def test_content_hash_not_dependent_on_chunks_or_matches():
doc1 = Document()
doc1.content = 'one'
doc1.update_content_hash()
doc2 = Document()
doc2.content = 'one'
doc2.update_content_hash()
assert doc1.content_hash == doc2.content_hash
doc3 = Document()
doc3.content = 'one'
for _ in range(3):
with Document() as m:
m.content = 'some chunk'
doc3.chunks.append(m)
doc3.update_content_hash()
assert doc1.content_hash == doc3.content_hash
doc4 = Document()
doc4.content = 'one'
for _ in range(3):
with Document() as m:
m.content = 'some match'
doc4.matches.append(m)
doc4.update_content_hash()
assert doc1.content_hash == doc4.content_hash
def test_uri_get_set():
a = Document()
a.uri = 'https://abc.com/a.jpg'
assert a.uri == 'https://abc.com/a.jpg'
assert a.mime_type == 'image/jpeg'
a.uri = 'abcdefg'
assert a.uri == 'abcdefg'
a.content = 'abcdefg'
assert a.text == 'abcdefg'
assert not a.uri
def test_sparse_get_set():
d = Document()
assert d.content is None
mat1 = coo_matrix(np.array([1, 2, 3]))
d.content = mat1
assert (d.content != mat1).nnz == 0
mat2 = coo_matrix(np.array([3, 2, 1]))
assert (d.content != mat2).nnz != 0
d.blob = mat2
assert (d.content != mat2).nnz == 0
