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
19 lines
700 B
Python
19 lines
700 B
Python
"""Regression: chunk_size=0 must not crash range() on long sentences.
|
|
|
|
Use the experiment's real configuration module. The former process-global
|
|
``sys.modules['config']`` stub leaked into later test modules and made their
|
|
imports depend on pytest collection order.
|
|
"""
|
|
|
|
from config import ChunkingConfig
|
|
from chunking import DocumentChunker
|
|
|
|
|
|
def test_chunk_size_zero_long_unsplittable_sentence():
|
|
cfg = ChunkingConfig(chunk_size=0, max_chunk_size=40, min_chunk_size=1)
|
|
chunker = DocumentChunker(cfg)
|
|
text = "alpha" * 80 # longer than max_chunk_size, no paragraph breaks
|
|
chunks = chunker.chunk_text(text, doc_id="d1")
|
|
assert isinstance(chunks, list)
|
|
assert len(chunks) >= 1
|