Go语言模型:string的底层数据结构与高效操作详解

package main
import (
	"fmt"
	"unsafe"
)
// from: string.go 在GoLand IDE中双击shift快速找到
type stringStruct struct {
	array unsafe.Pointer // 指向一个 [len]byte 的数组
	length int    // 长度
}
func main() {
	test := "hello"
	p := (*str)(unsafe.Pointer(&test))
	fmt.Println(&p, p) // 0xc420070018 &{0xa3f71 5}
	c := make([]byte, p.length)
	for i := 0; i < p.length; i++ {
		tmp := uintptr(unsafe.Pointer(p.array))   // 指针类型转换通过unsafe包
		c[i] = *(*byte)(unsafe.Pointer(tmp + uintptr(i))) // 指针运算只能通过uintptr
	}
	fmt.Println(c)   // [104 101 108 108 111]
	fmt.Println(string(c)) // [byte] --> string, "hello"
	test2 := test + " world" // 字符串是不可变类型，会生成一个新的string实例
	p2 := (*str)(unsafe.Pointer(&test2))
	fmt.Println(&p2, p2) // 0xc420028030 &{0xc42000a2e5 11}
	fmt.Println(test2) // hello, world
}

25		test2 := test + " world"
 0x00000000004824d7 <+1127>:	lea 0x105a2(%rip),%rax  # 0x492a80
 0x00000000004824de <+1134>:	mov %rax,(%rsp)
 0x00000000004824e2 <+1138>:	callq 0x40dda0 <runtime.newobject> # 调用newobject函数
 0x00000000004824e7 <+1143>:	mov 0x8(%rsp),%rax
 0x00000000004824ec <+1148>:	mov %rax,0xa0(%rsp)
 0x00000000004824f4 <+1156>:	mov 0xa8(%rsp),%rax
 0x00000000004824fc <+1164>:	mov 0x8(%rax),%rcx
 0x0000000000482500 <+1168>:	mov (%rax),%rax
 0x0000000000482503 <+1171>:	mov %rax,0x8(%rsp)
 0x0000000000482508 <+1176>:	mov %rcx,0x10(%rsp)
 0x000000000048250d <+1181>:	movq $0x0,(%rsp)
 0x0000000000482515 <+1189>:	lea 0x30060(%rip),%rax  # 0x4b257c
 0x000000000048251c <+1196>:	mov %rax,0x18(%rsp)
 0x0000000000482521 <+1201>:	movq $0x6,0x20(%rsp)
 0x000000000048252a <+1210>:	callq 0x43cc00 <runtime.concatstring2> # 调用concatstring2函数

func concatstring2(buf *tmpBuf, a [2]string) string {
 return concatstrings(buf, a[:])
}
// concatstrings implements a Go string concatenation x+y+z+...
// The operands are passed in the slice a.
// If buf != nil, the compiler has determined that the result does not
// escape the calling function, so the string data can be stored in buf
// if small enough.
func concatstrings(buf *tmpBuf, a []string) string {
 idx := 0
 l := 0
 count := 0
 for i, x := range a {
  n := len(x)
  if n == 0 {
   continue
  }
  if l+n < l {
   throw("string concatenation too long")
  }
  l += n
  count++
  idx = i
 }
 if count == 0 {
  return ""
 }
 // If there is just one string and either it is not on the stack
 // or our result does not escape the calling frame (buf != nil),
 // then we can return that string directly.
 if count == 1 && (buf != nil || !stringDataOnStack(a[idx])) {
  return a[idx]
 }
 s, b := rawstringtmp(buf, l)
 for _, x := range a {
  copy(b, x) // 最关键的拷贝操作
  b = b[len(x):]
 }
 return s
}

func main() {
 var buf bytes.Buffer
 for i := 0; i < 10; i++ {
  buf.WriteString("hi ")
 }
 fmt.Println(buf.String())
}

// @file: buffer.go
func (b *Buffer) WriteString(s string) (n int, err error) {
 b.lastRead = opInvalid
 m, ok := b.tryGrowByReslice(len(s))
 if !ok {
  m = b.grow(len(s)) // 高效的增长策略 -> let capacity get twice as large
 }
 return copy(b.buf[m:], s), nil
}
// @file: buffer.go
// let capacity get twice as large !!!
func (b *Buffer) grow(n int) int {
 m := b.Len()
 // If buffer is empty, reset to recover space.
 if m == 0 && b.off != 0 {
  b.Reset()
 }
 // Try to grow by means of a reslice.
 if i, ok := b.tryGrowByReslice(n); ok {
  return i
 }
 // Check if we can make use of bootstrap array.
 if b.buf == nil && n <= len(b.bootstrap) {
  b.buf = b.bootstrap[:n]
  return 0
 }
 c := cap(b.buf)
 if n <= c/2-m {
  // We can slide things down instead of allocating a new
  // slice. We only need m+n <= c to slide, but
  // we instead let capacity get twice as large so we
  // don't spend all our time copying.
  copy(b.buf, b.buf[b.off:])
 } else if c > maxInt-c-n {
  panic(ErrTooLarge)
 } else {
  // Not enough space anywhere, we need to allocate.
  buf := makeSlice(2*c + n)
  copy(buf, b.buf[b.off:])
  b.buf = buf
 }
 // Restore b.off and len(b.buf).
 b.off = 0
 b.buf = b.buf[:m+n]
 return m
}

func main() {
 var strs []string
 for i := 0; i < 10; i++ {
 strs = append(strs, "hi")
 }
 fmt.Println(strings.Join(strs, " "))
}

// Join concatenates the elements of a to create a single string. The separator string
// sep is placed between elements in the resulting string.
func Join(a []string, sep string) string {
 switch len(a) {
 case 0:
  return ""
 case 1:
  return a[0]
 case 2:
  // Special case for common small values.
  // Remove if golang.org/issue/6714 is fixed
  return a[0] + sep + a[1]
 case 3:
  // Special case for common small values.
  // Remove if golang.org/issue/6714 is fixed
  return a[0] + sep + a[1] + sep + a[2]
 }
 
 // 计算好最终的string的大小
 n := len(sep) * (len(a) - 1) //
 for i := 0; i < len(a); i++ {
  n += len(a[i])
 }
 b := make([]byte, n)
 bp := copy(b, a[0])
 for _, s := range a[1:] {
  bp += copy(b[bp:], sep)
  bp += copy(b[bp:], s)
 }
 return string(b)
}

func main() {
 var s strings.Builder
 for i := 0; i < 10; i++ {
  s.WriteString("hi ")
 }
 fmt.Println(s.String())
}

@file: builder.go
// WriteString appends the contents of s to b's buffer.
// It returns the length of s and a nil error.
func (b *Builder) WriteString(s string) (int, error) {
 b.copyCheck()
 b.buf = append(b.buf, s...)
 return len(s), nil
}

func boo(a int, b int)(int, string){
 return a + b, "abcd"
}

81079 000000000044dfa0 <main.boo>:
81080 44dfa0:>------48 c7 44 24 18 00 00 >--movq $0x0,0x18(%rsp)
81081 44dfa7:>------00 00- 
81082 44dfa9:>------0f 57 c0    >--xorps %xmm0,%xmm0
81083 44dfac:>------0f 11 44 24 20  >--movups %xmm0,0x20(%rsp)
81084 44dfb1:>------48 8b 44 24 08  >--mov 0x8(%rsp),%rax
81085 44dfb6:>------48 03 44 24 10  >--add 0x10(%rsp),%rax
81086 44dfbb:>------48 89 44 24 18  >--mov %rax,0x18(%rsp)
81087 44dfc0:>------48 8d 05 d4 eb 01 00 >--lea 0x1ebd4(%rip),%rax  # 46cb9b <go.string.*+0xbb>
81088 44dfc7:>------48 89 44 24 20  >--mov %rax,0x20(%rsp)
81089 44dfcc:>------48 c7 44 24 28 04 00 >--movq $0x4,0x28(%rsp)
81090 44dfd3:>------00 00- 
81091 44dfd5:>------c3     >--retq---

81087 44dfc0:>------48 8d 05 d4 eb 01 00 >--lea 0x1ebd4(%rip),%rax  # 46cb9b <go.string.*+0xbb>
81088 44dfc7:>------48 89 44 24 20  >--mov %rax,0x20(%rsp)
81089 44dfcc:>------48 c7 44 24 28 04 00 >--movq $0x4,0x28(%rsp)
81090 44dfd3:>------00 00- 
81091 44dfd5:>------c3     >--retq---
lea 0x1ebd4(%rip),%rax得到char*, mov %rax,0x20(%rsp)复制给返回值, movq $0x4,0x28(%rsp)把长度也填进去,