from haystack import Document
from haystack.components.preprocessors import DocumentPreprocessor


raw_document = Document(
    id="policy-draft",
    content=(
        "CONFIDENTIAL Solar policy drafts need precise source text.\n\n"
        "Retrieval chunks should stay focused on one section.\n\n"
        "Reviewers need overlap when a boundary carries context.\n\n"
        "Source metadata must remain attached for later indexing."
    ),
    meta={"source": "policy-draft.txt"},
)