Skip to content

TableStoreExcel-datetime-fix #387

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
elephantum merged 2 commits into from
Jun 4, 2026
Merged

TableStoreExcel-datetime-fix #387

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
419ca6e
TableStoreExcel-datetime-fix
SergeyZ06 Jun 3, 2026
cd8d63e
Parametrize test
elephantum Jun 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion datapipe/store/pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,19 @@ def load_file(self) -> pd.DataFrame | None:

if of.fs.exists(of.path):
dtypes = sql_schema_to_dtype(self.primary_schema)
df = pd.read_excel(of.open(), engine="openpyxl", dtype=dtypes)
plain_dtypes = {k: v for k, v in dtypes.items() if v not in _DATETIME_PYTHON_TYPES}

df = pd.read_excel(of.open(), engine="openpyxl", dtype=plain_dtypes)

for col, py_type in dtypes.items():
if col not in df.columns or py_type not in _DATETIME_PYTHON_TYPES:
continue
if py_type == datetime.datetime:
df[col] = pd.to_datetime(df[col])
elif py_type == datetime.date:
df[col] = pd.to_datetime(df[col]).dt.date
elif py_type == datetime.time:
df[col] = pd.to_datetime(df[col]).dt.time

return df
else:
Expand Down
91 changes: 45 additions & 46 deletions tests/test_table_store_json_line.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,20 +5,20 @@
import pandas as pd
import pytest
from sqlalchemy import (
BigInteger,
Boolean,
Column,
Date,
DateTime,
Float,
Integer,
Numeric,
SmallInteger,
String,
Text,
Time,
Unicode,
UnicodeText,
Integer,
BigInteger,
SmallInteger,
Float,
Numeric,
Boolean,
DateTime,
Date,
Time,
)

from datapipe.compute import Catalog, Pipeline, Table, build_compute, run_steps
Expand All @@ -27,6 +27,23 @@
from datapipe.step.update_external_table import UpdateExternalTable
from datapipe.store.pandas import TableStoreExcel, TableStoreJsonLine
from datapipe.store.tests.abstract import AbstractBaseStoreTests
from datapipe.tests.util import assert_df_equal

DTYPE_SCHEMA = [
Column("dtype_String", String),
Column("dtype_Text", Text),
Column("dtype_Unicode", Unicode),
Column("dtype_UnicodeText", UnicodeText),
Column("dtype_Integer", Integer),
Column("dtype_BigInteger", BigInteger),
Column("dtype_SmallInteger", SmallInteger),
Column("dtype_Float", Float),
Column("dtype_Numeric", Numeric),
Column("dtype_Boolean", Boolean),
Column("dtype_DateTime", DateTime),
Column("dtype_Date", Date),
Column("dtype_Time", Time),
]


def test_table_store_json_line_reading(tmp_dir):
Expand All @@ -36,8 +53,9 @@ def test_table_store_json_line_reading(tmp_dir):

store = TableStoreJsonLine(filename=test_fname)
df = store.load_file()
assert all(df.reset_index(drop=False)["id"].values == test_df["id"].values)
assert all(df["record"].values == test_df["record"].values)

assert df is not None
assert_df_equal(df, test_df)


def make_file1(file):
Expand Down Expand Up @@ -97,23 +115,20 @@ def test_table_store_json_line_with_deleting(dbconn, tmp_dir):
assert len(catalog.get_datatable(ds, "transfomed_data").get_data()) == 2


def test_dtype_mapping(tmp_dir):
schema = [
Column("dtype_String", String),
Column("dtype_Text", Text),
Column("dtype_Unicode", Unicode),
Column("dtype_UnicodeText", UnicodeText),
Column("dtype_Integer", Integer),
Column("dtype_BigInteger", BigInteger),
Column("dtype_SmallInteger", SmallInteger),
Column("dtype_Float", Float),
Column("dtype_Numeric", Numeric),
Column("dtype_Boolean", Boolean),
Column("dtype_DateTime", DateTime),
Column("dtype_Date", Date),
Column("dtype_Time", Time),
]
store = TableStoreJsonLine(filename=tmp_dir / "dtypes.json", primary_schema=schema)
@pytest.mark.parametrize(
"store_factory",
[
pytest.param(
lambda tmp_dir: TableStoreExcel(filename=tmp_dir / "dtypes.xlsx", primary_schema=DTYPE_SCHEMA), id="excel"
),
pytest.param(
lambda tmp_dir: TableStoreJsonLine(filename=tmp_dir / "dtypes.json", primary_schema=DTYPE_SCHEMA),
id="json_line",
),
],
)
def test_dtype_mapping(tmp_dir, store_factory):
store = store_factory(tmp_dir)

now = datetime.datetime(2024, 1, 15, 12, 0, 0)
df = pd.DataFrame(
Expand Down Expand Up @@ -153,35 +168,19 @@ def test_dtype_mapping(tmp_dir):


def test_table_store_json_line_with_dtype_mapping(dbconn, tmp_dir):
schema = [
Column("dtype_String", String),
Column("dtype_Text", Text),
Column("dtype_Unicode", Unicode),
Column("dtype_UnicodeText", UnicodeText),
Column("dtype_Integer", Integer),
Column("dtype_BigInteger", BigInteger),
Column("dtype_SmallInteger", SmallInteger),
Column("dtype_Float", Float),
Column("dtype_Numeric", Numeric),
Column("dtype_Boolean", Boolean),
Column("dtype_DateTime", DateTime),
Column("dtype_Date", Date),
Column("dtype_Time", Time),
]

ds = DataStore(dbconn, create_meta_table=True)
catalog = Catalog(
{
"input_dtypes": Table(
store=TableStoreJsonLine(
filename=tmp_dir / "dtypes.json",
primary_schema=schema,
primary_schema=DTYPE_SCHEMA,
),
),
"transfomed_dtypes": Table(
store=TableStoreJsonLine(
filename=tmp_dir / "dtypes_transformed.json",
primary_schema=schema,
primary_schema=DTYPE_SCHEMA,
),
),
}
Expand Down
Loading