diff --git a/favicon.ico b/favicon.ico new file mode 100755 index 0000000..9e74d3e Binary files /dev/null and b/favicon.ico differ diff --git a/index.html b/index.html index f2592a0..7ce9dbc 100644 --- a/index.html +++ b/index.html @@ -4,6 +4,15 @@ SheetSense Analyzer + + +
-

SheetSense Analyzer

+

SheetSense Analyzer

+

Excel workbook validation engine that detects quality issues, ensures consistency, and makes your spreadsheets bulletproof.

-

Drop your Excel file here or click to choose

+

Drop your Excel (xls or xlsx) file here or click to choose

+ +
+

Test Files

+
+
+
Circular Reference Tests
+ + + +
+
+
Data Quality Tests
+ +
+
+
Formula Errors
+ +
+
+
Hidden Content
+ + + +
+
+
+ -
+

- View on GitHub | - Created by @asadbek064 + View on GitHub | + Created by @asadbek064 + mylinx.cc/asad

+ - \ No newline at end of file + diff --git a/test_files/circular_reference/direct_circular.xlsx b/test_files/circular_reference/direct_circular.xlsx new file mode 100644 index 0000000..1b8ce97 Binary files /dev/null and b/test_files/circular_reference/direct_circular.xlsx differ diff --git a/test_files/circular_reference/gen_test.py b/test_files/circular_reference/gen_test.py new file mode 100644 index 0000000..641f71e --- /dev/null +++ b/test_files/circular_reference/gen_test.py @@ -0,0 +1,77 @@ +import openpyxl +from openpyxl import Workbook + +def create_direct_circular_reference(): + wb = Workbook() + ws = wb.active + ws.title = "Sheet1" + + # Create direct circular reference + cell = ws['A1'] + cell.value = '=A1+1' # This sets the formula + cell.data_type = 'f' # Explicitly set as formula type + + # Save with keep_vba=True to preserve formulas + wb.save('direct_circular.xlsx') + print("Created direct_circular.xlsx") + +def create_indirect_circular_reference(): + wb = Workbook() + ws = wb.active + ws.title = "Sheet1" + + # Create indirect circular reference chain + ws['A1'].value = '=B1+1' + ws['A1'].data_type = 'f' + ws['B1'].value = '=C1+1' + ws['B1'].data_type = 'f' + ws['C1'].value = '=A1+1' + ws['C1'].data_type = 'f' + + wb.save('indirect_circular.xlsx') + print("Created indirect_circular.xlsx") + +def create_valid_cross_reference(): + wb = Workbook() + ws = wb.active + ws.title = "Sheet1" + + # Create valid cross-reference + ws['A1'].value = 1 # Numeric value + ws['A1'].data_type = 'n' + ws['B1'].value = '=A1*2' # Formula referencing A1 + ws['B1'].data_type = 'f' + + wb.save('valid_cross_reference.xlsx') + print("Created valid_cross_reference.xlsx") + +def verify_formulas(): + """Verify the formulas were saved correctly""" + for filename in ['direct_circular.xlsx', 'indirect_circular.xlsx', 'valid_cross_reference.xlsx']: + wb = openpyxl.load_workbook(f'{filename}', data_only=False) + ws = wb.active + print(f"\nVerifying {filename}:") + for row in ws.iter_rows(): + for cell in row: + if cell.value and str(cell.value).startswith('='): + print(f"Cell {cell.coordinate}: Formula = {cell.value}") + else: + print(f"Cell {cell.coordinate}: Value = {cell.value}") + +def main(): + print("Generating Excel test files...") + + try: + create_direct_circular_reference() + create_indirect_circular_reference() + create_valid_cross_reference() + print("\nAll files generated successfully!") + + print("\nVerifying formula storage:") + verify_formulas() + + except Exception as e: + print(f"Error generating files: {str(e)}") + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/test_files/circular_reference/indirect_circular.xlsx b/test_files/circular_reference/indirect_circular.xlsx new file mode 100644 index 0000000..9492c80 Binary files /dev/null and b/test_files/circular_reference/indirect_circular.xlsx differ diff --git a/test_files/circular_reference/valid_cross_reference.xlsx b/test_files/circular_reference/valid_cross_reference.xlsx new file mode 100644 index 0000000..0202f67 Binary files /dev/null and b/test_files/circular_reference/valid_cross_reference.xlsx differ diff --git a/test_files/data_quality/data_quality_issues.xlsx b/test_files/data_quality/data_quality_issues.xlsx new file mode 100644 index 0000000..0ad0872 Binary files /dev/null and b/test_files/data_quality/data_quality_issues.xlsx differ diff --git a/test_files/data_quality/gen_test.py b/test_files/data_quality/gen_test.py new file mode 100644 index 0000000..3f6abc1 --- /dev/null +++ b/test_files/data_quality/gen_test.py @@ -0,0 +1,15 @@ +import pandas as pd +import numpy as np + +# Data quality issues dataset +data = { + 'Product_ID': ['A1', 'B2', 123, 'D4', None, 'F6', 'G7', np.nan, 'I9', 'J10'], + 'Stock_Count': [100, '200', 'invalid', 400, -999999, 600, '7OO', '800 ', None, 1000], + 'Price': [10.999, '20.00', 30, '40.0000', 50.5, '60', None, '80.0', 90.99999, '100.'], + 'Last_Updated': [None, '2024-13-01', '01/01/2024', '2024.01.01', 'yesterday', + '01-01-2024 ', '2024/01/01', '1st Jan 2024', pd.Timestamp.now(), '2024-01-01'] +} + +df = pd.DataFrame(data) +df.to_excel('data_quality_issues.xlsx', index=False) + diff --git a/test_files/formatting_issue/formatting_issues.xlsx b/test_files/formatting_issue/formatting_issues.xlsx new file mode 100644 index 0000000..3da2e7d Binary files /dev/null and b/test_files/formatting_issue/formatting_issues.xlsx differ diff --git a/test_files/formatting_issue/gen_test.py b/test_files/formatting_issue/gen_test.py new file mode 100644 index 0000000..f02f06a --- /dev/null +++ b/test_files/formatting_issue/gen_test.py @@ -0,0 +1,29 @@ +import pandas as pd + +data = { + 'Employee': [' John Doe', 'Jane Smith ', ' Bob Jones', 'Alice Brown ', 'Tom Wilson'], + 'Salary': ['$50,000', '60000', '$70,000.00', '80000.0', '90,000'], + 'Hire_Date': ['01-Jan-2024', '2024/01/02', '03.01.2024', 'Jan 4, 2024', '2024-01-05'], + 'Department': ['IT ', ' HR', 'Finance', ' Marketing ', 'Sales'], + 'Performance': ['95.00%', '87.5', '92', '88.75%', '90.0%'] +} + +df = pd.DataFrame(data) + +writer = pd.ExcelWriter('formatting_issues.xlsx', engine='xlsxwriter') +df.to_excel(writer, index=False) +workbook = writer.book +worksheet = writer.sheets['Sheet1'] + +# Add inconsistent formatting +formats = [ + workbook.add_format({'num_format': '#,##0'}), + workbook.add_format({'num_format': '0.00'}), + workbook.add_format({'num_format': '$#,##0.00'}), + workbook.add_format({'num_format': '0%'}) +] + +for col, fmt in enumerate(formats): + worksheet.set_column(col, col, 15, fmt) + +writer.close() diff --git a/test_files/formula_errors/formula_errors.xlsx b/test_files/formula_errors/formula_errors.xlsx new file mode 100644 index 0000000..5dffacd Binary files /dev/null and b/test_files/formula_errors/formula_errors.xlsx differ diff --git a/test_files/formula_errors/gen_test.py b/test_files/formula_errors/gen_test.py new file mode 100644 index 0000000..e9311b8 --- /dev/null +++ b/test_files/formula_errors/gen_test.py @@ -0,0 +1,18 @@ +import pandas as pd +import openpyxl + +wb = openpyxl.Workbook() +ws = wb.active + +formulas = [ + ['=A1/0', '=B1*C1', '=UNKNOWNFUNC()', '=D1+E1'], + ['=VLOOKUP("x",A1:A2,3,FALSE)', '=SUM(#REF!)', '=VALUE("abc")', '=NULL'], + ['=1/0', '=NA()', '=NAME?', '=VALUE!'], + ['=IF(A1="",,)', '=INDIRECT("invalid")', '=1+"text"', '=SUM()'] +] + +for row_idx, row in enumerate(formulas, start=1): + for col_idx, formula in enumerate(row, start=1): + ws.cell(row=row_idx, column=col_idx, value=formula) + +wb.save('formula_errors.xlsx') diff --git a/test_files/gen_test.py b/test_files/gen_test.py new file mode 100644 index 0000000..9283d47 --- /dev/null +++ b/test_files/gen_test.py @@ -0,0 +1,95 @@ +import pandas as pd +import numpy as np +from datetime import datetime, timedelta + +# Create test data +data = { + 'ID': [1, 2, 3, '4', 5, 6, 7, 8, 9, 10], + 'Date': [ + '2024-01-01', + '01/02/2024', + 'Invalid Date', + '2024-01-04', + '05-01-2024', + '2024/01/06', + datetime.now(), + '2024-01-08 ', # Extra space + '2024-01-09', + None + ], + 'Amount': [ + 1000.50, + '1,200.75', + 'abc', + -999999999, # Outlier + 1500.0000, # Extra decimals + 1600.50, + None, + ' 1800.25 ', # Leading/trailing spaces + 1900.50, + 2000 + ], + 'Category': [ + 'Sales', + 'Sales ', # Trailing space + 'SALES', # Inconsistent case + 'Marketing', + 'Marketing', # Duplicate + None, + 'Finance', + 'HR', + 'HR', + '' # Empty string + ], + 'Calculation': [ + '=A2/0', # #DIV/0! + '=VLOOKUP("missing",A1:B1,2)', # #N/A + '=INVALID_FUNCTION()', # #NAME? + '=A1', # Valid + None, + '=REF!', # #REF! + '=VALUE("abc")', # #VALUE! + '=1+1', + '=SUM()', # Empty sum + '=NULL' # #NULL! + ], + 'Percentage': [ + '50%', + '0.75', # Inconsistent format + '80.00%', + '.90', # Missing leading zero + '100%', + None, + '120%', # Outlier + '60.5%', + '70%', + '65' # Missing % symbol + ] +} + +df = pd.DataFrame(data) + +# Add duplicate column +df['Category_2'] = df['Category'] + +# Create Excel writer +writer = pd.ExcelWriter('test_data.xlsx', engine='xlsxwriter') + +# Write visible sheet +df.to_excel(writer, sheet_name='Main', index=False) + +# Write hidden sheet with duplicates +df.to_excel(writer, sheet_name='Hidden', index=False) + +# Get workbook and worksheet +workbook = writer.book +worksheet = writer.sheets['Main'] + +# Add some formatting inconsistencies +format1 = workbook.add_format({'num_format': '#,##0.00'}) +format2 = workbook.add_format({'num_format': '0.0'}) + +worksheet.set_column('C:C', 15, format1) +worksheet.write('C4', 1234.56, format2) + +writer.close() \ No newline at end of file diff --git a/test_files/hidden_cell/consecutive_hidden_rows.xlsx b/test_files/hidden_cell/consecutive_hidden_rows.xlsx new file mode 100644 index 0000000..092bf39 Binary files /dev/null and b/test_files/hidden_cell/consecutive_hidden_rows.xlsx differ diff --git a/test_files/hidden_cell/gen_test.py b/test_files/hidden_cell/gen_test.py new file mode 100644 index 0000000..93c71c0 --- /dev/null +++ b/test_files/hidden_cell/gen_test.py @@ -0,0 +1,62 @@ +import openpyxl +from openpyxl import Workbook +from openpyxl.styles import Protection +from openpyxl.worksheet.dimensions import DimensionHolder, ColumnDimension, RowDimension + +def create_hidden_cells_test(): + wb = Workbook() + ws = wb.active + + ws['A1'] = 'Visible' + ws['B1'] = 'Hidden' + + ws.protection.sheet = True + ws['B1'].protection = Protection(hidden=True) + + return wb + +def create_hidden_rows_columns_test(): + wb = Workbook() + ws = wb.active + + ws['A1'] = 'Content' + ws['B2'] = 'More' + ws['C3'] = 'Data' + + # Handle column dimensions + col_dims = DimensionHolder(worksheet=ws) + col_dims['A'] = ColumnDimension(ws, index='A', hidden=True) + col_dims['C'] = ColumnDimension(ws, index='C', hidden=True) + ws.column_dimensions = col_dims + + # Handle row dimensions separately + for row in [1, 3]: + ws.row_dimensions[row] = RowDimension(ws, index=row, hidden=True) + + return wb + +def create_consecutive_hidden_rows_test(): + wb = Workbook() + ws = wb.active + + for i in range(1, 6): + ws[f'A{i}'] = f'Row {i}' + + for row in [1, 2, 4, 5]: + ws.row_dimensions[row] = RowDimension(ws, index=row, hidden=True) + + return wb + +def main(): + test_files = { + 'hidden_cells.xlsx': create_hidden_cells_test(), + 'hidden_rows_columns.xlsx': create_hidden_rows_columns_test(), + 'consecutive_hidden_rows.xlsx': create_consecutive_hidden_rows_test() + } + + for filename, wb in test_files.items(): + wb.save(filename) + print(f"Created {filename}") + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/test_files/hidden_cell/hidden_cells.xlsx b/test_files/hidden_cell/hidden_cells.xlsx new file mode 100644 index 0000000..5b6ef45 Binary files /dev/null and b/test_files/hidden_cell/hidden_cells.xlsx differ diff --git a/test_files/hidden_cell/hidden_rows_columns.xlsx b/test_files/hidden_cell/hidden_rows_columns.xlsx new file mode 100644 index 0000000..4c5442d Binary files /dev/null and b/test_files/hidden_cell/hidden_rows_columns.xlsx differ diff --git a/test_files/test_data.xlsx b/test_files/test_data.xlsx new file mode 100644 index 0000000..f0a6f90 Binary files /dev/null and b/test_files/test_data.xlsx differ