[Golang1.20 source code reading] runtime/string.go

// Copyright 2014 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 runtime

import (
	"internal/abi"
	"internal/bytealg"
	"internal/goarch"
	"unsafe"
)

// The constant is known to the compiler.
// There is no fundamental theory behind this number.
// 编译器知道该常量。这个数字背后没有根本的理论。
const tmpStringBufSize = 32

type tmpBuf [tmpStringBufSize]byte

// concatstrings implements a Go string concatenation x+y+z+...
// concatstrings实现Go字符串串联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.
// 操作数在切片a中传递。如果buf！=nil，编译器已确定结果不会转义调用函数，因此如果字符串数据足够小，则可以将其存储在buf中。
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.
	// 如果只有一个字符串，或者它不在堆栈上，或者我们的结果没有转义调用帧（buf！=nil），那么我们可以直接返回该字符串。
	if count == 1 && (buf != nil || !stringDataOnStack(a[idx])) {
		return a[idx]
	}
	s, b := rawstringtmp(buf, l)
	for _, x := range a {
		copy(b, x)
		b = b[len(x):]
	}
	return s
}

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})
}

// slicebytetostring converts a byte slice to a string.
// It is inserted by the compiler into generated code.
// ptr is a pointer to the first element of the slice;
// n is the length of the slice.
// Buf is a fixed-size buffer for the result,
// it is not nil if the result does not escape.
// slicebytetostring将字节切片转换为字符串。它由编译器插入到生成的代码中。ptr是指向切片的第一个元素的指针；n是切片的长度。
// Buf是一个固定大小的结果缓冲区，如果结果没有转义，它就不是零。
func slicebytetostring(buf *tmpBuf, ptr *byte, n int) string {
	if n == 0 {
		// Turns out to be a relatively common case.
		// Consider that you want to parse out data between parens in "foo()bar",
		// you find the indices and convert the subslice to string.
		return ""
	}
	if raceenabled {
		racereadrangepc(unsafe.Pointer(ptr),
			uintptr(n),
			getcallerpc(),
			abi.FuncPCABIInternal(slicebytetostring))
	}
	if msanenabled {
		msanread(unsafe.Pointer(ptr), uintptr(n))
	}
	if asanenabled {
		asanread(unsafe.Pointer(ptr), uintptr(n))
	}
	if n == 1 {
		p := unsafe.Pointer(&staticuint64s[*ptr])
		if goarch.BigEndian {
			p = add(p, 7)
		}
		return unsafe.String((*byte)(p), 1)
	}

	var p unsafe.Pointer
	if buf != nil && n <= len(buf) {
		p = unsafe.Pointer(buf)
	} else {
		p = mallocgc(uintptr(n), nil, false)
	}
	memmove(p, unsafe.Pointer(ptr), uintptr(n))
	return unsafe.String((*byte)(p), n)
}

// stringDataOnStack reports whether the string's data is
// stored on the current goroutine's stack.
// stringDataOnStack报告字符串的数据是否存储在当前goroutine的堆栈上。
func stringDataOnStack(s string) bool {
	ptr := uintptr(unsafe.Pointer(unsafe.StringData(s)))
	stk := getg().stack
	return stk.lo <= ptr && ptr < stk.hi
}

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
}

// slicebytetostringtmp returns a "string" referring to the actual []byte bytes.
// slicebytetostringtmp返回一个“字符串”，指的是实际的[]字节。
// Callers need to ensure that the returned string will not be used after
// the calling goroutine modifies the original slice or synchronizes with
// another goroutine.
// 调用方需要确保在调用goroutine修改原始切片或与另一个goroutine同步后不会使用返回的字符串。
// The function is only called when instrumenting
// and otherwise intrinsified by the compiler.
// 该函数仅在检测时调用，否则将由编译器内部化。
// Some internal compiler optimizations use this function.
//   - Used for m[T1{... Tn{..., string(k), ...} ...}] and m[string(k)]
//     where k is []byte, T1 to Tn is a nesting of struct and array literals.
//   - Used for "<"+string(b)+">" concatenation where b is []byte.
//   - Used for string(b)=="foo" comparison where b is []byte.
func slicebytetostringtmp(ptr *byte, n int) string {
	if raceenabled && n > 0 {
		racereadrangepc(unsafe.Pointer(ptr),
			uintptr(n),
			getcallerpc(),
			abi.FuncPCABIInternal(slicebytetostringtmp))
	}
	if msanenabled && n > 0 {
		msanread(unsafe.Pointer(ptr), uintptr(n))
	}
	if asanenabled && n > 0 {
		asanread(unsafe.Pointer(ptr), uintptr(n))
	}
	return unsafe.String(ptr, n)
}

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 stringtoslicerune(buf *[tmpStringBufSize]rune, s string) []rune {
	// two passes.
	// unlike slicerunetostring, no race because strings are immutable.
	// 与sliceruneostring不同，没有种族，因为字符串是不可变的。
	n := 0
	for range s {
		n++
	}

	var a []rune
	if buf != nil && n <= len(buf) {
		*buf = [tmpStringBufSize]rune{}
		a = buf[:n]
	} else {
		a = rawruneslice(n)
	}

	n = 0
	for _, r := range s {
		a[n] = r
		n++
	}
	return a
}

func slicerunetostring(buf *tmpBuf, a []rune) string {
	if raceenabled && len(a) > 0 {
		racereadrangepc(unsafe.Pointer(&a[0]),
			uintptr(len(a))*unsafe.Sizeof(a[0]),
			getcallerpc(),
			abi.FuncPCABIInternal(slicerunetostring))
	}
	if msanenabled && len(a) > 0 {
		msanread(unsafe.Pointer(&a[0]), uintptr(len(a))*unsafe.Sizeof(a[0]))
	}
	if asanenabled && len(a) > 0 {
		asanread(unsafe.Pointer(&a[0]), uintptr(len(a))*unsafe.Sizeof(a[0]))
	}
	var dum [4]byte
	size1 := 0
	for _, r := range a {
		size1 += encoderune(dum[:], r)
	}
	s, b := rawstringtmp(buf, size1+3)
	size2 := 0
	for _, r := range a {
		// check for race
		if size2 >= size1 {
			break
		}
		size2 += encoderune(b[size2:], r)
	}
	return s[:size2]
}

type stringStruct struct {
	str unsafe.Pointer // 字符串的首地址
	len int // 字符串的长度
}

// Variant with *byte pointer type for DWARF debugging. 用于DWARF调试的具有*字节指针类型的变量。
type stringStructDWARF struct {
	str *byte
	len int
}

func stringStructOf(sp *string) *stringStruct {
	return (*stringStruct)(unsafe.Pointer(sp))
}

func intstring(buf *[4]byte, v int64) (s string) {
	var b []byte
	if buf != nil {
		b = buf[:]
		s = slicebytetostringtmp(&b[0], len(b))
	} else {
		s, b = rawstring(4)
	}
	if int64(rune(v)) != v {
		v = runeError
	}
	n := encoderune(b, rune(v))
	return s[:n]
}

// rawstring allocates storage for a new string. The returned
// string and byte slice both refer to the same storage.
// The storage is not zeroed. Callers should use
// b to set the string contents and then drop b.
// rawstring为新字符串分配存储空间。返回的字符串和字节片都引用相同的存储。存储未归零。调用方应使用b设置字符串内容，然后删除b
func rawstring(size int) (s string, b []byte) {
	p := mallocgc(uintptr(size), nil, false)
	return unsafe.String((*byte)(p), size), unsafe.Slice((*byte)(p), size)
}

// rawbyteslice allocates a new byte slice. The byte slice is not zeroed.
// rawbyteslice分配一个新的字节片。字节片未归零。
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
}

// rawruneslice allocates a new rune slice. The rune slice is not zeroed.
// rawruneslice分配一个新的rune切片。rune切片非零值。
func rawruneslice(size int) (b []rune) {
	if uintptr(size) > maxAlloc/4 {
		throw("out of memory")
	}
	mem := roundupsize(uintptr(size) * 4)
	p := mallocgc(mem, nil, false)
	if mem != uintptr(size)*4 {
		memclrNoHeapPointers(add(p, uintptr(size)*4), mem-uintptr(size)*4)
	}

	*(*slice)(unsafe.Pointer(&b)) = slice{p, size, int(mem / 4)}
	return
}

// used by cmd/cgo
func gobytes(p *byte, n int) (b []byte) {
	if n == 0 {
		return make([]byte, 0)
	}

	if n < 0 || uintptr(n) > maxAlloc {
		panic(errorString("gobytes: length out of range"))
	}

	bp := mallocgc(uintptr(n), nil, false)
	memmove(bp, unsafe.Pointer(p), uintptr(n))

	*(*slice)(unsafe.Pointer(&b)) = slice{bp, n, n}
	return
}

// This is exported via linkname to assembly in syscall (for Plan9).
// 这是通过链接名导出到系统调用中的程序集（对于Plan9）。
//go:linkname gostring
func gostring(p *byte) string {
	l := findnull(p)
	if l == 0 {
		return ""
	}
	s, b := rawstring(l)
	memmove(unsafe.Pointer(&b[0]), unsafe.Pointer(p), uintptr(l))
	return s
}

// internal_syscall_gostring is a version of gostring for internal/syscall/unix.
// internal_syscall_gostring是用于internal/syscall/unix的gostring版本。
//go:linkname internal_syscall_gostring internal/syscall/unix.gostring
func internal_syscall_gostring(p *byte) string {
	return gostring(p)
}

func gostringn(p *byte, l int) string {
	if l == 0 {
		return ""
	}
	s, b := rawstring(l)
	memmove(unsafe.Pointer(&b[0]), unsafe.Pointer(p), uintptr(l))
	return s
}

func hasPrefix(s, prefix string) bool {
	return len(s) >= len(prefix) && s[:len(prefix)] == prefix
}

const (
	maxUint64 = ^uint64(0)
	maxInt64  = int64(maxUint64 >> 1)
)

// atoi64 parses an int64 from a string s.
// The bool result reports whether s is a number
// representable by a value of type int64.
// atoi64从字符串s中解析一个int64。布尔结果报告s是否是一个可以由类型为int64的值表示的数字。
func atoi64(s string) (int64, bool) {
	if s == "" {
		return 0, false
	}

	neg := false
	if s[0] == '-' {
		neg = true
		s = s[1:]
	}

	un := uint64(0)
	for i := 0; i < len(s); i++ {
		c := s[i]
		if c < '0' || c > '9' {
			return 0, false
		}
		if un > maxUint64/10 {
			// overflow
			return 0, false
		}
		un *= 10
		un1 := un + uint64(c) - '0'
		if un1 < un {
			// overflow
			return 0, false
		}
		un = un1
	}

	if !neg && un > uint64(maxInt64) {
		return 0, false
	}
	if neg && un > uint64(maxInt64)+1 {
		return 0, false
	}

	n := int64(un)
	if neg {
		n = -n
	}

	return n, true
}

// atoi is like atoi64 but for integers
// that fit into an int.
// atoi类似于atoi64，但适用于整数。
func atoi(s string) (int, bool) {
	if n, ok := atoi64(s); n == int64(int(n)) {
		return int(n), ok
	}
	return 0, false
}

// atoi32 is like atoi but for integers
// that fit into an int32.
// atoi32类似于atoi，但适用于适合int32的整数。
func atoi32(s string) (int32, bool) {
	if n, ok := atoi64(s); n == int64(int32(n)) {
		return int32(n), ok
	}
	return 0, false
}

// parseByteCount parses a string that represents a count of bytes.
// parseByteCount解析表示字节计数的字符串。
// s must match the following regular expression:
// s必须与以下正则表达式匹配：
//	^[0-9]+(([KMGT]i)?B)?$
//
// In other words, an integer byte count with an optional unit
// suffix. Acceptable suffixes include one of
// - KiB, MiB, GiB, TiB which represent binary IEC/ISO 80000 units, or
// - B, which just represents bytes.
// 换句话说，一个带有可选单位后缀的整数字节计数。可接受的后缀包括KiB、MiB、GiB、TiB中的一个，表示二进制IEC/ISO 80000单位，或-B，仅表示字节。
// Returns an int64 because that's what its callers want and receive,
// but the result is always non-negative.
// 返回一个int64，因为这是它的调用者想要和接收的，但结果总是非负的。
func parseByteCount(s string) (int64, bool) {
	// The empty string is not valid. 空字符串无效。
	if s == "" {
		return 0, false
	}
	// Handle the easy non-suffix case. 处理简单的无后缀情况。
	last := s[len(s)-1]
	if last >= '0' && last <= '9' {
		n, ok := atoi64(s)
		if !ok || n < 0 {
			return 0, false
		}
		return n, ok
	}
	// Failing a trailing digit, this must always end in 'B'.
	// Also at this point there must be at least one digit before
	// that B.
	// 如果出现尾随数字，则必须始终以“B”结尾。在这一点上，B之前必须至少有一个数字。
	if last != 'B' || len(s) < 2 {
		return 0, false
	}
	// The one before that must always be a digit or 'i'.
	// 在此之前的一个必须始终是数字或“i”。
	if c := s[len(s)-2]; c >= '0' && c <= '9' {
		// Trivial 'B' suffix.
		n, ok := atoi64(s[:len(s)-1])
		if !ok || n < 0 {
			return 0, false
		}
		return n, ok
	} else if c != 'i' {
		return 0, false
	}
	// Finally, we need at least 4 characters now, for the unit
	// prefix and at least one digit.
	// 最后，我们现在至少需要4个字符，用于单位前缀和至少一个数字。
	if len(s) < 4 {
		return 0, false
	}
	power := 0
	switch s[len(s)-3] {
	case 'K':
		power = 1
	case 'M':
		power = 2
	case 'G':
		power = 3
	case 'T':
		power = 4
	default:
		// Invalid suffix.
		return 0, false
	}
	m := uint64(1)
	for i := 0; i < power; i++ {
		m *= 1024
	}
	n, ok := atoi64(s[:len(s)-3])
	if !ok || n < 0 {
		return 0, false
	}
	un := uint64(n)
	if un > maxUint64/m {
		// Overflow.
		return 0, false
	}
	un *= m
	if un > uint64(maxInt64) {
		// Overflow.
		return 0, false
	}
	return int64(un), true
}

//go:nosplit
func findnull(s *byte) int {
	if s == nil {
		return 0
	}

	// Avoid IndexByteString on Plan 9 because it uses SSE instructions
	// on x86 machines, and those are classified as floating point instructions,
	// which are illegal in a note handler.
	// 在Plan 9中避免使用IndexByteString，因为它在x86计算机上使用SSE指令，并且这些指令被归类为浮点指令，在注释处理程序中是非法的。
	if GOOS == "plan9" {
		p := (*[maxAlloc/2 - 1]byte)(unsafe.Pointer(s))
		l := 0
		for p[l] != 0 {
			l++
		}
		return l
	}

	// pageSize is the unit we scan at a time looking for NULL.
	// It must be the minimum page size for any architecture Go
	// runs on. It's okay (just a minor performance loss) if the
	// actual system page size is larger than this value.
	// pageSize是我们一次扫描查找NULL的单位。它必须是Go运行的任何架构的最小页面大小。如果实际系统页面大小大于这个值，也没关系（只是轻微的性能损失）。
	const pageSize = 4096

	offset := 0
	ptr := unsafe.Pointer(s)
	// IndexByteString uses wide reads, so we need to be careful
	// with page boundaries. Call IndexByteString on
	// [ptr, endOfPage) interval.
	// IndexByteString使用宽读取，因此我们需要小心页面边界。在[ptr，endOfPage）间隔调用IndexByteString。
	safeLen := int(pageSize - uintptr(ptr)%pageSize)

	for {
		t := *(*string)(unsafe.Pointer(&stringStruct{ptr, safeLen}))
		// Check one page at a time. 一次检查一页。
		if i := bytealg.IndexByteString(t, 0); i != -1 {
			return offset + i
		}
		// Move to next page 移动到下一页
		ptr = unsafe.Pointer(uintptr(ptr) + uintptr(safeLen))
		offset += safeLen
		safeLen = pageSize
	}
}

func findnullw(s *uint16) int {
	if s == nil {
		return 0
	}
	p := (*[maxAlloc/2/2 - 1]uint16)(unsafe.Pointer(s))
	l := 0
	for p[l] != 0 {
		l++
	}
	return l
}

//go:nosplit
func gostringnocopy(str *byte) string {
	ss := stringStruct{str: unsafe.Pointer(str), len: findnull(str)}
	s := *(*string)(unsafe.Pointer(&ss))
	return s
}

func gostringw(strw *uint16) string {
	var buf [8]byte
	str := (*[maxAlloc/2/2 - 1]uint16)(unsafe.Pointer(strw))
	n1 := 0
	for i := 0; str[i] != 0; i++ {
		n1 += encoderune(buf[:], rune(str[i]))
	}
	s, b := rawstring(n1 + 4)
	n2 := 0
	for i := 0; str[i] != 0; i++ {
		// check for race
		if n2 >= n1 {
			break
		}
		n2 += encoderune(b[n2:], rune(str[i]))
	}
	b[n2] = 0 // for luck
	return s[:n2]
}