#!/usr/bin/env python3
"""verify_wizards.py — re-derive the full commit-history extraction from live git
and compare every committed artifact (CSV/JSON/MD) against it. Exits 0 only when
every check matches exactly. No stubs: every number is re-derived from git."""
import subprocess, sys, json, csv, collections, os

REPO = '/root/troupe-standup'
OUT = '/root/troupe-standup/wizard-work/ledger'
CSV = os.path.join(OUT, '2026-10-25-git-history.csv')
JSON = os.path.join(OUT, '2026-10-25-git-history.json')
MD = os.path.join(OUT, '2026-10-25-git-history.md')

fails = []
def ok(msg):
    print('PASS: ' + msg)
def bad(msg):
    print('FAIL: ' + msg)
    fails.append(msg)

def git(*args):
    return subprocess.run(['git', '-C', REPO] + list(args),
                          check=True, capture_output=True, text=True).stdout

def file_count(hashfull):
    out = git('show', '--name-status', '--format=', hashfull)
    n = 0
    for l in out.split('\n'):
        if l and not l.startswith('only'):
            n += 1
    return n

# ---- Live ground truth (re-derived from git, nothing trusted) ----
commits = []
for line in git('log', '--date=iso-strict',
                '--format=%x1f%H%x1f%h%x1f%an%x1f%ae%x1f%aI%x1f%s').split('\n'):
    if not line:
        continue
    f = line.split('\x1f')
    assert len(f) == 7, line
    commits.append({'hash': f[1], 'short': f[2], 'name': f[3], 'email': f[4],
                    'date': f[5], 'subject': f[6]})
for c in commits:
    c['files'] = file_count(c['hash'])

N = len(commits)
earliest = min(c['date'] for c in commits)
latest = max(c['date'] for c in commits)
first_commit = commits[-1]['hash']
last_commit = commits[0]['hash']
count_by_author = collections.Counter((c['name'], c['email']) for c in commits)
census = [{'name': n, 'email': e, 'count': cnt}
          for (n, e), cnt in sorted(count_by_author.items(),
                                    key=lambda kv: (-kv[1], kv[0][0]))]
top50 = sorted(commits, key=lambda c: -c['files'])[:50]

# ---- Load committed artifacts ----
def load_csv():
    with open(CSV, encoding='utf-8') as fh:
        return list(csv.DictReader(fh))

def load_json():
    with open(JSON, encoding='utf-8') as fh:
        return json.load(fh)

def load_md_top50():
    rows = []
    with open(MD, encoding='utf-8') as fh:
        for line in fh:
            if line.startswith('| 1 |') or (line.startswith('| ') and '|' in line):
                pass
    # robust: parse any line starting with '| <rank> |'
    import re
    pat = re.compile(r'^\|\s*(\d+)\s*\|\s*`?([0-9a-f]+)`?\s*\|\s*([^|]+)\|\s*([^|]+)\|\s*([^|]+)\|\s*(\d+)\s*\|')
    out = []
    with open(MD, encoding='utf-8') as fh:
        for line in fh:
            m = pat.match(line)
            if m:
                out.append({'rank': int(m.group(1)), 'hash': m.group(2),
                           'author': m.group(3).strip(), 'date': m.group(4).strip(),
                           'subject': m.group(5).strip(), 'files': int(m.group(6))})
    return out

csv_rows = load_csv()
json_doc = load_json()
md_top50 = load_md_top50()

# ---- Checks ----
# 1. Counts
if len(csv_rows) == N:
    ok('csv data rows = %d == live commit count %d' % (len(csv_rows), N))
else:
    bad('csv data rows = %d, expected %d' % (len(csv_rows), N))
if json_doc.get('commits') == N:
    ok('json commits = %d == live count %d' % (json_doc.get('commits'), N))
else:
    bad('json commits = %r, expected %d' % (json_doc.get('commits'), N))

# 2. Earliest / latest
if earliest == json_doc.get('earliest') == csv_rows[0]['date']:
    ok('earliest = %s' % earliest)
else:
    bad('earliest declared=%r observed=%r' % (json_doc.get('earliest'), earliest))
if latest == json_doc.get('latest') == csv_rows[-1]['date']:
    ok('latest = %s' % latest)
else:
    bad('latest declared=%r observed=%r' % (json_doc.get('latest'), latest))

# 3. First / last commits
if csv_rows[0]['hash'] == last_commit and csv_rows[-1]['hash'] == first_commit:
    ok('csv first/last commits match live HEAD/root')
else:
    bad('csv first/last mismatch: %r / %r' % (csv_rows[0]['hash'], csv_rows[-1]['hash']))
if json_doc.get('first_commit') == first_commit and json_doc.get('last_commit') == last_commit:
    ok('json first/last commits match live')
else:
    bad('json first/last mismatch')

# 4. Field-for-field CSV vs live
bad_rows = 0
for i, c in enumerate(commits, 1):
    r = csv_rows[i-1]
    live = ['%d' % i, c['hash'], c['short'], c['name'], c['email'], c['date'], c['subject'], '%d' % c['files']]
    if [r.get(k) for k in ('rank','hash','short','name','email','date','subject','files')] != live:
        bad_rows += 1
        if bad_rows <= 3:
            bad('csv row %d mismatch: %r' % (i, r))
if bad_rows == 0:
    ok('csv field-for-field matches live derivation for all %d rows' % N)

# 5. JSON rows vs live
jrows = json_doc.get('rows', [])
if len(jrows) == N:
    ok('json rows = %d' % len(jrows))
else:
    bad('json rows = %d, expected %d' % (len(jrows), N))
jbad = 0
for i, c in enumerate(commits, 1):
    j = jrows[i-1]
    live = {'hash': c['hash'], 'short': c['short'], 'name': c['name'],
            'email': c['email'], 'date': c['date'], 'subject': c['subject'],
            'files': c['files']}
    if {k: j.get(k) for k in live} != live:
        jbad += 1
        if jbad <= 3:
            bad('json row %d mismatch' % i)
if jbad == 0:
    ok('json rows field-for-field match live derivation for all %d rows' % N)

# 6. Census
if json_doc.get('census') == census:
    ok('json census matches live derivation (%d authors)' % len(census))
else:
    bad('json census mismatch')

# 7. Top-50 markdown vs live
if len(md_top50) == 50:
    ok('md top-50 rows = %d' % len(md_top50))
else:
    bad('md top-50 rows = %d, expected 50' % len(md_top50))
mismatch = 0
for live50 in top50:
    m = next((x for x in md_top50 if x['rank'] == commits.index(live50) + 1), None)
    # top50 order == md order
    if not m or m['hash'] != live50['short'] or m['author'] != live50['name'] or m['date'] != live50['date'] or m['files'] != live50['files']:
        mismatch += 1
        if mismatch <= 3:
            bad('md top-50 row %d mismatch vs live' % live50['rank'])
if mismatch == 0:
    ok('md Top-50 table matches live re-derivation')

# 8. Root commit present & files count
root = json_doc.get('first_commit')
if root and git('rev-parse','-q','--verify', root + '^{commit}').strip():
    ok('root commit present: %s' % root)
else:
    bad('root commit missing from json or not a commit')

print('')
if fails:
    print('CHECK FAIL: %d check(s) failed.' % len(fails))
    sys.exit(1)
print('CHECK PASS: git commit-history extraction re-derives cleanly against live git.')