#!/usr/bin/env python3
"""Turn the gdb wait-object dumps into a table, discarding what does not check out.

The two waiting functions do not put the same thing in %rbx (see
freeze_waitobj.sh), so they are parsed separately:

    Wait          rbx = this           -> [rbx]        is the vtable
    WaitMultiple  rbx = XObject**      -> [[rbx+8i]]   is object i's vtable
                  ebp = count          -> entries past the count are garbage

Every reading is validated the same way: gdb's `info symbol` must resolve it to
a `vtable for ...` symbol. A polymorphic object's first word always is one, so
anything else is a misread and is COUNTED but not interpreted. That check is
what the reading is worth -- without it a stale register looks like a result.
"""
import re, sys, collections

VT = re.compile(r'vtable for ([\w:]+) \+ (\d+)')
HDR = re.compile(r'=== (\w+) T(\d+) (Wait|WaitMultiple) f(\d+) ===')

def parse(tag):
    """-> list of (thread, kind, count, [vtable-or-None per slot])"""
    try:
        txt = open('/tmp/fz-obj-%s.txt' % tag, errors='replace').read()
    except FileNotFoundError:
        return []
    out, cur = [], None
    for line in txt.splitlines():
        line = line.replace('(gdb) ', '')
        h = HDR.search(line)
        if h:
            if cur: out.append(cur)
            cur = dict(th=h.group(2), kind=h.group(3), count=None, slots=[], bad=0)
            continue
        if not cur: continue
        m = re.search(r'rbp\s+0x[0-9a-f]+\s+(\d+)', line)
        if m: cur['count'] = int(m.group(1)) & 0xffffffff
        if 'info symbol' in line or line.startswith('$'): continue
        v = VT.search(line)
        if v:
            cur['slots'].append(v.group(1))
        elif 'No symbol matches' in line:
            cur['slots'].append(None); cur['bad'] += 1
    if cur: out.append(cur)
    return out

def report(tag):
    recs = parse(tag)
    print('=== %s: %d wait frames ===' % (tag, len(recs)))
    if not recs: return collections.Counter()
    tally = collections.Counter()
    for r in recs:
        n = r['count'] if r['kind'] == 'WaitMultiple' and r['count'] else len(r['slots'])
        n = min(n, len(r['slots']))
        live = r['slots'][:n]
        for s in live:
            tally[s if s else '<unresolved>'] += 1
        print('  T%-4s %-13s count=%-4s %s' % (
            r['th'], r['kind'], r['count'] if r['count'] is not None else '-',
            ', '.join(s or '?' for s in live) or '(nothing readable)'))
    print('  --- objects waited on:')
    for k, c in tally.most_common():
        print('      %-45s %d' % (k, c))
    return tally

if __name__ == '__main__':
    tallies = {t: report(t) for t in (sys.argv[1:] or ['healthy'])}
    if len(tallies) > 1:
        a, b = list(tallies)
        print('=== %s -> %s ===' % (a, b))
        keys = set(tallies[a]) | set(tallies[b])
        for k in sorted(keys):
            x, y = tallies[a][k], tallies[b][k]
            print('   %-45s %3d -> %-3d %s' % (k, x, y, '' if x == y else '  CHANGED'))