summaryrefslogtreecommitdiff
path: root/jsonschema/_utils.py
blob: e5051ec1007c44c70b09ac0a20a77ea32ea70411 (plain)
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
from collections.abc import Mapping, MutableMapping, Sequence
from urllib.parse import urlsplit
import itertools
import json
import re
import sys

# The files() API was added in Python 3.9.
if sys.version_info >= (3, 9):  # pragma: no cover
    import importlib.resources as resources
else:  # pragma: no cover
    import importlib_resources as resources


class URIDict(MutableMapping):
    """
    Dictionary which uses normalized URIs as keys.
    """

    def normalize(self, uri):
        return urlsplit(uri).geturl()

    def __init__(self, *args, **kwargs):
        self.store = dict()
        self.store.update(*args, **kwargs)

    def __getitem__(self, uri):
        return self.store[self.normalize(uri)]

    def __setitem__(self, uri, value):
        self.store[self.normalize(uri)] = value

    def __delitem__(self, uri):
        del self.store[self.normalize(uri)]

    def __iter__(self):
        return iter(self.store)

    def __len__(self):
        return len(self.store)

    def __repr__(self):
        return repr(self.store)


class Unset(object):
    """
    An as-of-yet unset attribute or unprovided default parameter.
    """

    def __repr__(self):
        return "<unset>"


def load_schema(name):
    """
    Load a schema from ./schemas/``name``.json and return it.
    """

    path = resources.files(__package__).joinpath(f"schemas/{name}.json")
    data = path.read_text(encoding="utf-8")
    return json.loads(data)


def format_as_index(container, indices):
    """
    Construct a single string containing indexing operations for the indices.

    For example for a container ``bar``, [1, 2, "foo"] -> bar[1][2]["foo"]

    Arguments:

        container (str):

            A word to use for the thing being indexed

        indices (sequence):

            The indices to format.
    """

    if not indices:
        return container
    return f"{container}[{']['.join(repr(index) for index in indices)}]"


def find_additional_properties(instance, schema):
    """
    Return the set of additional properties for the given ``instance``.

    Weeds out properties that should have been validated by ``properties`` and
    / or ``patternProperties``.

    Assumes ``instance`` is dict-like already.
    """

    properties = schema.get("properties", {})
    patterns = "|".join(schema.get("patternProperties", {}))
    for property in instance:
        if property not in properties:
            if patterns and re.search(patterns, property):
                continue
            yield property


def extras_msg(extras):
    """
    Create an error message for extra items or properties.
    """

    if len(extras) == 1:
        verb = "was"
    else:
        verb = "were"
    return ", ".join(repr(extra) for extra in extras), verb


def ensure_list(thing):
    """
    Wrap ``thing`` in a list if it's a single str.

    Otherwise, return it unchanged.
    """

    if isinstance(thing, str):
        return [thing]
    return thing


def _mapping_equal(one, two):
    """
    Check if two mappings are equal using the semantics of `equal`.
    """
    if len(one) != len(two):
        return False
    return all(
        key in two and equal(value, two[key])
        for key, value in one.items()
    )


def _sequence_equal(one, two):
    """
    Check if two sequences are equal using the semantics of `equal`.
    """
    if len(one) != len(two):
        return False
    return all(equal(i, j) for i, j in zip(one, two))


def equal(one, two):
    """
    Check if two things are equal evading some Python type hierarchy semantics.

    Specifically in JSON Schema, evade `bool` inheriting from `int`,
    recursing into sequences to do the same.
    """
    if isinstance(one, str) or isinstance(two, str):
        return one == two
    if isinstance(one, Sequence) and isinstance(two, Sequence):
        return _sequence_equal(one, two)
    if isinstance(one, Mapping) and isinstance(two, Mapping):
        return _mapping_equal(one, two)
    return unbool(one) == unbool(two)


def unbool(element, true=object(), false=object()):
    """
    A hack to make True and 1 and False and 0 unique for ``uniq``.
    """

    if element is True:
        return true
    elif element is False:
        return false
    return element


def uniq(container):
    """
    Check if all of a container's elements are unique.

    Tries to rely on the container being recursively sortable, or otherwise
    falls back on (slow) brute force.
    """
    try:
        sort = sorted(unbool(i) for i in container)
        sliced = itertools.islice(sort, 1, None)

        for i, j in zip(sort, sliced):
            return not _sequence_equal(i, j)

    except (NotImplementedError, TypeError):
        seen = []
        for e in container:
            e = unbool(e)

            for i in seen:
                if equal(i, e):
                    return False

            seen.append(e)
    return True


def find_evaluated_item_indexes_by_schema(validator, instance, schema):
    """
    Get all indexes of items that get evaluated under the current schema

    Covers all keywords related to unevaluatedItems: items, prefixItems, if,
    then, else, contains, unevaluatedItems, allOf, oneOf, anyOf
    """
    if validator.is_type(schema, "boolean"):
        return []
    evaluated_indexes = []

    if "items" in schema:
        return list(range(0, len(instance)))

    if "$ref" in schema:
        scope, resolved = validator.resolver.resolve(schema["$ref"])
        validator.resolver.push_scope(scope)

        try:
            evaluated_indexes += find_evaluated_item_indexes_by_schema(
                validator, instance, resolved)
        finally:
            validator.resolver.pop_scope()

    if "prefixItems" in schema:
        evaluated_indexes += list(range(0, len(schema["prefixItems"])))

    if "if" in schema:
        if validator.evolve(schema=schema["if"]).is_valid(instance):
            evaluated_indexes += find_evaluated_item_indexes_by_schema(
                validator, instance, schema["if"],
            )
            if "then" in schema:
                evaluated_indexes += find_evaluated_item_indexes_by_schema(
                    validator, instance, schema["then"],
                )
        else:
            if "else" in schema:
                evaluated_indexes += find_evaluated_item_indexes_by_schema(
                    validator, instance, schema["else"],
                )

    for keyword in ["contains", "unevaluatedItems"]:
        if keyword in schema:
            for k, v in enumerate(instance):
                if validator.evolve(schema=schema[keyword]).is_valid(v):
                    evaluated_indexes.append(k)

    for keyword in ["allOf", "oneOf", "anyOf"]:
        if keyword in schema:
            for subschema in schema[keyword]:
                errs = list(validator.descend(instance, subschema))
                if not errs:
                    evaluated_indexes += find_evaluated_item_indexes_by_schema(
                        validator, instance, subschema,
                    )

    return evaluated_indexes


def find_evaluated_property_keys_by_schema(validator, instance, schema):
    """
    Get all keys of items that get evaluated under the current schema

    Covers all keywords related to unevaluatedProperties: properties,
    additionalProperties, unevaluatedProperties, patternProperties,
    dependentSchemas, allOf, oneOf, anyOf, if, then, else
    """
    if validator.is_type(schema, "boolean"):
        return []
    evaluated_keys = []

    if "$ref" in schema:
        scope, resolved = validator.resolver.resolve(schema["$ref"])
        validator.resolver.push_scope(scope)

        try:
            evaluated_keys += find_evaluated_property_keys_by_schema(
                validator, instance, resolved,
            )
        finally:
            validator.resolver.pop_scope()

    for keyword in [
        "properties", "additionalProperties", "unevaluatedProperties",
    ]:
        if keyword in schema:
            if validator.is_type(schema[keyword], "boolean"):
                for property, value in instance.items():
                    if validator.evolve(schema=schema[keyword]).is_valid(
                        {property: value},
                    ):
                        evaluated_keys.append(property)

            if validator.is_type(schema[keyword], "object"):
                for property, subschema in schema[keyword].items():
                    if property in instance and validator.evolve(
                        schema=subschema,
                    ).is_valid(instance[property]):
                        evaluated_keys.append(property)

    if "patternProperties" in schema:
        for property, value in instance.items():
            for pattern, _ in schema["patternProperties"].items():
                if re.search(pattern, property) and validator.evolve(
                    schema=schema["patternProperties"],
                ).is_valid({property: value}):
                    evaluated_keys.append(property)

    if "dependentSchemas" in schema:
        for property, subschema in schema["dependentSchemas"].items():
            if property not in instance:
                continue
            evaluated_keys += find_evaluated_property_keys_by_schema(
                validator, instance, subschema,
            )

    for keyword in ["allOf", "oneOf", "anyOf"]:
        if keyword in schema:
            for subschema in schema[keyword]:
                errs = list(validator.descend(instance, subschema))
                if not errs:
                    evaluated_keys += find_evaluated_property_keys_by_schema(
                        validator, instance, subschema,
                    )

    if "if" in schema:
        if validator.evolve(schema=schema["if"]).is_valid(instance):
            evaluated_keys += find_evaluated_property_keys_by_schema(
                validator, instance, schema["if"],
            )
            if "then" in schema:
                evaluated_keys += find_evaluated_property_keys_by_schema(
                    validator, instance, schema["then"],
                )
        else:
            if "else" in schema:
                evaluated_keys += find_evaluated_property_keys_by_schema(
                    validator, instance, schema["else"],
                )

    return evaluated_keys