# -*- coding: utf-8 -*-
"""WAPT package: offline, read-only HardeningKitty machine baseline audit.

This code runs under WAPT Agent's Python runtime on Windows.
Vendor assets are fetched on the packaging workstation, not on endpoints.
"""
from setuphelpers import *
import csv
import collections
import datetime
import hashlib
import json
import os
import shutil
import subprocess
import sys
import uuid

uninstallkey = []

PACKAGE_NAME = 'comi-audit-hardeningkitty'
AUDIT_SECTION = 'HardeningKitty'
PROGRAM_DATA = os.environ.get('ProgramData', r'C:\ProgramData')
INSTALL_ROOT = os.path.join(PROGRAM_DATA, 'Comitari', 'Audit-HardeningKitty')
REPORT_ROOT = os.path.join(PROGRAM_DATA, 'Comitari', 'Audit-HardeningKitty-Reports')


def _source_directory():
    # WAPT IDE can execute setup.py with a wrapper: verify __file__ before use.
    if '__file__' in globals():
        candidate = os.path.dirname(os.path.abspath(__file__))
        if os.path.isfile(os.path.join(candidate, 'WAPT', 'control')):
            return candidate
    return os.getcwd()


def _read_json(path):
    with open(path, 'r', encoding='utf-8-sig') as fh:
        return json.load(fh)


def _write_json(path, data):
    with open(path, 'w', encoding='utf-8') as fh:
        json.dump(data, fh, ensure_ascii=False, indent=2, sort_keys=True)


def _checksum(path):
    sha = hashlib.sha256()
    with open(path, 'rb') as fh:
        for block in iter(lambda: fh.read(1024 * 1024), b''):
            sha.update(block)
    return sha.hexdigest()


def _verify_vendor(root):
    manifest_path = os.path.join(root, 'vendor-manifest.json')
    if not os.path.isfile(manifest_path):
        raise RuntimeError('Vendor assets missing. Run python tools/vendor_assets.py before building the WAPT package.')
    manifest = _read_json(manifest_path)
    files = manifest.get('files', {})
    if not isinstance(files, dict) or len(files) < 5:
        raise RuntimeError('Invalid vendor manifest; refuse incomplete audit assets.')
    required = ('HardeningKitty.psm1', 'HardeningKitty.psd1', 'LICENSE',
                'lists/hardeningkitty_lists_manifest.psd1',
                'lists/hardeningkitty_lists_manifest.psd1.p7s',
                'lists/finding_list_0x6d69636b_machine.csv')
    for item in required:
        if item not in files:
            raise RuntimeError('Missing required vendor asset: %s' % item)
    root_real = os.path.realpath(root)
    for name, digest in files.items():
        if not isinstance(name, str) or '\\' in name or name.startswith('/') or '..' in name.split('/'):
            raise RuntimeError('Unsafe vendor path: %r' % name)
        dest = os.path.realpath(os.path.join(root, *name.split('/')))
        if not dest.startswith(root_real + os.sep):
            raise RuntimeError('Vendor asset escapes install directory: %r' % name)
        if not os.path.isfile(dest) or _checksum(dest).lower() != str(digest).lower():
            raise RuntimeError('Missing or altered vendor asset: %s' % name)
    return manifest


def _secure_directory(path):
    """Only LocalSystem and local Administrators can access audit assets."""
    if os.name != 'nt':
        return
    # Language-independent SIDs; do not rely on localized group names.
    subprocess.check_call(['icacls.exe', path, '/inheritance:r', '/grant:r',
                           '*S-1-5-18:(OI)(CI)F', '*S-1-5-32-544:(OI)(CI)F',
                           '/T', '/Q'])


def install():
    source = _source_directory()
    vendor = os.path.join(source, 'vendor')
    manifest = _verify_vendor(vendor)
    parent = os.path.dirname(INSTALL_ROOT)
    os.makedirs(parent, exist_ok=True)
    staging = INSTALL_ROOT + '.staging'
    previous = INSTALL_ROOT + '.previous'
    if os.path.isdir(staging):
        shutil.rmtree(staging)
    if os.path.isdir(previous):
        shutil.rmtree(previous)
    shutil.copytree(vendor, staging)
    shutil.copy2(os.path.join(source, 'runner.ps1'), os.path.join(staging, 'runner.ps1'))
    shutil.copy2(os.path.join(source, 'audit_config.json'), os.path.join(staging, 'audit_config.json'))
    _verify_vendor(staging)
    _secure_directory(staging)
    renamed_old = False
    try:
        if os.path.isdir(INSTALL_ROOT):
            os.rename(INSTALL_ROOT, previous)
            renamed_old = True
        os.rename(staging, INSTALL_ROOT)
    except Exception:
        if renamed_old and not os.path.exists(INSTALL_ROOT):
            os.rename(previous, INSTALL_ROOT)
        raise
    finally:
        if os.path.isdir(staging):
            shutil.rmtree(staging)
    if os.path.isdir(previous):
        shutil.rmtree(previous)
    os.makedirs(REPORT_ROOT, exist_ok=True)
    _secure_directory(REPORT_ROOT)
    print('Installed offline HardeningKitty audit assets, commit %s (%s files).' %
          (manifest.get('upstream_commit', 'unknown'), len(manifest['files'])))
    print('No Windows security setting has been modified.')


def uninstall():
    if os.path.isdir(INSTALL_ROOT):
        shutil.rmtree(INSTALL_ROOT)
    print('Removed HardeningKitty audit engine. Historical reports kept in %s' % REPORT_ROOT)


def _powershell_executable():
    windir = os.environ.get('SystemRoot', r'C:\Windows')
    for relative in ((r'Sysnative', 'WindowsPowerShell', 'v1.0', 'powershell.exe'),
                     (r'System32', 'WindowsPowerShell', 'v1.0', 'powershell.exe')):
        candidate = os.path.join(windir, *relative)
        if os.path.isfile(candidate):
            return candidate
    raise RuntimeError('Windows PowerShell 5.1 64-bit not found.')


def _read_report(path, publish_current_values=False):
    with open(path, 'r', encoding='utf-8-sig', newline='') as fh:
        reader = csv.DictReader(fh)
        required = {'ID', 'Category', 'Name', 'Severity', 'Result', 'Recommended', 'TestResult'}
        if not reader.fieldnames or not required.issubset(reader.fieldnames):
            raise RuntimeError('Unexpected HardeningKitty CSV headers: %r' % reader.fieldnames)
        rows = list(reader)
    if not rows:
        raise RuntimeError('HardeningKitty CSV is empty; refuse a false OK.')

    counts = {'passed': 0, 'high': 0, 'medium': 0, 'low': 0, 'unknown': 0, 'total': len(rows)}
    findings = []
    for item in rows:
        level = (item.get('Severity') or '').strip().lower()
        outcome = (item.get('TestResult') or '').strip().lower()
        if outcome == 'passed' and level == 'passed':
            counts['passed'] += 1
            continue
        if outcome != 'passed' and level in ('high', 'medium', 'low'):
            counts[level] += 1
        else:
            counts['unknown'] += 1
            level = 'unknown'
        finding = {
            'id': str(item.get('ID') or ''),
            'category': str(item.get('Category') or ''),
            'name': str(item.get('Name') or ''),
            'severity': level,
            'result': str(item.get('TestResult') or ''),
        }
        # Avoid uploading potentially sensitive local configuration by default.
        if publish_current_values:
            finding['current'] = str(item.get('Result') or '')
            finding['recommended'] = str(item.get('Recommended') or '')
        findings.append(finding)
    counts['compliant_percent'] = round(100.0 * counts['passed'] / counts['total'], 2)
    return counts, findings


def _check_coverage(baseline_path, report_path, counts, findings):
    """Mark tests skipped by HardeningKitty as unknown, never as Passed.

    HardeningKitty can skip a check (e.g. a tool is missing). Such an item
    may be absent from the output CSV. Counting only present rows could give
    a misleading green result, so compare to the original finding list.
    """
    with open(baseline_path, 'r', encoding='utf-8-sig', newline='') as fh:
        expected_rows = list(csv.DictReader(fh))
    with open(report_path, 'r', encoding='utf-8-sig', newline='') as fh:
        actual_rows = list(csv.DictReader(fh))
    if not expected_rows:
        raise RuntimeError('Finding list is empty.')

    def row_key(row):
        return (str(row.get('ID') or '').strip(),
                str(row.get('Name') or '').strip(),
                str(row.get('Category') or '').strip())

    actual = collections.Counter(row_key(row) for row in actual_rows)
    missing = []
    for row in expected_rows:
        key = row_key(row)
        if actual[key]:
            actual[key] -= 1
        else:
            missing.append({
                'id': key[0], 'name': key[1], 'category': key[2],
                'severity': 'unknown', 'result': 'Skipped / no CSV result',
            })
    if missing:
        findings.extend(missing)
        counts['unknown'] += len(missing)
        counts['total'] += len(missing)
    counts['executed'] = len(actual_rows)
    counts['skipped'] = len(missing)
    counts['expected'] = len(expected_rows)
    counts['compliant_percent'] = round(100.0 * counts['passed'] / counts['total'], 2)
    return counts, findings


def _status_from_counts(counts, config):
    if counts['total'] == 0 or counts['unknown']:
        return 'ERROR'
    if counts['high']:
        return 'ERROR' if config['error_on_high'] else 'WARNING'
    if counts['medium'] or (counts['low'] and config['warn_on_low']):
        return 'WARNING'
    return 'OK'


def _shard_findings(findings, bucket_count=16):
    buckets = [[] for i in range(bucket_count)]
    for item in findings:
        # Stable shards, including empty ones: no obsolete audit keys on a later run.
        key = ('%s:%s' % (item['id'], item['name'])).encode('utf-8')
        bucket = int(hashlib.sha256(key).hexdigest()[:8], 16) % bucket_count
        buckets[bucket].append(item)
    return buckets


def _publish_audit(summary, findings, config):
    if not config.get('publish_to_wapt', True):
        return
    wapt = globals().get('WAPT')
    write = getattr(wapt, 'write_audit_data_if_changed', None)
    if not callable(write):
        print('WAPT audit_data unavailable; only audit status and local CSV are published.')
        return

    # Per-metric keys are convenient for SQL reporting on HostAuditData.
    for key in ('status', 'benchmark', 'os_build', 'source', 'upstream_commit', 'last_error',
                'passed', 'high', 'medium', 'low', 'unknown', 'total', 'expected', 'executed', 'skipped', 'compliant_percent'):
        try:
            write(AUDIT_SECTION, key, str(summary[key]), max_count=5, keep_days=120)
        except Exception as exc:
            print('Could not publish WAPT audit metric %s: %s' % (key, exc))

    for index, group in enumerate(_shard_findings(findings)):
        try:
            payload = json.dumps(group, ensure_ascii=False, separators=(',', ':'))
            write(AUDIT_SECTION, 'findings_%02d' % index, payload, max_count=3, keep_days=120)
        except Exception as exc:
            print('Could not publish WAPT audit shard %02d: %s' % (index, exc))

    # Unlike the stable metrics above, store one timestamped observation each run.
    write_current = getattr(wapt, 'write_audit_data', None)
    if callable(write_current):
        try:
            write_current(AUDIT_SECTION, 'last_run_utc', summary['last_run_utc'],
                          max_count=5, keep_days=120)
        except Exception as exc:
            print('Could not publish WAPT audit timestamp: %s' % exc)


def _trim_reports(keep):
    paths = [os.path.join(REPORT_ROOT, name) for name in os.listdir(REPORT_ROOT)
             if name.startswith('run-') and os.path.isdir(os.path.join(REPORT_ROOT, name))]
    paths.sort(key=lambda p: os.path.getmtime(p), reverse=True)
    for path in paths[max(1, int(keep)):]:
        shutil.rmtree(path)


def _audit_impl():
    manifest = _verify_vendor(INSTALL_ROOT)
    config = _read_json(os.path.join(INSTALL_ROOT, 'audit_config.json'))
    if config.get('source') not in ('GPO', 'Intune'):
        raise RuntimeError('audit_config.json source must be GPO or Intune')
    profile = str(config.get('profile', 'auto'))
    # Runner validates the override independently to prevent command injection/traversal.
    if not isinstance(config.get('error_on_high'), bool) or not isinstance(config.get('warn_on_low'), bool):
        raise RuntimeError('Invalid compliance threshold settings.')
    timeout = int(config.get('timeout_seconds', 900))
    if timeout < 30 or timeout > 7200:
        raise RuntimeError('timeout_seconds must be between 30 and 7200.')

    os.makedirs(REPORT_ROOT, exist_ok=True)
    _secure_directory(REPORT_ROOT)
    run_dir = os.path.join(REPORT_ROOT, 'run-' + datetime.datetime.now(datetime.timezone.utc).strftime('%Y%m%d-%H%M%S') + '-' + uuid.uuid4().hex[:8])
    os.makedirs(run_dir, exist_ok=False)
    _secure_directory(run_dir)
    csv_file = os.path.join(run_dir, 'hardeningkitty.csv')
    log_file = os.path.join(run_dir, 'powershell.log')
    metadata_file = os.path.join(run_dir, 'host.json')

    cmd = [_powershell_executable(), '-NoLogo', '-NoProfile', '-NonInteractive',
           '-ExecutionPolicy', 'Bypass', '-File', os.path.join(INSTALL_ROOT, 'runner.ps1'),
           '-InstallRoot', INSTALL_ROOT, '-CsvFile', csv_file,
           '-MetadataFile', metadata_file, '-Source', config['source'], '-Profile', profile]
    with open(log_file, 'wb') as log:
        completed = subprocess.run(cmd, stdout=log, stderr=subprocess.STDOUT, timeout=timeout, check=False)
    if completed.returncode != 0:
        raise RuntimeError('HardeningKitty PowerShell runner exited %s; see %s' %
                           (completed.returncode, log_file))
    if not os.path.isfile(csv_file) or not os.path.isfile(metadata_file):
        raise RuntimeError('Audit runner did not create all required reports.')
    metadata = _read_json(metadata_file)
    counts, findings = _read_report(csv_file, bool(config.get('publish_current_values', False)))
    baseline_file = os.path.join(INSTALL_ROOT, 'lists', metadata['benchmark'])
    counts, findings = _check_coverage(baseline_file, csv_file, counts, findings)
    status = _status_from_counts(counts, config)
    summary = dict(counts)
    summary.update({
        'status': status,
        'benchmark': metadata['benchmark'],
        'os_build': str(metadata['build']),
        'source': metadata['source'],
        'upstream_commit': manifest['upstream_commit'],
        'last_error': '',
        'last_run_utc': datetime.datetime.now(datetime.timezone.utc).isoformat(),
        'report_csv': csv_file,
        'report_log': log_file,
    })
    _write_json(os.path.join(run_dir, 'summary.json'), summary)
    _publish_audit(summary, findings, config)
    print('HardeningKitty: %s | %s | total=%s passed=%s high=%s medium=%s low=%s unknown=%s skipped=%s | compliant=%s%%' %
          (status, summary['benchmark'], counts['total'], counts['passed'], counts['high'],
           counts['medium'], counts['low'], counts['unknown'], counts['skipped'], counts['compliant_percent']))
    sort_priority = {'high': 0, 'medium': 1, 'low': 2, 'unknown': 3}
    for entry in sorted(findings, key=lambda f: (sort_priority.get(f['severity'], 9), f['id']))[:int(config.get('max_findings_in_log', 15))]:
        print('[%s] %s | %s | %s' % (entry['severity'].upper(), entry['id'], entry['category'], entry['name']))
    print('Local full report: %s' % csv_file)
    _trim_reports(config.get('retain_audit_runs', 8))
    return status


def audit():
    try:
        return _audit_impl()
    except Exception as exc:
        message = str(exc)[:1000]
        print('HardeningKitty audit ERROR (execution/integrity failure): %s' % message)
        wapt = globals().get('WAPT')
        write = getattr(wapt, 'write_audit_data_if_changed', None)
        if callable(write):
            for key, value in [('status', 'ERROR'), ('last_error', message)]:
                try:
                    write(AUDIT_SECTION, key, value, max_count=5, keep_days=120)
                except Exception:
                    pass
        write_run = getattr(wapt, 'write_audit_data', None)
        if callable(write_run):
            try:
                write_run(AUDIT_SECTION, 'last_run_utc',
                          datetime.datetime.now(datetime.timezone.utc).isoformat(),
                          max_count=5, keep_days=120)
            except Exception:
                pass
        return 'ERROR'


def update_package():
    """Populate local offline vendor assets before building/signing WAPT."""
    source = _source_directory()
    script = os.path.join(source, 'tools', 'vendor_assets.py')
    subprocess.check_call([sys.executable, script, '--dest', os.path.join(source, 'vendor')])
    print('Vendor ready. Review the diff and build/sign/upload via WAPT Console.')