refactor(db)!: adopt project-routed pooled databases

Reorganize WNDB by responsibility and remove legacy scheme endpoints.\n\nRoute analysis and time-series access through project pools, preserve transactional realtime replacement, and refresh GIS materialized views after writes.\n\nAdd database architecture documentation, live pooling coverage, API contract updates, and executable container verification.\n\nBREAKING CHANGE: legacy scheme APIs and flat app.native.wndb module imports are removed.
2026-08-25 18:35:05 +08:00
parent fdbcc5c033
commit fa188af0b1
181 changed files with 8446 additions and 33546 deletions
@@ -5,15 +5,16 @@ from typing import Any, Dict, List, Optional, Tuple
 import numpy as np
 import pandas as pd
 from psycopg import AsyncConnection
+from uuid import UUID

-import app.native.wndb as wndb
 from app.algorithms.cleaning.flow import clean_flow_data_df_kf
 from app.algorithms.cleaning.pressure import clean_pressure_data_df_km
 from app.algorithms.health.analyzer import PipelineHealthAnalyzer
 from app.infra.db.postgresql.scada import ScadaInfoRepository
 from app.infra.db.timescaledb.repositories.realtime import RealtimeRepository
-from app.infra.db.timescaledb.repositories.scheme import SchemeRepository
+from app.infra.db.timescaledb.repositories.analysis import AnalysisResultsRepository
 from app.infra.db.timescaledb.repositories.scada import ScadaRepository
+from app.native.wndb.model.pipes import get_pipes_by_property


 class CompositeQueries:
@@ -26,7 +27,7 @@ class CompositeQueries:
        postgres_conn: AsyncConnection,
    ) -> Dict[str, Dict[str, Any]]:
        scadas = await ScadaInfoRepository.get_scadas(postgres_conn)
-        return {scada["id"]: scada for scada in scadas}
+        return {scada["device_id"]: scada for scada in scadas}

    @staticmethod
    async def get_scada_associated_realtime_simulation_data(
@@ -63,8 +64,12 @@ class CompositeQueries:
            if not target_scada:
                raise ValueError(f"SCADA device {device_id} not found")

-            element_id = target_scada["associated_element_id"]
-            scada_type = target_scada["type"]
+            scada_type = target_scada["device_type"]
+            element_id = (
+                target_scada["link_id"]
+                if scada_type in {"pipe_flow", "flow"}
+                else target_scada["node_id"]
+            )

            if scada_type == "pipe_flow":
                # 查询 link 模拟数据
@@ -85,17 +90,16 @@ class CompositeQueries:
        return result

    @staticmethod
-    async def get_scada_associated_scheme_simulation_data(
+    async def get_scada_associated_analysis_simulation_data(
        timescale_conn: AsyncConnection,
        postgres_conn: AsyncConnection,
        device_ids: List[str],
        start_time: datetime,
        end_time: datetime,
-        scheme_type: str,
-        scheme_name: str,
+        run_id: UUID,
    ) -> Dict[str, List[Dict[str, Any]]]:
        """
-        获取 SCADA 关联的 link/node scheme 模拟值
+        获取 SCADA 关联的 link/node 分析模拟值

        根据传入的 SCADA device_ids，找到关联的 link/node，
        并根据对应的 type，查询对应的模拟数据
@@ -121,30 +125,22 @@ class CompositeQueries:
            if not target_scada:
                raise ValueError(f"SCADA device {device_id} not found")

-            element_id = target_scada["associated_element_id"]
-            scada_type = target_scada["type"]
+            scada_type = target_scada["device_type"]
+            element_id = (
+                target_scada["link_id"]
+                if scada_type in {"pipe_flow", "flow"}
+                else target_scada["node_id"]
+            )

            if scada_type == "pipe_flow":
                # 查询 link 模拟数据
-                res = await SchemeRepository.get_link_field_by_scheme_and_time_range(
-                    timescale_conn,
-                    scheme_type,
-                    scheme_name,
-                    start_time,
-                    end_time,
-                    element_id,
-                    "flow",
+                res = await AnalysisResultsRepository.get_link_series(
+                    timescale_conn, run_id, element_id, start_time, end_time, "flow"
                )
            elif scada_type == "pressure":
                # 查询 node 模拟数据
-                res = await SchemeRepository.get_node_field_by_scheme_and_time_range(
-                    timescale_conn,
-                    scheme_type,
-                    scheme_name,
-                    start_time,
-                    end_time,
-                    element_id,
-                    "pressure",
+                res = await AnalysisResultsRepository.get_node_series(
+                    timescale_conn, run_id, element_id, start_time, end_time, "pressure"
                )
            else:
                raise ValueError(f"Unknown SCADA type: {scada_type}")
@@ -201,16 +197,15 @@ class CompositeQueries:
        return result

    @staticmethod
-    async def get_scheme_simulation_data(
+    async def get_analysis_simulation_data(
        timescale_conn: AsyncConnection,
        feature_infos: List[Tuple[str, str]],
        start_time: datetime,
        end_time: datetime,
-        scheme_type: str,
-        scheme_name: str,
+        run_id: UUID,
    ) -> Dict[str, List[Dict[str, Any]]]:
        """
-        获取 link/node scheme 模拟值
+        获取 link/node 分析模拟值

        根据传入的 feature_infos，找到关联的 link/node，
        并根据对应的 type，查询对应的模拟数据
@@ -220,8 +215,7 @@ class CompositeQueries:
            feature_infos: 传入的 feature 信息列表，包含 (element_id, type)
            start_time: 开始时间
            end_time: 结束时间
-            scheme_type: 工况类型
-            scheme_name: 工况名称
+            run_id: 分析运行 ID

        Returns:
            模拟数据字典，以 feature_id 为键，值为数据列表，每个数据包含 time, value 和 feature_id
@@ -233,25 +227,13 @@ class CompositeQueries:
        for feature_id, feature_type in feature_infos:
            if feature_type.lower() == "pipe":
                # 查询 link 模拟数据
-                res = await SchemeRepository.get_link_field_by_scheme_and_time_range(
-                    timescale_conn,
-                    scheme_type,
-                    scheme_name,
-                    start_time,
-                    end_time,
-                    feature_id,
-                    "flow",
+                res = await AnalysisResultsRepository.get_link_series(
+                    timescale_conn, run_id, feature_id, start_time, end_time, "flow"
                )
            elif feature_type.lower() == "junction":
                # 查询 node 模拟数据
-                res = await SchemeRepository.get_node_field_by_scheme_and_time_range(
-                    timescale_conn,
-                    scheme_type,
-                    scheme_name,
-                    start_time,
-                    end_time,
-                    feature_id,
-                    "pressure",
+                res = await AnalysisResultsRepository.get_node_series(
+                    timescale_conn, run_id, feature_id, start_time, end_time, "pressure"
                )
            else:
                raise ValueError(f"Unknown type: {feature_type}")
@@ -296,7 +278,7 @@ class CompositeQueries:
            (
                scada
                for scada in scada_by_id.values()
-                if scada["associated_element_id"] == element_id
+                if (scada.get("node_id") or scada.get("link_id")) == element_id
            ),
            None,
        )
@@ -304,7 +286,7 @@ class CompositeQueries:
        if not associated_scada:
            return None

-        device_id = associated_scada["id"]
+        device_id = associated_scada["device_id"]

        data_field = "cleaned_value" if use_cleaned else "monitored_value"

@@ -358,7 +340,7 @@ class CompositeQueries:
            unsupported_ids = [
                device_id
                for device_id in device_ids
-                if scada_by_id[device_id]["type"] not in supported_types
+                if scada_by_id[device_id]["device_type"] not in supported_types
            ]
            if unsupported_ids:
                raise ValueError(
@@ -368,7 +350,7 @@ class CompositeQueries:
            device_ids = [
                device_id
                for device_id, info in scada_by_id.items()
-                if info["type"] in supported_types
+                if info["device_type"] in supported_types
            ]

        if not device_ids:
@@ -409,12 +391,12 @@ class CompositeQueries:
        pressure_ids = [
            device_id
            for device_id in df.columns
-            if scada_by_id[device_id]["type"] == "pressure"
+            if scada_by_id[device_id]["device_type"] == "pressure"
        ]
        flow_ids = [
            device_id
            for device_id in df.columns
-            if scada_by_id[device_id]["type"] in {"pipe_flow", "flow"}
+            if scada_by_id[device_id]["device_type"] in {"pipe_flow", "flow"}
        ]

        updated_rows = 0
@@ -497,7 +479,7 @@ class CompositeQueries:

            # 批量查询这些管道的详细信息
            fields = ["id", "diameter", "node1", "node2"]
-            all_links = wndb.get_pipes_by_property(network_name, fields=fields)
+            all_links = get_pipes_by_property(network_name, fields=fields)

            # 转换为字典以快速查找
            links_dict = {link["id"]: link for link in all_links}