def test_simple_search_after_reuse(self, dir_index):
index_dir, _ = dir_index
index = Index(schema(), str(index_dir))
query = index.parse_query("sea whale", ["title", "body"])
result = index.searcher().search(query, 10)
assert len(result.hits) == 1
def test_simple_search_after_reuse(self, dir_index):
index_dir, _ = dir_index
index = Index(schema(), str(index_dir))
query = index.parse_query("sea whale", ["title", "body"])
top_docs = tantivy.TopDocs(10)
result = index.searcher().search(query, top_docs)
assert len(result) == 1
def test_order_by_search(self):
schema = (SchemaBuilder()
.add_unsigned_field("order", fast="single")
.add_text_field("title", stored=True).build()
)
index = Index(schema)
writer = index.writer()
doc = Document()
doc.add_unsigned("order", 0)
doc.add_text("title", "Test title")
writer.add_document(doc)
doc = Document()
doc.add_unsigned("order", 2)
doc.add_text("title", "Final test title")
writer.add_document(doc)
doc = Document()
doc.add_unsigned("order", 1)
doc.add_text("title", "Another test title")
writer.add_document(doc)
writer.commit()
index.reload()
query = index.parse_query("test")
searcher = index.searcher()
result = searcher.search(query, 10, offset=2, order_by_field="order")
assert len(result.hits) == 1
result = searcher.search(query, 10, order_by_field="order")
assert len(result.hits) == 3
_, doc_address = result.hits[0]
searched_doc = index.searcher().doc(doc_address)
assert searched_doc["title"] == ["Final test title"]
_, doc_address = result.hits[1]
searched_doc = index.searcher().doc(doc_address)
assert searched_doc["title"] == ["Another test title"]
_, doc_address = result.hits[2]
searched_doc = index.searcher().doc(doc_address)
assert searched_doc["title"] == ["Test title"]
def create_index(dir=None):
# assume all tests will use the same documents for now
# other methods may set up function-local indexes
schema_ = schema()
index = Index(schema_, dir)
writer = index.writer()
# 2 ways of adding documents
# 1
doc = Document()
# create a document instance
# add field-value pairs
doc.add_text("title", "The Old Man and the Sea")
doc.add_text(
"body",
("He was an old man who fished alone in a skiff in"
"the Gulf Stream and he had gone eighty-four days "
"now without taking a fish."),
)
# print( int( datetime.timestamp(datetime.utcnow())) % 2**64 )
# doc.add_integer("timestamp", int(int( datetime.timestamp(datetime.utcnow())) % 2**64 ))
writer.add_document(doc)
# 2 use the built-in json support
# keys need to coincide with field names
doc = Document.from_dict({
"title":
"Of Mice and Men",
"body": ("A few miles south of Soledad, the Salinas River drops "
"in close to the hillside bank and runs deep and "
"green. The water is warm too, for it has slipped "
"twinkling over the yellow sands in the sunlight "
"before reaching the narrow pool. On one side of the "
"river the golden foothill slopes curve up to the "
"strong and rocky Gabilan Mountains, but on the valley "
"side the water is lined with trees—willows fresh and "
"green with every spring, carrying in their lower leaf "
"junctures the debris of the winter’s flooding; and "
"sycamores with mottled, white, recumbent limbs and "
"branches that arch over the pool"),
})
writer.add_document(doc)
doc = Document.from_dict({
"title": ["Frankenstein", "The Modern Prometheus"],
"body":
("You will rejoice to hear that no disaster has accompanied the commencement of an enterprise which you have regarded with such evil forebodings. I arrived here yesterday, and my first task is to assure my dear sister of my welfare and increasing confidence in the success of my undertaking. "
),
})
writer.add_document(doc)
writer.commit()
index.reload()
return index, schema_
def test_order_by_search_without_fast_field(self):
schema = (SchemaBuilder().add_unsigned_field("order").add_text_field(
"title", stored=True).build())
index = Index(schema)
writer = index.writer()
doc = Document()
doc.add_unsigned("order", 0)
doc.add_text("title", "Test title")
query = index.parse_query("test")
searcher = index.searcher()
result = searcher.search(query, 10, order_by_field="order")
assert len(result.hits) == 0
def test_create_readers(self):
# not sure what is the point of this test.
idx = Index(schema())
idx.config_reader("Manual", 4)
assert idx.searcher().num_docs == 0
# by default this is manual mode
writer = idx.writer(30000000, 1)
writer.add_document(Document(title="mytitle", body="mybody"))
writer.commit()
assert idx.searcher().num_docs == 0
# Manual is the default setting.
# In this case, change are reflected only when
# the index is manually reloaded.
idx.reload()
assert idx.searcher().num_docs == 1
idx.config_reader("OnCommit", 4)
writer.add_document(Document(title="mytitle2", body="mybody2"))
writer.commit()
import time
for i in range(50):
# The index should be automatically reloaded.
# Wait for at most 5s for it to happen.
time.sleep(0.1)
if idx.searcher().num_docs == 2:
return
assert False
def test_opens_from_dir(self):
index = Index(schema(), PATH_TO_INDEX, reuse=True)
assert index.searcher().num_docs == 3
def test_exists(self):
# prefer to keep it separate in case anyone deletes this
# runs from the root directory
assert Index.exists(PATH_TO_INDEX)
def test_opens_from_dir(self, dir_index):
index_dir, _ = dir_index
index = Index(schema(), str(index_dir), reuse=True)
assert index.searcher().num_docs == 3
def test_opens_from_dir_invalid_schema(self):
with pytest.raises(ValueError):
index = Index(schema(), PATH_TO_INDEX, reuse=True)