kabukit 0.3.0__tar.gz → 0.3.1__tar.gz

{kabukit-0.3.0 → kabukit-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: kabukit
-Version: 0.3.0
+Version: 0.3.1
 Summary: A Python toolkit for Japanese financial market data, supporting J-Quants and EDINET APIs.
 Author: daizutabi
 Author-email: daizutabi <daizutabi@gmail.com>

{kabukit-0.3.0 → kabukit-0.3.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "kabukit"
-version = "0.3.0"
+version = "0.3.1"
 description = "A Python toolkit for Japanese financial market data, supporting J-Quants and EDINET APIs."
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -58,10 +58,14 @@ addopts = [
   "--cov=kabukit",
   "--cov-report=lcov:lcov.info",
   "--doctest-modules",
-  "-m not integration",
+  "-m",
+  "not integration and not validation",
+]
+testpaths = ["tests/unit", "tests/integration", "tests/validation"]
+markers = [
+  "integration: marks tests as integration tests",
+  "validation: marks tests as data validation tests",
 ]
-testpaths = ["tests/unit", "tests/integration"]
-markers = ["integration: marks tests as integration tests"]
 
 [tool.coverage.report]
 exclude_lines = ["no cov", "raise NotImplementedError", "if TYPE_CHECKING:"]

kabukit-0.3.1/src/kabukit/__init__.py

@@ -0,0 +1,17 @@
+from .core.info import Info
+from .core.list import List
+from .core.prices import Prices
+from .core.reports import Reports
+from .core.statements import Statements
+from .edinet.client import EdinetClient
+from .jquants.client import JQuantsClient
+
+__all__ = [
+    "EdinetClient",
+    "Info",
+    "JQuantsClient",
+    "List",
+    "Prices",
+    "Reports",
+    "Statements",
+]

{kabukit-0.3.0 → kabukit-0.3.1}/src/kabukit/cli/get.py

@@ -1,11 +1,14 @@
 from __future__ import annotations
 
-from typing import Annotated, Any
+from typing import TYPE_CHECKING, Annotated, Any
 
 import typer
 from async_typer import AsyncTyper  # pyright: ignore[reportMissingTypeStubs]
 from typer import Argument
 
+if TYPE_CHECKING:
+    from kabukit.core.base import Base
+
 app = AsyncTyper(
     add_completion=False,
     help="J-Quantsからデータを取得します。",
@@ -36,7 +39,7 @@ async def info(code: Code = None) -> None:
 async def _fetch(
     code: str | None,
     target: str,
-    writer_cls: type,
+    cls: type[Base],
     fetch_func_name: str,
     message: str,
     **kwargs: Any,
@@ -56,7 +59,7 @@ async def _fetch(
 
     df = await fetch_all(target, progress=tqdm.asyncio.tqdm, **kwargs)
     typer.echo(df)
-    path = writer_cls(df).write()
+    path = cls(df).write()
     typer.echo(f"全銘柄の{message}を '{path}' に保存しました。")
 
 
@@ -68,7 +71,7 @@ async def statements(code: Code = None) -> None:
     await _fetch(
         code=code,
         target="statements",
-        writer_cls=Statements,
+        cls=Statements,
         fetch_func_name="get_statements",
         message="財務情報",
     )
@@ -82,16 +85,55 @@ async def prices(code: Code = None) -> None:
     await _fetch(
         code=code,
         target="prices",
-        writer_cls=Prices,
+        cls=Prices,
         fetch_func_name="get_prices",
         message="株価情報",
         max_concurrency=8,
     )
 
 
+@app.async_command(name="list")  # pyright: ignore[reportUnknownMemberType]
+async def list_() -> None:
+    """報告書一覧を取得します。"""
+    import tqdm.asyncio
+
+    from kabukit.core.list import List
+    from kabukit.edinet.concurrent import fetch_list
+
+    df = await fetch_list(years=10, progress=tqdm.asyncio.tqdm)
+    typer.echo(df)
+    path = List(df).write()
+    typer.echo(f"報告書一覧を '{path}' に保存しました。")
+
+
+@app.async_command()  # pyright: ignore[reportUnknownMemberType]
+async def reports() -> None:
+    """報告書を取得します。"""
+    import polars as pl
+    import tqdm.asyncio
+
+    from kabukit.core.list import List
+    from kabukit.core.reports import Reports
+    from kabukit.edinet.concurrent import fetch_csv
+
+    try:
+        df = List.read().data
+    except FileNotFoundError:
+        await list_()
+        df = List.read().data
+
+    lst = df.filter(pl.col("csvFlag"), pl.col("secCode").is_not_null())
+    doc_ids = lst["docID"].unique()
+
+    df = await fetch_csv(doc_ids, limit=1000, progress=tqdm.asyncio.tqdm)
+    typer.echo(df)
+    path = Reports(df).write()
+    typer.echo(f"報告書を '{path}' に保存しました。")
+
+
 @app.async_command(name="all")  # pyright: ignore[reportUnknownMemberType]
 async def all_(code: Code = None) -> None:
-    """上場銘柄一覧、財務情報、株価を連続して取得します。"""
+    """上場銘柄一覧、財務情報、株価、報告書を連続して取得します。"""
     typer.echo("上場銘柄一覧を取得します。")
     await info(code)
 
@@ -102,3 +144,11 @@ async def all_(code: Code = None) -> None:
     typer.echo("---")
     typer.echo("株価を取得します。")
     await prices(code)
+
+    if code is None:
+        typer.echo("---")
+        typer.echo("報告書一覧を取得します。")
+        await list_()
+        typer.echo("---")
+        typer.echo("報告書を取得します。")
+        await reports()

kabukit-0.3.1/src/kabukit/core/list.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+class List(Base):
+    pass

kabukit-0.3.1/src/kabukit/core/reports.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+class Reports(Base):
+    pass

kabukit-0.3.1/src/kabukit/edinet/__init__.py

@@ -0,0 +1,3 @@
+from .concurrent import fetch, fetch_csv, fetch_list
+
+__all__ = ["fetch", "fetch_csv", "fetch_list"]

{kabukit-0.3.0 → kabukit-0.3.1}/src/kabukit/edinet/client.py

@@ -6,14 +6,13 @@ import zipfile
 from enum import StrEnum
 from typing import TYPE_CHECKING
 
-import polars as pl
 from polars import DataFrame
 
 from kabukit.core.client import Client
 from kabukit.utils.config import load_dotenv
 from kabukit.utils.params import get_params
 
-from .doc import clean_csv, clean_list
+from .doc import clean_csv, clean_list, read_csv
 
 if TYPE_CHECKING:
     import datetime
@@ -103,11 +102,8 @@ class EdinetClient(Client):
             for info in zf.infolist():
                 if info.filename.endswith(".csv"):
                     with zf.open(info) as f:
-                        return pl.read_csv(
-                            f.read(),
-                            separator="\t",
-                            encoding="utf-16-le",
-                        ).pipe(clean_csv, doc_id)
+                        df = read_csv(f.read())
+                        return clean_csv(df, doc_id)
 
         msg = "CSV is not available."
         raise ValueError(msg)

{kabukit-0.3.0 → kabukit-0.3.1}/src/kabukit/edinet/concurrent.py

@@ -83,13 +83,14 @@ async def fetch_list(
     if limit is not None:
         dates = dates[:limit]
 
-    return await fetch(
+    df = await fetch(
         "list",
         dates,
         max_concurrency=max_concurrency,
         progress=progress,
         callback=callback,
     )
+    return df.sort("Date")
 
 
 async def fetch_csv(
@@ -121,10 +122,11 @@ async def fetch_csv(
     if limit is not None:
         doc_ids = doc_ids[:limit]
 
-    return await fetch(
+    df = await fetch(
         "csv",
         doc_ids,
         max_concurrency=max_concurrency,
         progress=progress,
         callback=callback,
     )
+    return df.sort("docID")

kabukit-0.3.1/src/kabukit/edinet/doc.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+
+import datetime
+from typing import TYPE_CHECKING
+
+import polars as pl
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+def clean_list(df: DataFrame, date: str | datetime.date) -> DataFrame:
+    if isinstance(date, str):
+        date = datetime.datetime.strptime(date, "%Y-%m-%d").date()  # noqa: DTZ007
+
+    null_columns = [c for c in df.columns if df[c].dtype == pl.Null]
+
+    return (
+        df.with_columns(
+            pl.col(null_columns).cast(pl.String),
+        )
+        .with_columns(
+            pl.lit(date).alias("Date"),
+            pl.col("^.+DateTime$").str.to_datetime("%Y-%m-%d %H:%M", strict=False),
+            pl.col("^period.+$").str.to_date("%Y-%m-%d", strict=False),
+            pl.col("^.+Flag$").cast(pl.Int8).cast(pl.Boolean),
+            pl.col("^.+Code$").cast(pl.String),
+        )
+        .select("Date", pl.exclude("Date"))
+    )
+
+
+def read_csv(data: bytes) -> DataFrame:
+    return pl.read_csv(
+        data,
+        separator="\t",
+        encoding="utf-16-le",
+        infer_schema_length=None,
+    )
+
+
+def clean_csv(df: DataFrame, doc_id: str) -> DataFrame:
+    return df.select(
+        pl.lit(doc_id).alias("docID"),
+        pl.all(),
+    )

kabukit-0.3.1/src/kabukit/jquants/__init__.py

@@ -0,0 +1,4 @@
+from .concurrent import fetch, fetch_all
+from .schema import rename
+
+__all__ = ["fetch", "fetch_all", "rename"]

kabukit-0.3.0/src/kabukit/__init__.py

@@ -1,7 +0,0 @@
-from .core.info import Info
-from .core.prices import Prices
-from .core.statements import Statements
-from .edinet.client import EdinetClient
-from .jquants.client import JQuantsClient
-
-__all__ = ["EdinetClient", "Info", "JQuantsClient", "Prices", "Statements"]

kabukit-0.3.0/src/kabukit/edinet/__init__.py

@@ -1,3 +0,0 @@
-from .concurrent import fetch, fetch_list
-
-__all__ = ["fetch", "fetch_list"]

kabukit-0.3.0/src/kabukit/edinet/doc.py

@@ -1,32 +0,0 @@
-from __future__ import annotations
-
-import datetime
-from typing import TYPE_CHECKING
-
-import polars as pl
-
-if TYPE_CHECKING:
-    from polars import DataFrame
-
-
-def clean_list(df: DataFrame, date: str | datetime.date) -> DataFrame:
-    if isinstance(date, str):
-        date = datetime.datetime.strptime(date, "%Y-%m-%d").date()  # noqa: DTZ007
-
-    return df.with_columns(
-        pl.lit(date).alias("Date"),
-        pl.col("submitDateTime").str.to_datetime("%Y-%m-%d %H:%M", strict=False),
-        pl.col("^period.+$").str.to_date("%Y-%m-%d", strict=False),
-        pl.col("^.+Flag$").cast(pl.Int8).cast(pl.Boolean),
-        pl.col("^.+Code$").cast(pl.String),
-        pl.col("opeDateTime")
-        .cast(pl.String)
-        .str.to_datetime("%Y-%m-%d %H:%M", strict=False),
-    ).select("Date", pl.exclude("Date"))
-
-
-def clean_csv(df: DataFrame, doc_id: str) -> DataFrame:
-    return df.select(
-        pl.lit(doc_id).alias("docID"),
-        pl.all(),
-    )

kabukit-0.3.0/src/kabukit/jquants/__init__.py

@@ -1,3 +0,0 @@
-from .concurrent import fetch, fetch_all
-
-__all__ = ["fetch", "fetch_all"]