fix(api,codec): 修复 BUG-1 分时采样走错命令 + BUG-2 财务文件名纠正

BUG-1: A股 get_minutes(sampling=True) 原走 MacChartSamplingCmd(0x254D)
这是 EX 协议命令,7709 主机无响应(3×8s 超时≈24s)。
修复:A股采样由 MacTickChartCmd(0x122D) 分时数据派生,
EX 市场(hk)仍走 0x254D。4 个 A股 场景均<0.1s 返回 240 点。

BUG-2: tdxfin/gpcw.txt 索引声明 gpcwYYYYMMDD.zip,
但服务器实际只有 tdxfin/gpcwYYYYMMDD.dat(未压缩,~13MB),
.zip 请求返回 0-1 字节空壳。
修复:_fetch_financial_dat() 自动候选回退
tdxfin/*.zip → tdxfin/*.dat → 原始文件名,加 looks_like_gpcw_dat 校验。
实测 gpcw20260630.zip→5568 条,gpcw20260331.zip→5547 条。

新增 codec/financial.py: looks_like_gpcw_dat, extract_gpcw_dat(含 zip/未压缩双通道)。
同步更新 README/API_REFERENCE/docs/cli/cookbook/CHANGELOG 共 6 处文档。
tests: +18(总 182),ruff 无新增 findings,MkDocs strict 通过。
This commit is contained in:
openbot-coder committed 2026-09-21 20:47:48 +08:00
1 parent b78d0fabf5
commit 8951ec2678
10 files changed
+391 -39

No files matched your search

+140 -2
View File
@@ -6,14 +6,19 @@ from __future__ import annotations
import io
import struct
import unittest.mock as mock
import zipfile
from unittest import mock
import pytest
from pytdxdata.api import TdxData
from pytdxdata.codec.block import infer_block_category, parse_block_dat
from pytdxdata.codec.financial import parse_financial_dat, parse_financial_file_list
from pytdxdata.codec.financial import (
extract_gpcw_dat,
looks_like_gpcw_dat,
parse_financial_dat,
parse_financial_file_list,
)
from pytdxdata.codec.industry import parse_tdxhy_cfg
from pytdxdata.models import FinancialFileInfo, FinancialRecord, IndustryInfo, TdxBlock
@@ -317,3 +322,136 @@ async def test_api_get_financial_records_parsed_no_date_in_name():
new=mock.AsyncMock(return_value=zip_bytes)):
recs = await td.get_financial_records_parsed("gpcw.zip")
assert recs[0].report_date == 20260331
# --------------------------------------------------------------------------- #
# looks_like_gpcw_dat / extract_gpcw_dat(BUG-2 修复的判据层)
# --------------------------------------------------------------------------- #
def test_looks_like_gpcw_dat_accepts_real_dat():
assert looks_like_gpcw_dat(_valid_two_record_dat()) is True
def test_looks_like_gpcw_dat_rejects_short_shell():
"""服务器对不存在的文件名回的空壳(0~1 字节)必须判否。"""
assert looks_like_gpcw_dat(b"") is False
assert looks_like_gpcw_dat(b"\x00") is False
assert looks_like_gpcw_dat(b"abcd") is False
def test_looks_like_gpcw_dat_rejects_zero_header():
"""长度够但 header 全零(max_count=0 / report_size=0)也要判否。"""
assert looks_like_gpcw_dat(b"\x00" * 64) is False
def test_looks_like_gpcw_dat_rejects_report_size_not_multiple_of_4():
data = _make_dat_raw([(b"600000", 1, 31)], struct.pack("<2f", 1.0, 2.0),
report_size=6)
assert looks_like_gpcw_dat(data) is False
def test_looks_like_gpcw_dat_rejects_truncated_index():
"""header 声称的条目数超出实际长度 -> 判否。"""
data = _make_dat_raw([(b"600000", 1, 31)], struct.pack("<2f", 1.0, 2.0),
max_count=100)
assert looks_like_gpcw_dat(data) is False
def test_extract_gpcw_dat_from_uncompressed():
dat = _valid_two_record_dat()
assert extract_gpcw_dat(dat) == dat
def test_extract_gpcw_dat_from_zip():
dat = _valid_two_record_dat()
assert extract_gpcw_dat(_make_financial_zip(dat)) == dat
def test_extract_gpcw_dat_empty_and_garbage():
assert extract_gpcw_dat(b"") == b""
assert extract_gpcw_dat(b"\x00") == b""
assert extract_gpcw_dat(b"not a financial file") == b""
def test_extract_gpcw_dat_zip_without_dat_member():
assert extract_gpcw_dat(_make_financial_zip(b"x", inner_name="readme.txt")) == b""
def test_extract_gpcw_dat_zip_with_invalid_inner_dat():
"""zip 里虽有 .dat,但内容不是有效财报数据 -> 空。"""
assert extract_gpcw_dat(_make_financial_zip(b"\x00" * 4)) == b""
def test_extract_gpcw_dat_broken_zip():
"""以 PK 开头但不是合法 zip -> 空,不抛异常。"""
assert extract_gpcw_dat(b"PK\x03\x04broken-not-a-zip") == b""
# --------------------------------------------------------------------------- #
# TdxData._fetch_financial_dat 候选回退(BUG-2 回归)
# --------------------------------------------------------------------------- #
@pytest.mark.asyncio
async def test_fetch_financial_dat_falls_back_to_uncompressed_dat():
"""索引名 ``gpcw*.zip`` 取不到时,必须回退到服务器实际的 ``tdxfin/*.dat``。"""
td = _new_tdxdata()
dat = _valid_two_record_dat()
seen: list[str] = []
async def fake(name: str) -> bytes:
seen.append(name)
if name == "tdxfin/gpcw20260331.dat":
return dat
if name == "gpcw20260331.zip":
return b"\x00" # 裸名 -> MAC 路由 -> 1 字节空壳
return b"" # 带前缀的 .zip 不存在
with mock.patch.object(td, "get_file", new=fake):
got = await td._fetch_financial_dat("gpcw20260331.zip")
assert got == dat
assert seen == ["tdxfin/gpcw20260331.zip", "tdxfin/gpcw20260331.dat"]
@pytest.mark.asyncio
async def test_fetch_financial_dat_prefers_declared_zip_when_present():
"""服务器若恢复提供 .zip,应优先用索引声明的那个名字。"""
td = _new_tdxdata()
dat = _valid_two_record_dat()
seen: list[str] = []
async def fake(name: str) -> bytes:
seen.append(name)
return _make_financial_zip(dat)
with mock.patch.object(td, "get_file", new=fake):
got = await td._fetch_financial_dat("tdxfin/gpcw20260331.zip")
assert got == dat
assert seen == ["tdxfin/gpcw20260331.zip"]
@pytest.mark.asyncio
async def test_fetch_financial_dat_skips_raising_candidate():
"""某个候选取回时抛异常,不应中断,继续试后面的候选。"""
td = _new_tdxdata()
dat = _valid_two_record_dat()
async def fake(name: str) -> bytes:
if name.endswith(".zip"):
raise ConnectionError("模拟网络错误")
return dat
with mock.patch.object(td, "get_file", new=fake):
assert await td._fetch_financial_dat("gpcw20260331.zip") == dat
@pytest.mark.asyncio
async def test_fetch_financial_dat_all_candidates_fail_returns_empty():
td = _new_tdxdata()
async def fake(name: str) -> bytes:
return b""
with mock.patch.object(td, "get_file", new=fake):
assert await td._fetch_financial_dat("gpcw20260331.zip") == b""