nist control parser

control-parser.py

import re

# Input text (NIST 800-53 control AC-2 example)
nist_control_text = """
a. Identifies and selects the following types of information system accounts to support organizational missions/business functions: [Assignment: organization-defined information system account types];
b. Assigns account managers for information system accounts;
c. Establishes conditions for group and role membership;
d. Specifies authorized users of the information system, group and role membership, and access authorizations (i.e., privileges) and other attributes (as required) for each account;
e. Requires approvals by [Assignment: organization-defined personnel or roles] for requests to create information system accounts;
f. Creates, enables, modifies, disables, and removes information system accounts in accordance with [Assignment: organization-defined procedures or conditions];
g. Monitors the use of information system accounts;
h. Notifies account managers:
        1. When accounts are no longer required;
        2. When users are terminated or transferred; and
        3. When individual information system usage or need-to-know changes;
i. Authorizes access to the information system based on:
        1. A valid access authorization;
        2. Intended system usage; and
        3. Other attributes as required by the organization or associated missions/business functions;
j. Reviews accounts for compliance with account management requirements [Assignment: organization-defined frequency]; and
k. Establishes a process for reissuing shared/group account credentials (if deployed) when individuals are removed from the group.
"""

# Function to convert text into structured questions
def generate_questions(control_id, text):
    questions = []
    lines = text.strip().split("\n")
    
    for line in lines:
        # Match sub-items (e.g., "a.", "b.", "h.1", etc.)
        match = re.match(r"([a-z]+|\d+)\.\s*(.*)", line.strip())
        if match:
            key, value = match.groups()
            formatted_question = f"{control_id}.{key} {value}"
            questions.append(formatted_question)
        else:
            # Handle sub-items under main items (like h.1, h.2, etc.)
            if questions and line.strip():
                last_question = questions.pop()
                last_key = last_question.split(" ")[0]
                formatted_question = f"{last_key}.{line.strip()}"
                questions.append(formatted_question)
            else:
                continue

    return questions

# Generate formatted questions for AC-2
control_id = "AC-2"
questions = generate_questions(control_id, nist_control_text)

# Print formatted output
for q in questions:
    print(q)