refactor(utils): separate utils helper functions

convert_source_description/convert_source_description.py

@@ -49,6 +49,7 @@
 import argparse
 
 from bs4 import BeautifulSoup
+from file_utils import FileUtils
 from utils import ConversionUtils
 
 
@@ -63,24 +64,27 @@ def convert_source_description(directory: str, file_name: str):
         A JSON file with the source description.
     """
 
+    file_utils = FileUtils()
+    conversion_utils = ConversionUtils()
+
     # Define file path
     file_path = directory + file_name
 
     # Get HTML from Word file
-    html = ConversionUtils().read_html_from_word_file(file_path)
+    html = file_utils.read_html_from_word_file(file_path)
 
     # Parse HTML
     soup = BeautifulSoup(html, 'html.parser')
 
     # Create the full sourceList object
-    source_list = ConversionUtils().create_source_list(soup)
+    source_list = conversion_utils.create_source_list(soup)
 
     # Create the full textcritics object
-    textcritics = ConversionUtils().create_textcritics(soup)
+    textcritics = conversion_utils.create_textcritics(soup)
 
     # Output
-    ConversionUtils().write_json(source_list, file_path + '_source-description')
-    ConversionUtils().write_json(textcritics, file_path + '_textcritics')
+    file_utils.write_json(source_list, file_path + '_source-description')
+    file_utils.write_json(textcritics, file_path + '_textcritics')
 
 
 def main():

convert_source_description/file_utils.py

@@ -0,0 +1,66 @@
+"""Utility functions for file operations. This includes reading from WORD and writing to JSON."""
+
+import json
+import os
+from typing import Dict
+
+import mammoth
+
+
+############################################
+# Public class: FileUtils
+############################################
+class FileUtils:
+    """A class that contains utility functions for file operations which include reading and writing files."""
+
+    ############################################
+    # Public class function: read_html_from_word_file
+    ############################################
+    def read_html_from_word_file(self, file_path: str) -> str:
+        """
+        Reads a Word file in .docx format and returns its content as an HTML string.
+
+        Args:
+            filePath (str): The name of the Word file to be read, without the .docx extension.
+
+        Returns:
+            str: The content of the Word file as an HTML string.
+        """
+        source_file_name = file_path + ".docx"
+        if not os.path.exists(source_file_name):
+            raise FileNotFoundError("File not found: " + file_path + ".docx")
+
+        with open(source_file_name, "rb") as source_file:
+            try:
+                result = mammoth.convert_to_html(source_file)
+                return result.value  # The generated HTML
+            except ValueError as error:
+                raise ValueError('Error converting file: ' +
+                                 str(error)) from error
+
+    ############################################
+    # Public class function: write_json
+    ############################################
+    def write_json(self, data: Dict, file_path: str) -> None:
+        """
+        Serializes a data dictionary as a JSON formatted string and writes it to a file.
+
+        Args:
+            data (Dict): The data dictionary to be serialized and written.
+            file_path (str): The path to the file to be written, without the .json extension.
+
+        Returns:
+            None
+        """
+        # Serializing json
+        json_object = json.dumps(data, indent=4, ensure_ascii=False).encode(
+            'utf8').decode('utf8')
+
+        # Writing to target file
+        target_file_name = file_path + ".json"
+        try:
+            with open(target_file_name, "w", encoding='utf-8') as target_file:
+                target_file.write(json_object)
+            print(f"Data written to {target_file_name} successfully.")
+        except IOError:
+            print(f"Error writing data to {target_file_name}.")