strings, internal/stringslite: lite version of strings package

To be used by internal/filepathlite, which is to be used by os.
There are probably other places where it would be convenient
to have strings functions accessible to RUNTIME level packages.

Change-Id: Icda59e7a9e26d9e8f3692db0ea4fb7b3dbf570d7
Reviewed-on: https://go-review.googlesource.com/c/go/+/581516
Reviewed-by: Ian Lance Taylor <iant@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

1 files changed, 124 insertions, 0 deletions

diff --git a/src/internal/stringslite/strings.go b/src/internal/stringslite/strings.go
new file mode 100644
index 0000000000..ce8a913297
--- /dev/null
+++ b/src/internal/stringslite/strings.go
@@ -0,0 +1,124 @@
+// 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".
+//
+// Tests for these functions are in the strings package.
+package stringslite
+
+import "internal/bytealg"
+
+func HasPrefix(s, prefix string) bool {
+	return len(s) >= len(prefix) && s[0: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:
+		return 0
+	case n == 1:
+		return IndexByte(s, substr[0])
+	case n == len(s):
+		if substr == s {
+			return 0
+		}
+		return -1
+	case n > len(s):
+		return -1
+	case n <= bytealg.MaxLen:
+		// Use brute force when s and substr both are small
+		if len(s) <= bytealg.MaxBruteForce {
+			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
+			}
+			fails++
+			i++
+			// Switch to bytealg.IndexString when IndexByte produces too many false positives.
+			if fails > bytealg.Cutover(i) {
+				r := bytealg.IndexString(s[i:], substr)
+				if r >= 0 {
+					return r + i
+				}
+				return -1
+			}
+		}
+		return -1
+	}
+	c0 := substr[0]
+	c1 := substr[1]
+	i := 0
+	t := len(s) - n + 1
+	fails := 0
+	for i < t {
+		if s[i] != c0 {
+			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 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
+}