Fixed assembly source parsing

dasm.py

@@ -0,0 +1,166 @@
+#!/usr/bin/env python3
+
+from rply import LexerGenerator, ParserGenerator, Token
+
+
+_lexer = LexerGenerator()
+_lexer.add("OPCODE2", r"SET|ADD|SUB|MUL|MLI|DIV|MOD|MDI|AND|BOR|XOR|SHR|ASR|SHL|IFB|IFC|IFE|IFN|IFG|IFA|IFL|IFU|ADX|SBX|STI|STD")
+_lexer.add("OPCODE1", r"JSR|INT|IAG|IAS|RFI|IAQ|HWN|HWQ|HWI")
+_lexer.add("OPCODE0", r"HLT")
+_lexer.add("GREG", r"A|B|C|X|Y|Z|I|J")
+_lexer.add("SREG", r"SP|PC|EX")
+_lexer.add("STACK", r"PUSH|POP|PEEK|PICK")
+_lexer.add("COMMA", r",")
+_lexer.add("COLON", r":")
+_lexer.add("OPENSB", r"\[")
+_lexer.add("CLOSESB", r"\]")
+
+_lexer.add("OPENRB", r"\(")
+_lexer.add("CLOSERB", r"\)")
+_lexer.add("NUMBER", r"0x[0-9a-fA-F]+|[0-9]+")
+_lexer.add("SYMBOL", r"[a-zA-Z._@][a-zA-Z._@0-9]*")
+_lexer.add("PLUS", r"\+")
+_lexer.add("MINUS", r"-")
+_lexer.add("STAR", r"\*")
+_lexer.add("SLASH", r"/")
+_lexer.add("EOL", r"(([;#][^\n]*)?(\r?\n))+")
+_lexer.ignore(r"[ \t]+")
+#_lexer.ignore(r"\s+|([;#][^\n]*)?\n")
+lexer = _lexer.build()
+
+
+_parser = ParserGenerator([x.name for x in lexer.rules],
+        precedence=[
+            ("left", ["PLUS", "MINUS"]),
+            ("left", ["STAR", "SLASH"])
+        ]
+)
+
+@_parser.production("asmcode : asmline")
+def asmcode1(p):
+    return [p[0]]
+
+@_parser.production("asmcode : asmcode asmline")
+def asmcode2(p):
+    return p[0]+[p[1]]
+
+@_parser.production("asmline : SYMBOL asminst EOL")
+def asmline_label(p):
+    return (p[0].getstr(), p[1])
+
+@_parser.production("asmline : SYMBOL COLON asminst EOL")
+def asmline_label_colon(p):
+    return (p[0].getstr(), p[2])
+
+@_parser.production("asmline : asminst EOL")
+def asmline_asminst(p):
+    return (None, p[0])
+
+@_parser.production("asmline : SYMBOL COLON EOL")
+@_parser.production("asmline : SYMBOL EOL")
+def asmline_label_colon(p):
+    return (p[0].getstr(), None)
+
+@_parser.production("asmline : EOL")
+def asmline_empty(p):
+    return (None, None)
+
+@_parser.production("asminst : OPCODE0")
+def opcode0(p):
+    return (p[0], None, None)
+
+@_parser.production("asminst : OPCODE1 am")
+def opcode1(p):
+    return (p[0], p[1], None)
+
+@_parser.production("asminst : OPCODE2 am COMMA am")
+def opcode2(p):
+    return (p[0], p[1], p[3])
+
+@_parser.production("am : OPENSB GREG PLUS expression CLOSESB")
+@_parser.production("am : OPENSB GREG MINUS expression CLOSESB")
+def am_ind_reg_disp(p):
+    return (p[1], p[2], p[3])
+
+@_parser.production("am : OPENSB GREG CLOSESB")
+@_parser.production("am : OPENSB expression CLOSESB")
+def am_ind(p):
+    return p[1]
+
+@_parser.production("am : expression")
+def am_lit(p):
+    return p[0]
+
+@_parser.production("am : GREG")
+@_parser.production("am : SREG")
+@_parser.production("am : STACK")
+def am_reg_stack(p):
+    return p[0]
+
+@_parser.production("expression : OPENRB expression CLOSERB")
+def expression_parens(p):
+    return p[1]
+
+def do_binop(op, a, b):
+    an = int(a)
+    bn = int(b)
+    if op == "PLUS":
+        return an+bn
+    elif op == "MINUS":
+        return an-bn
+    if op == "STAR":
+        return an*bn
+    elif op == "SLASH":
+        return an/bn
+
+@_parser.production("expression : expression binop expression")
+def expression_binop(p):
+    a, op, b = tuple(p)
+    if a.gettokentype() == b.gettokentype() == "NUMBER":
+        result = do_binop(op.gettokentype(), a.getstr(), b.getstr())
+        return Token("NUMBER", str(result), a.getsourcepos())
+    return (op, a, b)
+
+@_parser.production("register : GREG")
+@_parser.production("register : SREG")
+@_parser.production("register : STACK")
+def expression_register(p):
+    return p[0]
+
+@_parser.production("expression : register")
+def expression_number(p):
+    return p[0]
+
+@_parser.production("expression : NUMBER")
+def expression_number(p):
+    return p[0]
+
+@_parser.production("binop : PLUS")
+@_parser.production("binop : MINUS")
+@_parser.production("binop : STAR")
+@_parser.production("binop : SLASH")
+def expression_parens(p):
+    return p[0]
+
+parser = _parser.build()
+
+
+def assemble(filename):
+    with open(filename, "r") as f:
+        text = f.read()
+        tokens = list(lexer.lex(text))
+        #print(tokens)
+        #print(parser.parse(iter(tokens)))
+        for instr in parser.parse(iter(tokens)):
+            print(instr)
+        #for token in lexer.lex(text):
+        #    print(token.source_pos, token)
+
+
+if __name__ == '__main__':
+    import sys
+    
+    for f in sys.argv[1:]:
+        assemble(f)
+
+# vim:et:sw=4:ts=4:sts=4:

samples/sample.asm

@@ -0,0 +1,9 @@
+;
+        SET A, 0
+l1:     SET B, 1
+l2      ADD A, B
+        XOR [A+1+2+3], [100+23]
+        XOR [B], 465
+        INT 1+2
+;
+