176 lines
6.9 KiB
Python
176 lines
6.9 KiB
Python
import pandas as pd
|
|
import openpyxl
|
|
from openpyxl import Workbook
|
|
from openpyxl.worksheet.worksheet import Worksheet
|
|
|
|
from .utils import load_charts, load_sparklines
|
|
|
|
from typing import Dict, List
|
|
from typing import Any
|
|
|
|
|
|
def compare_table(actual, expected):
|
|
df1 = pd.read_excel(expected)
|
|
df2 = pd.read_excel(actual)
|
|
|
|
# Compare the DataFrames
|
|
return 1 if df1.equals(df2) else 0
|
|
|
|
|
|
def compare_with_sparklines(actual: str, expected: str) -> float:
|
|
df1 = pd.read_excel(actual)
|
|
df2 = pd.read_excel(expected)
|
|
normal_content_metric: bool = df1.equals(df2)
|
|
print("Normal Contents Metric: {:}".format(normal_content_metric))
|
|
|
|
sp1 = load_sparklines(actual)
|
|
sp2 = load_sparklines(expected)
|
|
sparkline_metric: bool = sp1 == sp2
|
|
print("Sparkline Metric: {:}".format(sparkline_metric))
|
|
|
|
return float(normal_content_metric and sparkline_metric)
|
|
|
|
|
|
def compare_with_charts(actual: str, expected: str, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): path to result xlsx
|
|
expected (str): path to gold xlsx
|
|
options (Dict[str, List[str]]): dict like {"chart_props": list of str}
|
|
giving the concerned chart properties
|
|
"""
|
|
|
|
df1 = pd.read_excel(actual)
|
|
df2 = pd.read_excel(expected)
|
|
normal_content_metric: bool = df1.equals(df2)
|
|
print("Normal Contents Metric: {:}".format(normal_content_metric))
|
|
|
|
charts1 = load_charts(actual, **options)
|
|
charts2 = load_charts(expected, **options)
|
|
chart_metric: bool = charts1 == charts2
|
|
print("Chart Metric: {:}".format(chart_metric))
|
|
|
|
return float(normal_content_metric and chart_metric)
|
|
|
|
def compare_with_formats(actual: str, expected: str) -> float:
|
|
df1 = pd.read_excel(actual)
|
|
df2 = pd.read_excel(expected)
|
|
normal_content_metric: bool = df1.equals(df2)
|
|
print("Normal Contents Metric: {:}".format(normal_content_metric))
|
|
|
|
workbook1: Workbook = openpyxl.load_workbook(actual)
|
|
number_formats1: List[str] = [ c.number_format.lower()\
|
|
for col in workbook1.active.iter_cols()\
|
|
for c in col\
|
|
if c.data_type=="n"
|
|
]
|
|
workbook2: Workbook = openpyxl.load_workbook(expected)
|
|
number_formats2: List[str] = [ c.number_format.lower()\
|
|
for col in workbook2.active.iter_cols()\
|
|
for c in col\
|
|
if c.data_type=="n"
|
|
]
|
|
number_format_metric: bool = number_formats1==number_formats2
|
|
print("Number Format Metric: {:}".format(number_format_metric))
|
|
|
|
return float(normal_content_metric & number_format_metric)
|
|
|
|
def check_sheet_list(result: str, rules: List[Dict[str, Any]]) -> float:
|
|
# workbook: Workbook = openpyxl.load_workbook(filename=result)
|
|
workbook = pd.ExcelFile(result)
|
|
worksheet_names: List[str] = workbook.sheet_names
|
|
|
|
passes = True
|
|
for r in rules:
|
|
if r["type"] == "sheet_name":
|
|
expected_name: str = worksheet_names[r["sheet_idx"]]
|
|
actual_name: str = r["sheet_name"]
|
|
metric: bool = expected_name == actual_name
|
|
print("Assertion: {:d}.{:} is {:} - {:}".format(r["sheet_idx"], actual_name, expected_name, metric))
|
|
passes = passes and metric
|
|
elif r["type"] == "sheet_data":
|
|
if isinstance(r["sheet_idx0"], int):
|
|
df1: pd.DataFrame = pd.read_excel(workbook, r["sheet_idx0"])
|
|
else:
|
|
file_name: str
|
|
sheet_idx: str
|
|
file_name, sheet_idx = r["sheet_idx0"].rsplit("@", maxsplit=1)
|
|
sheet_idx: int = int(sheet_idx)
|
|
df1: pd.DataFrame = pd.read_excel(file_name, sheet_idx)
|
|
if isinstance(r["sheet_idx1"], int):
|
|
df2: pd.DataFrame = pd.read_excel(workbook, r["sheet_idx1"])
|
|
else:
|
|
file_name: str
|
|
sheet_idx: str
|
|
file_name, sheet_idx = r["sheet_idx1"].rsplit("@", maxsplit=1)
|
|
sheet_idx: int = int(sheet_idx)
|
|
df2: pd.DataFrame = pd.read_excel(file_name, sheet_idx)
|
|
metric: bool = df1.equals(df2)
|
|
print("Assertion: {:} == {:} - {:}".format(r["sheet_idx0"], r["sheet_idx1"], metric))
|
|
passes = passes and metric
|
|
else:
|
|
raise NotImplementedError("Unimplemented sheet check: {:}".format(r["type"]))
|
|
|
|
return float(passes)
|
|
|
|
|
|
def check_xlsx_freeze(result: str, rules: Dict[str, str]) -> float:
|
|
worksheet: Worksheet = openpyxl.load_workbook(filename=result).active
|
|
return float(worksheet.freeze_panes == rules["position"])
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# path1 = ""
|
|
# path2 = ""
|
|
# print(compare_table(path1, path2))
|
|
|
|
# path1 = "../../../../../任务数据/LibreOffice Calc/OrderId_Month_Chart_gold.xlsx"
|
|
# path2 = "../../../../../任务数据/LibreOffice Calc/OrderId_Month_Chart.xlsx"
|
|
# print(compare_with_sparklines(path1, path2))
|
|
|
|
# path1 = "../../../../../任务数据/LibreOffice Calc/Freeze_row_column_gold.xlsx"
|
|
# path2 = "../../../../../任务数据/LibreOffice Calc/Freeze_row_column.xlsx"
|
|
# workbook1: Workbook = openpyxl.load_workbook(filename=path1)
|
|
# worksheet1: Worksheet = workbook1.active
|
|
# print(worksheet1.freeze_panes)
|
|
# workbook2: Workbook = openpyxl.load_workbook(filename=path2)
|
|
# worksheet2: Worksheet = workbook2.active
|
|
# print(worksheet2.freeze_panes)
|
|
# rule = {"position": "C6"}
|
|
# print(check_xlsx_freeze(path1, rule))
|
|
|
|
# path1 = "../../../../../任务数据/LibreOffice Calc/copy_sheet_insert_gold.xlsx"
|
|
# rule = [ { "type": "sheet_name"
|
|
# , "sheet_idx": 0
|
|
# , "sheet_name": "Sheet1"
|
|
# }
|
|
# , { "type": "sheet_data"
|
|
# , "sheet_idx0": "../../../../../任务数据/LibreOffice Calc/copy_sheet_insert.xlsx@0"
|
|
# , "sheet_idx1": 1
|
|
# }
|
|
# , { "type": "sheet_name"
|
|
# , "sheet_idx": 2
|
|
# , "sheet_name": "Sheet2"
|
|
# }
|
|
# ]
|
|
# print(check_sheet_list(path1, rule))
|
|
|
|
#path1 = "../../../../../任务数据/LibreOffice Calc/Create_column_charts_using_statistics_gold.xlsx"
|
|
#path2 = "../../../../../任务数据/LibreOffice Calc/Create_column_charts_using_statistics_gold2.xlsx"
|
|
#print(compare_with_charts(path1, path2, chart_props=["type", "direction"]))
|
|
|
|
path1 = "../../任务数据/LibreOffice Calc/Represent_in_millions_billions_gold.xlsx"
|
|
path2 = "../../任务数据/LibreOffice Calc/Represent_in_millions_billions_gold3.xlsx"
|
|
#workbook1: Workbook = openpyxl.load_workbook(filename=path1)
|
|
#worksheet1: Worksheet = workbook1.active
|
|
#
|
|
#import itertools
|
|
#for col, r in itertools.product( ['A', 'B', 'C']
|
|
#, range(1, 9)
|
|
#):
|
|
#position: str = "{:}{:d}".format(col, r)
|
|
#print(worksheet1[position])
|
|
#print(worksheet1[position].value)
|
|
#print(worksheet1[position].number_format)
|
|
print(compare_with_formats(path1, path2))
|