49 lines
1.5 KiB
Plaintext
49 lines
1.5 KiB
Plaintext
# 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'
|
||
|
||
dbname = get_module_dbname('pipeline-sdlc')
|
||
|
||
async with DBPools().sqlorContext(dbname) as sor:
|
||
ws_dir, _ = await get_workspace_dir(sor, uid)
|
||
|
||
if not file_id or not ws_dir:
|
||
return {"error": "未指定文件或无工作空间", "markdown": ""}
|
||
|
||
full_path = ws_dir + '/' + file_id
|
||
|
||
# 路径穿越校验
|
||
real_ws = os.path.realpath(ws_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": ""}
|
||
|
||
# 读 docx bytes
|
||
with open(full_path, 'rb') as f:
|
||
docx_bytes = f.read()
|
||
|
||
# 调 univer-office 转 IDocumentData（格式保真，跳过 markdown）
|
||
try:
|
||
timeout = aiohttp.ClientTimeout(total=60)
|
||
async with aiohttp.ClientSession(timeout=timeout) as session:
|
||
async with session.post(
|
||
'http://127.0.0.1:19091/convert/docx-to-docdata',
|
||
data=docx_bytes,
|
||
headers={'Content-Type': 'application/octet-stream'},
|
||
) as resp:
|
||
if resp.status != 200:
|
||
return {"error": f"转换失败 HTTP {resp.status}", "documentData": None}
|
||
doc_data = await resp.json()
|
||
return {"documentData": doc_data}
|
||
except Exception as e:
|
||
return {"error": str(e), "documentData": None}
|