Little annot fix

src/docx_converter/html_docx_processor.py

@@ -1,7 +1,7 @@
 import re
 import json
 import pathlib
-from typing import List, Dict, Union
+from typing import List, Tuple, Dict, Union
 from bs4 import BeautifulSoup, Tag, NavigableString
 
 from src.util.helpers import BookLogger
@@ -26,8 +26,6 @@ class HTMLDocxProcessor:
             "attr_replacer": self._replace_attr,
             "unwrapper": self._unwrap_tag
         }
-        self.top_level_headers = None
-        self.content = list()
 
     def _process_toc_links(self):
         """Function to extract nodes which contains TOC links, remove links from file and detect headers."""
@@ -95,7 +93,7 @@ class HTMLDocxProcessor:
         Function do action with tags
         Parameters
         ----------
-        body_tag: BeautifulSoup
+        body_tag: Tag
             Tag & contents of the chapter tag
         rules: List[Dict[str, Union[List[str], str, Dict[str, Union[List[Dict[str, str]], int, str]]]]]
             list of conditions when fire function
@@ -430,7 +428,10 @@ class HTMLDocxProcessor:
             ind = self.content.index(toc_tag) + 1
             self.content = self.content[ind:]
 
-    def process_html(self, access=None, html_path: pathlib.Path = "", book_id: int = 0):
+    def process_html(self,
+                     access=None,
+                     html_path: pathlib.Path = "",
+                     book_id: int = 0) -> Tuple[List[Tag], List[str], List[Dict[str, Union[str, bool]]]]:
         """Process html code to satisfy LiveCarta formatting."""
         self.logger.log("Beginning of processing .html file.")
 
@@ -470,13 +471,14 @@ class HTMLDocxProcessor:
             f"{len(self.images)} images have been processed.")
 
         self.logger.log("Footnotes processing.")
-        self.footnotes = process_footnotes(self.body_tag)
+        self.footnotes: List[str] = process_footnotes(self.body_tag)
         self.logger.log(
             f"{len(self.footnotes)} footnotes have been processed.")
 
         self._process_div()
 
-        self.top_level_headers = self._get_top_level_headers()
+        self.top_level_headers: List[Dict[str, Union[str, bool]]]\
+            = self._get_top_level_headers()
         self._mark_introduction_headers()
 
         self._process_headings()

src/style_preprocessor.py

@@ -77,17 +77,17 @@ class StylePreprocessor:
             if has_style_attrs.group(1):
                 multiplier = 5.76 if is_indent else 0.16
                 size_value = float(size_value.replace("%", "")) * multiplier
-                return str(size_value)+'px'
+                return str(size_value) + "px"
             elif has_style_attrs.group(3):
                 multiplier = 18 if is_indent else 16
                 size_value = float(size_value.replace("em", "")) * multiplier
-                return str(size_value)+'px'
+                return str(size_value) + "px"
             elif has_style_attrs.group(5):
                 size_value = float(size_value.replace("pt", "")) * 4/3
-                return str(size_value)+'px'
+                return str(size_value) + "px"
             elif has_style_attrs.group(7):
                 size_value = float(size_value.replace("in", "")) * 96
-                return str(size_value)+'px'
+                return str(size_value) + "px"
             else:
                 return ""
         return size_value