explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 04:10:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add docstring to registry function

Browse Source
This commit is contained in:
Daniël de Kok 2023-01-18 15:14:10 +01:00
parent a4a08d826a
commit 1da9f15d62
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/training/corpus.py
View File

@ -64,6 +64,17 @@ def create_plain_text_reader(
min_length: int = 0, min_length: int = 0,
max_length: int = 0, max_length: int = 0,
) -> Callable[["Language"], Iterable[Doc]]: ) -> Callable[["Language"], Iterable[Doc]]:
"""Iterate Example objects from a file or directory of plain text
UTF-8 files with one line per doc.
path (Path): The directory or filename to read from.
min_length (int): Minimum document length (in tokens). Shorter documents
will be skipped. Defaults to 0, which indicates no limit.
max_length (int): Maximum document length (in tokens). Longer documents will
be skipped. Defaults to 0, which indicates no limit.
DOCS: https://spacy.io/api/corpus#plaintextcorpus
"""
if path is None: if path is None:
raise ValueError(Errors.E913) raise ValueError(Errors.E913)
return PlainTextCorpus(path, min_length=min_length, max_length=max_length) return PlainTextCorpus(path, min_length=min_length, max_length=max_length)