def test_span_characters():
ix = get_index()
with ix.searcher() as s:
pq = Phrase("text", ["bravo", "echo"])
m = pq.matcher(s)
while m.is_active():
orig = " ".join(s.stored_fields(m.id())["text"])
for span in m.spans():
startchar, endchar = span.startchar, span.endchar
assert orig[startchar:endchar] == "bravo echo"
m.next()
def test_posting_phrase():
schema = fields.Schema(name=fields.ID(stored=True), value=fields.TEXT)
storage = RamStorage()
ix = storage.create_index(schema)
writer = ix.writer()
writer.add_document(name=u("A"), value=u("Little Miss Muffet sat on a tuffet"))
writer.add_document(name=u("B"), value=u("Miss Little Muffet tuffet"))
writer.add_document(name=u("C"), value=u("Miss Little Muffet tuffet sat"))
writer.add_document(name=u("D"), value=u("Gibberish blonk falunk miss muffet sat tuffet garbonzo"))
writer.add_document(name=u("E"), value=u("Blah blah blah pancakes"))
writer.commit()
with ix.searcher() as s:
def names(results):
return sorted([fields['name'] for fields in results])
q = Phrase("value", [u("little"), u("miss"), u("muffet"), u("sat"), u("tuffet")])
m = q.matcher(s)
assert_equal(m.__class__.__name__, "SpanNearMatcher")
r = s.search(q)
assert_equal(names(r), ["A"])
assert_equal(len(r), 1)
q = Phrase("value", [u("miss"), u("muffet"), u("sat"), u("tuffet")])
assert_equal(names(s.search(q)), ["A", "D"])
q = Phrase("value", [u("falunk"), u("gibberish")])
r = s.search(q)
assert_equal(names(r), [])
assert_equal(len(r), 0)
q = Phrase("value", [u("gibberish"), u("falunk")], slop=2)
assert_equal(names(s.search(q)), ["D"])
q = Phrase("value", [u("blah")] * 4)
assert_equal(names(s.search(q)), []) # blah blah blah blah
q = Phrase("value", [u("blah")] * 3)
m = q.matcher(s)
assert_equal(names(s.search(q)), ["E"])
def test_phrase_score():
schema = fields.Schema(name=fields.ID(stored=True), value=fields.TEXT)
storage = RamStorage()
ix = storage.create_index(schema)
writer = ix.writer()
writer.add_document(name=u("A"), value=u("Little Miss Muffet sat on a tuffet"))
writer.add_document(name=u("D"), value=u("Gibberish blonk falunk miss muffet sat tuffet garbonzo"))
writer.add_document(name=u("E"), value=u("Blah blah blah pancakes"))
writer.add_document(name=u("F"), value=u("Little miss muffet little miss muffet"))
writer.commit()
with ix.searcher() as s:
q = Phrase("value", [u("little"), u("miss"), u("muffet")])
m = q.matcher(s)
assert_equal(m.id(), 0)
score1 = m.weight()
assert score1 > 0
m.next()
assert_equal(m.id(), 3)
assert m.weight() > score1
