-
Notifications
You must be signed in to change notification settings - Fork 2k
/
dictization_functions.py
439 lines (333 loc) · 12.4 KB
/
dictization_functions.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
# encoding: utf-8
import copy
import json
import six
from six import text_type
from ckan.common import config, _
class Missing(object):
def __unicode__(self):
raise Invalid(_('Missing value'))
def __str__(self):
raise Invalid(_('Missing value'))
def __int__(self):
raise Invalid(_('Missing value'))
def __complex__(self):
raise Invalid(_('Missing value'))
def __long__(self):
raise Invalid(_('Missing value'))
def __float__(self):
raise Invalid(_('Missing value'))
def __oct__(self):
raise Invalid(_('Missing value'))
def __hex__(self):
raise Invalid(_('Missing value'))
def __len__(self):
return 0
missing = Missing()
class State(object):
pass
class DictizationError(Exception):
def __str__(self):
return six.ensure_str(self.__unicode__())
def __unicode__(self):
if hasattr(self, 'error') and self.error:
return u'{}: {}'.format(self.__class__.__name__, repr(self.error))
return self.__class__.__name__
def __repr__(self):
if hasattr(self, 'error') and self.error:
return '<{} {}>'.format(self.__class__.__name__, repr(self.error))
return '<{}>'.format(self.__class__.__name__)
class Invalid(DictizationError):
'''Exception raised by some validator, converter and dictization functions
when the given value is invalid.
'''
def __init__(self, error, key=None):
self.error = error
class DataError(DictizationError):
def __init__(self, error):
self.error = error
class StopOnError(DictizationError):
'''error to stop validations for a particualar key'''
pass
def flattened_order_key(key):
'''order by key length first then values'''
return tuple([len(key)] + list(key))
def flatten_schema(schema, flattened=None, key=None):
'''convert schema into flat dict, where the keys become tuples
e.g.
{
"toplevel": [validators],
"parent": {
"child1": [validators],
"child2": [validators],
}
}
becomes:
{
('toplevel',): [validators],
('parent', 'child1'): [validators],
('parent', 'child2'): [validators],
}
See also: test_flatten_schema()
'''
flattened = flattened or {}
old_key = key or []
for key, value in six.iteritems(schema):
new_key = old_key + [key]
if isinstance(value, dict):
flattened = flatten_schema(value, flattened, new_key)
else:
flattened[tuple(new_key)] = value
return flattened
def get_all_key_combinations(data, flattened_schema):
'''Compare the schema against the given data and get all valid tuples that
match the schema ignoring the last value in the tuple.
'''
schema_prefixes = {key[:-1] for key in flattened_schema}
combinations = set([()])
for key in sorted(data.keys(), key=flattened_order_key):
# make sure the tuple key is a valid one in the schema
key_prefix = key[:-1:2]
if key_prefix not in schema_prefixes:
continue
# make sure the parent key exists, this is assured by sorting the keys
# first
if tuple(tuple(key[:-3])) not in combinations:
continue
combinations.add(tuple(key[:-1]))
return combinations
def make_full_schema(data, schema):
'''make schema by getting all valid combinations and making sure that all
keys are available'''
flattened_schema = flatten_schema(schema)
key_combinations = get_all_key_combinations(data, flattened_schema)
full_schema = {}
for combination in key_combinations:
sub_schema = schema
for key in combination[::2]:
sub_schema = sub_schema[key]
for key, value in six.iteritems(sub_schema):
if isinstance(value, list):
full_schema[combination + (key,)] = value
return full_schema
def augment_data(data, schema):
'''Takes 'flattened' data, compares it with the schema, and returns it with
any problems marked, as follows:
* keys in the data not in the schema are moved into a list under new key
('__junk')
* keys in the schema but not data are added as keys with value 'missing'
'''
flattened_schema = flatten_schema(schema)
key_combinations = get_all_key_combinations(data, flattened_schema)
full_schema = make_full_schema(data, schema)
new_data = copy.copy(data)
keys_to_remove = []
junk = {}
extras_keys = {}
# fill junk and extras
for key, value in new_data.items():
if key in full_schema:
continue
# check if any thing naughty is placed against subschemas
initial_tuple = key[::2]
if initial_tuple in [initial_key[:len(initial_tuple)]
for initial_key in flattened_schema]:
if data[key] != []:
raise DataError('Only lists of dicts can be placed against '
'subschema %s, not %s' %
(key, type(data[key])))
if key[:-1] in key_combinations:
extras_key = key[:-1] + ('__extras',)
extras = extras_keys.get(extras_key, {})
extras[key[-1]] = value
extras_keys[extras_key] = extras
else:
junk[key] = value
keys_to_remove.append(key)
if junk:
new_data[("__junk",)] = junk
for extra_key in extras_keys:
new_data[extra_key] = extras_keys[extra_key]
for key in keys_to_remove:
new_data.pop(key)
# add missing
for key, value in full_schema.items():
if key not in new_data and not key[-1].startswith("__"):
new_data[key] = missing
return new_data
def convert(converter, key, converted_data, errors, context):
try:
value = converter(converted_data.get(key))
converted_data[key] = value
return
except TypeError as e:
# hack to make sure the type error was caused by the wrong
# number of arguments given.
if converter.__name__ not in str(e):
raise
except Invalid as e:
errors[key].append(e.error)
return
try:
converter(key, converted_data, errors, context)
return
except Invalid as e:
errors[key].append(e.error)
return
except TypeError as e:
# hack to make sure the type error was caused by the wrong
# number of arguments given.
if converter.__name__ not in str(e):
raise
try:
value = converter(converted_data.get(key), context)
converted_data[key] = value
return
except Invalid as e:
errors[key].append(e.error)
return
def validate(data, schema, context=None):
'''Validate an unflattened nested dict against a schema.'''
context = context or {}
assert isinstance(data, dict)
# store any empty lists in the data as they will get stripped out by
# the _validate function. We do this so we can differentiate between
# empty fields and missing fields when doing partial updates.
empty_lists = [key for key, value in data.items() if value == []]
# create a copy of the context which also includes the schema keys so
# they can be used by the validators
validators_context = dict(context, schema_keys=list(schema.keys()))
flattened = flatten_dict(data)
converted_data, errors = _validate(flattened, schema, validators_context)
converted_data = unflatten(converted_data)
# check config for partial update fix option
if config.get('ckan.fix_partial_updates', True):
# repopulate the empty lists
for key in empty_lists:
if key not in converted_data:
converted_data[key] = []
# remove validators that passed
for key in list(errors.keys()):
if not errors[key]:
del errors[key]
errors_unflattened = unflatten(errors)
return converted_data, errors_unflattened
def _validate(data, schema, context):
'''validate a flattened dict against a schema'''
converted_data = augment_data(data, schema)
full_schema = make_full_schema(data, schema)
errors = dict((key, []) for key in full_schema)
# before run
for key in sorted(full_schema, key=flattened_order_key):
if key[-1] == '__before':
for converter in full_schema[key]:
try:
convert(converter, key, converted_data, errors, context)
except StopOnError:
break
# main run
for key in sorted(full_schema, key=flattened_order_key):
if not key[-1].startswith('__'):
for converter in full_schema[key]:
try:
convert(converter, key, converted_data, errors, context)
except StopOnError:
break
# extras run
for key in sorted(full_schema, key=flattened_order_key):
if key[-1] == '__extras':
for converter in full_schema[key]:
try:
convert(converter, key, converted_data, errors, context)
except StopOnError:
break
# after run
for key in reversed(sorted(full_schema, key=flattened_order_key)):
if key[-1] == '__after':
for converter in full_schema[key]:
try:
convert(converter, key, converted_data, errors, context)
except StopOnError:
break
# junk
if ('__junk',) in full_schema:
for converter in full_schema[('__junk',)]:
try:
convert(converter, ('__junk',), converted_data, errors,
context)
except StopOnError:
break
return converted_data, errors
def flatten_list(data, flattened=None, old_key=None):
'''flatten a list of dicts'''
flattened = flattened or {}
old_key = old_key or []
for num, value in enumerate(data):
if not isinstance(value, dict):
raise DataError('Values in lists need to be dicts')
new_key = old_key + [num]
flattened = flatten_dict(value, flattened, new_key)
return flattened
def flatten_dict(data, flattened=None, old_key=None):
'''Flatten a dict'''
flattened = flattened or {}
old_key = old_key or []
for key, value in six.iteritems(data):
new_key = old_key + [key]
if isinstance(value, list) and value and isinstance(value[0], dict):
flattened = flatten_list(value, flattened, new_key)
else:
flattened[tuple(new_key)] = value
return flattened
def unflatten(data):
'''Unflatten a simple dict whose keys are tuples.
e.g.
>>> unflatten(
{('name',): u'testgrp4',
('title',): u'',
('description',): u'',
('packages', 0, 'name'): u'testpkg',
('packages', 1, 'name'): u'testpkg',
('extras', 0, 'key'): u'packages',
('extras', 0, 'value'): u'["testpkg"]',
('extras', 1, 'key'): u'',
('extras', 1, 'value'): u'',
('state',): u'active'
('save',): u'Save Changes',
('cancel',): u'Cancel'})
{'name': u'testgrp4',
'title': u'',
'description': u'',
'packages': [{'name': u'testpkg'}, {'name': u'testpkg'}],
'extras': [{'key': u'packages', 'value': u'["testpkg"]'},
{'key': u'', 'value': u''}],
'state': u'active',
'save': u'Save Changes',
'cancel': u'Cancel'}
'''
unflattened = {}
convert_to_list = []
for flattend_key in sorted(data.keys(), key=flattened_order_key):
current_pos = unflattened
if (len(flattend_key) > 1
and not flattend_key[0] in convert_to_list
and not flattend_key[0] in unflattened):
convert_to_list.append(flattend_key[0])
for key in flattend_key[:-1]:
try:
current_pos = current_pos[key]
except KeyError:
new_pos = {}
current_pos[key] = new_pos
current_pos = new_pos
current_pos[flattend_key[-1]] = data[flattend_key]
for key in convert_to_list:
unflattened[key] = [unflattened[key][s]
for s in sorted(unflattened[key])]
return unflattened
class MissingNullEncoder(json.JSONEncoder):
'''json encoder that treats missing objects as null'''
def default(self, obj):
if isinstance(obj, Missing):
return None
return json.JSONEncoder.default(self, obj)