def test_xlsx_input_utf8(self):
"""This is an xlsx file saved by OpenOffice. It seems to use UTF8 internally."""
csvinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/unicode.xlsx')
csvinput.read_sheets()
assert list(csvinput.get_sheet_lines('main'))[0]['id'] == 'éαГ😼𝒞人'
def test_xlsx_input_utf8(self):
"""This is an xlsx file saved by OpenOffice. It seems to use UTF8 internally."""
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/unicode.xlsx")
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines("main"))[0]["id"] == "éαГ😼𝒞人"
def test_xlsx_no_main_sheet(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/basic.xlsx',
main_sheet_name='notmain')
with pytest.raises(ValueError) as e:
xlsxinput.read_sheets()
assert 'Main sheet "notmain" not found in workbook.' in text_type(e)
def test_xlsx_no_file(self, tmpdir):
xlsxinput = XLSXInput(input_name=tmpdir.strpath.join('test.xlsx'), main_sheet_name='main')
if sys.version > '3':
with pytest.raises(FileNotFoundError):
xlsxinput.read_sheets()
else:
with pytest.raises(IOError):
xlsxinput.read_sheets()
def test_xlsx_input_integer(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/integer.xlsx', main_sheet_name='main')
assert xlsxinput.main_sheet_name == 'main'
xlsxinput.read_sheets()
assert list(xlsxinput.get_main_sheet_lines()) == \
[{'colA': 1}]
assert xlsxinput.sub_sheet_names == []
def test_xlsx_vertical(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/basic_transpose.xlsx', vertical_orientation=True)
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 'cell1', 'colB': 'cell2'}, {'colA': 'cell3', 'colB': 'cell4'}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 'cell5', 'colD': 'cell6'}, {'colC': 'cell7', 'colD': 'cell8'}]
def test_xlsx_input_integer(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/integer.xlsx',
main_sheet_name='main')
assert xlsxinput.main_sheet_name == 'main'
xlsxinput.read_sheets()
assert list(xlsxinput.get_main_sheet_lines()) == \
[{'colA': 1}]
assert xlsxinput.sub_sheet_names == []
def test_xlsx_input(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/basic.xlsx', main_sheet_name='main')
assert xlsxinput.main_sheet_name == 'main'
xlsxinput.read_sheets()
assert list(xlsxinput.get_main_sheet_lines()) == \
[{'colA': 'cell1', 'colB': 'cell2'}, {'colA': 'cell3', 'colB': 'cell4'}]
assert xlsxinput.sub_sheet_names == ['subsheet']
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 'cell5', 'colD': 'cell6'}, {'colC': 'cell7', 'colD': 'cell8'}]
def test_xlsx_input_integer2(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/integer2.xlsx')
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines('Sheet1')) == \
[{'activity-status/@code': 2}]
# This is a float, but is converted to an int in the unflatten step, see
# test_input_SpreadsheetInput_unflatten.py
# 'Basic with float'
assert type(list(xlsxinput.get_sheet_lines('Sheet1'))[0]['activity-status/@code']) == float
assert xlsxinput.sub_sheet_names == ['Sheet1']
def test_xlsx_input_formula(self):
""" When a forumla is present, we should use the value, rather than the
formula itself. """
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/formula.xlsx')
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 1, 'colB': 2}, {'colA': 2, 'colB': 4}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 3, 'colD': 9}, {'colC': 4, 'colD': 12}]
def test_bad_xlsx(self):
""" XLSX file that is not a XLSX"""
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/file.xlsx')
try:
xlsxinput.read_sheets()
except Exception as e:
assert str(
e
) == "The supplied file has extension .xlsx but isn't an XLSX file."
return
assert False, "No Exception Raised"
def test_xlsx_input(self):
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/basic.xlsx")
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ["main", "subsheet"]
assert list(xlsxinput.get_sheet_lines("main")) == [
{
"colA": "cell1",
"colB": "cell2"
},
{
"colA": "cell3",
"colB": "cell4"
},
]
assert list(xlsxinput.get_sheet_lines("subsheet")) == [
{
"colC": "cell5",
"colD": "cell6"
},
{
"colC": "cell7",
"colD": "cell8"
},
]
def test_xlsx_input_formula(self):
""" When a forumla is present, we should use the value, rather than the
formula itself. """
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/formula.xlsx")
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ["main", "subsheet"]
assert list(xlsxinput.get_sheet_lines("main")) == [
{
"colA": 1,
"colB": 2
},
{
"colA": 2,
"colB": 4
},
]
assert list(xlsxinput.get_sheet_lines("subsheet")) == [
{
"colC": 3,
"colD": 9
},
{
"colC": 4,
"colD": 12
},
]
def test_xlsx_include_ignore(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/basic_meta.xlsx',
include_sheets=['Meta'], vertical_orientation=True
)
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['Meta']
assert list(xlsxinput.get_sheet_lines('Meta')) == \
[{'a': 'a1', 'b': 'b1', 'c': 'c1'}]
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/basic_meta.xlsx',
exclude_sheets=['Meta'])
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 'cell1', 'colB': 'cell2'}, {'colA': 'cell3', 'colB': 'cell4'}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 'cell5', 'colD': 'cell6'}, {'colC': 'cell7', 'colD': 'cell8'}]
def test_xlsx_no_file(self, tmpdir):
xlsxinput = XLSXInput(input_name=tmpdir.strpath.join('test.xlsx'))
if sys.version > '3':
with pytest.raises(FileNotFoundError):
xlsxinput.read_sheets()
else:
with pytest.raises(IOError):
xlsxinput.read_sheets()
def test_xlsx_input(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/basic.xlsx')
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 'cell1', 'colB': 'cell2'}, {'colA': 'cell3', 'colB': 'cell4'}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 'cell5', 'colD': 'cell6'}, {'colC': 'cell7', 'colD': 'cell8'}]
def test_xlsx_input_integer(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/integer.xlsx')
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 1}]
if sys.version_info[0] == 2:
assert type(list(
xlsxinput.get_sheet_lines('main'))[0]['colA']) == long
else:
assert type(list(
xlsxinput.get_sheet_lines('main'))[0]['colA']) == int
assert xlsxinput.sub_sheet_names == ['main']
def test_xlsx_input_integer(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/integer.xlsx')
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 1}]
if sys.version_info[0] == 2:
assert type(list(xlsxinput.get_sheet_lines('main'))[0]['colA']) == long
else:
assert type(list(xlsxinput.get_sheet_lines('main'))[0]['colA']) == int
assert xlsxinput.sub_sheet_names == ['main']
def test_xlsx_input_formula(self):
""" When a forumla is present, we should use the value, rather than the
formula itself. """
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/formula.xlsx')
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 1, 'colB': 2}, {'colA': 2, 'colB': 4}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 3, 'colD': 9}, {'colC': 4, 'colD': 12}]
def test_xlsx_input_integer2(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/integer2.xlsx')
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines('Sheet1')) == \
[{'activity-status/@code': 2}]
# This is a float, but is converted to an int in the unflatten step, see
# test_input_SpreadsheetInput_unflatten.py
# 'Basic with float'
assert type(
list(xlsxinput.get_sheet_lines('Sheet1'))[0]
['activity-status/@code']) == float
assert xlsxinput.sub_sheet_names == ['Sheet1']
def test_xlsx_input_integer2(self):
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/integer2.xlsx")
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines("Sheet1")) == [{
"activity-status/@code":
2
}]
# This is a float, but is converted to an int in the unflatten step, see
# test_input_SpreadsheetInput_unflatten.py
# 'Basic with float'
assert (type(
list(xlsxinput.get_sheet_lines("Sheet1"))[0]
["activity-status/@code"]) == float)
assert xlsxinput.sub_sheet_names == ["Sheet1"]
def test_xlsx_input_types(self):
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/types.xlsx")
xlsxinput.read_sheets()
assert list(xlsxinput.get_sheet_lines("main")) == [{
"colInt":
1,
"colFloat":
1.2,
"colDate":
datetime.datetime(2020, 3, 5),
"colDateTime":
datetime.datetime(2020, 2, 7, 16, 41, 0, 1),
}]
assert type(list(
xlsxinput.get_sheet_lines("main"))[0]["colInt"]) == int
assert type(list(
xlsxinput.get_sheet_lines("main"))[0]["colFloat"]) == float
assert xlsxinput.sub_sheet_names == ["main"]
def test_xlsx_input_utf8(self):
"""This is an xlsx file saved by OpenOffice. It seems to use UTF8 internally."""
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/unicode.xlsx', main_sheet_name='main')
xlsxinput.read_sheets()
assert list(xlsxinput.get_main_sheet_lines())[0]['id'] == 'éαГ😼𝒞人'
def test_xlsx_no_main_sheet(self):
xlsxinput = XLSXInput(input_name='flattentool/tests/fixtures/xlsx/basic.xlsx', main_sheet_name='notmain')
with pytest.raises(ValueError) as e:
xlsxinput.read_sheets()
assert 'Main sheet "notmain" not found in workbook.' in text_type(e)
def test_xlsx_include_ignore(self):
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/basic_meta.xlsx',
include_sheets=['Meta'],
vertical_orientation=True)
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['Meta']
assert list(xlsxinput.get_sheet_lines('Meta')) == \
[{'a': 'a1', 'b': 'b1', 'c': 'c1'}]
xlsxinput = XLSXInput(
input_name='flattentool/tests/fixtures/xlsx/basic_meta.xlsx',
exclude_sheets=['Meta'])
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ['main', 'subsheet']
assert list(xlsxinput.get_sheet_lines('main')) == \
[{'colA': 'cell1', 'colB': 'cell2'}, {'colA': 'cell3', 'colB': 'cell4'}]
assert list(xlsxinput.get_sheet_lines('subsheet')) == \
[{'colC': 'cell5', 'colD': 'cell6'}, {'colC': 'cell7', 'colD': 'cell8'}]
def test_xlsx_include_ignore(self):
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/basic_meta.xlsx",
include_sheets=["Meta"],
vertical_orientation=True,
)
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ["Meta"]
assert list(xlsxinput.get_sheet_lines("Meta")) == [{
"a": "a1",
"b": "b1",
"c": "c1"
}]
xlsxinput = XLSXInput(
input_name="flattentool/tests/fixtures/xlsx/basic_meta.xlsx",
exclude_sheets=["Meta"],
)
xlsxinput.read_sheets()
assert xlsxinput.sub_sheet_names == ["main", "subsheet"]
assert list(xlsxinput.get_sheet_lines("main")) == [
{
"colA": "cell1",
"colB": "cell2"
},
{
"colA": "cell3",
"colB": "cell4"
},
]
assert list(xlsxinput.get_sheet_lines("subsheet")) == [
{
"colC": "cell5",
"colD": "cell6"
},
{
"colC": "cell7",
"colD": "cell8"
},
]
def test_xlsx_no_file(self, tmpdir):
xlsxinput = XLSXInput(input_name=tmpdir.join("test.xlsx").strpath)
with pytest.raises(FileNotFoundError):
xlsxinput.read_sheets()