remove_toc.py

"""
This script removes TOC and Back-to-top links generated by the
generate_toc.py script.

author: Fabrizio Musacchio (https://www.fabriziomusacchio.com)
date:  19.02.2022
"""
# %% IMPORTS
import sys
import re
# %% MAIN ROUTINE
Current_Markdown_Text = sys.argv[1]

"""
    The following text conversion and re-conversion has to be performed,
    as the shell echo of multiline text within the Applescript introduces
    a a type of linebreaks other than "\n", which is not interpretable by
    Python. The following procedure re-introduces the "\n"-linebreaks:
"""
Current_Markdown_New_Text = Current_Markdown_Text.splitlines()
Current_Markdown_New_Text_tmp = [Current_Markdown_New_Text[0]]
#Current_Markdown_New_Text_tmp.append(Current_Markdown_New_Text[0])

# Scan the text for "#" and create the TOC:
for line_idx, line in enumerate(Current_Markdown_New_Text[1:]):
    line_idx+=1
    if line.startswith("#"):
        # remove any id in headlines from a previous run:
        line_cleaned = re.sub(r'\s*\[.*\]', '', line)

        # update the current cleaned heading:
        Current_Markdown_New_Text_tmp.append(line_cleaned)
    elif line=="<div style='text-align: right;'><a href='#toc'>Toc &#8593;</a></div>":
        # remove any previously place Back-to-top link and some whitespace:
        if Current_Markdown_New_Text_tmp[-1] == '':
            del Current_Markdown_New_Text_tmp[-1]
    else:
        Current_Markdown_New_Text_tmp.append(line)

# remove the TOC-section:
for line_idx, line in enumerate(Current_Markdown_New_Text_tmp):
    if line == '<!-- TOC START -->':
        toc_start_idx = line_idx
    if line == '<!-- TOC END -->':
        toc_end_idx = line_idx
if toc_start_idx!=0 and toc_end_idx!=0:
    Current_Markdown_New_Text_tmp2 = []
    Current_Markdown_New_Text_tmp2+=Current_Markdown_New_Text_tmp[0:toc_start_idx]
    Current_Markdown_New_Text_tmp2+=Current_Markdown_New_Text_tmp[toc_end_idx+1:]
else:
    Current_Markdown_New_Text_tmp2 = Current_Markdown_New_Text_tmp

Current_Markdown_New_Text = '\n'.join(Current_Markdown_New_Text_tmp2)
print(Current_Markdown_New_Text)