def test_limit_actually_limits(self):
collection = BsonCollection(
os.path.dirname(os.path.realpath(__file__)) + '/' +
config['bson']['valid'])
collection.get_iterator()
count = len(
list(tweet for tweet in collection.set_limit(5).get_iterator()))
self.assertEqual(5, count)
def test_collection_filters_custom_filter_filters_something(self): collection = BsonCollection(os.path.dirname(os.path.realpath(__file__)) +'/'+ config['bson']['valid']) long_len = len(list(collection.get_iterator())) def is_tweet_a_retweet(tweet): if 'retweeted' in tweet and tweet['retweeted']: return True else: return False collection.set_custom_filter(is_tweet_a_retweet) shorter_len = len(list(collection.get_iterator())) #there should be fewer retweets than all tweets. self.assertTrue(long_len > shorter_len)
def test_collection_filters_custom_filter_properly_applies_filter(self):
collectionone = BsonCollection(
os.path.dirname(os.path.realpath(__file__)) + '/' +
config['bson']['valid'])
full_collection_len = len(list(collectionone.get_iterator()))
def is_tweet_a_retweet(tweet):
if 'retweeted' in tweet and tweet['retweeted']:
return True
else:
return False
num_retweets = len(
list(
collectionone.set_custom_filter(
is_tweet_a_retweet).get_iterator()))
collectiontwo = BsonCollection(
os.path.dirname(os.path.realpath(__file__)) + '/' +
config['bson']['valid'])
def is_not_a_retweet(tweet):
if 'retweeted' in tweet and tweet['retweeted']:
return False
else:
return True
num_non_retweets = len(
list(
collectiontwo.set_custom_filter(
is_not_a_retweet).get_iterator()))
#the numbes of retweets and non retweets should add up to the whole collection
self.assertEqual(num_retweets + num_non_retweets, full_collection_len)
def test_collection_filters_custom_filter_filters_something(self):
collection = BsonCollection(
os.path.dirname(os.path.realpath(__file__)) + '/' +
config['bson']['valid'])
long_len = len(list(collection.get_iterator()))
def is_tweet_a_retweet(tweet):
if 'retweeted' in tweet and tweet['retweeted']:
return True
else:
return False
collection.set_custom_filter(is_tweet_a_retweet)
shorter_len = len(list(collection.get_iterator()))
#there should be fewer retweets than all tweets.
self.assertTrue(long_len > shorter_len)
def test_bson_collection_custom_filter_filters(self): collectionone = BsonCollection(os.path.dirname(os.path.realpath(__file__)) +'/'+ config['bson']['valid']) full_collection_len = len(list(collectionone.get_iterator())) def is_tweet_a_retweet(tweet): if 'retweeted' in tweet and tweet['retweeted']: return True else: return False num_retweets = len(list(collectionone.set_custom_filter(is_tweet_a_retweet).get_iterator())) collectiontwo = BsonCollection(os.path.dirname(os.path.realpath(__file__)) +'/'+ config['bson']['valid']) def is_not_a_retweet(tweet): if 'retweeted' in tweet and tweet['retweeted']: return False else: return True num_non_retweets = len(list(collectiontwo.set_custom_filter(is_not_a_retweet).get_iterator())) #the numbes of retweets and non retweets should add up to the whole collection self.assertEqual(num_retweets + num_non_retweets, full_collection_len)
def test_limit_actually_limits(self): collection = BsonCollection(os.path.dirname(os.path.realpath(__file__)) +'/'+ config['bson']['valid']) collection.get_iterator() count = len(list(tweet for tweet in collection.set_limit(5).get_iterator())) self.assertEqual(5, count)
def test_iterator_returns_tweets(self): collection = BsonCollection(os.path.dirname(os.path.realpath(__file__)) +'/'+ config['bson']['valid']) self.assertTrue(len(list(collection.get_iterator())) > 0)
