NewsBlur/utils/feed_functions.py

70 lines
2.2 KiB
Python
Raw Normal View History

2009-06-16 03:08:55 +00:00
import datetime
import time
import sys
from utils import feedfinder
2009-06-16 03:08:55 +00:00
def encode(tstr):
""" Encodes a unicode string in utf-8
"""
if not tstr:
return ''
# this is _not_ pretty, but it works
try:
return tstr.encode('utf-8', "xmlcharrefreplace")
except UnicodeDecodeError:
# it's already UTF8.. sigh
return tstr.decode('utf-8').encode('utf-8')
def prints(tstr):
""" lovely unicode
"""
sys.stdout.write('%s\n' % (tstr.encode(sys.getdefaultencoding(),
'replace')))
sys.stdout.flush()
def mtime(ttime):
""" datetime auxiliar function.
"""
return datetime.datetime.fromtimestamp(time.mktime(ttime))
# From: http://www.poromenos.org/node/87
def levenshtein_distance(first, second):
"""Find the Levenshtein distance between two strings."""
if len(first) > len(second):
first, second = second, first
if len(second) == 0:
return len(first)
first_length = len(first) + 1
second_length = len(second) + 1
distance_matrix = [[0] * second_length for x in range(first_length)]
for i in range(first_length):
distance_matrix[i][0] = i
for j in range(second_length):
distance_matrix[0][j]=j
for i in xrange(1, first_length):
for j in range(1, second_length):
deletion = distance_matrix[i-1][j] + 1
insertion = distance_matrix[i][j-1] + 1
substitution = distance_matrix[i-1][j-1]
if first[i-1] != second[j-1]:
substitution += 1
distance_matrix[i][j] = min(insertion, deletion, substitution)
return distance_matrix[first_length-1][second_length-1]
def fetch_address_from_page(url, existing_feed=None):
from apps.rss_feeds.models import Feed
feed_finder_url = feedfinder.feed(url)
if feed_finder_url:
if existing_feed:
existing_feed.feed_address = feed_finder_url
existing_feed.save()
feed = existing_feed
else:
try:
feed = Feed.objects.get(feed_address=feed_finder_url)
except Feed.DoesNotExist:
feed = Feed(feed_address=feed_finder_url)
feed.save()
feed.update()
return feed