dierk
8f7399de58
Supports .xls and .xlsx, Oracle and PostgreSQL via SQLAlchemy. Includes CLI (run/inspect/generate-config), YAML config, auto schema detection, and append/replace/upsert modes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
85 lines
2.3 KiB
Python
85 lines
2.3 KiB
Python
import io
|
|
from pathlib import Path
|
|
import pandas as pd
|
|
import pytest
|
|
|
|
from excel_import.reader import ExcelReader
|
|
from excel_import.config import SheetConfig
|
|
|
|
|
|
@pytest.fixture
|
|
def xlsx_file(tmp_path: Path) -> Path:
|
|
path = tmp_path / "test.xlsx"
|
|
df = pd.DataFrame({
|
|
"Artikelnummer": ["A001", "A002", "A003"],
|
|
"Bezeichnung": ["Widget", "Gadget", None],
|
|
"Preis": [9.99, 14.50, 0.99],
|
|
})
|
|
df.to_excel(path, index=False)
|
|
return path
|
|
|
|
|
|
def test_sheet_names(xlsx_file: Path):
|
|
reader = ExcelReader(xlsx_file)
|
|
assert reader.sheet_names() == ["Sheet1"]
|
|
|
|
|
|
def test_read_basic(xlsx_file: Path):
|
|
reader = ExcelReader(xlsx_file)
|
|
df = reader.read(SheetConfig(sheet=0, target_table="t"))
|
|
assert len(df) == 3
|
|
assert list(df.columns) == ["Artikelnummer", "Bezeichnung", "Preis"]
|
|
|
|
|
|
def test_read_drops_empty_rows(tmp_path: Path):
|
|
path = tmp_path / "empty_rows.xlsx"
|
|
df = pd.DataFrame({"A": ["x", None, "y"], "B": [1, None, 3]})
|
|
df.to_excel(path, index=False)
|
|
|
|
reader = ExcelReader(path)
|
|
result = reader.read(SheetConfig(sheet=0, target_table="t"))
|
|
assert len(result) == 2
|
|
|
|
|
|
def test_read_column_rename(xlsx_file: Path):
|
|
from excel_import.config import ColumnMapping
|
|
cfg = SheetConfig(
|
|
sheet=0,
|
|
target_table="t",
|
|
columns=[
|
|
ColumnMapping(source="Artikelnummer", target="art_nr"),
|
|
ColumnMapping(source="Bezeichnung", target="bez"),
|
|
ColumnMapping(source="Preis", target="preis"),
|
|
],
|
|
)
|
|
reader = ExcelReader(xlsx_file)
|
|
df = reader.read(cfg)
|
|
assert "art_nr" in df.columns
|
|
assert "Artikelnummer" not in df.columns
|
|
|
|
|
|
def test_read_column_skip(xlsx_file: Path):
|
|
from excel_import.config import ColumnMapping
|
|
cfg = SheetConfig(
|
|
sheet=0,
|
|
target_table="t",
|
|
columns=[
|
|
ColumnMapping(source="Preis", target="Preis", skip=True),
|
|
],
|
|
)
|
|
reader = ExcelReader(xlsx_file)
|
|
df = reader.read(cfg)
|
|
assert "Preis" not in df.columns
|
|
|
|
|
|
def test_file_not_found():
|
|
with pytest.raises(FileNotFoundError):
|
|
ExcelReader("/nonexistent/path/file.xlsx")
|
|
|
|
|
|
def test_unsupported_extension(tmp_path: Path):
|
|
f = tmp_path / "data.csv"
|
|
f.write_text("a,b\n1,2")
|
|
with pytest.raises(ValueError, match="Unsupported"):
|
|
ExcelReader(f)
|