go/scanner: the position of '\n's chars must be the last position of the current line

Background: This didn't matter until recently, because '\n' don't appear as token starts
in source code and thus the exact position was irrelevant (and set as was easiest in the
code). With auto semicolon insertion, a virtual semicolon may be inserted when a '\n' is
seen. The position of the semicolon is the position of the '\n'. Without this fix, these
semicolons appeared on the next line instead of the line where they were inserted.  This
affected the association of comments to declarations in the parser. As a result, some
lead comments where considered line comments, not collected in the ast, and not shown in
godoc pages. (This affected only godoc pages, not gofmt-formatted programs).

Fixes issue 592.

R=rsc
CC=golang-dev
http://codereview.appspot.com/224068

2 files changed, 12 insertions, 8 deletions

diff --git a/src/pkg/go/scanner/scanner.go b/src/pkg/go/scanner/scanner.go
index dc2f35939..b12f9152a 100644
--- a/src/pkg/go/scanner/scanner.go
+++ b/src/pkg/go/scanner/scanner.go
@@ -46,13 +46,15 @@ func (S *Scanner) next() {
 	if S.offset < len(S.src) {
 		S.pos.Offset = S.offset
 		S.pos.Column++
+		if S.ch == '\n' {
+			// next character starts a new line
+			S.pos.Line++
+			S.pos.Column = 1
+		}
 		r, w := int(S.src[S.offset]), 1
 		switch {
 		case r == 0:
 			S.error(S.pos, "illegal character NUL")
-		case r == '\n':
-			S.pos.Line++
-			S.pos.Column = 0
 		case r >= 0x80:
 			// not ASCII
 			r, w = utf8.DecodeRune(S.src[S.offset:])
@@ -168,7 +170,7 @@ func (S *Scanner) scanComment(pos token.Position) {
 								// valid //line filename:line comment;
 								// update scanner position
 								S.pos.Filename = string(text[len(prefix):i])
-								S.pos.Line = line
+								S.pos.Line = line - 1 // -1 since the '\n' has not been consumed yet
 							}
 						}
 					}
@@ -211,7 +213,7 @@ func (S *Scanner) findNewline(pos token.Position) bool {
 			newline = true
 			break
 		}
-		S.skipWhitespace()
+		S.skipWhitespace() // S.insertSemi is set
 		if S.ch == '\n' {
 			newline = true
 			break
@@ -526,7 +528,7 @@ scanAgain:
 		case -1:
 			tok = token.EOF
 		case '\n':
-			// we only reach here of S.insertSemi was
+			// we only reach here if S.insertSemi was
 			// set in the first place and exited early
 			// from S.skipWhitespace()
 			S.insertSemi = false // newline consumed
diff --git a/src/pkg/go/scanner/scanner_test.go b/src/pkg/go/scanner/scanner_test.go
index ad54dfd1f..002a81dd9 100644
--- a/src/pkg/go/scanner/scanner_test.go
+++ b/src/pkg/go/scanner/scanner_test.go
@@ -219,11 +219,12 @@ func TestScan(t *testing.T) {
 	for _, e := range tokens {
 		src += e.lit + whitespace
 	}
+	src_linecount := newlineCount(src)
 	whitespace_linecount := newlineCount(whitespace)
 
 	// verify scan
 	index := 0
-	epos := token.Position{"", 0, 1, 1}
+	epos := token.Position{"", 0, 1, 1} // expected position
 	nerrors := Tokenize("", []byte(src), &testErrorHandler{t}, ScanComments,
 		func(pos token.Position, tok token.Token, litb []byte) bool {
 			e := elt{token.EOF, "", special}
@@ -233,7 +234,8 @@ func TestScan(t *testing.T) {
 			lit := string(litb)
 			if tok == token.EOF {
 				lit = "<EOF>"
-				epos.Column = 0
+				epos.Line = src_linecount
+				epos.Column = 1
 			}
 			checkPos(t, lit, pos, epos)
 			if tok != e.tok {