Commit 9c968275 authored by Jonas Schüppen's avatar Jonas Schüppen
Browse files

Added cli for all possibly running postprocessing steps

parent 918aa82c

generateBaseline/postprocessing.py

+139 −85
Original line number Diff line number Diff line 
import json

import os

import re

import sys

import warnings

from pathlib import Path

import zipfile

from lxml import etree

import tempfile

import shutil

from typing import Union

import argparse

import subprocess
@@ -16,13 +16,108 @@ from docx.oxml import OxmlElement 
from docx.oxml.ns import qn

from docx.shared import Cm



#from file_helper import get_all_files_from_dir

def parse_input(args_to_parse=None, description = None):

    """

    args_to_parse: list of arguments, e.g. ["input", "output"]

    """

    if args_to_parse is None:

        args_to_parse = ["input", "output"]



    parser = argparse.ArgumentParser(description=description)



    if args_to_parse is None:

        args_to_parse = []



    if "input" in args_to_parse:

        parser.add_argument(

            "input", "-i", "--input",

            metavar="INPUT_FILE",

            type=str,

            required=True,

            help="Path to input DOCX file"

        )



    if "output" in args_to_parse:

        parser.add_argument(

            "output", "-o", "--output",

            metavar="OUTPUT_FILE",

            type=str,

            required=False,

            help="Path to output DOCX file"

        )

    if "lib_office_image" in args_to_parse:

        parser.add_argument("lib_office_image", "--loi",

                            default="docx-field-refresh",

                            help="Docker image name (default: docx-field-refresh)")

    if "default_style" in args_to_parse:

        parser.add_argument("default_style", "--dstyle",

                            default="Normal",

                            help="Docker image name (default: docx-field-refresh)")



    if "tables_folder" in args_to_parse:

        parser.add_argument("tables_folder", "--tf",

                            default="input/document_content/tables",

                            help="folder containing the json files for tables")

    args = parser.parse_args()



    # check input file

    input_file_path = Path.cwd() / args.input

    file_suffix = input_file_path.suffix

    print("Input file:\t", input_file_path)



    if not os.path.exists(input_file_path):

        print("Error: Input file doesn't exist")

        sys.exit()  # exit if input file does't exist



    if file_suffix != '.docx':

        print('Error: Input file with wrong file suffix! Expect file suffix .docx')

        sys.exit()  # exit if input file is not a markdown file



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")

    # check output file

    # create output file if output file does't exist

    if args.output is None:

        print("Using input file as output file")

        args.output = args.input



    output_file_path = Path.cwd() / args.output

    file_suffix = output_file_path.suffix

    file_path = output_file_path.parent

    print("Output file:\t", output_file_path)



    if file_suffix != '.docx':

        print('Error: Output file with wrong file suffix! Expect file suffix .docx')

        sys.exit()  # exit if output file is not a markdown file



    if not os.path.exists(output_file_path):

        print("Output file doesn't exist. Create empty output file.")

        Path(file_path).mkdir(parents=True, exist_ok=True)  # make directory

        Path(output_file_path).touch()  # touch empty file



    # Return requested args

    return tuple(getattr(args, name) for name in args_to_parse)



def update_toc_cli():

    docx_input, docx_output = parse_input(description="Update a DOCX table of contents.")

    update_toc(docx_input, docx_output)



def turn_table_contents_cli():

    docx_input, docx_output = parse_input(description="Searches for cells beginning with [rotate] and turns the content 90 degree counterclockwise")

    postprocess_table_content(docx_input, docx_output)



def refresh_docx_fields_cli():

    docx_input, image = parse_input(["input", "lib_office_image"],description="Refresh DOCX fields using LibreOffice in Docker (in-place).")

    refresh_docx_fields(docx_input, image)



def update_formats_cli():

    docx_input, docx_output, style = parse_input(["input", "output", "default_style"], description="Set unformated paragraphs to standard styling.")

    apply_standard_style_to_unformatted_paragraphs(docx_input, docx_output, style)



def table_width_adjustment_cli():

    docx_input, docx_output, tables_folder = parse_input(["input", "output", "tables_folder"],

                                                 description="Set the width of table columns according to values in json or if non there to be equal.")

    table_widths_adjustment(docx_input, docx_output, tables_folder)



def apply_standard_style_to_unformatted_paragraphs(docx_input, docx_output, standard_style_name = "Normal"):

    # Filter warning

    warnings.filterwarnings(

        "ignore",
@@ -31,7 +126,7 @@ def apply_standard_style_to_unformatted_paragraphs(config): 
    )





    doc = Document(docx_path)

    doc = Document(docx_input)

    changed = 0



    for p in doc.paragraphs:
@@ -42,7 +137,7 @@ def apply_standard_style_to_unformatted_paragraphs(config): 
            changed += 1



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

    doc.save(output_path)

    doc.save(docx_output)



def rotate_cell_text(cell):

    # Hole oder erstelle <w:tcPr>
@@ -78,14 +173,6 @@ def postprocess_table_content(docx_path, output_path): 
                    rotate_cell_text(cell)

    doc.save(output_path)



def turn_table_contents_cli():

    parser = argparse.ArgumentParser(description="Searches for cells beginning with [rotate] and turns the content 90 degree counterclockwise")

    parser.add_argument("docx_input", help="Path to input DOCX file")

    parser.add_argument("docx_output", help="Path to output DOCX file")

    args = parser.parse_args()



    postprocess_table_content(args.docx_input, args.docx_output)



def refresh_docx_fields(input_path: str, image: str = "docx-field-refresh") -> str:

    """

    Refreshes fields in a DOCX file using LibreOffice inside a Docker container.
@@ -199,44 +286,6 @@ def refresh_docx_fields(input_path: str, image: str = "docx-field-refresh") -> s 
    return str(input_path)





def refresh_docx_fields_cli():

    

    parser = argparse.ArgumentParser(description="Refresh DOCX fields using LibreOffice in Docker (in-place).")

    parser.add_argument("input", help="Path to input DOCX file.")

    parser.add_argument("--image", default="docx-field-refresh", help="Docker image name (default: docx-field-refresh)")



    args = parser.parse_args()

    refresh_docx_fields(args.input, args.image)



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:

            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



    # Speichern unter neuem Namen

    doc.SaveAs(output_path)

    doc.Close()

    word.Quit()



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

    root = etree.fromstring(xml_data)
@@ -301,35 +350,40 @@ def update_toc(docx_input, docx_output): 
        if os.path.exists(tmp_path):

            os.remove(tmp_path)



def update_toc_cli():

    docx_input, docx_output = parse_input()

def get_all_files_from_dir(relative_path, ending=None, subfolder=True):

    """

    Gibt eine Liste aller Dateien im angegebenen Verzeichnis (und optional in Unterordnern) zurück,

    die eine bestimmte Endung haben.



    update_toc(docx_input, docx_output)

    Parameter:

        relative_path (str | Path): Pfad zum Verzeichnis (relativ oder absolut)

        ending (str | None): Dateiendung (z. B. '.txt' oder 'txt'). Wenn None, werden alle Dateien berücksichtigt.

        subfolder (bool): Wenn True, werden Unterordner durchsucht.



def parse_input():

    parser = argparse.ArgumentParser(description="Update a DOCX table of contents.")

    parser.add_argument('docx_input', '-i', '--input',

                        metavar='INPUT_FILE',

                        required=True,

                        type=str,

                        default=None,

                        help='Path to input DOCX file')

    Rückgabe:

        list[Path]: Liste von pathlib.Path-Objekten

    """

    base_path = Path(relative_path)

    if not base_path.exists():

        print(f"Error: Folder not found: {base_path}")



    parser.add_argument('docx_output', '-o', '--output',

                        metavar='OUTPUT_FILE',

                        required=False,

                        type=str,

                        default=None,

                        help='Path to output DOCX file')

    args = parser.parse_args()

    # Endung normalisieren (z. B. 'txt' → '.txt')

    if ending is not None:

        if not ending.startswith('.'):

            ending = '.' + ending



    return args.docx_input, args.docx_output

    # Auswahl der passenden Dateien

    pattern = "**/*" if subfolder else "*"

    files = [p for p in base_path.glob(pattern) if p.is_file()]



    if ending is None:

        return files

    else:

        return [f for f in files if f.suffix.lower() == ending.lower()]



def table_widths_adjustment(config):

    table_path = config.get("tables_folder")

    docx_path = config.get("output_docx")

    doc = Document(docx_path)



def table_widths_adjustment(docx_input, docx_output, tables_folder):

    doc = Document(docx_input)

    def get_table_caption(table):

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

        tbl = table._tbl
@@ -364,7 +418,7 @@ def table_widths_adjustment(config): 
        # 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.")

            print("Error: 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]
@@ -394,21 +448,21 @@ def table_widths_adjustment(config): 




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

    table_list = get_all_files_from_dir(table_path, "json")

    table_list = get_all_files_from_dir(tables_folder, "json")

    json_tables = []

    for table_path in table_list:

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

    for tables_folder in table_list:

        with open(tables_folder, "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}")

                print(f"Skipped {tables_folder}. 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")

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

            continue



        json_tables.append(data)
@@ -431,4 +485,4 @@ def table_widths_adjustment(config): 
            for i, width in enumerate(col_widths):

                cell = row.cells[i]

                cell.width = width

    doc.save(docx_path)
 
 No newline at end of file
 
    doc.save(docx_output)
 
 No newline at end of file

generateBaseline/setup.py

+4 −4
Original line number Diff line number Diff line
@@ -14,11 +14,11 @@ setup( 
            '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",

								#"update_references=postprocessing:update_word_fields",

        						"update_formats=postprocessing:update_formats_cli",

        						"turn_table_contents=postprocessing:turn_table_contents_cli",

        						"table_width_adjustment=postprocessing:table_widths_adjustment",

        						"check_multipage_tables=postprocessing:insert_page_break_before_long_tables",

        						"table_width_adjustment=postprocessing:table_width_adjustment_cli",

        						#"check_multipage_tables=postprocessing:insert_page_break_before_long_tables",

        						#"apply_etsi_styling: postprocessing:postprocess_etsi_styles",

        						"update_toc=postprocessing:update_toc_cli",

								"refresh_docx_fields=postprocessing:refresh_docx_fields_cli",