Golang bytes源码分析

bytes/bytes.go源码分析

Golang JDK 1.10.3

bytes包提供了操作[]byte的常用方法。

 

源码分析

func equalPortable(a, b []byte) bool {
	if len(a) != len(b) {
		return false
	}
	for i, c := range a {
		if c != b[i] {
			return false
		}
	}
	return true
}

equalPortable函数是内部函数，用于比较两个切片的元素是否相等。

 

// explode splits s into a slice of UTF-8 sequences, one per Unicode code point (still slices of bytes),
// up to a maximum of n byte slices. Invalid UTF-8 sequences are chopped into individual bytes.
func explode(s []byte, n int) [][]byte {
	if n <= 0 {
		n = len(s)
	}
	a := make([][]byte, n)
	var size int
	na := 0
	for len(s) > 0 {
		if na+1 >= n {
			a[na] = s
			na++
			break
		}
		_, size = utf8.DecodeRune(s)
		a[na] = s[0:size:size]
		s = s[size:]
		na++
	}
	return a[0:na]
}

explode函数是内部函数，用于将字节切片s转成 UTF-8序列

 

// countGeneric actually implements Count
func countGeneric(s, sep []byte) int {
	// special case
	if len(sep) == 0 {
		return utf8.RuneCount(s) + 1
	}
	n := 0
	for {
		i := Index(s, sep)
		if i == -1 {
			return n
		}
		n++
		s = s[i+len(sep):]
	}
}

countGeneric函数也是内部函数，用于返回sep在s中出现的次数。如果sep为空，则返回s的rune长度+1

 

// Contains reports whether subslice is within b.
func Contains(b, subslice []byte) bool {
	return Index(b, subslice) != -1
}

作用：b中是否包含subslice切片

 

// ContainsAny reports whether any of the UTF-8-encoded code points in chars are within b.
func ContainsAny(b []byte, chars string) bool {
	return IndexAny(b, chars) >= 0
}

作用：判断切片b中是否包含字符串chanrs

 

// ContainsRune reports whether the rune is contained in the UTF-8-encoded byte slice b.
func ContainsRune(b []byte, r rune) bool {
	return IndexRune(b, r) >= 0
}

作用：判断字节切片b中是否包含UTF-8字符r

 

func indexBytePortable(s []byte, c byte) int {
	for i, b := range s {
		if b == c {
			return i
		}
	}
	return -1
}

indexBytePortable函数用于返回c在s中第一次出现的索引，如果在切片s中，则返回-1

 

// LastIndex returns the index of the last instance of sep in s, or -1 if sep is not present in s.
func LastIndex(s, sep []byte) int {
	n := len(sep)
	if n == 0 {
		return len(s)
	}
	c := sep[0]
	for i := len(s) - n; i >= 0; i-- {
		if s[i] == c && (n == 1 || Equal(s[i:i+n], sep)) {
			return i
		}
	}
	return -1
}

LastIndex函数用于获取sep在s中反向第一次出现的索引，子切片sep不包含在切片s中，则返回-1

 

// LastIndexByte returns the index of the last instance of c in s, or -1 if c is not present in s.
func LastIndexByte(s []byte, c byte) int {
	for i := len(s) - 1; i >= 0; i-- {
		if s[i] == c {
			return i
		}
	}
	return -1
}

作用：获取字节c在切片s中倒序第一次出现的索引

 

// IndexRune interprets s as a sequence of UTF-8-encoded code points.
// It returns the byte index of the first occurrence in s of the given rune.
// It returns -1 if rune is not present in s.
// If r is utf8.RuneError, it returns the first instance of any
// invalid UTF-8 byte sequence.
func IndexRune(s []byte, r rune) int {
	switch {
	case 0 <= r && r < utf8.RuneSelf:
		return IndexByte(s, byte(r))
	case r == utf8.RuneError:
		for i := 0; i < len(s); {
			r1, n := utf8.DecodeRune(s[i:])
			if r1 == utf8.RuneError {
				return i
			}
			i += n
		}
		return -1
	case !utf8.ValidRune(r):
		return -1
	default:
		var b [utf8.UTFMax]byte
		n := utf8.EncodeRune(b[:], r)
		return Index(s, b[:n])
	}
}

作用：获取UTF-8字符r在字节切片s中第一次出现的索引，不包含在切片s中返回-1

 

// IndexAny interprets s as a sequence of UTF-8-encoded Unicode code points.
// It returns the byte index of the first occurrence in s of any of the Unicode
// code points in chars. It returns -1 if chars is empty or if there is no code
// point in common.
func IndexAny(s []byte, chars string) int {
	if chars == "" {
		// Avoid scanning all of s.
		return -1
	}
	if len(s) > 8 {
		if as, isASCII := makeASCIISet(chars); isASCII {
			for i, c := range s {
				if as.contains(c) {
					return i
				}
			}
			return -1
		}
	}
	var width int
	for i := 0; i < len(s); i += width {
		r := rune(s[i])
		if r < utf8.RuneSelf {
			width = 1
		} else {
			r, width = utf8.DecodeRune(s[i:])
		}
		for _, ch := range chars {
			if r == ch {
				return i
			}
		}
	}
	return -1
}

作用：查找字符串 chars 中的任何一个字符在 切片s 中第一次出现的位置，找不到则返回 -1</