init

2026-07-10 18:55:55 +08:00
commit fce40c7d6c
317 changed files with 170079 additions and 0 deletions
@@ -0,0 +1,128 @@
+from datetime import datetime, timezone
+from flask import current_app
+from databricks import sql
+
+
+class DatabricksQuery:
+    def __init__(self):
+        """纯Python连接Databricks SQL，无JVM依赖"""
+        try:
+            # 读取配置（参数和原代码一致，无需修改）
+            self.host = current_app.config["DATABRICKS_HOST"]
+            self.token = current_app.config["DATABRICKS_TOKEN"]
+            self.cluster_id = current_app.config["CLUSTER_ID"]
+
+            # 校验参数
+            if not all([self.host, self.token, self.cluster_id]):
+                raise ValueError(
+                    "必须配置DATABRICKS_HOST、DATABRICKS_TOKEN、CLUSTER_ID"
+                )
+
+            print("Databricks SQL 连接器初始化成功")
+        except Exception as e:
+            print(f"初始化失败: {e}")
+            raise
+
+    # 复用原有参数校验逻辑
+    @staticmethod
+    def _validate_table_name(table_name):
+        if not table_name or not isinstance(table_name, str):
+            raise ValueError(f"无效的表名: {table_name}")
+        if ";" in table_name:
+            raise ValueError(f"表名包含非法字符 ';': {table_name}")
+        parts = table_name.split(".")
+        if len(parts) != 3:
+            raise ValueError(f"表名格式应为 catalog.schema.table: {table_name}")
+
+    @staticmethod
+    def _validate_vin(vin):
+        if vin is None:
+            return True
+        if not isinstance(vin, str):
+            raise ValueError(f"无效的 VIN: {vin} (必须是17位字母数字)")
+        return True
+
+    def query_table(
+        self, table_name, vin=None, start_time=None, end_time=None,limit=None
+    ):
+        """纯Python查询表数据，无JVM依赖"""
+        try:
+            # 验证参数
+            self._validate_table_name(table_name)
+            self._validate_vin(vin)
+
+            # 构建SQL查询语句（替代原PySpark DataFrame操作）
+            select_fields = """
+                Incident__Name AS incident_name,
+                Incident__description AS incident_description,
+                Meaning AS meaning,
+                Signal__Name As signal_name,
+                incident_time,
+                oneid,
+                speed,
+                int_value,
+                idc_tickcount_ms,
+                latitude,
+                longitude,
+                mux_data,
+                gps_heading,
+                float_value
+            """
+            
+            sql_query = f"SELECT {select_fields} FROM {table_name}"
+            where_conditions = []
+
+            # 拼接过滤条件
+            if vin:
+                where_conditions.append(f"oneid = '{vin}'")
+            if start_time:
+                start_dt = self._parse_iso_time(start_time).isoformat()
+                where_conditions.append(f"incident_time >= '{start_dt}'")
+            if end_time:
+                end_dt = self._parse_iso_time(end_time).isoformat()
+                where_conditions.append(f"incident_time <= '{end_dt}'")
+            
+            # 拼接WHERE子句
+            if where_conditions:
+                sql_query += " WHERE " + " AND ".join(where_conditions)
+            # 拼接LIMIT
+            if limit is not None:
+                sql_query += f" LIMIT {limit}"
+            
+            # sql_query="select * from hive_metastore.taf_level_two_plus.accident_report_data WHERE oneid = 'LE4LG4GB6SL256937' limit 1"
+            print(f"查询sql:{sql_query}")
+            
+            # 执行SQL（纯Python，无JVM）
+            with sql.connect(
+                server_hostname=self.host,
+                http_path=f"sql/protocolv1/o/3035612432650494/{self.cluster_id}",  # 注意路径格式
+                access_token=self.token,
+            ) as connection:
+                with connection.cursor() as cursor:
+                    cursor.execute(sql_query)
+                    # 获取列名和数据，转换为字典格式（和原代码返回格式一致）
+                    columns = [desc[0] for desc in cursor.description]
+                    results = []
+                    for row in cursor.fetchall():
+                        results.append(dict(zip(columns, row)))
+                return results
+            
+        except Exception as e:
+            print(f"查询失败: {str(e)}")
+            raise
+
+    # 复用原有时间解析逻辑
+    def _parse_iso_time(self, time_str):
+        try:
+            if time_str.endswith("Z"):
+                time_str = time_str[:-1] + "+00:00"
+            dt = datetime.fromisoformat(time_str)
+            if dt.tzinfo is None:
+                dt = dt.replace(tzinfo=timezone.utc)
+            return dt
+        except Exception as e:
+            raise ValueError(f"无效的时间格式 '{time_str}': {str(e)}")
+
+    def stop(self):
+        # 纯Python连接器无需关闭SparkSession，此处保留方法以兼容原有调用逻辑
+        print("Databricks SQL 连接已释放")