Commit 20656421 authored by Marco Cavalli's avatar Marco Cavalli
Browse files

fix: reorder logic in if statement to prevent false friends with dynamic links

parent 4190b972

md_to_docx_converter/src/to_html/postprocessing.py

+7 −6
Original line number Diff line number Diff line
@@ -477,11 +477,7 @@ def fix_custom_tags(soup: BeautifulSoup): 


    for a in a_tags:

        href = a.get("href", "")

        if href.startswith("#") and href.find("root") != -1 and notAnImage(href): # when root is used in md

            new_id_prefix = f"{h1_tag['id']}"

            a["href"] = href.replace("root", new_id_prefix)

            a.string = a.string.replace("root", new_id_prefix)

        elif "below" in href:

        if href.endswith("below"):

            is_table = "Table" in href

            class_name = "TH" if is_table else "FL"

            next_element = a.find_next("div", class_=class_name, id=True)
@@ -496,7 +492,7 @@ def fix_custom_tags(soup: BeautifulSoup): 
                print(p_error(f"Error: Found a broken custom tag in file {h1_tag.string}"))

                print(p_error(f"Error: No next element found for '{a.string}'. There are not any figures/tables above this tag."))

                os._exit(1)

        elif "above" in href:

        elif href.endswith("above"):

            is_table = "Table" in href

            class_name = "TH" if is_table else "FL"

            previous_element = a.find_previous("div", class_=class_name, id=True)
@@ -511,6 +507,11 @@ def fix_custom_tags(soup: BeautifulSoup): 
                print(p_error(f"Error: Found a broken custom tag in file {h1_tag.string}"))

                print(p_error(f"Error: No previous element found for '{a.string}'. There are not any figures/tables above this tag."))

                os._exit(1)

        elif href.find("#") != -1 and href.find("root") != -1 and notAnImage(href): # when root is used in md

            print(href)

            new_id_prefix = f"{h1_tag['id']}"

            a["href"] = href.replace("root", new_id_prefix)

            a.string = a.string.replace("root", new_id_prefix)

    return soup



def extract_images_from_html(soup: BeautifulSoup) -> dict: