"""文档解析：各类文件 → 纯文本（供 RAG 切块/embedding）。
按扩展名路由：txt/md/csv 直读；docx(python-docx)；xlsx(openpyxl)；pdf(pypdf)。
扫描件/版面 OCR(MinerU/PaddleOCR) 为后续。
"""

from __future__ import annotations

import csv
import io


def parse(filename: str, data: bytes) -> str:
    ext = filename.lower().rsplit(".", 1)[-1] if "." in filename else ""
    if ext in ("txt", "md", "markdown", "text", ""):
        return data.decode("utf-8", errors="replace")
    if ext == "csv":
        return _csv(data)
    if ext == "docx":
        return _docx(data)
    if ext == "xlsx":
        return _xlsx(data)
    if ext == "pdf":
        return _pdf(data)
    raise ValueError(f"暂不支持的文件类型: .{ext}")


def _csv(data: bytes) -> str:
    text = data.decode("utf-8", errors="replace")
    rows = list(csv.reader(io.StringIO(text)))
    return "\n".join(" | ".join(r) for r in rows if any(c.strip() for c in r))


def _docx(data: bytes) -> str:
    from docx import Document  # python-docx

    doc = Document(io.BytesIO(data))
    lines: list[str] = [p.text for p in doc.paragraphs if p.text.strip()]
    for table in doc.tables:
        for row in table.rows:
            cells = [c.text.strip() for c in row.cells]
            if any(cells):
                lines.append(" | ".join(cells))
    return "\n".join(lines)


def _xlsx(data: bytes) -> str:
    from openpyxl import load_workbook

    wb = load_workbook(io.BytesIO(data), read_only=True, data_only=True)
    lines: list[str] = []
    for ws in wb.worksheets:
        lines.append(f"# 工作表: {ws.title}")
        for row in ws.iter_rows(values_only=True):
            cells = [str(c) for c in row if c is not None]
            if cells:
                lines.append(" | ".join(cells))
    return "\n".join(lines)


def _pdf(data: bytes) -> str:
    from pypdf import PdfReader

    reader = PdfReader(io.BytesIO(data))
    pages = [(page.extract_text() or "").strip() for page in reader.pages]
    return "\n\n".join(p for p in pages if p)