forked from jtauber/dcpu16py
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathasm.py
executable file
·163 lines (134 loc) · 6.16 KB
/
asm.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
#!/usr/bin/env python
from __future__ import print_function
import struct
import re
import sys
import argparse
import os
import codecs
def disjunction(*lst):
"make a uppercase/lowercase disjunction out of a list of strings"
return "|".join([item.upper() for item in lst] + [item.lower() for item in lst])
BASIC_INSTRUCTIONS = disjunction("SET", "ADD", "SUB", "MUL", "DIV", "MOD", "SHL", "SHR", "AND", "BOR", "XOR", "IFE", "IFN", "IFG", "IFB")
GENERAL_REGISTERS = disjunction("A", "B", "C", "X", "Y", "Z", "I", "J")
ALL_REGISTERS = disjunction("A", "B", "C", "X", "Y", "Z", "I", "J", "POP", "PEEK", "PUSH", "SP", "PC", "O")
def operand_re(prefix):
return """
( # operand
(?P<""" + prefix + """register>""" + ALL_REGISTERS + """) # register
|
(\[\s*(?P<""" + prefix + """register_indirect>""" + GENERAL_REGISTERS + """)\s*\]) # register indirect
|
(\[\s*(0x(?P<""" + prefix + """hex_indexed>[0-9A-Fa-f]{1,4}))\s*\+\s*(?P<""" + prefix + """hex_indexed_index>""" + GENERAL_REGISTERS + """)\s*\]) # hex indexed
|
(\[\s*(?P<""" + prefix + """decimal_indexed>\d+)\s*\+\s*(?P<""" + prefix + """decimal_indexed_index>""" + GENERAL_REGISTERS + """)\s*\]) # decimal indexed
|
(\[\s*(?P<""" + prefix + """label_indexed>\w+)\s*\+\s*(?P<""" + prefix + """label_indexed_index>""" + GENERAL_REGISTERS + """)\s*\]) # label indexed
|
(\[\s*(0x(?P<""" + prefix + """hex_indirect>[0-9A-Fa-f]{1,4}))\s*\]) # hex indirect
|
(\[\s*(?P<""" + prefix + """decimal_indirect>\d+)\s*\]) # decimal indirect
|
(0x(?P<""" + prefix + """hex_literal>[0-9A-Fa-f]{1,4})) # hex literal
|
(\[\s*(?P<""" + prefix + """label_indirect>\w+)\s*\]) # label indirect
|
(?P<""" + prefix + """decimal_literal>\d+) # decimal literal
|
(?P<""" + prefix + """label>\w+) # label+
)
"""
line_regex = re.compile(r"""^\s*
(:(?P<label>\w+))? # label
\s*
(
(
(?P<basic>""" + BASIC_INSTRUCTIONS + """) # basic instruction
\s+""" + operand_re("op1_") + """\s*,\s*""" + operand_re("op2_") + """
)
|(
(?P<nonbasic>JSR|jsr) # non-basic instruction
\s+""" + operand_re("op3_") + """
)
|(
(DAT|dat) # data
\s+(?P<data>("[^"]*"|0x[0-9A-Fa-f]{1,4}|\d+)(,\s*("[^"]*"|0x[0-9A-Fa-f]{1,4}|\d+))*)
)
)?
\s*
(?P<comment>;.*)? # comment
$""", re.X)
IDENTIFIERS = {"A": 0x0, "B": 0x1, "C": 0x2, "X": 0x3, "Y": 0x4, "Z": 0x5, "I": 0x6, "J": 0x7, "POP": 0x18, "PEEK": 0x19, "PUSH": 0x1a, "SP":0x1b, "PC": 0x1C, "O": 0x1D}
OPCODES = {"SET": 0x1, "ADD": 0x2, "SUB": 0x3, "MUL": 0x4, "DIV": 0x5, "MOD": 0x6, "SHL": 0x7, "SHR": 0x8, "AND": 0x9, "BOR": 0xA, "XOR": 0xB, "IFE": 0xC, "IFN": 0xD, "IFG": 0xE, "IFB": 0xF}
def clamped_value(l):
return (0x20 + l, None) if l < 0x20 else (0x1F, l)
ADDR_MAP = {
"register": lambda t,v: (IDENTIFIERS[t.upper()], None),
"register_indirect": lambda t,v: (0x08 + IDENTIFIERS[t.upper()], None),
"hex_indexed_index": lambda t,v: (0x10 + IDENTIFIERS[t.upper()], int(v, 16)),
"decimal_indexed_index": lambda t,v: (0x10 + IDENTIFIERS[t.upper()], int(v, 16)),
"label_indexed_index": lambda t,v: (0x10 + IDENTIFIERS[t.upper()], v),
"hex_indirect": lambda t,v: (0x1E, int(t, 16)),
"decimal_indirect": lambda t,v: (0x1E, int(t)),
"hex_literal": lambda t,v: clamped_value(int(t, 16)),
"decimal_literal": lambda t,v: clamped_value(int(t)),
"label_indirect": lambda t,v: (0x1E, t),
"label": lambda t,v: (0x1F, t),
}
def handle(token_dict, prefix):
token = [t for t in token_dict.keys() if t.startswith(prefix) and token_dict[t] is not None][0]
suffix = token[len(prefix):]
v = token_dict[token[:token.rfind("_index")]] if token.endswith("_index") else None
return ADDR_MAP[suffix](token_dict[token], v)
def report_error(filename, lineno, error):
print("%s:%i: %s" % (filename, lineno, error), file=sys.stderr)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="DCPU-16 assembler")
parser.add_argument("-o", default="a.obj", help="Place the output into FILE", metavar="FILE")
parser.add_argument("input", help="File with DCPU assembly code")
args = parser.parse_args()
program = []
labels = {}
for lineno, line in enumerate(open(args.input), start=1):
if lineno == 1:
line = line.lstrip(codecs.BOM_UTF8)
mo = line_regex.match(line)
if mo is None:
report_error(args.input, lineno, "Syntax error: '%s'" % line.strip())
break
token_dict = mo.groupdict()
if token_dict is None:
report_error(args.input, lineno, "Syntax error: '%s'" % line.strip())
break
if token_dict["label"] is not None:
labels[token_dict["label"]] = len(program)
o = x = y = None
if token_dict["basic"] is not None:
o = OPCODES[token_dict["basic"].upper()]
a, x = handle(token_dict, "op1_")
b, y = handle(token_dict, "op2_")
elif token_dict["nonbasic"] is not None:
o, a = 0x00, 0x01
b, y = handle(token_dict, "op3_")
elif token_dict["data"] is not None:
for datum in re.findall("""("[^"]*"|0x[0-9A-Fa-f]{1,4}|\d+)""", token_dict["data"]):
if datum.startswith("\""):
program.extend(ord(ch) for ch in datum[1:-1])
elif datum.startswith("0x"):
program.append(int(datum[2:], 16))
else:
program.append(int(datum))
if o is not None:
program.append(((b << 10) + (a << 4) + o))
if x is not None:
program.append(x)
if y is not None:
program.append(y)
try:
with open(args.o, "wb") as f:
for word in program:
if isinstance(word, str):
word = labels[word]
f.write(struct.pack(">H", word))
except KeyError:
os.remove(args.o)