pppadump/linkify.py

from __future__ import print_function
import re, sys


def strip_tags (text):
	return re.sub(r"<.*?>", "", text)

def urlify (t, ext=".html"):
	return t.replace(" ", "_") + ext

def filename_to_padid (t):
	t = t.replace("_", " ")
	t = re.sub(r"\.html$", "", t)
	return t

def linkify (src, urlify=urlify):

	collect = []

	def s (m):
		contents = strip_tags(m.group(1))
		collect.append(contents)
		link = urlify(contents)
		# link = link.split("?", 1)[0]
		return "[[<a class=\"wikilink\" href=\"{0}\">{1}</a>]]".format(link, contents)

	# src = re.sub(r"\[\[([\w_\- ,]+?)\]\]", s, src)
	## question marks are ignored by etherpad, so split/strip it
	src = re.sub(r"\[\[(.+?)(\?.*)?\]\]", s, src)
	return (src, collect)


if __name__ == "__main__":
	src = sys.stdin.read()
	src, links = linkify(src)

	for l in links:
		print (l)

	print (src)