This change remove `BaseComponent`'s: - run_raw - run_batch_raw - run_document - run_batch_document - is_document - is_batch Each component is expected to support multiple types of inputs and a single type of output. Since we want the component to work out-of-the-box with both standardized and customized use cases, supporting multiple types of inputs are expected. At the same time, to reduce the complexity of understanding how to use a component, we restrict a component to only have a single output type. To accommodate these changes, we also refactor some components to remove their run_raw, run_batch_raw... methods, and to decide the common output interface for those components. Tests are updated accordingly. Commit changes: * Add kwargs to vector store's query * Simplify the BaseComponent * Update tests * Remove support for Python 3.8 and 3.9 * Bump version 0.3.0 * Fix github PR caching still use old environment after bumping version --------- Co-authored-by: ian <ian@cinnamon.is>
33 lines
999 B
Python
33 lines
999 B
Python
import pytest
|
|
|
|
from kotaemon.documents.base import Document
|
|
from kotaemon.post_processing.extractor import RegexExtractor
|
|
|
|
|
|
@pytest.fixture
|
|
def regex_extractor():
|
|
return RegexExtractor(
|
|
pattern=r"\d+", output_map={"1": "One", "2": "Two", "3": "Three"}
|
|
)
|
|
|
|
|
|
def test_run_document(regex_extractor):
|
|
document = Document(text="This is a test. 1 2 3")
|
|
extracted_document = regex_extractor(document)[0]
|
|
assert extracted_document.text == "One"
|
|
assert extracted_document.matches == ["One", "Two", "Three"]
|
|
|
|
|
|
def test_run_raw(regex_extractor):
|
|
output = regex_extractor("This is a test. 123")[0]
|
|
assert output.text == "123"
|
|
assert output.matches == ["123"]
|
|
|
|
|
|
def test_run_batch_raw(regex_extractor):
|
|
output = regex_extractor(["This is a test. 123", "456"])
|
|
extracted_text = [each.text for each in output]
|
|
extracted_matches = [each.matches for each in output]
|
|
assert extracted_text == ["123", "456"]
|
|
assert extracted_matches == [["123"], ["456"]]
|