Quentin
9b0910ccb1
后端 (book_mcp_server.py, 335 行, 15 个 MCP 工具):
- create_book / add_document / mark_html_ready / mark_json_ready / mark_failed
- update_book_status / soft_delete_book / retry_failed
- get_book / list_books / get_document / list_documents / get_document_url
- upload_to_rustfs / health
- 走 JSON-RPC + stateless_http + json_response（前端可直接调）
- launchd 守护 / 6 秒拉起（macOS）
- systemd 守护脚本（Linux/codelab）
存储:
- MongoDB (mongo:8.0 容器) - book/book_document/document_file 三表
- RustFS 对象存储（fs.code-lab.cn/scan/）- book/<id>/docs/<doc_id>/{docx,html,json}
- 幂等设计: zip_sha256 唯一 + (book_id+original_path) 唯一
前端 (Vue 3 + TS + Arco Design):
- 列表页 /book/list - 搜索 + 状态过滤 + 进度
- 详情页 /book/:id - 文档折叠 + 文件下载
- MCP 客户端 src/api/mcp.ts (JSON-RPC over fetch)
部署:
- deploy/install.sh (codelab 一键装 backend + systemd)
- deploy/install-frontend.sh (vite dev / 生产构建)
- docs/deploy.md (运维手册)
测试:
- tests/test_basic.py (sanity 7 项)
- tests/test_e2e.py (完整 e2e: docx→HTML→入库→上传→校验)
77 lines
2.5 KiB
Python
77 lines
2.5 KiB
Python
"""docx XML 清洗：去脏值（单位 / NaN / 浮点）以避开 docx4j 8.3.9 JAXB 解析失败。
|
||
|
||
参考 wordparse_server.py 的 _clean_docx_xml，独立成模块方便测试。
|
||
"""
|
||
import re
|
||
import os
|
||
import zipfile
|
||
|
||
XML_DECL = re.compile(r'<\?xml[^?]*\?>')
|
||
|
||
|
||
def _fix_text(txt: str) -> str:
|
||
"""修三类问题：
|
||
1. 带单位的数字属性："210mm" / "25.4cm" → "0"
|
||
2. NaN / Inf / -Inf / 空字符串 → "0"
|
||
3. 浮点属性 → 整数（JAXB BigInteger 不接小数）
|
||
"""
|
||
decl = XML_DECL.search(txt)
|
||
decl_str = decl.group(0) if decl else '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
|
||
if decl:
|
||
txt = XML_DECL.sub('__XMLDECL__', txt, count=1)
|
||
|
||
# 1. 单位
|
||
txt = re.sub(r'="(-?[0-9]*\.?[0-9]+)\s*(mm|cm|pt|px|in|em|%)"', r'="0"', txt, flags=re.I)
|
||
# 2. NaN / Inf
|
||
txt = re.sub(r'="(NaN|nan|Inf|-Inf|inf|-inf)"', '="0"', txt, flags=re.I)
|
||
# 3. 空
|
||
txt = re.sub(r'=""', '="0"', txt)
|
||
# 4. 浮点 → 整数
|
||
def _num(m):
|
||
try:
|
||
f = float(m.group(1))
|
||
if f != f or f == float('inf') or f == float('-inf'):
|
||
return '="0"'
|
||
return f'="{int(f)}"'
|
||
except Exception:
|
||
return m.group(0)
|
||
|
||
txt = re.sub(r'="(-?[0-9]+\.[0-9]+(?:[eE][-+]?[0-9]+)?)"', _num, txt)
|
||
|
||
if decl:
|
||
txt = txt.replace('__XMLDECL__', decl_str, 1)
|
||
return txt
|
||
|
||
|
||
def clean_docx(path: str) -> str:
|
||
"""清洗 docx 里的 word/document.xml，幂等。失败回退原文件。"""
|
||
marker = path + '.cleaned'
|
||
if os.path.exists(marker):
|
||
return path
|
||
|
||
try:
|
||
with zipfile.ZipFile(path, 'r') as zin:
|
||
entries = []
|
||
changed = False
|
||
for item in zin.infolist():
|
||
data = zin.read(item.filename)
|
||
if item.filename == 'word/document.xml':
|
||
raw = data.decode('utf-8', errors='replace')
|
||
new = _fix_text(raw)
|
||
if new != raw:
|
||
data = new.encode('utf-8')
|
||
changed = True
|
||
entries.append((item, data))
|
||
if not changed:
|
||
open(marker, 'w').close()
|
||
return path
|
||
tmp = path + '.tmp'
|
||
with zipfile.ZipFile(tmp, 'w', zipfile.ZIP_DEFLATED) as zout:
|
||
for item, data in entries:
|
||
zout.writestr(item, data)
|
||
os.replace(tmp, path)
|
||
open(marker, 'w').close()
|
||
return path
|
||
except Exception:
|
||
return path
|