lib-x17-fintech 2.1.3__py3-none-any.whl

xfintech/data/source/baostock/stock/tradedate/tradedate.py

@@ -0,0 +1,208 @@
+from __future__ import annotations
+
+from datetime import date, datetime
+from typing import Any, Dict, Optional
+
+import pandas as pd
+
+from xfintech.data.common.cache import Cache
+from xfintech.data.common.coolant import Coolant
+from xfintech.data.common.params import Params
+from xfintech.data.common.retry import Retry
+from xfintech.data.job import JobHouse
+from xfintech.data.source.baostock.job import BaostockJob
+from xfintech.data.source.baostock.session.session import Session
+from xfintech.data.source.baostock.stock.tradedate.constant import (
+    KEY,
+    NAME,
+    PAGINATE,
+    SOURCE,
+    TARGET,
+)
+
+
+@JobHouse.register(KEY, alias=KEY)
+class TradeDate(BaostockJob):
+    """
+    描述:
+    - 获取交易日历数据
+    - 包括交易所的交易日期和非交易日期信息
+    - 支持年份查询和日期范围查询
+    - API文档: http://www.baostock.com/mainContent?file=StockBasicInfoAPI.md
+    - SCALE: CrossSection
+    - TYPE: Static
+    - PAGINATE: 10000 rows / 100 pages
+
+    属性:
+    - name: str, 作业名称 'tradedate'。
+    - key: str, 作业键 '/baostock/tradedate'。
+    - session: Session, Baostock会话对象。
+    - source: TableInfo, 源表信息（BaoStock原始格式）。
+    - target: TableInfo, 目标表信息（xfintech格式）。
+    - params: Params, 查询参数。
+        - start_date: str, 可选, 开始日期（YYYY-MM-DD 或 YYYYMMDD）
+        - end_date: str, 可选, 结束日期（YYYY-MM-DD 或 YYYYMMDD）
+        - year: str | int, 可选, 年份（YYYY）
+    - coolant: Coolant, 请求冷却控制。
+    - paginate: Paginate, 分页控制（pagesize=10000, pagelimit=100）。
+    - retry: Retry, 重试策略。
+    - cache: Cache, 缓存管理。
+
+    方法:
+    - run(): 执行作业，返回交易日历DataFrame。
+    - _run(): 内部执行逻辑，处理日期参数并调用API。
+    - transform(data): 转换数据格式，将源格式转为目标格式。
+    - list_dates(): 返回所有日期列表。
+    - list_datecodes(): 返回所有日期代码列表。
+    - list_open_dates(): 返回交易日列表。
+    - list_open_datecodes(): 返回交易日代码列表。
+    - check(session, value): 检查指定日期是否为交易日。
+
+    例子:
+    ```python
+        from xfintech.data.source.baostock.session import Session
+        from xfintech.data.source.baostock.stock.tradedate import TradeDate
+
+        session = Session()
+
+        # 获取2026年交易日历
+        job = TradeDate(session=session, params={"year": "2026"})
+        df = job.run()
+
+        # 获取指定日期范围
+        job = TradeDate(
+            session=session,
+            params={
+                "start_date": "20260101",
+                "end_date": "20260131"
+            }
+        )
+        df = job.run()
+
+        # 检查是否为交易日
+        is_trading = TradeDate.check(session, "2026-01-10")
+    ```
+    """
+
+    @classmethod
+    def check(
+        cls,
+        session: Session,
+        value: Optional[datetime | date | str] = None,
+    ) -> bool:
+        if isinstance(value, datetime):
+            value = value.date()
+        elif isinstance(value, date):
+            pass
+        elif isinstance(value, str):
+            if "-" in value:
+                value = datetime.strptime(value, "%Y-%m-%d").date()
+            else:
+                value = datetime.strptime(value, "%Y%m%d").date()
+        else:
+            value = datetime.now().date()
+
+        datecode = value.strftime("%Y-%m-%d")
+        job = cls(
+            session=session,
+            params={
+                "start_date": datecode,
+                "end_date": datecode,
+            },
+        )
+        result = job.run()
+        return not result.empty
+
+    def __init__(
+        self,
+        session: Session,
+        params: Optional[Params | Dict[str, Any]] = None,
+        coolant: Optional[Coolant | Dict[str, Any]] = None,
+        retry: Optional[Retry | Dict[str, Any]] = None,
+        cache: Optional[Cache | Dict[str, Any] | bool] = None,
+    ) -> None:
+        super().__init__(
+            session=session,
+            name=NAME,
+            key=KEY,
+            source=SOURCE,
+            target=TARGET,
+            params=params,
+            paginate=PAGINATE,
+            coolant=coolant,
+            retry=retry,
+            cache=cache,
+        )
+
+    def _run(self) -> pd.DataFrame:
+        cached = self._load_cache()
+        if cached is not None:
+            return cached
+
+        payload = self.params.to_dict()
+        payload = self._parse_date_params(
+            payload,
+            keys=["start_date", "end_date"],
+        )
+        payload = self._parse_year_params(
+            payload,
+            key="year",
+        )
+        data = self._fetchall(
+            api=self.connection.query_trade_dates,
+            **payload,
+        )
+        result = self.transform(data)
+        self._save_cache(result)
+        return result
+
+    # Transform logic
+    def transform(
+        self,
+        data: pd.DataFrame,
+    ) -> pd.DataFrame:
+        cols = self.target.list_column_names()
+        if data is None or data.empty:
+            return pd.DataFrame(columns=cols)
+
+        out = data.copy()
+        out["dt"] = pd.to_datetime(
+            out["calendar_date"],
+            format="%Y-%m-%d",
+            errors="coerce",
+        )
+        out["date"] = out["dt"].dt.strftime("%Y-%m-%d")
+        out["datecode"] = out["dt"].dt.strftime("%Y%m%d")
+        out["exchange"] = "ALL"
+        out["previous"] = out["dt"].shift(1).dt.strftime("%Y-%m-%d")
+        out["is_open"] = out["is_trading_day"].astype(int).eq(1)
+        out["year"] = out["dt"].dt.year.fillna(0).astype(int)
+        out["month"] = out["dt"].dt.month.fillna(0).astype(int)
+        out["day"] = out["dt"].dt.day.fillna(0).astype(int)
+        out["week"] = out["dt"].dt.isocalendar().week.fillna(0).astype(int)
+        out["weekday"] = out["dt"].dt.day_name().fillna("").str[:3]
+        out["quarter"] = out["dt"].dt.quarter.fillna(0).astype(int)
+
+        # Clean up temporary columns
+        out.drop(columns=["dt"], inplace=True)
+        out = out[cols].drop_duplicates()
+        out = out.sort_values(by=["datecode"])
+        out = out.reset_index(drop=True)
+        self.markpoint("transform[OK]")
+        return out
+
+    def list_dates(self) -> list[str]:
+        df = self.run()
+        return sorted(df["date"].unique().tolist())
+
+    def list_datecodes(self) -> list[str]:
+        df = self.run()
+        return sorted(df["datecode"].unique().tolist())
+
+    def list_open_dates(self) -> list[str]:
+        df = self.run()
+        return sorted(df.loc[df["is_open"], "date"].unique().tolist())
+
+    def list_open_datecodes(self) -> list[str]:
+        df = self.run()
+        return sorted(df.loc[df["is_open"], "datecode"].unique().tolist())

xfintech/data/source/baostock/stock/zz500stock/__init__.py

@@ -0,0 +1,3 @@
+from .zz500stock import ZZ500Stock
+
+__all__ = ["ZZ500Stock"]

xfintech/data/source/baostock/stock/zz500stock/constant.py

@@ -0,0 +1,55 @@
+"""
+Constants for ZZ500Stock module.
+
+This module defines the source and target schemas for the Baostock ZZ500 constituent stocks data.
+"""
+
+from __future__ import annotations
+
+from xfintech.data.common.paginate import Paginate
+from xfintech.fabric.column.info import ColumnInfo
+from xfintech.fabric.column.kind import ColumnKind
+from xfintech.fabric.table.info import TableInfo
+
+PROVIDER = "baostock"
+SOURCE_NAME = "query_zz500_stocks"
+URL = "http://www.baostock.com/mainContent?file=zz500Stock.md"
+ARGS = {}
+
+# Exported constants
+NAME = "zz500stock"
+KEY = "/baostock/zz500stock"
+PAGINATE = Paginate(
+    pagesize=10000,
+    pagelimit=100,
+)
+SOURCE = TableInfo(
+    desc="中证500成分股（BaoStock格式）",
+    meta={
+        "provider": PROVIDER,
+        "source": SOURCE_NAME,
+        "url": URL,
+        "args": ARGS,
+        "type": "static",
+        "scale": "crosssection",
+    },
+    columns=[
+        ColumnInfo(name="updateDate", kind=ColumnKind.STRING, desc="更新日期"),
+        ColumnInfo(name="code", kind=ColumnKind.STRING, desc="证券代码"),
+        ColumnInfo(name="code_name", kind=ColumnKind.STRING, desc="证券名称"),
+    ],
+)
+TARGET = TableInfo(
+    desc="中证500成分股（xfintech格式）",
+    meta={
+        "key": KEY,
+        "name": NAME,
+        "type": "static",
+        "scale": "crosssection",
+    },
+    columns=[
+        ColumnInfo(name="update_date", kind=ColumnKind.STRING, desc="更新日期"),
+        ColumnInfo(name="code", kind=ColumnKind.STRING, desc="证券代码"),
+        ColumnInfo(name="name", kind=ColumnKind.STRING, desc="证券名称"),
+    ],
+)

xfintech/data/source/baostock/stock/zz500stock/tests/__init__.py

@@ -0,0 +1 @@
+"""Tests for zz500stock module."""

xfintech/data/source/baostock/stock/zz500stock/tests/test_class_zz500stock_all.py

@@ -0,0 +1,421 @@
+"""
+Comprehensive tests for ZZ500Stock class.
+"""
+
+from unittest.mock import MagicMock, patch
+
+import pandas as pd
+import pytest
+
+from xfintech.data.common.cache import Cache
+from xfintech.data.common.coolant import Coolant
+from xfintech.data.common.retry import Retry
+from xfintech.data.source.baostock.session.session import Session
+from xfintech.data.source.baostock.stock.zz500stock.constant import (
+    KEY,
+    NAME,
+    SOURCE,
+    TARGET,
+)
+from xfintech.data.source.baostock.stock.zz500stock.zz500stock import ZZ500Stock
+
+# ============================================================================
+# Fixtures
+# ============================================================================
+
+
+@pytest.fixture
+def mock_session():
+    """Create a mock Baostock session"""
+    session = MagicMock(spec=Session)
+    session._credential = None
+    session.id = "test1234"
+    session.mode = "direct"
+    session.relay_url = None
+    session.relay_secret = None
+    session.connected = True
+
+    # Mock the connection object
+    mock_connection = MagicMock()
+    mock_connection.query_zz500_stocks = MagicMock()
+    session.connection = mock_connection
+
+    return session
+
+
+@pytest.fixture
+def sample_source_data():
+    """Create sample source data in Baostock format"""
+    return pd.DataFrame(
+        {
+            "updateDate": ["2018-11-26"] * 15,
+            "code": [
+                "sh.600004",
+                "sh.600006",
+                "sh.600007",
+                "sh.600011",
+                "sh.600012",
+                "sh.600017",
+                "sh.600020",
+                "sh.600021",
+                "sh.600022",
+                "sh.600026",
+                "sz.000004",
+                "sz.000005",
+                "sz.000006",
+                "sz.000007",
+                "sz.000008",
+            ],
+            "code_name": [
+                "白云机场",
+                "东风汽车",
+                "中国国贸",
+                "华能国际",
+                "皖通高速",
+                "日照港",
+                "中原高速",
+                "上海电力",
+                "山东钢铁",
+                "中远海能",
+                "国华网安",
+                "ST星源",
+                "深振业A",
+                "全新好",
+                "神州高铁",
+            ],
+        }
+    )
+
+
+# ============================================================================
+# Initialization Tests
+# ============================================================================
+
+
+def test_zz500stock_initialization_basic(mock_session):
+    """Test basic initialization"""
+    job = ZZ500Stock(session=mock_session)
+
+    assert job.name == NAME
+    assert job.key == KEY
+    assert job.source == SOURCE
+    assert job.target == TARGET
+
+
+def test_zz500stock_initialization_with_params(mock_session):
+    """Test initialization with params (not used for this API)"""
+    params = {}
+    job = ZZ500Stock(session=mock_session, params=params)
+
+    # No specific params needed for ZZ500 API
+    assert job.params is not None
+
+
+def test_zz500stock_initialization_with_all_components(mock_session):
+    """Test initialization with all components"""
+    coolant = Coolant(interval=0.2)
+    retry = Retry(retry=3)
+    cache = Cache(path="/tmp/test_cache")
+
+    job = ZZ500Stock(
+        session=mock_session,
+        coolant=coolant,
+        retry=retry,
+        cache=cache,
+    )
+
+    assert job.coolant.interval == 0.2
+    assert job.retry.retry == 3
+    assert job.cache is not None
+    assert isinstance(job.cache, Cache)
+
+
+def test_zz500stock_name_and_key():
+    """Test name and key constants"""
+    assert NAME == "zz500stock"
+    assert KEY == "/baostock/zz500stock"
+
+
+def test_zz500stock_source_schema():
+    """Test source schema has all required columns"""
+    assert SOURCE is not None
+    assert "中证500成分股" in SOURCE.desc
+
+    column_names = SOURCE.columns
+    assert "updatedate" in column_names
+    assert "code" in column_names
+    assert "code_name" in column_names
+
+
+def test_zz500stock_target_schema():
+    """Test target schema has all required columns"""
+    assert TARGET is not None
+    assert "中证500成分股" in TARGET.desc
+
+    column_names = TARGET.columns
+    assert "update_date" in column_names
+    assert "code" in column_names
+    assert "name" in column_names
+
+
+# ============================================================================
+# Transform Tests
+# ============================================================================
+
+
+def test_zz500stock_transform_basic(mock_session, sample_source_data):
+    """Test basic data transformation"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    assert len(result) == 15
+    assert "update_date" in result.columns
+    assert "code" in result.columns
+    assert "name" in result.columns
+    assert result.iloc[0]["code"] == "sh.600004"
+    assert result.iloc[0]["name"] == "白云机场"
+
+
+def test_zz500stock_transform_field_types(mock_session, sample_source_data):
+    """Test field type conversions"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    # Check string fields
+    assert isinstance(result.iloc[0]["update_date"], str)
+    assert isinstance(result.iloc[0]["code"], str)
+    assert isinstance(result.iloc[0]["name"], str)
+
+
+def test_zz500stock_transform_field_mapping(mock_session, sample_source_data):
+    """Test field name mappings"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    # Verify field mappings
+    row = result[result["code"] == "sh.600004"].iloc[0]
+    assert row["update_date"] == "2018-11-26"  # from updateDate
+    assert row["name"] == "白云机场"  # from code_name
+    assert row["code"] == "sh.600004"
+
+
+def test_zz500stock_transform_empty_data(mock_session):
+    """Test transform with empty data"""
+    job = ZZ500Stock(session=mock_session)
+
+    # Test with None
+    result = job.transform(None)
+    assert result.empty
+    assert len(result.columns) == len(TARGET.columns)
+
+    # Test with empty DataFrame
+    empty_df = pd.DataFrame()
+    result = job.transform(empty_df)
+    assert result.empty
+    assert len(result.columns) == len(TARGET.columns)
+
+
+def test_zz500stock_transform_duplicate_removal(mock_session):
+    """Test that duplicates are removed"""
+    data = pd.DataFrame(
+        {
+            "updateDate": ["2018-11-26", "2018-11-26", "2018-11-26"],
+            "code": ["sh.600004", "sh.600004", "sh.600006"],
+            "code_name": ["白云机场", "白云机场", "东风汽车"],
+        }
+    )
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(data)
+
+    assert len(result) == 2  # Duplicates removed
+
+
+def test_zz500stock_transform_sorting(mock_session):
+    """Test that results are sorted by code"""
+    data = pd.DataFrame(
+        {
+            "updateDate": ["2018-11-26", "2018-11-26", "2018-11-26"],
+            "code": ["sz.000004", "sh.600004", "sh.600006"],
+            "code_name": ["国华网安", "白云机场", "东风汽车"],
+        }
+    )
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(data)
+
+    # Should be sorted by code
+    assert result.iloc[0]["code"] == "sh.600004"
+    assert result.iloc[1]["code"] == "sh.600006"
+    assert result.iloc[2]["code"] == "sz.000004"
+
+
+def test_zz500stock_transform_mixed_exchanges(mock_session, sample_source_data):
+    """Test transform with stocks from both Shanghai and Shenzhen exchanges"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    # Should have both sh. and sz. codes
+    sh_codes = [code for code in result["code"] if code.startswith("sh.")]
+    sz_codes = [code for code in result["code"] if code.startswith("sz.")]
+
+    assert len(sh_codes) > 0
+    assert len(sz_codes) > 0
+
+
+# ============================================================================
+# Run Tests
+# ============================================================================
+
+
+def test_zz500stock_run_basic(mock_session, sample_source_data):
+    """Test basic run functionality"""
+    job = ZZ500Stock(session=mock_session)
+
+    # Mock _fetchall to return sample data
+    with patch.object(job, "_fetchall", return_value=sample_source_data):
+        with patch.object(job, "_load_cache", return_value=None):
+            with patch.object(job, "_save_cache"):
+                result = job._run()
+
+                assert isinstance(result, pd.DataFrame)
+                assert len(result) == 15
+                assert "update_date" in result.columns
+                assert "code" in result.columns
+                assert "name" in result.columns
+
+
+def test_zz500stock_run_calls_api(mock_session, sample_source_data):
+    """Test that run calls the correct API"""
+    job = ZZ500Stock(session=mock_session)
+
+    with patch.object(job, "_fetchall", return_value=sample_source_data) as mock_fetchall:
+        with patch.object(job, "_load_cache", return_value=None):
+            with patch.object(job, "_save_cache"):
+                job._run()
+
+                # Verify API was called
+                mock_fetchall.assert_called_once()
+                call_kwargs = mock_fetchall.call_args[1]
+                assert call_kwargs["api"] == job.connection.query_zz500_stocks
+
+
+def test_zz500stock_run_with_cache(mock_session, sample_source_data):
+    """Test that cache is used when available"""
+    job = ZZ500Stock(session=mock_session)
+    cached_data = sample_source_data.copy()
+
+    with patch.object(job, "_load_cache", return_value=cached_data):
+        with patch.object(job, "_fetchall") as mock_fetchall:
+            result = job._run()
+
+            # Should return cached data without calling API
+            mock_fetchall.assert_not_called()
+            assert len(result) == 15
+
+
+# ============================================================================
+# List Methods Tests
+# ============================================================================
+
+
+def test_zz500stock_list_codes(mock_session, sample_source_data):
+    """Test list_codes method"""
+    job = ZZ500Stock(session=mock_session)
+
+    with patch.object(job, "run", return_value=job.transform(sample_source_data)):
+        codes = job.list_codes()
+
+        assert isinstance(codes, list)
+        assert len(codes) == 15
+        assert "sh.600004" in codes
+        assert "sz.000008" in codes
+        # Should be sorted
+        assert codes == sorted(codes)
+
+
+def test_zz500stock_list_names(mock_session, sample_source_data):
+    """Test list_names method"""
+    job = ZZ500Stock(session=mock_session)
+
+    with patch.object(job, "run", return_value=job.transform(sample_source_data)):
+        names = job.list_names()
+
+        assert isinstance(names, list)
+        assert len(names) == 15
+        assert "白云机场" in names
+        assert "神州高铁" in names
+        # Should be sorted
+        assert names == sorted(names)
+
+
+def test_zz500stock_list_codes_with_duplicates(mock_session):
+    """Test list_codes with duplicate codes"""
+    data = pd.DataFrame(
+        {
+            "updateDate": ["2018-11-26", "2018-11-26", "2018-11-26"],
+            "code": ["sh.600004", "sh.600004", "sh.600006"],
+            "code_name": ["白云机场", "白云机场", "东风汽车"],
+        }
+    )
+    job = ZZ500Stock(session=mock_session)
+    transformed = job.transform(data)
+
+    with patch.object(job, "run", return_value=transformed):
+        codes = job.list_codes()
+
+        # Should return unique codes only
+        assert len(codes) == 2
+        assert "sh.600004" in codes
+        assert "sh.600006" in codes
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+
+def test_zz500stock_full_workflow(mock_session, sample_source_data):
+    """Test full workflow from initialization to result"""
+    job = ZZ500Stock(session=mock_session)
+
+    with patch.object(job, "_fetchall", return_value=sample_source_data):
+        with patch.object(job, "_load_cache", return_value=None):
+            with patch.object(job, "_save_cache"):
+                result = job._run()
+
+                # Verify result structure
+                assert isinstance(result, pd.DataFrame)
+                assert len(result) == 15
+                assert "update_date" in result.columns
+                assert "code" in result.columns
+                assert "name" in result.columns
+
+                # Verify data types
+                assert isinstance(result.iloc[0]["update_date"], str)
+                assert isinstance(result.iloc[0]["code"], str)
+                assert isinstance(result.iloc[0]["name"], str)
+
+                # Verify sorting
+                codes = result["code"].tolist()
+                assert codes == sorted(codes)
+
+
+def test_zz500stock_same_update_date(mock_session, sample_source_data):
+    """Test that all stocks have the same update date"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    # All stocks should have the same update date
+    unique_dates = result["update_date"].unique()
+    assert len(unique_dates) == 1
+    assert unique_dates[0] == "2018-11-26"
+
+
+def test_zz500stock_code_format(mock_session, sample_source_data):
+    """Test that codes follow sh./sz.XXXXXX format"""
+    job = ZZ500Stock(session=mock_session)
+    result = job.transform(sample_source_data)
+
+    # All codes should start with "sh." or "sz."
+    for code in result["code"]:
+        assert code.startswith("sh.") or code.startswith("sz.")
+        assert len(code) == 9  # sh./sz. + 6 digits