Commit acbab9b3 authored by Marco Cavalli's avatar Marco Cavalli
Browse files

feat: support sequences of above and below special links

parent e704c035

md_to_docx_converter/md_to_html_3.lua

+19 −6
Original line number Diff line number Diff line
@@ -21,7 +21,13 @@ end 


function countPlusChars(str)

    local count = 0

    str:gsub("%+", function() count = count + 1 end)

    str:gsub("%+%+%+", function() count = count + 1 end)

    return count

end



function countWordChars(text, word)

    local count = 0

    text:gsub(word, function() count = count + 1 end)

    return count

end
@@ -32,17 +38,24 @@ function CustomTagsToLinks(el, prefix) 
  for _, child in ipairs(children) do

    if child.t == "Str" and child.text:find(prefix .. "+++") then



      if child.text:find("Clause") and (child.text:find("below") or child.text:find("above")) then

      if child.text:find("Clause") and (child.text:find("+++below") or child.text:find("+++above")) then

        -- flash an error and stop execution, they are only allowed when there are only 2 parts

        error(string.format("%s\nInvalid reference: 'below' and 'above' are only allowed for Tables and Figures.", pandoc.utils.stringify(child)))

      end



      if child.text:find("+++below") or child.text:find("+++above") then

        local plusCount = countPlusChars(child.text)

      if plusCount > 3 and (child.text:find("below") or child.text:find("above")) then

        if plusCount > 1 and countWordChars(child.text, "+++below") ~= plusCount and countWordChars(child.text, "+++above") ~= plusCount then

          -- flash an error and stop execution, they are only allowed when there are only 2 parts

        error(string.format("%s\nInvalid reference: 'below' and 'above' are only allowed within the same file, for custom references that have the (Table|Figure)+++(below|above) format.", pandoc.utils.stringify(child)))

          error(string.format("%s\nInvalid reference: 'below' and 'above' are only allowed within the same file, for custom references that have the (Table|Figure)+++(below|above)[+++(below|above)]+ format. You can't mix up below and after in the same link.", pandoc.utils.stringify(child)))

        end



        local html_link = string.format('<a href="#%s">%s</a>', child.text, child.text)

        new_content:insert(pandoc.RawInline('html', html_link))

        goto continue

      end





      local remaining_text = child.text



      -- check if there is some text before the link (punctuation or words) and keep it

md_to_docx_converter/src/to_html/postprocessing.py

+22 −14
Original line number Diff line number Diff line
@@ -504,15 +504,19 @@ def fix_custom_tags(soup: BeautifulSoup): 
    for a in a_tags:

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

        if href.endswith("below"):

            count_below = href.count("+++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)

            if next_element:

                prefix = "Table_" if is_table else "Figure_"

                string_to_be_replaced = f"{prefix}below"

                new_a_text = next_element["id"].replace(prefix, "")

                a["href"] = href.replace(string_to_be_replaced, next_element["id"])

                a.string = a.string.replace("below", new_a_text)

            next_nth_element = a

            for _ in range(count_below):

                next_nth_element = next_nth_element.find_next("div", class_=class_name, id=True)

            if next_nth_element:

                prefix = "Table" if is_table else "Figure"

                postfix = "+++below" * count_below

                string_to_be_replaced = f"{prefix}{postfix}"

                new_a_text = next_nth_element["id"].replace(prefix + "_", " ")

                a["href"] = href.replace(string_to_be_replaced, next_nth_element["id"])

                a.string = a.string.replace(postfix, new_a_text)

            else:

                # flash an error

                print(
@@ -525,15 +529,19 @@ def fix_custom_tags(soup: BeautifulSoup): 
                )

                os._exit(1)

        elif href.endswith("above"):

            count_above = href.count("+++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)

            if previous_element:

                prefix = "Table_" if is_table else "Figure_"

                string_to_be_replaced = f"{prefix}above"

                new_a_text = previous_element["id"].replace(prefix, "")

                a["href"] = href.replace(string_to_be_replaced, previous_element["id"])

                a.string = a.string.replace("above", new_a_text)

            next_nth_element = a

            for _ in range(count_above):

                next_nth_element = next_nth_element.find_previous("div", class_=class_name, id=True)

            if next_nth_element:

                prefix = "Table" if is_table else "Figure"

                postfix = "+++above" * count_above

                string_to_be_replaced = f"{prefix}{postfix}"

                new_a_text = next_nth_element["id"].replace(prefix + "_", " ")

                a["href"] = href.replace(string_to_be_replaced, next_nth_element["id"])

                a.string = a.string.replace(postfix, new_a_text)

            else:

                # flash an error

                print(