# office_read.dspy - 读取工作空间 docx 文件，转 markdown 返回给 univer-office 前端
import os
import aiohttp

file_id = (params_kw or {}).get('file', '').strip()

uid = await get_user()
if not uid:
    uid = 'user-01'

session_id = (params_kw or {}).get('session_id', '') or ''
pipeline_id = (params_kw or {}).get('pipeline_id', '') or ''

dbname = get_module_dbname('pipeline-sdlc')

async with DBPools().sqlorContext(dbname) as sor:
    # 产线隔离：跨产线项目视为无项目（与弹窗入口一致，防绕过）
    project_dir, _ = await get_project_dir_pl(sor, uid, session_id, pipeline_id)
    space_dir, _ = await get_space_dir(sor, uid, session_id)
    # 通用会话（pipeline_id=_generic）：锁用户专属目录 _general/{uid}
    # （2026-09-17 补齐：此前缺该分支，通用助手在线编辑 docx 报「未指定文件或无工作空间」）
    if pipeline_id == '_generic':
        _gd = generic_workspace_dir(uid)
        os.makedirs(_gd, exist_ok=True)
        project_dir = _gd
        space_dir = _gd

if not file_id or not space_dir:
    return {"error": "未指定文件或无工作空间", "markdown": ""}

full_path = resolve_workspace_path(project_dir, space_dir, file_id)

# 路径穿越校验
real_ws = os.path.realpath(space_dir)
real_full = os.path.realpath(full_path)
if not real_full.startswith(real_ws + os.sep):
    return {"error": "非法路径", "markdown": ""}

if not os.path.isfile(full_path):
    return {"error": "文件不存在", "markdown": ""}

# 按扩展名分流：xlsx → IWorkbookData（表格），其余（docx）→ IDocumentData（文档）
# （2026-09-18 xlsx 在线查看/编辑接入）
_is_sheet = file_id.lower().endswith(('.xlsx', '.xlsm'))

# 读文件 bytes
with open(full_path, 'rb') as f:
    file_bytes = f.read()

# 调 univer-office 转换（格式保真，跳过 markdown）
try:
    timeout = aiohttp.ClientTimeout(total=60)
    async with aiohttp.ClientSession(timeout=timeout) as session:
        if _is_sheet:
            async with session.post(
                'http://127.0.0.1:19091/convert/xlsx-to-workbookdata',
                data=file_bytes,
                headers={'Content-Type': 'application/octet-stream'},
            ) as resp:
                if resp.status != 200:
                    return {"error": "转换失败 HTTP " + str(resp.status), "workbookData": None}
                workbook_data = await resp.json()
                return {"workbookData": workbook_data}
        else:
            async with session.post(
                'http://127.0.0.1:19091/convert/docx-to-docdata',
                data=file_bytes,
                headers={'Content-Type': 'application/octet-stream'},
            ) as resp:
                if resp.status != 200:
                    return {"error": "转换失败 HTTP " + str(resp.status), "documentData": None}
                doc_data = await resp.json()
                return {"documentData": doc_data}
except Exception as e:
    return {"error": str(e), "documentData": None, "workbookData": None}