summaryrefslogtreecommitdiff
path: root/worker
diff options
context:
space:
mode:
authorSomhairle H. Marisol <[email protected]>2026-09-18 08:26:18 +0800
committerSomhairle H. Marisol <[email protected]>2026-09-18 08:26:18 +0800
commit95215e84e045602db2370586f6089a7f9f91b33b (patch)
tree5119907dea5918d6eb26520e6dceed63b8030ad6 /worker
parent5c0ba37eda80d39e6ceca59bb1d5f4942f858995 (diff)
downloadstrategy-lab-95215e84e045602db2370586f6089a7f9f91b33b.tar.gz
fix(data): ETF 身份契约与挂载权限修复(159399 QA 回归)
[问题原因] 前端手动录入表单保存的 market 字段是 SH/SZ/BJ 原文,但 worker 的 split_identity 只接受 market:"cn" 并按代码前缀推交易所,导致 market:"SZ" 的 159399 在发起任何网络请求前就报 unsupported_market。 同时 server 为非 root 容器(uid 65534)准备挂载时,完整文件挂载从不 被 chmod,且所有 chmod 失败都被静默吞掉,worker 容器读数据集可能 Permission denied 且不易定位。 [问题根因] 身份契约在 server 持久化层与 worker 适配层不一致;挂载权限处理是 best-effort 静默吞错,缺少最小作用域约束。 [修复方案] worker/data.py: market 原样映射 IDENTITY_EXCHANGES(SH/SZ/BJ), "cn" 保持代码前缀推断(SH=3/6/9 开头,否则 SZ),未知市场仍显式拒绝 绝不猜测;sina 数据源的警告文案改为只陈述可证实事实(无日期参数、 不除权、成交量单位为股且不换算),删除与其它 provider 的 100x 换算 断言。server/src/worker.rs: prepare_mounts 严格化——独立文件挂载仅在 "只读 + /data/ 前缀"范围内 chmod 0644,拒绝符号链接,目录挂载保持 0755/0777,所有 chmod 失败作为错误返回而非吞掉。tests/worker/ test_data.py 新增身份契约用例:SZ/SH 原文、cn 推断不变、SZ 直达 sina provider 的端到端 fetch。 [影响范围] worker 数据获取链路与 server 任务编排;server/target/release 二进制 已含本改动(2026-09-17 构建);pytest 数据模块全绿。
Diffstat (limited to 'worker')
-rw-r--r--worker/data.py30
1 files changed, 19 insertions, 11 deletions
diff --git a/worker/data.py b/worker/data.py
index 841a1eb..13f8808 100644
--- a/worker/data.py
+++ b/worker/data.py
@@ -66,13 +66,20 @@ def split_identity(instrument: dict) -> tuple[str, str]:
raise DataError("bad_identity", f"unknown exchange prefix: {exch}")
else:
code = symbol
- market = instrument.get("market", "cn")
- if market != "cn":
- raise DataError("unsupported_market", f"market not supported by this adapter: {market}")
- if len(code) == 6 and code[0] in "369":
- exch = "SH"
+ market = str(instrument.get("market", "cn")).strip() or "cn"
+ # The server persists the user-facing market field verbatim (SH/SZ/BJ
+ # from the manual-entry form); "cn" (search-sourced items, any case)
+ # keeps the original code-prefix inference. Unknown markets must still
+ # be rejected — never guessed.
+ if market.upper() in IDENTITY_EXCHANGES:
+ exch = market.upper()
+ elif market.lower() == "cn":
+ if len(code) == 6 and code[0] in "369":
+ exch = "SH"
+ else:
+ exch = "SZ"
else:
- exch = "SZ"
+ raise DataError("unsupported_market", f"market not supported by this adapter: {market}")
if not code.isdigit() or len(code) != 6:
raise DataError("bad_identity", "A-share code must be a 6-digit number")
return exch, code
@@ -157,11 +164,12 @@ def _fetch_sina(instrument: dict, start: str, end: str,
# requested window (ISO strings compare lexicographically like dates)
df = df[(df["date"] >= start) & (df["date"] <= end)].reset_index(drop=True)
df.attrs["source_warnings"] = [
- "sina returns the full trading history without date parameters; sliced "
- "locally to the requested range; data is unadjusted (no adjust parameter)",
- "sina volume unit is 股 (shares); verified to be 100x the 手 (lots) "
- "convention used by lot-based providers on the same session "
- "(2026-09-17 evidence, docs/recovery-01-plan.md)",
+ "sina fund_etf_hist_sina has no date-range parameter: the provider "
+ "returned its available history and it was sliced locally to the "
+ "requested range (actual coverage differences are reported separately)",
+ "sina ETF klines are unadjusted: the interface has no adjust parameter",
+ "sina fund_etf_hist_sina 成交量单位为股;数值按 provider 原样保留,未做换算或取整。"
+ "与其他行情接口对比时,请先核对各 provider 自己公布的口径,不要按惯例直接换算",
]
return FetchResult(df, endpoint, params, raw, "sina")