strings: add EqualFold

Case-insensitive strcmp without using ToLower.
(Using ToLower is not always correct, and it allocates.)

R=golang-dev, r
CC=golang-dev
https://golang.org/cl/5143044

1 files changed, 54 insertions, 0 deletions

diff --git a/src/pkg/strings/strings.go b/src/pkg/strings/strings.go
index c547297e66..446fa3a0c8 100644
--- a/src/pkg/strings/strings.go
+++ b/src/pkg/strings/strings.go
@@ -583,3 +583,57 @@ func Replace(s, old, new string, n int) string {
 	w += copy(t[w:], s[start:])
 	return string(t[0:w])
 }
+
+// EqualFold returns true if s and t are equal under Unicode case-folding.
+func EqualFold(s, t string) bool {
+	for s != "" && t != "" {
+		// Extract first rune from each string.
+		var sr, tr int
+		if s[0] < utf8.RuneSelf {
+			sr, s = int(s[0]), s[1:]
+		} else {
+			r, size := utf8.DecodeRuneInString(s)
+			sr, s = r, s[size:]
+		}
+		if t[0] < utf8.RuneSelf {
+			tr, t = int(t[0]), t[1:]
+		} else {
+			r, size := utf8.DecodeRuneInString(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 && 'A' <= sr && sr <= 'Z' {
+			// ASCII, and sr is upper case.  tr must be lower case.
+			if 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 s == t
+}