Skip to content

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

fix(mcp): 修复关键词正则配置的 JSON 序列化 (#1137)

VanAlwaysd09c77eaaa33
diff --git a/mcp_server/services/data_service.py b/mcp_server/services/data_service.py
index 7ad0f8c60b..1db1758381 100644
--- a/mcp_server/services/data_service.py
+++ b/mcp_server/services/data_service.py
@@ -43,6 +43,16 @@ class DataService:
self.parser = ParserService(project_root)
self.cache = get_cache()
+ def _make_json_serializable(self, obj):
+ """将对象中的 re.Pattern 转换为字符串,使其可 JSON 序列化"""
+ if isinstance(obj, re.Pattern):
+ return obj.pattern
+ elif isinstance(obj, dict):
+ return {k: self._make_json_serializable(v) for k, v in obj.items()}
+ elif isinstance(obj, list):
+ return [self._make_json_serializable(item) for item in obj]
+ return obj
+
def get_latest_news(
self,
platforms: Optional[List[str]] = None,
@@ -476,6 +486,9 @@ class DataService:
config_data = self.parser.parse_yaml_config()
word_groups = self.parser.parse_frequency_words()
+ # 将 word_groups 中的正则表达式对象转换为字符串,使其可 JSON 序列化
+ word_groups = self._make_json_serializable(word_groups)
+
# 根据section返回对应配置
advanced = config_data.get("advanced", {})
advanced_crawler = advanced.get("crawler", {})
diff --git a/tests/test_config_serialization.py b/tests/test_config_serialization.py
new file mode 100644
index 0000000000..ed0598a362
--- /dev/null
+++ b/tests/test_config_serialization.py
@@ -0,0 +1,56 @@
+"""Configuration responses serialize regexes without changing cached matchers."""
+
+import json
+import re
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from mcp_server.services.data_service import DataService
+from trendradar.core.frequency import matches_word_groups
+
+
+class ConfigSerializationTests(unittest.TestCase):
+ def test_config_response_keeps_cached_regexes_usable(self):
+ with tempfile.TemporaryDirectory() as directory:
+ config = Path(directory) / "config"
+ config.mkdir()
+ (config / "config.yaml").write_text("{}\n", encoding="utf-8")
+ (config / "frequency_words.txt").write_text(
+ "[WORD_GROUPS]\n/ai|ml/i\n", encoding="utf-8"
+ )
+ service = DataService(directory)
+ cached_groups = service.parser.parse_frequency_words()
+ self.assertTrue(matches_word_groups("AI news", cached_groups, []))
+
+ with patch.dict("os.environ", {}, clear=True):
+ for section in ("keywords", "all"):
+ with self.subTest(section=section):
+ result = service.get_current_config(section)
+ decoded = json.loads(json.dumps(result))
+ keywords = decoded if section == "keywords" else decoded["keywords"]
+ self.assertEqual(keywords["total_groups"], 1)
+ self.assertTrue(keywords["word_groups"])
+
+ self.assertIs(service.parser.parse_frequency_words(), cached_groups)
+ regexes = []
+
+ def collect_regexes(value):
+ if isinstance(value, re.Pattern):
+ regexes.append(value)
+ elif isinstance(value, dict):
+ for child in value.values():
+ collect_regexes(child)
+ elif isinstance(value, list):
+ for child in value:
+ collect_regexes(child)
+
+ collect_regexes(cached_groups)
+ self.assertTrue(regexes)
+ self.assertTrue(matches_word_groups("ML update", cached_groups, []))
+ self.assertFalse(matches_word_groups("unrelated headline", cached_groups, []))
+
+
+if __name__ == "__main__":
+ unittest.main()