mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-11-04 11:49:23 +00:00
a59bca3661
* Testing black on ui/ * Applying black on docstores * Add latest docstring and tutorial changes * Create a single GH action for Black and docs to reduce commit noise to the minimum, slightly refactor the OpenAPI action too * Remove comments * Relax constraints on pydoc-markdown * Split temporary black from the docs. Pydoc-markdown was obsolete and needs a separate PR to upgrade * Fix a couple of bugs * Add a type: ignore that was missing somehow * Give path to black * Apply Black * Apply Black * Relocate a couple of type: ignore * Update documentation * Make Linux CI run after applying Black * Triggering Black * Apply Black * Remove dependency, does not work well * Remove manually double trailing commas * Update documentation Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
94 lines
3.4 KiB
Python
94 lines
3.4 KiB
Python
from pathlib import Path
|
|
|
|
from haystack.nodes.file_converter.pdf import PDFToTextConverter
|
|
from haystack.nodes.preprocessor.preprocessor import PreProcessor
|
|
|
|
from conftest import SAMPLES_PATH
|
|
|
|
TEXT = """
|
|
This is a sample sentence in paragraph_1. This is a sample sentence in paragraph_1. This is a sample sentence in
|
|
paragraph_1. This is a sample sentence in paragraph_1. This is a sample sentence in paragraph_1.
|
|
|
|
This is a sample sentence in paragraph_2. This is a sample sentence in paragraph_2. This is a sample sentence in
|
|
paragraph_2. This is a sample sentence in paragraph_2. This is a sample sentence in paragraph_2.
|
|
|
|
This is a sample sentence in paragraph_3. This is a sample sentence in paragraph_3. This is a sample sentence in
|
|
paragraph_3. This is a sample sentence in paragraph_3. This is to trick the test with using an abbreviation like Dr.
|
|
in the sentence.
|
|
"""
|
|
|
|
|
|
def test_preprocess_sentence_split():
|
|
document = {"content": TEXT}
|
|
preprocessor = PreProcessor(
|
|
split_length=1, split_overlap=0, split_by="sentence", split_respect_sentence_boundary=False
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 15
|
|
|
|
preprocessor = PreProcessor(
|
|
split_length=10,
|
|
split_overlap=0,
|
|
split_by="sentence",
|
|
split_respect_sentence_boundary=False,
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 2
|
|
|
|
|
|
def test_preprocess_word_split():
|
|
document = {"content": TEXT}
|
|
preprocessor = PreProcessor(
|
|
split_length=10, split_overlap=0, split_by="word", split_respect_sentence_boundary=False
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 11
|
|
|
|
preprocessor = PreProcessor(split_length=15, split_overlap=0, split_by="word", split_respect_sentence_boundary=True)
|
|
documents = preprocessor.process(document)
|
|
for i, doc in enumerate(documents):
|
|
if i == 0:
|
|
assert len(doc["content"].split(" ")) == 14
|
|
assert len(doc["content"].split(" ")) <= 15 or doc["content"].startswith("This is to trick")
|
|
assert len(documents) == 8
|
|
|
|
preprocessor = PreProcessor(
|
|
split_length=40, split_overlap=10, split_by="word", split_respect_sentence_boundary=True
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 5
|
|
|
|
preprocessor = PreProcessor(split_length=5, split_overlap=0, split_by="word", split_respect_sentence_boundary=True)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 15
|
|
|
|
|
|
def test_preprocess_passage_split():
|
|
document = {"content": TEXT}
|
|
preprocessor = PreProcessor(
|
|
split_length=1, split_overlap=0, split_by="passage", split_respect_sentence_boundary=False
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 3
|
|
|
|
preprocessor = PreProcessor(
|
|
split_length=2, split_overlap=0, split_by="passage", split_respect_sentence_boundary=False
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 2
|
|
|
|
|
|
def test_clean_header_footer():
|
|
converter = PDFToTextConverter()
|
|
document = converter.convert(
|
|
file_path=Path(SAMPLES_PATH / "pdf" / "sample_pdf_2.pdf")
|
|
) # file contains header/footer
|
|
|
|
preprocessor = PreProcessor(clean_header_footer=True, split_by=None)
|
|
documents = preprocessor.process(document)
|
|
|
|
assert len(documents) == 1
|
|
|
|
assert "This is a header." not in documents[0]["content"]
|
|
assert "footer" not in documents[0]["content"]
|