-
Notifications
You must be signed in to change notification settings - Fork 2k
/
dictization_functions.py
381 lines (300 loc) · 11.2 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
import copy
import formencode as fe
import inspect
class Missing(object):
def __unicode__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __str__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __int__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __complex__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __long__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __float__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __oct__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __hex__(self):
raise Invalid(fe.api._stdtrans('Missing value'))
def __nonzero__(self):
return False
missing = Missing()
class State(object):
pass
class Invalid(Exception):
def __init__(self, error, key=None):
self.error = error
class DataError(Exception):
def __init__(self, error):
self.error = error
class StopOnError(Exception):
'''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 are tuples'''
flattened = flattened or {}
old_key = key or []
for key, value in schema.iteritems():
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, flattented_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 = set([key[:-1] for key in flattented_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'''
flattented_schema = flatten_schema(schema)
key_combinations = get_all_key_combinations(data, flattented_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 sub_schema.iteritems():
if isinstance(value, list):
full_schema[combination + (key,)] = value
return full_schema
def augment_data(data, schema):
'''add missing, extras and junk data'''
flattented_schema = flatten_schema(schema)
key_combinations = get_all_key_combinations(data, flattented_schema)
full_schema = make_full_schema(data, schema)
new_data = copy.deepcopy(data)
## fill junk and extras
for key, value in new_data.items():
if key in full_schema:
continue
## check if any thing naugthy is placed against subschemas
initial_tuple = key[::2]
if initial_tuple in [initial_key[:len(initial_tuple)]
for initial_key in flattented_schema]:
if data[key] <> []:
raise DataError('Only lists of dicts can be placed against '
'subschema %s' % key)
if key[:-1] in key_combinations:
extras_key = key[:-1] + ('__extras',)
extras = new_data.get(extras_key, {})
extras[key[-1]] = value
new_data[extras_key] = extras
else:
junk = new_data.get(("__junk",), {})
junk[key] = value
new_data[("__junk",)] = junk
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):
if inspect.isclass(converter) and issubclass(converter, fe.Validator):
try:
value = converted_data.get(key)
value = converter().to_python(value, state=context)
except fe.Invalid, e:
errors[key].append(e.msg)
return
if isinstance(converter, fe.Validator):
try:
value = converted_data.get(key)
value = converter.to_python(value, state=context)
except fe.Invalid, e:
errors[key].append(e.msg)
return
try:
value = converter(converted_data.get(key))
converted_data[key] = value
return
except TypeError, e:
## hack to make sure the type error was caused by the wrong
## number of arguments given.
if not converter.__name__ in str(e):
raise
except Invalid, e:
errors[key].append(e.error)
return
try:
converter(key, converted_data, errors, context)
return
except Invalid, e:
errors[key].append(e.error)
return
except TypeError, e:
## hack to make sure the type error was caused by the wrong
## number of arguments given.
if not converter.__name__ in str(e):
raise
try:
value = converter(converted_data.get(key), context)
converted_data[key] = value
return
except Invalid, e:
errors[key].append(e.error)
return
def _remove_blank_keys(schema):
for key, value in schema.items():
if isinstance(value[0], dict):
for item in value:
_remove_blank_keys(item)
if not any(value):
schema.pop(key)
return schema
def validate(data, schema, context=None):
'''Validate an unflattened nested dict against a schema.'''
context = context or {}
assert isinstance(data, dict)
flattened = flatten_dict(data)
converted_data, errors = _validate(flattened, schema, context)
converted_data = unflatten(converted_data)
errors_unflattened = unflatten(errors)
##remove validators that passed
dicts_to_process = [errors_unflattened]
while dicts_to_process:
dict_to_process = dicts_to_process.pop()
for key, value in dict_to_process.items():
if not value:
dict_to_process.pop(key)
continue
if isinstance(value[0], dict):
dicts_to_process.extend(value)
_remove_blank_keys(errors_unflattened)
return converted_data, errors_unflattened
def validate_flattened(data, schema, context=None):
context = context or {}
assert isinstance(data, dict)
converted_data, errors = _validate(data, schema, context)
for key, value in errors.items():
if not value:
errors.pop(key)
return converted_data, errors
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 data.iteritems():
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 = {}
for flattend_key in sorted(data.keys(), key=flattened_order_key):
current_pos = unflattened
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
except IndexError:
new_pos = {}
current_pos.append(new_pos)
current_pos = new_pos
current_pos[flattend_key[-1]] = data[flattend_key]
return unflattened