spaCy/spacy/tests/training/test_corpus.py
Daniël de Kok 8d69874afb
Add spacy.PlainTextCorpusReader.v1 (#12122)
* Add `spacy.PlainTextCorpusReader.v1`

This is a corpus reader that reads plain text corpora with the following
format:

- UTF-8 encoding
- One line per document.
- Blank lines are ignored.

It is useful for applications where we deal with very large corpora,
such as distillation, and don't want to deal with the space overhead of
serialized formats. Additionally, many large corpora already use such
a text format, keeping the necessary preprocessing to a minimum.

* Update spacy/training/corpus.py

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* docs: add version to `PlainTextCorpus`

* Add docstring to registry function

* Add plain text corpus tests

* Only strip newline/carriage return

* Add return type _string_to_tmp_file helper

* Use a temporary directory in place of file name

Different OS auto delete/sharing semantics are just wonky.

* This will be new in 3.5.1 (rather than 4)

* Test improvements from code review

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
2023-01-26 11:33:22 +01:00

79 lines
1.9 KiB
Python

from typing import IO, Generator, Iterable, List, TextIO, Tuple
from contextlib import contextmanager
from pathlib import Path
import pytest
import tempfile
from spacy.lang.en import English
from spacy.training import Example, PlainTextCorpus
from spacy.util import make_tempdir
# Intentional newlines to check that they are skipped.
PLAIN_TEXT_DOC = """
This is a doc. It contains two sentences.
This is another doc.
A third doc.
"""
PLAIN_TEXT_DOC_TOKENIZED = [
[
"This",
"is",
"a",
"doc",
".",
"It",
"contains",
"two",
"sentences",
".",
],
["This", "is", "another", "doc", "."],
["A", "third", "doc", "."],
]
@pytest.mark.parametrize("min_length", [0, 5])
@pytest.mark.parametrize("max_length", [0, 5])
def test_plain_text_reader(min_length, max_length):
nlp = English()
with _string_to_tmp_file(PLAIN_TEXT_DOC) as file_path:
corpus = PlainTextCorpus(
file_path, min_length=min_length, max_length=max_length
)
check = [
doc
for doc in PLAIN_TEXT_DOC_TOKENIZED
if len(doc) >= min_length and (max_length == 0 or len(doc) <= max_length)
]
reference, predicted = _examples_to_tokens(corpus(nlp))
assert reference == check
assert predicted == check
@contextmanager
def _string_to_tmp_file(s: str) -> Generator[Path, None, None]:
with make_tempdir() as d:
file_path = Path(d) / "string.txt"
with open(file_path, "w", encoding="utf-8") as f:
f.write(s)
yield file_path
def _examples_to_tokens(
examples: Iterable[Example],
) -> Tuple[List[List[str]], List[List[str]]]:
reference = []
predicted = []
for eg in examples:
reference.append([t.text for t in eg.reference])
predicted.append([t.text for t in eg.predicted])
return reference, predicted