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
|
import uuid
import boto3
import pytest
from botocore.exceptions import ClientError
from moto import mock_aws
from moto.core import DEFAULT_ACCOUNT_ID as ACCOUNT_ID
def _create_databrew_client():
client = boto3.client("databrew", region_name="us-west-1")
return client
def _create_test_dataset(
client,
tags=None,
dataset_name=None,
dataset_format="JSON",
dataset_format_options=None,
):
if dataset_name is None:
dataset_name = str(uuid.uuid4())
if not dataset_format_options:
if dataset_format == "JSON":
dataset_format_options = {"Json": {"MultiLine": True}}
elif dataset_format == "CSV":
dataset_format_options = {"Csv": {"Delimiter": ",", "HeaderRow": False}}
elif dataset_format == "EXCEL":
dataset_format_options = {
"Excel": {
"SheetNames": [
"blaa",
],
"SheetIndexes": [
123,
],
"HeaderRow": True,
}
}
return client.create_dataset(
Name=dataset_name,
Format=dataset_format,
FormatOptions=dataset_format_options,
Input={
"S3InputDefinition": {
"Bucket": "somerandombucketname",
},
"DataCatalogInputDefinition": {
"DatabaseName": "somedbname",
"TableName": "sometablename",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
"DatabaseInputDefinition": {
"GlueConnectionName": "someglueconnectionname",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
},
PathOptions={
"LastModifiedDateCondition": {
"Expression": "string",
"ValuesMap": {"string": "string"},
},
"FilesLimit": {
"MaxFiles": 123,
"OrderedBy": "LAST_MODIFIED_DATE",
"Order": "ASCENDING",
},
"Parameters": {
"string": {
"Name": "string",
"Type": "string",
"CreateColumn": False,
"Filter": {
"Expression": "string",
"ValuesMap": {"string": "string"},
},
}
},
},
Tags=tags or {},
)
def _create_test_datasets(client, count):
for _ in range(count):
_create_test_dataset(client)
@mock_aws
def test_dataset_list_when_empty():
client = _create_databrew_client()
response = client.list_datasets()
assert "Datasets" in response
assert len(response["Datasets"]) == 0
@mock_aws
def test_list_datasets_with_max_results():
client = _create_databrew_client()
_create_test_datasets(client, 4)
response = client.list_datasets(MaxResults=2)
assert len(response["Datasets"]) == 2
assert "ResourceArn" in response["Datasets"][0]
assert "NextToken" in response
@mock_aws
def test_list_datasets_from_next_token():
client = _create_databrew_client()
_create_test_datasets(client, 10)
first_response = client.list_datasets(MaxResults=3)
response = client.list_datasets(NextToken=first_response["NextToken"])
assert len(response["Datasets"]) == 7
@mock_aws
def test_list_datasets_with_max_results_greater_than_actual_results():
client = _create_databrew_client()
_create_test_datasets(client, 4)
response = client.list_datasets(MaxResults=10)
assert len(response["Datasets"]) == 4
@mock_aws
def test_describe_dataset():
client = _create_databrew_client()
# region basic test
response = _create_test_dataset(client)
dataset = client.describe_dataset(Name=response["Name"])
assert dataset["Name"] == response["Name"]
assert (
dataset["ResourceArn"]
== f"arn:aws:databrew:us-west-1:{ACCOUNT_ID}:dataset/{response['Name']}"
)
# endregion
# region JSON test
response = _create_test_dataset(client, dataset_format="CSV")
dataset = client.describe_dataset(Name=response["Name"])
assert dataset["Format"] == "CSV"
# endregion
@mock_aws
def test_describe_dataset_that_does_not_exist():
client = _create_databrew_client()
with pytest.raises(ClientError) as exc:
client.describe_dataset(Name="DoseNotExist")
err = exc.value.response["Error"]
assert err["Code"] == "ResourceNotFoundException"
assert err["Message"] == "One or more resources can't be found."
@mock_aws
def test_create_dataset_that_already_exists():
client = _create_databrew_client()
response = _create_test_dataset(client)
with pytest.raises(ClientError) as exc:
_create_test_dataset(client, dataset_name=response["Name"])
err = exc.value.response["Error"]
assert err["Code"] == "AlreadyExistsException"
assert err["Message"] == f"{response['Name']} already exists."
@mock_aws
@pytest.mark.parametrize("name", ["name", "name with space"])
def test_delete_dataset(name):
client = _create_databrew_client()
response = _create_test_dataset(client, dataset_name=name)
assert response["Name"] == name
# Check dataset exists
dataset = client.describe_dataset(Name=name)
assert dataset["Name"] == name
# Delete the dataset
client.delete_dataset(Name=name)
# Check it does not exist anymore
with pytest.raises(ClientError) as exc:
client.describe_dataset(Name=name)
err = exc.value.response["Error"]
assert err["Code"] == "ResourceNotFoundException"
assert err["Message"] == "One or more resources can't be found."
# Check that a dataset that does not exist errors
with pytest.raises(ClientError) as exc:
client.delete_dataset(Name=name)
err = exc.value.response["Error"]
assert err["Code"] == "ResourceNotFoundException"
assert err["Message"] == "One or more resources can't be found."
@mock_aws
@pytest.mark.parametrize("name", ["name", "name with space"])
def test_update_dataset(name):
client = _create_databrew_client()
_create_test_dataset(client, dataset_name=name)
# Update the dataset and check response
dataset = client.update_dataset(
Name=name,
Format="TEST",
Input={
"S3InputDefinition": {
"Bucket": "somerandombucketname",
},
"DataCatalogInputDefinition": {
"DatabaseName": "somedbname",
"TableName": "sometablename",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
"DatabaseInputDefinition": {
"GlueConnectionName": "someglueconnectionname",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
},
)
assert dataset["Name"] == name
# Describe the dataset and check the changes
dataset = client.describe_dataset(Name=name)
assert dataset["Name"] == name
assert dataset["Format"] == "TEST"
assert (
dataset["ResourceArn"]
== f"arn:aws:databrew:us-west-1:{ACCOUNT_ID}:dataset/{name}"
)
@mock_aws
def test_update_dataset_that_does_not_exist():
client = _create_databrew_client()
# Update the dataset and check response
with pytest.raises(ClientError) as exc:
client.update_dataset(
Name="RANDOMNAME",
Format="TEST",
Input={
"S3InputDefinition": {
"Bucket": "somerandombucketname",
},
"DataCatalogInputDefinition": {
"DatabaseName": "somedbname",
"TableName": "sometablename",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
"DatabaseInputDefinition": {
"GlueConnectionName": "someglueconnectionname",
"TempDirectory": {
"Bucket": "sometempbucketname",
},
},
},
)
err = exc.value.response["Error"]
assert err["Code"] == "ResourceNotFoundException"
assert err["Message"] == "One or more resources can't be found."
|
