"""Extract clean text from uploaded files.

Supported formats: TXT, MD, PDF, DOCX. Raw bytes pasted as text are handled
by KnowledgePipeline.ingest_text() directly without going through this module.
"""

from __future__ import annotations

from pathlib import Path


def parse_document(path: str | Path) -> str:
    """Return clean plain text extracted from the file at path."""
    path = Path(path)
    suffix = path.suffix.lower()
    if suffix in {".txt", ".md", ".markdown"}:
        return path.read_text(encoding="utf-8", errors="ignore")
    if suffix == ".pdf":
        return _parse_pdf(path)
    if suffix == ".docx":
        return _parse_docx(path)
    raise ValueError(f"Unsupported file type: {suffix}")


def _parse_pdf(path: Path) -> str:
    from pypdf import PdfReader
    reader = PdfReader(str(path))
    pages = []
    for page in reader.pages:
        try:
            pages.append(page.extract_text() or "")
        except Exception:
            continue
    return "\n\n".join(p.strip() for p in pages if p.strip())


def _parse_docx(path: Path) -> str:
    from docx import Document
    doc = Document(str(path))
    return "\n\n".join(p.text for p in doc.paragraphs if p.text.strip())