/
utils.py
445 lines (366 loc) · 13.1 KB
/
utils.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
440
441
442
443
444
445
"""Utilities for working with schemas"""
import json
import keyword
import pkgutil
import re
import textwrap
import urllib
import jsonschema
EXCLUDE_KEYS = ("definitions", "title", "description", "$schema", "id")
def resolve_references(schema, root=None):
"""Resolve References within a JSON schema"""
resolver = jsonschema.RefResolver.from_schema(root or schema)
while "$ref" in schema:
with resolver.resolving(schema["$ref"]) as resolved:
schema = resolved
return schema
def get_valid_identifier(
prop, replacement_character="", allow_unicode=False, url_decode=True
):
"""Given a string property, generate a valid Python identifier
Parameters
----------
prop: string
Name of property to decode.
replacement_character: string, default ''
The character to replace invalid characters with.
allow_unicode: boolean, default False
If True, then allow Python 3-style unicode identifiers.
url_decode: boolean, default True
If True, decode URL characters in identifier names.
Examples
--------
>>> get_valid_identifier('my-var')
'myvar'
>>> get_valid_identifier('if')
'if_'
>>> get_valid_identifier('$schema', '_')
'_schema'
>>> get_valid_identifier('$*#$')
'_'
>>> get_valid_identifier("Name%3Cstring%3E")
'Namestring'
"""
# Decode URL characters.
if url_decode:
prop = urllib.parse.unquote(prop)
# Deal with []
prop = prop.replace("[]", "Array")
# First substitute-out all non-valid characters.
flags = re.UNICODE if allow_unicode else re.ASCII
valid = re.sub(r"\W", replacement_character, prop, flags=flags)
# If nothing is left, use just an underscore
if not valid:
valid = "_"
# first character must be a non-digit. Prefix with an underscore
# if needed
if re.match(r"^[\d\W]", valid):
valid = "_" + valid
# if the result is a reserved keyword, then add an underscore at the end
if keyword.iskeyword(valid):
valid += "_"
return valid
def is_valid_identifier(var, allow_unicode=False):
"""Return true if var contains a valid Python identifier
Parameters
----------
val : string
identifier to check
allow_unicode : bool (default: False)
if True, then allow Python 3 style unicode identifiers.
"""
flags = re.UNICODE if allow_unicode else re.ASCII
is_valid = re.match(r"^[^\d\W]\w*\Z", var, flags)
return is_valid and not keyword.iskeyword(var)
class SchemaProperties(object):
"""A wrapper for properties within a schema"""
def __init__(self, properties, schema, rootschema=None):
self._properties = properties
self._schema = schema
self._rootschema = rootschema or schema
def __bool__(self):
return bool(self._properties)
def __dir__(self):
return list(self._properties.keys())
def __getattr__(self, attr):
try:
return self[attr]
except KeyError:
return super(SchemaProperties, self).__getattr__(attr)
def __getitem__(self, attr):
dct = self._properties[attr]
if "definitions" in self._schema and "definitions" not in dct:
dct = dict(definitions=self._schema["definitions"], **dct)
return SchemaInfo(dct, self._rootschema)
def __iter__(self):
return iter(self._properties)
def items(self):
return ((key, self[key]) for key in self)
def keys(self):
return self._properties.keys()
def values(self):
return (self[key] for key in self)
class SchemaInfo(object):
"""A wrapper for inspecting a JSON schema"""
def __init__(self, schema, rootschema=None):
if hasattr(schema, "_schema"):
if hasattr(schema, "_rootschema"):
schema, rootschema = schema._schema, schema._rootschema
else:
schema, rootschema = schema._schema, schema._schema
elif not rootschema:
rootschema = schema
self.raw_schema = schema
self.rootschema = rootschema
self.schema = resolve_references(schema, rootschema)
def child(self, schema):
return self.__class__(schema, rootschema=self.rootschema)
def __repr__(self):
keys = []
for key in sorted(self.schema.keys()):
val = self.schema[key]
rval = repr(val).replace("\n", "")
if len(rval) > 30:
rval = rval[:30] + "..."
if key == "definitions":
rval = "{...}"
elif key == "properties":
rval = "{\n " + "\n ".join(sorted(map(repr, val))) + "\n }"
keys.append('"{}": {}'.format(key, rval))
return "SchemaInfo({\n " + "\n ".join(keys) + "\n})"
@property
def title(self):
if self.is_reference():
return get_valid_identifier(self.refname)
else:
return ""
@property
def short_description(self):
if self.title:
# use RST syntax for generated sphinx docs
return ":class:`{}`".format(self.title)
else:
return self.medium_description
@property
def medium_description(self):
_simple_types = {
"string": "string",
"number": "float",
"integer": "integer",
"object": "mapping",
"boolean": "boolean",
"array": "list",
"null": "None",
}
if self.is_list():
return "[{0}]".format(
", ".join(self.child(s).short_description for s in self.schema)
)
elif self.is_empty():
return "Any"
elif self.is_enum():
return "enum({})".format(", ".join(map(repr, self.enum)))
elif self.is_anyOf():
return "anyOf({})".format(
", ".join(s.short_description for s in self.anyOf)
)
elif self.is_oneOf():
return "oneOf({})".format(
", ".join(s.short_description for s in self.oneOf)
)
elif self.is_allOf():
return "allOf({})".format(
", ".join(s.short_description for s in self.allOf)
)
elif self.is_not():
return "not {}".format(self.not_.short_description)
elif isinstance(self.type, list):
options = []
subschema = SchemaInfo(dict(**self.schema))
for typ_ in self.type:
subschema.schema["type"] = typ_
options.append(subschema.short_description)
return "anyOf({})".format(", ".join(options))
elif self.is_object():
return "Mapping(required=[{}])".format(", ".join(self.required))
elif self.is_array():
return "List({})".format(self.child(self.items).short_description)
elif self.type in _simple_types:
return _simple_types[self.type]
elif not self.type:
import warnings
warnings.warn("no short_description for schema\n{}" "".format(self.schema))
return "any"
@property
def long_description(self):
# TODO
return "Long description including arguments and their types"
@property
def properties(self):
return SchemaProperties(
self.schema.get("properties", {}), self.schema, self.rootschema
)
@property
def definitions(self):
return SchemaProperties(
self.schema.get("definitions", {}), self.schema, self.rootschema
)
@property
def required(self):
return self.schema.get("required", [])
@property
def patternProperties(self):
return self.schema.get("patternProperties", {})
@property
def additionalProperties(self):
return self.schema.get("additionalProperties", True)
@property
def type(self):
return self.schema.get("type", None)
@property
def anyOf(self):
return [self.child(s) for s in self.schema.get("anyOf", [])]
@property
def oneOf(self):
return [self.child(s) for s in self.schema.get("oneOf", [])]
@property
def allOf(self):
return [self.child(s) for s in self.schema.get("allOf", [])]
@property
def not_(self):
return self.child(self.schema.get("not", {}))
@property
def items(self):
return self.schema.get("items", {})
@property
def enum(self):
return self.schema.get("enum", [])
@property
def refname(self):
return self.raw_schema.get("$ref", "#/").split("/")[-1]
@property
def ref(self):
return self.raw_schema.get("$ref", None)
@property
def description(self):
return self.raw_schema.get("description", self.schema.get("description", ""))
def is_list(self):
return isinstance(self.schema, list)
def is_reference(self):
return "$ref" in self.raw_schema
def is_enum(self):
return "enum" in self.schema
def is_empty(self):
return not (set(self.schema.keys()) - set(EXCLUDE_KEYS))
def is_compound(self):
return any(key in self.schema for key in ["anyOf", "allOf", "oneOf"])
def is_anyOf(self):
return "anyOf" in self.schema
def is_allOf(self):
return "allOf" in self.schema
def is_oneOf(self):
return "oneOf" in self.schema
def is_not(self):
return "not" in self.schema
def is_object(self):
if self.type == "object":
return True
elif self.type is not None:
return False
elif (
self.properties
or self.required
or self.patternProperties
or self.additionalProperties
):
return True
else:
raise ValueError("Unclear whether schema.is_object() is True")
def is_value(self):
return not self.is_object()
def is_array(self):
return self.type == "array"
def schema_type(self):
if self.is_empty():
return "empty"
elif self.is_compound():
for key in ["anyOf", "oneOf", "allOf"]:
if key in self.schema:
return key
elif self.is_object():
return "object"
elif self.is_array():
return "array"
elif self.is_value():
return "value"
else:
raise ValueError("Unknown type with keys {}".format(self.schema))
def property_name_map(self):
"""
Return a mapping of schema property names to valid Python attribute names
Only properties which are not valid Python identifiers will be included in
the dictionary.
"""
pairs = [(prop, get_valid_identifier(prop)) for prop in self.properties]
return {prop: val for prop, val in pairs if prop != val}
def indent_arglist(args, indent_level, width=100, lstrip=True):
"""Indent an argument list for use in generated code"""
wrapper = textwrap.TextWrapper(
width=width,
initial_indent=indent_level * " ",
subsequent_indent=indent_level * " ",
break_long_words=False,
)
wrapped = "\n".join(wrapper.wrap(", ".join(args)))
if lstrip:
wrapped = wrapped.lstrip()
return wrapped
def indent_docstring(lines, indent_level, width=100, lstrip=True):
"""Indent a docstring for use in generated code"""
final_lines = []
for i, line in enumerate(lines):
stripped = line.lstrip()
if stripped:
leading_space = len(line) - len(stripped)
indent = indent_level + leading_space
wrapper = textwrap.TextWrapper(
width=width - indent,
initial_indent=indent * " ",
subsequent_indent=indent * " ",
break_long_words=False,
break_on_hyphens=False,
drop_whitespace=True,
)
list_wrapper = textwrap.TextWrapper(
width=width - indent,
initial_indent=indent * " " + "* ",
subsequent_indent=indent * " " + " ",
break_long_words=False,
break_on_hyphens=False,
drop_whitespace=True,
)
for line in stripped.split("\n"):
if line == "":
final_lines.append("")
elif line.startswith("* "):
final_lines.extend(list_wrapper.wrap(line[2:]))
else:
final_lines.extend(wrapper.wrap(line.lstrip()))
# If this is the last line, put in an indent
elif i + 1 == len(lines):
final_lines.append(indent_level * " ")
# If it's not the last line, this is a blank line that should not indent.
else:
final_lines.append("")
# Remove any trailing whitespaces on the right side
stripped_lines = []
for i, line in enumerate(final_lines):
if i + 1 == len(final_lines):
stripped_lines.append(line)
else:
stripped_lines.append(line.rstrip())
# Join it all together
wrapped = "\n".join(stripped_lines)
if lstrip:
wrapped = wrapped.lstrip()
return wrapped