Annotations for Docx Converter

src/docx_converter/libre_html2json_converter.py

@@ -1,12 +1,15 @@
 import re
 import logging
 from copy import copy
+from typing import List, Tuple, Dict, Union
+from bs4 import Tag
 
 from src.livecarta_config import LiveCartaConfig
 
 
 class LibreHTML2JSONConverter:
-    def __init__(self, content, footnotes, top_level_headers, logger_object, book_api_status=None):
+    def __init__(self, content: List[Tag], footnotes: List[str], top_level_headers: List[Dict[str, Union[str, bool]]],
+                 logger_object, book_api_status=None):
         self.content_dict = None
         self.content = content
         self.footnotes = footnotes
@@ -33,7 +36,7 @@ class LibreHTML2JSONConverter:
         return new_text
 
     # TODO: rethink the function structure without indexes.
-    def header_to_livecarta_chapter_item(self, ind) -> (dict, int):
+    def header_to_livecarta_chapter_item(self, ind: int) -> Union[Tuple[Dict[str, Union[str, List]], int], str]:
         """
         Function process header and collects all content for it.
         Parameters
@@ -90,7 +93,7 @@ class LibreHTML2JSONConverter:
         return ""
 
     @staticmethod
-    def _is_empty_p_tag(tag):
+    def _is_empty_p_tag(tag: Tag) -> bool:
         if tag.name != "p":
             return False
 
@@ -102,7 +105,6 @@ class LibreHTML2JSONConverter:
         text = re.sub(r"\s+", "", temp_tag.text)
         if text:
             return False
-
         return True
 
     def convert_to_dict(self):
@@ -148,9 +150,7 @@ class LibreHTML2JSONConverter:
         # Add is_introduction field to json structure
         # after deleting content before toc, some chapters can be deleted
         if self.top_level_headers:
-            same_first_titles = self.top_level_headers[0]["title"] == json_strc[0]["title"]
             is_first_header_introduction = not self.top_level_headers[0]["should_be_numbered"]
-
             json_strc[0]["is_introduction"] = is_first_header_introduction
 
         self.content_dict = {