forked from huggingface/transformers
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_doc_samples.py
114 lines (97 loc) · 4.33 KB
/
test_doc_samples.py
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
# coding=utf-8
# Copyright 2019-present, the HuggingFace Inc. team.
#
# 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.
import doctest
import logging
import os
import unittest
from pathlib import Path
from typing import List, Union
import transformers
from transformers.testing_utils import require_tf, require_torch, slow
logger = logging.getLogger()
@unittest.skip("Temporarily disable the doc tests.")
@require_torch
@require_tf
@slow
class TestCodeExamples(unittest.TestCase):
def analyze_directory(
self,
directory: Path,
identifier: Union[str, None] = None,
ignore_files: Union[List[str], None] = None,
n_identifier: Union[str, List[str], None] = None,
only_modules: bool = True,
):
"""
Runs through the specific directory, looking for the files identified with `identifier`. Executes
the doctests in those files
Args:
directory (:obj:`Path`): Directory containing the files
identifier (:obj:`str`): Will parse files containing this
ignore_files (:obj:`List[str]`): List of files to skip
n_identifier (:obj:`str` or :obj:`List[str]`): Will not parse files containing this/these identifiers.
only_modules (:obj:`bool`): Whether to only analyze modules
"""
files = [file for file in os.listdir(directory) if os.path.isfile(os.path.join(directory, file))]
if identifier is not None:
files = [file for file in files if identifier in file]
if n_identifier is not None:
if isinstance(n_identifier, List):
for n_ in n_identifier:
files = [file for file in files if n_ not in file]
else:
files = [file for file in files if n_identifier not in file]
ignore_files = ignore_files or []
ignore_files.append("__init__.py")
files = [file for file in files if file not in ignore_files]
for file in files:
# Open all files
print("Testing", file)
if only_modules:
module_identifier = file.split(".")[0]
try:
module_identifier = getattr(transformers, module_identifier)
suite = doctest.DocTestSuite(module_identifier)
result = unittest.TextTestRunner().run(suite)
self.assertIs(len(result.failures), 0)
except AttributeError:
logger.info(f"{module_identifier} is not a module.")
else:
result = doctest.testfile(str(".." / directory / file), optionflags=doctest.ELLIPSIS)
self.assertIs(result.failed, 0)
def test_modeling_examples(self):
transformers_directory = Path("src/transformers")
files = "modeling"
ignore_files = [
"modeling_ctrl.py",
"modeling_tf_ctrl.py",
]
self.analyze_directory(transformers_directory, identifier=files, ignore_files=ignore_files)
def test_tokenization_examples(self):
transformers_directory = Path("src/transformers")
files = "tokenization"
self.analyze_directory(transformers_directory, identifier=files)
def test_configuration_examples(self):
transformers_directory = Path("src/transformers")
files = "configuration"
self.analyze_directory(transformers_directory, identifier=files)
def test_remaining_examples(self):
transformers_directory = Path("src/transformers")
n_identifiers = ["configuration", "modeling", "tokenization"]
self.analyze_directory(transformers_directory, n_identifier=n_identifiers)
def test_doc_sources(self):
doc_source_directory = Path("docs/source")
ignore_files = ["favicon.ico"]
self.analyze_directory(doc_source_directory, ignore_files=ignore_files, only_modules=False)