Files
buddha-gpt/tests/test_index.py
2026-08-14 17:18:42 -07:00

15 lines
449 B
Python

from buddhagpt.index import chunk_text
def test_chunk_text_respects_max_words():
text = " ".join(f"w{i}" for i in range(700))
chunks = chunk_text(text, max_words=300, overlap=50)
assert all(len(c.split()) <= 300 for c in chunks)
assert len(chunks) == 3
def test_chunks_overlap():
text = " ".join(f"w{i}" for i in range(400))
a, b = chunk_text(text, max_words=300, overlap=50)
assert a.split()[-50:] == b.split()[:50]