Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/rag/chunkers.py
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ def chunk_document(document: Document, chunk_size: int, overlap: int) -> list[Ch
if overlap >= chunk_size:
raise ValueError("overlap must be smaller than chunk_size")

if not document.text:
if not document.text.strip():
return []

if len(document.text) <= chunk_size:
Expand Down
19 changes: 19 additions & 0 deletions tests/test_chunkers.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,25 @@ def test_chunk_document_empty_text() -> None:

assert chunk_document(document, chunk_size=10, overlap=2) == []

def test_chunk_document_whitespace_only_text() -> None:
document = Document(
document_id="doc-whitespace",
text=" ",
metadata={"source": "fixture", "filename": "whitespace.txt"},
)

assert chunk_document(document, chunk_size=10, overlap=2) == []


def test_chunk_document_newline_only_text() -> None:
document = Document(
document_id="doc-newlines",
text="\n\n",
metadata={"source": "fixture", "filename": "newlines.txt"},
)

assert chunk_document(document, chunk_size=10, overlap=2) == []


def test_chunk_document_shorter_than_chunk_size(sample_document: Document) -> None:
chunks = chunk_document(sample_document, chunk_size=20, overlap=2)
Expand Down