Commit b9a56316 authored by Marco Cavalli's avatar Marco Cavalli
Browse files

feat: capitalize words in links when needed

parent 20656421

md_to_docx_converter/md_to_html_2.lua

+4 −1
Original line number Diff line number Diff line
@@ -131,7 +131,10 @@ function MultipleClauses(el) 
            --this may be the start of a list of multiple clauses

            if elem.text:lower():find("clauses") then

                clausesFound = true

                newContent:insert(elem)

                -- Replace plain "clauses" text with a span containing it

                local clausesSpan = pandoc.Span({pandoc.Str(elem.text)})

                clausesSpan.classes = pandoc.List({"clauses-marker"})

                newContent:insert(clausesSpan)

                goto continue

            end

md_to_docx_converter/src/to_html/postprocessing.py

+40 −1
Original line number Diff line number Diff line
@@ -508,7 +508,6 @@ def fix_custom_tags(soup: BeautifulSoup): 
                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)
@@ -564,6 +563,45 @@ def add_custom_link_to_images(soup: BeautifulSoup, images_mapping: dict) -> Beau 


    return soup



def fix_capitalization_in_links(soup: BeautifulSoup) -> BeautifulSoup:

    """

    Ensures that the capitalization in the link text matches the capitalization in the href attribute.

    """

    a_tags = soup.find_all("a")

    span_clauses_tags = soup.find_all("span", class_="clauses-marker")

    for a in a_tags:

        text = a.get_text()

        if not text:

            continue



        if not text.startswith(("figure", "table", "clause", "annex")):

            continue

        

        # First case: it is the first word in a sentence

        if a.parent and a.parent.contents[0] == a:

            capitalized_text = text.capitalize()

            a.string = capitalized_text



        # Second case: it is after a period

        elif a.previous_sibling and isinstance(a.previous_sibling, NavigableString):

            prev_text = a.previous_sibling.strip()

            if prev_text.endswith(".") or prev_text.endswith("!") or prev_text.endswith("?"):

                capitalized_text = text.capitalize()

                a.string = capitalized_text

    for span in span_clauses_tags:

        text = span.get_text()

        if not text:

            continue

        if span.parent and span.parent.contents[0] == span:

            capitalized_text = text.capitalize()

            span.string = capitalized_text

        elif span.previous_sibling and isinstance(span.previous_sibling, NavigableString):

            prev_text = span.previous_sibling.strip()

            if prev_text.endswith(".") or prev_text.endswith("!") or prev_text.endswith("?"):

                capitalized_text = text.capitalize()

                span.string = capitalized_text

    return soup





def postprocess(html_dir: str):

    """
@@ -637,6 +675,7 @@ def postprocess(html_dir: str): 
            

            try:

                soup = add_custom_link_to_images(soup, images_mapping)

                soup = fix_capitalization_in_links(soup)

            except ValueError as e:

                print(p_error(f"Error in file {filename}:"))

                print(p_error(str(e)))