refactor: replace dicttoxml with stdlib implementation to avoid GPL license risk

Author: ulleo

backend/apps/data_training/curd/data_training.py

@@ -1,10 +1,8 @@
 import datetime
-import logging
 import traceback
 from typing import List, Optional
 from xml.dom.minidom import parseString
 
-import dicttoxml
 from sqlalchemy import and_, select, func, delete, update, or_
 from sqlalchemy import text
 
@@ -15,6 +13,7 @@
 from apps.template.generate_chart.generator import get_base_data_training_template
 from common.core.config import settings
 from common.core.deps import SessionDep, Trans
+from common.utils.dict_to_xml import dict_to_xml
 from common.utils.embedding_threads import run_save_data_training_embeddings
 
 
@@ -594,14 +593,7 @@ def select_training_by_question(session: SessionDep, question: str, oid: int, da
 
 def to_xml_string(_dict: list[dict] | dict, root: str = 'sql-examples') -> str:
     item_name_func = lambda x: 'sql-example' if x == 'sql-examples' else 'item'
-    dicttoxml.LOG.setLevel(logging.ERROR)
-    xml = dicttoxml.dicttoxml(_dict,
-                              cdata=['question', 'suggestion-answer'],
-                              custom_root=root,
-                              item_func=item_name_func,
-                              xml_declaration=False,
-                              encoding='utf-8',
-                              attr_type=False).decode('utf-8')
+    xml = dict_to_xml(_dict, root_name=root, item_func=item_name_func)
     pretty_xml = parseString(xml).toprettyxml()
 
     if pretty_xml.startswith('<?xml'):

backend/apps/terminology/curd/terminology.py

@@ -1,10 +1,8 @@
 import datetime
-import logging
 import traceback
 from typing import List, Optional, Any
 from xml.dom.minidom import parseString
 
-import dicttoxml
 from sqlalchemy import and_, or_, select, func, delete, update, union, text, BigInteger
 from sqlalchemy.orm import aliased
 
@@ -15,6 +13,7 @@
 from apps.terminology.models.terminology_model import Terminology, TerminologyInfo, TerminologyInfoResult
 from common.core.config import settings
 from common.core.deps import SessionDep, Trans
+from common.utils.dict_to_xml import dict_to_xml
 from common.utils.embedding_threads import run_save_terminology_embeddings
 
 
@@ -949,14 +948,7 @@ def get_example():
 
 def to_xml_string(_dict: list[dict] | dict, root: str = 'terminologies') -> str:
     item_name_func = lambda x: 'terminology' if x == 'terminologies' else 'word' if x == 'words' else 'item'
-    dicttoxml.LOG.setLevel(logging.ERROR)
-    xml = dicttoxml.dicttoxml(_dict,
-                              cdata=['word', 'description'],
-                              custom_root=root,
-                              item_func=item_name_func,
-                              xml_declaration=False,
-                              encoding='utf-8',
-                              attr_type=False).decode('utf-8')
+    xml = dict_to_xml(_dict, root_name=root, item_func=item_name_func)
     pretty_xml = parseString(xml).toprettyxml()
 
     if pretty_xml.startswith('<?xml'):

backend/common/utils/dict_to_xml.py

@@ -0,0 +1,49 @@
+"""
+将 dict/list 转换为 XML 字符串的工具函数，用于替代 dicttoxml 库（GPL 许可证风险）。
+仅依赖 Python 标准库。
+"""
+
+import xml.etree.ElementTree as ET
+
+
+def _add_element(parent: ET.Element, key: str, value, item_func=None):
+    """递归地将值添加为 XML 子元素。"""
+    elem = ET.SubElement(parent, key)
+
+    if isinstance(value, dict):
+        for k, v in value.items():
+            _add_element(elem, k, v, item_func)
+    elif isinstance(value, list):
+        item_name = item_func(key) if item_func else 'item'
+        for item in value:
+            _add_element(elem, item_name, item, item_func)
+    elif isinstance(value, bool):
+        elem.text = str(value).lower()
+    elif value is None:
+        elem.text = ''
+    else:
+        elem.text = str(value)
+
+
+def dict_to_xml(data: dict | list, root_name: str = 'root', item_func=None) -> str:
+    """
+    将 dict 或 list 转换为 XML 字符串。
+
+    :param data: 要转换的 dict 或 list
+    :param root_name: XML 根元素名称
+    :param item_func: 列表项元素名的函数，接收父元素名，返回子元素名
+    :return: XML 字符串
+    """
+    root = ET.Element(root_name)
+
+    if isinstance(data, dict):
+        for key, value in data.items():
+            _add_element(root, key, value, item_func)
+    elif isinstance(data, list):
+        item_name = item_func(root_name) if item_func else 'item'
+        for item in data:
+            _add_element(root, item_name, item, item_func)
+    else:
+        root.text = str(data)
+
+    return ET.tostring(root, encoding='unicode', xml_declaration=False)

backend/pyproject.toml

@@ -47,7 +47,6 @@ dependencies = [
     "python-calamine>=0.4.0",
     "xlrd>=2.0.2",
     "clickhouse-sqlalchemy>=0.3.2",
-    "dicttoxml>=1.7.16",
     "dmpython==2.5.22; platform_system != 'Darwin'",
     "redshift-connector>=2.1.8",
     "elasticsearch[requests] (>=7.10,<8.0)",