diff options
Diffstat (limited to '.venv/lib/python3.12/site-packages/tokenizers/normalizers')
| -rw-r--r-- | .venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.py | 29 | ||||
| -rw-r--r-- | .venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.pyi | 595 |
2 files changed, 624 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.py b/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.py new file mode 100644 index 00000000..15a16f1e --- /dev/null +++ b/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.py @@ -0,0 +1,29 @@ +from .. import normalizers + + +Normalizer = normalizers.Normalizer +BertNormalizer = normalizers.BertNormalizer +NFD = normalizers.NFD +NFKD = normalizers.NFKD +NFC = normalizers.NFC +NFKC = normalizers.NFKC +Sequence = normalizers.Sequence +Lowercase = normalizers.Lowercase +Prepend = normalizers.Prepend +Strip = normalizers.Strip +StripAccents = normalizers.StripAccents +Nmt = normalizers.Nmt +Precompiled = normalizers.Precompiled +Replace = normalizers.Replace + + +NORMALIZERS = {"nfc": NFC, "nfd": NFD, "nfkc": NFKC, "nfkd": NFKD} + + +def unicode_normalizer_from_str(normalizer: str) -> Normalizer: + if normalizer not in NORMALIZERS: + raise ValueError( + "{} is not a known unicode normalizer. Available are {}".format(normalizer, NORMALIZERS.keys()) + ) + + return NORMALIZERS[normalizer]() diff --git a/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.pyi b/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.pyi new file mode 100644 index 00000000..507d4473 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/tokenizers/normalizers/__init__.pyi @@ -0,0 +1,595 @@ +# Generated content DO NOT EDIT +class Normalizer: + """ + Base class for all normalizers + + This class is not supposed to be instantiated directly. Instead, any implementation of a + Normalizer will return an instance of this class when instantiated. + """ + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class BertNormalizer(Normalizer): + """ + BertNormalizer + + Takes care of normalizing raw text before giving it to a Bert model. + This includes cleaning the text, handling accents, chinese chars and lowercasing + + Args: + clean_text (:obj:`bool`, `optional`, defaults to :obj:`True`): + Whether to clean the text, by removing any control characters + and replacing all whitespaces by the classic one. + + handle_chinese_chars (:obj:`bool`, `optional`, defaults to :obj:`True`): + Whether to handle chinese chars by putting spaces around them. + + strip_accents (:obj:`bool`, `optional`): + Whether to strip all accents. If this option is not specified (ie == None), + then it will be determined by the value for `lowercase` (as in the original Bert). + + lowercase (:obj:`bool`, `optional`, defaults to :obj:`True`): + Whether to lowercase. + """ + def __init__(self, clean_text=True, handle_chinese_chars=True, strip_accents=None, lowercase=True): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Lowercase(Normalizer): + """ + Lowercase Normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class NFC(Normalizer): + """ + NFC Unicode Normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class NFD(Normalizer): + """ + NFD Unicode Normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class NFKC(Normalizer): + """ + NFKC Unicode Normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class NFKD(Normalizer): + """ + NFKD Unicode Normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Nmt(Normalizer): + """ + Nmt normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Precompiled(Normalizer): + """ + Precompiled normalizer + Don't use manually it is used for compatiblity for SentencePiece. + """ + def __init__(self, precompiled_charsmap): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Prepend(Normalizer): + """ + Prepend normalizer + """ + def __init__(self, prepend): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Replace(Normalizer): + """ + Replace normalizer + """ + def __init__(self, pattern, content): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Sequence(Normalizer): + """ + Allows concatenating multiple other Normalizer as a Sequence. + All the normalizers run in sequence in the given order + + Args: + normalizers (:obj:`List[Normalizer]`): + A list of Normalizer to be run as a sequence + """ + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class Strip(Normalizer): + """ + Strip normalizer + """ + def __init__(self, left=True, right=True): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass + +class StripAccents(Normalizer): + """ + StripAccents normalizer + """ + def __init__(self): + pass + + def normalize(self, normalized): + """ + Normalize a :class:`~tokenizers.NormalizedString` in-place + + This method allows to modify a :class:`~tokenizers.NormalizedString` to + keep track of the alignment information. If you just want to see the result + of the normalization on a raw string, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize_str` + + Args: + normalized (:class:`~tokenizers.NormalizedString`): + The normalized string on which to apply this + :class:`~tokenizers.normalizers.Normalizer` + """ + pass + + def normalize_str(self, sequence): + """ + Normalize the given string + + This method provides a way to visualize the effect of a + :class:`~tokenizers.normalizers.Normalizer` but it does not keep track of the alignment + information. If you need to get/convert offsets, you can use + :meth:`~tokenizers.normalizers.Normalizer.normalize` + + Args: + sequence (:obj:`str`): + A string to normalize + + Returns: + :obj:`str`: A string after normalization + """ + pass |