Build a CSV validator tool

Here’s a complete Python-based CSV validator tool that checks the structure and content of CSV files. It validates:

• File existence and format

• Header consistency

• Row length uniformity

• Optional: Value type checks (e.g., integers, emails)

• Custom rules (e.g., required columns)

python
CopyEdit
import csv
import os
import re

class CSVValidator:
    def __init__(self, filepath, required_columns=None, column_types=None):
        self.filepath = filepath
        self.required_columns = required_columns or []
        self.column_types = column_types or {}
        self.errors = []

    def validate(self):
        if not os.path.isfile(self.filepath):
            self.errors.append(f"File not found: {self.filepath}")
            return False

        if not self.filepath.lower().endswith('.csv'):
            self.errors.append("Invalid file format. Only CSV files are allowed.")
            return False

        try:
            with open(self.filepath, newline='', encoding='utf-8') as csvfile:
                reader = csv.reader(csvfile)
                headers = next(reader, None)
                if headers is None:
                    self.errors.append("CSV file is empty.")
                    return False

                self._validate_headers(headers)

                for i, row in enumerate(reader, start=2):  # Start from 2 to account for header
                    self._validate_row_length(headers, row, i)
                    self._validate_column_types(headers, row, i)

        except Exception as e:
            self.errors.append(f"Error reading CSV file: {e}")
            return False

        return len(self.errors) == 0

    def _validate_headers(self, headers):
        missing = [col for col in self.required_columns if col not in headers]
        if missing:
            self.errors.append(f"Missing required columns: {', '.join(missing)}")

    def _validate_row_length(self, headers, row, line_num):
        if len(row) != len(headers):
            self.errors.append(f"Line {line_num}: Expected {len(headers)} values, found {len(row)}.")

    def _validate_column_types(self, headers, row, line_num):
        for i, header in enumerate(headers):
            expected_type = self.column_types.get(header)
            if not expected_type:
                continue
            value = row[i].strip()
            if expected_type == "int":
                if not value.isdigit():
                    self.errors.append(f"Line {line_num}, column '{header}': Expected integer, got '{value}'.")
            elif expected_type == "email":
                if not re.match(r"[^@]+@[^@]+.[^@]+", value):
                    self.errors.append(f"Line {line_num}, column '{header}': Invalid email '{value}'.")

    def get_errors(self):
        return self.errors


# Example Usage
if __name__ == "__main__":
    filepath = "example.csv"
    required_columns = ["Name", "Email", "Age"]
    column_types = {
        "Email": "email",
        "Age": "int"
    }

    validator = CSVValidator(filepath, required_columns, column_types)
    if validator.validate():
        print("CSV is valid.")
    else:
        print("CSV validation failed with the following errors:")
        for error in validator.get_errors():
            print(" -", error)

Features to Extend Later:

• Configurable delimiter

• Date/time format validation

• Support for quoting and escaping rules

• Web-based frontend (e.g., Flask or Streamlit)

Let me know if you want this turned into a GUI tool or web app.