#!/usr/bin/env python3
"""symcrash.py -- turn a tester's [crash] line into function names.

BTCrashFilter (btl4main.cpp) writes module-relative offsets into the day log:

    [crash] UNHANDLED EXCEPTION code=0xc0000005 addr=0xb8260 (btl4+0x8260) ...
    [crash] stack: btl4+0x8260 btl4+0xfe7ed 0x763ffcc9 ...

Those offsets mean nothing without the symbols for the EXACT build that produced
them -- which is why every session header carries `build=4.11.<n> (<hash>)` and
why the linker .map is archived per build alongside the PDB.

Usage:
    python tools/symcrash.py <btl4.map> "btl4+0x8260"
    python tools/symcrash.py <btl4.map> <tester.log>       (scans for [crash])

Resolution is nearest-preceding-symbol, so the answer is the function the
address falls INSIDE, plus the byte offset into it.  Addresses outside the
module (kernel32, ntdll) are passed through untouched -- they are not ours.
"""
import re
import sys


def load_map(path):
    """Return (sorted [(rva, name)], preferred_base)."""
    syms = []
    base = None
    with open(path, "r", encoding="utf-8", errors="replace") as fh:
        for line in fh:
            if base is None:
                m = re.search(r"Preferred load address is ([0-9A-Fa-f]+)", line)
                if m:
                    base = int(m.group(1), 16)
                    continue
            # " 0001:00000a10  ?Foo@Bar@@QAEXXZ  00401a10 f   thing.obj"
            m = re.match(r"\s+[0-9A-Fa-f]{4}:[0-9A-Fa-f]{8}\s+(\S+)\s+([0-9A-Fa-f]{8,16})\s",
                         line)
            if m and base is not None:
                syms.append((int(m.group(2), 16) - base, m.group(1)))
    syms.sort(key=lambda s: s[0])
    return syms, base


def resolve(syms, rva):
    lo, hi, best = 0, len(syms) - 1, None
    while lo <= hi:                      # nearest preceding symbol
        mid = (lo + hi) // 2
        if syms[mid][0] <= rva:
            best = syms[mid]
            lo = mid + 1
        else:
            hi = mid - 1
    return best


def main():
    if len(sys.argv) < 3:
        sys.exit(__doc__)
    syms, base = load_map(sys.argv[1])
    if not syms:
        sys.exit("no symbols parsed from %s -- is it a linker .map?" % sys.argv[1])
    print("%d symbols, preferred base 0x%x\n" % (len(syms), base))

    arg = sys.argv[2]
    try:                                  # a log file?
        text = open(arg, "r", encoding="utf-8", errors="replace").read()
    except OSError:
        text = arg                        # ...no, a literal offset

    for line in text.splitlines() or [text]:
        if "btl4+" not in line:
            continue
        if line.lstrip().startswith("[crash]"):
            print(line.strip())
        for off in re.findall(r"btl4\+0x([0-9A-Fa-f]+)", line):
            rva = int(off, 16)
            hit = resolve(syms, rva)
            if hit is None:
                print("    btl4+0x%-8x  <before first symbol>" % rva)
            else:
                print("    btl4+0x%-8x  %s +0x%x" % (rva, hit[1], rva - hit[0]))
        print()


if __name__ == "__main__":
    main()