def test_column_query():
schema = fields.Schema(id=fields.STORED,
a=fields.ID(sortable=True),
b=fields.NUMERIC(sortable=True))
with TempIndex(schema, "columnquery") as ix:
with ix.writer(codec=W3Codec()) as w:
w.add_document(id=1, a=u("alfa"), b=10)
w.add_document(id=2, a=u("bravo"), b=20)
w.add_document(id=3, a=u("charlie"), b=30)
w.add_document(id=4, a=u("delta"), b=40)
w.add_document(id=5, a=u("echo"), b=50)
w.add_document(id=6, a=u("foxtrot"), b=60)
with ix.searcher() as s:
def check(q):
return [s.stored_fields(docnum)["id"] for docnum in q.docs(s)]
q = query.ColumnQuery("a", u("bravo"))
assert check(q) == [2]
q = query.ColumnQuery("b", 30)
assert check(q) == [3]
q = query.ColumnQuery("a", lambda v: v != u("delta"))
assert check(q) == [1, 2, 3, 5, 6]
q = query.ColumnQuery("b", lambda v: v > 30)
assert check(q) == [4, 5, 6]
def test_hit_column():
# Not stored
schema = fields.Schema(text=fields.TEXT())
ix = RamStorage().create_index(schema)
with ix.writer() as w:
w.add_document(text=u("alfa bravo charlie"))
with ix.searcher() as s:
r = s.search(query.Term("text", "alfa"))
assert len(r) == 1
hit = r[0]
with pytest.raises(KeyError):
_ = hit["text"]
# With column
schema = fields.Schema(text=fields.TEXT(sortable=True))
ix = RamStorage().create_index(schema)
with ix.writer(codec=W3Codec()) as w:
w.add_document(text=u("alfa bravo charlie"))
with ix.searcher() as s:
r = s.search(query.Term("text", "alfa"))
assert len(r) == 1
hit = r[0]
assert hit["text"] == u("alfa bravo charlie")
def test_multivalue():
schema = fields.Schema(s=fields.TEXT(sortable=True),
n=fields.NUMERIC(sortable=True))
ix = RamStorage().create_index(schema)
with ix.writer(codec=W3Codec()) as w:
w.add_document(s=u("alfa foxtrot charlie").split(), n=[100, 200, 300])
w.add_document(s=u("juliet bravo india").split(), n=[10, 20, 30])
with ix.reader() as r:
scr = r.column_reader("s")
assert list(scr) == ["alfa", "juliet"]
ncr = r.column_reader("n")
assert list(ncr) == [100, 10]
def test_column_field():
schema = fields.Schema(a=fields.TEXT(sortable=True),
b=fields.COLUMN(columns.RefBytesColumn()))
with TempIndex(schema, "columnfield") as ix:
with ix.writer(codec=W3Codec()) as w:
w.add_document(a=u("alfa bravo"), b=b("charlie delta"))
w.add_document(a=u("bravo charlie"), b=b("delta echo"))
w.add_document(a=u("charlie delta"), b=b("echo foxtrot"))
with ix.reader() as r:
assert r.has_column("a")
assert r.has_column("b")
cra = r.column_reader("a")
assert cra[0] == u("alfa bravo")
assert type(cra[0]) == text_type
crb = r.column_reader("b")
assert crb[0] == b("charlie delta")
assert type(crb[0]) == bytes_type
def default_codec(*args, **kwargs):
from whoosh.codec.whoosh3 import W3Codec
return W3Codec(*args, **kwargs)
def test_plaintext_codec():
pytest.importorskip("ast")
from whoosh.codec.plaintext import PlainTextCodec
from whoosh.codec.whoosh3 import W3Codec
ana = analysis.StemmingAnalyzer()
schema = fields.Schema(a=fields.TEXT(vector=True, sortable=True),
b=fields.STORED,
c=fields.NUMERIC(stored=True, sortable=True),
d=fields.TEXT(analyzer=ana, spelling=True))
st = RamStorage()
ix = st.create_index(schema)
with ix.writer(codec=W3Codec()) as w:
w.add_document(a=u("alfa bravo charlie"), b="hello", c=100,
d=u("quelling whining echoing"))
w.add_document(a=u("bravo charlie delta"), b=1000, c=200,
d=u("rolling timing yelling"))
w.add_document(a=u("charlie delta echo"), b=5.5, c=300,
d=u("using opening pulling"))
w.add_document(a=u("delta echo foxtrot"), b=True, c=-100,
d=u("aching selling dipping"))
w.add_document(a=u("echo foxtrot india"), b=None, c=-200,
d=u("filling going hopping"))
with ix.reader() as r:
assert r.has_column("a")
c = r.column_reader("a")
assert c[2] == u("charlie delta echo")
w = ix.writer(codec=PlainTextCodec())
w.commit(optimize=True)
with ix.searcher() as s:
reader = s.reader()
r = s.search(query.Term("a", "delta"))
assert len(r) == 3
assert [hit["b"] for hit in r] == [1000, 5.5, True]
assert (" ".join(s.field_terms("a"))
== "alfa bravo charlie delta echo foxtrot india")
assert reader.doc_field_length(2, "a") == 3
cfield = schema["c"]
assert type(cfield), fields.NUMERIC
sortables = list(cfield.sortable_terms(reader, "c"))
assert sortables
assert ([cfield.from_bytes(t) for t in sortables]
== [-200, -100, 100, 200, 300])
assert reader.has_column("a")
c = reader.column_reader("a")
assert c[2] == u("charlie delta echo")
assert reader.has_column("c")
c = reader.column_reader("c")
assert list(c) == [100, 200, 300, -100, -200]
assert s.has_vector(2, "a")
v = s.vector(2, "a")
assert " ".join(v.all_ids()) == "charlie delta echo"