新增：查询数据库的重试次数配置

Author: Samge0

ragflows/configs.demo.py

@@ -31,6 +31,9 @@
 # 切片进度查询间隔时间（秒）
 PROGRESS_CHECK_INTERVAL = 1
 
+# 查数据库重试次数（单次重试间隔为1秒）
+SQL_RETRIES = 1
+
 
 def get_header():
     return {'authorization': AUTHORIZATION}

ragflows/ragflowdb.py

@@ -7,6 +7,7 @@
 from ragflows import configs
 from utils.mysqlutils import BaseMySql
 from utils import timeutils
+import time
 
 
 rag_db = None
@@ -17,8 +18,8 @@ def reset_connection():
     if rag_db:
         try:
             rag_db.close_connect()
-        except:
-            pass
+        except Exception as e:
+            timeutils.print_log(f'reset_connection error: {e}')
     rag_db = None
 
 def get_db():
@@ -47,17 +48,28 @@ def get_doc_item(doc_id):
     results = db.query_list(sql)
     return results[0] if results else None
 
-# @timeutils.monitor
-def get_doc_item_by_name(name):
-    db = get_db()
-    kb_id = configs.DIFY_DOC_KB_ID
-    if kb_id:
-        # 这里同时查询kb_id和name，如果document表中的数据量很大，需要增加kb_id和name的组合索引：CREATE INDEX document_kb_id_name ON document(kb_id, name);
-        sql = f"select id,name,progress from document where kb_id = '{kb_id}' and name = '{name}'"
-    else:
-        sql = f"select id,name,progress from document where name = '{name}'"
-    results = db.query_list(sql)
-    return results[0] if results else None
+def get_doc_item_by_name(name, max_retries=configs.SQL_RETRIES, retry_interval=1):
+    """
+    根据文档名称获取文档信息，支持重试机制
+    :param name: 文档名称
+    :param max_retries: 最大重试次数
+    :param retry_interval: 重试间隔（秒）
+    :return: 文档信息或None
+    """
+    for attempt in range(max_retries):
+        db = get_db()
+        kb_id = configs.DIFY_DOC_KB_ID
+        if kb_id:
+            sql = f"select id,name,progress from document where kb_id = '{kb_id}' and name = '{name}'"
+        else:
+            sql = f"select id,name,progress from document where name = '{name}'"
+        results = db.query_list(sql)
+        if results:
+            return results[0]
+        if attempt < max_retries - 1:  # 如果不是最后一次尝试
+            timeutils.print_log(f"查询 {name} 无结果，第{attempt + 1}次重试...")
+            time.sleep(retry_interval)
+    return None
 
 def exist(doc_id):
     return get_doc_item(doc_id) is not None

scripts/launcher.py

@@ -77,10 +77,10 @@ def __init__(self):
         self.log_handlers = []  # 添加日志处理器列表
         self.original_print_log = None  # 保存原始的日志打印函数
         self.title("RagFlow Upload")
-        self.geometry("800x660")
+        self.geometry("800x700")
 
         # 版本和仓库信息
-        self.version = "v1.0.2"  # 版本号
+        self.version = "v1.0.2-alpha"  # 版本号
         self.github_repo = "https://github.com/Samge0/ragflow-upload"  # GitHub仓库地址
 
         # 自定义图标
@@ -99,6 +99,7 @@ def __init__(self):
             "DOC_DIR": {"type": str, "label": "文档目录", "default": "your doc dir"},
             "DOC_SUFFIX": {"type": str, "label": "文档后缀", "default": "md,txt,pdf,docx"},
             "PROGRESS_CHECK_INTERVAL": {"type": int, "label": "切片进度查询间隔", "default": "1"},
+            "SQL_RETRIES": {"type": int, "label": "SQL查询重试次数", "default": "1"},
 
             "MYSQL_HOST": {"type": str, "label": "MySQL主机", "default": "localhost"},
             "MYSQL_PORT": {"type": int, "label": "MySQL端口", "default": "5455"},

utils/mysqlutils.py

@@ -6,6 +6,8 @@
 import pymysql
 import logging
 
+from utils import timeutils
+
 class BaseMySql(object):
 
     conn = None
@@ -34,7 +36,7 @@ def __init__(self, host=None, user=None, password=None, database=None, port=None
             self.conn.commit()
 
         except Exception as e:
-            self.e(e)
+            timeutils.print_log(f'连接数据库异常: {e}')
             pass
 
     def query_list(self, sql: str) -> list:
@@ -51,7 +53,7 @@ def query_list(self, sql: str) -> list:
             columns = [col[0] for col in cur.description]
             return [dict(zip(columns, self.parse_encoding(row))) for row in cur.fetchall()]
         except Exception as e:
-            self.e(e)
+            timeutils.print_log(f'query_list 查询数据异常: {e}')
             return []
 
     def execute(self, sql: str) -> bool:
@@ -67,7 +69,7 @@ def execute(self, sql: str) -> bool:
             self.conn.commit()
             return True
         except Exception as e:
-            self.e(e)
+            timeutils.print_log(f'execute 执行sql异常，sql = {sql}\n error: {e}')
             return False
 
     def parse_encoding(self, row) -> list:
@@ -89,43 +91,15 @@ def close_connect(self) -> None:
             self.cursor.close()
             self.conn.close()
             self.child_close()
-            self.i('释放数据库连接')
+            timeutils.print_log(f'close_connect 已关闭数据库连接')
         except Exception as e:
-            self.e(e)
+            timeutils.print_log(f'close_connect 关闭数据库异常: {e}')
 
     def child_close(self) -> None:
         """
         提供给子类处理的关闭操作
         """
         pass
-
-    def _need_update(self, spider) -> bool:
-        """
-        判断该爬虫是否需要进行更新操作
-        :param spider:
-        :return:
-        """
-        try:
-            if not spider or not hasattr(spider, 'NEED_UPDATE'):
-                return False
-            self.i(f"是否需要进行更新 spider.NEED_UPDATE={spider.NEED_UPDATE}")
-            return spider.NEED_UPDATE
-        except:
-            return False
-
-    def _get_update_field_list(self, spider) -> list:
-        """
-        获取需要指定更新的字段
-        :param spider:
-        :return:
-        """
-        try:
-            if not spider or not hasattr(spider, 'UPDATE_FIELD_LIST'):
-                return []
-            self.i(f"指定更新字段 spider.UPDATE_FIELD_LIST={spider.UPDATE_FIELD_LIST}")
-            return spider.UPDATE_FIELD_LIST
-        except:
-            return []
 
     def i(self, msg):
         self.logger.info(msg)