Commit 29d024df authored by Marco Cavalli's avatar Marco Cavalli
Browse files

feat: front-page is added when generating the word

parent ed0b9245

md_to_docx_converter/front_page_template.docx

0 → 100644
+120 KiB

File added.

No diff preview for this file type.

View file

md_to_docx_converter/src/constants.py

+15 −0
Original line number Diff line number Diff line
@@ -161,3 +161,18 @@ BAD_COLON_GROUP_REGEX = ( 
# Match lines that start with : or :: and are not followed by letters

BAD_DIV_DELINEATOR_REGEX = r"^\s*(?::{1,2})(?![a-zA-Z])"

# endregion



TEXT_TO_REPLACE_IN_FRONTPAGE = [

    "WORKITEMNAME",

    "VERSION_NO",

    "DATE",

    "{{TYPEDOCUMENT}}",

    "{{TITLE}}",

    "{{PART}}",

    "{{SUBPART}}",

    "{{RELEASE}}",

    "{{WORKITEM}}",

    "{{KEYWORDS}}",

    "yyyy",

    "-mm",

]
 
 No newline at end of file

md_to_docx_converter/src/to_docx/include_frontpage.py

0 → 100644
+74 −0
Original line number Diff line number Diff line 
from docx import Document

from docx.enum.text import WD_BREAK

from docxcompose.composer import Composer

from docx.oxml import parse_xml

from docx.oxml.ns import nsdecls

import os

from src.constants import TEXT_TO_REPLACE_IN_FRONTPAGE

from bs4 import BeautifulSoup, Tag, NavigableString



def scrap_replacements_from_html(front_page_html_file: str) -> dict:

    replacements = {}

    with open(front_page_html_file, 'r', encoding='utf-8') as f:

        soup = BeautifulSoup(f, 'html.parser')

        for key in TEXT_TO_REPLACE_IN_FRONTPAGE:

            element = soup.find(attrs={"data-replace": key})

            if element:

                if key == "DATE":

                    # Special handling for DATE to format it as needed

                    date_text = element.get_text(strip=True)

                    print(f"Found date: {date_text}")

                    split_date = date_text.split('-')

                    YEAR = split_date[0] if len(split_date) > 0 else ''

                    MONTH = split_date[1] if len(split_date) > 1 else ''

                    replacements["yyyy"] = YEAR

                    replacements["-mm"] = f"-{MONTH}"

                else:

                    replacements[key] = element.get_text(strip=True)

    return replacements



def include_frontpage(output_path):

    def merge_docx(output_path: str, *input_paths: str):

        master = Document(input_paths[0])

        composer = Composer(master)

        for path in input_paths[1:]:

            p = master.add_paragraph()

            run = p.add_run()

            run.add_break(WD_BREAK.PAGE)

            

            composer.append(Document(path))

        composer.save(output_path)





    def replace_placeholders(file_path: str, replacements: dict, output_path: str = None):

        doc = Document(file_path)

        

        for paragraph in doc.paragraphs:

            for key in TEXT_TO_REPLACE_IN_FRONTPAGE:

                value = replacements.get(key, "")

                if key in paragraph.text:

                    for run in paragraph.runs:

                        run.text = run.text.replace(key, value)

        

        doc.save(output_path or file_path)



    def set_update_fields_on_open(doc_path: str):

        """Force to update fields when opening the document in Word."""

        doc = Document(doc_path)

        

        settings = doc.settings.element

        update_fields = parse_xml(

            f'<w:updateFields {nsdecls("w")} w:val="true"/>'

        )

        settings.append(update_fields)

        

        doc.save(doc_path)



    front_page_html = os.path.join(os.path.dirname(output_path), "html", "front-page.html")

    replacements = scrap_replacements_from_html(front_page_html)

    document = os.path.join(output_path, "document.docx")

    front_page_filled = os.path.join(output_path, "front_page_filled.docx")

    replace_placeholders("front_page_template.docx", replacements, front_page_filled)

    merge_docx(document, front_page_filled, document)

    # set_update_fields_on_open(document)

    os.remove(front_page_filled)
 
 No newline at end of file

md_to_docx_converter/src/to_docx/postprocessing.py

+5 −2
Original line number Diff line number Diff line 
import re

import re, os

from docx import Document

from docx.shared import Pt

from docx.document import Document as Doc
@@ -27,6 +27,7 @@ from src.constants import ( 
    UNDERLINE_TAGS,

    WITH_SPACE,

)

from src.to_docx.include_frontpage import include_frontpage

from src.utils import get_bold_italic_underline_css_classes
@@ -577,7 +578,6 @@ def postprocess(docx_dir: str): 
    ### Arguments

    - `docx_dir`: The absolute or relative path at which the generated Docx was saved

    """



    doc: Doc = Document(docx_dir)



    doc = format_references(doc)
@@ -589,3 +589,6 @@ def postprocess(docx_dir: str): 
    doc = set_keep_with_next_false(doc)



    doc.save(docx_dir)



    containing_folder = os.path.dirname(docx_dir)

    include_frontpage(containing_folder)

md_to_docx_converter/src/to_html/postprocessing.py

+90 −0
Original line number Diff line number Diff line
@@ -5,6 +5,7 @@ from src.utils import ( 
    apply_renaming_logic,

    get_dirty_filenames_mapping_with_expected_filenames,

    p_error,

    p_warning,

)



from src.constants import ABBREVIATION_CLASS
@@ -307,6 +308,92 @@ def format_tables(soup: BeautifulSoup) -> BeautifulSoup: 
                    tr['class'] = existing_classes + ['bg-striped-row']

    return soup



def format_front_page(soup: BeautifulSoup) -> BeautifulSoup:

    ZA = soup.find_all("div", class_="ZA")

    try:

        p = ZA[0].find("p")

        children = list(p.children)

        try:

            # TITLE IN HEADER

            header = children[0]

            header['data-replace'] = 'WORKITEMNAME'

        except IndexError:

            print(p_warning("front-page is missing WORKITEMNAME information."))

        # Version in HEADER

        try:

            version = children[1]

            new_span = soup.new_tag("span")

            version.wrap(new_span)

            new_span['data-replace'] = 'VERSION_NO'

        except IndexError:

            print(p_warning("front-page is missing VERSION_NO information."))

        # DATE IN HEADER

        try:

            date = children[2]

            text = date.get_text(strip=True)

            text = text.replace("(", "").replace(")", "")

            open_bracket = NavigableString("(")

            date_text = new_span = soup.new_tag("span")

            date_text['data-replace'] = 'DATE'

            date_text.string = text

            close_bracket = NavigableString(")")

            date.append(open_bracket)

            date.append(date_text)

            date.append(close_bracket)

        except IndexError:

            print(p_warning("front-page is missing DATE information."))

    except IndexError:

        print(p_warning("front-page is missing the section with WORKITEMNAME, VERSION_NO, and DATE information."))



    ZT = soup.find_all("div", class_="ZT")

    try:

        # first is title

        ZT[0]['data-replace'] = '{{TITLE}}'

    except IndexError:

        print(p_warning("front-page is missing TITLE information."))

    try:

        # second is part

        ZT[1]['data-replace'] = '{{PART}}'

    except IndexError:

        print(p_warning("front-page is missing PART information."))

    try:

        # third is subpart

        ZT[2]['data-replace'] = '{{SUBPART}}'

    except IndexError:

        print(p_warning("front-page is missing SUBPART information."))

    try:

        # fourth is release

        ZT[3]['data-replace'] = '{{RELEASE}}'

    except IndexError:

        print(p_warning("front-page is missing RELEASE information."))





    ZB = soup.find_all("div", class_="ZB")

    try:

        ZB[0]['data-replace'] = '{{TYPEDOCUMENT}}'

    except IndexError:

        print(p_warning("front-page is missing TYPEDOCUMENT information."))



    TAC = soup.find_all("div", class_="TAC")

    try:

        children = list(TAC[0].children)

        try:

            # SECOND is WORKITEM

            workitem = children[3]

            workitem['data-replace'] = '{{WORKITEM}}'

        except IndexError:

            print(p_warning("front-page is missing WORKITEM information."))

        # FOURTH is KEYWORDS

        try:

            keywords = children[7]

            keywords['data-replace'] = '{{KEYWORDS}}'

        except IndexError:

            print(p_warning("front-page is missing KEYWORDS information."))

    except IndexError:

        print(p_warning("front-page is missing the section with WORKITEM and KEYWORDS information."))



    return soup





def add_links_to_references_in_text(soup):

    def reform_broken_links_in_text(soup: BeautifulSoup):
@@ -811,6 +898,9 @@ def postprocess(html_dir: str): 
        soup = format_examples_and_notes(soup)

        soup = format_tables(soup)



        if new_filename == "front-page.html":

            soup = format_front_page(soup)



        if (

            new_filename.replace(".html", "") in files_with_references

        ):  # Reference-specific formatting