XMLUtil.py

from nltk.corpus import stopwords
import re
import xml.etree.ElementTree as ET
stop_words = set(stopwords.words("english"))

def compress_XML(input_file, output_file):
    """
    Processes the XML to reduces its length for saving context window quota.
    """
    with open(input_file, "r", encoding="utf-8") as input_file:
        input_text = input_file.read()

    def process_text(text):
        text = re.sub(r"[\n\r]+", "\n", text)
        text = re.sub(r"[^a-zA-Z0-9\s_.,!?:;@#$%^&*()+\-=[\]{}|\\<>`~'\"/]+", "", text)
        text = re.sub(r"\s+", " ", text)
        text = text.lower()
        words = text.split()
        words = [word for word in words if word not in stop_words]
        return " ".join(words)

    try:
        root = ET.fromstring(input_text)
        for elem in root.iter():
            if elem.text:
                elem.text = process_text(elem.text)
            if elem.tail:
                elem.tail = process_text(elem.tail)

        tree = ET.ElementTree(root)
        tree.write(output_file, encoding="utf-8", xml_declaration=True)

    except ET.ParseError:
        processed_text = process_text(input_text)
        with open(output_file, "w", encoding="utf-8") as out_file:
            out_file.write(processed_text)
        print("Parsing failed, Text preprocessing finished but without XML structure.")