check_cfr.py

import os
import sys

# Requires LXML. See: https://lxml.de/installation.html
from lxml import etree as ET

def check_file(path):
    print(f'Checking file at path: {path}')
    huge_tree_parser = ET.XMLParser(huge_tree=True)
    tree = ET.parse(path, huge_tree_parser)
    root = tree.getroot()

    for section in root.findall('.//SECTION'):
        sect_no = section.find('SECTNO').text
        internal_sections = list(section.findall('.//SECTION'))
        mismatched_sections = []
        for internal_section in internal_sections:
            internal_sect_no = internal_section.find('SECTNO').text
            if internal_sect_no != sect_no:
                mismatched_sections.append(internal_sect_no)
        if mismatched_sections:
            print(f'`{sect_no}` contains mismatched sections `{",".join(mismatched_sections)}`')
    print(f'Check complete: {path}')

if __name__ == '__main__':
    path = os.path.expanduser(sys.argv[1])
    if os.path.isfile(path):
        check_file(path)
    else:
        for dirpath, _, file_names in os.walk(path):
            for f in file_names:
                if f.endswith(".xml"):
                    check_file(os.path.join(dirpath, f))