import re

# Rough word-count targets standing in for the 300-800 token / 10-20% overlap guideline —
# English prose runs ~0.75 words per token, so ~380 words ≈ 500 tokens.
WORDS_PER_CHUNK = 380
OVERLAP_WORDS = 60

_WHITESPACE_RE = re.compile(r"[ \t]+")
_BLANK_LINES_RE = re.compile(r"\n{3,}")


def _normalize(text: str) -> str:
    text = _WHITESPACE_RE.sub(" ", text)
    text = _BLANK_LINES_RE.sub("\n\n", text)
    return text.strip()


def chunk_text(
    text: str, words_per_chunk: int = WORDS_PER_CHUNK, overlap_words: int = OVERLAP_WORDS
) -> list[str]:
    words = _normalize(text).split()
    if not words:
        return []

    step = words_per_chunk - overlap_words
    chunks = []
    start = 0
    while start < len(words):
        chunks.append(" ".join(words[start : start + words_per_chunk]))
        if start + words_per_chunk >= len(words):
            break
        start += step
    return chunks