class TestBTreesUnicode(unittest.TestCase):
""" test unicode"""
def setUp(self):
#setup an OOBTree with some unicode strings
from BTrees.OOBTree import OOBTree
self.s = b'dreit\xe4gigen'.decode('latin1')
self.data = [
(b'alien', 1),
(b'k\xf6nnten', 2),
(b'fox', 3),
(b'future', 4),
(b'quick', 5),
(b'zerst\xf6rt', 6),
(u'dreit\xe4gigen', 7),
]
self.tree = OOBTree()
for k, v in self.data:
if isinstance(k, bytes):
k = k.decode('latin1')
self.tree[k] = v
def testAllKeys(self):
# check every item of the tree
for k, v in self.data:
if isinstance(k, bytes):
k = k.decode(encoding)
self.assertIn(k, self.tree)
self.assertEqual(self.tree[k], v)
def testUnicodeKeys(self):
# try to access unicode keys in tree
k, v = self.data[-1]
self.assertEqual(k, self.s)
self.assertEqual(self.tree[k], v)
self.assertEqual(self.tree[self.s], v)
def testAsciiKeys(self):
# try to access some "plain ASCII" keys in the tree;
# they get upconverted to unicode for comparison on Python 2
for k, v in self.data[0], self.data[2]:
self.assertIsInstance(k, bytes)
if bytes is str:
self.assertEqual(self.tree[k], v)
else:
with self.assertRaises(TypeError):
self.tree.__getitem__(k)
def __getitem__(self, item):
if not isinstance(item, slice):
return OOBTree.__getitem__(self, item)
# Performance shortcuts
if item.start is None and item.stop is None:
if item.step == -1:
return reversed(OOBTree.values(self))
if item.step == 1 or item.step is None:
return OOBTree.values(self)
keys = OOBTree.keys(self, min=item.start, max=item.stop)
if item.step and item.step < 0:
return (OOBTree.__getitem__(self, keys[i - 1])
for i in range(len(keys), 0, item.step))
return (OOBTree.__getitem__(self, keys[i])
for i in range(0, len(keys), item.step or 1))
def __getitem__(self, key):
return OOBTree.__getitem__(self, key).data
def __getitem__(self, key):
if key == 'display':
return OOBTree.__getitem__(self, key)
else:
return OOBTree.__getitem__(self, key).data
self.row_num = []
self.business_id = []
def insert(self,row,b_id):
self.row_num.append(row)
self.business_id.append(b_id)
datas = pandas.read_csv(path+"review-1m.csv")
for i in range (datas.shape[0]):
print(i)
row = i
b_id = datas.iloc[row]['business_id']
key = datas.iloc[row]['useful']
if t.has_key(key):
c = t.__getitem__(key)
c.insert(row,b_id)
t.update({key:c})
else:
c = content()
c.insert(row,b_id)
t.update({key:c})
funny_file = open(r'../test/useful.pkl', 'wb')
pickle.dump(t, funny_file)
funny_file.close()
#c = content(1)
#c.insert(1,100,200)
#c.insert(1,200,300)
#print(c.key,c.row_num,c.business_id)
#
def __getitem__(self, key):
return OOBTree.__getitem__(self, key).data
self.row_num = []
self.business_id = []
def insert(self, row, b_id):
self.row_num.append(row)
self.business_id.append(b_id)
datas = pandas.read_csv(path + "review-1m.csv")
for i in range(datas.shape[0]):
print(i)
row = i
b_id = datas.iloc[row]['business_id']
key = datas.iloc[row]['useful']
if t.has_key(key):
c = t.__getitem__(key)
c.insert(row, b_id)
t.update({key: c})
else:
c = content()
c.insert(row, b_id)
t.update({key: c})
funny_file = open(r'../test/useful.pkl', 'wb')
pickle.dump(t, funny_file)
funny_file.close()
#c = content(1)
#c.insert(1,100,200)
#c.insert(1,200,300)
#print(c.key,c.row_num,c.business_id)
#
def __getitem__(self, key):
if key == 'display':
return OOBTree.__getitem__(self, key)
else:
return OOBTree.__getitem__(self, key).data