from langchain_core.documents import Document
from langchain_text_splitters import RecursiveCharacterTextSplitter

source = Document(
    page_content=(
        "checkout incidents page the on-call engineer immediately "
        "checkout incidents use priority P1 and send status updates every fifteen minutes "
        "billing questions use priority P3 and route to finance support "
        "password reset requests use priority P4 and route to the help desk"
    ),
    metadata={"source": "support-runbook"},
)

splitter = RecursiveCharacterTextSplitter(
    chunk_size=75,
    chunk_overlap=22,
    separators=["\n\n", "\n", " ", ""],
    add_start_index=True,
)

chunks = splitter.split_documents([source])

print(f"chunk_count={len(chunks)}")
for number, chunk in enumerate(chunks, start=1):
    previous = chunks[number - 2] if number > 1 else None
    if previous is None:
        overlap = "n/a"
    else:
        previous_end = previous.metadata["start_index"] + len(previous.page_content)
        overlap = previous_end - chunk.metadata["start_index"]
    print(
        f"chunk_{number}: chars={len(chunk.page_content)} "
        f"start={chunk.metadata['start_index']} "
        f"overlap_from_previous={overlap} "
        f"source={chunk.metadata['source']}"
    )
    print(chunk.page_content)

assert len(chunks) == 5
assert all(len(chunk.page_content) <= 75 for chunk in chunks)
assert all("start_index" in chunk.metadata for chunk in chunks)
assert all(
    chunks[i - 1].metadata["start_index"] + len(chunks[i - 1].page_content)
    > chunks[i].metadata["start_index"]
    for i in range(1, len(chunks))
)