Commit ea6db6ba authored by Miguel Angel Reina Ortega's avatar Miguel Angel Reina Ortega
Browse files

new update toc function

parent 37746c11

generateBaseline/pandocFilter.py

+10 −6
Original line number Diff line number Diff line
@@ -211,21 +211,25 @@ def correctTableSeparators(progress: Progress, mdLines: list[str]) -> list[str]: 
	return _lines





def process(document:str, outDirectory:str) -> None:

def process(args) -> None:

	with Progress(TextColumn('{task.description}'),  TimeElapsedColumn()) as progress:

		mdLines = readMDFile(progress, document)

		mdLines = readMDFile(progress, args.document)

		mdLines = correctTOC(progress, mdLines)

		mdLines = replaceTableCaptions(progress, mdLines)

		mdLines = replaceFigureCaptions(progress, mdLines)

		if args.figure_paths:

			mdLines = replaceFiguresPathSvgToPng(progress, mdLines)

		mdLines = replaceLineBreaks(progress, mdLines)

		if args.table_separators:

			mdLines = correctTableSeparators(progress, mdLines)

		writeMDFile(progress, mdLines, document, outDirectory)

		writeMDFile(progress, mdLines, args.document, args.outDirectory)





def main(args=None):

	# Parse command line arguments

	parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)

	parser.add_argument('-ts', '--table-separators',        action='store_true', required=False, default=False, help="Correct table separators")

	parser.add_argument('-fp', '--figure-paths',        action='store_true', required=False, default=False, help="Replace figure paths")

	parser.add_argument('--outdir', '-o', action='store', dest='outDirectory', default = 'out', metavar = '<output directory>',  help = 'specify output directory')

	parser.add_argument('document',  help = 'document to parse')

	args = parser.parse_args()
@@ -233,7 +237,7 @@ def main(args=None): 
	# Process documents and print output

	os.makedirs(args.outDirectory, exist_ok = True)



	process(args.document, args.outDirectory)

	process(args)



if __name__ == '__main__':

    sys.exit(main())
 
 No newline at end of file

generateBaseline/postprocessing.py

+99 −36
Original line number Diff line number Diff line
@@ -3,6 +3,10 @@ import os 
import re

import warnings

from pathlib import Path

import zipfile

from lxml import etree

import tempfile

import shutil



import win32com.client #pip install pywin32
@@ -11,7 +15,6 @@ from docx.oxml import OxmlElement 
from docx.oxml.ns import qn

from docx.shared import Cm



from errors import ErrorHandler, Level, Mode

from file_helper import get_all_files_from_dir
@@ -37,7 +40,7 @@ def apply_standard_style_to_unformatted_paragraphs(config): 
            p.style = standard_style_name

            changed += 1



    ErrorHandler()(f"Changed style to '{standard_style_name}' for {changed} paragraphs.")

    print(f'Changed style to {standard_style_name} for {changed} paragraphs.')

    doc.save(output_path)



def rotate_cell_text(cell):
@@ -86,7 +89,7 @@ def update_word_fields(config_path: dict|str): 
    relativer_pfad = Path(docx_path)

    docx_absolute_path = relativer_pfad.resolve()

    if not os.path.isfile(docx_absolute_path):

        ErrorHandler()(f"File not found: {docx_absolute_path}", Level.ERROR)

        print(f'File not found: {docx_absolute_path}')



    # Word starten

    word = win32com.client.Dispatch("Word.Application")
@@ -105,7 +108,7 @@ def update_word_fields(config_path: dict|str): 


        # Schließen

        doc.Close()

        ErrorHandler()(f"Fields in '{docx_absolute_path}' updated and saved")

        print(f'Fields in {docx_absolute_path} updated and saved')

    finally:

        word.Quit()
@@ -128,7 +131,7 @@ def insert_page_break_before_long_tables(config): 
        end_page = doc.Range(end - 1, end - 1).Information(3)



        if end_page > start_page:

            ErrorHandler()(f"Table {i + 1} is on a page break: {start_page} -> {end_page}", Level.INFO)

            print(f'Table {i + 1} is on a page break: {start_page} -> {end_page}')

            # Seitenumbruch einfügen

            para = doc.Range(start, start)

            para.InsertBreak(7)  # wdPageBreak = 7
@@ -138,39 +141,99 @@ def insert_page_break_before_long_tables(config): 
    doc.Close()

    word.Quit()



def update_toc_level(config):

    docx_path = config.get("output_docx")

    word = win32com.client.Dispatch("Word.Application")

    word.Visible = False

def format_toc_header(xml_data, ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}):

    root = etree.fromstring(xml_data)



    doc = word.Documents.Open(docx_path)

    counter = 0

    # Find <w:pStyle w:val="TOCHeading">

    for pstyle in root.xpath('.//w:pStyle[@w:val="TOCHeading"]', namespaces=ns):

        # Change it to be <w:pStyle w:val="TT">

        old_text = pstyle

        pstyle.set(f"{{{ns['w']}}}val", "TT")

        counter+=1

    print(f'Changed Style "TOCHeading" to "TT" {counter} times')

    return etree.tostring(root, xml_declaration=True, encoding="UTF-8", standalone="yes")



    # Wenn kein TOC vorhanden ist, kannst du eins hinzufügen:

    if doc.TablesOfContents.Count == 0:

        # Inhaltsverzeichnis am Anfang des Dokuments einfügen

        doc.TablesOfContents.Add(

            Range=doc.Range(0, 0),

            UseHeadingStyles=True,

            UpperHeadingLevel=1,

            LowerHeadingLevel=9,  # 👉 bis Heading 9

            UseHyperlinks=True,

            HidePageNumbersInWeb=False,

            UseOutlineLevels=True

        )

    # Vorhandenes TOC anpassen

    toc = doc.TablesOfContents(1)

    #Formating heading -> ToDo: last line not working so skipped for the moment

    #toc_range = toc.Range

    #heading_para = toc_range.Paragraphs(1)

    #heading_para.Style = doc.Styles("Heading 1")

    #set level range from 1-9

    toc.UpperHeadingLevel = 1

    toc.LowerHeadingLevel = 9

    toc.Update()



    doc.SaveAs(docx_path)

    doc.Close()

    word.Quit()

def update_toc_level(xml_data, ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}):

    root = etree.fromstring(xml_data)

    new_range = "1-9"

    # Regex for \o "x-y" with x and y being numbers

    pattern = re.compile(r'(?<=\\o )"\d+-\d+"\s*')





    # Loop over all elements to find "TOC"

    for elem in root.xpath('.//w:instrText', namespaces=ns):

        if 'TOC' in elem.text:

            old_text = elem.text

            elem.text = pattern.sub('', elem.text)



            print(f'Changed TOC: {old_text} → {elem.text}')



    return etree.tostring(root, xml_declaration=True, encoding="UTF-8", standalone="yes")



def update_toc(docx_input, docx_output):

    # read xml

    with zipfile.ZipFile(docx_input, 'r') as zin:

        xml_data = zin.read("word/document.xml")



    xml_data = update_toc_level(xml_data)



    xml_data = format_toc_header(xml_data)



    # create temp file

    tmp_fd, tmp_path = tempfile.mkstemp(suffix=".docx")

    os.close(tmp_fd)  # Datei wird nur über zipfile geöffnet



    try:

        # write new docx to temp file

        with zipfile.ZipFile(docx_input, 'r') as zin, zipfile.ZipFile(tmp_path, 'w', zipfile.ZIP_DEFLATED) as zout:

            for item in zin.infolist():

                if item.filename != "word/document.xml":

                    data = zin.read(item.filename)

                    zout.writestr(item.filename, data)

            zout.writestr("word/document.xml", xml_data)



        # Write to output file

        shutil.move(tmp_path, docx_output)



    finally:

        # delete temp file if still existing

        if os.path.exists(tmp_path):

            os.remove(tmp_path)



#def update_toc_level(config):

#    docx_path = config.get("output_docx")

#    word = win32com.client.Dispatch("Word.Application")

#    word.Visible = False

#

#    doc = word.Documents.Open(docx_path)

#

#    # Wenn kein TOC vorhanden ist, kannst du eins hinzufügen:

#    if doc.TablesOfContents.Count == 0:

#        # Inhaltsverzeichnis am Anfang des Dokuments einfügen

#        doc.TablesOfContents.Add(

#            Range=doc.Range(0, 0),

#            UseHeadingStyles=True,

#            UpperHeadingLevel=1,

#            LowerHeadingLevel=9,  # 👉 bis Heading 9

#            UseHyperlinks=True,

#            HidePageNumbersInWeb=False,

#            UseOutlineLevels=True

#        )

#    # Vorhandenes TOC anpassen

#    toc = doc.TablesOfContents(1)

#    #Formating heading -> ToDo: last line not working so skipped for the moment

#    #toc_range = toc.Range

#    #heading_para = toc_range.Paragraphs(1)

#    #heading_para.Style = doc.Styles("Heading 1")

#    #set level range from 1-9

#    toc.UpperHeadingLevel = 1

#    toc.LowerHeadingLevel = 9

#    toc.Update()



#    doc.SaveAs(docx_path)

#    doc.Close()

#    word.Quit()



def table_widths_adjustment(config):

    table_path = config.get("tables_folder")

generateBaseline/setup.py

+1 −1
Original line number Diff line number Diff line
@@ -20,7 +20,7 @@ setup( 
        						"table_width_adjustment=postprocessing:table_widths_adjustment",

        						"check_multipage_tables=postprocessing:insert_page_break_before_long_tables",

        						#"apply_etsi_styling: postprocessing:postprocess_etsi_styles",

        						"update_toc_level=postprocessing:update_toc_level",

        						"update_toc=postprocessing:update_toc",

			]

            }