def test_multifilter():
f1 = analysis.LowercaseFilter()
f2 = analysis.PassFilter()
mf = analysis.MultiFilter(a=f1, b=f2)
ana = analysis.RegexTokenizer(r"\S+") | mf
text = u("ALFA BRAVO CHARLIE")
assert [t.text for t in ana(text, mode="a")] == ["alfa", "bravo", "charlie"]
assert [t.text for t in ana(text, mode="b")] == ["ALFA", "BRAVO", "CHARLIE"]
def test_multifilter():
iwf_for_index = analysis.IntraWordFilter(mergewords=True, mergenums=False)
iwf_for_query = analysis.IntraWordFilter(mergewords=False, mergenums=False)
mf = analysis.MultiFilter(index=iwf_for_index, query=iwf_for_query)
ana = analysis.RegexTokenizer() | mf | analysis.LowercaseFilter()
schema = fields.Schema(text=fields.TEXT(analyzer=ana, stored=True))
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text=u("Our BabbleTron5000 is great"))
w.commit()
with ix.searcher() as s:
hit = s.search(query.Term("text", "5000"))[0]
assert_equal(hit.highlights("text"),
'Our BabbleTron<b class="match term0">5000</b> is great')