Capstone: A Reliable Catalog CLI

import argparseimport jsonimport osfrom pathlib import Pathimport sysimport tempfileMAX_BYTES = 1_000_000MAX_RECORDS = 1000def read_courses(path):    with path.open('rb') as stream:        payload = stream.read(MAX_BYTES + 1)    if len(payload) > MAX_BYTES:        raise ValueError('input exceeds byte limit')    data = json.loads(payload.decode('utf-8'))    if not isinstance(data, list) or len(data) > MAX_RECORDS:        raise ValueError('expected an array of at most 1000 courses')    courses, seen = [], set()    for number, item in enumerate(data, 1):        if not isinstance(item, dict):            raise ValueError(f'record {number}: expected object')        identifier = item.get('id')        title, minutes = item.get('title'), item.get('minutes')        if type(identifier) is not int or identifier < 1 or identifier in seen:            raise ValueError(f'record {number}: invalid or duplicate id')        if not isinstance(title, str) or not 1 <= len(title.strip()) <= 80:            raise ValueError(f'record {number}: invalid title')        if type(minutes) is not int or minutes < 0:            raise ValueError(f'record {number}: invalid minutes')        seen.add(identifier)        courses.append({'id': identifier, 'title': title.strip(), 'minutes': minutes})    return sorted(courses, key=lambda item: item['id'])def make_report(courses):    return {'schema_version': 1, 'count': len(courses),            'total_minutes': sum(item['minutes'] for item in courses),            'courses': courses}def atomic_write(destination, text):    temporary = None    try:        with tempfile.NamedTemporaryFile(                mode='w', encoding='utf-8', newline='\n', delete=False,                dir=destination.parent, prefix='.catalog-', suffix='.tmp') as stream:            temporary = Path(stream.name)            stream.write(text)            stream.flush()        os.replace(temporary, destination)        temporary = None    finally:        if temporary is not None:            temporary.unlink(missing_ok=True)def main(argv=None):    parser = argparse.ArgumentParser(        prog='catalog-report', description='Validate and summarize a course catalog.',        allow_abbrev=False)    parser.add_argument('input', type=Path, help='UTF-8 JSON catalog')    parser.add_argument('--output', type=Path, help='replace this report file')    args = parser.parse_args(argv)    try:        if args.output is not None and args.input.resolve() == args.output.resolve():            raise ValueError('input and output must be different paths')        report = make_report(read_courses(args.input))        text = json.dumps(report, ensure_ascii=False, sort_keys=True) + '\n'        if args.output is None:            sys.stdout.write(text)        else:            atomic_write(args.output, text)    except (OSError, ValueError, RecursionError) as error:        # Do not echo source payloads or credential-bearing paths.        if isinstance(error, OSError):            message = 'file operation failed'        elif isinstance(error, (json.JSONDecodeError, UnicodeDecodeError, RecursionError)):            message = 'input is not valid UTF-8 catalog JSON'        else:            message = str(error)        print(f'catalog-report: {message}', file=sys.stderr)        return 1    return 0if __name__ == '__main__':    raise SystemExit(main())

# Create fixture.json containing:# [{"id":2,"title":"SQL","minutes":90},{"id":1,"title":"Python","minutes":120}]python catalog_cli.py fixture.jsonpython catalog_cli.py fixture.json --output report.jsonpython catalog_cli.py --help# Invalid JSON or a missing input should produce exit status 1:python catalog_cli.py missing.json