Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SIMSBIOHUB-8-2: Update duplicate key validation rule to account for empty cells. #1037

Merged
merged 7 commits into from
May 29, 2023
Merged

SIMSBIOHUB-8-2: Update duplicate key validation rule to account for empty cells. #1037

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
4bc0001
Update duplicate key validation rule to account for empty cells.
NickPhura May 26, 2023
0693afa
Nit: cleanup filter
NickPhura May 29, 2023
a027b6f
Update JSDoc
NickPhura May 29, 2023
77a9ada
nit: test name
NickPhura May 29, 2023
e13c458
nit: doc
NickPhura May 29, 2023
68e91d5
Fix bad test nesting
NickPhura May 29, 2023
bbdd537
Fix tests
NickPhura May 29, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
203 changes: 122 additions & 81 deletions api/src/utils/media/csv/validation/csv-row-validator.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -605,87 +605,128 @@ describe('getValidFormatFieldsValidator', () => {
}
]);
});
});

describe('getUniqueColumnsValidator', () => {
it('adds no errors when no config is supplied', () => {
const validator = getUniqueColumnsValidator();
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when no columns are specified in config', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when specified key column is missing from the worksheet', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when key cells are empty', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[, , 3],
[, , 3],
[, , 3]
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when all keys specified are unique', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[1, 2, 3],
[2, 2, 3],
[3, 2, 3]
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds errors when not all keys are unique', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[1, 2, 3],
[2, 2, 3], // produces key: `2, 2`
[2, 2, 3] // produces duplicate key: `2, 2`
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.not.be.empty;
expect(csvWorkSheet.csvValidation.rowErrors[0].errorCode).to.be.eql(SUBMISSION_MESSAGE_TYPE.NON_UNIQUE_KEY);
});

it('adds errors when not all keys are unique and some columns are empty', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[1, , 3],
[, 2, 3], // produces key: `2`
[2, , 3] // produces duplicate key: `2`
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

describe('getValidFormatFieldsValidator', () => {
it('adds no errors when no config is supplied', () => {
const validator = getUniqueColumnsValidator();
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when no columns are specified in config', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when specified key column is missing from the worksheet', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([['Header1'], ['stuff']]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds no errors when all keys specified are unique', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[1, 2, 3],
[2, 2, 3],
[3, 2, 3]
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.be.empty;
});

it('adds errors when not all keys are unique', () => {
const config: FileColumnUniqueValidatorConfig = {
file_column_unique_validator: {
column_names: ['Header1', 'Header2']
}
};
const validator = getUniqueColumnsValidator(config);
const worksheet = xlsx.utils.aoa_to_sheet([
['Header1', 'Header2', 'Header3'],
[1, 2, 3],
[2, 2, 3],
[2, 2, 3]
]);
const csvWorkSheet = new CSVWorksheet('Sheet', worksheet);

validator(csvWorkSheet);

expect(csvWorkSheet.csvValidation.rowErrors).to.not.be.empty;
expect(csvWorkSheet.csvValidation.rowErrors[0].errorCode).to.be.eql(SUBMISSION_MESSAGE_TYPE.NON_UNIQUE_KEY);
});
expect(csvWorkSheet.csvValidation.rowErrors).to.not.be.empty;
expect(csvWorkSheet.csvValidation.rowErrors[0].errorCode).to.be.eql(SUBMISSION_MESSAGE_TYPE.NON_UNIQUE_KEY);
});
});
44 changes: 41 additions & 3 deletions api/src/utils/media/csv/validation/csv-row-validator.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,6 +351,35 @@ export type FileColumnUniqueValidatorConfig = {
};
};

/**
* Checks for duplicate key values between rows, an adds an error for each duplicate found.
*
* Note: A key is one or more columns combined into a single string.
* Note: Empty cells are ignored when performing this check.
*
* @example
* // Valid
* | Col1 | Col2 |
* |------|------|
* | A | B | // key = 'A, B'
* | A | | // key = 'A'
* | B | A | // key = 'B, A'
*
* // Invalid
* | Col1 | Col2 |
* |------|------|
* | A | B | // key = 'A, B'
* | A | B | // key = 'A, B'
*
* // Invalid
* | Col1 | Col2 |
* |------|------|
* | A | | // key = 'A'
* | | A | // key = 'A'
*
* @param {FileColumnUniqueValidatorConfig} [config]
* @return {*} {CSVValidator}
*/
export const getUniqueColumnsValidator = (config?: FileColumnUniqueValidatorConfig): CSVValidator => {
return (csvWorksheet) => {
if (!config) {
Expand All @@ -377,8 +406,16 @@ export const getUniqueColumnsValidator = (config?: FileColumnUniqueValidatorConf

rows.forEach((row, rowIndex) => {
const key = config.file_column_unique_validator.column_names
.map((columnIndex) => `${row[columnIndex] || ''}`.trim().toLowerCase())
.map((columnName) => `${row[columnName] || ''}`.trim().toLowerCase())
.filter(Boolean)
.join(', ');

if (!key) {
// If key is empty, ignore this check.
// It is the job of a separate validation rule to ensure non-empty (required) cells
return;
}

NickPhura marked this conversation as resolved.
Show resolved Hide resolved
// check if key exists already
if (!keySet.has(key)) {
keySet.add(key);
Expand All @@ -389,15 +426,16 @@ export const getUniqueColumnsValidator = (config?: FileColumnUniqueValidatorConf
errorCode: SUBMISSION_MESSAGE_TYPE.NON_UNIQUE_KEY,
message: `Row ${
rowIndex + 2
} has duplicate values ${key} to another row. The combination of values in columns: ${config.file_column_unique_validator.column_names.join(
} has duplicate values ${key} to another row. The combination of values in columns: ${config.file_column_unique_validator.column_names.join(
', '
)} must be unique across rows. Details: `,
)} must be unique across rows. Details: `,
col: key,
row: rowIndex + 2
}
]);
}
});

return csvWorksheet;
};
};
2 changes: 1 addition & 1 deletion api/src/utils/media/xlsx/transformation/xlsx-transform.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,7 @@ export class XLSXTransform {
.map((columnName: string) => {
return RowObject[columnName];
})
.filter((value) => !isNaN || value)
.filter(Boolean)
.join(':');

return primaryKey;
Expand Down