hoedown toc rewriting script

hoedown toc rewriter.py

# this script was tested to work with Hoedown 3.0.7.
from collections import defaultdict
import subprocess
import re

p = re.compile(r'^(<a href="#toc_[0-9]+">)(.+)(<\/a>\n)$')

# takes a bunch of html lines starting and ending with ul tags
# return a single html string starting and ending with div tags
def rewrite_toc(lines):
    first_line = """<div id="toc" class="toc" ><div class="toctitle" ><h2>Contents</h2></div>"""
    result = [first_line]
    last_line = "</div>"
    level = 0
    count = defaultdict(int)
    for line in lines:
        if line == "<ul>\n":
            level += 1
            count[level] = 0
        if line == "</ul>\n":
            level -= 1
        if line == "<li>\n":
            count[level] += 1
            numbering = str(count[1])
            for i in range(2, level + 1):
                numbering += "." + str(count[i])
        if line.startswith("<a "):
            match_groups = p.match(line).groups()
            if len(match_groups) != 3:
                print("ERROR: Not expected number of match groups")
                exit(1)
            span_tocnumber_open = '<span class="tocnumber">'
            span_toctext_open = '<span class="toctext">'
            span_close = "</span>"
            numbering_html = span_tocnumber_open + numbering + span_close
            toctext_html = span_toctext_open + match_groups[1] + span_close
            toprint = match_groups[0] + numbering_html + " " + toctext_html + match_groups[2]
            result.append(toprint)
        else:
            result.append(line)

    result.append(last_line)
    result = ''.join(result)
    return result



cmd = ["/path/to/hoedown", "--html-toc", "--toc-level", "500", "input_file.md"]
result = subprocess.Popen(cmd, shell=False, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
lines = [line.decode("utf-8")  for line in result.stdout.readlines()]




print("===========")
print(rewrite_toc(lines))