Fix style processor error

src/docx_converter/html_docx_processor.py

@@ -14,13 +14,12 @@ class HtmlDocxProcessor:
     def __init__(self, logger: BookLogger, html_soup: BeautifulSoup, html_preprocessor, style_preprocessor):
         self.logger = logger
         self.html_soup = html_soup
-        self.body_tag = self.html_soup.body
         self.html_preprocessor = html_preprocessor
         self.style_preprocessor = style_preprocessor
         self.content: List[Tag] = []
 
     def _font_to_span(self):
-        for font in self.body_tag.find_all("font"):
+        for font in self.html_soup.find_all("font"):
             font.name = "span"
 
 
@@ -226,10 +225,12 @@ class HtmlDocxProcessor:
 
         self.logger.log("Inline style reading.")
         self.style_preprocessor.process_inline_styles_in_html_soup(
-            self.body_tag)
+            self.html_soup)
 
         self.logger.log("Inline style processing.")
-        modify_html_soup_with_css_styles(self.body_tag)
+        self.html_soup = modify_html_soup_with_css_styles(self.html_soup)
+
+        self.body_tag = self.html_soup.body
 
         self.logger.log("Image processing.")
         images = process_images(access, path_to_html=html_path,

src/inline_style_processor.py

@@ -14,7 +14,7 @@ class InlineStyleProcessor:
     def __init__(self, tag_inline_style: Tag):
         # tag with inline style + style parsed from css file
         self.tag_inline_style = tag_inline_style
-        self.tag_inline_style.attrs['style']: str = self.process_inline_style()
+        self.tag_inline_style.attrs["style"]: str = self.process_inline_style()
 
     @staticmethod
     def remove_white_if_no_bgcolor(style_: str, tag: Tag) -> str:
@@ -80,19 +80,19 @@ class InlineStyleProcessor:
         processed_style = ";".join(split_style)+';'
 
         margin_left_regexp = re.compile(
-            r"((margin-left|margin): *(-*\w+);*)")
+            r"((margin-left|margin): *-*((\d*)\.*\d+)\w+;*)")
         text_indent_regexp = re.compile(
-            r"(text-indent: *(-*\w+);*)")
+            r"(text-indent: *-*((\d*)\.*\d+)\w+;*)")
 
         has_margin = re.search(margin_left_regexp, processed_style)
         has_text_indent = re.search(text_indent_regexp, processed_style)
         if has_margin:
             num_m = abs(int("0" + "".join(
-                filter(str.isdigit, str(has_margin.group(3))))))
+                filter(str.isdigit, str(has_margin.group(4))))))
 
             if has_text_indent:
                 num_ti = abs(int("0" + "".join(
-                    filter(str.isdigit, str(has_text_indent.group(2))))))
+                    filter(str.isdigit, str(has_text_indent.group(3))))))
                 processed_style = processed_style.replace(has_text_indent.group(1), "text-indent: " +
                                                           str(abs(num_m - num_ti)) + "px; ")
                 processed_style = processed_style.replace(
@@ -106,7 +106,7 @@ class InlineStyleProcessor:
         elif has_text_indent:
             processed_style = processed_style.replace(has_text_indent.group(1), "text-indent: " +
                                                       str(abs(int("0" + "".join(
-                                                          filter(str.isdigit, str(has_text_indent.group(2)))))))
+                                                          filter(str.isdigit, str(has_text_indent.group(3)))))))
                                                       + "px; ")
             return processed_style
         return processed_style
@@ -127,8 +127,9 @@ class InlineStyleProcessor:
             processed inline style
 
         """
+        if self.tag_inline_style.attrs.get("style"):
             inline_style = self.tag_inline_style.attrs.get("style") + ";"
-        # 1. Remove white color if tag doesn"t have background color in style
+            # 1. Remove white color if tag doesn't have background color in style
             inline_style = self.remove_white_if_no_bgcolor(
                 inline_style, self.tag_inline_style)
             inline_style = inline_style.replace(
@@ -143,6 +144,8 @@ class InlineStyleProcessor:
             # 4. Processing indents
             inline_style: str = self.indents_processing(split_inline_style)
             return inline_style
+        else:
+            return ""
 
     @staticmethod
     def check_style_to_be_tag(style: str) -> List[tuple]:

src/style_reader.py

@@ -126,17 +126,18 @@ class StyleReader:
         return constraints_on_value, value_not_in_possible_values_list
 
     def update_inline_styles_to_livecarta_convention(self, split_style: list) -> list:
-        for i, style in enumerate(split_style):
+        for i, style in reversed(list(enumerate(split_style))):
             style_name, style_value = style.split(":")
             if style_name not in LiveCartaConfig.LIVECARTA_STYLE_ATTRS:
-                # property not in LIVECARTA_STYLE_ATTRS, remove from css file
+                # property not in LIVECARTA_STYLE_ATTRS, remove
-                split_style[i] = ""
+                split_style.remove(style)
-                return split_style
+                continue
 
             cleaned_value = self.clean_value(style_value, style_name)
             if all(self.style_conditions(cleaned_value, style_name)):
-                # there are constraints + value not in LIVECARTA_STYLE_ATTRS, remove from css file
+                # there are constraints + value not in LIVECARTA_STYLE_ATTRS, remove
-                split_style[i] = ""
+                split_style.remove(style)
+                continue
             else:
                 if style_name in self.LIVECARTA_STYLE_ATTRS_MAPPING:
                     # function that converts our data
@@ -157,7 +158,7 @@ class StyleReader:
 
         split_style = self.update_inline_styles_to_livecarta_convention(
             split_style)
-        style = "; ".join(split_style)
+        style = "; ".join(split_style) if split_style else ""
         return style
 
     def process_inline_styles_in_html_soup(self, html_content):