目录
一、字符串的本质
1.字符串的定义
golangcharacterUTF-8nil// go/src/builtin/builtin.go // string is the set of all strings of 8-bit bytes, conventionally but not // necessarily representing UTF-8-encoded text. A string may be empty, but // not nil. Values of string type are immutable. type string string
字符串在本质上是一串字符数组，每个字符在存储时都对应了一个或多个整数，整数是多少取决于字符集的编码方式。
s := "golang"
for i := 0; i < len(s); i++ {
fmt.Printf("s[%v]: %v\n",i, s[i])
}
// s[0]: 103
// s[1]: 111
// s[2]: 108
// s[3]: 97
// s[4]: 110
// s[5]: 103
stringreflect// go/src/reflect/value.go
// StringHeader is the runtime representation of a string.
// ...
type StringHeader struct {
Data uintptr
Len int
}
LenData2.字符串的长度
golangutf8utf8len(s)pythonprint(len("go语言"))
# 4
s := "go语言"
fmt.Printf("len(s): %v\n", len(s))
// len(s): 8
3.字符与符文
goruneruneint32[]runeutf8.RuneCountInString()s := "go语言" fmt.Println(len([]rune(s))) // 4 count := utf8.RuneCountInString(s) fmt.Println(count) // 4
rangerunes := "go语言"
for _, r := range s {
fmt.Printf("rune: %v string: %#U\n", r, r)
}
// rune: 103 unicode: U+0067 'g'
// rune: 111 unicode: U+006F 'o'
// rune: 35821 unicode: U+8BED '语'
// rune: 35328 unicode: U+8A00 '言'
二、字符串的原理
1.字符串的解析
golang// go/src/cmd/compile/internal/syntax/scanner.go
func (s *scanner) next() {
...
switch s.ch {
...
case '"':
s.stdString()
case '`':
s.rawString()
...
string(s.segment())setLlit()kindStringLitfunc (s *scanner) stdString() {
ok := true
s.nextch()
for {
if s.ch == '"' {
s.nextch()
break
}
...
s.nextch()
}
s.setLit(StringLit, ok)
}
func (s *scanner) rawString() {
ok := true
s.nextch()
for {
if s.ch == '`' {
s.nextch()
break
}
...
s.nextch()
}
s.setLit(StringLit, ok)
}
// setLit sets the scanner state for a recognized _Literal token.
func (s *scanner) setLit(kind LitKind, ok bool) {
s.nlsemi = true
s.tok = _Literal
s.lit = string(s.segment())
s.bad = !ok
s.kind = kind
}
2.字符串的拼接
字符串可以通过+进行拼接:
s := "go" + "lang"
"go"+"lang"AddStringExpropOADDSTRNodeList// go/src/cmd/compile/internal/ir/expr.go
// An AddStringExpr is a string concatenation Expr[0] + Exprs[1] + ... + Expr[len(Expr)-1].
type AddStringExpr struct {
miniExpr
List Nodes
Prealloc *Name
}
func NewAddStringExpr(pos src.XPos, list []Node) *AddStringExpr {
n := &AddStringExpr{}
n.pos = pos
n.op = OADDSTR
n.List = list
return n
}
OpOADDSTRwalkAddString// go/src/cmd/compile/internal/walk/expr.go
func walkExpr(n ir.Node, init *ir.Nodes) ir.Node {
...
n = walkExpr1(n, init)
...
return n
}
func walkExpr1(n ir.Node, init *ir.Nodes) ir.Node {
switch n.Op() {
...
case ir.OADDSTR:
return walkAddString(n.(*ir.AddStringExpr), init)
...
}
...
}
walkAddStringcstackBufAddr()// go/src/cmd/compile/internal/walk/walk.go
const tmpstringbufsize = 32
// go/src/cmd/compile/internal/walk/expr.go
func walkAddString(n *ir.AddStringExpr, init *ir.Nodes) ir.Node {
c := len(n.List)
if c < 2 {
base.Fatalf("walkAddString count %d too small", c)
}
buf := typecheck.NodNil()
if n.Esc() == ir.EscNone {
sz := int64(0)
for _, n1 := range n.List {
if n1.Op() == ir.OLITERAL {
sz += int64(len(ir.StringVal(n1)))
}
}
// Don't allocate the buffer if the result won't fit.
if sz < tmpstringbufsize {
// Create temporary buffer for result string on stack.
buf = stackBufAddr(tmpstringbufsize, types.Types[types.TUINT8])
}
}
// build list of string arguments
args := []ir.Node{buf}
for _, n2 := range n.List {
args = append(args, typecheck.Conv(n2, types.Types[types.TSTRING]))
}
var fn string
if c <= 5 {
// small numbers of strings use direct runtime helpers.
// note: order.expr knows this cutoff too.
fn = fmt.Sprintf("concatstring%d", c)
} else {
// large numbers of strings are passed to the runtime as a slice.
fn = "concatstrings"
t := types.NewSlice(types.Types[types.TSTRING])
// args[1:] to skip buf arg
slice := ir.NewCompLitExpr(base.Pos, ir.OCOMPLIT, t, args[1:])
slice.Prealloc = n.Prealloc
args = []ir.Node{buf, slice}
slice.SetEsc(ir.EscNone)
}
cat := typecheck.LookupRuntime(fn)
r := ir.NewCallExpr(base.Pos, ir.OCALL, cat, nil)
r.Args = args
r1 := typecheck.Expr(r)
r1 = walkExpr(r1, init)
r1.SetType(n.Type())
return r1
}
concatstring1-concatstring5concatstringsslicetypecheck.LookupRuntime(fn)OpOCALLconcatstring1-concatstring5concatstrings// go/src/runtime/string.go
const tmpStringBufSize = 32
type tmpBuf [tmpStringBufSize]byte
func concatstring2(buf *tmpBuf, a0, a1 string) string {
return concatstrings(buf, []string{a0, a1})
}
func concatstring3(buf *tmpBuf, a0, a1, a2 string) string {
return concatstrings(buf, []string{a0, a1, a2})
}
func concatstring4(buf *tmpBuf, a0, a1, a2, a3 string) string {
return concatstrings(buf, []string{a0, a1, a2, a3})
}
func concatstring5(buf *tmpBuf, a0, a1, a2, a3, a4 string) string {
return concatstrings(buf, []string{a0, a1, a2, a3, a4})
}
concatstring1-concatstring5slicebytetostringtmprawstringcopy(b,x)b// concatstrings implements a Go string concatenation x+y+z+...
func concatstrings(buf *tmpBuf, a []string) string {
...
l := 0
for i, x := range a {
...
n := len(x)
...
l += n
...
}
s, b := rawstringtmp(buf, l)
for _, x := range a {
copy(b, x)
b = b[len(x):]
}
return s
}
func rawstringtmp(buf *tmpBuf, l int) (s string, b []byte) {
if buf != nil && l <= len(buf) {
b = buf[:l]
s = slicebytetostringtmp(&b[0], len(b))
} else {
s, b = rawstring(l)
}
return
}
func slicebytetostringtmp(ptr *byte, n int) (str string) {
...
stringStructOf(&str).str = unsafe.Pointer(ptr)
stringStructOf(&str).len = n
return
}
// rawstring allocates storage for a new string. The returned
// string and byte slice both refer to the same storage.
func rawstring(size int) (s string, b []byte) {
p := mallocgc(uintptr(size), nil, false)
stringStructOf(&s).str = p
stringStructOf(&s).len = size
*(*slice)(unsafe.Pointer(&b)) = slice{p, size, size}
return
}
type stringStruct struct {
str unsafe.Pointer
len int
}
func stringStructOf(sp *string) *stringStruct {
return (*stringStruct)(unsafe.Pointer(sp))
}
3.字符串的转换
尽管字符串的底层是字节数组， 但字节数组与字符串的相互转换并不是简单的指针引用，而是涉及了内存复制。当字符串大于32字节时，还需要申请堆内存。
s := "go语言" b := []byte(s) // stringtoslicebyte ss := string(b) // slicebytetostring
stringtoslicebytebufrawbyteslice// go/src/runtime/string.go
func stringtoslicebyte(buf *tmpBuf, s string) []byte {
var b []byte
if buf != nil && len(s) <= len(buf) {
*buf = tmpBuf{}
b = buf[:len(s)]
} else {
b = rawbyteslice(len(s))
}
copy(b, s)
return b
}
func rawbyteslice(size int) (b []byte) {
cap := roundupsize(uintptr(size))
p := mallocgc(cap, nil, false)
if cap != uintptr(size) {
memclrNoHeapPointers(add(p, uintptr(size)), cap-uintptr(size))
}
*(*slice)(unsafe.Pointer(&b)) = slice{p, size, int(cap)}
return
}
func slicebytetostring(buf *tmpBuf, ptr *byte, n int) (str string) {
...
var p unsafe.Pointer
if buf != nil && n <= len(buf) {
p = unsafe.Pointer(buf)
} else {
p = mallocgc(uintptr(n), nil, false)
}
stringStructOf(&str).str = p
stringStructOf(&str).len = n
memmove(p, unsafe.Pointer(ptr), uintptr(n))
return
}
字节切片转换为字符串时，原理同上。因此字符串和切片的转换涉及内存拷贝，在一些密集转换的场景中，需要评估转换带来的性能损耗。
总结
utf8