Adding new features

import json

import os

import re

import warnings

from pathlib import Path

import win32com.client #pip install pywin32

from docx import Document  #pip install python-docx

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

def apply_standard_style_to_unformatted_paragraphs(config):

    docx_path = config.get("output_docx")

    output_path = config.get("output_docx")

    standard_style_name = config.get("standard_style_name", "etsi_standard")

    # Filter warning

    warnings.filterwarnings(

        "ignore",

        category=UserWarning,

        message=re.escape("style lookup by style_id is deprecated. Use style name as key instead.")

    )

    doc = Document(docx_path)

    changed = 0

    for p in doc.paragraphs:

        current_style = p.style.name if p.style else None

        # Prüfe, ob Stil nicht 'Standard' ist

        if current_style == "Body Text":

            p.style = standard_style_name

            changed += 1

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

    doc.save(output_path)

def rotate_cell_text(cell):

    # Hole oder erstelle <w:tcPr>

    tcPr = cell._element.find(qn('w:tcPr'))

    if tcPr is None:

        tcPr = OxmlElement('w:tcPr')

        cell._element.insert(0, tcPr)

    # Erstelle oder ersetze <w:textDirection w:val="btLr"/>

    text_dir = tcPr.find(qn('w:textDirection'))

    if text_dir is None:

        text_dir = OxmlElement('w:textDirection')

        tcPr.append(text_dir)

    text_dir.set(qn('w:val'), 'btLr')  # bottom-to-top, left-to-right

def clean_and_set_text(cell, new_text):

    # Entferne alle vorhandenen Paragraphen

    for p in cell.paragraphs:

        p._element.getparent().remove(p._element)

    # Füge neuen Absatz mit dem bereinigten Text hinzu

    cell.add_paragraph(new_text)

def postprocess_table_content(config):

    docx_path = config.get("output_docx")

    output_path = config.get("output_docx")

    doc = Document(docx_path)

    for table in doc.tables:

        for row in table.rows:

            for cell in row.cells:

                if cell.text.strip().startswith("[rotate]"):

                    # Entferne den Marker und setze neuen Text

                    new_text = cell.text.replace("[rotate]", "").strip()

                    clean_and_set_text(cell, new_text)

                    rotate_cell_text(cell)

    doc.save(output_path)

def update_word_fields(config_path: dict|str):

    if os.path.isfile(config_path):

        docx_path = config_path

    else:

        docx_path = config_path.get("output_docx")

    # Prüfen, ob Datei existiert

    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)

    # Word starten

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

    word.Visible = False  # unsichtbar im Hintergrund

    try:

        # Dokument öffnen

        doc = word.Documents.Open(str(docx_absolute_path))

        # Alle Felder im Dokument aktualisieren

        for field in doc.Fields:

            field.Update()

        # Dokument speichern

        doc.Save()

        # Schließen

        doc.Close()

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

    finally:

        word.Quit()

def insert_page_break_before_long_tables(config):

    docx_path = config.get("output_docx")

    output_path = config.get("output_docx")

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

    word.Visible = False

    doc = word.Documents.Open(docx_path)

    for i, table in enumerate(doc.Tables):

        # Tabellenbereich abrufen

        start = table.Range.Start

        end = table.Range.End

        # Seitenzahl berechnen

        start_page = doc.Range(start, start).Information(3)  # wdActiveEndPageNumber = 3

        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)

            # Seitenumbruch einfügen

            para = doc.Range(start, start)

            para.InsertBreak(7)  # wdPageBreak = 7

    # Speichern unter neuem Namen

    doc.SaveAs(output_path)

    doc.Close()

    word.Quit()

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")

    docx_path = config.get("output_docx")

    doc = Document(docx_path)

    def get_table_caption(table):

        """Liest den Alternativtext-Titel (Caption) aus einer Tabelle."""

        tbl = table._tbl

        tblPr = tbl.tblPr

        if tblPr is None:

            return None  # Tabelle hat keine Eigenschaften

        # Suche nach <w:tblCaption w:val="...">

        caption_el = tblPr.find(qn("w:tblCaption"))

        if caption_el is not None:

            return caption_el.get(qn("w:val"))

        # Manche Word-Versionen speichern den Text als direktes Element ohne w:val

        for el in tblPr:

            if el.tag == qn("w:tblCaption"):

                return el.text or None

        return None

    def percent_to_cm(width_percentages, total_width_cm):

        """

        Wandelt Prozentangaben (z. B. [30, 40, 30]) in absolute cm-Werte um.

        Args:

            width_percentages (list[float]): Prozentwerte (Summe kann ein beliebiger positiver wert (>0) sein)

            total_width_cm (float): Gesamtbreite der Tabelle in cm

        Returns:

            list[float]: Spaltenbreiten in cm

        """

        # Falls Prozente als Ganzzahlen angegeben sind, normalisieren wir sie

        total_percent = sum(width_percentages)

        if total_percent == 0:

            ErrorHandler()("sum of percent-values is 0.")

        # Umrechnen auf relative cm-Werte

        widths_cm = [Cm((p / total_percent) * total_width_cm) for p in width_percentages]

        return widths_cm

    def get_json_data(json_data_array, value, matching_json_field):

        """

        Sucht in einer Liste von JSON-Dictionaries nach einem bestimmten Feldwert.

        Args:

            json_data_array (list[dict]): Liste von JSON-Objekten

            value (str): Der gesuchte Wert

            matching_json_field (str): Name des JSON-Feldes, in dem gesucht werden soll

        Returns:

            dict | None: Das gefundene JSON-Objekt oder None, falls kein Treffer

        """

        for item in json_data_array:

            if not isinstance(item, dict):

                continue  # Überspringt ungültige Einträge

            if(matching_json_field==caption):

                if value.endswith(item.get(matching_json_field)):

                    return item

            if item.get(matching_json_field) == value:

                return item

        return None

    # preparing json_table list -> getting caption and width from table-json files

    table_list = get_all_files_from_dir(table_path, "json")

    json_tables = []

    for table_path in table_list:

        with open(table_path, "r", encoding="utf-8") as f:

            try:

                data = json.load(f)

            except json.JSONDecodeError as e:

                ErrorHandler()(f"Skipped {table_path}. Error in reading file: {e}")

                continue

        caption = data.get("caption")

        widths = data.get("column_width")

        if not caption or not widths:

            ErrorHandler()(f"Skipping {table_path} – as caption and/or column_width are not set as expected")

            continue

        json_tables.append(data)

    for table in doc.tables:

        # Get matching of table in docx and json

        docx_caption=get_table_caption(table)

        data = get_json_data(json_tables, docx_caption, "caption")

        #found json

        if(data is not None):

            total_width = data.get("total_width", 16.88)

            col_widths_percent = data.get("column_width")

        else:

            total_width = 16.88

            col_widths_percent = [1] * len(table.rows[0].cells)

        col_widths = percent_to_cm(col_widths_percent, total_width)

        # Jede Zelle in der jeweiligen Spalte auf Breite setzen

        for row in table.rows:

            for i, width in enumerate(col_widths):

                cell = row.cells[i]

                cell.width = width

    doc.save(docx_path)

 No newline at end of file

            'console_scripts' : ['pandocFilter=pandocFilter:main',

								'generateTOC=generateTOC:main',

								'svg2png=svg2png:main',

								"update_references=postprocessing:update_word_fields",

        						"update_formats=postprocessing:apply_standard_style_to_unformatted_paragraphs",

        						"turn_table_contents=postprocessing:postprocess_table_content",

        						"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",

			]

            }