TeslaRel410/emulator/firmware-decomp/derive860.py

"""Empirically derive the i860 opcode table from matched .S (PGI/AS860 assembly)
and .O (COFF machine code) pairs. Byte-accounting is proven correct by
cross-checking every .S label against its .O symbol offset; only then is the
op6->mnemonic harvest trusted."""
import sys, struct, re, glob, os
sys.path.insert(0, r'C:\VWE\TeslaRel410\emulator\firmware-decomp')
from coff860 import parse

DATASZ = {'.long':4, '.word':4, '.int':4, '.float':4, '.single':4,
          '.double':8, '.short':2, '.half':2, '.byte':1, '.string':None}

def parse_S(path):
    """Return (labels{name:off}, instrs[(off,mnem,line)]) for the .text section."""
    labels, instrs = {}, []
    off = 0; sect = '.text'; in_text = True
    for raw in open(path, encoding='latin1'):
        line = raw.split('//', 1)[0].rstrip()
        s = line.strip()
        if not s:
            continue
        # label(s): possibly "name:" / "name::" possibly followed by an instr
        while True:
            m = re.match(r'^([A-Za-z_.$][\w.$]*)::?\s*(.*)$', s)
            if m and (m.group(2) == '' or not m.group(2).startswith('.')) and ':' in s[:m.end(1)+2]:
                # confirm it's really a label (colon right after the name)
                after = s[m.end(1):]
                if after.startswith('::') or after.startswith(':'):
                    if in_text: labels[m.group(1)] = off
                    s = after.lstrip(':').strip()
                    if not s: break
                    continue
            break
        if not s:
            continue
        if s.startswith('.'):
            d = s.split()[0].lower()
            if d in ('.text',): sect='.text'; in_text=True
            elif d in ('.data','.bss','.section'): sect=d; in_text=False
            elif d == '.align' and in_text:
                n = int(s.split()[1]); off = (off + n - 1) & ~(n - 1)
            elif d in DATASZ and in_text:
                sz = DATASZ[d]
                if sz is None:  # .string -> count bytes incl NUL
                    txt = s[s.index('"')+1:s.rindex('"')]
                    off += len(txt.encode('latin1').decode('unicode_escape')) + 1
                else:
                    vals = s[len(d):].split(',')
                    off += sz * len([v for v in vals if v.strip()])
            # other directives: no size
            continue
        if in_text:
            mnem = s.split()[0]
            instrs.append((off, mnem, s))
            off += 4
    return labels, instrs

def load_text(opath):
    o = parse(opath); d = open(opath, 'rb').read()
    text = syms = None
    for (name, vaddr, size, scnptr, nreloc, sf) in o['sections']:
        if name == '.text': text = d[scnptr:scnptr+size]
    syms = {nm: v for (nm, v, sn, ty, sc, na) in o['syms'] if sn == 1 and sc in (2,3)}
    return text, syms

def derive(spath, opath, table):
    labels, instrs = parse_S(spath)
    text, syms = load_text(opath)
    # cross-check label offsets vs symbol table
    common = [k for k in labels if k in syms]
    good = [k for k in common if labels[k] == syms[k]]
    bad  = [(k, labels[k], syms[k]) for k in common if labels[k] != syms[k]]
    tag = os.path.basename(opath)
    print(f"[{tag}] instrs={len(instrs)} textwords={len(text)//4} "
          f"labels_ok={len(good)}/{len(common)}", end='')
    if bad:
        print(f"  MISALIGNED e.g. {bad[:3]}")
        return False
    print("  ALIGNED")
    for (off, mnem, line) in instrs:
        if off + 4 > len(text): break
        w = struct.unpack_from('<I', text, off)[0]
        op6 = (w >> 26) & 0x3f
        table.setdefault(op6, {}).setdefault(mnem, 0)
        table[op6][mnem] += 1
    return True

if __name__ == '__main__':
    base = r'C:\VWE\TeslaRel410\sda4\DPL3\VRENDER\AS860'
    pairs = []
    for s in glob.glob(os.path.join(base, '*.S')):
        o = s[:-2] + '.O'
        if os.path.exists(o): pairs.append((s, o))
    table = {}
    for s, o in sorted(pairs):
        try: derive(s, o, table)
        except Exception as e: print(f"[{os.path.basename(o)}] ERROR {e}")
    print("\n=== derived op6 -> mnemonic(count) ===")
    for op6 in sorted(table):
        items = sorted(table[op6].items(), key=lambda x: -x[1])
        print(f"  {op6:#04x} ({op6:06b}): " + ", ".join(f"{m}×{c}" for m,c in items))