue
}
if start < i {
buf.WriteString(s[start:i])
}
switch b {
case '\\', '"':
buf.WriteByte('\\')
buf.WriteByte(b)
case '\n':
buf.WriteByte('\\')
buf.WriteByte('n')
case '\r':
buf.WriteByte('\\')
buf.WriteByte('r')
case '\t':
buf.WriteByte('\\')
buf.WriteByte('t')
default:
// This encodes bytes < 0x20 except for \n, \r, and \t.
buf.WriteString(`\u00`)
buf.WriteByte(hex[b>>4])
buf.WriteByte(hex[b&0xF])
}
i++
start = i
continue
}
c, size := utf8.DecodeRuneInString(s[i:])
if c == utf8.RuneError {
if start < i {
buf.WriteString(s[start:i])
}
buf.WriteString(`\ufffd`)
i += size
start = i
continue
}
i += size
}
if start < len(s) {
buf.WriteString(s[start:])
}
buf.WriteByte('"')
n, err := w.Write(buf.Bytes())
poolBuffer(buf)
return n, err
}
// NOTE: keep in sync with writeQuoteString above.
func writeQuotedBytes(w io.Writer, s []byte) (int, error) {
buf := getBuffer()
buf.WriteByte('"')
start := 0
for i := 0; i < len(s); {
if b := s[i]; b < utf8.RuneSelf {
if 0x20 <= b && b != '\\' && b != '"' {
i++
continue
}
if start < i {
buf.Write(s[start:i])
}
switch b {
case '\\', '"':
buf.WriteByte('\\')
buf.WriteByte(b)
case '\n':
buf.WriteByte('\\')
buf.WriteByte('n')
case '\r':
buf.WriteByte('\\')
buf.WriteByte('r')
case '\t':
buf.WriteByte('\\')
buf.WriteByte('t')
default:
// This encodes bytes < 0x20 except for \n, \r, and \t.
buf.WriteString(`\u00`)
buf.WriteByte(hex[b>>4])
buf.WriteByte(hex[b&0xF])
}
i++
start = i
continue
}
c, size := utf8.DecodeRune(s[i:])
if c == utf8.RuneError {
if start < i {
buf.Write(s[start:i])
}
buf.WriteString(`\ufffd`)
i += size
start = i
continue
}
i += size
}
if start < len(s) {
buf.Write(s[start:])
}
buf.WriteByte('"')
n, err := w.Write(buf.Bytes())
poolBuffer(buf)
return n, err
}
// getu4 decodes \uXXXX from the beginning of s, returning the hex value,
// or it returns -1.
func getu4(s []byte) rune {
if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
return -1
}
r, err := strconv.ParseUint(string(s[2:6]), 16, 64)
if err != nil {
return -1
}
return rune(r)
}
func unquoteBytes(s []byte) (t []byte, ok bool) {
if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
return
}
s = s[1 : len(s)-1]
// Check for unusual characters. If there are none,
// then no unquoting is needed, so return a slice of the
// original bytes.
r := 0
for r < len(s) {
c := s[r]
if c == '\\' || c == '"' || c < ' ' {
break
}
if c < utf8.RuneSelf {
r++
continue
}
rr, size := utf8.DecodeRune(s[r:])
if rr == utf8.RuneError {
break
}
r += size
}
if r == len(s) {
return s, true
}
b := make([]byte, len(s)+2*utf8.UTFMax)
w := copy(b, s[0:r])
for r < len(s) {
// Out of room? Can only happen if s is full of
// malformed UTF-8 and we're replacing each
// byte with RuneError.
if w >= len(b)-2*utf8.UTFMax {
nb := make([]byte, (len(b)+utf8.UTFMax)*2)
copy(nb, b[0:w])
b = nb
}
switch c := s[r]; {
case c == '\\':
r++
if r >= len(s) {
return
}
switch s[r] {
default:
return
case '"', '\\', '/', '\'':
b[w] = s[r]
r++
w++
case 'b':
b[w] = '\b'
r++
w++
case 'f':
b[w] = '\f'
r++
w++
case 'n':
b[w] = '\n'
r++
w++
case 'r':
b[w] = '\r'
r++
w++
case 't':
b[w] = '\t'
r++
w++
case 'u':
r--
rr := getu4(s[r:])
if rr < 0 {
return
}
r += 6
if utf16.IsSurrogate(rr) {
rr1 := getu4(s[r:])
if dec := utf16.DecodeRune(rr, rr1); dec != unicode.ReplacementChar {
// A valid pair; consume.
r += 6
w += utf8.EncodeRune(b[w:], dec)
break
}
// Invalid surrogate; fall back to replacement rune.
rr = unicode.ReplacementChar
}
w += utf8.EncodeRune(b[w:], rr)
}
// Quote, control characters are invalid.
case c == '"', c < ' ':
return
// ASCII
case c < utf8.RuneSelf:
b[w] = c
r++
w++
// Coerce to well-formed UTF-8.
default:
rr, size := utf8.DecodeRune(s[r:])
r += size
w += utf8.EncodeRune(b[w:], rr)
}
}
return b[0:w], true
}