forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathrisk_test.py
More file actions
354 lines (300 loc) · 9.4 KB
/
Copy pathrisk_test.py
File metadata and controls
354 lines (300 loc) · 9.4 KB
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
# Copyright 2017 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the 'License');
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License 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.
from flaky import flaky
import uuid
import google.cloud.pubsub
import google.cloud.bigquery
import pytest
import os
import risk
UNIQUE_STRING = str(uuid.uuid4()).split("-")[0]
GCLOUD_PROJECT = os.environ.get("GCLOUD_PROJECT")
TABLE_PROJECT = os.environ.get("GCLOUD_PROJECT")
TOPIC_ID = "dlp-test" + UNIQUE_STRING
SUBSCRIPTION_ID = "dlp-test-subscription" + UNIQUE_STRING
UNIQUE_FIELD = "Name"
REPEATED_FIELD = "Mystery"
NUMERIC_FIELD = "Age"
STRING_BOOLEAN_FIELD = "Gender"
BIGQUERY_DATASET_ID = "dlp_test_dataset" + UNIQUE_STRING
BIGQUERY_TABLE_ID = "dlp_test_table" + UNIQUE_STRING
BIGQUERY_HARMFUL_TABLE_ID = "harmful" + UNIQUE_STRING
# Create new custom topic/subscription
@pytest.fixture(scope="module")
def topic_id():
# Creates a pubsub topic, and tears it down.
publisher = google.cloud.pubsub.PublisherClient()
topic_path = publisher.topic_path(GCLOUD_PROJECT, TOPIC_ID)
try:
publisher.create_topic(topic_path)
except google.api_core.exceptions.AlreadyExists:
pass
yield TOPIC_ID
publisher.delete_topic(topic_path)
@pytest.fixture(scope="module")
def subscription_id(topic_id):
# Subscribes to a topic.
subscriber = google.cloud.pubsub.SubscriberClient()
topic_path = subscriber.topic_path(GCLOUD_PROJECT, topic_id)
subscription_path = subscriber.subscription_path(
GCLOUD_PROJECT, SUBSCRIPTION_ID
)
try:
subscriber.create_subscription(subscription_path, topic_path)
except google.api_core.exceptions.AlreadyExists:
pass
yield SUBSCRIPTION_ID
subscriber.delete_subscription(subscription_path)
@pytest.fixture(scope="module")
def bigquery_project():
# Adds test Bigquery data, yields the project ID and then tears down.
bigquery_client = google.cloud.bigquery.Client()
dataset_ref = bigquery_client.dataset(BIGQUERY_DATASET_ID)
dataset = google.cloud.bigquery.Dataset(dataset_ref)
try:
dataset = bigquery_client.create_dataset(dataset)
except google.api_core.exceptions.Conflict:
dataset = bigquery_client.get_dataset(dataset)
table_ref = dataset_ref.table(BIGQUERY_TABLE_ID)
table = google.cloud.bigquery.Table(table_ref)
harmful_table_ref = dataset_ref.table(BIGQUERY_HARMFUL_TABLE_ID)
harmful_table = google.cloud.bigquery.Table(harmful_table_ref)
table.schema = (
google.cloud.bigquery.SchemaField("Name", "STRING"),
google.cloud.bigquery.SchemaField("Comment", "STRING"),
)
harmful_table.schema = (
google.cloud.bigquery.SchemaField("Name", "STRING", "REQUIRED"),
google.cloud.bigquery.SchemaField(
"TelephoneNumber", "STRING", "REQUIRED"
),
google.cloud.bigquery.SchemaField("Mystery", "STRING", "REQUIRED"),
google.cloud.bigquery.SchemaField("Age", "INTEGER", "REQUIRED"),
google.cloud.bigquery.SchemaField("Gender", "STRING"),
google.cloud.bigquery.SchemaField("RegionCode", "STRING"),
)
try:
table = bigquery_client.create_table(table)
except google.api_core.exceptions.Conflict:
table = bigquery_client.get_table(table)
try:
harmful_table = bigquery_client.create_table(harmful_table)
except google.api_core.exceptions.Conflict:
harmful_table = bigquery_client.get_table(harmful_table)
rows_to_insert = [(u"Gary Smith", u"My email is gary@example.com")]
harmful_rows_to_insert = [
(
u"Gandalf",
u"(123) 456-7890",
"4231 5555 6781 9876",
27,
"Male",
"US",
),
(
u"Dumbledore",
u"(313) 337-1337",
"6291 8765 1095 7629",
27,
"Male",
"US",
),
(u"Joe", u"(452) 123-1234", "3782 2288 1166 3030", 35, "Male", "US"),
(u"James", u"(567) 890-1234", "8291 3627 8250 1234", 19, "Male", "US"),
(
u"Marie",
u"(452) 123-1234",
"8291 3627 8250 1234",
35,
"Female",
"US",
),
(
u"Carrie",
u"(567) 890-1234",
"2253 5218 4251 4526",
35,
"Female",
"US",
),
]
bigquery_client.insert_rows(table, rows_to_insert)
bigquery_client.insert_rows(harmful_table, harmful_rows_to_insert)
yield GCLOUD_PROJECT
bigquery_client.delete_dataset(dataset_ref, delete_contents=True)
@flaky
def test_numerical_risk_analysis(
topic_id, subscription_id, bigquery_project, capsys
):
risk.numerical_risk_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
NUMERIC_FIELD,
topic_id,
subscription_id,
)
out, _ = capsys.readouterr()
assert "Value Range:" in out
@flaky
def test_categorical_risk_analysis_on_string_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.categorical_risk_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
UNIQUE_FIELD,
topic_id,
subscription_id,
timeout=180,
)
out, _ = capsys.readouterr()
assert "Most common value occurs" in out
@flaky
def test_categorical_risk_analysis_on_number_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.categorical_risk_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
NUMERIC_FIELD,
topic_id,
subscription_id,
)
out, _ = capsys.readouterr()
assert "Most common value occurs" in out
@flaky
def test_k_anonymity_analysis_single_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.k_anonymity_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
[NUMERIC_FIELD],
)
out, _ = capsys.readouterr()
assert "Quasi-ID values:" in out
assert "Class size:" in out
@flaky
def test_k_anonymity_analysis_multiple_fields(
topic_id, subscription_id, bigquery_project, capsys
):
risk.k_anonymity_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
[NUMERIC_FIELD, REPEATED_FIELD],
)
out, _ = capsys.readouterr()
assert "Quasi-ID values:" in out
assert "Class size:" in out
@flaky
def test_l_diversity_analysis_single_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.l_diversity_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
UNIQUE_FIELD,
[NUMERIC_FIELD],
)
out, _ = capsys.readouterr()
assert "Quasi-ID values:" in out
assert "Class size:" in out
assert "Sensitive value" in out
@flaky
def test_l_diversity_analysis_multiple_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.l_diversity_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
UNIQUE_FIELD,
[NUMERIC_FIELD, REPEATED_FIELD],
)
out, _ = capsys.readouterr()
assert "Quasi-ID values:" in out
assert "Class size:" in out
assert "Sensitive value" in out
@flaky
def test_k_map_estimate_analysis_single_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.k_map_estimate_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
[NUMERIC_FIELD],
["AGE"],
)
out, _ = capsys.readouterr()
assert "Anonymity range:" in out
assert "Size:" in out
assert "Values" in out
@flaky
def test_k_map_estimate_analysis_multiple_field(
topic_id, subscription_id, bigquery_project, capsys
):
risk.k_map_estimate_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
[NUMERIC_FIELD, STRING_BOOLEAN_FIELD],
["AGE", "GENDER"],
)
out, _ = capsys.readouterr()
assert "Anonymity range:" in out
assert "Size:" in out
assert "Values" in out
@flaky
def test_k_map_estimate_analysis_quasi_ids_info_types_equal(
topic_id, subscription_id, bigquery_project
):
with pytest.raises(ValueError):
risk.k_map_estimate_analysis(
GCLOUD_PROJECT,
TABLE_PROJECT,
BIGQUERY_DATASET_ID,
BIGQUERY_HARMFUL_TABLE_ID,
topic_id,
subscription_id,
[NUMERIC_FIELD, STRING_BOOLEAN_FIELD],
["AGE"],
)