How to fix RecursionError: maximum recursion depth exceeded while calling a Python object

Question

I am trying to write a Python script that reads an XML file, replaces some variables with placeholders, translates the text using Google Translate API, restores the variables and writes the output to another XML file.

However, when I run my script, I get this error:

Traceback (most recent call last): File "C:\Users\lazar\AppData\Local\Programs\Python\Python311\Lib\xml\etree\ElementTree.py", line 757, in _get_writer write = file_or_filename.write ^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'str' object has no attribute 'write'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "\translate.py", line 48, in _serialize_xml return ET._serialize_xml(write, elem, qnames, namespaces, short_empty_elements=short_empty_elements) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "\translate.py", line 48, in _serialize_xml return ET._serialize_xml(write, elem, qnames, namespaces, short_empty_elements=short_empty_elements) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "./translate.py", line 48, in _serialize_xml return ET._serialize_xml(write, elem, qnames, namespaces, short_empty_elements=short_empty_elements) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [Previous line repeated 997 more times] RecursionError: maximum recursion depth exceeded

I have searched online and found out that this error occurs because the Python interpreter has exceeded the recursion limit allowed.

Here is my code:

import xml.etree.ElementTree as ET
import re
from google.cloud import translate_v2 as translate
from google.oauth2 import service_account

credentials_dict = {
#keys goes here
}


credentials = service_account.Credentials.from_service_account_info(credentials_dict)

client = translate.Client(credentials=credentials)

tree = ET.parse("input.xml")
root = tree.getroot()

def replace_variables(text):
    variables = re.findall(r"\{.*?\}", text)
    for i, variable in enumerate(variables):
        text = text.replace(variable, "~" * (i + 1))
    return text, variables

def restore_variables(text, variables):
    placeholders = re.findall(r"~+", text)
    for i, placeholder in enumerate(placeholders):
        if len(variables) > i:
            text = text.replace(placeholder, variables[i])
    return text

def CDATA(text=None):
    element = ET.Element('![CDATA[')
    element.text = text
    return element

def _serialize_xml(write, elem, qnames, namespaces, *, short_empty_elements=True):
    if elem.tag == '![CDATA[':
        write("\n<%s%s]]>\n" % (elem.tag, elem.text))
        return
    return ET._serialize_xml(write, elem, qnames, namespaces, short_empty_elements=short_empty_elements)

ET._serialize_xml = _serialize_xml

new_elements = []
for i, element in enumerate(root.iter()):
    if element.text is not None:
        text = element.text.strip()
        modified_text, variables = replace_variables(text)
        translation = client.translate(modified_text, target_language="es")
        translated_text = translation["translatedText"]
        restored_text = restore_variables(translated_text, variables)
        print(text + " -> " + restored_text)

        cdata_element = CDATA(restored_text)
        new_element = element.makeelement(element.tag, element.attrib)
        new_element.append(cdata_element)
        new_elements.append(new_element)

for i, new_element in enumerate(new_elements):
    if i < len(root):
        root[i] = new_element
    else:
        root.append(new_element)
tree.write("output.xml", encoding="utf-8", xml_declaration=True)

Can anyone help me fix this error or suggest a better way to write my script? Any advice would be greatly appreciated.

Thank you very much.

I don’t know how to fix this error or why it occurs.

Answer 1

Modify the _serialize_xml() function to avoid calling itself when the tag of the current element is ![CDATA[.

def _serialize_xml(write, elem, qnames, namespaces, *, short_empty_elements=True):
    if elem.tag == '![CDATA[':
        write("\n<%s%s]]>\n" % (elem.tag, elem.text))
        return
    else:
        return ET._serialize_xml(write, elem, qnames, namespaces, short_empty_elements=short_empty_elements)