bytes.go

func trimLeftUnicode(s []byte, cutset string) []byte {
	for len(s) > 0 {
		r, n := rune(s[0]), 1
		if r >= utf8.RuneSelf {
			r, n = utf8.DecodeRune(s)
		}
		if !containsRune(cutset, r) {
			break
		}
		s = s[n:]
	}
	if len(s) == 0 {
		// This is what we've historically done.
		return nil
	}
	return s
}

// TrimRight returns a subslice of s by slicing off all trailing
// UTF-8-encoded code points that are contained in cutset.
func TrimRight(s []byte, cutset string) []byte {
	if len(s) == 0 || cutset == "" {
		return s
	}
	if len(cutset) == 1 && cutset[0] < utf8.RuneSelf {
		return trimRightByte(s, cutset[0])
	}
	if as, ok := makeASCIISet(cutset); ok {
		return trimRightASCII(s, &as)
	}
	return trimRightUnicode(s, cutset)
}

func trimRightByte(s []byte, c byte) []byte {
	for len(s) > 0 && s[len(s)-1] == c {
		s = s[:len(s)-1]
	}
	return s
}

func trimRightASCII(s []byte, as *asciiSet) []byte {
	for len(s) > 0 {
		if !as.contains(s[len(s)-1]) {
			break
		}
		s = s[:len(s)-1]
	}
	return s
}

func trimRightUnicode(s []byte, cutset string) []byte {
	for len(s) > 0 {
		r, n := rune(s[len(s)-1]), 1
		if r >= utf8.RuneSelf {
			r, n = utf8.DecodeLastRune(s)
		}
		if !containsRune(cutset, r) {
			break
		}
		s = s[:len(s)-n]
	}
	return s
}

// TrimSpace returns a subslice of s by slicing off all leading and
// trailing white space, as defined by Unicode.
func TrimSpace(s []byte) []byte {
	// Fast path for ASCII: look for the first ASCII non-space byte
	start := 0
	for ; start < len(s); start++ {
		c := s[start]
		if c >= utf8.RuneSelf {
			// If we run into a non-ASCII byte, fall back to the
			// slower unicode-aware method on the remaining bytes
			return TrimFunc(s[start:], unicode.IsSpace)
		}
		if asciiSpace[c] == 0 {
			break
		}
	}

	// Now look for the first ASCII non-space byte from the end
	stop := len(s)
	for ; stop > start; stop-- {
		c := s[stop-1]
		if c >= utf8.RuneSelf {
			return TrimFunc(s[start:stop], unicode.IsSpace)
		}
		if asciiSpace[c] == 0 {
			break
		}
	}

	// At this point s[start:stop] starts and ends with an ASCII
	// non-space bytes, so we're done. Non-ASCII cases have already
	// been handled above.
	if start == stop {
		// Special case to preserve previous TrimLeftFunc behavior,
		// returning nil instead of empty slice if all spaces.
		return nil
	}
	return s[start:stop]
}

// Runes interprets s as a sequence of UTF-8-encoded code points.
// It returns a slice of runes (Unicode code points) equivalent to s.
func Runes(s []byte) []rune {
	t := make([]rune, utf8.RuneCount(s))
	i := 0
	for len(s) > 0 {
		r, l := utf8.DecodeRune(s)
		t[i] = r
		i++
		s = s[l:]
	}
	return t
}

// Replace returns a copy of the slice s with the first n
// non-overlapping instances of old replaced by new.
// If old is empty, it matches at the beginning of the slice
// and after each UTF-8 sequence, yielding up to k+1 replacements
// for a k-rune slice.
// If n < 0, there is no limit on the number of replacements.
func Replace(s, old, new []byte, n int) []byte {
	m := 0
	if n != 0 {
		// Compute number of replacements.
		m = Count(s, old)
	}
	if m == 0 {
		// Just return a copy.
		return append([]byte(nil), s...)
	}
	if n < 0 || m < n {
		n = m
	}

	// Apply replacements to buffer.
	t := make([]byte, len(s)+n*(len(new)-len(old)))
	w := 0
	start := 0
	for i := 0; i < n; i++ {
		j := start
		if len(old) == 0 {
			if i > 0 {
				_, wid := utf8.DecodeRune(s[start:])
				j += wid
			}
		} else {
			j += Index(s[start:], old)
		}
		w += copy(t[w:], s[start:j])
		w += copy(t[w:], new)
		start = j + len(old)
	}
	w += copy(t[w:], s[start:])
	return t[0:w]
}

// ReplaceAll returns a copy of the slice s with all
// non-overlapping instances of old replaced by new.
// If old is empty, it matches at the beginning of the slice
// and after each UTF-8 sequence, yielding up to k+1 replacements
// for a k-rune slice.
func ReplaceAll(s, old, new []byte) []byte {
	return Replace(s, old, new, -1)
}

// EqualFold reports whether s and t, interpreted as UTF-8 strings,
// are equal under simple Unicode case-folding, which is a more general
// form of case-insensitivity.
func EqualFold(s, t []byte) bool {
	// ASCII fast path
	i := 0
	for ; i < len(s) && i < len(t); i++ {
		sr := s[i]
		tr := t[i]
		if sr|tr >= utf8.RuneSelf {
			goto hasUnicode
		}

		// Easy case.
		if tr == sr {
			continue
		}

		// Make sr < tr to simplify what follows.
		if tr < sr {
			tr, sr = sr, tr
		}
		// ASCII only, sr/tr must be upper/lower case
		if 'A' <= sr && sr <= 'Z' && tr == sr+'a'-'A' {
			continue
		}
		return false
	}
	// Check if we've exhausted both strings.
	return len(s) == len(t)

hasUnicode:
	s = s[i:]
	t = t[i:]
	for len(s) != 0 && len(t) != 0 {
		// Extract first rune from each.
		var sr, tr rune
		if s[0] < utf8.RuneSelf {
			sr, s = rune(s[0]), s[1:]
		} else {
			r, size := utf8.DecodeRune(s)
			sr, s = r, s[size:]
		}
		if t[0] < utf8.RuneSelf {
			tr, t = rune(t[0]), t[1:]
		} else {
			r, size := utf8.DecodeRune(t)
			tr, t = r, t[size:]
		}

		// If they match, keep going; if not, return false.

		// Easy case.
		if tr == sr {
			continue
		}

		// Make sr < tr to simplify what follows.
		if tr < sr {
			tr, sr = sr, tr
		}
		// Fast check for ASCII.
		if tr < utf8.RuneSelf {
			// ASCII only, sr/tr must be upper/lower case
			if 'A' <= sr && sr <= 'Z' && tr == sr+'a'-'A' {
				continue
			}
			return false
		}

		// General case. SimpleFold(x) returns the next equivalent rune > x
		// or wraps around to smaller values.
		r := unicode.SimpleFold(sr)
		for r != sr && r < tr {
			r = unicode.SimpleFold(r)
		}
		if r == tr {
			continue
		}
		return false
	}

	// One string is empty. Are both?
	return len(s) == len(t)
}

// Index returns the index of the first instance of sep in s, or -1 if sep is not present in s.
func Index(s, sep []byte) int {
	n := len(sep)
	switch {
	case n == 0:
		return 0
	case n == 1:
		return IndexByte(s, sep[0])
	case n == len(s):
		if Equal(sep, s) {
			return 0
		}
		return -1
	case n > len(s):
		return -1
	case n <= bytealg.MaxLen:
		// Use brute force when s and sep both are small
		if len(s) <= bytealg.MaxBruteForce {
			return bytealg.Index(s, sep)
		}
		c0 := sep[0]
		c1 := sep[1]
		i := 0
		t := len(s) - n + 1
		fails := 0
		for i < t {
			if s[i] != c0 {
				// IndexByte is faster than bytealg.Index, so use it as long as
				// we're not getting lots of false positives.
				o := IndexByte(s[i+1:t], c0)
				if o < 0 {
					return -1
				}
				i += o + 1
			}
			if s[i+1] == c1 && Equal(s[i:i+n], sep) {
				return i
			}
			fails++
			i++
			// Switch to bytealg.Index when IndexByte produces too many false positives.
			if fails > bytealg.Cutover(i) {
				r := bytealg.Index(s[i:], sep)
				if r >= 0 {
					return r + i
				}
				return -1
			}
		}
		return -1
	}
	c0 := sep[0]
	c1 := sep[1]
	i := 0
	fails := 0
	t := len(s) - n + 1
	for i < t {
		if s[i] != c0 {
			o := IndexByte(s[i+1:t], c0)
			if o < 0 {
				break
			}
			i += o + 1
		}
		if s[i+1] == c1 && Equal(s[i:i+n], sep) {
			return i
		}
		i++
		fails++
		if fails >= 4+i>>4 && i < t {
			// Give up on IndexByte, it isn't skipping ahead
			// far enough to be better than Rabin-Karp.
			// Experiments (using IndexPeriodic) suggest
			// the cutover is about 16 byte skips.
			// TODO: if large prefixes of sep are matching
			// we should cutover at even larger average skips,
			// because Equal becomes that much more expensive.
			// This code does not take that effect into account.
			j := bytealg.IndexRabinKarpBytes(s[i:], sep)
			if j < 0 {
				return -1
			}
			return i + j
		}
	}
	return -1
}

// Cut slices s around the first instance of sep,
// returning the text before and after sep.
// The found result reports whether sep appears in s.
// If sep does not appear in s, cut returns s, nil, false.
//
// Cut returns slices of the original slice s, not copies.
func Cut(s, sep []byte) (before, after []byte, found bool) {
	if i := Index(s, sep); i >= 0 {
		return s[:i], s[i+len(sep):], true
	}
	return s, nil, false
}

// Clone returns a copy of b[:len(b)].
// The result may have additional unused capacity.
// Clone(nil) returns nil.
func Clone(b []byte) []byte {
	if b == nil {
		return nil
	}
	return append([]byte{}, b...)
}

// CutPrefix returns s without the provided leading prefix byte slice
// and reports whether it found the prefix.
// If s doesn't start with prefix, CutPrefix returns s, false.
// If prefix is the empty byte slice, CutPrefix returns s, true.
//
// CutPrefix returns slices of the original slice s, not copies.
func CutPrefix(s, prefix []byte) (after []byte, found bool) {
	if !HasPrefix(s, prefix) {
		return s, false
	}
	return s[len(prefix):], true
}

// CutSuffix returns s without the provided ending suffix byte slice
// and reports whether it found the suffix.
// If s doesn't end with suffix, CutSuffix returns s, false.
// If suffix is the empty byte slice, CutSuffix returns s, true.
//
// CutSuffix returns slices of the original slice s, not copies.
func CutSuffix(s, suffix []byte) (before []byte, found bool) {
	if !HasSuffix(s, suffix) {
		return s, false
	}
	return s[:len(s)-len(suffix)], true
}