miklo
/
pandas_ods_reader
mirror of https://forge.citizen4.eu/miklo/pandas_ods_reader.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

refactor tests, use pathlib instead of os

This commit is contained in:
iuvbio 2020-02-23 16:53:22 +01:00
parent 4844310707
commit 9c485d42b9
1 changed files with 39 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
pandas_ods_reader/tests/test_read_ods.py
View File

@ -1,4 +1,5 @@
import os
"""Tests for core read_ods function with different files"""
from pathlib import Path
import pandas as pd
import pytest
@ -6,8 +7,8 @@ import pytest
from pandas_ods_reader import read_ods
root = os.path.dirname(os.path.abspath(__file__))
rsc = os.path.join(root, "rsc")
root = Path(__file__).parent
rsc = root / "rsc"
header_file = "example_headers.ods"
no_header_file = "example_no_headers.ods"
@ -18,81 +19,105 @@ mixed_dtypes_file = "mixed_dtypes.ods"
class TestOdsReader(object):
def test_header_file_with_int(self):
path = os.path.join(rsc, header_file)
path = rsc / header_file
df = read_ods(path, 1)
assert isinstance(df, pd.DataFrame)
assert len(df) == 10
assert (len(df.columns) == 5)
def test_header_file_with_str(self):
path = os.path.join(rsc, header_file)
path = rsc / header_file
df = read_ods(path, "Sheet1")
assert isinstance(df, pd.DataFrame)
assert len(df) == 10
assert (len(df.columns) == 5)
def test_header_file_with_cols(self):
path = os.path.join(rsc, header_file)
path = rsc / header_file
columns = ["One", "Two", "Three", "Four", "Five"]
df = read_ods(path, "Sheet1", columns=columns)
assert list(df.columns) == columns
assert len(df) == 10
assert (len(df.columns) == 5)
def test_no_header_file_no_cols(self):
path = os.path.join(rsc, no_header_file)
path = rsc / no_header_file
df = read_ods(path, 1, headers=False)
assert list(df.columns) == [
f"column.{i}" for i in range(len(df.columns))]
assert len(df) == 10
assert (len(df.columns) == 5)
def test_no_header_file_with_cols(self):
path = os.path.join(rsc, no_header_file)
path = rsc / no_header_file
columns = ["A", "B", "C", "D", "E"]
df = read_ods(path, 1, headers=False, columns=columns)
assert list(df.columns) == columns
assert len(df) == 10
def test_duplicated_column_names(self):
path = os.path.join(rsc, duplicated_column_names_file)
path = rsc / duplicated_column_names_file
df = read_ods(path, 1)
assert isinstance(df, pd.DataFrame)
assert len(df.columns) == 4
assert "website.1" in df.columns
def test_header_file_col_len(self):
path = os.path.join(rsc, col_len_file)
path = rsc / col_len_file
df = read_ods(path, 1)
assert isinstance(df, pd.DataFrame)
assert len(df) == 10
assert (len(df.columns) == 5)
def test_wrong_id_type(self):
path = os.path.join(rsc, header_file)
path = rsc / header_file
with pytest.raises(ValueError) as e_info:
read_ods(path, 1.0)
assert e_info.match("Sheet id has to be either `str` or `int`")
def test_non_existent_sheet(self):
path = os.path.join(rsc, header_file)
path = rsc / header_file
sheet_name = "No_Sheet"
with pytest.raises(ValueError) as e_info:
read_ods(path, sheet_name)
assert e_info.match(f"There is no sheet named {sheet_name}")
def test_missing_header(self):
path = os.path.join(rsc, missing_header_file)
path = rsc / missing_header_file
df = read_ods(path, 1)
assert isinstance(df, pd.DataFrame)
assert len(df) == 10
assert (len(df.columns) == 5)
assert df.columns[2] == "unnamed.1"
def test_mixed_dtypes(sefl):
path = os.path.join(rsc, mixed_dtypes_file)
path = rsc / mixed_dtypes_file
df = read_ods(path, 1)
assert isinstance(df, pd.DataFrame)
assert len(df) == 10
assert (len(df.columns) == 5)