File: test_response_parsing.py

package info (click to toggle)
python-botocore 1.12.103%2Brepack-1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 41,552 kB
  • sloc: python: 43,119; xml: 15,052; makefile: 131
file content (326 lines) | stat: -rw-r--r-- 13,891 bytes parent folder | download | duplicates (2)
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
# Copyright 2012-2014 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
# http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is
# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific
# language governing permissions and limitations under the License.

import os
import glob
import json
import pprint
import logging
import difflib
from tests import create_session

import botocore.session
from botocore import xform_name
from botocore import parsers

log = logging.getLogger(__name__)


SPECIAL_CASES = [
    'iam-get-user-policy.xml', # Needs the JSON decode from handlers.py
    'iam-list-roles.xml',  # Needs the JSON decode from handlers.py for the policy
    's3-get-bucket-location.xml', # Confirmed, this will need a special handler
    #'s3-list-multipart-uploads.xml',  # Bug in model, missing delimeter
    'cloudformation-get-template.xml', # Need to JSON decode the template body.
]


def _test_parsed_response(xmlfile, response_body, operation_model, expected):
    response = {
        'body': response_body,
        'status_code': 200,
        'headers': {}
    }
    for case in SPECIAL_CASES:
        if case in xmlfile:
            print("SKIP: %s" % xmlfile)
            return
    if 'errors' in xmlfile:
        response['status_code'] = 400
    # Handle the special cased __headers__ key if it exists.
    if b'__headers__' in response_body:
        loaded = json.loads(response_body.decode('utf-8'))
        response['headers'] = loaded.pop('__headers__')
        response['body'] = json.dumps(loaded).encode('utf-8')

    protocol = operation_model.service_model.protocol
    parser_cls = parsers.PROTOCOL_PARSERS[protocol]
    parser = parser_cls(timestamp_parser=lambda x: x)
    parsed = parser.parse(response, operation_model.output_shape)
    parsed = _convert_bytes_to_str(parsed)
    expected['ResponseMetadata']['HTTPStatusCode'] = response['status_code']
    expected['ResponseMetadata']['HTTPHeaders'] = response['headers']

    d2 = parsed
    d1 = expected

    if d1 != d2:
        log.debug('-' * 40)
        log.debug("XML FILE:\n" + xmlfile)
        log.debug('-' * 40)
        log.debug("ACTUAL:\n" + pprint.pformat(parsed))
        log.debug('-' * 40)
        log.debug("EXPECTED:\n" + pprint.pformat(expected))
    if not d1 == d2:
        # Borrowed from assertDictEqual, though this doesn't
        # handle the case when unicode literals are used in one
        # dict but not in the other (and we want to consider them
        # as being equal).
        print(d1)
        print()
        print(d2)
        pretty_d1 = pprint.pformat(d1, width=1).splitlines()
        pretty_d2 = pprint.pformat(d2, width=1).splitlines()
        diff = ('\n' + '\n'.join(difflib.ndiff(pretty_d1, pretty_d2)))
        raise AssertionError("Dicts are not equal:\n%s" % diff)


def _convert_bytes_to_str(parsed):
    if isinstance(parsed, dict):
        new_dict = {}
        for key, value in parsed.items():
            new_dict[key] = _convert_bytes_to_str(value)
        return new_dict
    elif isinstance(parsed, bytes):
        return parsed.decode('utf-8')
    elif isinstance(parsed, list):
        new_list = []
        for item in parsed:
            new_list.append(_convert_bytes_to_str(item))
        return new_list
    else:
        return parsed


def test_xml_parsing():
    for dp in ['responses', 'errors']:
        data_path = os.path.join(os.path.dirname(__file__), 'xml')
        data_path = os.path.join(data_path, dp)
        session = create_session()
        xml_files = glob.glob('%s/*.xml' % data_path)
        service_names = set()
        for fn in xml_files:
            service_names.add(os.path.split(fn)[1].split('-')[0])
        for service_name in service_names:
            service_model = session.get_service_model(service_name)
            service_xml_files = glob.glob('%s/%s-*.xml' % (data_path,
                                                           service_name))
            for xmlfile in service_xml_files:
                expected = _get_expected_parsed_result(xmlfile)
                operation_model = _get_operation_model(service_model, xmlfile)
                raw_response_body = _get_raw_response_body(xmlfile)
                yield _test_parsed_response, xmlfile, raw_response_body, \
                    operation_model, expected


def _get_raw_response_body(xmlfile):
    with open(xmlfile, 'rb') as f:
        return f.read()


def _get_operation_model(service_model, filename):
    dirname, filename = os.path.split(filename)
    basename = os.path.splitext(filename)[0]
    sn, opname = basename.split('-', 1)
    # In order to have multiple tests for the same
    # operation a '#' char is used to separate
    # operation names from some other suffix so that
    # the tests have a different filename, e.g
    # my-operation#1.xml, my-operation#2.xml.
    opname = opname.split('#')[0]
    operation_names = service_model.operation_names
    for operation_name in operation_names:
        if xform_name(operation_name) == opname.replace('-', '_'):
            return service_model.operation_model(operation_name)
    return operation


def _get_expected_parsed_result(filename):
    dirname, filename = os.path.split(filename)
    basename = os.path.splitext(filename)[0]
    jsonfile = os.path.join(dirname, basename + '.json')
    with open(jsonfile) as f:
        return json.load(f)


def test_json_errors_parsing():
    # The outputs/ directory has sample output responses
    # For each file in outputs/ there's a corresponding file
    # in expected/ that has the expected parsed response.
    base_dir = os.path.join(os.path.dirname(__file__), 'json')
    json_responses_dir = os.path.join(base_dir, 'errors')
    expected_parsed_dir = os.path.join(base_dir, 'expected')
    session = botocore.session.get_session()
    for json_response_file in os.listdir(json_responses_dir):
        # Files look like: 'datapipeline-create-pipeline.json'
        service_name, operation_name = os.path.splitext(
            json_response_file)[0].split('-', 1)
        expected_parsed_response = os.path.join(expected_parsed_dir,
                                                json_response_file)
        raw_response_file = os.path.join(json_responses_dir,
                                         json_response_file)
        with open(expected_parsed_response) as f:
            expected = json.load(f)
        service_model = session.get_service_model(service_name)
        operation_names = service_model.operation_names
        operation_model = None
        for op_name in operation_names:
            if xform_name(op_name) == operation_name.replace('-', '_'):
                operation_model = service_model.operation_model(op_name)
        with open(raw_response_file, 'rb') as f:
            raw_response_body = f.read()
        yield _test_parsed_response, raw_response_file, \
            raw_response_body, operation_model, expected


def _uhg_test_json_parsing():
    input_path = os.path.join(os.path.dirname(__file__), 'json')
    input_path = os.path.join(input_path, 'inputs')
    output_path = os.path.join(os.path.dirname(__file__), 'json')
    output_path = os.path.join(output_path, 'outputs')
    session = botocore.session.get_session()
    jsonfiles = glob.glob('%s/*.json' % input_path)
    service_names = set()
    for fn in jsonfiles:
        service_names.add(os.path.split(fn)[1].split('-')[0])
    for service_name in service_names:
        service_model = session.get_service_model(service_name)
        service_json_files = glob.glob('%s/%s-*.json' % (input_path,
                                                         service_name))
        for jsonfile in service_json_files:
            expected = _get_expected_parsed_result(jsonfile)
            operation_model = _get_operation_model(service_model, jsonfile)
            with open(jsonfile, 'rb') as f:
                raw_response_body = f.read()
            yield _test_parsed_response, jsonfile, \
                raw_response_body, operation_model, expected
            # TODO: handle the __headers crap.


#class TestHeaderParsing(unittest.TestCase):
#
#    maxDiff = None
#
#    def setUp(self):
#        self.session = botocore.session.get_session()
#        self.s3 = self.session.get_service('s3')
#
#    def test_put_object(self):
#        http_response = Mock()
#        http_response.encoding = 'utf-8'
#        http_response.headers = CaseInsensitiveDict(
#            {'Date': 'Thu, 22 Aug 2013 02:11:57 GMT',
#             'Content-Length': '0',
#             'x-amz-request-id': '2B74ECB010FF029E',
#             'ETag': '"b081e66e7e0c314285c655cafb4d1e71"',
#             'x-amz-id-2': 'bKECRRBFttBRVbJPIVBLQwwipI0i+s9HMvNFdttR17ouR0pvQSKEJUR+1c6cW1nQ',
#             'Server': 'AmazonS3',
#             'content-type': 'text/xml'})
#        http_response.content = ''
#        put_object = self.s3.get_operation('PutObject')
#        expected = {"ETag": '"b081e66e7e0c314285c655cafb4d1e71"'}
#        response_data = get_response(self.session, put_object, http_response)[1]
#        self.assertEqual(response_data, expected)
#
#    def test_head_object(self):
#        http_response = Mock()
#        http_response.encoding = 'utf-8'
#        http_response.headers = CaseInsensitiveDict(
#            {'Date': 'Thu, 22 Aug 2013 02:11:57 GMT',
#             'Content-Length': '265',
#             'x-amz-request-id': '2B74ECB010FF029E',
#             'ETag': '"40d06eb6194712ac1c915783004ef730"',
#             'Server': 'AmazonS3',
#             'content-type': 'binary/octet-stream',
#             'Content-Type': 'binary/octet-stream',
#             'accept-ranges': 'bytes',
#             'Last-Modified': 'Tue, 20 Aug 2013 18:33:25 GMT',
#             'x-amz-server-side-encryption': 'AES256',
#             'x-amz-meta-mykey1': 'value1',
#             'x-amz-meta-mykey2': 'value2',
#             })
#        http_response.content = ''
#        http_response.request.method = 'HEAD'
#        put_object = self.s3.get_operation('HeadObject')
#        expected = {"AcceptRanges": "bytes",
#                    "ContentType": "binary/octet-stream",
#                    "LastModified": "Tue, 20 Aug 2013 18:33:25 GMT",
#                    "ContentLength": "265",
#                    "ETag": '"40d06eb6194712ac1c915783004ef730"',
#                    "ServerSideEncryption": "AES256",
#                    "Metadata": {
#                        'mykey1': 'value1',
#                        'mykey2': 'value2',
#                    }}
#        response_data = get_response(self.session, put_object,
#                                     http_response)[1]
#        self.assertEqual(response_data, expected)
#
#    def test_list_objects_with_invalid_content_length(self):
#        http_response = Mock()
#        http_response.encoding = 'utf-8'
#        http_response.headers = CaseInsensitiveDict(
#            {'Date': 'Thu, 22 Aug 2013 02:11:57 GMT',
#             # We say we have 265 bytes but we're returning 0,
#             # this should raise an exception because this is not
#             # a HEAD request.
#             'Content-Length': '265',
#             'x-amz-request-id': '2B74ECB010FF029E',
#             'ETag': '"40d06eb6194712ac1c915783004ef730"',
#             'Server': 'AmazonS3',
#             'content-type': 'binary/octet-stream',
#             'Content-Type': 'binary/octet-stream',
#             'accept-ranges': 'bytes',
#             'Last-Modified': 'Tue, 20 Aug 2013 18:33:25 GMT',
#             'x-amz-server-side-encryption': 'AES256'
#             })
#        http_response.content = ''
#        http_response.request.method = 'GET'
#        list_objects = self.s3.get_operation('ListObjects')
#        expected = {"AcceptRanges": "bytes",
#                    "ContentType": "binary/octet-stream",
#                    "LastModified": "Tue, 20 Aug 2013 18:33:25 GMT",
#                    "ContentLength": "265",
#                    "ETag": '"40d06eb6194712ac1c915783004ef730"',
#                    "ServerSideEncryption": "AES256"
#                    }
#        with self.assertRaises(IncompleteReadError):
#            response_data = get_response(self.session, list_objects,
#                                         http_response)[1]
#
#    def test_head_object_with_json(self):
#        http_response = Mock()
#        http_response.encoding = 'utf-8'
#        http_response.headers = CaseInsensitiveDict(
#            {'Date': 'Thu, 22 Aug 2013 02:11:57 GMT',
#             'Content-Length': '0',
#             'x-amz-request-id': '2B74ECB010FF029E',
#             'ETag': '"40d06eb6194712ac1c915783004ef730"',
#             'Server': 'AmazonS3',
#             'content-type': 'application/json',
#             'Content-Type': 'application/json',
#             'accept-ranges': 'bytes',
#             'Last-Modified': 'Tue, 20 Aug 2013 18:33:25 GMT',
#             'x-amz-server-side-encryption': 'AES256'})
#        http_response.content = ''
#        put_object = self.s3.get_operation('HeadObject')
#        expected = {"AcceptRanges": "bytes",
#                    "ContentType": "application/json",
#                    "LastModified": "Tue, 20 Aug 2013 18:33:25 GMT",
#                    "ContentLength": "0",
#                    "ETag": '"40d06eb6194712ac1c915783004ef730"',
#                    "ServerSideEncryption": "AES256"
#                    }
#        response_data = get_response(self.session, put_object,
#                                     http_response)[1]
#        self.assertEqual(response_data, expected)