修改数据结构

ESConnect.py

@@ -15,7 +15,7 @@ AUTH = None  # 如需认证则改为("用户名","密码")
 es = Elasticsearch(["http://localhost:9200"])
 
 # 定义索引名称和类型名称
-index_name = "wordsearch2"
+index_name = "wordsearch2666"
 
 def create_index_with_mapping():
     """修正后的索引映射配置"""
@@ -23,22 +23,12 @@ def create_index_with_mapping():
     mapping = {
         "mappings": {
             "properties": {
-                "id": {
-                    "type": "text",  # 改为text类型支持分词
+                "data": {
+                    "type": "text",  # 存储转换后的字符串，支持分词搜索
                     "analyzer": "ik_max_word",
                     "search_analyzer": "ik_smart"
                 },
-                "name": {
-                    "type": "text",
-                    "analyzer": "ik_max_word",
-                    "search_analyzer": "ik_smart"
-                },
-                "students": {"type": "keyword"},  # 仅保留type参数
-                "teacher": {"type": "keyword"},    # 仅保留type参数
-                "timestamp": {
-                    "type": "date",
-                    "format": "strict_date_optional_time||epoch_millis"
-                }
+                "image": {"type": "keyword"},  # 存储图片路径或标识
             }
         }
     }
@@ -54,8 +44,7 @@ def create_index_with_mapping():
 
 def get_doc_id(data):
     """
-    根据关键字段生成唯一ID（用于去重）
-    可以根据实际需求调整字段组合
+    根据数据内容生成唯一ID（用于去重）
     
     参数:
         data (dict): 包含文档数据的字典
@@ -63,8 +52,10 @@ def get_doc_id(data):
     返回:
         str: 基于数据内容生成的MD5哈希值作为唯一ID
     """
-    # 组合关键字段生成唯一字符串
-    unique_str = f"{data['id']}{data['name']}{data['students']}{data['teacher']}"
+    # 使用data字段的内容生成唯一字符串
+    data_str = data.get('data', '')
+    image_str = data.get('image', '')
+    unique_str = f"{data_str}{image_str}"
     # 使用MD5哈希生成唯一ID
     return hashlib.md5(unique_str.encode('utf-8')).hexdigest()
 
@@ -184,47 +175,3 @@ def batch_write_data(data):
     except requests.exceptions.HTTPError as e:
         print(f"文档写入失败: {e.response.text}, 数据: {data}")
         return False
-
-def update_mapping():
-    # 定义新的映射配置
-    new_mapping = {
-        "properties": {
-            "id": {
-                "type": "text",
-                "analyzer": "ik_max_word",
-                "search_analyzer": "ik_smart"
-            },
-            "name": {
-                "type": "text",
-                "analyzer": "ik_max_word"
-            },
-            "students": {
-                "type": "keyword"
-            },
-            "teacher": {
-                "type": "keyword"
-            }
-        }
-    }
-
-    # 执行PUT请求更新映射
-    try:
-        response = requests.put(
-            f"{ES_URL}/{index_name}/_mapping",
-            auth=AUTH,
-            json=new_mapping,
-            headers={"Content-Type": "application/json"}
-        )
-        response.raise_for_status()
-        print("索引映射更新成功")
-        print(response.json())
-
-        # 验证映射更新结果
-        verify = requests.get(
-            f"{ES_URL}/{index_name}/_mapping",
-            auth=AUTH
-        )
-        print("\n验证结果：")
-        print(verify.json())
-    except requests.exceptions.HTTPError as e:
-        print(f"请求失败: {e.response.text}")