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
|
import click
import json
import pytest
from click.testing import CliRunner
from sqlite_utils import Database, cli
def test_memory_basic():
result = CliRunner().invoke(cli.cli, ["memory", "select 1 + 1"])
assert result.exit_code == 0
assert result.output.strip() == '[{"1 + 1": 2}]'
@pytest.mark.parametrize("sql_from", ("test", "t", "t1"))
@pytest.mark.parametrize("use_stdin", (True, False))
def test_memory_csv(tmpdir, sql_from, use_stdin):
content = "id,name\n1,Cleo\n2,Bants"
input = None
if use_stdin:
input = content
csv_path = "-"
if sql_from == "test":
sql_from = "stdin"
else:
csv_path = str(tmpdir / "test.csv")
with open(csv_path, "w") as fp:
fp.write(content)
result = CliRunner().invoke(
cli.cli,
["memory", csv_path, "select * from {}".format(sql_from), "--nl"],
input=input,
)
assert result.exit_code == 0
assert (
result.output.strip() == '{"id": 1, "name": "Cleo"}\n{"id": 2, "name": "Bants"}'
)
@pytest.mark.parametrize("use_stdin", (True, False))
def test_memory_tsv(tmpdir, use_stdin):
data = "id\tname\n1\tCleo\n2\tBants"
if use_stdin:
input = data
path = "stdin:tsv"
sql_from = "stdin"
else:
input = None
path = str(tmpdir / "chickens.tsv")
with open(path, "w") as fp:
fp.write(data)
path = path + ":tsv"
sql_from = "chickens"
result = CliRunner().invoke(
cli.cli,
["memory", path, "select * from {}".format(sql_from)],
input=input,
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == [
{"id": 1, "name": "Cleo"},
{"id": 2, "name": "Bants"},
]
@pytest.mark.parametrize("use_stdin", (True, False))
def test_memory_json(tmpdir, use_stdin):
data = '[{"name": "Bants"}, {"name": "Dori", "age": 1, "nested": {"nest": 1}}]'
if use_stdin:
input = data
path = "stdin:json"
sql_from = "stdin"
else:
input = None
path = str(tmpdir / "chickens.json")
with open(path, "w") as fp:
fp.write(data)
path = path + ":json"
sql_from = "chickens"
result = CliRunner().invoke(
cli.cli,
["memory", path, "select * from {}".format(sql_from)],
input=input,
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == [
{"name": "Bants", "age": None, "nested": None},
{"name": "Dori", "age": 1, "nested": '{"nest": 1}'},
]
@pytest.mark.parametrize("use_stdin", (True, False))
def test_memory_json_nl(tmpdir, use_stdin):
data = '{"name": "Bants"}\n\n{"name": "Dori"}'
if use_stdin:
input = data
path = "stdin:nl"
sql_from = "stdin"
else:
input = None
path = str(tmpdir / "chickens.json")
with open(path, "w") as fp:
fp.write(data)
path = path + ":nl"
sql_from = "chickens"
result = CliRunner().invoke(
cli.cli,
["memory", path, "select * from {}".format(sql_from)],
input=input,
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == [
{"name": "Bants"},
{"name": "Dori"},
]
@pytest.mark.parametrize("use_stdin", (True, False))
def test_memory_csv_encoding(tmpdir, use_stdin):
latin1_csv = (
b"date,name,latitude,longitude\n" b"2020-03-04,S\xe3o Paulo,-23.561,-46.645\n"
)
input = None
if use_stdin:
input = latin1_csv
csv_path = "-"
sql_from = "stdin"
else:
csv_path = str(tmpdir / "test.csv")
with open(csv_path, "wb") as fp:
fp.write(latin1_csv)
sql_from = "test"
# Without --encoding should error:
assert (
CliRunner()
.invoke(
cli.cli,
["memory", csv_path, "select * from {}".format(sql_from), "--nl"],
input=input,
)
.exit_code
== 1
)
# With --encoding should work:
result = CliRunner().invoke(
cli.cli,
["memory", "-", "select * from stdin", "--encoding", "latin-1", "--nl"],
input=latin1_csv,
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == {
"date": "2020-03-04",
"name": "São Paulo",
"latitude": -23.561,
"longitude": -46.645,
}
@pytest.mark.parametrize("extra_args", ([], ["select 1"]))
def test_memory_dump(extra_args):
result = CliRunner().invoke(
cli.cli,
["memory", "-"] + extra_args + ["--dump"],
input="id,name\n1,Cleo\n2,Bants",
)
assert result.exit_code == 0
expected = (
"BEGIN TRANSACTION;\n"
'CREATE TABLE IF NOT EXISTS "stdin" (\n'
" [id] INTEGER,\n"
" [name] TEXT\n"
");\n"
"INSERT INTO \"stdin\" VALUES(1,'Cleo');\n"
"INSERT INTO \"stdin\" VALUES(2,'Bants');\n"
"CREATE VIEW t1 AS select * from [stdin];\n"
"CREATE VIEW t AS select * from [stdin];\n"
"COMMIT;"
)
# Using sqlite-dump it won't have IF NOT EXISTS
expected_alternative = expected.replace("IF NOT EXISTS ", "")
assert result.output.strip() in (expected, expected_alternative)
@pytest.mark.parametrize("extra_args", ([], ["select 1"]))
def test_memory_schema(extra_args):
result = CliRunner().invoke(
cli.cli,
["memory", "-"] + extra_args + ["--schema"],
input="id,name\n1,Cleo\n2,Bants",
)
assert result.exit_code == 0
assert result.output.strip() == (
'CREATE TABLE "stdin" (\n'
" [id] INTEGER,\n"
" [name] TEXT\n"
");\n"
"CREATE VIEW t1 AS select * from [stdin];\n"
"CREATE VIEW t AS select * from [stdin];"
)
@pytest.mark.parametrize("extra_args", ([], ["select 1"]))
def test_memory_save(tmpdir, extra_args):
save_to = str(tmpdir / "save.db")
result = CliRunner().invoke(
cli.cli,
["memory", "-"] + extra_args + ["--save", save_to],
input="id,name\n1,Cleo\n2,Bants",
)
assert result.exit_code == 0
db = Database(save_to)
assert list(db["stdin"].rows) == [
{"id": 1, "name": "Cleo"},
{"id": 2, "name": "Bants"},
]
@pytest.mark.parametrize("option", ("-n", "--no-detect-types"))
def test_memory_no_detect_types(option):
result = CliRunner().invoke(
cli.cli,
["memory", "-", "select * from stdin"] + [option],
input="id,name,weight\n1,Cleo,45.5\n2,Bants,3.5",
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == [
{"id": "1", "name": "Cleo", "weight": "45.5"},
{"id": "2", "name": "Bants", "weight": "3.5"},
]
def test_memory_flatten():
result = CliRunner().invoke(
cli.cli,
["memory", "-", "select * from stdin", "--flatten"],
input=json.dumps(
{
"httpRequest": {
"latency": "0.112114537s",
"requestMethod": "GET",
},
"insertId": "6111722f000b5b4c4d4071e2",
}
),
)
assert result.exit_code == 0, result.output
assert json.loads(result.output.strip()) == [
{
"httpRequest_latency": "0.112114537s",
"httpRequest_requestMethod": "GET",
"insertId": "6111722f000b5b4c4d4071e2",
}
]
def test_memory_analyze():
result = CliRunner().invoke(
cli.cli,
["memory", "-", "--analyze"],
input="id,name\n1,Cleo\n2,Bants",
)
assert result.exit_code == 0
assert result.output == (
"stdin.id: (1/2)\n\n"
" Total rows: 2\n"
" Null rows: 0\n"
" Blank rows: 0\n\n"
" Distinct values: 2\n\n"
"stdin.name: (2/2)\n\n"
" Total rows: 2\n"
" Null rows: 0\n"
" Blank rows: 0\n\n"
" Distinct values: 2\n\n"
)
def test_memory_two_files_with_same_stem(tmpdir):
(tmpdir / "one").mkdir()
(tmpdir / "two").mkdir()
one = tmpdir / "one" / "data.csv"
two = tmpdir / "two" / "data.csv"
one.write_text("id,name\n1,Cleo\n2,Bants", encoding="utf-8")
two.write_text("id,name\n3,Blue\n4,Lila", encoding="utf-8")
result = CliRunner().invoke(cli.cli, ["memory", str(one), str(two), "", "--schema"])
assert result.exit_code == 0
assert result.output == (
'CREATE TABLE "data" (\n'
" [id] INTEGER,\n"
" [name] TEXT\n"
");\n"
"CREATE VIEW t1 AS select * from [data];\n"
"CREATE VIEW t AS select * from [data];\n"
'CREATE TABLE "data_2" (\n'
" [id] INTEGER,\n"
" [name] TEXT\n"
");\n"
"CREATE VIEW t2 AS select * from [data_2];\n"
)
def test_memory_functions():
result = CliRunner().invoke(
cli.cli,
["memory", "select hello()", "--functions", "hello = lambda: 'Hello'"],
)
assert result.exit_code == 0
assert result.output.strip() == '[{"hello()": "Hello"}]'
def test_memory_return_db(tmpdir):
# https://github.com/simonw/sqlite-utils/issues/643
from sqlite_utils.cli import cli
path = str(tmpdir / "dogs.csv")
open(path, "w").write("id,name\n1,Cleo")
with click.Context(cli) as ctx:
db = ctx.invoke(cli.commands["memory"], paths=(path,), return_db=True)
assert db.table_names() == ["dogs"]
|
