text/scanner: Fix EOF reporting on strange Readers

Currently, scanner uses -1 to represent 2 different states:

1. I haven't yet scanned anything, call it "Beginning of File"
2. I've reached the end of the input, ie EOF

The result of this behavior is that calling Peek() when next()
has detected the end of the input and set s.ch to scanner.EOF,
is that Peek() things "oh, s.ch is < 0, which to me means that
I haven't scanned any next yet, let me try and clear the BOM
marker."

When this behavior is run on a typical IO, next() will issue
a Read and get (0, io.EOF) back for the second time without
blocking and Peek() will return scanner.EOF.

The bug comes into play when, inside a terminal, hitting Control-D.
This causes the terminal to return a EOF condition to the reader
but it does not actually close the fd.

So, combining these 2 situations, we arrive at the bug:

What is expected: hitting Control-D in a terminal will make Peek()
return scanner.EOF instantly.

What actually happens:

0. Code waiting in Next()
1. User hits Control-D
2. fd returns EOF condition
3. EOF bubbles it's way out to line 249 in scanner.go
4. next() returns scanner.EOF
5. Next() saves the scanner.EOF to s.ch and returns the previous value
6. Peek() runs, sees s.ch < 0, mistakenly thinks it hasn't run yet and
   tries to read the BOM marker.
7. next() sees the buffer is empty and tries to fill it again, blocking
   on line 249.

The fix is simple: use a different code to indicate that no data
has been scanned.

Change-Id: Iee8f4da5881682c4d4c36b93b9bf397ac5798179
Reviewed-on: https://go-review.googlesource.com/7913
Reviewed-by: Robert Griesemer <[email protected]>

src/text/scanner/scanner.go

@@ -208,7 +208,7 @@ func (s *Scanner) Init(src io.Reader) *Scanner {
 	s.tokPos = -1
 
 	// initialize one character look-ahead
-	s.ch = -1 // no char read yet
+	s.ch = -2 // no char read yet, not EOF
 
 	// initialize public fields
 	s.Error = nil
@@ -322,7 +322,7 @@ func (s *Scanner) Next() rune {
 // the scanner. It returns EOF if the scanner's position is at the last
 // character of the source.
 func (s *Scanner) Peek() rune {
-	if s.ch < 0 {
+	if s.ch == -2 {
 		// this code is only run for the very first character
 		s.ch = s.next()
 		if s.ch == '\uFEFF' {

src/text/scanner/scanner_test.go

@@ -616,3 +616,32 @@ func TestPos(t *testing.T) {
 		t.Errorf("%d errors", s.ErrorCount)
 	}
 }
+
+type countReader int
+
+func (c *countReader) Read([]byte) (int, error) {
+	*c++
+
+	return 0, io.EOF
+}
+
+func TestPeekEOFHandling(t *testing.T) {
+	var r countReader
+
+	// corner case: empty source
+	s := new(Scanner).Init(&r)
+
+	tok := s.Next()
+	if tok != EOF {
+		t.Errorf("EOF not reported")
+	}
+
+	tok = s.Peek()
+	if tok != EOF {
+		t.Errorf("EOF not reported")
+	}
+
+	if r != 2 {
+		t.Errorf("scanner called Read %d times, not twice", r)
+	}
+}