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
|
#!/usr/bin/env python3
##
# 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
#
# https://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 contextlib
import itertools
import os
import tempfile
import unittest
import avro.codecs
import avro.datafile
import avro.io
import avro.schema
CODECS_TO_VALIDATE = avro.codecs.KNOWN_CODECS.keys()
TEST_PAIRS = tuple(
(avro.schema.parse(schema), datum)
for schema, datum in (
('"null"', None),
('"boolean"', True),
('"string"', "adsfasdf09809dsf-=adsf"),
('"bytes"', b"12345abcd"),
('"int"', 1234),
('"long"', 1234),
('"float"', 1234.0),
('"double"', 1234.0),
('{"type": "fixed", "name": "Test", "size": 1}', b"B"),
('{"type": "enum", "name": "Test", "symbols": ["A", "B"]}', "B"),
('{"type": "array", "items": "long"}', [1, 3, 2]),
('{"type": "map", "values": "long"}', {"a": 1, "b": 3, "c": 2}),
('["string", "null", "long"]', None),
(
"""\
{"type": "record",
"name": "Test",
"fields": [{"name": "f", "type": "long"}]}
""",
{"f": 5},
),
(
"""\
{"type": "record",
"name": "Lisp",
"fields": [{"name": "value",
"type": ["null", "string",
{"type": "record",
"name": "Cons",
"fields": [{"name": "car", "type": "Lisp"},
{"name": "cdr", "type": "Lisp"}]}]}]}
""",
{"value": {"car": {"value": "head"}, "cdr": {"value": None}}},
),
)
)
@contextlib.contextmanager
def writer(path, schema=None, codec=avro.datafile.NULL_CODEC, mode="wb"):
with avro.datafile.DataFileWriter(open(path, mode), avro.io.DatumWriter(), schema, codec) as dfw:
yield dfw
@contextlib.contextmanager
def reader(path, mode="rb"):
with avro.datafile.DataFileReader(open(path, mode), avro.io.DatumReader()) as dfr:
yield dfr
class TestDataFile(unittest.TestCase):
files = None
def setUp(self):
"""Initialize tempfiles collection."""
self.files = []
def tempfile(self):
"""Generate a tempfile and register it for cleanup."""
with tempfile.NamedTemporaryFile(delete=False, suffix=".avro") as f:
pass
self.files.append(f.name)
return f.name
def tearDown(self):
"""Clean up temporary files."""
for f in self.files:
os.unlink(f)
def test_append(self):
"""A datafile can be written to, appended to, and read from."""
for codec in CODECS_TO_VALIDATE:
for schema, datum in TEST_PAIRS:
# write data in binary to file once
path = self.tempfile()
with writer(path, schema, codec) as dfw:
dfw.append(datum)
# open file, write, and close nine times
for _ in range(9):
with writer(path, mode="ab+") as dfw:
dfw.append(datum)
# read data in binary from file
with reader(path) as dfr:
data = list(itertools.islice(dfr, 10))
self.assertRaises(StopIteration, next, dfr)
self.assertEqual(len(data), 10)
self.assertEqual(data, [datum] * 10)
def test_round_trip(self):
"""A datafile can be written to and read from."""
for codec in CODECS_TO_VALIDATE:
for schema, datum in TEST_PAIRS:
# write data in binary to file 10 times
path = self.tempfile()
with writer(path, schema, codec) as dfw:
for _ in range(10):
dfw.append(datum)
# read data in binary from file
with reader(path) as dfr:
data = list(itertools.islice(dfr, 10))
self.assertRaises(StopIteration, next, dfr)
self.assertEqual(len(data), 10)
self.assertEqual(data, [datum] * 10)
def test_context_manager(self):
"""A datafile closes its buffer object when it exits a with block."""
path = self.tempfile()
for schema, _ in TEST_PAIRS:
with writer(path, schema) as dfw:
self.assertFalse(dfw.writer.closed)
self.assertTrue(dfw.writer.closed)
with reader(path) as dfr:
self.assertFalse(dfr.reader.closed)
self.assertTrue(dfr.reader.closed)
def test_metadata(self):
"""Metadata can be written to a datafile, and read from it later."""
path = self.tempfile()
for schema, _ in TEST_PAIRS:
with writer(path, schema) as dfw:
dfw.set_meta("test.string", b"foo")
dfw.set_meta("test.number", b"1")
with reader(path) as dfr:
self.assertEqual(b"foo", dfr.get_meta("test.string"))
self.assertEqual(b"1", dfr.get_meta("test.number"))
def test_empty_datafile(self):
"""A reader should not fail to read a file consisting of a single empty block."""
path = self.tempfile()
for schema, _ in TEST_PAIRS:
with writer(path, schema) as dfw:
dfw.flush()
# Write an empty block
dfw.encoder.write_long(0)
dfw.encoder.write_long(0)
dfw.writer.write(dfw.sync_marker)
with reader(path) as dfr:
self.assertRaises(StopIteration, next, dfr)
|
