pyxecm 1.6__py3-none-any.whl → 2.0.0__py3-none-any.whl

pyxecm/helper/xml.py

@@ -1,68 +1,82 @@
-""" XML helper module
-
-Class: XML
-Methods:
-
-load_xml_file: Load an XML file into a Python list of dictionaries
-load_xml_files_from_directory: Load all XML files from a directory that matches defined file names
-                               then using the XPath to identify a set of elements and convert them
-                               into a Python list of dictionaries.
-get_xml_element: Retrieve an XML Element from a string using an XPath expression
-modify_xml_element: Update the text (= content) of an XML element
-search_setting: Search a JSON-like setting inside an XML text telement
-replace_setting: Update a setting value
-replace_in_xml_files: Replace all occurrences of the search pattern with the replace string in all
-                      XML files in the directory and its subdirectories.
-
-"""
+"""XML helper module."""
 
 __author__ = "Dr. Marc Diefenbruch"
-__copyright__ = "Copyright 2024, OpenText"
+__copyright__ = "Copyright (C) 2024-2025, OpenText"
 __credits__ = ["Kai-Philip Gatzweiler"]
 __maintainer__ = "Dr. Marc Diefenbruch"
 __email__ = "mdiefenb@opentext.com"
 
+import fnmatch
+import glob
 import logging
 import os
 import re
-import fnmatch
 import zipfile
+from concurrent.futures import ThreadPoolExecutor
+from queue import Queue
+
+import xmltodict
 
 # we need lxml instead of stadard xml.etree to have xpath capabilities!
 from lxml import etree
-import xmltodict
+from lxml.etree import Element
 
-# import xml.etree.ElementTree as etree
-from pyxecm.helper.assoc import Assoc
+from pyxecm.helper import Assoc
 
-logger = logging.getLogger("pyxecm.xml")
+default_logger = logging.getLogger("pyxecm.helper.xml")
 
 
 class XML:
-    """XML Class to handle XML processing, e.g. to parse and update Extended ECM transport packages"""
+    """Handle XML processing, e.g. to parse and update Extended ECM transport packages."""
+
+    logger: logging.Logger = default_logger
 
     @classmethod
     def load_xml_file(
-        cls, file_path: str, xpath: str, dir_name: str | None = None
+        cls,
+        file_path: str,
+        xpath: str,
+        dir_name: str | None = None,
+        logger: logging.Logger = default_logger,
     ) -> list | None:
-        """Load an XML file into a Python list of dictionaries
+        """Load an XML file into a Python list of dictionaries.
 
         Args:
-            file_path (str): Path to XML file
-            xpath (str): XPath to select sub-elements
+            file_path (str):
+                The path to XML file.
+            xpath (str):
+                XPath to select sub-elements.
+            dir_name (str | None, optional):
+                Directory name to include in each dictionary, if provided.
+            logger (logging.Logger):
+                The logging object used for all log messages.
 
         Returns:
-            dict | None: _description_
+            dict | None:
+                A list of dictionaries representing the parsed XML elements,
+                or None if an error occurs during file reading or parsing.
+
         """
 
-        try:
+        if not os.path.exists(file_path):
+            logger.error("XML File -> %s does not exist!", file_path)
+            return None
 
+        try:
             tree = etree.parse(file_path)
             if not tree:
-                return []
-
-            # Perform the XPath query to select 'child' elements
-            elements = tree.xpath(xpath)  # Adjust XPath as needed
+                logger.warning("Empty or invalid XML tree for file -> %s", file_path)
+                return None
+
+            # Extract elements using the XPath:
+            elements = tree.xpath(xpath)
+            if not elements:
+                logger.warning(
+                    "No elements matched XPath -> %s in file -> '%s'",
+                    xpath,
+                    file_path,
+                )
+                return None
 
             # Convert the selected elements to dictionaries
             results = []
@@ -75,12 +89,15 @@ class XML:
                     element_dict["directory"] = dir_name
                 results.append(element_dict)
 
-        except IOError as e:
-            logger.error("IO Error -> %s", str(e))
-        except etree.XMLSyntaxError as e:
-            logger.error("XML Syntax Error -> %s", str(e))
-        except etree.DocumentInvalid as e:
-            logger.error("Document Invalid -> %s", str(e))
+        except OSError:
+            logger.error("IO Error with file -> %s", file_path)
+            return None
+        except etree.XMLSyntaxError:
+            logger.error("XML Syntax Error in file -> %s", file_path)
+            return None
+        except etree.DocumentInvalid:
+            logger.error("Invalid XML document -> %s", file_path)
+            return None
 
         return results
 
@@ -88,33 +105,50 @@ class XML:
 
     @classmethod
     def load_xml_files_from_directory(
-        cls, path_to_root: str, filenames: list | None, xpath: str | None = None
+        cls,
+        path_to_root: str,
+        filenames: list | None,
+        xpath: str | None = None,
+        logger: logging.Logger = default_logger,
     ) -> list | None:
-        """Load all XML files from a directory that matches defined file names
-           then using the XPath to identify a set of elements and convert them
-           into a Python list of dictionaries.
+        """Load all XML files from a directory that matches defined file names.
+
+        Then using the XPath to identify a set of elements and convert them
+        into a Python list of dictionaries.
 
         Args:
-            path_to_root (str): Path to the root element of the
-                                directory structure
-            filenames (list): list of filenames. If empty all filenames ending
-                              with ".xml" are used.
-            xpath (str, optional): XPath to the elements we want to select
+            path_to_root (str):
+                Path to the root element of the
+                directory structure
+            filenames (list):
+                A list of filenames. This can also be patterns like
+                "*/en/docovw.xml". If empty all filenames ending
+                with ".xml" is used.
+            xpath (str, optional):
+                The XPath to the elements we want to select.
+            logger (logging.Logger):
+                The logging object used for all log messages.
 
         Returns:
-            list: List of dictionaries
+            list:
+                List of dictionaries.
+
         """
 
-        try:
+        if not filenames:
+            filenames = ["*.xml"]
 
-            # Check if the provided path is a directory
+        try:
+            # Check if the provided path is a directory or a zip file that can be extracted
+            # into a directory:
             if not os.path.isdir(path_to_root) and not path_to_root.endswith(".zip"):
                 logger.error(
-                    "The provided path '%s' is not a valid directory or Zip file.",
+                    "The provided path -> '%s' is not a valid directory or Zip file.",
                     path_to_root,
                 )
-                return False
+                return None
 
+            # If we have a zip file we extract it - but only if it has not been extracted before:
             if path_to_root.endswith(".zip"):
                 zip_file_folder = os.path.splitext(path_to_root)[0]
                 if not os.path.exists(zip_file_folder):
@@ -123,8 +157,21 @@ class XML:
                         path_to_root,
                         zip_file_folder,
                     )
-                    with zipfile.ZipFile(path_to_root, "r") as zfile:
-                        zfile.extractall(zip_file_folder)
+                    try:
+                        with zipfile.ZipFile(path_to_root, "r") as zfile:
+                            zfile.extractall(zip_file_folder)
+                    except zipfile.BadZipFile:
+                        logger.error(
+                            "Failed to extract zip file -> '%s'",
+                            path_to_root,
+                        )
+                        return None
+                    except OSError:
+                        logger.error(
+                            "OS error occurred while trying to extract -> '%s'",
+                            path_to_root,
+                        )
+                        return None
                 else:
                     logger.info(
                         "Zip file is already extracted (path -> '%s' exists). Reusing extracted data...",
@@ -142,37 +189,308 @@ class XML:
                     file_name = os.path.basename(file_path)
                     dir_name = os.path.dirname(file_path)
 
-                    if any(
-                        fnmatch.fnmatch(file_path, pattern) for pattern in filenames
-                    ) and file_name.endswith(".xml"):
+                    if any(fnmatch.fnmatch(file_path, pattern) for pattern in filenames) and file_name.endswith(".xml"):
                         logger.info(
-                            "Load XML file -> '%s' of size -> %s", file_path, file_size
+                            "Load XML file -> '%s' of size -> %s",
+                            file_path,
+                            file_size,
                         )
-                        results += cls.load_xml_file(
-                            file_path, xpath=xpath, dir_name=dir_name
+                        elements = cls.load_xml_file(
+                            file_path,
+                            xpath=xpath,
+                            dir_name=dir_name,
                         )
+                        if elements:
+                            results += elements
+
+        except NotADirectoryError:
+            logger.error(
+                "The given path -> '%s' is not a directory!",
+                path_to_root,
+            )
+            return None
+        except FileNotFoundError:
+            logger.error(
+                "The given path -> '%s' does not exist!",
+                path_to_root,
+            )
+            return None
+        except PermissionError:
+            logger.error(
+                "No permission to access path -> '%s'!",
+                path_to_root,
+            )
+            return None
+        except OSError:
+            logger.error("Low level OS error with file -> %s", path_to_root)
+            return None
+
+        return results
+
+    # end method definition
+
+    @classmethod
+    def load_xml_files_from_directories(
+        cls,
+        directories: list[str],
+        filenames: list[str] | None = None,
+        xpath: str | None = None,
+        logger: logging.Logger = default_logger,
+    ) -> list[dict] | None:
+        """Load XML files from multiple directories or zip files concurrently.
+
+        Process them using XPath, and return a list of dictionaries containing the extracted elements.
+
+        This method handles multiple directories or zip files, processes XML files inside them in parallel
+        using threads, and extracts elements that match the specified XPath. It also supports pattern matching
+        for filenames and handles errors such as missing files or permission issues.
+
+        Args:
+            directories (list[str]):
+                A list of directories or zip files to process. Each item can be a path
+                to a directory or a zip file that contains XML files.
+            filenames (list[str] | None, optional):
+                A list of filename patterns (e.g., ["*/en/docovw.xml"]) to match
+                against the XML files. If None or empty, defaults to ["*.xml"].
+            xpath (str | None, optional):
+                An optional XPath string used to filter elements from the XML files.
+            logger (logging.Logger):
+                The logging object used for all log messages.
+
+        Returns:
+            list[dict] | None:
+                A list of dictionaries containing the extracted XML elements. Returns None
+                if any error occurs during processing.
+
+        Raises:
+            Exception: If any error occurs during processing, such as issues with directories, files, or zip extraction.
+
+        """
+
+        # Set default for filenames if not provided
+        if not filenames:
+            filenames = ["*.xml"]
+
+        results_queue = Queue()
+
+        def process_xml_file(file_path: str) -> None:
+            """Process a single XML file.
+
+            Args:
+                file_path (str):
+                    Path to the XML file.
+
+            Results:
+                Adds elements to the result_queue defined outside this sub-method.
+
+            """
+
+            try:
+                file_size = os.path.getsize(file_path)
+                file_name = os.path.basename(file_path)
+                dir_name = os.path.dirname(file_path)
+
+                if (
+                    not filenames or any(fnmatch.fnmatch(file_path, pattern) for pattern in filenames)
+                ) and file_name.endswith(".xml"):
+                    logger.info(
+                        "Load XML file -> '%s' of size -> %s",
+                        file_path,
+                        file_size,
+                    )
+                    elements = cls.load_xml_file(
+                        file_path,
+                        xpath=xpath,
+                        dir_name=dir_name,
+                    )
+                    if elements:
+                        results_queue.put(elements)
+            except FileNotFoundError:
+                logger.error("File not found -> '%s'!", file_path)
+            except PermissionError:
+                logger.error(
+                    "Permission error with file -> '%s'!",
+                    file_path,
+                )
+            except OSError:
+                logger.error(
+                    "OS error processing file -> '%s'!",
+                    file_path,
+                )
+            except ValueError:
+                logger.error(
+                    "Value error processing file -> '%s'!",
+                    file_path,
+                )
+
+        # end method process_xml_file
 
-        except NotADirectoryError as nde:
-            logger.error("Error -> %s", str(nde))
-        except FileNotFoundError as fnfe:
-            logger.error("Error -> %s", str(fnfe))
-        except PermissionError as pe:
-            logger.error("Error -> %s", str(pe))
+        def process_directory_or_zip(path_to_root: str) -> list | None:
+            """Process all files in a directory or zip file.
+
+            Args:
+                path_to_root (str):
+                    File path to the root directory or zip file.
+
+            """
+
+            try:
+                # Handle zip files
+                if path_to_root.endswith(".zip"):
+                    zip_file_folder = os.path.splitext(path_to_root)[0]
+                    if not os.path.exists(zip_file_folder):
+                        logger.info(
+                            "Unzipping -> '%s' into folder -> '%s'...",
+                            path_to_root,
+                            zip_file_folder,
+                        )
+                        try:
+                            with zipfile.ZipFile(path_to_root, "r") as zfile:
+                                zfile.extractall(zip_file_folder)
+                        except zipfile.BadZipFile:
+                            logger.error(
+                                "Bad zip file -> '%s'!",
+                                path_to_root,
+                            )
+                        except zipfile.LargeZipFile:
+                            logger.error(
+                                "Zip file is too large to process -> '%s'!",
+                                path_to_root,
+                            )
+                        except PermissionError:
+                            logger.error(
+                                "Permission error extracting zip file -> '%s'!",
+                                path_to_root,
+                            )
+                        except OSError:
+                            logger.error(
+                                "OS error occurred while extracting zip file -> '%s'!",
+                                path_to_root,
+                            )
+                        return  # Don't proceed further if zip extraction fails
+
+                    else:
+                        logger.info(
+                            "Zip file is already extracted (path -> '%s' exists). Reusing extracted data...",
+                            zip_file_folder,
+                        )
+                    path_to_root = zip_file_folder
+                # end if path_to_root.endswith(".zip")
+
+                # Use inner threading to process files within the directory
+                with ThreadPoolExecutor(
+                    thread_name_prefix="ProcessXMLFile",
+                ) as inner_executor:
+                    for root, _, files in os.walk(path_to_root):
+                        for file_data in files:
+                            file_path = os.path.join(root, file_data)
+                            inner_executor.submit(process_xml_file, file_path)
+
+            except FileNotFoundError:
+                logger.error(
+                    "Directory or file not found -> '%s'!",
+                    path_to_root,
+                )
+            except PermissionError:
+                logger.error(
+                    "Permission error with directory -> '%s'!",
+                    path_to_root,
+                )
+            except OSError:
+                logger.error(
+                    "OS error processing path -> '%s'!",
+                    path_to_root,
+                )
+            except ValueError:
+                logger.error(
+                    "Value error processing path -> '%s'!",
+                    path_to_root,
+                )
+
+        # end method process_directory_or_zip
+
+        try:
+            # Resolve wildcards in the directories list
+            expanded_directories: list[str] = []
+            for directory in directories:
+                if "*" in directory:
+                    expanded_directory: list = glob.glob(directory)
+                    logger.info(
+                        "Expanding directory -> '%s' with wildcards...",
+                        directory,
+                    )
+                    expanded_directories.extend(expanded_directory)
+                else:
+                    logger.info(
+                        "Directory -> '%s' has no wildcards. Not expanding...",
+                        directory,
+                    )
+                    expanded_directories.append(directory)
+
+            # Use ThreadPoolExecutor for outer level: processing directories/zip files
+            logger.info(
+                "Starting %d threads for each directory or zip file...",
+                len(expanded_directories),
+            )
+            with ThreadPoolExecutor(
+                thread_name_prefix="ProcessDirOrZip",
+            ) as outer_executor:
+                futures = [
+                    outer_executor.submit(process_directory_or_zip, directory) for directory in expanded_directories
+                ]
+
+                # Wait for all futures to complete
+                for future in futures:
+                    future.result()
+
+            # Collect results from the queue
+            logger.info("Collecting results from worker queue...")
+            results = []
+            while not results_queue.empty():
+                results.extend(results_queue.get())
+            logger.info("Done. Collected %d results.", len(results))
+
+        except FileNotFoundError:
+            logger.error(
+                "Directory or file not found during execution!",
+            )
+            return None
+        except PermissionError:
+            logger.error("Permission error during execution!")
+            return None
+        except TimeoutError:
+            logger.error(
+                "Timeout occurred while waiting for threads!",
+            )
+            return None
+        except BrokenPipeError:
+            logger.error(
+                "Broken pipe error occurred during thread communication!",
+            )
+            return None
 
         return results
 
     # end method definition
 
     @classmethod
-    def get_xml_element(cls, xml_content: str, xpath: str):
-        """Retrieves an XML Element from a string using an XPath expression
+    def get_xml_element(
+        cls,
+        xml_content: str,
+        xpath: str,
+    ) -> Element:
+        """Retrieve an XML Element from a string using an XPath expression.
 
         Args:
-            xml_content (str): XML file as a string
-            xpath (str): XPath to find the element
+            xml_content (str):
+                XML file as a string
+            xpath (str):
+                XPath used to find the element.
 
         Returns:
-            str: text of element
+            Element:
+                The XML element.
+
         """
 
         # Parse XML content into an etree
@@ -186,13 +504,25 @@ class XML:
     # end method definition
 
     @classmethod
-    def modify_xml_element(cls, xml_content: str, xpath: str, new_value: str):
-        """Update the text (= content) of an XML element
+    def modify_xml_element(
+        cls,
+        xml_content: str,
+        xpath: str,
+        new_value: str,
+        logger: logging.Logger = default_logger,
+    ) -> None:
+        """Update the text (= content) of an XML element.
 
         Args:
-            xml_content (str): the content of an XML file
-            xpath (str): XML Path to identify the XML element
-            new_value (str): new text (content)
+            xml_content (str):
+                The content of an XML file.
+            xpath (str):
+                XML Path to identify the XML element.
+            new_value (str):
+                The new text (content).
+            logger (logging.Logger):
+                The logging object used for all log messages.
+
         """
         element = cls.get_xml_element(xml_content=xml_content, xpath=xpath)
 
@@ -212,7 +542,7 @@ class XML:
         is_simple: bool = True,
         is_escaped: bool = False,
     ) -> str | None:
-        """Search a setting in an XML element and return its value
+        """Search a setting in an XML element and return its value.
 
         The simple case covers settings like this:
         "syncCandidates":true,
@@ -226,25 +556,27 @@ class XML:
         but we take the value for a string delimited by double quotes ("...")
 
         Args:
-            element_text (str): the text to examine - typically content of an XML element
-            setting_key (str): name of the setting key (before the colon)
-            is_simple (bool, optional): True if the value is scalar (not having assocs with commas). Defaults to True.
-            is_escaped (bool, optional): True if the quotes or escaped with ". Defaults to False.
+            element_text (str):
+                The text to examine - typically content of an XML element.
+            setting_key (str):
+                The name of the setting key (before the colon).
+            is_simple (bool, optional):
+                True if the value is scalar (not having assocs with commas). Defaults to True.
+            is_escaped (bool, optional):
+                True if the quotes or escaped with ". Defaults to False.
 
         Returns:
-            str: the value of the setting or None if the setting is not found.
+            str:
+                The value of the setting or None if the setting is not found.
+
         """
 
         if is_simple:
-            if is_escaped:
-                pattern = r""{0}":[^,]*".format(setting_key)
-            else:
-                pattern = r'"{0}":[^,]*'.format(setting_key)
+            pattern = r""{}":[^,]*".format(setting_key) if is_escaped else r'"{}":[^,]*'.format(setting_key)
+        elif is_escaped:
+            pattern = r""{}":".*"".format(setting_key)
         else:
-            if is_escaped:
-                pattern = r""{0}":".*"".format(setting_key)
-            else:
-                pattern = r'"{0}":"([^"]*)"'.format(setting_key)
+            pattern = r'"{}":"([^"]*)"'.format(setting_key)
 
         match = re.search(pattern, element_text)
         if match:
@@ -279,26 +611,29 @@ class XML:
         but we take the value for a string delimited by double quotes ("...")
 
         Args:
-            element_text (str): original text of the XML element (that is to be updated)
-            setting_key (str): name of the setting
-            new_value (str): new value of the setting
-            is_simple (bool, optional): True = value is a scalar like true, false, a number or none. Defaults to True.
-            is_escaped (bool, optional): True if the value is surrrounded with ". Defaults to False.
+            element_text (str):
+                The original text of the XML element (that is to be updated).
+            setting_key (str):
+                The name of the setting.
+            new_value (str):
+                The new value of the setting.
+            is_simple (bool, optional):
+                True = value is a scalar like true, false, a number or none. Defaults to True.
+            is_escaped (bool, optional):
+                True if the value is surrrounded with ". Defaults to False.
 
         Returns:
-            str: updated element text
+            str:
+                The updated element text.
+
         """
 
         if is_simple:
-            if is_escaped:
-                pattern = r""{0}":[^,]*".format(setting_key)
-            else:
-                pattern = r'"{0}":[^,]*'.format(setting_key)
+            pattern = r""{}":[^,]*".format(setting_key) if is_escaped else r'"{}":[^,]*'.format(setting_key)
+        elif is_escaped:
+            pattern = r""{}":".*"".format(setting_key)
         else:
-            if is_escaped:
-                pattern = r""{0}":".*"".format(setting_key)
-            else:
-                pattern = r'"{0}":"([^"]*)"'.format(setting_key)
+            pattern = r'"{}":"([^"]*)"'.format(setting_key)
 
         new_text = re.sub(pattern, new_value, element_text)
 
@@ -315,24 +650,38 @@ class XML:
         xpath: str = "",
         setting: str = "",
         assoc_elem: str = "",
+        logger: logging.Logger = default_logger,
     ) -> bool:
-        """Replaces all occurrences of the search pattern with the replace string in all XML files
-            in the directory and its subdirectories.
+        """Replace all occurrences of the search pattern with the replace string.
+
+        This is done in all XML files in the directory and its subdirectories.
 
         Args:
-            directory (str): directory to traverse for XML files
-            search_pattern (str): string to search in the XML file. This can be empty
-                                  if xpath is used!
-            replace_string (str): replacement string
-            xpath (str): narrow down the replacement to an XML element that es defined by the XPath
-                         for now the XPath needs to be constructed in a way the it returns
-                         one or none element.
-            setting (str): narrow down the replacement to the line that includes the setting with this name.
-                           This parameter is optional.
-            assoc_elem (str): lookup a specific assoc element. This parameter is optional.
+            directory (str):
+                Directory to traverse for XML files
+            search_pattern (str):
+                The string to search in the XML file.
+                This can be empty if xpath is used!
+            replace_string (str):
+                The replacement string.
+            xpath (str, optional):
+                An XPath can be given to narrow down the replacement to an XML element.
+                For now the XPath needs to be constructed in a way the it returns
+                one or none element.
+            setting (str, optional):
+                Narrow down the replacement to the line that includes the setting with this name.
+                This parameter is optional.
+            assoc_elem (str, optional):
+                Lookup a specific assoc element. This parameter is optional.
+            logger (logging.Logger):
+                The logging object used for all log messages.
+
         Returns:
-            bool: True if a replacement happened, False otherwise
+            bool:
+                True if a replacement happened, False otherwise
+
         """
+
         # Define the regular expression pattern to search for
         # search pattern can be empty if an xpath is used. So
         # be careful here:
@@ -362,7 +711,8 @@ class XML:
                         tree = etree.parse(file_path)
                         if not tree:
                             logger.error(
-                                "Cannot parse XML tree -> %s. Skipping...", file_path
+                                "Cannot parse XML tree -> %s. Skipping...",
+                                file_path,
                             )
                             continue
                         root = tree.getroot()
@@ -402,7 +752,9 @@ class XML:
                                     replace_string,
                                 )
                                 setting_value = cls.search_setting(
-                                    element.text, setting, is_simple=True
+                                    element.text,
+                                    setting,
+                                    is_simple=True,
                                 )
                                 if setting_value:
                                     logger.debug(
@@ -411,21 +763,13 @@ class XML:
                                     )
                                     # Check if the setting value needs to be surrounded by quotes.
                                     # Only simplistic values like booleans or numeric values don't need quotes
-                                    if (
-                                        replace_string == "true"
-                                        or replace_string == "false"
-                                        or replace_string == "none"
-                                        or replace_string.isnumeric()
-                                    ):
-                                        replace_setting = (
-                                            '"' + setting + '":' + replace_string
-                                        )
+                                    if replace_string in ("true", "false", "none") or replace_string.isnumeric():
+                                        replace_setting = '"' + setting + '":' + replace_string
                                     else:
-                                        replace_setting = (
-                                            '"' + setting + '":"' + replace_string + '"'
-                                        )
+                                        replace_setting = '"' + setting + '":"' + replace_string + '"'
                                     logger.debug(
-                                        "Replacement setting -> %s", replace_setting
+                                        "Replacement setting -> %s",
+                                        replace_setting,
                                     )
                                     element.text = cls.replace_setting(
                                         element_text=element.text,
@@ -449,21 +793,20 @@ class XML:
                                     replace_string,
                                 )
                                 assoc_string: str = Assoc.extract_assoc_string(
-                                    input_string=element.text
+                                    input_string=element.text,
                                 )
                                 logger.debug("Assoc String -> %s", assoc_string)
                                 assoc_dict = Assoc.string_to_dict(
-                                    assoc_string=assoc_string
+                                    assoc_string=assoc_string,
                                 )
                                 logger.debug("Assoc Dict -> %s", str(assoc_dict))
-                                assoc_dict[assoc_elem] = (
-                                    replace_string  # escaped_replace_string
-                                )
+                                assoc_dict[assoc_elem] = replace_string  # escaped_replace_string
                                 assoc_string_new: str = Assoc.dict_to_string(
-                                    assoc_dict=assoc_dict
+                                    assoc_dict=assoc_dict,
                                 )
                                 logger.debug(
-                                    "Replace assoc with -> %s", assoc_string_new
+                                    "Replace assoc with -> %s",
+                                    assoc_string_new,
                                 )
                                 element.text = assoc_string_new
                                 element.text = element.text.replace('"', """)
@@ -478,42 +821,43 @@ class XML:
                                     replace_string,
                                 )
                                 setting_value = cls.search_setting(
-                                    element.text, setting, is_simple=False
+                                    element.text,
+                                    setting,
+                                    is_simple=False,
                                 )
                                 if setting_value:
                                     logger.debug(
-                                        "Found setting value -> %s", setting_value
+                                        "Found setting value -> %s",
+                                        setting_value,
                                     )
                                     assoc_string: str = Assoc.extract_assoc_string(
-                                        input_string=setting_value
+                                        input_string=setting_value,
                                     )
                                     logger.debug("Assoc String -> %s", assoc_string)
                                     assoc_dict = Assoc.string_to_dict(
-                                        assoc_string=assoc_string
+                                        assoc_string=assoc_string,
                                     )
                                     logger.debug("Assoc Dict -> %s", str(assoc_dict))
                                     escaped_replace_string = replace_string.replace(
-                                        "'", "\\\\\u0027"
+                                        "'",
+                                        "\\\\\u0027",
                                     )
                                     logger.debug(
                                         "Escaped replacement string -> %s",
                                         escaped_replace_string,
                                     )
-                                    assoc_dict[assoc_elem] = (
-                                        escaped_replace_string  # escaped_replace_string
-                                    )
+                                    assoc_dict[assoc_elem] = escaped_replace_string  # escaped_replace_string
                                     assoc_string_new: str = Assoc.dict_to_string(
-                                        assoc_dict=assoc_dict
+                                        assoc_dict=assoc_dict,
                                     )
                                     assoc_string_new = assoc_string_new.replace(
-                                        "'", "\\u0027"
-                                    )
-                                    # replace_setting = """ + setting + "":"" + assoc_string_new + """
-                                    replace_setting = (
-                                        '"' + setting + '":"' + assoc_string_new + '"'
+                                        "'",
+                                        "\\u0027",
                                     )
+                                    replace_setting = '"' + setting + '":"' + assoc_string_new + '"'
                                     logger.debug(
-                                        "Replacement setting -> %s", replace_setting
+                                        "Replacement setting -> %s",
+                                        replace_setting,
                                     )
                                     # here we need to apply a "trick". It is required
                                     # as regexp cannot handle the special unicode escapes \u0027
@@ -524,13 +868,13 @@ class XML:
                                     element.text = cls.replace_setting(
                                         element_text=element.text,
                                         setting_key=setting,
-                                        #                                        new_value=replace_setting,
                                         new_value="PLACEHOLDER",
                                         is_simple=False,
                                         is_escaped=False,
                                     )
                                     element.text = element.text.replace(
-                                        "PLACEHOLDER", replace_setting
+                                        "PLACEHOLDER",
+                                        replace_setting,
                                     )
                                     element.text = element.text.replace('"', """)
                                     xml_modified = True
@@ -554,10 +898,12 @@ class XML:
                             )
                             # we need to undo some of the stupid things tostring() did:
                             new_contents = new_contents.replace(
-                                b""", b"""
+                                b""",
+                                b""",
                             )
                             new_contents = new_contents.replace(
-                                b"'", b"'"
+                                b"'",
+                                b"'",
                             )
                             new_contents = new_contents.replace(b">", b">")
                             new_contents = new_contents.replace(b"<", b"<")
@@ -576,12 +922,14 @@ class XML:
                             # This is required as we next want to replace all double quotes with single quotes
                             # to make the XML files as similar as possible with Extended ECM's format
                             pattern = b">([^<>]+?)<"
-                            replacement = lambda match: match.group(0).replace(
-                                b'"', b"&quot;"
+                            replacement = lambda match: match.group(0).replace(  # noqa: E731
+                                b'"',
+                                b"&quot;",
                             )
                             new_contents = re.sub(pattern, replacement, new_contents)
-                            replacement = lambda match: match.group(0).replace(
-                                b"'", b"&apos;"
+                            replacement = lambda match: match.group(0).replace(  # noqa: E731
+                                b"'",
+                                b"&apos;",
                             )
                             new_contents = re.sub(pattern, replacement, new_contents)
 
@@ -600,7 +948,7 @@ class XML:
                     # this is not using xpath - do a simple search and replace
                     else:
                         logger.debug("Replacement without xpath...")
-                        with open(file_path, "r", encoding="UTF-8") as f:
+                        with open(file_path, encoding="UTF-8") as f:
                             contents = f.read()
                         # Replace all occurrences of the search pattern with the replace string
                         new_contents = pattern.sub(replace_string, contents)
@@ -626,15 +974,22 @@ class XML:
         cls,
         directory: str,
         xpath: str,
+        logger: logging.Logger = default_logger,
     ) -> list | None:
-        """Extracts the XML subtrees using an XPath in all XML files
-            in the directory and its subdirectories.
+        """Extract the XML subtrees using an XPath in all XML files in the directory and its subdirectories.
 
         Args:
-            directory (str): directory to traverse for XML files
-            xpath (str): used to determine XML elements to extract
+            directory (str):
+                The directory to traverse for XML files.
+            xpath (str):
+                Used to determine XML elements to extract.
+            logger (logging.Logger):
+                The logging object used for all log messages.
+
         Returns:
-            list | None: Extracted data if it is found by the XPath, None otherwise
+            list | None:
+                Extracted data if it is found by the XPath, None otherwise.
+
         """
 
         extracted_data_list = []
@@ -651,7 +1006,8 @@ class XML:
                     tree = etree.parse(file_path)
                     if not tree:
                         logger.error(
-                            "Cannot parse XML file -> '%s'. Skipping...", file_path
+                            "Cannot parse XML file -> '%s'. Skipping...",
+                            file_path,
                         )
                         continue
                     root = tree.getroot()