fix(lexer): treat trailing CR as line end so comment text is idempotent

Assisted-by: GLM 5.3 Flash

format/fuzz_test.go

@@ -31,6 +31,12 @@ func FuzzFormatIdempotency(f *testing.F) {
 	f.Add("TEXT ·f(SB), NOSPLIT, $0\n\tMOVQ AX, BX\n\tRET\n")
 	f.Add("TEXT ·f(SB),NOSPLIT,$0\n\tMOVQ   AX,BX\n\n\n\tRET\n")
 	f.Add("garbage ### ???\n")
+	// Line-ending whitespace at the edge of a comment: a CR followed by more
+	// trailing whitespace once survived the first pass and disappeared on
+	// re-lexing, so formatting was not idempotent.
+	f.Add("//\r ")
+	f.Add("// loop \r\t\nMOVQ AX, BX\n")
+	f.Add("TEXT ·f(SB), NOSPLIT, $0 // tail\r\n\tMOVQ AX, BX\r\n\tRET\r\n")
 
 	f.Fuzz(func(t *testing.T, src string) {
 		once := Source(src)

format/testdata/fuzz/FuzzFormatIdempotency/f1f73934513efdb3

@@ -0,0 +1,2 @@
+go test fuzz v1
+string("//\r ")

lexer/lexer.go

@@ -186,15 +186,19 @@ func (l *Lexer) Next() token.Token {
 }
 
 // lineComment consumes a // comment up to, but not including, the newline.  A
-// trailing \r is part of a CRLF line ending rather than comment content:
+// trailing run of \r, spaces and tabs is line-ending whitespace rather than
-// dropping it keeps the formatter's output uniformly LF-terminated.
+// comment content, so it never enters the token text.  Trimming only a \r
+// directly before the token's end would make the text depend on what follows
+// the comment (a newline or the end of the input): "//x\r " would carry the
+// "\r " while "//x\r\n" would not, and a formatter that terminates the line
+// with \n would then re-lex its own output to a shorter comment.
 func (l *Lexer) lineComment(start token.Position) token.Token {
 	var b strings.Builder
 	for !l.atEnd() && l.cur() != '\n' {
 		b.WriteRune(l.cur())
 		l.advance()
 	}
-	return l.make(token.Comment, start, strings.TrimSuffix(b.String(), "\r"))
+	return l.make(token.Comment, start, strings.TrimRight(b.String(), " \t\r"))
 }
 
 // blockComment consumes a /* ... */ comment, tolerating an unterminated one.

lexer/lexer_test.go

@@ -85,6 +85,19 @@ func TestLabelAndComment(t *testing.T) {
 		[]token.Kind{token.Ident, token.Colon, token.Ident, token.Ident, token.Comment})
 }
 
+func TestLineCommentTrailingWhitespace(t *testing.T) {
+	// A trailing run of CR, spaces and tabs is line-ending whitespace, not
+	// comment content.  The token text must not depend on what follows the
+	// comment: before the trim covered only a CR directly before the token's
+	// end, "// loop\r " kept the CR while "// loop\r\n" dropped it, and the
+	// formatter re-lexed its own output to a shorter comment.
+	eq(t, texts("// loop\r"), []string{"// loop"})
+	eq(t, texts("// loop\r "), []string{"// loop"})
+	eq(t, texts("// loop \r\t\nMOVQ AX, BX"), []string{"// loop", "MOVQ", "AX", ",", "BX"})
+	// A CR inside the comment is content and stays.
+	eq(t, texts("// loops\rall"), []string{"// loops\rall"})
+}
+
 func TestAVX512Mnemonics(t *testing.T) {
 	eq(t, texts("VFMADD231PD Z14, Z12, Z10"),
 		[]string{"VFMADD231PD", "Z14", ",", "Z12", ",", "Z10"})