# ============================================================
# 知识文档导入与切块（moduleId: knowledge-ingest, 可重生 ✅）
# plan.md §8.2：PDF/docx/md/txt → chunk → 知识资产（版本化+审批）
# ============================================================
from __future__ import annotations

import os
import re
from typing import Any

# 切块目标长度（字符）与重叠
_CHUNK_SIZE = 500
_CHUNK_OVERLAP = 50


def _ext(path: str) -> str:
    return os.path.splitext(path)[1].lower()


def extract_text_from_bytes(filename: str, raw: bytes) -> list[dict[str, Any]]:
    """按扩展名解析文件为带页/段元数据的文本块列表（尚未切 chunk）。

    Returns: [{text, page?, heading?}, ...]
    """
    name = filename or "upload.txt"
    ext = _ext(name)
    if ext in (".md", ".txt", ".markdown"):
        text = raw.decode("utf-8", errors="replace")
        return _split_markdown_sections(text)
    if ext == ".pdf":
        return _extract_pdf(raw)
    if ext in (".docx",):
        return _extract_docx(raw)
    if ext in (".xlsx", ".xlsm"):
        return _extract_xlsx(raw)
    # 兜底当纯文本
    try:
        return [{"text": raw.decode("utf-8"), "page": 1}]
    except UnicodeDecodeError as exc:
        raise ValueError(f"不支持的文件类型或编码：{name}") from exc


def extract_text_from_path(path: str) -> list[dict[str, Any]]:
    """从本地路径读取并解析。"""
    if not os.path.isfile(path):
        raise FileNotFoundError(f"文件不存在：{path}")
    with open(path, "rb") as f:
        raw = f.read()
    return extract_text_from_bytes(os.path.basename(path), raw)


def _split_markdown_sections(text: str) -> list[dict[str, Any]]:
    parts: list[dict[str, Any]] = []
    current_heading = ""
    buf: list[str] = []
    for line in text.splitlines():
        if re.match(r"^#{1,3}\s+", line):
            if buf:
                parts.append({"text": "\n".join(buf).strip(), "heading": current_heading or None})
                buf = []
            current_heading = re.sub(r"^#{1,3}\s+", "", line).strip()
            buf.append(line)
        else:
            buf.append(line)
    if buf:
        parts.append({"text": "\n".join(buf).strip(), "heading": current_heading or None})
    return [p for p in parts if p["text"]]


def _extract_pdf(raw: bytes) -> list[dict[str, Any]]:
    try:
        import pdfplumber
    except ImportError as exc:
        raise ValueError("解析 PDF 需要安装 pdfplumber：pip install pdfplumber") from exc
    from io import BytesIO
    pages: list[dict[str, Any]] = []
    with pdfplumber.open(BytesIO(raw)) as pdf:
        for i, page in enumerate(pdf.pages, start=1):
            t = (page.extract_text() or "").strip()
            if t:
                pages.append({"text": t, "page": i})
    if not pages:
        raise ValueError("PDF 未提取到文本（可能是扫描件）")
    return pages


def _extract_docx(raw: bytes) -> list[dict[str, Any]]:
    try:
        from docx import Document
    except ImportError as exc:
        raise ValueError("解析 docx 需要安装 python-docx：pip install python-docx") from exc
    from io import BytesIO
    doc = Document(BytesIO(raw))
    paras = [p.text.strip() for p in doc.paragraphs if p.text and p.text.strip()]
    if not paras:
        raise ValueError("docx 未提取到文本")
    return [{"text": "\n".join(paras), "page": 1}]


def _extract_xlsx(raw: bytes) -> list[dict[str, Any]]:
    from io import BytesIO
    from openpyxl import load_workbook
    wb = load_workbook(BytesIO(raw), data_only=True, read_only=True)
    parts: list[dict[str, Any]] = []
    for sheet in wb.worksheets:
        rows = []
        for row in sheet.iter_rows(values_only=True):
            cells = [str(c) for c in row if c is not None and str(c).strip()]
            if cells:
                rows.append(" | ".join(cells))
        if rows:
            parts.append({"text": f"# {sheet.title}\n" + "\n".join(rows), "heading": sheet.title})
    if not parts:
        raise ValueError("xlsx 无有效单元格")
    return parts


def chunk_sections(sections: list[dict[str, Any]], *,
                   size: int = _CHUNK_SIZE, overlap: int = _CHUNK_OVERLAP) -> list[dict[str, Any]]:
    """把段落/页切成固定长度 chunk（带重叠）。"""
    chunks: list[dict[str, Any]] = []
    idx = 0
    for sec in sections:
        text = (sec.get("text") or "").strip()
        if not text:
            continue
        heading = sec.get("heading")
        page = sec.get("page")
        if len(text) <= size:
            chunks.append({
                "chunkId": f"c{idx:04d}", "text": text,
                "heading": heading, "page": page, "seq": idx,
            })
            idx += 1
            continue
        start = 0
        while start < len(text):
            end = min(start + size, len(text))
            piece = text[start:end].strip()
            if piece:
                chunks.append({
                    "chunkId": f"c{idx:04d}", "text": piece,
                    "heading": heading, "page": page, "seq": idx,
                })
                idx += 1
            if end >= len(text):
                break
            start = max(end - overlap, start + 1)
    return chunks


def preview_ingest(filename: str, raw: bytes | None = None, path: str | None = None,
                   *, kind: str = "sop", title: str | None = None) -> dict[str, Any]:
    """预览导入：解析+切块，不写库。"""
    if path:
        sections = extract_text_from_path(path)
        fname = os.path.basename(path)
    elif raw is not None:
        sections = extract_text_from_bytes(filename, raw)
        fname = filename
    else:
        raise ValueError("需要提供 path 或 raw")
    chunks = chunk_sections(sections)
    title = title or os.path.splitext(fname)[0]
    return {
        "filename": fname,
        "title": title,
        "kind": kind,
        "sectionCount": len(sections),
        "chunkCount": len(chunks),
        "preview": [{"seq": c["seq"], "heading": c.get("heading"), "page": c.get("page"),
                     "chars": len(c["text"]), "snippet": c["text"][:80]} for c in chunks[:8]],
        "chunks": chunks,
    }


def confirmation_for_knowledge_import(preview: dict[str, Any]) -> tuple[str, list[str]]:
    """P2 确认卡文案。"""
    title = f"导入知识文档《{preview.get('title')}》"
    lines = [
        f"文件：{preview.get('filename')}",
        f"类型：{preview.get('kind')}",
        f"切块：{preview.get('chunkCount')} 段（来自 {preview.get('sectionCount')} 节/页）",
        "入库后可检索；默认已审批（approved=true）。",
    ]
    return title, lines


def apply_knowledge_import(preview: dict[str, Any], *, tags: list[str] | None = None,
                           store: Any = None) -> dict[str, Any]:
    """把预览结果写入知识库（带 chunks）。"""
    from server.knowledge.assets import get_knowledge
    kb = store or get_knowledge()
    chunks = preview.get("chunks") or []
    content = "\n\n".join(
        (f"【{c.get('heading') or '段落'}】\n" if c.get("heading") else "") + c["text"]
        for c in chunks
    )
    if not content.strip():
        raise ValueError("无正文可入库")
    asset = kb.add_with_chunks(
        kind=str(preview.get("kind") or "sop"),
        title=str(preview.get("title") or preview.get("filename") or "导入文档"),
        content=content[:8000],  # 资产摘要正文（检索仍优先 chunk）
        chunks=chunks,
        tags=tags or ["导入", str(preview.get("filename") or "")],
        source=str(preview.get("filename") or ""),
        approved=True,
    )
    return {"assetId": asset["assetId"], "title": asset["title"],
            "version": asset["version"], "chunkCount": len(asset.get("chunks") or [])}