Class HfDocTestParser

src/transformers/testing_utils.py:2920–2963

Overwrites the DocTestParser from doctest to properly parse the codeblocks that are formatted with black. This means that there are no extra lines at the end of our snippets. The `# doctest: +IGNORE_RESULT` marker is also added anywhere a `load_dataset` call is made as a print would oth

class HfDocTestParser(doctest.DocTestParser):
    """
    Overwrites the DocTestParser from doctest to properly parse the codeblocks that are formatted with black. This
    means that there are no extra lines at the end of our snippets. The `# doctest: +IGNORE_RESULT` marker is also
    added anywhere a `load_dataset` call is made as a print would otherwise fail the corresponding line.

    Tests involving cuda are skipped base on a naive pattern that should be updated if it is not enough.
    """

    # This regular expression is used to find doctest examples in a
    # string.  It defines three groups: `source` is the source code
    # (including leading indentation and prompts); `indent` is the
    # indentation of the first (PS1) line of the source code; and
    # `want` is the expected output (including leading indentation).
    # fmt: off
    _EXAMPLE_RE = re.compile(r'''
        # Source consists of a PS1 line followed by zero or more PS2 lines.
        (?P<source>
            (?:^(?P<indent> [ ]*) >>>    .*)    # PS1 line
            (?:\n           [ ]*  \.\.\. .*)*)  # PS2 lines
        \n?
        # Want consists of any non-blank lines that do not start with PS1.
        (?P<want> (?:(?![ ]*$)    # Not a blank line
             (?![ ]*>>>)          # Not a line starting with PS1
             # !!!!!!!!!!! HF Specific !!!!!!!!!!!
             (?:(?!```).)*        # Match any character except '`' until a '```' is found (this is specific to HF because black removes the last line)
             # !!!!!!!!!!! HF Specific !!!!!!!!!!!
             (?:\n|$)  # Match a new line or end of string
          )*)
        ''&#x27;, re.MULTILINE | re.VERBOSE
    )
    # fmt: on

    # !!!!!!!!!!! HF Specific !!!!!!!!!!!
    skip_cuda_tests: bool = os.environ.get("SKIP_CUDA_DOCTEST", "0") == "1"
    # !!!!!!!!!!! HF Specific !!!!!!!!!!!

    def parse(self, string, name="<string>"):
        """
        Overwrites the `parse` method to incorporate a skip for CUDA tests, and remove logs and dataset prints before
        calling `super().parse`
        """
        string = preprocess_string(string, self.skip_cuda_tests)
        return super().parse(string, name)


class HfDoctestModule(Module):