etherpump/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 normalize_pad_name (n):
    if '?' in n:
        n = n.split('?', 1)[0]
    if '/' in n:
        n = n.split('/', 1)[0]
    return n

def linkify (src, urlify=urlify):

    collect = []

    def s (m):
        contents = strip_tags(m.group(1))
        contents = normalize_pad_name(contents)
        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
    ## strip slashes as well!! (/timeslider)
    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)