diff options
Diffstat (limited to 'src/web/utils.py')
| -rwxr-xr-x | src/web/utils.py | 19 |
1 files changed, 1 insertions, 18 deletions
diff --git a/src/web/utils.py b/src/web/utils.py index 2d9378c0..e0ab8d81 100755 --- a/src/web/utils.py +++ b/src/web/utils.py @@ -1,7 +1,7 @@ #! /usr/bin/env python #-*- coding: utf-8 -*- -# jarr - A Web based news aggregator. +# JARR - A Web based news aggregator. # Copyright (C) 2010-2016 Cédric Bonhomme - https://www.cedricbonhomme.org # # For more information : https://github.com/JARR-aggregator/JARR @@ -28,7 +28,6 @@ __license__ = "AGPLv3" # # This file provides functions used for: -# - detection of duplicate articles; # - import from a JSON file; # - generation of tags cloud; # - HTML processing. @@ -279,22 +278,6 @@ def tag_cloud(tags): (min(1 + count * 7 / max([tag[1] for tag in tags]), 7), word, format(count, ',d'), word)) \ for (word, count) in tags]) -def compare_documents(feed): - """ - Compare a list of documents by pair. - Pairs of duplicates are sorted by "retrieved date". - """ - duplicates = [] - for pair in itertools.combinations(feed.articles, 2): - date1, date2 = pair[0].date, pair[1].date - if clear_string(pair[0].title) == clear_string(pair[1].title) and \ - (date1 - date2) < timedelta(days = 1): - if pair[0].retrieved_date < pair[1].retrieved_date: - duplicates.append((pair[0], pair[1])) - else: - duplicates.append((pair[1], pair[0])) - return duplicates - def search_feed(url): """ Search a feed in a HTML page. |