Skip to content

edsnlp.pipelines.core.normalizer.quotes

quotes

Quotes

Bases: object

We normalise quotes, following this source <https://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html>_.

PARAMETER DESCRIPTION
quotes

List of quotation characters and their transcription.

TYPE: List[Tuple[str, str]]

Source code in edsnlp/pipelines/core/normalizer/quotes/quotes.py 
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
class Quotes(object):
    """
    We normalise quotes, following this
    `source <https://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html>`_.

    Parameters
    ----------
    quotes : List[Tuple[str, str]]
        List of quotation characters and their transcription.
    """

    def __init__(self, quotes: Optional[List[Tuple[str, str]]]) -> None:
        if quotes is None:
            quotes = quotes_and_apostrophes
        self.quotes = quotes

    def __call__(self, doc: Doc) -> Doc:
        """
        Normalises quotes.

        Parameters
        ----------
        doc : Doc
            Document to process.

        Returns
        -------
        Doc
            Same document, with quotes normalised.
        """

        for token in doc:
            token.norm_ = replace(text=token.norm_, rep=self.quotes)

        return doc
__call__(doc)

Normalises quotes.

PARAMETER DESCRIPTION
doc

Document to process.

TYPE: Doc

RETURNS DESCRIPTION
Doc

Same document, with quotes normalised.
Source code in edsnlp/pipelines/core/normalizer/quotes/quotes.py 
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
def __call__(self, doc: Doc) -> Doc:
    """
    Normalises quotes.

    Parameters
    ----------
    doc : Doc
        Document to process.

    Returns
    -------
    Doc
        Same document, with quotes normalised.
    """

    for token in doc:
        token.norm_ = replace(text=token.norm_, rep=self.quotes)

    return doc
Back to top