Updated script that can be controled by Nodejs web app

This commit is contained in:
mac OS
2024-11-25 12:24:18 +07:00
parent c440eda1f4
commit 8b0ab2bd3a
8662 changed files with 1803808 additions and 34 deletions

View File

@ -0,0 +1,77 @@
import functools
import numpy as np
import pytest
from pandas.compat import is_platform_windows
import pandas as pd
import pandas._testing as tm
pytest.importorskip("odf")
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
@pytest.fixture(autouse=True)
def cd_and_set_engine(monkeypatch, datapath):
func = functools.partial(pd.read_excel, engine="odf")
monkeypatch.setattr(pd, "read_excel", func)
monkeypatch.chdir(datapath("io", "data", "excel"))
def test_read_invalid_types_raises():
# the invalid_value_type.ods required manually editing
# of the included content.xml file
with pytest.raises(ValueError, match="Unrecognized type awesome_new_type"):
pd.read_excel("invalid_value_type.ods")
def test_read_writer_table():
# Also test reading tables from an text OpenDocument file
# (.odt)
index = pd.Index(["Row 1", "Row 2", "Row 3"], name="Header")
expected = pd.DataFrame(
[[1, np.nan, 7], [2, np.nan, 8], [3, np.nan, 9]],
index=index,
columns=["Column 1", "Unnamed: 2", "Column 3"],
)
result = pd.read_excel("writertable.odt", sheet_name="Table1", index_col=0)
tm.assert_frame_equal(result, expected)
def test_read_newlines_between_xml_elements_table():
# GH#45598
expected = pd.DataFrame(
[[1.0, 4.0, 7], [np.nan, np.nan, 8], [3.0, 6.0, 9]],
columns=["Column 1", "Column 2", "Column 3"],
)
result = pd.read_excel("test_newlines.ods")
tm.assert_frame_equal(result, expected)
def test_read_unempty_cells():
expected = pd.DataFrame(
[1, np.nan, 3, np.nan, 5],
columns=["Column 1"],
)
result = pd.read_excel("test_unempty_cells.ods")
tm.assert_frame_equal(result, expected)
def test_read_cell_annotation():
expected = pd.DataFrame(
["test", np.nan, "test 3"],
columns=["Column 1"],
)
result = pd.read_excel("test_cell_annotation.ods")
tm.assert_frame_equal(result, expected)

View File

@ -0,0 +1,106 @@
from datetime import (
date,
datetime,
)
import re
import pytest
from pandas.compat import is_platform_windows
import pandas as pd
import pandas._testing as tm
from pandas.io.excel import ExcelWriter
odf = pytest.importorskip("odf")
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
@pytest.fixture
def ext():
return ".ods"
def test_write_append_mode_raises(ext):
msg = "Append mode is not supported with odf!"
with tm.ensure_clean(ext) as f:
with pytest.raises(ValueError, match=msg):
ExcelWriter(f, engine="odf", mode="a")
@pytest.mark.parametrize("engine_kwargs", [None, {"kwarg": 1}])
def test_engine_kwargs(ext, engine_kwargs):
# GH 42286
# GH 43445
# test for error: OpenDocumentSpreadsheet does not accept any arguments
with tm.ensure_clean(ext) as f:
if engine_kwargs is not None:
error = re.escape(
"OpenDocumentSpreadsheet() got an unexpected keyword argument 'kwarg'"
)
with pytest.raises(
TypeError,
match=error,
):
ExcelWriter(f, engine="odf", engine_kwargs=engine_kwargs)
else:
with ExcelWriter(f, engine="odf", engine_kwargs=engine_kwargs) as _:
pass
def test_book_and_sheets_consistent(ext):
# GH#45687 - Ensure sheets is updated if user modifies book
with tm.ensure_clean(ext) as f:
with ExcelWriter(f) as writer:
assert writer.sheets == {}
table = odf.table.Table(name="test_name")
writer.book.spreadsheet.addElement(table)
assert writer.sheets == {"test_name": table}
@pytest.mark.parametrize(
["value", "cell_value_type", "cell_value_attribute", "cell_value"],
argvalues=[
(True, "boolean", "boolean-value", "true"),
("test string", "string", "string-value", "test string"),
(1, "float", "value", "1"),
(1.5, "float", "value", "1.5"),
(
datetime(2010, 10, 10, 10, 10, 10),
"date",
"date-value",
"2010-10-10T10:10:10",
),
(date(2010, 10, 10), "date", "date-value", "2010-10-10"),
],
)
def test_cell_value_type(ext, value, cell_value_type, cell_value_attribute, cell_value):
# GH#54994 ODS: cell attributes should follow specification
# http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os-part1.html#refTable13
from odf.namespaces import OFFICENS
from odf.table import (
TableCell,
TableRow,
)
table_cell_name = TableCell().qname
with tm.ensure_clean(ext) as f:
pd.DataFrame([[value]]).to_excel(f, header=False, index=False)
with pd.ExcelFile(f) as wb:
sheet = wb._reader.get_sheet_by_index(0)
sheet_rows = sheet.getElementsByType(TableRow)
sheet_cells = [
x
for x in sheet_rows[0].childNodes
if hasattr(x, "qname") and x.qname == table_cell_name
]
cell = sheet_cells[0]
assert cell.attributes.get((OFFICENS, "value-type")) == cell_value_type
assert cell.attributes.get((OFFICENS, cell_value_attribute)) == cell_value

View File

@ -0,0 +1,432 @@
import contextlib
from pathlib import Path
import re
import numpy as np
import pytest
from pandas.compat import is_platform_windows
import pandas as pd
from pandas import DataFrame
import pandas._testing as tm
from pandas.io.excel import (
ExcelWriter,
_OpenpyxlWriter,
)
from pandas.io.excel._openpyxl import OpenpyxlReader
openpyxl = pytest.importorskip("openpyxl")
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
@pytest.fixture
def ext():
return ".xlsx"
def test_to_excel_styleconverter():
from openpyxl import styles
hstyle = {
"font": {"color": "00FF0000", "bold": True},
"borders": {"top": "thin", "right": "thin", "bottom": "thin", "left": "thin"},
"alignment": {"horizontal": "center", "vertical": "top"},
"fill": {"patternType": "solid", "fgColor": {"rgb": "006666FF", "tint": 0.3}},
"number_format": {"format_code": "0.00"},
"protection": {"locked": True, "hidden": False},
}
font_color = styles.Color("00FF0000")
font = styles.Font(bold=True, color=font_color)
side = styles.Side(style=styles.borders.BORDER_THIN)
border = styles.Border(top=side, right=side, bottom=side, left=side)
alignment = styles.Alignment(horizontal="center", vertical="top")
fill_color = styles.Color(rgb="006666FF", tint=0.3)
fill = styles.PatternFill(patternType="solid", fgColor=fill_color)
number_format = "0.00"
protection = styles.Protection(locked=True, hidden=False)
kw = _OpenpyxlWriter._convert_to_style_kwargs(hstyle)
assert kw["font"] == font
assert kw["border"] == border
assert kw["alignment"] == alignment
assert kw["fill"] == fill
assert kw["number_format"] == number_format
assert kw["protection"] == protection
def test_write_cells_merge_styled(ext):
from pandas.io.formats.excel import ExcelCell
sheet_name = "merge_styled"
sty_b1 = {"font": {"color": "00FF0000"}}
sty_a2 = {"font": {"color": "0000FF00"}}
initial_cells = [
ExcelCell(col=1, row=0, val=42, style=sty_b1),
ExcelCell(col=0, row=1, val=99, style=sty_a2),
]
sty_merged = {"font": {"color": "000000FF", "bold": True}}
sty_kwargs = _OpenpyxlWriter._convert_to_style_kwargs(sty_merged)
openpyxl_sty_merged = sty_kwargs["font"]
merge_cells = [
ExcelCell(
col=0, row=0, val="pandas", mergestart=1, mergeend=1, style=sty_merged
)
]
with tm.ensure_clean(ext) as path:
with _OpenpyxlWriter(path) as writer:
writer._write_cells(initial_cells, sheet_name=sheet_name)
writer._write_cells(merge_cells, sheet_name=sheet_name)
wks = writer.sheets[sheet_name]
xcell_b1 = wks["B1"]
xcell_a2 = wks["A2"]
assert xcell_b1.font == openpyxl_sty_merged
assert xcell_a2.font == openpyxl_sty_merged
@pytest.mark.parametrize("iso_dates", [True, False])
def test_engine_kwargs_write(ext, iso_dates):
# GH 42286 GH 43445
engine_kwargs = {"iso_dates": iso_dates}
with tm.ensure_clean(ext) as f:
with ExcelWriter(f, engine="openpyxl", engine_kwargs=engine_kwargs) as writer:
assert writer.book.iso_dates == iso_dates
# ExcelWriter won't allow us to close without writing something
DataFrame().to_excel(writer)
def test_engine_kwargs_append_invalid(ext):
# GH 43445
# test whether an invalid engine kwargs actually raises
with tm.ensure_clean(ext) as f:
DataFrame(["hello", "world"]).to_excel(f)
with pytest.raises(
TypeError,
match=re.escape(
"load_workbook() got an unexpected keyword argument 'apple_banana'"
),
):
with ExcelWriter(
f, engine="openpyxl", mode="a", engine_kwargs={"apple_banana": "fruit"}
) as writer:
# ExcelWriter needs us to write something to close properly
DataFrame(["good"]).to_excel(writer, sheet_name="Sheet2")
@pytest.mark.parametrize("data_only, expected", [(True, 0), (False, "=1+1")])
def test_engine_kwargs_append_data_only(ext, data_only, expected):
# GH 43445
# tests whether the data_only engine_kwarg actually works well for
# openpyxl's load_workbook
with tm.ensure_clean(ext) as f:
DataFrame(["=1+1"]).to_excel(f)
with ExcelWriter(
f, engine="openpyxl", mode="a", engine_kwargs={"data_only": data_only}
) as writer:
assert writer.sheets["Sheet1"]["B2"].value == expected
# ExcelWriter needs us to writer something to close properly?
DataFrame().to_excel(writer, sheet_name="Sheet2")
# ensure that data_only also works for reading
# and that formulas/values roundtrip
assert (
pd.read_excel(
f,
sheet_name="Sheet1",
engine="openpyxl",
engine_kwargs={"data_only": data_only},
).iloc[0, 1]
== expected
)
@pytest.mark.parametrize("kwarg_name", ["read_only", "data_only"])
@pytest.mark.parametrize("kwarg_value", [True, False])
def test_engine_kwargs_append_reader(datapath, ext, kwarg_name, kwarg_value):
# GH 55027
# test that `read_only` and `data_only` can be passed to
# `openpyxl.reader.excel.load_workbook` via `engine_kwargs`
filename = datapath("io", "data", "excel", "test1" + ext)
with contextlib.closing(
OpenpyxlReader(filename, engine_kwargs={kwarg_name: kwarg_value})
) as reader:
assert getattr(reader.book, kwarg_name) == kwarg_value
@pytest.mark.parametrize(
"mode,expected", [("w", ["baz"]), ("a", ["foo", "bar", "baz"])]
)
def test_write_append_mode(ext, mode, expected):
df = DataFrame([1], columns=["baz"])
with tm.ensure_clean(ext) as f:
wb = openpyxl.Workbook()
wb.worksheets[0].title = "foo"
wb.worksheets[0]["A1"].value = "foo"
wb.create_sheet("bar")
wb.worksheets[1]["A1"].value = "bar"
wb.save(f)
with ExcelWriter(f, engine="openpyxl", mode=mode) as writer:
df.to_excel(writer, sheet_name="baz", index=False)
with contextlib.closing(openpyxl.load_workbook(f)) as wb2:
result = [sheet.title for sheet in wb2.worksheets]
assert result == expected
for index, cell_value in enumerate(expected):
assert wb2.worksheets[index]["A1"].value == cell_value
@pytest.mark.parametrize(
"if_sheet_exists,num_sheets,expected",
[
("new", 2, ["apple", "banana"]),
("replace", 1, ["pear"]),
("overlay", 1, ["pear", "banana"]),
],
)
def test_if_sheet_exists_append_modes(ext, if_sheet_exists, num_sheets, expected):
# GH 40230
df1 = DataFrame({"fruit": ["apple", "banana"]})
df2 = DataFrame({"fruit": ["pear"]})
with tm.ensure_clean(ext) as f:
df1.to_excel(f, engine="openpyxl", sheet_name="foo", index=False)
with ExcelWriter(
f, engine="openpyxl", mode="a", if_sheet_exists=if_sheet_exists
) as writer:
df2.to_excel(writer, sheet_name="foo", index=False)
with contextlib.closing(openpyxl.load_workbook(f)) as wb:
assert len(wb.sheetnames) == num_sheets
assert wb.sheetnames[0] == "foo"
result = pd.read_excel(wb, "foo", engine="openpyxl")
assert list(result["fruit"]) == expected
if len(wb.sheetnames) == 2:
result = pd.read_excel(wb, wb.sheetnames[1], engine="openpyxl")
tm.assert_frame_equal(result, df2)
@pytest.mark.parametrize(
"startrow, startcol, greeting, goodbye",
[
(0, 0, ["poop", "world"], ["goodbye", "people"]),
(0, 1, ["hello", "world"], ["poop", "people"]),
(1, 0, ["hello", "poop"], ["goodbye", "people"]),
(1, 1, ["hello", "world"], ["goodbye", "poop"]),
],
)
def test_append_overlay_startrow_startcol(ext, startrow, startcol, greeting, goodbye):
df1 = DataFrame({"greeting": ["hello", "world"], "goodbye": ["goodbye", "people"]})
df2 = DataFrame(["poop"])
with tm.ensure_clean(ext) as f:
df1.to_excel(f, engine="openpyxl", sheet_name="poo", index=False)
with ExcelWriter(
f, engine="openpyxl", mode="a", if_sheet_exists="overlay"
) as writer:
# use startrow+1 because we don't have a header
df2.to_excel(
writer,
index=False,
header=False,
startrow=startrow + 1,
startcol=startcol,
sheet_name="poo",
)
result = pd.read_excel(f, sheet_name="poo", engine="openpyxl")
expected = DataFrame({"greeting": greeting, "goodbye": goodbye})
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize(
"if_sheet_exists,msg",
[
(
"invalid",
"'invalid' is not valid for if_sheet_exists. Valid options "
"are 'error', 'new', 'replace' and 'overlay'.",
),
(
"error",
"Sheet 'foo' already exists and if_sheet_exists is set to 'error'.",
),
(
None,
"Sheet 'foo' already exists and if_sheet_exists is set to 'error'.",
),
],
)
def test_if_sheet_exists_raises(ext, if_sheet_exists, msg):
# GH 40230
df = DataFrame({"fruit": ["pear"]})
with tm.ensure_clean(ext) as f:
with pytest.raises(ValueError, match=re.escape(msg)):
df.to_excel(f, sheet_name="foo", engine="openpyxl")
with ExcelWriter(
f, engine="openpyxl", mode="a", if_sheet_exists=if_sheet_exists
) as writer:
df.to_excel(writer, sheet_name="foo")
def test_to_excel_with_openpyxl_engine(ext):
# GH 29854
with tm.ensure_clean(ext) as filename:
df1 = DataFrame({"A": np.linspace(1, 10, 10)})
df2 = DataFrame({"B": np.linspace(1, 20, 10)})
df = pd.concat([df1, df2], axis=1)
styled = df.style.map(
lambda val: f"color: {'red' if val < 0 else 'black'}"
).highlight_max()
styled.to_excel(filename, engine="openpyxl")
@pytest.mark.parametrize("read_only", [True, False])
def test_read_workbook(datapath, ext, read_only):
# GH 39528
filename = datapath("io", "data", "excel", "test1" + ext)
with contextlib.closing(
openpyxl.load_workbook(filename, read_only=read_only)
) as wb:
result = pd.read_excel(wb, engine="openpyxl")
expected = pd.read_excel(filename)
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize(
"header, expected_data",
[
(
0,
{
"Title": [np.nan, "A", 1, 2, 3],
"Unnamed: 1": [np.nan, "B", 4, 5, 6],
"Unnamed: 2": [np.nan, "C", 7, 8, 9],
},
),
(2, {"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]}),
],
)
@pytest.mark.parametrize(
"filename", ["dimension_missing", "dimension_small", "dimension_large"]
)
# When read_only is None, use read_excel instead of a workbook
@pytest.mark.parametrize("read_only", [True, False, None])
def test_read_with_bad_dimension(
datapath, ext, header, expected_data, filename, read_only
):
# GH 38956, 39001 - no/incorrect dimension information
path = datapath("io", "data", "excel", f"{filename}{ext}")
if read_only is None:
result = pd.read_excel(path, header=header)
else:
with contextlib.closing(
openpyxl.load_workbook(path, read_only=read_only)
) as wb:
result = pd.read_excel(wb, engine="openpyxl", header=header)
expected = DataFrame(expected_data)
tm.assert_frame_equal(result, expected)
def test_append_mode_file(ext):
# GH 39576
df = DataFrame()
with tm.ensure_clean(ext) as f:
df.to_excel(f, engine="openpyxl")
with ExcelWriter(
f, mode="a", engine="openpyxl", if_sheet_exists="new"
) as writer:
df.to_excel(writer)
# make sure that zip files are not concatenated by making sure that
# "docProps/app.xml" only occurs twice in the file
data = Path(f).read_bytes()
first = data.find(b"docProps/app.xml")
second = data.find(b"docProps/app.xml", first + 1)
third = data.find(b"docProps/app.xml", second + 1)
assert second != -1 and third == -1
# When read_only is None, use read_excel instead of a workbook
@pytest.mark.parametrize("read_only", [True, False, None])
def test_read_with_empty_trailing_rows(datapath, ext, read_only):
# GH 39181
path = datapath("io", "data", "excel", f"empty_trailing_rows{ext}")
if read_only is None:
result = pd.read_excel(path)
else:
with contextlib.closing(
openpyxl.load_workbook(path, read_only=read_only)
) as wb:
result = pd.read_excel(wb, engine="openpyxl")
expected = DataFrame(
{
"Title": [np.nan, "A", 1, 2, 3],
"Unnamed: 1": [np.nan, "B", 4, 5, 6],
"Unnamed: 2": [np.nan, "C", 7, 8, 9],
}
)
tm.assert_frame_equal(result, expected)
# When read_only is None, use read_excel instead of a workbook
@pytest.mark.parametrize("read_only", [True, False, None])
def test_read_empty_with_blank_row(datapath, ext, read_only):
# GH 39547 - empty excel file with a row that has no data
path = datapath("io", "data", "excel", f"empty_with_blank_row{ext}")
if read_only is None:
result = pd.read_excel(path)
else:
with contextlib.closing(
openpyxl.load_workbook(path, read_only=read_only)
) as wb:
result = pd.read_excel(wb, engine="openpyxl")
expected = DataFrame()
tm.assert_frame_equal(result, expected)
def test_book_and_sheets_consistent(ext):
# GH#45687 - Ensure sheets is updated if user modifies book
with tm.ensure_clean(ext) as f:
with ExcelWriter(f, engine="openpyxl") as writer:
assert writer.sheets == {}
sheet = writer.book.create_sheet("test_name", 0)
assert writer.sheets == {"test_name": sheet}
def test_ints_spelled_with_decimals(datapath, ext):
# GH 46988 - openpyxl returns this sheet with floats
path = datapath("io", "data", "excel", f"ints_spelled_with_decimals{ext}")
result = pd.read_excel(path)
expected = DataFrame(range(2, 12), columns=[1])
tm.assert_frame_equal(result, expected)
def test_read_multiindex_header_no_index_names(datapath, ext):
# GH#47487
path = datapath("io", "data", "excel", f"multiindex_no_index_names{ext}")
result = pd.read_excel(path, index_col=[0, 1, 2], header=[0, 1, 2])
expected = DataFrame(
[[np.nan, "x", "x", "x"], ["x", np.nan, np.nan, np.nan]],
columns=pd.MultiIndex.from_tuples(
[("X", "Y", "A1"), ("X", "Y", "A2"), ("XX", "YY", "B1"), ("XX", "YY", "B2")]
),
index=pd.MultiIndex.from_tuples([("A", "AA", "AAA"), ("A", "BB", "BBB")]),
)
tm.assert_frame_equal(result, expected)

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,298 @@
import contextlib
import time
import numpy as np
import pytest
from pandas.compat import is_platform_windows
import pandas.util._test_decorators as td
from pandas import (
DataFrame,
read_excel,
)
import pandas._testing as tm
from pandas.io.excel import ExcelWriter
from pandas.io.formats.excel import ExcelFormatter
pytest.importorskip("jinja2")
# jinja2 is currently required for Styler.__init__(). Technically Styler.to_excel
# could compute styles and render to excel without jinja2, since there is no
# 'template' file, but this needs the import error to delayed until render time.
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
def assert_equal_cell_styles(cell1, cell2):
# TODO: should find a better way to check equality
assert cell1.alignment.__dict__ == cell2.alignment.__dict__
assert cell1.border.__dict__ == cell2.border.__dict__
assert cell1.fill.__dict__ == cell2.fill.__dict__
assert cell1.font.__dict__ == cell2.font.__dict__
assert cell1.number_format == cell2.number_format
assert cell1.protection.__dict__ == cell2.protection.__dict__
@pytest.mark.parametrize(
"engine",
["xlsxwriter", "openpyxl"],
)
def test_styler_to_excel_unstyled(engine):
# compare DataFrame.to_excel and Styler.to_excel when no styles applied
pytest.importorskip(engine)
df = DataFrame(np.random.default_rng(2).standard_normal((2, 2)))
with tm.ensure_clean(".xlsx") as path:
with ExcelWriter(path, engine=engine) as writer:
df.to_excel(writer, sheet_name="dataframe")
df.style.to_excel(writer, sheet_name="unstyled")
openpyxl = pytest.importorskip("openpyxl") # test loading only with openpyxl
with contextlib.closing(openpyxl.load_workbook(path)) as wb:
for col1, col2 in zip(wb["dataframe"].columns, wb["unstyled"].columns):
assert len(col1) == len(col2)
for cell1, cell2 in zip(col1, col2):
assert cell1.value == cell2.value
assert_equal_cell_styles(cell1, cell2)
shared_style_params = [
(
"background-color: #111222",
["fill", "fgColor", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
(
"color: #111222",
["font", "color", "value"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
("font-family: Arial;", ["font", "name"], "arial"),
("font-weight: bold;", ["font", "b"], True),
("font-style: italic;", ["font", "i"], True),
("text-decoration: underline;", ["font", "u"], "single"),
("number-format: $??,???.00;", ["number_format"], "$??,???.00"),
("text-align: left;", ["alignment", "horizontal"], "left"),
(
"vertical-align: bottom;",
["alignment", "vertical"],
{"xlsxwriter": None, "openpyxl": "bottom"}, # xlsxwriter Fails
),
("vertical-align: middle;", ["alignment", "vertical"], "center"),
# Border widths
("border-left: 2pt solid red", ["border", "left", "style"], "medium"),
("border-left: 1pt dotted red", ["border", "left", "style"], "dotted"),
("border-left: 2pt dotted red", ["border", "left", "style"], "mediumDashDotDot"),
("border-left: 1pt dashed red", ["border", "left", "style"], "dashed"),
("border-left: 2pt dashed red", ["border", "left", "style"], "mediumDashed"),
("border-left: 1pt solid red", ["border", "left", "style"], "thin"),
("border-left: 3pt solid red", ["border", "left", "style"], "thick"),
# Border expansion
(
"border-left: 2pt solid #111222",
["border", "left", "color", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
("border: 1pt solid red", ["border", "top", "style"], "thin"),
(
"border: 1pt solid #111222",
["border", "top", "color", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
("border: 1pt solid red", ["border", "right", "style"], "thin"),
(
"border: 1pt solid #111222",
["border", "right", "color", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
("border: 1pt solid red", ["border", "bottom", "style"], "thin"),
(
"border: 1pt solid #111222",
["border", "bottom", "color", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
("border: 1pt solid red", ["border", "left", "style"], "thin"),
(
"border: 1pt solid #111222",
["border", "left", "color", "rgb"],
{"xlsxwriter": "FF111222", "openpyxl": "00111222"},
),
# Border styles
(
"border-left-style: hair; border-left-color: black",
["border", "left", "style"],
"hair",
),
]
@pytest.mark.parametrize(
"engine",
["xlsxwriter", "openpyxl"],
)
@pytest.mark.parametrize("css, attrs, expected", shared_style_params)
def test_styler_to_excel_basic(engine, css, attrs, expected):
pytest.importorskip(engine)
df = DataFrame(np.random.default_rng(2).standard_normal((1, 1)))
styler = df.style.map(lambda x: css)
with tm.ensure_clean(".xlsx") as path:
with ExcelWriter(path, engine=engine) as writer:
df.to_excel(writer, sheet_name="dataframe")
styler.to_excel(writer, sheet_name="styled")
openpyxl = pytest.importorskip("openpyxl") # test loading only with openpyxl
with contextlib.closing(openpyxl.load_workbook(path)) as wb:
# test unstyled data cell does not have expected styles
# test styled cell has expected styles
u_cell, s_cell = wb["dataframe"].cell(2, 2), wb["styled"].cell(2, 2)
for attr in attrs:
u_cell, s_cell = getattr(u_cell, attr, None), getattr(s_cell, attr)
if isinstance(expected, dict):
assert u_cell is None or u_cell != expected[engine]
assert s_cell == expected[engine]
else:
assert u_cell is None or u_cell != expected
assert s_cell == expected
@pytest.mark.parametrize(
"engine",
["xlsxwriter", "openpyxl"],
)
@pytest.mark.parametrize("css, attrs, expected", shared_style_params)
def test_styler_to_excel_basic_indexes(engine, css, attrs, expected):
pytest.importorskip(engine)
df = DataFrame(np.random.default_rng(2).standard_normal((1, 1)))
styler = df.style
styler.map_index(lambda x: css, axis=0)
styler.map_index(lambda x: css, axis=1)
null_styler = df.style
null_styler.map(lambda x: "null: css;")
null_styler.map_index(lambda x: "null: css;", axis=0)
null_styler.map_index(lambda x: "null: css;", axis=1)
with tm.ensure_clean(".xlsx") as path:
with ExcelWriter(path, engine=engine) as writer:
null_styler.to_excel(writer, sheet_name="null_styled")
styler.to_excel(writer, sheet_name="styled")
openpyxl = pytest.importorskip("openpyxl") # test loading only with openpyxl
with contextlib.closing(openpyxl.load_workbook(path)) as wb:
# test null styled index cells does not have expected styles
# test styled cell has expected styles
ui_cell, si_cell = wb["null_styled"].cell(2, 1), wb["styled"].cell(2, 1)
uc_cell, sc_cell = wb["null_styled"].cell(1, 2), wb["styled"].cell(1, 2)
for attr in attrs:
ui_cell, si_cell = getattr(ui_cell, attr, None), getattr(si_cell, attr)
uc_cell, sc_cell = getattr(uc_cell, attr, None), getattr(sc_cell, attr)
if isinstance(expected, dict):
assert ui_cell is None or ui_cell != expected[engine]
assert si_cell == expected[engine]
assert uc_cell is None or uc_cell != expected[engine]
assert sc_cell == expected[engine]
else:
assert ui_cell is None or ui_cell != expected
assert si_cell == expected
assert uc_cell is None or uc_cell != expected
assert sc_cell == expected
# From https://openpyxl.readthedocs.io/en/stable/api/openpyxl.styles.borders.html
# Note: Leaving behavior of "width"-type styles undefined; user should use border-width
# instead
excel_border_styles = [
# "thin",
"dashed",
"mediumDashDot",
"dashDotDot",
"hair",
"dotted",
"mediumDashDotDot",
# "medium",
"double",
"dashDot",
"slantDashDot",
# "thick",
"mediumDashed",
]
@pytest.mark.parametrize(
"engine",
["xlsxwriter", "openpyxl"],
)
@pytest.mark.parametrize("border_style", excel_border_styles)
def test_styler_to_excel_border_style(engine, border_style):
css = f"border-left: {border_style} black thin"
attrs = ["border", "left", "style"]
expected = border_style
pytest.importorskip(engine)
df = DataFrame(np.random.default_rng(2).standard_normal((1, 1)))
styler = df.style.map(lambda x: css)
with tm.ensure_clean(".xlsx") as path:
with ExcelWriter(path, engine=engine) as writer:
df.to_excel(writer, sheet_name="dataframe")
styler.to_excel(writer, sheet_name="styled")
openpyxl = pytest.importorskip("openpyxl") # test loading only with openpyxl
with contextlib.closing(openpyxl.load_workbook(path)) as wb:
# test unstyled data cell does not have expected styles
# test styled cell has expected styles
u_cell, s_cell = wb["dataframe"].cell(2, 2), wb["styled"].cell(2, 2)
for attr in attrs:
u_cell, s_cell = getattr(u_cell, attr, None), getattr(s_cell, attr)
if isinstance(expected, dict):
assert u_cell is None or u_cell != expected[engine]
assert s_cell == expected[engine]
else:
assert u_cell is None or u_cell != expected
assert s_cell == expected
def test_styler_custom_converter():
openpyxl = pytest.importorskip("openpyxl")
def custom_converter(css):
return {"font": {"color": {"rgb": "111222"}}}
df = DataFrame(np.random.default_rng(2).standard_normal((1, 1)))
styler = df.style.map(lambda x: "color: #888999")
with tm.ensure_clean(".xlsx") as path:
with ExcelWriter(path, engine="openpyxl") as writer:
ExcelFormatter(styler, style_converter=custom_converter).write(
writer, sheet_name="custom"
)
with contextlib.closing(openpyxl.load_workbook(path)) as wb:
assert wb["custom"].cell(2, 2).font.color.value == "00111222"
@pytest.mark.single_cpu
@td.skip_if_not_us_locale
def test_styler_to_s3(s3_public_bucket, s3so):
# GH#46381
mock_bucket_name, target_file = s3_public_bucket.name, "test.xlsx"
df = DataFrame({"x": [1, 2, 3], "y": [2, 4, 6]})
styler = df.style.set_sticky(axis="index")
styler.to_excel(f"s3://{mock_bucket_name}/{target_file}", storage_options=s3so)
timeout = 5
while True:
if target_file in (obj.key for obj in s3_public_bucket.objects.all()):
break
time.sleep(0.1)
timeout -= 0.1
assert timeout > 0, "Timed out waiting for file to appear on moto"
result = read_excel(
f"s3://{mock_bucket_name}/{target_file}", index_col=0, storage_options=s3so
)
tm.assert_frame_equal(result, df)

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,76 @@
import io
import numpy as np
import pytest
from pandas.compat import is_platform_windows
import pandas as pd
import pandas._testing as tm
from pandas.io.excel import ExcelFile
from pandas.io.excel._base import inspect_excel_format
xlrd = pytest.importorskip("xlrd")
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
@pytest.fixture(params=[".xls"])
def read_ext_xlrd(request):
"""
Valid extensions for reading Excel files with xlrd.
Similar to read_ext, but excludes .ods, .xlsb, and for xlrd>2 .xlsx, .xlsm
"""
return request.param
def test_read_xlrd_book(read_ext_xlrd, datapath):
engine = "xlrd"
sheet_name = "Sheet1"
pth = datapath("io", "data", "excel", "test1.xls")
with xlrd.open_workbook(pth) as book:
with ExcelFile(book, engine=engine) as xl:
result = pd.read_excel(xl, sheet_name=sheet_name, index_col=0)
expected = pd.read_excel(
book, sheet_name=sheet_name, engine=engine, index_col=0
)
tm.assert_frame_equal(result, expected)
def test_read_xlsx_fails(datapath):
# GH 29375
from xlrd.biffh import XLRDError
path = datapath("io", "data", "excel", "test1.xlsx")
with pytest.raises(XLRDError, match="Excel xlsx file; not supported"):
pd.read_excel(path, engine="xlrd")
def test_nan_in_xls(datapath):
# GH 54564
path = datapath("io", "data", "excel", "test6.xls")
expected = pd.DataFrame({0: np.r_[0, 2].astype("int64"), 1: np.r_[1, np.nan]})
result = pd.read_excel(path, header=None)
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize(
"file_header",
[
b"\x09\x00\x04\x00\x07\x00\x10\x00",
b"\x09\x02\x06\x00\x00\x00\x10\x00",
b"\x09\x04\x06\x00\x00\x00\x10\x00",
b"\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1",
],
)
def test_read_old_xls_files(file_header):
# GH 41226
f = io.BytesIO(file_header)
assert inspect_excel_format(f) == "xls"

View File

@ -0,0 +1,86 @@
import contextlib
import pytest
from pandas.compat import is_platform_windows
from pandas import DataFrame
import pandas._testing as tm
from pandas.io.excel import ExcelWriter
xlsxwriter = pytest.importorskip("xlsxwriter")
if is_platform_windows():
pytestmark = pytest.mark.single_cpu
@pytest.fixture
def ext():
return ".xlsx"
def test_column_format(ext):
# Test that column formats are applied to cells. Test for issue #9167.
# Applicable to xlsxwriter only.
openpyxl = pytest.importorskip("openpyxl")
with tm.ensure_clean(ext) as path:
frame = DataFrame({"A": [123456, 123456], "B": [123456, 123456]})
with ExcelWriter(path) as writer:
frame.to_excel(writer)
# Add a number format to col B and ensure it is applied to cells.
num_format = "#,##0"
write_workbook = writer.book
write_worksheet = write_workbook.worksheets()[0]
col_format = write_workbook.add_format({"num_format": num_format})
write_worksheet.set_column("B:B", None, col_format)
with contextlib.closing(openpyxl.load_workbook(path)) as read_workbook:
try:
read_worksheet = read_workbook["Sheet1"]
except TypeError:
# compat
read_worksheet = read_workbook.get_sheet_by_name(name="Sheet1")
# Get the number format from the cell.
try:
cell = read_worksheet["B2"]
except TypeError:
# compat
cell = read_worksheet.cell("B2")
try:
read_num_format = cell.number_format
except AttributeError:
read_num_format = cell.style.number_format._format_code
assert read_num_format == num_format
def test_write_append_mode_raises(ext):
msg = "Append mode is not supported with xlsxwriter!"
with tm.ensure_clean(ext) as f:
with pytest.raises(ValueError, match=msg):
ExcelWriter(f, engine="xlsxwriter", mode="a")
@pytest.mark.parametrize("nan_inf_to_errors", [True, False])
def test_engine_kwargs(ext, nan_inf_to_errors):
# GH 42286
engine_kwargs = {"options": {"nan_inf_to_errors": nan_inf_to_errors}}
with tm.ensure_clean(ext) as f:
with ExcelWriter(f, engine="xlsxwriter", engine_kwargs=engine_kwargs) as writer:
assert writer.book.nan_inf_to_errors == nan_inf_to_errors
def test_book_and_sheets_consistent(ext):
# GH#45687 - Ensure sheets is updated if user modifies book
with tm.ensure_clean(ext) as f:
with ExcelWriter(f, engine="xlsxwriter") as writer:
assert writer.sheets == {}
sheet = writer.book.add_worksheet("test_name")
assert writer.sheets == {"test_name": sheet}