def test_copyfield():
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"b": "c"}, None))
assert_equal(text_type(qp.parse("hello b:matt")), "(a:hello AND b:matt AND c:matt)")
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"b": "c"}, syntax.AndMaybeGroup))
assert_equal(text_type(qp.parse("hello b:matt")), "(a:hello AND (b:matt ANDMAYBE c:matt))")
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"b": "c"}, syntax.RequireGroup))
assert_equal(text_type(qp.parse("hello (there OR b:matt)")), "(a:hello AND (a:there OR (b:matt REQUIRE c:matt)))")
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"a": "c"}, syntax.OrGroup))
assert_equal(text_type(qp.parse("hello there")), "((a:hello OR c:hello) AND (a:there OR c:there))")
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"b": "c"}, mirror=True))
assert_equal(text_type(qp.parse("hello c:matt")), "(a:hello AND (c:matt OR b:matt))")
qp = qparser.QueryParser("a", None)
qp.add_plugin(plugins.CopyFieldPlugin({"c": "a"}, mirror=True))
assert_equal(text_type(qp.parse("hello c:matt")), "((a:hello OR c:hello) AND (c:matt OR a:matt))")
ana = analysis.RegexAnalyzer(r"\w+") | analysis.DoubleMetaphoneFilter()
fmt = formats.Frequency()
schema = fields.Schema(name=fields.KEYWORD, name_phone=fields.FieldType(fmt, ana, multitoken_query="or"))
qp = qparser.QueryParser("name", schema)
qp.add_plugin(plugins.CopyFieldPlugin({"name": "name_phone"}))
assert_equal(text_type(qp.parse(u("spruce view"))), "((name:spruce OR name_phone:SPRS) AND (name:view OR name_phone:F OR name_phone:FF))")
def test_vector_phrase(self):
ana = analysis.StandardAnalyzer()
ftype = fields.FieldType(formats.Frequency(ana),
formats.Positions(ana),
scorable=True)
schema = fields.Schema(name=fields.ID(stored=True), value=ftype)
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()
searcher = ix.searcher()
def names(results):
return sorted([fields['name'] for fields in results])
q = query.Phrase("value",
[u"little", u"miss", u"muffet", u"sat", u"tuffet"])
sc = q.scorer(searcher)
self.assertEqual(sc.__class__.__name__, "VectorPhraseScorer")
self.assertEqual(names(searcher.search(q)), ["A"])
q = query.Phrase("value", [u"miss", u"muffet", u"sat", u"tuffet"])
self.assertEqual(names(searcher.search(q)), ["A", "D"])
q = query.Phrase("value", [u"falunk", u"gibberish"])
self.assertEqual(names(searcher.search(q)), [])
q = query.Phrase("value", [u"gibberish", u"falunk"], slop=2)
self.assertEqual(names(searcher.search(q)), ["D"])
#q = query.Phrase("value", [u"blah"] * 4)
#self.assertEqual(names(searcher.search(q)), []) # blah blah blah blah
q = query.Phrase("value", [u"blah"] * 3)
self.assertEqual(names(searcher.search(q)), ["E"])
def get_index():
global _ix
if _ix is not None:
return _ix
charfield = fields.FieldType(formats.Characters(),
analysis.SimpleAnalyzer(),
scorable=True, stored=True)
schema = fields.Schema(text=charfield)
st = RamStorage()
_ix = st.create_index(schema)
w = _ix.writer()
for ls in permutations(domain, 4):
w.add_document(text=u(" ").join(ls), _stored_text=ls)
w.commit()
return _ix
def _roundtrip(content, format_, astype, ana=None):
with TempStorage("roundtrip") as st:
codec = default_codec()
seg = codec.new_segment(st, "")
ana = ana or analysis.StandardAnalyzer()
field = fields.FieldType(format=format_, analyzer=ana)
fw = codec.field_writer(st, seg)
fw.start_field("f1", field)
for text, _, weight, valuestring in sorted(field.index(content)):
fw.start_term(text)
fw.add(0, weight, valuestring, None)
fw.finish_term()
fw.finish_field()
fw.close()
tr = codec.terms_reader(st, seg)
ps = []
for fieldname, btext in tr.terms():
m = tr.matcher(fieldname, btext, format_)
ps.append((field.from_bytes(btext), m.value_as(astype)))
tr.close()
return ps