def testPairs(self):
t1 = IFBTree([(1, 10), (3, 30), (7, 70)])
t2 = IFBTree([(3, 30), (5, 50), (7, 7), (9, 90)])
allkeys = [1, 3, 5, 7, 9]
b1 = IFBucket(t1)
b2 = IFBucket(t2)
for x in t1, t2, b1, b2:
for key in x.keys():
self.assertEqual(key in allkeys, 1)
for y in t1, t2, b1, b2:
for w1, w2 in (0, 0), (1, 10), (10, 1), (2, 3):
# Test the union.
expected = []
for key in allkeys:
if x.has_key(key) or y.has_key(key):
result = x.get(key, 0) * w1 + y.get(key, 0) * w2
expected.append((key, result))
expected.sort()
got = mass_weightedUnion([(x, w1), (y, w2)])
self.assertEqual(expected, list(got.items()))
got = mass_weightedUnion([(y, w2), (x, w1)])
self.assertEqual(expected, list(got.items()))
# Test the intersection.
expected = []
for key in allkeys:
if x.has_key(key) and y.has_key(key):
result = x[key] * w1 + y[key] * w2
expected.append((key, result))
expected.sort()
got = mass_weightedIntersection([(x, w1), (y, w2)])
self.assertEqual(expected, list(got.items()))
got = mass_weightedIntersection([(y, w2), (x, w1)])
self.assertEqual(expected, list(got.items()))
def search_phrase(self, phrase):
wids = self._lexicon.termToWordIds(phrase)
cleaned_wids = self._remove_oov_wids(wids)
if len(wids) != len(cleaned_wids):
# At least one wid was OOV: can't possibly find it.
return IFBTree()
scores = self._search_wids(wids)
hits = mass_weightedIntersection(scores)
if not hits:
return hits
code = widcode.encode(wids)
result = IFBTree()
for docid, weight in hits.items():
docwords = self._docwords[docid]
if docwords.find(code) >= 0:
result[docid] = weight
return result
def search_phrase(self, phrase):
wids = self._lexicon.termToWordIds(phrase)
cleaned_wids = self._remove_oov_wids(wids)
if len(wids) != len(cleaned_wids):
# At least one wid was OOV: can't possibly find it.
return self.family.IF.BTree()
scores = self._search_wids(wids)
hits = mass_weightedIntersection(scores, self.family)
if not hits:
return hits
code = widcode.encode(wids)
result = self.family.IF.BTree()
for docid, weight in hits.items():
docwords = self._docwords[docid]
if docwords.find(code) >= 0:
result[docid] = weight
return result
def testMany(self):
import random
N = 15 # number of IFBTrees to feed in
L = []
commonkey = N * 1000
allkeys = {commonkey: 1}
for i in range(N):
t = IFBTree()
t[commonkey] = i
for j in range(N-i):
key = i + j
allkeys[key] = 1
t[key] = N*i + j
L.append((t, i+1))
random.shuffle(L)
allkeys = allkeys.keys()
allkeys.sort()
# Test the union.
expected = []
for key in allkeys:
sum = 0
for t, w in L:
if t.has_key(key):
sum += t[key] * w
expected.append((key, sum))
# print 'union', expected
got = mass_weightedUnion(L)
self.assertEqual(expected, list(got.items()))
# Test the intersection.
expected = []
for key in allkeys:
sum = 0
for t, w in L:
if t.has_key(key):
sum += t[key] * w
else:
break
else:
# We didn't break out of the loop so it's in the intersection.
expected.append((key, sum))
# print 'intersection', expected
got = mass_weightedIntersection(L)
self.assertEqual(expected, list(got.items()))
def executeQuery(self, index):
L = []
Nots = []
for subnode in self.getValue():
if subnode.nodeType() == "NOT":
r = subnode.getValue().executeQuery(index)
# If None, technically it matches every doc, but we treat
# it as if it matched none (we want
# real_word AND NOT stop_word
# to act like plain real_word).
if r is not None:
Nots.append((r, 1))
else:
r = subnode.executeQuery(index)
# If None, technically it matches every doc, so needn't be
# included.
if r is not None:
L.append((r, 1))
set = mass_weightedIntersection(L, index.family)
if Nots:
notset = mass_weightedUnion(Nots, index.family)
set = index.family.IF.difference(set, notset)
return set
def executeQuery(self, index):
L = []
Nots = []
for subnode in self.getValue():
if subnode.nodeType() == "NOT":
r = subnode.getValue().executeQuery(index)
# If None, technically it matches every doc, but we treat
# it as if it matched none (we want
# real_word AND NOT stop_word
# to act like plain real_word).
if r is not None:
Nots.append((r, 1))
else:
r = subnode.executeQuery(index)
# If None, technically it matches every doc, so needn't be
# included.
if r is not None:
L.append((r, 1))
set = mass_weightedIntersection(L)
if Nots:
notset = mass_weightedUnion(Nots)
set = difference(set, notset)
return set
def _callFUT(self, L, family=_marker):
from zope.index.text.setops import mass_weightedIntersection
if family is _marker:
return mass_weightedIntersection(L)
return mass_weightedIntersection(L, family)
def testEmptyLists(self):
self.assertEqual(len(mass_weightedIntersection([])), 0)
self.assertEqual(len(mass_weightedUnion([])), 0)
def _callFUT(self, L, family=_marker):
from zope.index.text.setops import mass_weightedIntersection
if family is _marker:
return mass_weightedIntersection(L)
return mass_weightedIntersection(L, family)