Release portable deterministic core 1.1.0: frozen formats, offline recovery and regression checks
ecad52f verified | """Bounded UTF-8 JSON boundary, rejecting duplicate keys and non-finite values.""" | |
| import json | |
| MAX_JSON_BYTES = 1_048_576 | |
| MAX_JSON_DEPTH = 32 | |
| def _pairs(pairs): | |
| result = {} | |
| for key, value in pairs: | |
| if key in result: | |
| raise ValueError("Duplicate JSON key") | |
| result[key] = value | |
| return result | |
| def _constant(value): | |
| raise ValueError("Non-finite JSON number") | |
| def _float(value): | |
| import math | |
| parsed = float(value) | |
| if not math.isfinite(parsed): | |
| raise ValueError("Non-finite JSON number") | |
| return parsed | |
| def _integer(value): | |
| # Cross-runtime bound, independent of Python's changing int conversion cap. | |
| if len(value.lstrip("-")) > 128: | |
| raise ValueError("JSON integer exceeds 128 digits") | |
| return int(value) | |
| def _check_text(text): | |
| if not isinstance(text, str) or len(text) > MAX_JSON_BYTES: | |
| raise ValueError("JSON input must be bounded UTF-8 text") | |
| try: | |
| if len(text.encode("utf-8", errors="strict")) > MAX_JSON_BYTES: | |
| raise ValueError("JSON input too large") | |
| except UnicodeEncodeError as exc: | |
| raise ValueError("Invalid Unicode scalar value") from exc | |
| # Limit nesting before asking a recursive JSON decoder to allocate objects. | |
| depth = 0 | |
| quoted = escaped = False | |
| for ch in text: | |
| if quoted: | |
| if escaped: | |
| escaped = False | |
| elif ch == "\\": | |
| escaped = True | |
| elif ch == '"': | |
| quoted = False | |
| elif ch == '"': | |
| quoted = True | |
| elif ch in "[{": | |
| depth += 1 | |
| if depth > MAX_JSON_DEPTH: | |
| raise ValueError("JSON nesting too deep") | |
| elif ch in "]}": | |
| depth -= 1 | |
| def strict_loads(text): | |
| _check_text(text) | |
| try: | |
| value = json.loads(text, object_pairs_hook=_pairs, parse_constant=_constant, parse_float=_float, parse_int=_integer) | |
| # Escaped surrogate pairs are decoded normally; lone surrogates fail. | |
| stack = [value] | |
| while stack: | |
| item = stack.pop() | |
| if isinstance(item, str): | |
| item.encode("utf-8", errors="strict") | |
| elif isinstance(item, dict): | |
| stack.extend(item.keys()) | |
| stack.extend(item.values()) | |
| elif isinstance(item, list): | |
| stack.extend(item) | |
| return value | |
| except (UnicodeError, RecursionError) as exc: | |
| raise ValueError("Invalid JSON Unicode or nesting") from exc | |
| def strict_dumps(value): | |
| return json.dumps(value, ensure_ascii=True, sort_keys=True, indent=2, allow_nan=False) | |