Update app.py

app.py

@@ -4,7 +4,8 @@ import os
 import base64
 import glob
 import json
-from xml.etree import ElementTree
+import re
+from xml.etree import ElementTree as ET
 from datetime import datetime
 from dotenv import load_dotenv
 from openai import ChatCompletion
@@ -38,6 +39,19 @@ def get_table_download_link(file_path):
     href = f'<a href="data:file/htm;base64,{b64}" target="_blank" download="{os.path.basename(file_path)}">{os.path.basename(file_path)}</a>'
     return href
 
+def CompressXML_Old(xml_text):
+    words = xml_text.split()
+    english_words = [word for word in words if re.fullmatch(r'[A-Za-z ]*', word)]
+    compressed_text = ' '.join(english_words)
+    return compressed_text
+
+def CompressXML(xml_text):
+    tree = ET.ElementTree(ET.fromstring(xml_text))
+    for elem in tree.iter():
+        if isinstance(elem.tag, ET.Comment):
+            elem.getparent().remove(elem)
+    return ET.tostring(tree.getroot(), encoding='unicode')
+
 def read_file_content(file):
     if file.type == "application/json":
         content = json.load(file)
@@ -45,10 +59,15 @@ def read_file_content(file):
     elif file.type == "text/html":
         content = BeautifulSoup(file, "html.parser")
         return content.text
-    elif file.type == "application/xml" or file.type == "text/xml":
+    elif file.type == "application/xmlold" or file.type == "text/xmlold":
         tree = ElementTree.parse(file)
         root = tree.getroot()
         return ElementTree.tostring(root, encoding='unicode')
+    elif file.type == "application/xml" or file.type == "text/xml":
+        tree = ElementTree.parse(file)
+        root = tree.getroot()
+        xml_text = ElementTree.tostring(root, encoding='unicode')
+        return CompressXML(xml_text)
     elif file.type == "text/plain":
         return file.getvalue().decode()
     else: