forked from apache/datafusion-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_context.py
More file actions
458 lines (341 loc) · 12.8 KB
/
test_context.py
File metadata and controls
458 lines (341 loc) · 12.8 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
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
446
447
448
449
450
451
452
453
454
455
456
457
458
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you 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.
import gzip
import os
import pyarrow as pa
import pyarrow.dataset as ds
import pytest
from datafusion import (
DataFrame,
RuntimeConfig,
SessionConfig,
SessionContext,
SQLOptions,
column,
literal,
)
def test_create_context_no_args():
SessionContext()
def test_create_context_with_all_valid_args():
runtime = RuntimeConfig().with_disk_manager_os().with_fair_spill_pool(10000000)
config = (
SessionConfig()
.with_create_default_catalog_and_schema(True)
.with_default_catalog_and_schema("foo", "bar")
.with_target_partitions(1)
.with_information_schema(True)
.with_repartition_joins(False)
.with_repartition_aggregations(False)
.with_repartition_windows(False)
.with_parquet_pruning(False)
)
ctx = SessionContext(config, runtime)
# verify that at least some of the arguments worked
ctx.catalog("foo").database("bar")
with pytest.raises(KeyError):
ctx.catalog("datafusion")
def test_register_record_batches(ctx):
# create a RecordBatch and register it as memtable
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
ctx.register_record_batches("t", [[batch]])
assert ctx.tables() == {"t"}
result = ctx.sql("SELECT a+b, a-b FROM t").collect()
assert result[0].column(0) == pa.array([5, 7, 9])
assert result[0].column(1) == pa.array([-3, -3, -3])
def test_create_dataframe_registers_unique_table_name(ctx):
# create a RecordBatch and register it as memtable
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
df = ctx.create_dataframe([[batch]])
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert len(tables[0]) == 33
assert tables[0].startswith("c")
# ensure that the rest of the table name contains
# only hexadecimal numbers
for c in tables[0][1:]:
assert c in "0123456789abcdef"
def test_create_dataframe_registers_with_defined_table_name(ctx):
# create a RecordBatch and register it as memtable
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
df = ctx.create_dataframe([[batch]], name="tbl")
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert tables[0] == "tbl"
def test_from_arrow_table(ctx):
# create a PyArrow table
data = {"a": [1, 2, 3], "b": [4, 5, 6]}
table = pa.Table.from_pydict(data)
# convert to DataFrame
df = ctx.from_arrow_table(table)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert type(df) == DataFrame
assert set(df.schema().names) == {"a", "b"}
assert df.collect()[0].num_rows == 3
def test_from_arrow_table_with_name(ctx):
# create a PyArrow table
data = {"a": [1, 2, 3], "b": [4, 5, 6]}
table = pa.Table.from_pydict(data)
# convert to DataFrame with optional name
df = ctx.from_arrow_table(table, name="tbl")
tables = list(ctx.tables())
assert df
assert tables[0] == "tbl"
def test_from_arrow_table_empty(ctx):
data = {"a": [], "b": []}
schema = pa.schema([("a", pa.int32()), ("b", pa.string())])
table = pa.Table.from_pydict(data, schema=schema)
# convert to DataFrame
df = ctx.from_arrow_table(table)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert isinstance(df, DataFrame)
assert set(df.schema().names) == {"a", "b"}
assert len(df.collect()) == 0
def test_from_arrow_table_empty_no_schema(ctx):
data = {"a": [], "b": []}
table = pa.Table.from_pydict(data)
# convert to DataFrame
df = ctx.from_arrow_table(table)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert isinstance(df, DataFrame)
assert set(df.schema().names) == {"a", "b"}
assert len(df.collect()) == 0
def test_from_pylist(ctx):
# create a dataframe from Python list
data = [
{"a": 1, "b": 4},
{"a": 2, "b": 5},
{"a": 3, "b": 6},
]
df = ctx.from_pylist(data)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert type(df) == DataFrame
assert set(df.schema().names) == {"a", "b"}
assert df.collect()[0].num_rows == 3
def test_from_pydict(ctx):
# create a dataframe from Python dictionary
data = {"a": [1, 2, 3], "b": [4, 5, 6]}
df = ctx.from_pydict(data)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert type(df) == DataFrame
assert set(df.schema().names) == {"a", "b"}
assert df.collect()[0].num_rows == 3
def test_from_pandas(ctx):
# create a dataframe from pandas dataframe
pd = pytest.importorskip("pandas")
data = {"a": [1, 2, 3], "b": [4, 5, 6]}
pandas_df = pd.DataFrame(data)
df = ctx.from_pandas(pandas_df)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert type(df) == DataFrame
assert set(df.schema().names) == {"a", "b"}
assert df.collect()[0].num_rows == 3
def test_from_polars(ctx):
# create a dataframe from Polars dataframe
pd = pytest.importorskip("polars")
data = {"a": [1, 2, 3], "b": [4, 5, 6]}
polars_df = pd.DataFrame(data)
df = ctx.from_polars(polars_df)
tables = list(ctx.tables())
assert df
assert len(tables) == 1
assert type(df) == DataFrame
assert set(df.schema().names) == {"a", "b"}
assert df.collect()[0].num_rows == 3
def test_register_table(ctx, database):
default = ctx.catalog()
public = default.database("public")
assert public.names() == {"csv", "csv1", "csv2"}
table = public.table("csv")
ctx.register_table("csv3", table)
assert public.names() == {"csv", "csv1", "csv2", "csv3"}
def test_read_table(ctx, database):
default = ctx.catalog()
public = default.database("public")
assert public.names() == {"csv", "csv1", "csv2"}
table = public.table("csv")
table_df = ctx.read_table(table)
table_df.show()
def test_deregister_table(ctx, database):
default = ctx.catalog()
public = default.database("public")
assert public.names() == {"csv", "csv1", "csv2"}
ctx.deregister_table("csv")
assert public.names() == {"csv1", "csv2"}
def test_register_dataset(ctx):
# create a RecordBatch and register it as a pyarrow.dataset.Dataset
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
dataset = ds.dataset([batch])
ctx.register_dataset("t", dataset)
assert ctx.tables() == {"t"}
result = ctx.sql("SELECT a+b, a-b FROM t").collect()
assert result[0].column(0) == pa.array([5, 7, 9])
assert result[0].column(1) == pa.array([-3, -3, -3])
def test_dataset_filter(ctx, capfd):
# create a RecordBatch and register it as a pyarrow.dataset.Dataset
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
dataset = ds.dataset([batch])
ctx.register_dataset("t", dataset)
assert ctx.tables() == {"t"}
df = ctx.sql("SELECT a+b, a-b FROM t WHERE a BETWEEN 2 and 3 AND b > 5")
# Make sure the filter was pushed down in Physical Plan
df.explain()
captured = capfd.readouterr()
assert "filter_expr=(((a >= 2) and (a <= 3)) and (b > 5))" in captured.out
result = df.collect()
assert result[0].column(0) == pa.array([9])
assert result[0].column(1) == pa.array([-3])
def test_dataset_filter_nested_data(ctx):
# create Arrow StructArrays to test nested data types
data = pa.StructArray.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
batch = pa.RecordBatch.from_arrays(
[data],
names=["nested_data"],
)
dataset = ds.dataset([batch])
ctx.register_dataset("t", dataset)
assert ctx.tables() == {"t"}
df = ctx.table("t")
# This filter will not be pushed down to DatasetExec since it
# isn't supported
df = df.filter(column("nested_data")["b"] > literal(5)).select(
column("nested_data")["a"] + column("nested_data")["b"],
column("nested_data")["a"] - column("nested_data")["b"],
)
result = df.collect()
assert result[0].column(0) == pa.array([9])
assert result[0].column(1) == pa.array([-3])
def test_table_exist(ctx):
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
dataset = ds.dataset([batch])
ctx.register_dataset("t", dataset)
assert ctx.table_exist("t") is True
def test_read_json(ctx):
path = os.path.dirname(os.path.abspath(__file__))
# Default
test_data_path = os.path.join(path, "data_test_context", "data.json")
df = ctx.read_json(test_data_path)
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].column(1) == pa.array([1, 2, 3])
# Schema
schema = pa.schema(
[
pa.field("A", pa.string(), nullable=True),
]
)
df = ctx.read_json(test_data_path, schema=schema)
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].schema == schema
# File extension
test_data_path = os.path.join(path, "data_test_context", "data.json")
df = ctx.read_json(test_data_path, file_extension=".json")
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].column(1) == pa.array([1, 2, 3])
def test_read_json_compressed(ctx, tmp_path):
path = os.path.dirname(os.path.abspath(__file__))
test_data_path = os.path.join(path, "data_test_context", "data.json")
# File compression type
gzip_path = tmp_path / "data.json.gz"
with open(test_data_path, "rb") as csv_file:
with gzip.open(gzip_path, "wb") as gzipped_file:
gzipped_file.writelines(csv_file)
df = ctx.read_json(gzip_path, file_extension=".gz", file_compression_type="gz")
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].column(1) == pa.array([1, 2, 3])
def test_read_csv(ctx):
csv_df = ctx.read_csv(path="testing/data/csv/aggregate_test_100.csv")
csv_df.select(column("c1")).show()
def test_read_csv_compressed(ctx, tmp_path):
test_data_path = "testing/data/csv/aggregate_test_100.csv"
# File compression type
gzip_path = tmp_path / "aggregate_test_100.csv.gz"
with open(test_data_path, "rb") as csv_file:
with gzip.open(gzip_path, "wb") as gzipped_file:
gzipped_file.writelines(csv_file)
csv_df = ctx.read_csv(gzip_path, file_extension=".gz", file_compression_type="gz")
csv_df.select(column("c1")).show()
def test_read_parquet(ctx):
csv_df = ctx.read_parquet(path="parquet/data/alltypes_plain.parquet")
csv_df.show()
def test_read_avro(ctx):
csv_df = ctx.read_avro(path="testing/data/avro/alltypes_plain.avro")
csv_df.show()
def test_create_sql_options():
SQLOptions()
def test_sql_with_options_no_ddl(ctx):
sql = "CREATE TABLE IF NOT EXISTS valuetable AS VALUES(1,'HELLO'),(12,'DATAFUSION')"
ctx.sql(sql)
options = SQLOptions().with_allow_ddl(False)
with pytest.raises(Exception, match="DDL"):
ctx.sql_with_options(sql, options=options)
def test_sql_with_options_no_dml(ctx):
table_name = "t"
batch = pa.RecordBatch.from_arrays(
[pa.array([1, 2, 3]), pa.array([4, 5, 6])],
names=["a", "b"],
)
dataset = ds.dataset([batch])
ctx.register_dataset(table_name, dataset)
sql = f'INSERT INTO "{table_name}" VALUES (1, 2), (2, 3);'
ctx.sql(sql)
options = SQLOptions().with_allow_dml(False)
with pytest.raises(Exception, match="DML"):
ctx.sql_with_options(sql, options=options)
def test_sql_with_options_no_statements(ctx):
sql = "SET time zone = 1;"
ctx.sql(sql)
options = SQLOptions().with_allow_statements(False)
with pytest.raises(Exception, match="SetVariable"):
ctx.sql_with_options(sql, options=options)