plesna/tests/repository/test_fs_repository.py

import shutil
from pathlib import Path

import pytest
from pandas import pandas

from dashboard.libs.repository.fs_repository import FSRepository

EXAMPLE_DIR = "./tests/repository/fs_examples/"


@pytest.fixture
def location(tmp_path):
    loc = tmp_path
    username_loc = loc / "username"
    username_loc.mkdir()
    salary_loc = loc / "salary"
    salary_loc.mkdir()
    example_src = Path(EXAMPLE_DIR)

    for f in example_src.glob("*"):
        if "username" in str(f):
            shutil.copy(f, username_loc)
        else:
            shutil.copy(f, salary_loc)

    return loc


def test_init(location):
    repo = FSRepository("example", location)
    assert repo.ls() == [
        "username",
        "salary",
    ]
    assert repo.schemas() == [
        ".",
        "username",
        "salary",
    ]

    assert repo.tables() == []
    assert repo.tables("username") == [
        "username.csv",
        "username-password-recovery-code.xlsx",
        "username-password-recovery-code.xls",
    ]
    assert repo.tables("salary") == ["salary.pdf"]


def test_read_csv(location):
    repo = FSRepository("example", location)
    username = repo.read("username.csv", "username", delimiter=";")
    assert list(username.columns) == [
        "Username",
        "Identifier",
        "First name",
        "Last name",
    ]
    assert len(username.index) == 5


def test_fake_read_xlsx(location):
    repo = FSRepository("example", location)
    df = pandas.read_excel(
        location / "username" / "username-password-recovery-code.xls"
    )
    print(df)


def test_read_xlsx(location):
    repo = FSRepository("example", location)
    username = repo.read("username-password-recovery-code.xls", "username")
    assert list(username.columns) == [
        "Username",
        "Identifier",
        "One-time password",
        "Recovery code",
        "First name",
        "Last name",
        "Department",
        "Location",
    ]
    assert len(username.index) == 5