pokecrystal/preprocessor.py

556 lines
12 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
from extras.crystal import command_classes, \
Warp, \
XYTrigger, \
Signpost, \
PeopleEvent, \
DataByteWordMacro, \
PointerLabelBeforeBank, \
PointerLabelAfterBank, \
MoneyByteParam, \
ItemFragment, \
TextEndingCommand, \
text_command_classes
macros = command_classes + \
[
Warp,
XYTrigger,
Signpost,
PeopleEvent,
DataByteWordMacro,
ItemFragment,
] + [x[1] for x in text_command_classes]
chars = {
"": 0x05,
"": 0x06,
"": 0x07,
"": 0x08,
"": 0x09,
"": 0x0A,
"": 0x0B,
"": 0x0C,
"": 0x0D,
"": 0x0E,
"": 0x0F,
"": 0x10,
"": 0x11,
"": 0x12,
"": 0x13,
"": 0x19,
"": 0x1A,
"": 0x1B,
"": 0x1C,
"": 0x26,
"": 0x27,
"": 0x28,
"": 0x29,
"": 0x2A,
"": 0x2B,
"": 0x2C,
"": 0x2D,
"": 0x2E,
"": 0x2F,
"": 0x30,
"": 0x31,
"": 0x32,
"": 0x33,
"": 0x34,
"": 0x3A,
"": 0x3B,
"": 0x3C,
"": 0x3D,
"": 0x3E,
"": 0x40,
"": 0x41,
"": 0x42,
"": 0x43,
"": 0x44,
"": 0x45,
"": 0x46,
"": 0x47,
"": 0x48,
"": 0x80,
"": 0x81,
"": 0x82,
"": 0x83,
"": 0x84,
"": 0x85,
"": 0x86,
"": 0x87,
"": 0x88,
"": 0x89,
"": 0x8A,
"": 0x8B,
"": 0x8C,
"": 0x8D,
"": 0x8E,
"": 0x8F,
"": 0x90,
"": 0x91,
"": 0x92,
"": 0x93,
"": 0x94,
"": 0x95,
"": 0x96,
"": 0x97,
"": 0x98,
"": 0x99,
"": 0x9A,
"": 0x9B,
"": 0x9C,
"": 0x9D,
"": 0x9E,
"": 0x9F,
"": 0xA0,
"": 0xA1,
"": 0xA2,
"": 0xA3,
"": 0xA4,
"": 0xA5,
"": 0xA6,
"": 0xA7,
"": 0xA8,
"": 0xA9,
"": 0xAA,
"": 0xAB,
"": 0xAC,
"": 0xAD,
"": 0xAE,
"": 0xAF,
"": 0xB0,
"": 0xB1,
"": 0xB2,
"": 0xB3,
"": 0xB4,
"": 0xB5,
"": 0xB6,
"": 0xB7,
"": 0xB8,
"": 0xB9,
"": 0xBA,
"": 0xBB,
"": 0xBC,
"": 0xBD,
"": 0xBE,
"": 0xBF,
"": 0xC0,
"": 0xC1,
"": 0xC2,
"": 0xC3,
"": 0xC4,
"": 0xC5,
"": 0xC6,
"": 0xC7,
"": 0xC8,
"": 0xC9,
"": 0xCA,
"": 0xCB,
"": 0xCC,
"": 0xCD,
"": 0xCE,
"": 0xCF,
"": 0xD0,
"": 0xD1,
"": 0xD2,
"": 0xD3,
"": 0xD4,
"": 0xD5,
"": 0xD6,
"": 0xD7,
"": 0xD8,
"": 0xD9,
"": 0xDA,
"": 0xDB,
"": 0xDC,
"": 0xDD,
"": 0xDE,
"": 0xDF,
"": 0xE0,
"": 0xE1,
"": 0xE2,
"": 0xE3,
"@": 0x50,
"#": 0x54,
"": 0x75,
"": 0x79,
"": 0x7A,
"": 0x7B,
"": 0x7C,
"": 0x7D,
"": 0x7E,
"": 0x74,
" ": 0x7F,
"A": 0x80,
"B": 0x81,
"C": 0x82,
"D": 0x83,
"E": 0x84,
"F": 0x85,
"G": 0x86,
"H": 0x87,
"I": 0x88,
"J": 0x89,
"K": 0x8A,
"L": 0x8B,
"M": 0x8C,
"N": 0x8D,
"O": 0x8E,
"P": 0x8F,
"Q": 0x90,
"R": 0x91,
"S": 0x92,
"T": 0x93,
"U": 0x94,
"V": 0x95,
"W": 0x96,
"X": 0x97,
"Y": 0x98,
"Z": 0x99,
"(": 0x9A,
")": 0x9B,
":": 0x9C,
";": 0x9D,
"[": 0x9E,
"]": 0x9F,
"a": 0xA0,
"b": 0xA1,
"c": 0xA2,
"d": 0xA3,
"e": 0xA4,
"f": 0xA5,
"g": 0xA6,
"h": 0xA7,
"i": 0xA8,
"j": 0xA9,
"k": 0xAA,
"l": 0xAB,
"m": 0xAC,
"n": 0xAD,
"o": 0xAE,
"p": 0xAF,
"q": 0xB0,
"r": 0xB1,
"s": 0xB2,
"t": 0xB3,
"u": 0xB4,
"v": 0xB5,
"w": 0xB6,
"x": 0xB7,
"y": 0xB8,
"z": 0xB9,
"Ä": 0xC0,
"Ö": 0xC1,
"Ü": 0xC2,
"ä": 0xC3,
"ö": 0xC4,
"ü": 0xC5,
"'d": 0xD0,
"'l": 0xD1,
"'m": 0xD2,
"'r": 0xD3,
"'s": 0xD4,
"'t": 0xD5,
"'v": 0xD6,
"'": 0xE0,
"-": 0xE3,
"?": 0xE6,
"!": 0xE7,
".": 0xE8,
"&": 0xE9,
"é": 0xEA,
"": 0xEB,
"": 0xEF,
"¥": 0xF0,
"×": 0xF1,
"/": 0xF3,
",": 0xF4,
"": 0xF5,
"0": 0xF6,
"1": 0xF7,
"2": 0xF8,
"3": 0xF9,
"4": 0xFA,
"5": 0xFB,
"6": 0xFC,
"7": 0xFD,
"8": 0xFE,
"9": 0xFF
}
def separate_comment(l):
""" Separates asm and comments on a single line.
"""
asm = ""
comment = None
in_quotes = False
in_comment = False
# token either belongs to the line or to the comment
for token in l:
if in_comment:
comment += token
elif in_quotes and token != "\"":
asm += token
elif in_quotes and token == "\"":
in_quotes = False
asm += token
elif not in_quotes and token == "\"":
in_quotes = True
asm += token
elif not in_quotes and token != "\"":
if token == ";":
in_comment = True
comment = ";"
else:
asm += token
return asm, comment
def quote_translator(asm):
""" Writes asm with quoted text translated into bytes.
"""
# split by quotes
asms = asm.split("\"")
# skip asm that actually does use ASCII in quotes
lowasm = asms[0].lower()
if "section" in lowasm \
or "include" in lowasm \
or "incbin" in lowasm:
sys.stdout.write(asm)
return
even = False
i = 0
for token in asms:
i = i + 1
if even:
# token is a string to convert to byte values
while len(token):
# read a single UTF-8 codepoint
char = token[0]
if ord(char) >= 0xFC:
char = char + token[1:6]
token = token[6:]
elif ord(char) >= 0xF8:
char = char + token[1:5]
token = token[5:]
elif ord(char) >= 0xF0:
char = char + token[1:4]
token = token[4:]
elif ord(char) >= 0xE0:
char = char + token[1:3]
token = token[3:]
elif ord(char) >= 0xC0:
char = char + token[1:2]
token = token[2:]
else:
token = token[1:]
# certain apostrophe-letter pairs are only a single byte
if char == "'" and len(token) > 0 and \
(token[0] == "d" or \
token[0] == "l" or \
token[0] == "m" or \
token[0] == "r" or \
token[0] == "s" or \
token[0] == "t" or \
token[0] == "v"):
char = char + token[0]
token = token[1:]
sys.stdout.write("${0:02X}".format(chars[char]))
if len(token):
sys.stdout.write(", ")
# if not even
else:
sys.stdout.write(token)
even = not even
return
def extract_token(asm):
token = asm.split(" ")[0].replace("\t", "").replace("\n", "")
return token
def macro_test(asm):
""" Returns a matching macro, or None/False.
"""
# macros are determined by the first symbol on the line
token = extract_token(asm)
# check against all names
for macro in macros:
if macro.macro_name == token:
return macro, token
return None, None
def macro_translator(macro, token, line):
""" Converts a line with a macro into a rgbasm-compatible line.
"""
assert macro.macro_name == token, "macro/token mismatch"
original_line = line
# remove trailing newline
if line[-1] == "\n":
line = line[:-1]
else:
original_line += "\n"
# remove first tab
has_tab = False
if line[0] == "\t":
has_tab = True
line = line[1:]
# remove duplicate whitespace (also trailing)
line = " ".join(line.split())
params = []
# check if the line has params
if " " in line:
# split the line into separate parameters
params = line.replace(token, "").split(",")
# check if there are no params (redundant)
if len(params) == 1 and params[0] == "":
raise Exception, "macro has no params?"
# write out a comment showing the original line
sys.stdout.write("; original_line: " + original_line)
# "db" is a macro because of TextEndingCommand
# rgbasm can handle "db" so no preprocessing is required
# (don't check its param count)
if macro.macro_name == "db" and macro == TextEndingCommand:
sys.stdout.write(original_line)
return
# certain macros don't need an initial byte written
# do: all scripting macros
# don't: signpost, warp_def, person_event, xy_trigger
if not macro.override_byte_check:
sys.stdout.write("db $%.2x\n" % (macro.id))
# --- long-winded sanity check goes here ---
# sanity check... this won't work because PointerLabelBeforeBank shows
# up as two params, so these two lengths will always be different.
#assert len(params) == len(macro.param_types), \
# "mismatched number of parameters on this line: " + \
# original_line
# v2 sanity check :) although it sorta sucks that this loop happens twice?
allowed_length = 0
for (index, param_type) in macro.param_types.items():
param_klass = param_type["class"]
if param_klass.byte_type == "db":
allowed_length += 1 # just one value
elif param_klass.byte_type == "dw":
if param_klass.size == 2:
allowed_length += 1 # just label
elif param_klass == MoneyByteParam:
allowed_length += 1
elif param_klass.size == 3:
allowed_length += 2 # bank and label
else:
raise Exception, "dunno what to do with a macro param with a size > 3"
else:
raise Exception, "dunno what to do with this non db/dw macro param: " + \
str(param_klass) + " in line: " + original_line
assert len(params) == allowed_length, \
"mismatched number of parameters on this line: " + \
original_line
# --- end of ridiculously long sanity check ---
index = 0
while index < len(macro.param_types):
param_type = macro.param_types[index]
description = param_type["name"]
param_klass = param_type["class"]
byte_type = param_klass.byte_type # db or dw
size = param_klass.size
param = params[index].strip()
# param_klass.to_asm() won't work here because it doesn't
# include db/dw.
# some parameters are really multiple types of bytes
if (byte_type == "dw" and size != 2) or \
(byte_type == "db" and size != 1):
sys.stdout.write("; " + description + "\n")
if size == 3 and issubclass(param_klass, PointerLabelBeforeBank):
# write the bank first
sys.stdout.write("db " + params[index] + "\n")
# write the pointer second
sys.stdout.write("dw " + params[index+1] + "\n")
index += 2
elif size == 3 and issubclass(param_klass, PointerLabelAfterBank):
# write the pointer first
sys.stdout.write("dw " + params[index] + "\n")
# write the bank second
sys.stdout.write("db " + params[index+1] + "\n")
index += 2
elif size == 3 and issubclass(param_klass, MoneyByteParam):
sys.stdout.write("db " + MoneyByteParam.from_asm(params[index]) + "\n")
index += 1
else:
raise Exception, "dunno what to do with this macro " + \
"param (" + str(param_klass) + ") " + "on this line: " + \
original_line
# or just print out the byte
else:
sys.stdout.write(byte_type + " " + param + " ; " + description + "\n")
index += 1
for l in sys.stdin:
# strip and store any comment on this line
if ";" in l:
asm, comment = separate_comment(l)
else:
asm = l
comment = None
# convert text to bytes when a quote appears (not in a comment)
if "\"" in asm:
quote_translator(asm)
# check against other preprocessor features
else:
macro, token = macro_test(asm)
if macro:
macro_translator(macro, token, asm)
else:
sys.stdout.write(asm)
# show line comment
if comment != None:
sys.stdout.write(comment)