#!/usr/bin/env python # In order to run the docstrings: # python3 -m deepdiff.diff # You might need to run it many times since dictionaries come in different orders # every time you run the docstrings. # However the docstring expects it in a specific order in order to pass! import difflib import logging import types import datetime import uuid from enum import Enum from copy import deepcopy from math import isclose as is_close from typing import List, Dict, Callable, Union, Any, Pattern, Tuple, Optional, Set, FrozenSet, TYPE_CHECKING, Protocol, Literal, cast from collections.abc import Mapping, Iterable, Sequence from collections import defaultdict from inspect import getmembers from itertools import zip_longest from functools import lru_cache from deepdiff.helper import (strings, bytes_type, numbers, uuids, ListItemRemovedOrAdded, notpresent, not_found, IndexedHash, unprocessed, add_to_frozen_set, basic_types, convert_item_or_items_into_set_else_none, get_type, convert_item_or_items_into_compiled_regexes_else_none, type_is_subclass_of_type_group, type_in_type_group, get_doc, number_to_string, datetime_normalize, KEY_TO_VAL_STR, booleans, np_ndarray, np_floating, get_numpy_ndarray_rows, RepeatedTimer, TEXT_VIEW, TREE_VIEW, DELTA_VIEW, COLORED_VIEW, COLORED_COMPACT_VIEW, detailed__dict__, add_root_to_paths, np, get_truncate_datetime, dict_, CannotCompare, ENUM_INCLUDE_KEYS, PydanticBaseModel, Opcode, SetOrdered, ipranges, separate_wildcard_and_exact_paths) from deepdiff.serialization import SerializationMixin from deepdiff.distance import DistanceMixin, logarithmic_similarity from deepdiff.model import ( RemapDict, ResultDict, TextResult, TreeResult, DiffLevel, DictRelationship, AttributeRelationship, REPORT_KEYS, SubscriptableIterableRelationship, NonSubscriptableIterableRelationship, SetRelationship, NumpyArrayRelationship, CUSTOM_FIELD, FORCE_DEFAULT, ChildRelationship, ) from deepdiff.deephash import DeepHash, combine_hashes_lists from deepdiff.base import Base from deepdiff.lfucache import LFUCache, DummyLFU from deepdiff.colored_view import ColoredView from deepdiff._multiprocessing import ( normalize_mp_config, compute_distances_parallel, compute_hashes_parallel, compute_subtree_diffs_parallel, ) if TYPE_CHECKING: from pytz.tzinfo import BaseTzInfo logger = logging.getLogger(__name__) MAX_PASSES_REACHED_MSG = ( 'DeepDiff has reached the max number of passes of {}. ' 'You can possibly get more accurate results by increasing the max_passes parameter.') MAX_DIFFS_REACHED_MSG = ( 'DeepDiff has reached the max number of diffs of {}. ' 'You can possibly get more accurate results by increasing the max_diffs parameter.') notpresent_indexed = IndexedHash(indexes=[0], item=notpresent) doc = get_doc('diff_doc.rst') PROGRESS_MSG = "DeepDiff {} seconds in progress. Pass #{}, Diff #{}" def _report_progress(_stats: Dict[str, Any], progress_logger: Callable[[str], None], duration: float) -> None: """ Report the progress every few seconds. """ progress_logger(PROGRESS_MSG.format(duration, _stats[PASSES_COUNT], _stats[DIFF_COUNT])) DISTANCE_CACHE_HIT_COUNT = 'DISTANCE CACHE HIT COUNT' DIFF_COUNT = 'DIFF COUNT' PASSES_COUNT = 'PASSES COUNT' MAX_PASS_LIMIT_REACHED = 'MAX PASS LIMIT REACHED' MAX_DIFF_LIMIT_REACHED = 'MAX DIFF LIMIT REACHED' DISTANCE_CACHE_ENABLED = 'DISTANCE CACHE ENABLED' PREVIOUS_DIFF_COUNT = 'PREVIOUS DIFF COUNT' PREVIOUS_DISTANCE_CACHE_HIT_COUNT = 'PREVIOUS DISTANCE CACHE HIT COUNT' WORKER_DIFF_COUNT = 'WORKER DIFF COUNT' WORKER_PASSES_COUNT = 'WORKER PASSES COUNT' WORKER_DISTANCE_CACHE_HIT_COUNT = 'WORKER DISTANCE CACHE HIT COUNT' WORKER_BATCH_COUNT = 'WORKER BATCH COUNT' CANT_FIND_NUMPY_MSG = 'Unable to import numpy. This must be a bug in DeepDiff since a numpy array is detected.' INVALID_VIEW_MSG = "view parameter must be one of 'text', 'tree', 'delta', 'colored' or 'colored_compact'. But {} was passed." CUTOFF_RANGE_ERROR_MSG = 'cutoff_distance_for_pairs needs to be a positive float max 1.' VERBOSE_LEVEL_RANGE_MSG = 'verbose_level should be 0, 1, or 2.' PURGE_LEVEL_RANGE_MSG = 'cache_purge_level should be 0, 1, or 2.' _ENABLE_CACHE_EVERY_X_DIFF = '_ENABLE_CACHE_EVERY_X_DIFF' model_fields_set = frozenset(["model_fields_set"]) # What is the threshold to consider 2 items to be pairs. Only used when ignore_order = True. CUTOFF_DISTANCE_FOR_PAIRS_DEFAULT = 0.3 # What is the threshold to calculate pairs of items between 2 iterables. # For example 2 iterables that have nothing in common, do not need their pairs to be calculated. CUTOFF_INTERSECTION_FOR_PAIRS_DEFAULT = 0.7 DEEPHASH_PARAM_KEYS = ( 'exclude_types', 'exclude_paths', 'exclude_glob_paths', 'include_paths', 'include_glob_paths', 'exclude_regex_paths', 'hasher', 'significant_digits', 'number_format_notation', 'ignore_string_type_changes', 'ignore_numeric_type_changes', 'ignore_uuid_types', 'use_enum_value', 'ignore_type_in_groups', 'ignore_type_subclasses', 'ignore_string_case', 'exclude_obj_callback', 'ignore_private_variables', 'encodings', 'ignore_encoding_errors', 'default_timezone', 'custom_operators', ) class DeepDiffProtocol(Protocol): t1: Any t2: Any cutoff_distance_for_pairs: float use_log_scale: bool log_scale_similarity_threshold: float view: str math_epsilon: Optional[float] class DeepDiff(ResultDict, SerializationMixin, DistanceMixin, DeepDiffProtocol, Base): __doc__ = doc CACHE_AUTO_ADJUST_THRESHOLD = 0.25 def __init__(self, t1: Any, t2: Any, _original_type: Optional[Any]=None, cache_purge_level: int=1, cache_size: int=0, cache_tuning_sample_size: int=0, custom_operators: Optional[List[Any]] =None, cutoff_distance_for_pairs: float=CUTOFF_DISTANCE_FOR_PAIRS_DEFAULT, cutoff_intersection_for_pairs: float=CUTOFF_INTERSECTION_FOR_PAIRS_DEFAULT, default_timezone:Union[datetime.timezone, "BaseTzInfo"]=datetime.timezone.utc, encodings: Optional[List[str]]=None, exclude_obj_callback: Optional[Callable]=None, exclude_obj_callback_strict: Optional[Callable]=None, exclude_paths: Union[str, List[str], Set[str], FrozenSet[str], None]=None, exclude_regex_paths: Union[str, List[str], Pattern[str], List[Pattern[str]], None]=None, exclude_types: Optional[List[type]]=None, get_deep_distance: bool=False, group_by: Union[str, Tuple[str, str], Callable, None]=None, group_by_sort_key: Union[str, Callable, None]=None, hasher: Optional[Callable]=None, hashes: Optional[Dict[Any, Any]]=None, ignore_encoding_errors: bool=False, ignore_nan_inequality: bool=False, ignore_numeric_type_changes: bool=False, ignore_order: bool=False, ignore_order_func: Optional[Callable]=None, ignore_private_variables: bool=True, ignore_string_case: bool=False, ignore_string_type_changes: bool=False, ignore_type_in_groups: Optional[List[Tuple[Any, ...]]]=None, ignore_type_subclasses: bool=False, ignore_uuid_types: bool=False, include_obj_callback: Optional[Callable]=None, include_obj_callback_strict: Optional[Callable]=None, include_paths: Union[str, List[str], None]=None, iterable_compare_func: Optional[Callable]=None, log_frequency_in_sec: int=0, log_scale_similarity_threshold: float=0.1, log_stacktrace: bool=False, math_epsilon: Optional[float]=None, max_diffs: Optional[int]=None, max_passes: int=10000000, multiprocessing: bool=False, multiprocessing_workers: Optional[int]=None, multiprocessing_threshold: Optional[int]=None, number_format_notation: Literal["f", "e"]="f", number_to_string_func: Optional[Callable]=None, progress_logger: Callable[[str], None]=logger.info, report_repetition: bool=False, significant_digits: Optional[int]=None, threshold_to_diff_deeper: float = 0.33, truncate_datetime: Optional[str]=None, use_enum_value: bool=False, use_log_scale: bool=False, verbose_level: int=1, view: str=TEXT_VIEW, zip_ordered_iterables: bool=False, _parameters: Optional[Dict[str, Any]]=None, _shared_parameters: Optional[Dict[str, Any]]=None, **kwargs): super().__init__() # Defaults for glob path attributes — needed for non-root instances # that may receive _parameters without these keys. self.exclude_glob_paths = None self.include_glob_paths = None if kwargs: raise ValueError(( "The following parameter(s) are not valid: %s\n" "The valid parameters are ignore_order, report_repetition, significant_digits, " "number_format_notation, exclude_paths, include_paths, exclude_types, exclude_regex_paths, ignore_type_in_groups, " "ignore_string_type_changes, ignore_numeric_type_changes, ignore_type_subclasses, ignore_uuid_types, truncate_datetime, " "ignore_private_variables, ignore_nan_inequality, number_to_string_func, verbose_level, " "view, hasher, hashes, max_passes, max_diffs, zip_ordered_iterables, " "cutoff_distance_for_pairs, cutoff_intersection_for_pairs, log_frequency_in_sec, cache_size, " "cache_tuning_sample_size, get_deep_distance, group_by, group_by_sort_key, cache_purge_level, log_stacktrace," "math_epsilon, iterable_compare_func, use_enum_value, _original_type, threshold_to_diff_deeper, default_timezone " "ignore_order_func, custom_operators, encodings, ignore_encoding_errors, use_log_scale, log_scale_similarity_threshold " "multiprocessing, multiprocessing_workers, multiprocessing_threshold, " "_parameters and _shared_parameters.") % ', '.join(kwargs.keys())) if _parameters: self.__dict__.update(_parameters) else: self.custom_operators = custom_operators or [] self.ignore_order = ignore_order self.ignore_order_func = ignore_order_func ignore_type_in_groups = ignore_type_in_groups or [] if numbers == ignore_type_in_groups or numbers in ignore_type_in_groups: ignore_numeric_type_changes = True self.ignore_numeric_type_changes = ignore_numeric_type_changes if strings == ignore_type_in_groups or strings in ignore_type_in_groups: ignore_string_type_changes = True # Handle ignore_uuid_types - check if uuid+str group is already in ignore_type_in_groups uuid_str_group = (uuids[0], str) if uuid_str_group == ignore_type_in_groups or uuid_str_group in ignore_type_in_groups: ignore_uuid_types = True self.ignore_uuid_types = ignore_uuid_types self.use_enum_value = use_enum_value self.log_scale_similarity_threshold = log_scale_similarity_threshold self.use_log_scale = use_log_scale self.default_timezone = default_timezone self.log_stacktrace = log_stacktrace self.threshold_to_diff_deeper = threshold_to_diff_deeper self.ignore_string_type_changes = ignore_string_type_changes self.ignore_type_in_groups = self.get_ignore_types_in_groups( ignore_type_in_groups=ignore_type_in_groups, ignore_string_type_changes=ignore_string_type_changes, ignore_numeric_type_changes=ignore_numeric_type_changes, ignore_type_subclasses=ignore_type_subclasses, ignore_uuid_types=ignore_uuid_types) self.report_repetition = report_repetition _exclude_set = convert_item_or_items_into_set_else_none(exclude_paths) _exclude_exact, self.exclude_glob_paths = separate_wildcard_and_exact_paths(_exclude_set) self.exclude_paths = add_root_to_paths(_exclude_exact) _include_set = convert_item_or_items_into_set_else_none(include_paths) _include_exact, self.include_glob_paths = separate_wildcard_and_exact_paths(_include_set) self.include_paths = add_root_to_paths(_include_exact) self.exclude_regex_paths = convert_item_or_items_into_compiled_regexes_else_none(exclude_regex_paths) self.exclude_types = set(exclude_types) if exclude_types else None self.exclude_types_tuple = tuple(exclude_types) if exclude_types else None # we need tuple for checking isinstance self.ignore_type_subclasses = ignore_type_subclasses self.type_check_func = type_in_type_group if ignore_type_subclasses else type_is_subclass_of_type_group self.ignore_string_case = ignore_string_case self.exclude_obj_callback = exclude_obj_callback self.exclude_obj_callback_strict = exclude_obj_callback_strict self.include_obj_callback = include_obj_callback self.include_obj_callback_strict = include_obj_callback_strict self.number_to_string = number_to_string_func or number_to_string self.iterable_compare_func = iterable_compare_func self.zip_ordered_iterables = zip_ordered_iterables self.ignore_private_variables = ignore_private_variables self.ignore_nan_inequality = ignore_nan_inequality self.hasher = hasher self.cache_tuning_sample_size = cache_tuning_sample_size self.group_by = group_by if callable(group_by_sort_key): self.group_by_sort_key = group_by_sort_key elif group_by_sort_key: def _group_by_sort_key(x): return x[group_by_sort_key] self.group_by_sort_key = _group_by_sort_key else: self.group_by_sort_key = None self.encodings = encodings self.ignore_encoding_errors = ignore_encoding_errors self.significant_digits = self.get_significant_digits(significant_digits, ignore_numeric_type_changes) self.math_epsilon = math_epsilon if self.math_epsilon is not None and self.ignore_order: logger.warning("math_epsilon in conjunction with ignore_order=True is only used for flat object comparisons. Custom math_epsilon will not have an effect when comparing nested objects.") self.truncate_datetime = get_truncate_datetime(truncate_datetime) self.number_format_notation = number_format_notation if verbose_level in {0, 1, 2}: self.verbose_level = verbose_level else: raise ValueError(VERBOSE_LEVEL_RANGE_MSG) if cache_purge_level not in {0, 1, 2}: raise ValueError(PURGE_LEVEL_RANGE_MSG) self.view = view # Setting up the cache for dynamic programming. One dictionary per instance of root of DeepDiff running. self.max_passes = max_passes self.max_diffs = max_diffs self.cutoff_distance_for_pairs = float(cutoff_distance_for_pairs) self.cutoff_intersection_for_pairs = float(cutoff_intersection_for_pairs) if self.cutoff_distance_for_pairs < 0 or self.cutoff_distance_for_pairs > 1: raise ValueError(CUTOFF_RANGE_ERROR_MSG) # _Parameters are the clean _parameters to initialize DeepDiff with so we avoid all the above # cleaning functionalities when running DeepDiff recursively. # However DeepHash has its own set of _parameters that are slightly different than DeepDIff. # DeepDiff _parameters are transformed to DeepHash _parameters via _get_deephash_params method. self.progress_logger = progress_logger self.cache_size = cache_size self._mp_config = normalize_mp_config( multiprocessing, multiprocessing_workers, multiprocessing_threshold) _parameters = self.__dict__.copy() _parameters['group_by'] = None # overwriting since these parameters will be passed on to other passes. if log_stacktrace: self.log_err = logger.exception else: self.log_err = logger.error # Non-Root if _shared_parameters: self.is_root = False self._shared_parameters = _shared_parameters self.__dict__.update(_shared_parameters) # We are in some pass other than root progress_timer = None # Root else: self.is_root = True # Caching the DeepDiff results for dynamic programming self._distance_cache = LFUCache(cache_size) if cache_size else DummyLFU() self._stats = { PASSES_COUNT: 0, DIFF_COUNT: 0, DISTANCE_CACHE_HIT_COUNT: 0, PREVIOUS_DIFF_COUNT: 0, PREVIOUS_DISTANCE_CACHE_HIT_COUNT: 0, MAX_PASS_LIMIT_REACHED: False, MAX_DIFF_LIMIT_REACHED: False, DISTANCE_CACHE_ENABLED: bool(cache_size), # Multiprocessing aggregates: each parallel batch sums per-worker # _stats deltas into these keys. Parent-side counters above stay # comparable to a serial run so existing tests are unaffected. WORKER_DIFF_COUNT: 0, WORKER_PASSES_COUNT: 0, WORKER_DISTANCE_CACHE_HIT_COUNT: 0, WORKER_BATCH_COUNT: 0, } self.hashes = dict_() if hashes is None else hashes self._numpy_paths = dict_() # if _numpy_paths is None else _numpy_paths self.group_by_keys = set() # Track keys that originated from group_by operations self._shared_parameters = { 'hashes': self.hashes, '_stats': self._stats, '_distance_cache': self._distance_cache, 'group_by_keys': self.group_by_keys, '_numpy_paths': self._numpy_paths, _ENABLE_CACHE_EVERY_X_DIFF: self.cache_tuning_sample_size * 10, } if log_frequency_in_sec: # Creating a progress log reporter that runs in a separate thread every log_frequency_in_sec seconds. progress_timer = RepeatedTimer(log_frequency_in_sec, _report_progress, self._stats, progress_logger) else: progress_timer = None self._parameters = _parameters self.deephash_parameters = self._get_deephash_params() self.tree = TreeResult() self._iterable_opcodes = {} if group_by and self.is_root: try: original_t1 = t1 t1 = self._group_iterable_to_dict(t1, group_by, item_name='t1') except (KeyError, ValueError): pass else: try: t2 = self._group_iterable_to_dict(t2, group_by, item_name='t2') except (KeyError, ValueError): t1 = original_t1 self.t1 = t1 self.t2 = t2 try: root = DiffLevel(t1, t2, verbose_level=self.verbose_level) # _original_type is only used to pass the original type of the data. Currently only used for numpy arrays. # The reason is that we convert the numpy array to python list and then later for distance calculations # we convert only the the last dimension of it into numpy arrays. self._diff(root, parents_ids=frozenset({id(t1)}), _original_type=_original_type) if get_deep_distance and view in {TEXT_VIEW, TREE_VIEW}: self.tree['deep_distance'] = self._get_rough_distance() self.tree.remove_empty_keys() view_results = self._get_view_results(self.view) if isinstance(view_results, ColoredView): self.update(view_results.tree) self._colored_view = view_results else: self.update(view_results) finally: if self.is_root: if cache_purge_level: del self._distance_cache del self.hashes del self._shared_parameters del self._parameters for key in (PREVIOUS_DIFF_COUNT, PREVIOUS_DISTANCE_CACHE_HIT_COUNT, DISTANCE_CACHE_ENABLED): del self._stats[key] if progress_timer: duration = progress_timer.stop() self._stats['DURATION SEC'] = duration logger.info('stats {}'.format(self.get_stats())) if cache_purge_level == 2: self.__dict__.clear() def _get_deephash_params(self): result = {key: self._parameters.get(key) for key in DEEPHASH_PARAM_KEYS} result['ignore_repetition'] = not self.report_repetition result['number_to_string_func'] = self.number_to_string return result def _report_result(self, report_type, change_level, local_tree=None): """ Add a detected change to the reference-style result dictionary. report_type will be added to level. (We'll create the text-style report from there later.) :param report_type: A well defined string key describing the type of change. Examples: "set_item_added", "values_changed" :param change_level: A DiffLevel object describing the objects in question in their before-change and after-change object structure. :local_tree: None """ if not self._skip_this(change_level): if self._skip_report_for_include_glob(change_level): return change_level.report_type = report_type tree = self.tree if local_tree is None else local_tree tree[report_type].add(change_level) def custom_report_result(self, report_type, level, extra_info=None): """ Add a detected change to the reference-style result dictionary. report_type will be added to level. (We'll create the text-style report from there later.) :param report_type: A well defined string key describing the type of change. Examples: "set_item_added", "values_changed" :param parent: A DiffLevel object describing the objects in question in their before-change and after-change object structure. :param extra_info: A dict that describe this result :rtype: None """ if not self._skip_this(level): if self._skip_report_for_include_glob(level): return level.report_type = report_type level.additional[CUSTOM_FIELD] = extra_info self.tree[report_type].add(level) def _skip_report_for_include_glob(self, level): """When include_glob_paths is set, _skip_this allows ancestors through for traversal. This method does a stricter check at report time: only report if the path actually matches a glob pattern or is a descendant of a matching path, or if it already matches an exact include_path.""" if not self.include_glob_paths: return False level_path = level.path() # If exact include_paths already matched, don't skip if self.include_paths: if level_path in self.include_paths: return False for prefix in self.include_paths: if prefix in level_path: return False # Check glob patterns: match or descendant for gp in self.include_glob_paths: if gp.match_or_is_descendant(level_path): return False return True @staticmethod def _dict_from_slots(object: Any) -> Dict[str, Any]: def unmangle(attribute: str) -> str: if attribute.startswith('__') and attribute != '__weakref__': return '_{type}{attribute}'.format( type=type(object).__name__, attribute=attribute ) return attribute all_slots = [] if isinstance(object, type): mro = object.__mro__ # pragma: no cover. I have not been able to write a test for this case. But we still check for it. else: mro = object.__class__.__mro__ for type_in_mro in mro: slots = getattr(type_in_mro, '__slots__', None) if slots: if isinstance(slots, strings): all_slots.append(slots) else: all_slots.extend(slots) return {i: getattr(object, key) for i in all_slots if hasattr(object, key := unmangle(i))} def _diff_enum(self, level: Any, parents_ids: FrozenSet[int]=frozenset(), local_tree: Optional[Any]=None) -> None: t1 = detailed__dict__(level.t1, include_keys=ENUM_INCLUDE_KEYS) t2 = detailed__dict__(level.t2, include_keys=ENUM_INCLUDE_KEYS) self._diff_dict( level, parents_ids, print_as_attribute=True, override=True, override_t1=t1, override_t2=t2, local_tree=local_tree, ) def _diff_obj(self, level: Any, parents_ids: FrozenSet[int]=frozenset(), is_namedtuple: bool=False, local_tree: Optional[Any]=None, is_pydantic_object: bool=False) -> None: """Difference of 2 objects""" processing_error = False t1: Optional[Dict[str, Any]] = None t2: Optional[Dict[str, Any]] = None try: if is_namedtuple: t1 = level.t1._asdict() t2 = level.t2._asdict() elif is_pydantic_object: t1 = detailed__dict__(level.t1, ignore_private_variables=self.ignore_private_variables, ignore_keys=model_fields_set) t2 = detailed__dict__(level.t2, ignore_private_variables=self.ignore_private_variables, ignore_keys=model_fields_set) elif all('__dict__' in dir(t) for t in level): t1 = detailed__dict__(level.t1, ignore_private_variables=self.ignore_private_variables) t2 = detailed__dict__(level.t2, ignore_private_variables=self.ignore_private_variables) elif all('__slots__' in dir(t) for t in level): t1 = self._dict_from_slots(level.t1) t2 = self._dict_from_slots(level.t2) else: t1 = {k: v for k, v in getmembers(level.t1) if not callable(v)} t2 = {k: v for k, v in getmembers(level.t2) if not callable(v)} except AttributeError: processing_error = True if processing_error is True or t1 is None or t2 is None: self._report_result('unprocessed', level, local_tree=local_tree) return self._diff_dict( level, parents_ids, print_as_attribute=True, override=True, override_t1=t1, override_t2=t2, local_tree=local_tree, ) def _skip_this(self, level: Any) -> bool: """ Check whether this comparison should be skipped because one of the objects to compare meets exclusion criteria. :rtype: bool """ level_path = level.path() skip = False if self.exclude_paths and level_path in self.exclude_paths: skip = True elif self.exclude_glob_paths and any(gp.match(level_path) for gp in self.exclude_glob_paths): skip = True if not skip and (self.include_paths or self.include_glob_paths) and level_path != 'root': skip = True if self.include_paths: if level_path in self.include_paths: skip = False else: for prefix in self.include_paths: if prefix in level_path or level_path in prefix: skip = False break if skip and self.include_glob_paths: for gp in self.include_glob_paths: if gp.match_or_is_ancestor(level_path): skip = False break elif self.exclude_regex_paths and any( [exclude_regex_path.search(level_path) for exclude_regex_path in self.exclude_regex_paths]): skip = True elif self.exclude_types_tuple and \ (isinstance(level.t1, self.exclude_types_tuple) or isinstance(level.t2, self.exclude_types_tuple)): skip = True elif self.exclude_obj_callback and \ (self.exclude_obj_callback(level.t1, level_path) or self.exclude_obj_callback(level.t2, level_path)): skip = True elif self.exclude_obj_callback_strict and \ (self.exclude_obj_callback_strict(level.t1, level_path) and self.exclude_obj_callback_strict(level.t2, level_path)): skip = True elif self.include_obj_callback and level_path != 'root': skip = True if (self.include_obj_callback(level.t1, level_path) or self.include_obj_callback(level.t2, level_path)): skip = False elif self.include_obj_callback_strict and level_path != 'root': skip = True if (self.include_obj_callback_strict(level.t1, level_path) and self.include_obj_callback_strict(level.t2, level_path)): skip = False return skip def _skip_this_key(self, level: Any, key: Any) -> bool: # if include_paths is not set, than treet every path as included if self.include_paths is None and self.include_glob_paths is None: return False key_path = "{}['{}']".format(level.path(), key) if self.include_paths: if key_path in self.include_paths: return False if level.path() in self.include_paths: # matches e.g. level+key root['foo']['bar']['veg'] include_paths ["root['foo']['bar']"] return False for prefix in self.include_paths: if key_path in prefix: # matches as long the prefix is longer than this object key # eg.: level+key root['foo']['bar'] matches prefix root['foo']['bar'] from include paths # level+key root['foo'] matches prefix root['foo']['bar'] from include_paths # level+key root['foo']['bar'] DOES NOT match root['foo'] from include_paths This needs to be handled afterwards return False # check if a higher level is included as a whole (=without any sublevels specified) # matches e.g. level+key root['foo']['bar']['veg'] include_paths ["root['foo']"] # but does not match, if it is level+key root['foo']['bar']['veg'] include_paths ["root['foo']['bar']['fruits']"] up = level.up while up is not None: if up.path() in self.include_paths: return False up = up.up if self.include_glob_paths: for gp in self.include_glob_paths: if gp.match_or_is_ancestor(key_path): return False return True def _get_clean_to_keys_mapping(self, keys: Any, level: Any) -> Dict[Any, Any]: """ Get a dictionary of cleaned value of keys to the keys themselves. This is mainly used to transform the keys when the type changes of keys should be ignored. TODO: needs also some key conversion for groups of types other than the built-in strings and numbers. """ result = dict_() for key in keys: if self.ignore_string_type_changes and isinstance(key, bytes): clean_key = key.decode('utf-8') elif self.ignore_string_type_changes and isinstance(key, memoryview): clean_key = key.tobytes().decode('utf-8') elif self.use_enum_value and isinstance(key, Enum): clean_key = key.value elif isinstance(key, numbers): # Skip type prefixing for keys that originated from group_by operations if hasattr(self, 'group_by_keys') and key in self.group_by_keys: if self.significant_digits is None: clean_key = key else: clean_key = self.number_to_string(key, significant_digits=self.significant_digits, number_format_notation=self.number_format_notation) # type: ignore # type: ignore else: type_ = "number" if self.ignore_numeric_type_changes else key.__class__.__name__ if self.significant_digits is None: clean_key = key else: clean_key = self.number_to_string(key, significant_digits=self.significant_digits, number_format_notation=self.number_format_notation) # type: ignore # type: ignore clean_key = KEY_TO_VAL_STR.format(type_, clean_key) else: clean_key = key if self.ignore_string_case and isinstance(clean_key, str): clean_key = clean_key.lower() if clean_key in result: logger.warning(('{} and {} in {} become the same key when ignore_numeric_type_changes' 'or ignore_numeric_type_changes are set to be true.').format( key, result[clean_key], level.path())) else: result[clean_key] = key return result def _diff_dict( self, level: Any, parents_ids: FrozenSet[int]=frozenset([]), print_as_attribute: bool=False, override: bool=False, override_t1: Any=None, override_t2: Any=None, local_tree: Optional[Any]=None, ) -> None: """Difference of 2 dictionaries""" if override: # for special stuff like custom objects and named tuples we receive preprocessed t1 and t2 # but must not spoil the chain (=level) with it t1 = override_t1 t2 = override_t2 else: t1 = level.t1 t2 = level.t2 if print_as_attribute: item_added_key = "attribute_added" item_removed_key = "attribute_removed" rel_class = AttributeRelationship else: item_added_key = "dictionary_item_added" item_removed_key = "dictionary_item_removed" rel_class = DictRelationship if self.ignore_private_variables: t1_keys = SetOrdered([key for key in t1 if not(isinstance(key, str) and key.startswith('__')) and not self._skip_this_key(level, key)]) t2_keys = SetOrdered([key for key in t2 if not(isinstance(key, str) and key.startswith('__')) and not self._skip_this_key(level, key)]) else: t1_keys = SetOrdered([key for key in t1 if not self._skip_this_key(level, key)]) t2_keys = SetOrdered([key for key in t2 if not self._skip_this_key(level, key)]) if self.ignore_string_type_changes or self.ignore_numeric_type_changes or self.ignore_string_case: t1_clean_to_keys = self._get_clean_to_keys_mapping(keys=t1_keys, level=level) t2_clean_to_keys = self._get_clean_to_keys_mapping(keys=t2_keys, level=level) t1_keys = SetOrdered(t1_clean_to_keys.keys()) t2_keys = SetOrdered(t2_clean_to_keys.keys()) else: t1_clean_to_keys = t2_clean_to_keys = None t_keys_intersect = t2_keys & t1_keys t_keys_added = t2_keys - t_keys_intersect t_keys_removed = t1_keys - t_keys_intersect if self.threshold_to_diff_deeper: if self.exclude_paths or self.exclude_glob_paths: t_keys_union = {f"{level.path()}[{repr(key)}]" for key in (t2_keys | t1_keys)} if self.exclude_paths: t_keys_union -= self.exclude_paths if self.exclude_glob_paths: t_keys_union = {k for k in t_keys_union if not any(gp.match(k) for gp in self.exclude_glob_paths)} t_keys_union_len = len(t_keys_union) else: t_keys_union_len = len(t2_keys | t1_keys) if t_keys_union_len > 1 and len(t_keys_intersect) / t_keys_union_len < self.threshold_to_diff_deeper: self._report_result('values_changed', level, local_tree=local_tree) return for key in t_keys_added: if self._count_diff() is StopIteration: return key = t2_clean_to_keys[key] if t2_clean_to_keys else key change_level = level.branch_deeper( notpresent, t2[key], child_relationship_class=rel_class, child_relationship_param=key, child_relationship_param2=key, ) self._report_result(item_added_key, change_level, local_tree=local_tree) for key in t_keys_removed: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. key = t1_clean_to_keys[key] if t1_clean_to_keys else key change_level = level.branch_deeper( t1[key], notpresent, child_relationship_class=rel_class, child_relationship_param=key, child_relationship_param2=key, ) self._report_result(item_removed_key, change_level, local_tree=local_tree) for key in t_keys_intersect: # key present in both dicts - need to compare values if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. key1 = t1_clean_to_keys[key] if t1_clean_to_keys else key key2 = t2_clean_to_keys[key] if t2_clean_to_keys else key item_id = id(t1[key1]) if parents_ids and item_id in parents_ids: continue parents_ids_added = add_to_frozen_set(parents_ids, item_id) # Go one level deeper next_level = level.branch_deeper( t1[key1], t2[key2], child_relationship_class=rel_class, child_relationship_param=key, child_relationship_param2=key, ) self._diff(next_level, parents_ids_added, local_tree=local_tree) def _diff_set(self, level: Any, local_tree: Optional[Any]=None) -> None: """Difference of sets""" t1_hashtable = self._create_hashtable(level, 't1') t2_hashtable = self._create_hashtable(level, 't2') t1_hashes = set(t1_hashtable.keys()) t2_hashes = set(t2_hashtable.keys()) hashes_added = t2_hashes - t1_hashes hashes_removed = t1_hashes - t2_hashes items_added = [t2_hashtable[i].item for i in hashes_added] items_removed = [t1_hashtable[i].item for i in hashes_removed] for item in items_added: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. change_level = level.branch_deeper( notpresent, item, child_relationship_class=SetRelationship) self._report_result('set_item_added', change_level, local_tree=local_tree) for item in items_removed: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. change_level = level.branch_deeper( item, notpresent, child_relationship_class=SetRelationship) self._report_result('set_item_removed', change_level, local_tree=local_tree) @staticmethod def _iterables_subscriptable(t1: Any, t2: Any) -> bool: try: if getattr(t1, '__getitem__') and getattr(t2, '__getitem__'): return True else: # pragma: no cover return False # should never happen except AttributeError: return False def _diff_iterable(self, level: Any, parents_ids: FrozenSet[int]=frozenset(), _original_type: Optional[type]=None, local_tree: Optional[Any]=None) -> None: """Difference of iterables""" if (self.ignore_order_func and self.ignore_order_func(level)) or self.ignore_order: self._diff_iterable_with_deephash(level, parents_ids, _original_type=_original_type, local_tree=local_tree) else: self._diff_iterable_in_order(level, parents_ids, _original_type=_original_type, local_tree=local_tree) def _compare_in_order( self, level, t1_from_index: Optional[int]=None, t1_to_index: Optional[int]=None, t2_from_index: Optional[int]=None, t2_to_index: Optional[int]=None ) -> List[Tuple[Tuple[int, int], Tuple[Any, Any]]]: """ Default compare if `iterable_compare_func` is not provided. This will compare in sequence order. """ if t1_from_index is None or t2_from_index is None: return [((i, i), (x, y)) for i, (x, y) in enumerate( zip_longest( level.t1, level.t2, fillvalue=ListItemRemovedOrAdded))] else: t1_chunk = level.t1[t1_from_index:t1_to_index] t2_chunk = level.t2[t2_from_index:t2_to_index] return [((i + t1_from_index, i + t2_from_index), (x, y)) for i, (x, y) in enumerate( zip_longest( t1_chunk, t2_chunk, fillvalue=ListItemRemovedOrAdded))] def _get_matching_pairs( self, level, t1_from_index=None, t1_to_index=None, t2_from_index=None, t2_to_index=None ) -> List[Tuple[Tuple[int, int], Tuple[Any, Any]]]: """ Given a level get matching pairs. This returns list of two tuples in the form: [ (t1 index, t2 index), (t1 item, t2 item) ] This will compare using the passed in `iterable_compare_func` if available. Default it to compare in order """ if self.iterable_compare_func is None: # Match in order if there is no compare function provided return self._compare_in_order( level, t1_from_index=t1_from_index, t1_to_index=t1_to_index, t2_from_index=t2_from_index, t2_to_index=t2_to_index, ) try: matches = [] y_matched = set() y_index_matched = set() for i, x in enumerate(level.t1): x_found = False for j, y in enumerate(level.t2): if(j in y_index_matched): # This ensures a one-to-one relationship of matches from t1 to t2. # If y this index in t2 has already been matched to another x # it cannot have another match, so just continue. continue if(self.iterable_compare_func(x, y, level)): deep_hash = DeepHash(y, hashes=self.hashes, apply_hash=True, **self.deephash_parameters, ) y_index_matched.add(j) y_matched.add(deep_hash[y]) matches.append(((i, j), (x, y))) x_found = True break if(not x_found): matches.append(((i, -1), (x, ListItemRemovedOrAdded))) for j, y in enumerate(level.t2): deep_hash = DeepHash(y, hashes=self.hashes, apply_hash=True, **self.deephash_parameters, ) if(deep_hash[y] not in y_matched): matches.append(((-1, j), (ListItemRemovedOrAdded, y))) return matches except CannotCompare: return self._compare_in_order( level, t1_from_index=t1_from_index, t1_to_index=t1_to_index, t2_from_index=t2_from_index, t2_to_index=t2_to_index ) def _diff_iterable_in_order(self, level, parents_ids=frozenset(), _original_type=None, local_tree=None): # We're handling both subscriptable and non-subscriptable iterables. Which one is it? subscriptable = self._iterables_subscriptable(level.t1, level.t2) if subscriptable: child_relationship_class = SubscriptableIterableRelationship else: child_relationship_class = NonSubscriptableIterableRelationship if ( not self.zip_ordered_iterables and isinstance(level.t1, Sequence) and isinstance(level.t2, Sequence) and self._all_values_basic_hashable(level.t1) and self._all_values_basic_hashable(level.t2) and self.iterable_compare_func is None ): local_tree_pass = TreeResult() opcodes_with_values = self._diff_ordered_iterable_by_difflib( level, parents_ids=parents_ids, _original_type=_original_type, child_relationship_class=child_relationship_class, local_tree=local_tree_pass, ) # Sometimes DeepDiff's old iterable diff does a better job than DeepDiff if len(local_tree_pass) > 1: local_tree_pass2 = TreeResult() self._diff_by_forming_pairs_and_comparing_one_by_one( level, parents_ids=parents_ids, _original_type=_original_type, child_relationship_class=child_relationship_class, local_tree=local_tree_pass2, ) if len(local_tree_pass) >= len(local_tree_pass2): local_tree_pass = local_tree_pass2 else: self._iterable_opcodes[level.path(force=FORCE_DEFAULT)] = opcodes_with_values for report_type, levels in local_tree_pass.items(): if levels: self.tree[report_type] |= levels else: self._diff_by_forming_pairs_and_comparing_one_by_one( level, parents_ids=parents_ids, _original_type=_original_type, child_relationship_class=child_relationship_class, local_tree=local_tree, ) def _all_values_basic_hashable(self, iterable: Iterable[Any]) -> bool: """ Are all items basic hashable types? Or there are custom types too? """ # We don't want to exhaust a generator if isinstance(iterable, types.GeneratorType): return False for item in iterable: if not isinstance(item, basic_types): return False return True def _diff_by_forming_pairs_and_comparing_one_by_one( self, level, local_tree, parents_ids=frozenset(), _original_type=None, child_relationship_class=None, t1_from_index=None, t1_to_index=None, t2_from_index=None, t2_to_index=None, ): for (i, j), (x, y) in self._get_matching_pairs( level, t1_from_index=t1_from_index, t1_to_index=t1_to_index, t2_from_index=t2_from_index, t2_to_index=t2_to_index ): if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. reference_param1 = i reference_param2 = j if y is ListItemRemovedOrAdded: # item removed completely change_level = level.branch_deeper( x, notpresent, child_relationship_class=child_relationship_class, child_relationship_param=reference_param1, child_relationship_param2=reference_param2, ) self._report_result('iterable_item_removed', change_level, local_tree=local_tree) elif x is ListItemRemovedOrAdded: # new item added change_level = level.branch_deeper( notpresent, y, child_relationship_class=child_relationship_class, child_relationship_param=reference_param1, child_relationship_param2=reference_param2, ) self._report_result('iterable_item_added', change_level, local_tree=local_tree) else: # check if item value has changed if (i != j and ((x == y) or self.iterable_compare_func)): # Item moved change_level = level.branch_deeper( x, y, child_relationship_class=child_relationship_class, child_relationship_param=reference_param1, child_relationship_param2=reference_param2 ) self._report_result('iterable_item_moved', change_level, local_tree=local_tree) if self.iterable_compare_func: # Mark additional context denoting that we have moved an item. # This will allow for correctly setting paths relative to t2 when using an iterable_compare_func level.additional["moved"] = True else: continue item_id = id(x) if parents_ids and item_id in parents_ids: continue parents_ids_added = add_to_frozen_set(parents_ids, item_id) # Go one level deeper next_level = level.branch_deeper( x, y, child_relationship_class=child_relationship_class, child_relationship_param=reference_param1, child_relationship_param2=reference_param2 ) self._diff(next_level, parents_ids_added, local_tree=local_tree) def _diff_ordered_iterable_by_difflib( self, level, local_tree, parents_ids=frozenset(), _original_type=None, child_relationship_class=None, ): seq = difflib.SequenceMatcher(isjunk=None, a=level.t1, b=level.t2, autojunk=False) opcodes = seq.get_opcodes() opcodes_with_values = [] # TODO: this logic should be revisted so we detect reverse operations # like when a replacement happens at index X and a reverse replacement happens at index Y # in those cases we have a "iterable_item_moved" operation. for tag, t1_from_index, t1_to_index, t2_from_index, t2_to_index in opcodes: if tag == 'equal': opcodes_with_values.append(Opcode( tag, t1_from_index, t1_to_index, t2_from_index, t2_to_index, )) continue # print('{:7} t1[{}:{}] --> t2[{}:{}] {!r:>8} --> {!r}'.format( # tag, t1_from_index, t1_to_index, t2_from_index, t2_to_index, level.t1[t1_from_index:t1_to_index], level.t2[t2_from_index:t2_to_index])) opcodes_with_values.append(Opcode( tag, t1_from_index, t1_to_index, t2_from_index, t2_to_index, old_values = level.t1[t1_from_index: t1_to_index], new_values = level.t2[t2_from_index: t2_to_index], )) if tag == 'replace': self._diff_by_forming_pairs_and_comparing_one_by_one( level, local_tree=local_tree, parents_ids=parents_ids, _original_type=_original_type, child_relationship_class=child_relationship_class, t1_from_index=t1_from_index, t1_to_index=t1_to_index, t2_from_index=t2_from_index, t2_to_index=t2_to_index, ) elif tag == 'delete': for index, x in enumerate(level.t1[t1_from_index:t1_to_index]): change_level = level.branch_deeper( x, notpresent, child_relationship_class=child_relationship_class, child_relationship_param=index + t1_from_index, child_relationship_param2=index + t1_from_index, ) self._report_result('iterable_item_removed', change_level, local_tree=local_tree) elif tag == 'insert': for index, y in enumerate(level.t2[t2_from_index:t2_to_index]): change_level = level.branch_deeper( notpresent, y, child_relationship_class=child_relationship_class, child_relationship_param=index + t2_from_index, child_relationship_param2=index + t2_from_index, ) self._report_result('iterable_item_added', change_level, local_tree=local_tree) return opcodes_with_values def _diff_str(self, level, local_tree=None): """Compare strings""" if self.ignore_string_case: level.t1 = level.t1.lower() level.t2 = level.t2.lower() if type(level.t1) == type(level.t2) and level.t1 == level.t2: # NOQA return # do we add a diff for convenience? do_diff = True t1_str = level.t1 t2_str = level.t2 if isinstance(level.t1, memoryview): try: t1_str = level.t1.tobytes().decode('ascii') except UnicodeDecodeError: do_diff = False elif isinstance(level.t1, bytes_type): try: t1_str = level.t1.decode('ascii') except UnicodeDecodeError: do_diff = False if isinstance(level.t2, memoryview): try: t2_str = level.t2.tobytes().decode('ascii') except UnicodeDecodeError: do_diff = False elif isinstance(level.t2, bytes_type): try: t2_str = level.t2.decode('ascii') except UnicodeDecodeError: do_diff = False if isinstance(level.t1, Enum): t1_str = level.t1.value if isinstance(level.t2, Enum): t2_str = level.t2.value if t1_str == t2_str: return if do_diff: if '\n' in t1_str or isinstance(t2_str, str) and '\n' in t2_str: diff = difflib.unified_diff( t1_str.splitlines(), t2_str.splitlines(), lineterm='') diff = list(diff) if diff: level.additional['diff'] = '\n'.join(diff) self._report_result('values_changed', level, local_tree=local_tree) def _diff_tuple(self, level, parents_ids, local_tree=None): # Checking to see if it has _fields. Which probably means it is a named # tuple. try: level.t1._asdict # It must be a normal tuple except AttributeError: self._diff_iterable(level, parents_ids, local_tree=local_tree) # We assume it is a namedtuple then else: self._diff_obj(level, parents_ids, is_namedtuple=True, local_tree=local_tree) def _add_hash(self, hashes, item_hash, item, i): if item_hash in hashes: hashes[item_hash].indexes.append(i) else: hashes[item_hash] = IndexedHash(indexes=[i], item=item) def _maybe_compute_hashes_parallel(self, level, obj): """Optionally hash iterable items in worker processes. Returns a list of per-index ``item_hash`` values (or ``None`` for items the worker could not process), aligned to ``enumerate(obj)`` order. Returns ``None`` when the section ran serially (no ``_mp_config``, below threshold, generator without ``__len__``, unsafe inputs). Iteration order is captured here once via ``list(obj)`` so the parent loop and the worker job list see the same items even for order-sensitive iterables like sets. """ mp_config = getattr(self, '_mp_config', None) if mp_config is None or not mp_config.enabled: return None, None try: n = len(obj) except TypeError: # Generators / unsized iterables: serial fallback. Materializing # would change semantics (single-pass consumption). return None, None if not mp_config.should_parallelize(n): return None, None items = list(obj) parent_base = level.path() jobs = [ (item, "{}[{}]".format(parent_base, i)) for i, item in enumerate(items) ] hashes = compute_hashes_parallel( jobs=jobs, deephash_parameters=self.deephash_parameters, config=mp_config, ) if hashes is None: return None, None return hashes, items def _create_hashtable(self, level, t): """Create hashtable of {item_hash: (indexes, item)}""" obj = getattr(level, t) # Optionally precompute item hashes in worker processes. Workers # operate on serial-order job indices and the parent merges back # in that same order, so output is independent of worker # completion order. ``items`` is the materialized iterable when # parallel ran (set/dict iteration is deterministic per run but we # need a single pass we can re-walk here). parallel_hashes, materialized_items = self._maybe_compute_hashes_parallel(level, obj) iterator = enumerate(materialized_items) if materialized_items is not None else enumerate(obj) local_hashes = dict_() for (i, item) in iterator: try: parent = "{}[{}]".format(level.path(), i) if parallel_hashes is not None: item_hash = parallel_hashes[i] if item_hash is None: # Worker could not process this item (KeyError or # unprocessed marker). Mirror the serial pass: # log once, skip. self.log_err("Item %s was not processed while hashing " "thus not counting this object." % level.path()) continue self._add_hash(hashes=local_hashes, item_hash=item_hash, item=item, i=i) continue # Note: in the DeepDiff we only calculate the hash of items when we have to. # So self.hashes does not include hashes of all objects in t1 and t2. # It only includes the ones needed when comparing iterables. # The self.hashes dictionary gets shared between different runs of DeepHash # So that any object that is already calculated to have a hash is not re-calculated. deep_hash = DeepHash( item, hashes=self.hashes, parent=parent, apply_hash=True, **self.deephash_parameters, ) except UnicodeDecodeError as err: err.reason = f"Can not produce a hash for {level.path()}: {err.reason}" raise except NotImplementedError: raise # except Exception as e: # pragma: no cover # logger.error("Can not produce a hash for %s." # "Not counting this object.\n %s" % # (level.path(), e)) else: try: item_hash = deep_hash[item] except KeyError: pass else: if item_hash is unprocessed: # pragma: no cover self.log_err("Item %s was not processed while hashing " "thus not counting this object." % level.path()) else: self._add_hash(hashes=local_hashes, item_hash=item_hash, item=item, i=i) # Also we hash the iterables themselves too so that we can later create cache keys from those hashes. # When the per-item loop ran in parallel, child hashes were not merged into ``self.hashes`` # (cross-process id keys would not match). The iterable-level pass therefore re-hashes # children serially; this is intentional — correctness over cache reuse for now. DeepHash( obj, hashes=self.hashes, parent=level.path(), apply_hash=True, **self.deephash_parameters, ) return local_hashes @staticmethod @lru_cache(maxsize=2028) def _get_distance_cache_key(added_hash, removed_hash): key1, key2 = (added_hash, removed_hash) if added_hash > removed_hash else (removed_hash, added_hash) if isinstance(key1, int): # If the hash function produces integers we convert them to hex values. # This was used when the default hash function was Murmur3 128bit which produces integers. key1 = hex(key1).encode('utf-8') key2 = hex(key2).encode('utf-8') elif isinstance(key1, str): key1 = key1.encode('utf-8') key2 = key2.encode('utf-8') return key1 + b'--' + key2 + b'dc' def _get_rough_distance_of_hashed_objs( self, added_hash, removed_hash, added_hash_obj, removed_hash_obj, _original_type=None): # We need the rough distance between the 2 objects to see if they qualify to be pairs or not _distance = cache_key = None if self._stats[DISTANCE_CACHE_ENABLED]: cache_key = self._get_distance_cache_key(added_hash, removed_hash) cached_distance = self._distance_cache.get(cache_key) if cached_distance is not_found: _distance = None else: self._stats[DISTANCE_CACHE_HIT_COUNT] += 1 _distance = cast(float, cached_distance) if _distance is None: # We can only cache the rough distance and not the actual diff result for reuse. # The reason is that we have modified the parameters explicitly so they are different and can't # be used for diff reporting diff = DeepDiff( removed_hash_obj.item, added_hash_obj.item, _parameters=self._parameters, _shared_parameters=self._shared_parameters, view=DELTA_VIEW, _original_type=_original_type, iterable_compare_func=self.iterable_compare_func, ) _distance = diff._get_rough_distance() if cache_key and self._stats[DISTANCE_CACHE_ENABLED]: self._distance_cache.set(cache_key, value=_distance) return _distance def _maybe_compute_pair_distances_parallel( self, hashes_added, hashes_removed, t1_hashtable, t2_hashtable, parents_ids, _original_type, pre_calced_distances): """Optionally run distance computation for non-cached pairs in workers. Returns a dict ``{(added_hash, removed_hash): distance}`` for pairs whose distance was computed in parallel, or ``None`` if the section ran serially (below threshold, unsafe inputs, no _mp_config, etc.). The job list is built in the exact order of the serial nested loop so the parent merge order is identical regardless of how many workers run or which one finishes first. """ mp_config = getattr(self, '_mp_config', None) if mp_config is None or not mp_config.enabled: return None # Build candidate job list in stable nested-loop order. We skip pairs # that the serial loop also skips (loop detection, pre-calculated # distance, distance cache hit) so workers only get real work. jobs = [] cache_enabled = self._stats[DISTANCE_CACHE_ENABLED] for added_hash in hashes_added: for removed_hash in hashes_removed: added_hash_obj = t2_hashtable[added_hash] removed_hash_obj = t1_hashtable[removed_hash] if id(removed_hash_obj.item) in parents_ids: continue if pre_calced_distances and pre_calced_distances.get( "{}--{}".format(added_hash, removed_hash)) is not None: continue if cache_enabled: cache_key = self._get_distance_cache_key(added_hash, removed_hash) if self._distance_cache.get(cache_key) is not not_found: # Serial path will pull this from cache; no worker # needed and we keep cache-hit accounting in the # parent. continue jobs.append((added_hash, removed_hash, added_hash_obj.item, removed_hash_obj.item)) if not mp_config.should_parallelize(len(jobs)): return None result = compute_distances_parallel( jobs=jobs, parameters=self._parameters, original_type=_original_type, iterable_compare_func=self.iterable_compare_func, config=mp_config, ) if result is None: return None distances, worker_stats = result self._merge_worker_stats(worker_stats) return distances def _merge_worker_stats(self, worker_stats): """Aggregate one parallel-batch's worker ``_stats`` delta into self._stats. Counters (DIFF / PASSES / DISTANCE CACHE HIT) sum into the matching ``WORKER_*`` keys; limit flags OR-merge into the parent's existing MAX_*_LIMIT_REACHED flags so any worker hitting a guard surfaces the same warning state on the public ``get_stats()`` output. """ if not worker_stats: return self._stats[WORKER_DIFF_COUNT] += int(worker_stats.get('DIFF COUNT', 0) or 0) self._stats[WORKER_PASSES_COUNT] += int(worker_stats.get('PASSES COUNT', 0) or 0) self._stats[WORKER_DISTANCE_CACHE_HIT_COUNT] += int( worker_stats.get('DISTANCE CACHE HIT COUNT', 0) or 0) self._stats[WORKER_BATCH_COUNT] += 1 if worker_stats.get(MAX_PASS_LIMIT_REACHED): self._stats[MAX_PASS_LIMIT_REACHED] = True if worker_stats.get(MAX_DIFF_LIMIT_REACHED): self._stats[MAX_DIFF_LIMIT_REACHED] = True def _get_most_in_common_pairs_in_iterables( self, hashes_added, hashes_removed, t1_hashtable, t2_hashtable, parents_ids, _original_type): """ Get the closest pairs between items that are removed and items that are added. returns a dictionary of hashes that are closest to each other. The dictionary is going to be symmetrical so any key will be a value too and otherwise. Note that due to the current reporting structure in DeepDiff, we don't compare an item that was added to an item that is in both t1 and t2. For example [{1, 2}, {4, 5, 6}] [{1, 2}, {1, 2, 3}] is only compared between {4, 5, 6} and {1, 2, 3} even though technically {1, 2, 3} is just one item different than {1, 2} Perhaps in future we can have a report key that is item duplicated and modified instead of just added. """ cache_key = None if self._stats[DISTANCE_CACHE_ENABLED]: cache_key = combine_hashes_lists(items=[hashes_added, hashes_removed], prefix='pairs_cache') cached_pairs = self._distance_cache.get(cache_key) if cached_pairs is not_found: cached_pairs = None else: return cast(dict, cached_pairs).copy() # A dictionary of hashes to distances and each distance to an ordered set of hashes. # It tells us about the distance of each object from other objects. # And the objects with the same distances are grouped together in an ordered set. # It also includes a "max" key that is just the value of the biggest current distance in the # most_in_common_pairs dictionary. def defaultdict_orderedset(): return defaultdict(SetOrdered) most_in_common_pairs = defaultdict(defaultdict_orderedset) pairs = dict_() pre_calced_distances = None if hashes_added and hashes_removed and np and len(hashes_added) > 1 and len(hashes_removed) > 1: # pre-calculates distances ONLY for 1D arrays whether an _original_type # was explicitly passed or a homogeneous array is detected. # Numpy is needed for this optimization. pre_calced_distances = self._precalculate_numpy_arrays_distance( hashes_added, hashes_removed, t1_hashtable, t2_hashtable, _original_type) if hashes_added and hashes_removed \ and self.iterable_compare_func \ and len(hashes_added) > 0 and len(hashes_removed) > 0: pre_calced_distances = self._precalculate_distance_by_custom_compare_func( hashes_added, hashes_removed, t1_hashtable, t2_hashtable, _original_type) # Optionally precompute non-cached distances in worker processes. # Returns a dict keyed by (added_hash, removed_hash). Pair selection # below stays serial and walks the same nested loop order, so the # public output is independent of worker completion order. parallel_distances = self._maybe_compute_pair_distances_parallel( hashes_added, hashes_removed, t1_hashtable, t2_hashtable, parents_ids, _original_type, pre_calced_distances) for added_hash in hashes_added: for removed_hash in hashes_removed: added_hash_obj = t2_hashtable[added_hash] removed_hash_obj = t1_hashtable[removed_hash] # Loop is detected if id(removed_hash_obj.item) in parents_ids: continue _distance = None if pre_calced_distances: _distance = pre_calced_distances.get("{}--{}".format(added_hash, removed_hash)) if _distance is None and parallel_distances is not None: _distance = parallel_distances.get((added_hash, removed_hash)) if _distance is None: _distance = self._get_rough_distance_of_hashed_objs( added_hash, removed_hash, added_hash_obj, removed_hash_obj, _original_type) _distance = cast(float, _distance) # Left for future debugging # print(f'{Fore.RED}distance of {added_hash_obj.item} and {removed_hash_obj.item}: {_distance}{Style.RESET_ALL}') # Discard potential pairs that are too far. if _distance >= self.cutoff_distance_for_pairs: continue pairs_of_item = most_in_common_pairs[added_hash] pairs_of_item[_distance].add(removed_hash) used_to_hashes = set() distances_to_from_hashes = defaultdict(SetOrdered) for from_hash, distances_to_to_hashes in most_in_common_pairs.items(): # del distances_to_to_hashes['max'] for dist in distances_to_to_hashes: distances_to_from_hashes[dist].add(from_hash) for dist in sorted(distances_to_from_hashes.keys()): from_hashes = distances_to_from_hashes[dist] while from_hashes: from_hash = from_hashes.pop() if from_hash not in used_to_hashes: to_hashes = most_in_common_pairs[from_hash][dist] while to_hashes: to_hash = to_hashes.pop() if to_hash not in used_to_hashes: used_to_hashes.add(from_hash) used_to_hashes.add(to_hash) # Left for future debugging: # print(f'{bcolors.FAIL}Adding {t2_hashtable[from_hash].item} as a pairs of {t1_hashtable[to_hash].item} with distance of {dist}{bcolors.ENDC}') pairs[from_hash] = to_hash inverse_pairs = {v: k for k, v in pairs.items()} pairs.update(inverse_pairs) if cache_key and self._stats[DISTANCE_CACHE_ENABLED]: self._distance_cache.set(cache_key, value=pairs) return pairs.copy() def _subtree_parallel_safe(self): """Return True if paired-subtree diffs in this run can be sent to workers. Excluded features are ones whose semantics depend on the *parent's* absolute path or on parent-process state, neither of which is visible in a worker: - ``custom_operators`` (per docs/multi_processing.md) can call ``custom_report_result`` and mutate the parent diff instance. - ``exclude_obj_callback`` / ``include_obj_callback`` (and their ``_strict`` variants) receive the level path; in a worker that path is rooted at the subtree, not the original tree, so they would fire on the wrong paths. - ``ignore_order_func`` is also called with the level and would see worker-local paths. Path-only filters (``exclude_paths`` / ``include_paths`` / ``exclude_regex_paths``) are handled by re-applying ``_skip_this`` after rebasing rather than disabling parallelism. """ if self.custom_operators: return False if self.exclude_obj_callback or self.exclude_obj_callback_strict: return False if self.include_obj_callback or self.include_obj_callback_strict: return False if self.ignore_order_func: return False return True def _rebase_subtree_leaf(self, leaf, change_level): """Splice a worker-built leaf chain onto the parent's ``change_level``. The worker constructed ``leaf`` inside a fresh ``DeepDiff`` whose root DiffLevel holds the paired items themselves; that root is irrelevant once we're back in the parent. We replace it with a *fresh copy* of ``change_level`` (so each leaf gets its own up-chain — DiffLevel.up is shared by reference, and reusing one chain across leaves would scramble paths). Returns the rebased leaf. Path caches along the chain are cleared so ``leaf.path()`` recomputes against the new up-chain. """ # Walk up to find the worker root (up=None). worker_root = leaf while worker_root.up is not None: worker_root = worker_root.up new_cl = change_level.copy() # fresh, independent chain; new_cl is bottom if worker_root is leaf: # The worker reported at the very root of its diff (e.g. the two # paired items differ at the top level — type_changes, # values_changed). Transfer the report payload onto our fresh # change_level copy. new_cl.report_type = leaf.report_type new_cl.additional = leaf.additional cur = new_cl while cur is not None: cur._path = dict_() cur = cur.up return new_cl first_under_root = worker_root.down # Splice: new_cl takes worker_root's place. Setting .down auto-sets # the opposite .up link (see DiffLevel.__setattr__). new_cl.down = first_under_root if worker_root.t1_child_rel is not None: new_cl.t1_child_rel = ChildRelationship.create( klass=worker_root.t1_child_rel.__class__, parent=new_cl.t1, child=first_under_root.t1, param=worker_root.t1_child_rel.param, ) if worker_root.t2_child_rel is not None: new_cl.t2_child_rel = ChildRelationship.create( klass=worker_root.t2_child_rel.__class__, parent=new_cl.t2, child=first_under_root.t2, param=worker_root.t2_child_rel.param, ) # Clear path cache on the entire chain so path() recomputes against # the new up-chain. cur = leaf while cur is not None: cur._path = dict_() cur = cur.up return leaf def _dispatch_subtree_jobs(self, pending_jobs, _original_type, local_tree): """Run deferred paired-subtree diffs (parallel when allowed, else serial). ``pending_jobs`` is the list of ``(change_level, t1_item, t2_item, parents_ids_added)`` tuples in the exact order the inline serial code would have visited them. Parallel results are merged in that same order regardless of worker completion order, so output is identical to the equivalent serial run. """ if not pending_jobs: return mp_config = getattr(self, '_mp_config', None) parallel_results = None if (mp_config is not None and mp_config.enabled and mp_config.should_parallelize(len(pending_jobs))): jobs_payload = [(t1_item, t2_item) for (_, t1_item, t2_item, _) in pending_jobs] outcome = compute_subtree_diffs_parallel( jobs=jobs_payload, parameters=self._parameters, original_type=_original_type, config=mp_config, ) if outcome is not None: parallel_results, worker_stats = outcome self._merge_worker_stats(worker_stats) if parallel_results is None: # Below threshold or unsafe inputs — run inline-equivalent serial. # Walking pending_jobs in order matches how inline serial would # have run them; the parent tree fills up the same way. for change_level, _t1_item, _t2_item, parents_ids_added in pending_jobs: self._diff(change_level, parents_ids_added, local_tree=local_tree) return target_tree = self.tree if local_tree is None else local_tree for (change_level, _t1_item, _t2_item, _parents_ids_added), entries in zip( pending_jobs, parallel_results): for report_type, leaf in entries: rebased_leaf = self._rebase_subtree_leaf(leaf, change_level) # Re-apply path-based filters in the parent — exclude_paths # and friends were not applied correctly inside the worker # because the worker's level paths are subtree-relative. if self._skip_this(rebased_leaf): continue rebased_leaf.report_type = report_type target_tree[report_type].add(rebased_leaf) def _diff_iterable_with_deephash(self, level, parents_ids, _original_type=None, local_tree=None): """Diff of hashable or unhashable iterables. Only used when ignoring the order.""" full_t1_hashtable = self._create_hashtable(level, 't1') full_t2_hashtable = self._create_hashtable(level, 't2') t1_hashes = SetOrdered(full_t1_hashtable.keys()) t2_hashes = SetOrdered(full_t2_hashtable.keys()) hashes_added = t2_hashes - t1_hashes hashes_removed = t1_hashes - t2_hashes # Deciding whether to calculate pairs or not. if (len(hashes_added) + len(hashes_removed)) / (len(full_t1_hashtable) + len(full_t2_hashtable) + 1) > self.cutoff_intersection_for_pairs: get_pairs = False else: get_pairs = True # reduce the size of hashtables if self.report_repetition: t1_hashtable = full_t1_hashtable t2_hashtable = full_t2_hashtable else: t1_hashtable = {k: v for k, v in full_t1_hashtable.items() if k in hashes_removed} t2_hashtable = {k: v for k, v in full_t2_hashtable.items() if k in hashes_added} if self._stats[PASSES_COUNT] < self.max_passes and get_pairs: self._stats[PASSES_COUNT] += 1 pairs = self._get_most_in_common_pairs_in_iterables( hashes_added, hashes_removed, t1_hashtable, t2_hashtable, parents_ids, _original_type) elif get_pairs: if not self._stats[MAX_PASS_LIMIT_REACHED]: self._stats[MAX_PASS_LIMIT_REACHED] = True logger.warning(MAX_PASSES_REACHED_MSG.format(self.max_passes)) pairs = dict_() else: pairs = dict_() def get_other_pair(hash_value, in_t1=True): """ Gets the other paired indexed hash item to the hash_value in the pairs dictionary in_t1: are we looking for the other pair in t1 or t2? """ if in_t1: hashtable = t1_hashtable the_other_hashes = hashes_removed else: hashtable = t2_hashtable the_other_hashes = hashes_added other = pairs.pop(hash_value, notpresent) if other is notpresent: other = notpresent_indexed else: # The pairs are symmetrical. # removing the other direction of pair # so it does not get used. del pairs[other] the_other_hashes.remove(other) other = hashtable[other] return other # Phase 3: paired-subtree diffs may be deferred so they can run in a # worker pool. ``pending_subtree_jobs is None`` keeps the inline # serial path (and the existing ordering of inline ``_diff`` calls # vs. ``_report_result`` calls) — so any feature that disables # subtree parallelism degrades cleanly to today's behavior. mp_config = getattr(self, '_mp_config', None) use_mp = ( mp_config is not None and mp_config.enabled and self._subtree_parallel_safe() ) pending_subtree_jobs = [] if use_mp else None if self.report_repetition: for hash_value in hashes_added: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition (when report_repetition=False). other = get_other_pair(hash_value) item_id = id(other.item) indexes = t2_hashtable[hash_value].indexes if other.item is notpresent else other.indexes # When we report repetitions, we want the child_relationship_param2 only if there is no repetition. # Because when there is a repetition, we report it in a different way (iterable_items_added_at_indexes for example). # When there is no repetition, we want child_relationship_param2 so that we report the "new_path" correctly. if len(t2_hashtable[hash_value].indexes) == 1: index2 = t2_hashtable[hash_value].indexes[0] else: index2 = None for i in indexes: change_level = level.branch_deeper( other.item, t2_hashtable[hash_value].item, child_relationship_class=SubscriptableIterableRelationship, child_relationship_param=i, child_relationship_param2=index2, ) if other.item is notpresent: self._report_result('iterable_item_added', change_level, local_tree=local_tree) else: parents_ids_added = add_to_frozen_set(parents_ids, item_id) if pending_subtree_jobs is None: self._diff(change_level, parents_ids_added, local_tree=local_tree) else: pending_subtree_jobs.append( (change_level, other.item, t2_hashtable[hash_value].item, parents_ids_added)) for hash_value in hashes_removed: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. other = get_other_pair(hash_value, in_t1=False) item_id = id(other.item) # When we report repetitions, we want the child_relationship_param2 only if there is no repetition. # Because when there is a repetition, we report it in a different way (iterable_items_added_at_indexes for example). # When there is no repetition, we want child_relationship_param2 so that we report the "new_path" correctly. if other.item is notpresent or len(other.indexes) > 1: index2 = None else: index2 = other.indexes[0] for i in t1_hashtable[hash_value].indexes: change_level = level.branch_deeper( t1_hashtable[hash_value].item, other.item, child_relationship_class=SubscriptableIterableRelationship, child_relationship_param=i, child_relationship_param2=index2, ) if other.item is notpresent: self._report_result('iterable_item_removed', change_level, local_tree=local_tree) else: # I was not able to make a test case for the following 2 lines since the cases end up # getting resolved above in the hashes_added calcs. However I am leaving these 2 lines # in case things change in future. parents_ids_added = add_to_frozen_set(parents_ids, item_id) # pragma: no cover. if pending_subtree_jobs is None: # pragma: no cover. self._diff(change_level, parents_ids_added, local_tree=local_tree) else: # pragma: no cover. pending_subtree_jobs.append( (change_level, t1_hashtable[hash_value].item, other.item, parents_ids_added)) items_intersect = t2_hashes.intersection(t1_hashes) for hash_value in items_intersect: t1_indexes = t1_hashtable[hash_value].indexes t2_indexes = t2_hashtable[hash_value].indexes t1_indexes_len = len(t1_indexes) t2_indexes_len = len(t2_indexes) if t1_indexes_len != t2_indexes_len: # this is a repetition change! # create "change" entry, keep current level untouched to handle further changes repetition_change_level = level.branch_deeper( t1_hashtable[hash_value].item, t2_hashtable[hash_value].item, # nb: those are equal! child_relationship_class=SubscriptableIterableRelationship, child_relationship_param=t1_hashtable[hash_value] .indexes[0]) repetition_change_level.additional['repetition'] = RemapDict( old_repeat=t1_indexes_len, new_repeat=t2_indexes_len, old_indexes=t1_indexes, new_indexes=t2_indexes) self._report_result('repetition_change', repetition_change_level, local_tree=local_tree) else: for hash_value in hashes_added: if self._count_diff() is StopIteration: return other = get_other_pair(hash_value) item_id = id(other.item) index = t2_hashtable[hash_value].indexes[0] if other.item is notpresent else other.indexes[0] index2 = t2_hashtable[hash_value].indexes[0] change_level = level.branch_deeper( other.item, t2_hashtable[hash_value].item, child_relationship_class=SubscriptableIterableRelationship, child_relationship_param=index, child_relationship_param2=index2, ) if other.item is notpresent: self._report_result('iterable_item_added', change_level, local_tree=local_tree) else: parents_ids_added = add_to_frozen_set(parents_ids, item_id) if pending_subtree_jobs is None: self._diff(change_level, parents_ids_added, local_tree=local_tree) else: pending_subtree_jobs.append( (change_level, other.item, t2_hashtable[hash_value].item, parents_ids_added)) for hash_value in hashes_removed: if self._count_diff() is StopIteration: return # pragma: no cover. This is already covered for addition. other = get_other_pair(hash_value, in_t1=False) item_id = id(other.item) index = t1_hashtable[hash_value].indexes[0] index2 = t1_hashtable[hash_value].indexes[0] if other.item is notpresent else other.indexes[0] change_level = level.branch_deeper( t1_hashtable[hash_value].item, other.item, child_relationship_class=SubscriptableIterableRelationship, child_relationship_param=index, child_relationship_param2=index2, ) if other.item is notpresent: self._report_result('iterable_item_removed', change_level, local_tree=local_tree) else: # Just like the case when report_repetition = True, these lines never run currently. # However they will stay here in case things change in future. parents_ids_added = add_to_frozen_set(parents_ids, item_id) # pragma: no cover. if pending_subtree_jobs is None: # pragma: no cover. self._diff(change_level, parents_ids_added, local_tree=local_tree) else: # pragma: no cover. pending_subtree_jobs.append( (change_level, t1_hashtable[hash_value].item, other.item, parents_ids_added)) if pending_subtree_jobs: self._dispatch_subtree_jobs(pending_subtree_jobs, _original_type, local_tree) def _diff_booleans(self, level, local_tree=None): if level.t1 != level.t2: self._report_result('values_changed', level, local_tree=local_tree) def _diff_numbers(self, level, local_tree=None, report_type_change=True): """Diff Numbers""" if report_type_change: t1_type = "number" if self.ignore_numeric_type_changes else level.t1.__class__.__name__ t2_type = "number" if self.ignore_numeric_type_changes else level.t2.__class__.__name__ else: t1_type = t2_type = '' if self.use_log_scale: if not logarithmic_similarity(level.t1, level.t2, threshold=self.log_scale_similarity_threshold): self._report_result('values_changed', level, local_tree=local_tree) elif self.math_epsilon is not None: if not is_close(level.t1, level.t2, abs_tol=self.math_epsilon): self._report_result('values_changed', level, local_tree=local_tree) elif self.significant_digits is None: if level.t1 != level.t2: self._report_result('values_changed', level, local_tree=local_tree) else: # Bernhard10: I use string formatting for comparison, to be consistent with usecases where # data is read from files that were previously written from python and # to be consistent with on-screen representation of numbers. # Other options would be abs(t1-t2)<10**-self.significant_digits # or math.is_close (python3.5+) # Note that abs(3.25-3.251) = 0.0009999999999998899 < 0.001 # Note also that "{:.3f}".format(1.1135) = 1.113, but "{:.3f}".format(1.11351) = 1.114 # For Decimals, format seems to round 2.5 to 2 and 3.5 to 4 (to closest even number) t1_s = self.number_to_string(level.t1, significant_digits=self.significant_digits, number_format_notation=self.number_format_notation) # type: ignore t2_s = self.number_to_string(level.t2, significant_digits=self.significant_digits, number_format_notation=self.number_format_notation) # type: ignore t1_s = KEY_TO_VAL_STR.format(t1_type, t1_s) t2_s = KEY_TO_VAL_STR.format(t2_type, t2_s) if t1_s != t2_s: self._report_result('values_changed', level, local_tree=local_tree) def _diff_ipranges(self, level, local_tree=None): """Diff IP ranges""" if str(level.t1) != str(level.t2): self._report_result('values_changed', level, local_tree=local_tree) def _diff_datetime(self, level, local_tree=None): """Diff DateTimes""" level.t1 = datetime_normalize(self.truncate_datetime, level.t1, default_timezone=self.default_timezone) level.t2 = datetime_normalize(self.truncate_datetime, level.t2, default_timezone=self.default_timezone) if level.t1 != level.t2: self._report_result('values_changed', level, local_tree=local_tree) def _diff_time(self, level, local_tree=None): """Diff DateTimes""" if self.truncate_datetime: level.t1 = datetime_normalize(self.truncate_datetime, level.t1, default_timezone=self.default_timezone) level.t2 = datetime_normalize(self.truncate_datetime, level.t2, default_timezone=self.default_timezone) if level.t1 != level.t2: self._report_result('values_changed', level, local_tree=local_tree) def _diff_uuids(self, level, local_tree=None): """Diff UUIDs""" if level.t1.int != level.t2.int: self._report_result('values_changed', level, local_tree=local_tree) def _diff_numpy_array(self, level, parents_ids=frozenset(), local_tree=None): """Diff numpy arrays""" if level.path() not in self._numpy_paths: self._numpy_paths[level.path()] = get_type(level.t2).__name__ if np is None: # This line should never be run. If it is ever called means the type check detected a numpy array # which means numpy module needs to be available. So np can't be None. raise ImportError(CANT_FIND_NUMPY_MSG) # pragma: no cover if (self.ignore_order_func and not self.ignore_order_func(level)) or not self.ignore_order: # fast checks if self.significant_digits is None: if np.array_equal(level.t1, level.t2, equal_nan=self.ignore_nan_inequality): return # all good else: try: np.testing.assert_almost_equal(level.t1, level.t2, decimal=self.significant_digits) except TypeError: np.array_equal(level.t1, level.t2, equal_nan=self.ignore_nan_inequality) except AssertionError: pass # do detailed checking below else: return # all good # compare array meta-data _original_type = level.t1.dtype if level.t1.shape != level.t2.shape: # arrays are converted to python lists so that certain features of DeepDiff can apply on them easier. # They will be converted back to Numpy at their final dimension. level.t1 = level.t1.tolist() level.t2 = level.t2.tolist() self._diff_iterable(level, parents_ids, _original_type=_original_type, local_tree=local_tree) else: # metadata same -- the difference is in the content shape = level.t1.shape dimensions = len(shape) if dimensions == 1: self._diff_iterable(level, parents_ids, _original_type=_original_type, local_tree=local_tree) elif (self.ignore_order_func and self.ignore_order_func(level)) or self.ignore_order: # arrays are converted to python lists so that certain features of DeepDiff can apply on them easier. # They will be converted back to Numpy at their final dimension. level.t1 = level.t1.tolist() level.t2 = level.t2.tolist() self._diff_iterable_with_deephash(level, parents_ids, _original_type=_original_type, local_tree=local_tree) else: for (t1_path, t1_row), (t2_path, t2_row) in zip( get_numpy_ndarray_rows(level.t1, shape), get_numpy_ndarray_rows(level.t2, shape)): new_level = level.branch_deeper( t1_row, t2_row, child_relationship_class=NumpyArrayRelationship, child_relationship_param=t1_path, child_relationship_param2=t2_path, ) self._diff_iterable_in_order(new_level, parents_ids, _original_type=_original_type, local_tree=local_tree) def _diff_types(self, level, local_tree=None): """Diff types""" level.report_type = 'type_changes' self._report_result('type_changes', level, local_tree=local_tree) def _count_diff(self): if (self.max_diffs is not None and self._stats[DIFF_COUNT] > self.max_diffs): if not self._stats[MAX_DIFF_LIMIT_REACHED]: self._stats[MAX_DIFF_LIMIT_REACHED] = True logger.warning(MAX_DIFFS_REACHED_MSG.format(self.max_diffs)) return StopIteration self._stats[DIFF_COUNT] += 1 if self.cache_size and self.cache_tuning_sample_size: self._auto_tune_cache() def _auto_tune_cache(self): take_sample = (self._stats[DIFF_COUNT] % self.cache_tuning_sample_size == 0) if self.cache_tuning_sample_size: if self._stats[DISTANCE_CACHE_ENABLED]: if take_sample: self._auto_off_cache() # Turn on the cache once in a while elif self._stats[DIFF_COUNT] % self._shared_parameters[_ENABLE_CACHE_EVERY_X_DIFF] == 0: self.progress_logger('Re-enabling the distance and level caches.') # decreasing the sampling frequency self._shared_parameters[_ENABLE_CACHE_EVERY_X_DIFF] *= 10 self._stats[DISTANCE_CACHE_ENABLED] = True if take_sample: for key in (PREVIOUS_DIFF_COUNT, PREVIOUS_DISTANCE_CACHE_HIT_COUNT): self._stats[key] = self._stats[key[9:]] def _auto_off_cache(self): """ Auto adjust the cache based on the usage """ if self._stats[DISTANCE_CACHE_ENABLED]: angle = (self._stats[DISTANCE_CACHE_HIT_COUNT] - self._stats['PREVIOUS {}'.format(DISTANCE_CACHE_HIT_COUNT)]) / (self._stats[DIFF_COUNT] - self._stats[PREVIOUS_DIFF_COUNT]) if angle < self.CACHE_AUTO_ADJUST_THRESHOLD: self._stats[DISTANCE_CACHE_ENABLED] = False self.progress_logger('Due to minimal cache hits, {} is disabled.'.format('distance cache')) def _use_custom_operator(self, level): """ For each level we check all custom operators. If any one of them was a match for the level, we run the diff of the operator. If the operator returned True, the operator must have decided these objects should not be compared anymore. It might have already reported their results. In that case the report will appear in the final results of this diff. Otherwise basically the 2 objects in the level are being omitted from the results. """ for operator in self.custom_operators: if operator.match(level): prevent_default = operator.give_up_diffing(level=level, diff_instance=self) if prevent_default: return True return False def _diff(self, level, parents_ids=frozenset(), _original_type=None, local_tree=None): """ The main diff method **parameters** level: the tree level or tree node parents_ids: the ids of all the parent objects in the tree from the current node. _original_type: If the objects had an original type that was different than what currently exists in the level.t1 and t2 """ if self._count_diff() is StopIteration: return if self._use_custom_operator(level): return if level.t1 is level.t2: return if self._skip_this(level): return report_type_change = True if get_type(level.t1) != get_type(level.t2): for type_group in self.ignore_type_in_groups: if self.type_check_func(level.t1, type_group) and self.type_check_func(level.t2, type_group): report_type_change = False break if self.use_enum_value and isinstance(level.t1, Enum): level.t1 = level.t1.value report_type_change = False if self.use_enum_value and isinstance(level.t2, Enum): level.t2 = level.t2.value report_type_change = False if report_type_change: self._diff_types(level, local_tree=local_tree) return # This is an edge case where t1=None or t2=None and None is in the ignore type group. if level.t1 is None or level.t2 is None: self._report_result('values_changed', level, local_tree=local_tree) return if self.ignore_nan_inequality and isinstance(level.t1, (float, np_floating)) and str(level.t1) == str(level.t2) == 'nan': return if isinstance(level.t1, booleans): self._diff_booleans(level, local_tree=local_tree) elif isinstance(level.t1, strings): # Special handling when comparing string with UUID and ignore_uuid_types is True if self.ignore_uuid_types and isinstance(level.t2, uuids): try: # Convert string to UUID for comparison t1_uuid = uuid.UUID(str(level.t1)) if t1_uuid.int != level.t2.int: self._report_result('values_changed', level, local_tree=local_tree) except (ValueError, AttributeError): # If string is not a valid UUID, report as changed self._report_result('values_changed', level, local_tree=local_tree) else: self._diff_str(level, local_tree=local_tree) elif isinstance(level.t1, datetime.datetime): self._diff_datetime(level, local_tree=local_tree) elif isinstance(level.t1, ipranges): self._diff_ipranges(level, local_tree=local_tree) elif isinstance(level.t1, (datetime.date, datetime.timedelta, datetime.time)): self._diff_time(level, local_tree=local_tree) elif isinstance(level.t1, uuids): # Special handling when comparing UUID with string and ignore_uuid_types is True if self.ignore_uuid_types and isinstance(level.t2, str): try: # Convert string to UUID for comparison t2_uuid = uuid.UUID(level.t2) if level.t1.int != t2_uuid.int: self._report_result('values_changed', level, local_tree=local_tree) except (ValueError, AttributeError): # If string is not a valid UUID, report as changed self._report_result('values_changed', level, local_tree=local_tree) else: self._diff_uuids(level, local_tree=local_tree) elif isinstance(level.t1, numbers): self._diff_numbers(level, local_tree=local_tree, report_type_change=report_type_change) elif isinstance(level.t1, Mapping): self._diff_dict(level, parents_ids, local_tree=local_tree) elif isinstance(level.t1, tuple): self._diff_tuple(level, parents_ids, local_tree=local_tree) elif isinstance(level.t1, (set, frozenset, SetOrdered)): self._diff_set(level, local_tree=local_tree) elif isinstance(level.t1, np_ndarray): self._diff_numpy_array(level, parents_ids, local_tree=local_tree) elif isinstance(level.t1, PydanticBaseModel): self._diff_obj(level, parents_ids, local_tree=local_tree, is_pydantic_object=True) elif isinstance(level.t1, Iterable): self._diff_iterable(level, parents_ids, _original_type=_original_type, local_tree=local_tree) elif isinstance(level.t1, Enum): self._diff_enum(level, parents_ids, local_tree=local_tree) else: self._diff_obj(level, parents_ids) def _get_view_results(self, view, verbose_level=None): """ Get the results based on the view """ result = self.tree if not self.report_repetition: # and self.is_root: result.mutual_add_removes_to_become_value_changes() if view == TREE_VIEW: pass elif view == TEXT_VIEW: effective_verbose_level = verbose_level if verbose_level is not None else self.verbose_level result = TextResult(tree_results=self.tree, verbose_level=effective_verbose_level) result.remove_empty_keys() elif view == DELTA_VIEW: result = self._to_delta_dict(report_repetition_required=False) elif view == COLORED_VIEW: result = ColoredView(t2=self.t2, tree_result=self.tree, compact=False) elif view == COLORED_COMPACT_VIEW: result = ColoredView(t2=self.t2, tree_result=self.tree, compact=True) else: raise ValueError(INVALID_VIEW_MSG.format(view)) return result @staticmethod def _get_key_for_group_by(row, group_by, item_name): """ Get the key value to group a row by, using the specified group_by parameter. Example >>> row = {'first': 'John', 'middle': 'Joe', 'last': 'Smith'} >>> DeepDiff._get_key_for_group_by(row, 'first', 't1') 'John' >>> nested_row = {'id': 123, 'demographics': {'names': {'first': 'John', 'middle': 'Joe', 'last': 'Smith'}}} >>> group_by = lambda x: x['demographics']['names']['first'] >>> DeepDiff._get_key_for_group_by(nested_row, group_by, 't1') 'John' Args: row (dict): The dictionary (row) to extract the group by key from. group_by (str or callable): The key name or function to call to get to the key value to group by. item_name (str): The name of the item, used for error messages. Returns: str: The key value to group by. Raises: KeyError: If the specified key is not found in the row. """ try: if callable(group_by): return group_by(row) return row.pop(group_by) except KeyError: logger.error("Unable to group {} by {}. The key is missing in {}".format(item_name, group_by, row)) raise def _group_iterable_to_dict(self, item, group_by, item_name): """ Convert a list of dictionaries into a dictionary of dictionaries where the key is the value of the group_by key in each dictionary. """ group_by_level2 = None if isinstance(group_by, (list, tuple)): group_by_level1 = group_by[0] if len(group_by) > 1: group_by_level2 = group_by[1] else: group_by_level1 = group_by if isinstance(item, Iterable) and not isinstance(item, Mapping): result = {} item_copy = deepcopy(item) for row in item_copy: if isinstance(row, Mapping): key1 = self._get_key_for_group_by(row, group_by_level1, item_name) # Track keys created by group_by to avoid type prefixing later if hasattr(self, 'group_by_keys'): self.group_by_keys.add(key1) if group_by_level2: key2 = self._get_key_for_group_by(row, group_by_level2, item_name) # Track level 2 keys as well if hasattr(self, 'group_by_keys'): self.group_by_keys.add(key2) if key1 not in result: result[key1] = {} if self.group_by_sort_key: if key2 not in result[key1]: result[key1][key2] = [] result_key1_key2 = result[key1][key2] if row not in result_key1_key2: result_key1_key2.append(row) else: result[key1][key2] = row else: if self.group_by_sort_key: if key1 not in result: result[key1] = [] if row not in result[key1]: result[key1].append(row) else: result[key1] = row else: msg = "Unable to group {} by {} since the item {} is not a dictionary.".format(item_name, group_by_level1, row) logger.error(msg) raise ValueError(msg) if self.group_by_sort_key: if group_by_level2: for key1, row1 in result.items(): for key2, row in row1.items(): row.sort(key=self.group_by_sort_key) else: for key, row in result.items(): row.sort(key=self.group_by_sort_key) return result msg = "Unable to group {} by {}".format(item_name, group_by) logger.error(msg) raise ValueError(msg) def get_stats(self): """ Get some stats on internals of the DeepDiff run. """ return self._stats @property def affected_paths(self): """ Get the list of paths that were affected. Whether a value was changed or they were added or removed. Example >>> from pprint import pprint >>> t1 = {1: 1, 2: 2, 3: [3], 4: 4} >>> t2 = {1: 1, 2: 4, 3: [3, 4], 5: 5, 6: 6} >>> ddiff = DeepDiff(t1, t2) >>> pprint(ddiff, indent=4) { 'dictionary_item_added': ['root[5]', 'root[6]'], 'dictionary_item_removed': ['root[4]'], 'iterable_item_added': {'root[3][1]': 4}, 'values_changed': {'root[2]': {'new_value': 4, 'old_value': 2}}} >>> sorted(ddiff.affected_paths) ['root[2]', 'root[3][1]', 'root[4]', 'root[5]', 'root[6]'] >>> sorted(ddiff.affected_root_keys) [2, 3, 4, 5, 6] """ result = SetOrdered() for key in REPORT_KEYS: value = self.get(key) if value: if isinstance(value, SetOrdered): result |= value else: result |= SetOrdered(value.keys()) return result @property def affected_root_keys(self): """ Get the list of root keys that were affected. Whether a value was changed or they were added or removed. Example >>> from pprint import pprint >>> t1 = {1: 1, 2: 2, 3: [3], 4: 4} >>> t2 = {1: 1, 2: 4, 3: [3, 4], 5: 5, 6: 6} >>> ddiff = DeepDiff(t1, t2) >>> pprint(ddiff, indent=4) { 'dictionary_item_added': ['root[5]', 'root[6]'], 'dictionary_item_removed': ['root[4]'], 'iterable_item_added': {'root[3][1]': 4}, 'values_changed': {'root[2]': {'new_value': 4, 'old_value': 2}}} >>> sorted(ddiff.affected_paths) ['root[2]', 'root[3][1]', 'root[4]', 'root[5]', 'root[6]'] >>> sorted(ddiff.affected_root_keys) [2, 3, 4, 5, 6] """ result = SetOrdered() for key in REPORT_KEYS: value = self.tree.get(key) if value: if isinstance(value, SetOrdered): values_list = value else: values_list = value.keys() for item in values_list: root_key = item.get_root_key() if root_key is not notpresent: result.add(root_key) return result def __str__(self): if hasattr(self, '_colored_view') and self.view in {COLORED_VIEW, COLORED_COMPACT_VIEW}: return str(self._colored_view) return super().__str__() if __name__ == "__main__": # pragma: no cover import doctest doctest.testmod()