From: Robert Griesemer <gri@golang.org>
Date: Wed, 16 Mar 2022 04:44:37 +0000 (-0700)
Subject: text/scanner: guard against installed IsIdentRune that accepts EOF
X-Git-Tag: go1.19beta1~1037
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=9956a5423e40bab92c572489eae26ba80ed803ab;p=gostls13.git

text/scanner: guard against installed IsIdentRune that accepts EOF

IsIdentRune may be installed by a client of the scanner. If the
installed function accepts EOF as a valid identifier rune, Scan
calls may not terminate.

Check for EOF when a user-defined IsIdentRune is used.

Fixes #50909.

Change-Id: Ib104b03ee59e2d58faa71f227c3b51ba424f7f61
Reviewed-on: https://go-review.googlesource.com/c/go/+/393254
Trust: Robert Griesemer <gri@golang.org>
Run-TryBot: Robert Griesemer <gri@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
---

diff --git a/src/text/scanner/scanner.go b/src/text/scanner/scanner.go
index f1fbf9861d..735982afcb 100644
--- a/src/text/scanner/scanner.go
+++ b/src/text/scanner/scanner.go
@@ -346,7 +346,7 @@ func (s *Scanner) errorf(format string, args ...any) {
 
 func (s *Scanner) isIdentRune(ch rune, i int) bool {
 	if s.IsIdentRune != nil {
-		return s.IsIdentRune(ch, i)
+		return ch != EOF && s.IsIdentRune(ch, i)
 	}
 	return ch == '_' || unicode.IsLetter(ch) || unicode.IsDigit(ch) && i > 0
 }
diff --git a/src/text/scanner/scanner_test.go b/src/text/scanner/scanner_test.go
index fe39d3060b..6a454d9be7 100644
--- a/src/text/scanner/scanner_test.go
+++ b/src/text/scanner/scanner_test.go
@@ -913,3 +913,22 @@ func extractInts(t string, mode uint) (res string) {
 		}
 	}
 }
+
+func TestIssue50909(t *testing.T) {
+	var s Scanner
+	s.Init(strings.NewReader("hello \n\nworld\n!\n"))
+	s.IsIdentRune = func(ch rune, _ int) bool { return ch != '\n' }
+
+	r := ""
+	n := 0
+	for s.Scan() != EOF && n < 10 {
+		r += s.TokenText()
+		n++
+	}
+
+	const R = "hello world!"
+	const N = 3
+	if r != R || n != N {
+		t.Errorf("got %q (n = %d); want %q (n = %d)", r, n, R, N)
+	}
+}