"""Knowledge document parsing for supported upload formats."""
from __future__ import annotations

from pathlib import Path
from xml.etree import ElementTree
from zipfile import BadZipFile, ZipFile

from pypdf import PdfReader

SUPPORTED_EXTENSIONS = {".txt", ".md", ".docx", ".pdf"}
_WORD_NS = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}"


def parse_document(path: str | Path) -> str:
    """Return document text for a supported knowledge-base upload."""
    document_path = Path(path)
    suffix = document_path.suffix.lower()
    if suffix not in SUPPORTED_EXTENSIONS:
        raise ValueError(f"Unsupported document type: {suffix or '<none>'}")
    if not document_path.is_file():
        raise FileNotFoundError(document_path)

    if suffix in {".txt", ".md"}:
        return document_path.read_text(encoding="utf-8-sig")
    if suffix == ".pdf":
        return _parse_pdf(document_path)
    return _parse_docx(document_path)


def _parse_docx(path: Path) -> str:
    try:
        with ZipFile(path) as archive:
            xml = archive.read("word/document.xml")
        root = ElementTree.fromstring(xml)
    except (BadZipFile, KeyError, ElementTree.ParseError) as exc:
        raise ValueError(f"Invalid DOCX document: {path}") from exc

    paragraphs = []
    for paragraph in root.iter(f"{_WORD_NS}p"):
        text = "".join(node.text or "" for node in paragraph.iter(f"{_WORD_NS}t"))
        if text:
            paragraphs.append(text)
    return "\n".join(paragraphs)


def _parse_pdf(path: Path) -> str:
    try:
        reader = PdfReader(str(path))
        return "\n".join(page.extract_text() or "" for page in reader.pages).strip()
    except Exception as exc:  # pypdf raises format-specific exceptions
        raise ValueError(f"Invalid PDF document: {path}") from exc