analyzeDescriptions.py

import json
import sys
import re

def check_descriptions(description, path, issues):
    rfc2119_words = {"MUST", "SHALL", "REQUIRED", "SHOULD", "MAY", "MUST NOT", "SHALL NOT", "SHOULD NOT", "MAY NOT"}

    if isinstance(description, str):
        # Check for RFC-2119 words
        for word in rfc2119_words:
            if re.search(rf'\b{word}\b', description):
                issues.append(f'Description at path {path} contains RFC-2119 word: {word}')

        # Check if description starts with an uppercase letter
        if not description[0].isupper():
            issues.append(f'Description at path {path} does not start with an uppercase letter.')

        # Check if description ends with a single period
        if not description.endswith('.'):
            issues.append(f'Description at path {path} does not end with a single period.')

        # Check if description contains multiple consecutive periods
        if '..' in description:
            issues.append(f'Description at path {path} contains multiple consecutive periods.')

        # Split sentences by period followed by a space
        sentences = re.split(r'\.\s', description)

        # Check for exactly one space between sentences for descriptions with more than one sentence
        if len(sentences) > 1:
            matches = re.findall(r'\.\s{2,}', description)
            if matches:
                issues.append(f'Description at path {path} has more than one space after a period before the next sentence.')
            matches = re.findall(r'\.[^\s]', description)
            if matches:
                issues.append(f'Description at path {path} does not have one space after a period before the next sentence.')

def traverse_schema(schema, path, issues):
    if isinstance(schema, dict):
        for key, value in schema.items():
            if key == 'description':
                check_descriptions(value, path + 'description', issues)
            else:
                traverse_schema(value, path + key + '.', issues)
    elif isinstance(schema, list):
        for index, item in enumerate(schema):
            traverse_schema(item, path + f'{index}.', issues)

def main():
    if len(sys.argv) != 2:
        print("Usage: python analyzeDescriptions.py <path_to_schema>")
        sys.exit(1)

    schema_file_path = sys.argv[1]

    try:
        with open(schema_file_path, 'r') as file:
            schema = json.load(file)
    except FileNotFoundError:
        print(f"Error: File not found: {schema_file_path}")
        sys.exit(1)
    except json.JSONDecodeError:
        print(f"Error: Failed to parse JSON from file: {schema_file_path}")
        sys.exit(1)

    issues = []
    traverse_schema(schema, '', issues)

    if issues:
        print("Issues found:")
        for issue in issues:
            print(issue)
        sys.exit(1)
    else:
        print("All descriptions are correctly formatted.")
        sys.exit(0)

if __name__ == "__main__":
    main()