mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-10-31 01:39:45 +00:00
834f8c4902
* Change return types of file converters * Change return types of preprocessor * Change return types of crawler * Adapt utils to functions to new return types * Adapt __init__.py to new method names * Prevent circular imports * Update Documentation & Code Style * Let DocStores' run method accept Documents * Adapt tests to new return types * Update Documentation & Code Style * Put "# type: ignore" to right place * Remove id_hash_keys property from Document primitive * Update Documentation & Code Style * Adapt tests to new return types and missing id_hash_keys property * Fix mypy * Fix mypy * Adapt PDFToTextOCRConverter * Remove id_hash_keys from RestAPI tests * Update Documentation & Code Style * Rename tests * Remove redundant setting of content_type="text" * Add DeprecationWarning * Add id_hash_keys to elasticsearch_index_to_document_store * Change document type from dict to Docuemnt in PreProcessor test * Fix file path in Tutorial 5 * Remove added output in Tutorial 5 * Update Documentation & Code Style * Fix file_paths in Tutorial 9 + fix gz files in fetch_archive_from_http * Adapt tutorials to new return types * Adapt tutorial 14 to new return types * Update Documentation & Code Style * Change assertions to HaystackErrors * Import HaystackError correctly Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
112 lines
4.2 KiB
Python
112 lines
4.2 KiB
Python
from pathlib import Path
|
|
|
|
from haystack import Document
|
|
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 = 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 = 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 = 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
|
|
|
|
|
|
def test_remove_substrings():
|
|
document = Document(content="This is a header. Some additional text. wiki. Some emoji ✨ 🪲 Weird whitespace\b\b\b.")
|
|
|
|
# check that the file contains the substrings we are about to remove
|
|
assert "This is a header." in document.content
|
|
assert "wiki" in document.content
|
|
assert "🪲" in document.content
|
|
assert "whitespace" in document.content
|
|
assert "✨" in document.content
|
|
|
|
preprocessor = PreProcessor(remove_substrings=["This is a header.", "wiki", "🪲"])
|
|
documents = preprocessor.process(document)
|
|
|
|
assert "This is a header." not in documents[0].content
|
|
assert "wiki" not in documents[0].content
|
|
assert "🪲" not in documents[0].content
|
|
assert "whitespace" in documents[0].content
|
|
assert "✨" in documents[0].content
|