Function fix_encoding_and_explain

ftfy/__init__.py:424–465

Apply the steps of ftfy that detect mojibake and fix it. Returns the fixed text and a list explaining what was fixed. This includes fixing text by encoding and decoding it in different encodings, as well as the subordinate fixes `restore_byte_a0`, `replace_lossy_sequences`, `de

(
    text: str, config: TextFixerConfig | None = None, **kwargs: Any
)

def fix_encoding_and_explain(
    text: str, config: TextFixerConfig | None = None, **kwargs: Any
) -> ExplainedText:
    """
    Apply the steps of ftfy that detect mojibake and fix it. Returns the fixed
    text and a list explaining what was fixed.

    This includes fixing text by encoding and decoding it in different encodings,
    as well as the subordinate fixes `restore_byte_a0`, `replace_lossy_sequences`,
    `decode_inconsistent_utf8`, and `fix_c1_controls`.

    Examples::

        >>> fix_encoding_and_explain("só")
        ExplainedText(text='só', explanation=[('encode', 'latin-1'), ('decode', 'utf-8')])

        >>> result = fix_encoding_and_explain("voilà le travail")
        >>> result.text
        'voilà le travail'
        >>> result.explanation
        [('encode', 'latin-1'), ('transcode', 'restore_byte_a0'), ('decode', 'utf-8')]

    """
    if config is None:
        config = TextFixerConfig()
    if isinstance(text, bytes):
        raise UnicodeError(BYTES_ERROR_TEXT)
    config = _config_from_kwargs(config, kwargs)

    if not config.fix_encoding:
        # A weird trivial case: we're asked to fix the encoding, but skip
        # fixing the encoding
        return ExplainedText(text, [])

    plan_so_far: list[ExplanationStep] = []
    while True:
        prevtext = text
        text, plan = _fix_encoding_one_step_and_explain(text, config)
        if plan is not None:
            plan_so_far.extend(plan)
        if text == prevtext:
            return ExplainedText(text, plan_so_far)


def _fix_encoding_one_step_and_explain(