mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-27 02:40:41 +00:00
e5b4b62d75
* Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
78 lines
3.3 KiB
Python
78 lines
3.3 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from haystack.file_converter.pdf import PDFToTextConverter
|
|
from haystack.preprocessor.preprocessor import PreProcessor
|
|
|
|
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/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"] |