refactor: centralize numeric normalization

app/ARCHITECTURE.md

@@ -36,7 +36,7 @@ background scheduler
 - `backend/features/<feature>/` owns the mechanically moved service, repository, HTTP, agent,
   or deterministic calculation code for that product area.
 - `backend/data/` owns provider construction, source policy, provenance, units, freshness,
-  coverage, and display-versus-calculation eligibility.
+  coverage, display-versus-calculation eligibility, and shared numeric normalization policies.
 - `backend/database/` owns connection management, ordered migrations, and narrow repository
   adapters. Root `database.py` remains the legacy schema/composition anchor and combines the
   feature repository mixins; do not add feature queries to it.

app/backend/data/numbers.py

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+import math
+from typing import Any
+
+
+def finite_number(value: Any, default: float = 0.0) -> float:
+    try:
+        number = float(value)
+        return number if math.isfinite(number) else default
+    except (TypeError, ValueError):
+        return default
+
+
+def non_nan_number(value: Any, default: float = 0.0) -> float:
+    try:
+        number = float(value)
+        return number if number == number else default
+    except (TypeError, ValueError):
+        return default

app/backend/data/providers/tushare_client.py

@@ -11,6 +11,7 @@ from datetime import datetime, time as dt_time, timedelta
 from threading import Lock
 from typing import Any, ClassVar
 
+from backend.data.numbers import finite_number as _number
 from backend.features.sentiment.engine import apply_sentiment_to_dashboard
 
 
@@ -1812,14 +1813,6 @@ class TushareClient:
         }
 
 
-def _number(value: Any, default: float = 0.0) -> float:
-    try:
-        number = float(value)
-        return number if math.isfinite(number) else default
-    except (TypeError, ValueError):
-        return default
-
-
 def _text(value: Any) -> str:
     if isinstance(value, (list, tuple, set)):
         return "、".join(str(item).strip() for item in value if str(item).strip())

app/backend/features/market/charts.py

@@ -12,6 +12,7 @@ from datetime import datetime, time as dt_time, timedelta
 from threading import Lock
 from typing import Any, ClassVar
 
+from backend.bootstrap.config import tushare_code as _stock_market_code
 from backend.data.providers.ifind_client import IfindError, IfindHttpClient
 
 
@@ -475,16 +476,6 @@ def _ifind_point(row: dict[str, Any]) -> dict[str, Any] | None:
     }
 
 
-def _stock_market_code(code: str) -> str:
-    if code.startswith(("4", "8", "9")):
-        suffix = "BJ"
-    elif code.startswith("6"):
-        suffix = "SH"
-    else:
-        suffix = "SZ"
-    return f"{code}.{suffix}"
-
-
 def _number(value: Any) -> float:
     try:
         return float(value or 0)

app/backend/features/market/insights.py

@@ -6,6 +6,7 @@ from datetime import datetime, time as dt_time, timedelta, timezone
 from statistics import median
 from typing import TYPE_CHECKING, Any, Callable
 
+from backend.data.numbers import non_nan_number as _number
 from backend.data.providers.ifind_client import IfindError, IfindHttpClient
 from backend.data.providers.tushare_client import TushareClient, TushareError
 
@@ -16,14 +17,6 @@ if TYPE_CHECKING:
 CHINA_TIMEZONE = timezone(timedelta(hours=8))
 
 
-def _number(value: Any, default: float = 0.0) -> float:
-    try:
-        number = float(value)
-        return number if number == number else default
-    except (TypeError, ValueError):
-        return default
-
-
 def _display_date(value: str) -> str:
     text = str(value or "").replace("-", "")
     if len(text) != 8:

app/backend/features/screener/engine.py

@@ -9,6 +9,7 @@ from datetime import datetime, timedelta
 from typing import Any
 
 from advanced_strategies import ADVANCED_CURATED_STRATEGIES
+from backend.data.numbers import finite_number as _number
 from database import ReviewDatabase
 from backend.features.sentiment.engine import build_sentiment_history, latest_contiguous_history
 from tushare_client import TushareClient, TushareError
@@ -2201,13 +2202,5 @@ def _regime_reason(regime: str) -> str:
     }.get(regime, "市场阶段待确认。")
 
 
-def _number(value: Any, default: float = 0.0) -> float:
-    try:
-        number = float(value)
-        return number if math.isfinite(number) else default
-    except (TypeError, ValueError):
-        return default
-
-
 def _display_date(value: str) -> str:
     return f"{value[:4]}-{value[4:6]}-{value[6:8]}" if len(value) == 8 else value

app/backend/features/sentiment/engine.py

@@ -4,6 +4,8 @@ from copy import deepcopy
 from statistics import mean, median
 from typing import Any
 
+from backend.data.numbers import non_nan_number as _number
+
 
 COMPONENT_WEIGHTS = {
     "breadth": 20,
@@ -16,14 +18,6 @@ COMPONENT_WEIGHTS = {
 SENTIMENT_ENGINE_VERSION = 2
 
 
-def _number(value: Any, default: float = 0.0) -> float:
-    try:
-        number = float(value)
-        return number if number == number else default
-    except (TypeError, ValueError):
-        return default
-
-
 def _clamp(value: float, lower: float = 0.0, upper: float = 100.0) -> float:
     return min(upper, max(lower, value))
 

app/config/architecture-inventory.json

@@ -220,6 +220,16 @@
       "runtime_role": "index observation fallback"
     }
   ],
+  "numeric_normalization": [
+    {
+      "function": "finite_number",
+      "path": "backend/data/numbers.py"
+    },
+    {
+      "function": "non_nan_number",
+      "path": "backend/data/numbers.py"
+    }
+  ],
   "llm_entrypoints": [
     {
       "function": "stream_with_mentor",
@@ -279,13 +289,13 @@
     },
     {
       "path": "backend/features/screener/engine.py",
-      "bytes": 108552,
+      "bytes": 108394,
-      "lines": 2213
+      "lines": 2206
     },
     {
       "path": "backend/data/providers/tushare_client.py",
-      "bytes": 94329,
+      "bytes": 94171,
-      "lines": 2175
+      "lines": 2168
     },
     {
       "path": "frontend/app.js",
@@ -314,8 +324,8 @@
     },
     {
       "path": "backend/features/market/insights.py",
-      "bytes": 58150,
+      "bytes": 57998,
-      "lines": 1314
+      "lines": 1307
     },
     {
       "path": "frontend/pages/market/runtime.js",

app/tests/preservation_helpers.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import ast
 import hashlib
 import re
 from pathlib import Path
@@ -33,6 +34,41 @@ def sha256(path: Path) -> str:
     return hashlib.sha256(path.read_bytes()).hexdigest()
 
 
+def function_contract(path: Path, name: str) -> tuple[str, str]:
+    tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
+    function = next(
+        node for node in tree.body if isinstance(node, ast.FunctionDef) and node.name == name
+    )
+    body = ast.Module(body=function.body, type_ignores=[])
+    return (
+        ast.dump(function.args, include_attributes=False),
+        ast.dump(body, include_attributes=False),
+    )
+
+
+def module_contract(
+    path: Path,
+    *,
+    excluded_definitions: set[str] | None = None,
+    excluded_import_modules: set[str] | None = None,
+    exclude_imports: bool = False,
+) -> str:
+    excluded_definitions = excluded_definitions or set()
+    excluded_import_modules = excluded_import_modules or set()
+    tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
+    tree.body = [
+        node
+        for node in tree.body
+        if not (exclude_imports and isinstance(node, (ast.Import, ast.ImportFrom)))
+        and not (
+            isinstance(node, ast.ImportFrom)
+            and node.module in excluded_import_modules
+        )
+        and getattr(node, "name", None) not in excluded_definitions
+    ]
+    return ast.dump(tree, include_attributes=False)
+
+
 def reassembled_frontend_runtime() -> str:
     chunks: dict[tuple[int, int], str] = {}
     for path in FRONTEND_ROOT.rglob("*.js"):

app/tests/test_market_symbol_normalization.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+import unittest
+
+from backend.bootstrap.config import tushare_code
+from backend.features.market import charts
+
+
+class MarketSymbolNormalizationTests(unittest.TestCase):
+    def test_chart_and_market_services_share_one_suffix_converter(self) -> None:
+        self.assertIs(charts._stock_market_code, tushare_code)
+
+    def test_existing_exchange_mapping_is_preserved(self) -> None:
+        cases = {
+            "000001": "000001.SZ",
+            "600000": "600000.SH",
+            "430047": "430047.BJ",
+            "830799": "830799.BJ",
+        }
+        for code, expected in cases.items():
+            with self.subTest(code=code):
+                self.assertEqual(charts._stock_market_code(code), expected)
+
+
+if __name__ == "__main__":
+    unittest.main()

app/tests/test_numeric_normalization.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+import math
+import unittest
+
+from backend.data.numbers import finite_number, non_nan_number
+from backend.data.providers import tushare_client
+from backend.features.market import insights
+from backend.features.screener import engine as screener_engine
+from backend.features.sentiment import engine as sentiment_engine
+
+
+class NumericNormalizationTests(unittest.TestCase):
+    def test_consumers_use_their_declared_shared_policy(self) -> None:
+        self.assertIs(tushare_client._number, finite_number)
+        self.assertIs(screener_engine._number, finite_number)
+        self.assertIs(insights._number, non_nan_number)
+        self.assertIs(sentiment_engine._number, non_nan_number)
+
+    def test_finite_policy_preserves_existing_results(self) -> None:
+        self.assertEqual(finite_number("12.5"), 12.5)
+        self.assertEqual(finite_number(None), 0.0)
+        self.assertEqual(finite_number("invalid", 7.0), 7.0)
+        self.assertEqual(finite_number(math.nan, 7.0), 7.0)
+        self.assertEqual(finite_number(math.inf, 7.0), 7.0)
+        self.assertEqual(finite_number(-math.inf, 7.0), 7.0)
+
+    def test_non_nan_policy_keeps_infinity_but_rejects_nan(self) -> None:
+        self.assertEqual(non_nan_number("12.5"), 12.5)
+        self.assertEqual(non_nan_number(None), 0.0)
+        self.assertEqual(non_nan_number("invalid", 7.0), 7.0)
+        self.assertEqual(non_nan_number(math.nan, 7.0), 7.0)
+        self.assertEqual(non_nan_number(math.inf, 7.0), math.inf)
+        self.assertEqual(non_nan_number(-math.inf, 7.0), -math.inf)
+
+
+if __name__ == "__main__":
+    unittest.main()

app/tests/test_preservation_slice_market.py

@@ -9,13 +9,16 @@ import chart_data_provider
 import ifind_client
 import realtime_aggregator
 import tushare_client
+from backend.bootstrap import config as bootstrap_config
 from backend.data import realtime
+from backend.data.numbers import finite_number
 from backend.data.providers import ifind_client as canonical_ifind
 from backend.data.providers import tushare_client as canonical_tushare
 from backend.features.market import charts
 from tests.preservation_helpers import (
     assert_frontend_runtime_matches_audited_baseline,
     assert_moved_asset_matches,
+    function_contract,
 )
 
 
@@ -141,14 +144,32 @@ class MarketSliceSourceEquivalenceTests(unittest.TestCase):
         )
         for original, migrated in exact_moves:
             self.assertEqual(sha256(ORIGINAL_ROOT / original), sha256(APP_ROOT / migrated))
+        original_tushare = top_level_definitions(ORIGINAL_ROOT / "tushare_client.py")
+        original_tushare.pop("_number")
         self.assertEqual(
-            top_level_definitions(ORIGINAL_ROOT / "tushare_client.py"),
+            original_tushare,
             top_level_definitions(APP_ROOT / "backend/data/providers/tushare_client.py"),
         )
         self.assertEqual(
-            top_level_definitions(ORIGINAL_ROOT / "chart_data_provider.py"),
+            function_contract(ORIGINAL_ROOT / "tushare_client.py", "_number"),
+            function_contract(APP_ROOT / "backend/data/numbers.py", "finite_number"),
+        )
+        self.assertIs(canonical_tushare._number, finite_number)
+        original_charts = top_level_definitions(ORIGINAL_ROOT / "chart_data_provider.py")
+        original_charts.pop("_stock_market_code")
+        self.assertEqual(
+            original_charts,
             top_level_definitions(APP_ROOT / "backend/features/market/charts.py"),
         )
+        self.assertEqual(
+            function_contract(
+                ORIGINAL_ROOT / "chart_data_provider.py", "_stock_market_code"
+            ),
+            function_contract(
+                APP_ROOT / "backend/bootstrap/config.py", "tushare_code"
+            ),
+        )
+        self.assertIs(charts._stock_market_code, bootstrap_config.tushare_code)
 
     def test_relocated_frontend_preserves_original_market_runtime_and_styles(self) -> None:
         assert_frontend_runtime_matches_audited_baseline(self)

app/tests/test_preservation_slice_market_insights.py

@@ -6,11 +6,13 @@ import unittest
 from pathlib import Path
 
 import market_insights
+from backend.data.numbers import non_nan_number
 from backend.features.market import insights as canonical_insights
 from tests.preservation_helpers import (
     assert_frontend_runtime_matches_audited_baseline,
     assert_moved_asset_matches,
     assert_page_prefix_matches,
+    function_contract,
 )
 
 
@@ -106,6 +108,11 @@ class MarketInsightsSliceSourceEquivalenceTests(unittest.TestCase):
             MARKET_INSIGHT_METHODS,
         )
         self.assertIs(market_insights.MarketInsightsService, canonical_insights.MarketInsightsService)
+        self.assertEqual(
+            function_contract(ORIGINAL_ROOT / "market_insights.py", "_number"),
+            function_contract(APP_ROOT / "backend/data/numbers.py", "non_nan_number"),
+        )
+        self.assertIs(canonical_insights._number, non_nan_number)
 
     def test_dashboard_service_methods_are_exact_original_ast(self) -> None:
         original = ORIGINAL_ROOT / "server.py"

app/tests/test_preservation_slice_screener.py

@@ -9,12 +9,15 @@ import advanced_strategies
 import llm_strategy
 import screener
 import strategy_tracking
+from backend.data.numbers import finite_number
 from backend.features.screener import compiler, engine, strategies, tracking
 from backend.features.screener import service as screener_service
 from tests.preservation_helpers import (
     assert_frontend_runtime_matches_audited_baseline,
     assert_moved_asset_matches,
     assert_page_prefix_matches,
+    function_contract,
+    module_contract,
 )
 
 
@@ -91,14 +94,6 @@ def top_level_definition(path: Path, name: str) -> str:
     return ast.dump(node, include_attributes=False)
 
 
-def module_without_imports(path: Path) -> str:
-    tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
-    tree.body = [
-        node for node in tree.body if not isinstance(node, (ast.Import, ast.ImportFrom))
-    ]
-    return ast.dump(tree, include_attributes=False)
-
-
 def sha256(path: Path) -> str:
     return hashlib.sha256(path.read_bytes()).hexdigest()
 
@@ -154,11 +149,22 @@ class ScreenerSliceSourceEquivalenceTests(unittest.TestCase):
 
     def test_engine_and_tracking_logic_match_the_original(self) -> None:
         self.assertEqual(
-            module_without_imports(ORIGINAL_ROOT / "screener.py"),
+            module_contract(
-            module_without_imports(
+                ORIGINAL_ROOT / "screener.py",
-                APP_ROOT / "backend" / "features" / "screener" / "engine.py"
+                excluded_definitions={"_number"},
+                exclude_imports=True,
+            ),
+            module_contract(
+                APP_ROOT / "backend" / "features" / "screener" / "engine.py",
+                excluded_definitions={"_number"},
+                exclude_imports=True,
             ),
         )
+        self.assertEqual(
+            function_contract(ORIGINAL_ROOT / "screener.py", "_number"),
+            function_contract(APP_ROOT / "backend/data/numbers.py", "finite_number"),
+        )
+        self.assertIs(engine._number, finite_number)
         self.assertEqual(
             class_methods(
                 ORIGINAL_ROOT / "backend" / "features" / "screener" / "tracking.py",

app/tests/test_preservation_slice_sentiment_pools.py

@@ -6,11 +6,14 @@ import unittest
 from pathlib import Path
 
 import sentiment_engine
+from backend.data.numbers import non_nan_number
 from backend.features.sentiment import engine as canonical_engine
 from tests.preservation_helpers import (
     assert_frontend_runtime_matches_audited_baseline,
     assert_moved_asset_matches,
     assert_page_prefix_matches,
+    function_contract,
+    module_contract,
 )
 
 
@@ -94,10 +97,22 @@ class SentimentPoolSliceSourceEquivalenceTests(unittest.TestCase):
 
     def test_sentiment_engine_is_exact_original_with_legacy_alias(self) -> None:
         self.assertEqual(
-            sha256(ORIGINAL_ROOT / "sentiment_engine.py"),
+            module_contract(
-            sha256(APP_ROOT / "backend" / "features" / "sentiment" / "engine.py"),
+                ORIGINAL_ROOT / "sentiment_engine.py",
+                excluded_definitions={"_number"},
+            ),
+            module_contract(
+                APP_ROOT / "backend" / "features" / "sentiment" / "engine.py",
+                excluded_definitions={"_number"},
+                excluded_import_modules={"backend.data.numbers"},
+            ),
+        )
+        self.assertEqual(
+            function_contract(ORIGINAL_ROOT / "sentiment_engine.py", "_number"),
+            function_contract(APP_ROOT / "backend/data/numbers.py", "non_nan_number"),
         )
         self.assertIs(sentiment_engine, canonical_engine)
+        self.assertIs(canonical_engine._number, non_nan_number)
 
     def test_api_and_frontend_assets_are_unchanged(self) -> None:
         self.assertEqual(

app/tools/build_architecture_inventory.py

@@ -155,6 +155,10 @@ def build() -> dict[str, Any]:
             {"provider": "eastmoney", "path": "backend/data/realtime.py", "runtime_role": "isolated realtime observation"},
             {"provider": "tencent", "path": "backend/data/realtime.py", "runtime_role": "index observation fallback"},
         ],
+        "numeric_normalization": [
+            {"function": "finite_number", "path": "backend/data/numbers.py"},
+            {"function": "non_nan_number", "path": "backend/data/numbers.py"},
+        ],
         "llm_entrypoints": [
             {"function": "stream_with_mentor", "path": "backend/features/mentor/agent.py"},
             {"function": "interpret_heaven", "path": "backend/features/heaven/agent.py"},

docs/governance/code-reduction.md

@@ -20,6 +20,8 @@
 |---|---|---|---|---|
 | CR-01 | LLM供应商传输 | 问师、问天、复盘助手和策略编译各自构造HTTP请求、解析响应和读取错误 | 只保留`backend/llm/transport.py`一个网络出口 | 已完成 |
 | CR-02 | HTTP精确POST委托 | 27个端点重复使用“比较路径、调用无参数处理器、返回”三行分支 | 用公开/受保护两张显式映射统一委托，同时保留复杂路由的原控制流 | 已完成 |
+| CR-03 | 股票市场后缀转换 | Tushare业务与iFinD图表各保留一份完全相同的沪深京代码转换函数 | 图表复用`bootstrap/config.py::tushare_code`，只保留一份函数体 | 已完成 |
+| CR-04 | 数值归一化策略 | 四个业务模块分别保留两组完全相同的数值转换函数体 | 由`backend/data/numbers.py`集中拥有两种既有语义，消费者保留原局部别名 | 已完成 |
 
 ## CR-01验收口径
 
@@ -66,3 +68,54 @@
 
 本批基线为`xiaobai-reduction-01-llm-transport-20260801`；检查点为
 `xiaobai-reduction-02-http-dispatch-20260801`。
+
+## CR-03验收口径
+
+- 图表模块不再定义第二份市场后缀转换函数，仍保留原局部名称和两个调用点。
+- 深市、沪市、北交所的既有映射结果保持不变；不借本批修正或扩展代码规则。
+- 原图表文件除该函数外的所有顶层定义继续与原版AST逐项相等。
+- 原版`_stock_market_code`函数的参数和函数体必须与唯一共享实现AST相等，运行时别名必须指向
+  同一个函数对象。
+
+## CR-03结果
+
+- 删除`backend/features/market/charts.py`中第二份10行定义，以1行导入别名复用共享实现，生产代码
+  净减少9行；全仓后端只剩一份沪深京后缀转换函数体。
+- 未合并实时聚合、东方财富图表、iFinD和Tushare的HTTP传输；它们的缓存、错误、重试和降级语义
+  不同，仅有外形相似，证据不足以安全抽象。
+- 原有迁移期整文件相等断言被等价范围断言、共享函数AST断言和唯一对象断言替代，没有降低门禁。
+- 原版231项、候选317项、纯`app/`导出254项、45项Playwright通过；API/架构注册表、
+  24个JavaScript文件、Git空白检查和SQLite完整性检查通过。
+- 本批不修改图表请求、数据来源、缓存、时间范围、行情计算、前端、CSS、数据库或部署。
+
+本批基线为`xiaobai-reduction-02-http-dispatch-20260801`；检查点为
+`xiaobai-reduction-03-market-symbol-20260801`。
+
+## CR-04验收口径
+
+- 只合并参数、函数体和运行结果完全一致的数值转换函数，不借本批改变任何业务计算或异常默认值。
+- `finite_number`继续拒绝`NaN`与正负无穷；`non_nan_number`继续只拒绝`NaN`并保留正负无穷。
+- Tushare与智能选股必须复用有限数策略；市场洞察与情绪引擎必须复用非NaN策略，并继续暴露原局部
+  `_number`名称以保持兼容。
+- 实时行情和图表转换器的空值、默认值或参数签名语义不同，必须继续独立保留，不能因名称相同而合并。
+- 原版函数参数和函数体分别与共享实现AST相等；四个消费者的局部别名必须指向对应的唯一函数对象。
+
+## CR-04结果
+
+- 删除Tushare、智能选股、市场洞察和情绪引擎中的四份重复函数体，新建两种明确命名的共享策略；生产
+  代码净减少约12行，全仓AST扫描不再发现完全相同的函数定义。
+- 将可复用的函数及模块AST契约归入测试辅助层，原有迁移保持性测试改为“未改范围保持相等、被替换
+  函数与共享实现相等、运行时唯一对象”三重断言，没有降低门禁。
+- 实时行情`backend/data/realtime.py::_number`与图表`backend/features/market/charts.py::_number`
+  被明确保留；它们不是本批重复实现，也未改变行为。
+- 58项定向测试、41项保持性/治理测试、原版231项、候选320项、纯`app/`导出257项和45项
+  Playwright通过；24个JavaScript文件、API/架构注册表、Git空白检查和SQLite完整性检查通过。
+- 本批不修改前端、CSS、接口、数据来源、行情口径、选股条件、数据库、LLM、权限或部署。
+
+本批基线为`xiaobai-reduction-03-market-symbol-20260801`；检查点为
+`xiaobai-reduction-04-numeric-normalization-20260801`。
+
+## 人工验收记录
+
+- 2026-08-01：用户检查CR-02与CR-03运行结果，确认未发现明显异常。本记录仅表示本轮可见功能与
+  页面使用未发现明显回归，不替代后续批次各自的自动测试和人工抽查。