feat(parser): macro expansion, conditionals and include splicing with -I

Assisted-by: GLM 5.3 Flash

lexer/lexer.go

@@ -119,7 +119,9 @@ func (l *Lexer) Next() token.Token {
 		// is a C-preprocessor line continuation (used by #define macros in the
 		// runtime .s files): splice the lines together by consuming both, so
 		// the whole macro becomes one logical line that the parser treats as an
-		// opaque preprocessor directive.
+		// opaque preprocessor directive.  The backslash may also reach its
+		// newline across whitespace and a trailing comment ("…; \ // note\n"),
+		// which the toolchain's scanner skips the same way.
 		for {
 			c := l.cur()
 			if c == ' ' || c == '\t' || c == '\r' {
@@ -136,6 +138,16 @@ func (l *Lexer) Next() token.Token {
 				}
 				continue
 			}
+			if c == '\\' && l.continuationAhead() {
+				l.advance() // backslash, then the runes the scan saw
+				for !l.atEnd() && l.cur() != '\n' {
+					l.advance()
+				}
+				if !l.atEnd() {
+					l.advance() // the newline that closes the continuation
+				}
+				continue
+			}
 			break
 		}
 
@@ -185,6 +197,28 @@ func (l *Lexer) Next() token.Token {
 	}
 }
 
+// continuationAhead reports, without consuming anything, whether the
+// backslash at the current position closes onto a newline through nothing
+// but horizontal whitespace and one line comment.  Positions after the
+// backslash are inspected directly on the rune slice so a non-match leaves
+// the scanner state untouched.
+func (l *Lexer) continuationAhead() bool {
+	i := l.i + 1
+	for i < len(l.src) {
+		switch r := l.src[i]; {
+		case r == ' ' || r == '\t' || r == '\r':
+			i++
+		case r == '/' && i+1 < len(l.src) && l.src[i+1] == '/':
+			for i < len(l.src) && l.src[i] != '\n' {
+				i++
+			}
+		default:
+			return r == '\n'
+		}
+	}
+	return false
+}
+
 // lineComment consumes a // comment up to, but not including, the newline.  A
 // trailing run of \r, spaces and tabs is line-ending whitespace rather than
 // comment content, so it never enters the token text.  Trimming only a \r
@@ -403,6 +437,15 @@ func (l *Lexer) punct(start token.Position) token.Token {
 	case '|':
 		l.advance()
 		return l.make(token.Pipe, start, "|")
+	case ';':
+		l.advance()
+		return l.make(token.Semicolon, start, ";")
+	case '&':
+		l.advance()
+		return l.make(token.Ampersand, start, "&")
+	case '~':
+		l.advance()
+		return l.make(token.Tilde, start, "~")
 	default:
 		// Unknown rune: emit it as Illegal and move on.
 		l.advance()