src/internal/stringslite/strings.go

// Copyright 2024 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 stringslite implements a subset of strings,
// only using packages that may be imported by "os".
//
// Most tests for these functions are in the strings package.
package stringslite

import (
	"internal/bytealg"
	"unsafe"
)

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

func HasSuffix(s, suffix string) bool {
	return len(s) >= len(suffix) && s[len(s)-len(suffix):] == suffix
}

func IndexByte(s string, c byte) int {
	return bytealg.IndexByteString(s, c)
}

func Index(s, substr string) int {
	n := len(substr)
	switch {
	case n == 0 || substr == s:
		return 0
	case n == 1:
		return IndexByte(s, substr[0])
	case n >= len(s):
		return -1
	case n <= bytealg.MaxLen && len(s) <= bytealg.MaxBruteForce:
		// Use brute force when s and substr both are small
		return bytealg.IndexString(s, substr)
	}
	c0 := substr[0]
	c1 := substr[1]
	i := 0
	t := len(s) - n + 1
	fails := 0
	for i < t {
		if s[i] != c0 {
			// IndexByte is faster than bytealg.IndexString, 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 && s[i:i+n] == substr {
			return i
		}
		i++
		fails++
		if n <= bytealg.MaxLen && fails > bytealg.Cutover(i) {
			// Switch to bytealg.IndexString when IndexByte produces too many false positives.
			r := bytealg.IndexString(s[i:], substr)
			if r >= 0 {
				return r + i
			}
			return -1
		} else if n > bytealg.MaxLen && fails >= 4+i>>4 && i < t {
			// See comment in ../bytes/bytes.go.
			j := bytealg.IndexRabinKarp(s[i:], substr)
			if j < 0 {
				return -1
			}
			return i + j
		}
	}
	return -1
}

func Cut(s, sep string) (before, after string, found bool) {
	if i := Index(s, sep); i >= 0 {
		return s[:i], s[i+len(sep):], true
	}
	return s, "", false
}

func CutPrefix(s, prefix string) (after string, found bool) {
	if !HasPrefix(s, prefix) {
		return s, false
	}
	return s[len(prefix):], true
}

func CutSuffix(s, suffix string) (before string, found bool) {
	if !HasSuffix(s, suffix) {
		return s, false
	}
	return s[:len(s)-len(suffix)], true
}

func TrimPrefix(s, prefix string) string {
	if HasPrefix(s, prefix) {
		return s[len(prefix):]
	}
	return s
}

func TrimSuffix(s, suffix string) string {
	if HasSuffix(s, suffix) {
		return s[:len(s)-len(suffix)]
	}
	return s
}

// IsSpace reports whether r is a space character as defined by
// Unicode's White Space property.
func IsSpace(r rune) bool {
	switch r {
	case '\t', '\n', '\v', '\f', '\r', ' ',
		0x0085, // NEXT LINE
		0x00A0, // NO-BREAK SPACE
		0x1680, // OGHAM SPACE MARK
		0x2000, // EN QUAD
		0x2001, // EM QUAD
		0x2002, // EN SPACE
		0x2003, // EM SPACE
		0x2004, // THREE-PER-EM SPACE
		0x2005, // FOUR-PER-EM SPACE
		0x2006, // SIX-PER-EM SPACE
		0x2007, // FIGURE SPACE
		0x2008, // PUNCTUATION SPACE
		0x2009, // THIN SPACE
		0x200A, // HAIR SPACE
		0x2028, // LINE SEPARATOR
		0x2029, // PARAGRAPH SEPARATOR
		0x202F, // NARROW NO-BREAK SPACE
		0x205F, // MEDIUM MATHEMATICAL SPACE
		0x3000: // IDEOGRAPHIC SPACE
		return true
	}
	return false
}

func Clone(s string) string {
	if len(s) == 0 {
		return ""
	}
	b := make([]byte, len(s))
	copy(b, s)
	return unsafe.String(&b[0], len(b))
}