Function infer_tests_to_run

utils/tests_fetcher.py:909–996

The main function called by the test fetcher. Determines the tests to run from the diff. Args: output_file (`str`): The path where to store the summary of the test fetcher analysis. Other files will be stored in the same folder: - examples_test_

(
    output_file: str,
    diff_with_last_commit: bool = False,
    json_output_file: str | None = None,
)

def infer_tests_to_run(
    output_file: str,
    diff_with_last_commit: bool = False,
    json_output_file: str | None = None,
):
    """
    The main function called by the test fetcher. Determines the tests to run from the diff.

    Args:
        output_file (`str`):
            The path where to store the summary of the test fetcher analysis. Other files will be stored in the same
            folder:

            - examples_test_list.txt: The list of examples tests to run.
            - test_repo_utils.txt: Will indicate if the repo utils tests should be run or not.
            - doctest_list.txt: The list of doctests to run.

        diff_with_last_commit (`bool`, *optional*, defaults to `False`):
            Whether to analyze the diff with the last commit (for use on the main branch after a PR is merged) or with
            the branching point from main (for use on each PR).
        filter_models (`bool`, *optional*, defaults to `True`):
            Whether or not to filter the tests to core models only, when a file modified results in a lot of model
            tests.
        json_output_file (`str`, *optional*):
            The path where to store the json file mapping categories of tests to tests to run (used for parallelism or
            the slow tests).
    """
    modified_files = get_modified_python_files(diff_with_last_commit=diff_with_last_commit)
    print(f"\n### MODIFIED FILES ###\n{_print_list(modified_files)}")
    # Create the map that will give us all impacted modules.
    reverse_map = create_reverse_dependency_map()
    impacted_files = modified_files.copy()
    for f in modified_files:
        if f in reverse_map:
            impacted_files.extend(reverse_map[f])

    # Remove duplicates
    impacted_files = sorted(set(impacted_files))
    print(f"\n### IMPACTED FILES ###\n{_print_list(impacted_files)}")

    # Grab the corresponding test files:
    if any(x in modified_files for x in ["setup.py"]):
        test_files_to_run = ["tests", "examples"]

    # in order to trigger pipeline tests even if no code change at all
    if "tests/utils/tiny_model_summary.json" in modified_files:
        test_files_to_run = ["tests"]
        any(f.split(os.path.sep)[0] == "utils" for f in modified_files)
    else:
        # All modified tests need to be run.
        test_files_to_run = [
            f for f in modified_files if f.startswith("tests") and f.split(os.path.sep)[-1].startswith("test")
        ]
        # Then we grab the corresponding test files.
        test_map = create_module_to_test_map(reverse_map=reverse_map)
        for f in modified_files:
            if f in test_map:
                test_files_to_run.extend(test_map[f])