connection = Connection()
db = connection[DB_NAME]
coll = db[COLL_NAME]
#remove everything in the collection
coll.remove()
#populate database with data/biz.dat
for line in open('data/biz.dat'):
binfo_l = map(lambda s:s.strip(), line.split('\t'))
assert(len(binfo_l) == 2)
coll.insert({'name':binfo_l[0], 'url':binfo_l[1]})
#generate bloom filter based on 'url'
bfcoll = db[COLL_NAME] #get another collection object
bfcoll = bloomify(bfcoll, 'url')
#generate test files
T1 = 'data/testset'; gendata(1000,0.5, output_file=open(T1,'w'))
#function to performtimed tests
def timed_test(testf_path, coll):
tic = time.clock()
for line in open(testf_path):
binfo_l = map(lambda l:l.strip(), line.split("\t"))
assert(len(binfo_l)==2)
[bname, burl] = binfo_l
coll.find_one({'url':burl})
toc = time.clock()
return toc-tic
connection = Connection()
db = connection[DB_NAME]
coll = db[COLL_NAME]
#remove everything in the collection
coll.remove()
data = [{"name":"user_a", "value":1},
{"name":"user_b", "value":2},
{"name":"user_c", "value":3},
{"name":"user_d", "value":4}
]
#populate collection with documents (data)
coll.insert(data)
#generate bloom filter based on 'name'
bfcoll = bloomify(coll, "name")
#checks (all elements will be within the set):
for doc in data:
assert( coll._bf.contains(doc["name"]) ) #will return True
assert( None != coll.find_one(doc) ) #will not return None
#attempt to find something not in the database
qry = {"name":"XXXy"}
assert( not(coll._bf.contains("XXXy")) ) #SHOULD return False since XXX not in coll
assert( None == coll.find_one(qry) ) #will return None object since XXX not in coll