create_circleci_config.py 25.6 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
# coding=utf-8
# Copyright 2022 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 argparse
import copy
18
import glob
19
import os
20
import random
21
22
23
from dataclasses import dataclass
from typing import Any, Dict, List, Optional

24
import yaml
25
26


27
28
29
30
31
32
33
34
COMMON_ENV_VARIABLES = {
    "OMP_NUM_THREADS": 1,
    "TRANSFORMERS_IS_CI": True,
    "PYTEST_TIMEOUT": 120,
    "RUN_PIPELINE_TESTS": False,
    "RUN_PT_TF_CROSS_TESTS": False,
    "RUN_PT_FLAX_CROSS_TESTS": False,
}
Yih-Dar's avatar
Yih-Dar committed
35
36
# Disable the use of {"s": None} as the output is way too long, causing the navigation on CircleCI impractical
COMMON_PYTEST_OPTIONS = {"max-worker-restart": 0, "dist": "loadfile"}
37
DEFAULT_DOCKER_IMAGE = [{"image": "cimg/python:3.8.12"}]
38
39


40
41
42
43
44
45
46
47
48
49
50
class EmptyJob:
    job_name = "empty"

    def to_dict(self):
        return {
            "working_directory": "~/transformers",
            "docker": copy.deepcopy(DEFAULT_DOCKER_IMAGE),
            "steps":["checkout"],
        }


51
52
53
54
55
@dataclass
class CircleCIJob:
    name: str
    additional_env: Dict[str, Any] = None
    cache_name: str = None
Yih-Dar's avatar
Yih-Dar committed
56
    cache_version: str = "0.7"
57
58
59
60
61
62
63
64
65
    docker_image: List[Dict[str, str]] = None
    install_steps: List[str] = None
    marker: Optional[str] = None
    parallelism: Optional[int] = 1
    pytest_num_workers: int = 8
    pytest_options: Dict[str, Any] = None
    resource_class: Optional[str] = "xlarge"
    tests_to_run: Optional[List[str]] = None
    working_directory: str = "~/transformers"
66
67
    # This should be only used for doctest job!
    command_timeout: Optional[int] = None
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83

    def __post_init__(self):
        # Deal with defaults for mutable attributes.
        if self.additional_env is None:
            self.additional_env = {}
        if self.cache_name is None:
            self.cache_name = self.name
        if self.docker_image is None:
            # Let's avoid changing the default list and make a copy.
            self.docker_image = copy.deepcopy(DEFAULT_DOCKER_IMAGE)
        if self.install_steps is None:
            self.install_steps = []
        if self.pytest_options is None:
            self.pytest_options = {}
        if isinstance(self.tests_to_run, str):
            self.tests_to_run = [self.tests_to_run]
84
85
        if self.parallelism is None:
            self.parallelism = 1
86
87

    def to_dict(self):
88
89
        env = COMMON_ENV_VARIABLES.copy()
        env.update(self.additional_env)
90
91
92
93
94

        cache_branch_prefix = os.environ.get("CIRCLE_BRANCH", "pull")
        if cache_branch_prefix != "main":
            cache_branch_prefix = "pull"

95
96
97
        job = {
            "working_directory": self.working_directory,
            "docker": self.docker_image,
98
            "environment": env,
99
100
101
102
103
104
105
106
107
108
109
        }
        if self.resource_class is not None:
            job["resource_class"] = self.resource_class
        if self.parallelism is not None:
            job["parallelism"] = self.parallelism
        steps = [
            "checkout",
            {"attach_workspace": {"at": "~/transformers/test_preparation"}},
            {
                "restore_cache": {
                    "keys": [
110
                        # check the fully-matched cache first
111
                        f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-pip-" + '{{ checksum "setup.py" }}',
112
113
114
115
                        # try the partially-matched cache from `main`
                        f"v{self.cache_version}-{self.cache_name}-main-pip-",
                        # try the general partially-matched cache
                        f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-pip-",
116
117
118
                    ]
                }
            },
119
120
121
            {
                "restore_cache": {
                    "keys": [
122
                        f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-site-packages-" + '{{ checksum "setup.py" }}',
123
124
                        f"v{self.cache_version}-{self.cache_name}-main-site-packages-",
                        f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-site-packages-",
125
126
127
                    ]
                }
            },
128
129
        ]
        steps.extend([{"run": l} for l in self.install_steps])
130
131
132
133
134
        steps.append(
            {
                "save_cache": {
                    "key": f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-pip-" + '{{ checksum "setup.py" }}',
                    "paths": ["~/.cache/pip"],
135
                }
136
137
138
139
140
141
142
            }
        )
        steps.append(
            {
                "save_cache": {
                    "key": f"v{self.cache_version}-{self.cache_name}-{cache_branch_prefix}-site-packages-" + '{{ checksum "setup.py" }}',
                    "paths": ["~/.pyenv/versions/"],
143
                }
144
145
            }
        )
146
147
        steps.append({"run": {"name": "Show installed libraries and their versions", "command": "pip freeze | tee installed.txt"}})
        steps.append({"store_artifacts": {"path": "~/transformers/installed.txt"}})
148
149

        all_options = {**COMMON_PYTEST_OPTIONS, **self.pytest_options}
150
        pytest_flags = [f"--{key}={value}" if (value is not None or key in ["doctest-modules"]) else f"-{key}" for key, value in all_options.items()]
151
152
153
        pytest_flags.append(
            f"--make-reports={self.name}" if "examples" in self.name else f"--make-reports=tests_{self.name}"
        )
154
155
156
157
        test_command = ""
        if self.command_timeout:
            test_command = f"timeout {self.command_timeout} "
        test_command += f"python -m pytest -n {self.pytest_num_workers} " + " ".join(pytest_flags)
amyeroberts's avatar
amyeroberts committed
158

159
160
161
162
163
        if self.parallelism == 1:
            if self.tests_to_run is None:
                test_command += " << pipeline.parameters.tests_to_run >>"
            else:
                test_command += " " + " ".join(self.tests_to_run)
164
        else:
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
            # We need explicit list instead of `pipeline.parameters.tests_to_run` (only available at job runtime)
            tests = self.tests_to_run
            if tests is None:
                folder = os.environ["test_preparation_dir"]
                test_file = os.path.join(folder, "filtered_test_list.txt")
                if os.path.exists(test_file):
                    with open(test_file) as f:
                        tests = f.read().split(" ")

            # expand the test list
            if tests == ["tests"]:
                tests = [os.path.join("tests", x) for x in os.listdir("tests")]
            expanded_tests = []
            for test in tests:
                if test.endswith(".py"):
                    expanded_tests.append(test)
                elif test == "tests/models":
                    expanded_tests.extend([os.path.join(test, x) for x in os.listdir(test)])
                elif test == "tests/pipelines":
                    expanded_tests.extend([os.path.join(test, x) for x in os.listdir(test)])
                else:
                    expanded_tests.append(test)
            # Avoid long tests always being collected together
            random.shuffle(expanded_tests)
            tests = " ".join(expanded_tests)

            # Each executor to run ~10 tests
            n_executors = max(len(tests) // 10, 1)
            # Avoid empty test list on some executor(s) or launching too many executors
            if n_executors > self.parallelism:
                n_executors = self.parallelism
            job["parallelism"] = n_executors

            # Need to be newline separated for the command `circleci tests split` below
            command = f'echo {tests} | tr " " "\\n" >> tests.txt'
            steps.append({"run": {"name": "Get tests", "command": command}})

            command = 'TESTS=$(circleci tests split tests.txt) && echo $TESTS > splitted_tests.txt'
            steps.append({"run": {"name": "Split tests", "command": command}})

            steps.append({"store_artifacts": {"path": "~/transformers/tests.txt"}})
            steps.append({"store_artifacts": {"path": "~/transformers/splitted_tests.txt"}})

208
209
210
211
            test_command = ""
            if self.timeout:
                test_command = f"timeout {self.timeout} "
            test_command += f"python -m pytest -n {self.pytest_num_workers} " + " ".join(pytest_flags)
212
            test_command += " $(cat splitted_tests.txt)"
213
214
        if self.marker is not None:
            test_command += f" -m {self.marker}"
215
216
217
218
219
220
221
222
223
224
225

        if self.name == "pr_documentation_tests":
            # can't use ` | tee tee tests_output.txt` as usual
            test_command += " > tests_output.txt"
            # Save the return code, so we can check if it is timeout in the next step.
            test_command += '; touch "$?".txt'
            # Never fail the test step for the doctest job. We will check the results in the next step, and fail that
            # step instead if the actual test failures are found. This is to avoid the timeout being reported as test
            # failure.
            test_command = f"({test_command}) || true"
        else:
226
            test_command += " || true"
227
        steps.append({"run": {"name": "Run tests", "command": test_command}})
228

229
        check_test_command = f'if [ -s reports/{self.job_name}/failures_short.txt ]; '
230
        check_test_command += 'then echo "Some test failed!"; echo ""; '
231
        check_test_command += f'cat reports/{self.job_name}/failures_short.txt; '
232
233
        check_test_command += 'echo ""; echo ""; '

Yih-Dar's avatar
Yih-Dar committed
234
        py_command = f'import os; fp = open("reports/{self.job_name}/summary_short.txt"); failed = os.linesep.join([x for x in fp.read().split(os.linesep) if x.startswith(("FAILED ", "ERROR "))]); fp.close(); fp = open("summary_short.txt", "w"); fp.write(failed); fp.close()'
235
236
237
        check_test_command += f"$(python3 -c '{py_command}'); "

        check_test_command += f'cat summary_short.txt; echo ""; exit -1; '
238
        check_test_command += f'elif [ -s reports/{self.job_name}/stats.txt ]; then echo "All tests pass!"; '
239

240
241
        # return code `124` means the previous (pytest run) step is timeout
        if self.name == "pr_documentation_tests":
242
243
244
245
246
            check_test_command += 'elif [ -f 124.txt ]; then echo "doctest timeout!"; '

        check_test_command += 'else echo "other fatal error"; echo ""; exit -1; fi;'

        steps.append({"run": {"name": "Check test results", "command": check_test_command}})
247

248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
        steps.append({"store_artifacts": {"path": "~/transformers/tests_output.txt"}})
        steps.append({"store_artifacts": {"path": "~/transformers/reports"}})
        job["steps"] = steps
        return job

    @property
    def job_name(self):
        return self.name if "examples" in self.name else f"tests_{self.name}"


# JOBS
torch_and_tf_job = CircleCIJob(
    "torch_and_tf",
    additional_env={"RUN_PT_TF_CROSS_TESTS": True},
    install_steps=[
263
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng git-lfs cmake",
264
        "git lfs install",
Yih-Dar's avatar
Yih-Dar committed
265
266
267
268
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,tf-cpu,torch,testing,sentencepiece,torch-speech,vision]",
        "pip install -U --upgrade-strategy eager tensorflow_probability",
        "pip install -U --upgrade-strategy eager git+https://github.com/huggingface/accelerate",
269
270
271
272
273
274
275
276
277
278
279
    ],
    marker="is_pt_tf_cross_test",
    pytest_options={"rA": None, "durations": 0},
)


torch_and_flax_job = CircleCIJob(
    "torch_and_flax",
    additional_env={"RUN_PT_FLAX_CROSS_TESTS": True},
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng",
Yih-Dar's avatar
Yih-Dar committed
280
281
282
        "pip install -U --upgrade-strategy eager --upgrade pip",
        "pip install -U --upgrade-strategy eager .[sklearn,flax,torch,testing,sentencepiece,torch-speech,vision]",
        "pip install -U --upgrade-strategy eager git+https://github.com/huggingface/accelerate",
283
284
285
286
287
288
289
290
291
292
    ],
    marker="is_pt_flax_cross_test",
    pytest_options={"rA": None, "durations": 0},
)


torch_job = CircleCIJob(
    "torch",
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng time",
Yih-Dar's avatar
Yih-Dar committed
293
294
295
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,torch,testing,sentencepiece,torch-speech,vision,timm]",
        "pip install -U --upgrade-strategy eager git+https://github.com/huggingface/accelerate",
296
    ],
297
    parallelism=1,
298
    pytest_num_workers=8,
299
300
301
302
303
304
)


tf_job = CircleCIJob(
    "tf",
    install_steps=[
305
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng cmake",
Yih-Dar's avatar
Yih-Dar committed
306
307
308
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,tf-cpu,testing,sentencepiece,tf-speech,vision]",
        "pip install -U --upgrade-strategy eager tensorflow_probability",
309
    ],
310
    parallelism=1,
311
312
313
314
315
316
317
)


flax_job = CircleCIJob(
    "flax",
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng",
Yih-Dar's avatar
Yih-Dar committed
318
319
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[flax,testing,sentencepiece,flax-speech,vision]",
320
    ],
321
    parallelism=1,
322
323
324
325
326
)


pipelines_torch_job = CircleCIJob(
    "pipelines_torch",
327
    additional_env={"RUN_PIPELINE_TESTS": True},
328
329
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng",
Yih-Dar's avatar
Yih-Dar committed
330
331
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,torch,testing,sentencepiece,torch-speech,vision,timm,video]",
332
    ],
333
    marker="is_pipeline_test",
334
335
336
337
338
)


pipelines_tf_job = CircleCIJob(
    "pipelines_tf",
339
    additional_env={"RUN_PIPELINE_TESTS": True},
340
    install_steps=[
Sylvain Gugger's avatar
Sylvain Gugger committed
341
        "sudo apt-get -y update && sudo apt-get install -y cmake",
Yih-Dar's avatar
Yih-Dar committed
342
343
344
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,tf-cpu,testing,sentencepiece,vision]",
        "pip install -U --upgrade-strategy eager tensorflow_probability",
345
    ],
346
    marker="is_pipeline_test",
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
)


custom_tokenizers_job = CircleCIJob(
    "custom_tokenizers",
    additional_env={"RUN_CUSTOM_TOKENIZERS": True},
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y cmake",
        {
            "name": "install jumanpp",
            "command":
                "wget https://github.com/ku-nlp/jumanpp/releases/download/v2.0.0-rc3/jumanpp-2.0.0-rc3.tar.xz\n"
                "tar xvf jumanpp-2.0.0-rc3.tar.xz\n"
                "mkdir jumanpp-2.0.0-rc3/bld\n"
                "cd jumanpp-2.0.0-rc3/bld\n"
                "sudo cmake .. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr/local\n"
                "sudo make install\n",
        },
Yih-Dar's avatar
Yih-Dar committed
365
366
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[ja,testing,sentencepiece,jieba,spacy,ftfy,rjieba]",
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
        "python -m unidic download",
    ],
    parallelism=None,
    resource_class=None,
    tests_to_run=[
        "./tests/models/bert_japanese/test_tokenization_bert_japanese.py",
        "./tests/models/openai/test_tokenization_openai.py",
        "./tests/models/clip/test_tokenization_clip.py",
    ],
)


examples_torch_job = CircleCIJob(
    "examples_torch",
    cache_name="torch_examples",
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng",
Yih-Dar's avatar
Yih-Dar committed
384
385
386
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,torch,sentencepiece,testing,torch-speech]",
        "pip install -U --upgrade-strategy eager -r examples/pytorch/_tests_requirements.txt",
387
388
389
390
391
392
393
394
    ],
)


examples_tensorflow_job = CircleCIJob(
    "examples_tensorflow",
    cache_name="tensorflow_examples",
    install_steps=[
395
        "sudo apt-get -y update && sudo apt-get install -y cmake",
Yih-Dar's avatar
Yih-Dar committed
396
397
398
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[sklearn,tensorflow,sentencepiece,testing]",
        "pip install -U --upgrade-strategy eager -r examples/tensorflow/_tests_requirements.txt",
399
400
401
402
403
404
405
406
    ],
)


examples_flax_job = CircleCIJob(
    "examples_flax",
    cache_name="flax_examples",
    install_steps=[
Yih-Dar's avatar
Yih-Dar committed
407
408
409
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[flax,testing,sentencepiece]",
        "pip install -U --upgrade-strategy eager -r examples/flax/_tests_requirements.txt",
410
411
412
413
414
415
    ],
)


hub_job = CircleCIJob(
    "hub",
Sylvain Gugger's avatar
Sylvain Gugger committed
416
    additional_env={"HUGGINGFACE_CO_STAGING": True},
417
418
419
420
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install git-lfs",
        'git config --global user.email "ci@dummy.com"',
        'git config --global user.name "ci"',
Yih-Dar's avatar
Yih-Dar committed
421
        "pip install --upgrade --upgrade-strategy eager pip",
Sylvain Gugger's avatar
Sylvain Gugger committed
422
        "pip install -U --upgrade-strategy eager .[torch,sentencepiece,testing,vision]",
423
424
425
426
427
428
429
430
431
    ],
    marker="is_staging_test",
    pytest_num_workers=1,
)


onnx_job = CircleCIJob(
    "onnx",
    install_steps=[
432
        "sudo apt-get -y update && sudo apt-get install -y cmake",
Yih-Dar's avatar
Yih-Dar committed
433
434
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[torch,tf,testing,sentencepiece,onnxruntime,vision,rjieba]",
435
436
437
438
439
440
    ],
    pytest_options={"k onnx": None},
    pytest_num_workers=1,
)


441
442
exotic_models_job = CircleCIJob(
    "exotic_models",
443
444
    install_steps=[
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev",
Yih-Dar's avatar
Yih-Dar committed
445
446
447
448
449
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[torch,testing,vision]",
        "pip install -U --upgrade-strategy eager torchvision",
        "pip install -U --upgrade-strategy eager scipy",
        "pip install -U --upgrade-strategy eager 'git+https://github.com/facebookresearch/detectron2.git'",
450
        "sudo apt install tesseract-ocr",
Yih-Dar's avatar
Yih-Dar committed
451
452
453
454
        "pip install -U --upgrade-strategy eager pytesseract",
        "pip install -U --upgrade-strategy eager natten",
        # TODO (ydshieh): Remove this line once `https://github.com/facebookresearch/detectron2/issues/5010` is resolved
        'pip install -U --upgrade-strategy eager "Pillow<10.0.0"',
455
456
457
458
    ],
    tests_to_run=[
        "tests/models/*layoutlmv*",
        "tests/models/*nat",
NielsRogge's avatar
NielsRogge committed
459
        "tests/models/deta",
460
461
462
463
464
465
    ],
    pytest_num_workers=1,
    pytest_options={"durations": 100},
)


Sylvain Gugger's avatar
Sylvain Gugger committed
466
467
468
repo_utils_job = CircleCIJob(
    "repo_utils",
    install_steps=[
Yih-Dar's avatar
Yih-Dar committed
469
470
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager .[quality,testing,torch]",
Sylvain Gugger's avatar
Sylvain Gugger committed
471
472
473
    ],
    parallelism=None,
    pytest_num_workers=1,
474
    resource_class="large",
Sylvain Gugger's avatar
Sylvain Gugger committed
475
476
477
    tests_to_run="tests/repo_utils",
)

478
479
480
481
482

# We also include a `dummy.py` file in the files to be doc-tested to prevent edge case failure. Otherwise, the pytest
# hangs forever during test collection while showing `collecting 0 items / 21 errors`. (To see this, we have to remove
# the bash output redirection.)
py_command = 'from utils.tests_fetcher import get_doctest_files; to_test = get_doctest_files() + ["dummy.py"]; to_test = " ".join(to_test); print(to_test)'
483
py_command = f"$(python3 -c '{py_command}')"
484
command = f'echo "{py_command}" > pr_documentation_tests_temp.txt'
485
486
487
488
doc_test_job = CircleCIJob(
    "pr_documentation_tests",
    additional_env={"TRANSFORMERS_VERBOSITY": "error", "DATASETS_VERBOSITY": "error", "SKIP_CUDA_DOCTEST": "1"},
    install_steps=[
489
        "sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev espeak-ng time ffmpeg",
Yih-Dar's avatar
Yih-Dar committed
490
491
492
493
494
        "pip install --upgrade --upgrade-strategy eager pip",
        "pip install -U --upgrade-strategy eager -e .[dev]",
        "pip install -U --upgrade-strategy eager git+https://github.com/huggingface/accelerate",
        "pip install --upgrade --upgrade-strategy eager pytest pytest-sugar",
        "pip install -U --upgrade-strategy eager natten",
495
496
497
498
499
500
        "find -name __pycache__ -delete",
        "find . -name \*.pyc -delete",
        # Add an empty file to keep the test step running correctly even no file is selected to be tested.
        "touch dummy.py",
        {
            "name": "Get files to test",
501
            "command": command,
502
503
        },
        {
504
            "name": "Show information in `Get files to test`",
505
            "command":
506
                "cat pr_documentation_tests_temp.txt"
507
508
        },
        {
509
            "name": "Get the last line in `pr_documentation_tests.txt`",
510
            "command":
511
                "tail -n1 pr_documentation_tests_temp.txt | tee pr_documentation_tests.txt"
512
513
        },
    ],
514
    tests_to_run="$(cat pr_documentation_tests.txt)",  # noqa
515
    pytest_options={"-doctest-modules": None, "doctest-glob": "*.md", "dist": "loadfile", "rvsA": None},
516
517
518
519
    command_timeout=1200,  # test cannot run longer than 1200 seconds
    pytest_num_workers=1,
)

520
521
522
523
524
525
526
527
528
REGULAR_TESTS = [
    torch_and_tf_job,
    torch_and_flax_job,
    torch_job,
    tf_job,
    flax_job,
    custom_tokenizers_job,
    hub_job,
    onnx_job,
529
    exotic_models_job,
530
531
532
533
534
535
536
537
538
539
]
EXAMPLES_TESTS = [
    examples_torch_job,
    examples_tensorflow_job,
    examples_flax_job,
]
PIPELINE_TESTS = [
    pipelines_torch_job,
    pipelines_tf_job,
]
Sylvain Gugger's avatar
Sylvain Gugger committed
540
REPO_UTIL_TESTS = [repo_utils_job]
541
542
DOC_TESTS = [doc_test_job]

543
544
545
546

def create_circleci_config(folder=None):
    if folder is None:
        folder = os.getcwd()
547
548
    # Used in CircleCIJob.to_dict() to expand the test list (for using parallelism)
    os.environ["test_preparation_dir"] = folder
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
    jobs = []
    all_test_file = os.path.join(folder, "test_list.txt")
    if os.path.exists(all_test_file):
        with open(all_test_file) as f:
            all_test_list = f.read()
    else:
        all_test_list = []
    if len(all_test_list) > 0:
        jobs.extend(PIPELINE_TESTS)

    test_file = os.path.join(folder, "filtered_test_list.txt")
    if os.path.exists(test_file):
        with open(test_file) as f:
            test_list = f.read()
    else:
        test_list = []
    if len(test_list) > 0:
        jobs.extend(REGULAR_TESTS)

Yih-Dar's avatar
Yih-Dar committed
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
        extended_tests_to_run = set(test_list.split())
        # Extend the test files for cross test jobs
        for job in jobs:
            if job.job_name in ["tests_torch_and_tf", "tests_torch_and_flax"]:
                for test_path in copy.copy(extended_tests_to_run):
                    dir_path, fn = os.path.split(test_path)
                    if fn.startswith("test_modeling_tf_"):
                        fn = fn.replace("test_modeling_tf_", "test_modeling_")
                    elif fn.startswith("test_modeling_flax_"):
                        fn = fn.replace("test_modeling_flax_", "test_modeling_")
                    else:
                        if job.job_name == "test_torch_and_tf":
                            fn = fn.replace("test_modeling_", "test_modeling_tf_")
                        elif job.job_name == "test_torch_and_flax":
                            fn = fn.replace("test_modeling_", "test_modeling_flax_")
                    new_test_file = str(os.path.join(dir_path, fn))
                    if os.path.isfile(new_test_file):
                        if new_test_file not in extended_tests_to_run:
                            extended_tests_to_run.add(new_test_file)
        extended_tests_to_run = sorted(extended_tests_to_run)
        for job in jobs:
            if job.job_name in ["tests_torch_and_tf", "tests_torch_and_flax"]:
                job.tests_to_run = extended_tests_to_run
        fn = "filtered_test_list_cross_tests.txt"
        f_path = os.path.join(folder, fn)
        with open(f_path, "w") as fp:
            fp.write(" ".join(extended_tests_to_run))

596
597
    example_file = os.path.join(folder, "examples_test_list.txt")
    if os.path.exists(example_file) and os.path.getsize(example_file) > 0:
598
        with open(example_file, "r", encoding="utf-8") as f:
599
            example_tests = f.read()
600
601
602
603
604
        for job in EXAMPLES_TESTS:
            framework = job.name.replace("examples_", "").replace("torch", "pytorch")
            if example_tests == "all":
                job.tests_to_run = [f"examples/{framework}"]
            else:
605
                job.tests_to_run = [f for f in example_tests.split(" ") if f.startswith(f"examples/{framework}")]
606

607
608
            if len(job.tests_to_run) > 0:
                jobs.append(job)
609

610
611
612
613
614
615
616
617
618
    doctest_file = os.path.join(folder, "doctest_list.txt")
    if os.path.exists(doctest_file):
        with open(doctest_file) as f:
            doctest_list = f.read()
    else:
        doctest_list = []
    if len(doctest_list) > 0:
        jobs.extend(DOC_TESTS)

Sylvain Gugger's avatar
Sylvain Gugger committed
619
620
621
    repo_util_file = os.path.join(folder, "test_repo_utils.txt")
    if os.path.exists(repo_util_file) and os.path.getsize(repo_util_file) > 0:
        jobs.extend(REPO_UTIL_TESTS)
622

623
624
625
626
627
628
629
630
631
632
633
634
    if len(jobs) == 0:
        jobs = [EmptyJob()]
    config = {"version": "2.1"}
    config["parameters"] = {
        # Only used to accept the parameters from the trigger
        "nightly": {"type": "boolean", "default": False},
        "tests_to_run": {"type": "string", "default": test_list},
    }
    config["jobs"] = {j.job_name: j.to_dict() for j in jobs}
    config["workflows"] = {"version": 2, "run_tests": {"jobs": [j.job_name for j in jobs]}}
    with open(os.path.join(folder, "generated_config.yml"), "w") as f:
        f.write(yaml.dump(config, indent=2, width=1000000, sort_keys=False))
635
636
637
638
639
640
641
642
643
644


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--fetcher_folder", type=str, default=None, help="Only test that all tests and modules are accounted for."
    )
    args = parser.parse_args()

    create_circleci_config(args.fetcher_folder)