#!/usr/bin/python

import time
import feedparser
import sys
import re

def utf8_lead_byte(b):
    '''A UTF-8 intermediate byte starts with the bits 10xxxxxx.'''
    return (b & 0xC0) != 0x80

def utf8_byte_truncate(text, max_bytes):
    '''If text[max_bytes] is not a lead byte, back up until a lead byte is
    found and truncate before that character.'''
    utf8 = text.encode('utf8')
    if len(utf8) <= max_bytes:
        return utf8
    i = max_bytes
    while i > 0 and not utf8_lead_byte(utf8[i]):
        i -= 1
    return utf8[:i]

url = sys.argv[1]
feed = feedparser.parse(url)['entries']

while not feed:
    time.sleep(900)
    feed = feedparser.parse(url)['entries']

old = []

for item in feed[::-1]:
    old.append(item['link'])

max1 = 356 # :Twitter!<10>@<63> PRIVMSG #piraatit :(<author>) <title> https://twitter.com/<author>/status/<19>

while True:
    time.sleep(900)
    feed = feedparser.parse(url)['entries']
    for item in feed[4::-1]:
        if {'link', 'author', 'title'}.issubset(item) and item['link'] not in old:
            title = re.sub('(https?://)?pic\.twitter.com/\S+', '', re.sub('\n+\s*', ' ', item['title']))
            author = item['author'].replace('@', '')
            maxlength = max1 - 2*(len(author)-2)
            if len(title.encode('utf-8')) > maxlength:
                title = ' '.join(utf8_byte_truncate(title, maxlength-1).decode('utf-8').split(' ')[0:-1])+'…'
            print(
                author,
                title,
                item['link'],
                flush=True
            )
            old.append(item['link'])
    old = old[-100:]