liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
18 lines
541 B
Python
18 lines
541 B
Python
import pytest
|
|
from bm25_engine import InvertedIndex, BM25, TextProcessor
|
|
|
|
|
|
def test_bm25_search_empty_term_in_query_terms_no_index_error():
|
|
index = InvertedIndex()
|
|
index.add_document(1, "hello world")
|
|
bm25 = BM25(index)
|
|
|
|
orig_tokenize = TextProcessor.tokenize
|
|
try:
|
|
TextProcessor.tokenize = lambda self, text, remove_stop_words=True: ["hello", ""]
|
|
results = bm25.search("hello")
|
|
assert len(results) == 1
|
|
assert results[0][0] == 1
|
|
finally:
|
|
TextProcessor.tokenize = orig_tokenize
|