def test_convert_pathlib():
data = random.choice([GLOVE, W2V, W2V_TEXT, LEADER])
output_type = random.choice(list(FileType))
input_path = DATA / data
gold_output_path = os.path.splitext(str(input_path))[0] + "." + str(output_type)
with patch("word_vectors.convert_module.write") as write_patch:
w, wv = read(input_path)
convert(input_path, output_file_type=output_type)
call_file, call_w, call_wv, call_type = write_patch.call_args_list[0][0]
assert str(call_file) == gold_output_path
assert call_w == w
np.testing.assert_allclose(call_wv, wv)
assert call_type is output_type
def test_convert_with_output_pathlib():
data = random.choice([GLOVE, W2V, W2V_TEXT, LEADER])
output_type = random.choice(list(FileType))
output = pathlib.Path(rand_str())
input_path = DATA / data
with patch("word_vectors.convert_module.write") as write_patch:
w, wv = read(input_path)
convert(input_path, output, output_file_type=output_type)
call_file, call_w, call_wv, call_type = write_patch.call_args_list[0][0]
assert call_file == output
assert call_w == w
assert call_type == output_type
np.testing.assert_allclose(call_wv, wv)
def test_convert_with_input_pathlib():
data = random.choice([GLOVE, W2V, W2V_TEXT, LEADER])
input_type = INPUT_MAPPING[data]
output_type = random.choice(list(FileType))
input_path = DATA / data
output = pathlib.Path(rand_str())
with patch("word_vectors.convert_module.read") as read_patch:
with patch("word_vectors.convert_module.write") as write_patch:
w, wv = read(input_path)
read_patch.return_value = (w, wv)
convert(input_path, output, output_file_type=output_type, input_file_type=input_type)
read_patch.assert_called_once_with(input_path, input_type)
call_file, call_w, call_wv, call_type = write_patch.call_args_list[0][0]
assert call_file == output
assert call_w == w
assert call_type == output_type
np.testing.assert_allclose(call_wv, wv)
def main():
parser = argparse.ArgumentParser(
description="Convert Pre-trained embeddings between different formats")
parser.add_argument("embeddings")
parser.add_argument("--output-format",
"--output_format",
default=FileType.LEADER,
type=FileType.from_string)
parser.add_argument("--input-format",
"--input_format",
type=FileType.from_string)
parser.add_argument("--output", help="The output path.")
args = parser.parse_args()
convert(args.embeddings,
output=args.output,
output_file_type=args.output_format,
input_file_type=args.input_format)
def test_convert_with_output_open():
data = random.choice([GLOVE, W2V, W2V_TEXT, LEADER])
output_type = random.choice(list(FileType))
output = rand_str()
input_path = DATA / data
print(output)
try:
with open(input_path, "r" if data in (GLOVE, W2V_TEXT) else "rb") as input_path:
with open(output, "w" if output_type in (FileType.GLOVE, FileType.W2V_TEXT) else "wb") as output:
with patch("word_vectors.convert_module.write") as write_patch:
w, wv = read(input_path)
convert(input_path, output, output_file_type=output_type)
call_file, call_w, call_wv, call_type = write_patch.call_args_list[0][0]
assert call_file == output
assert call_w == w
assert call_type == output_type
np.testing.assert_allclose(call_wv, wv)
finally:
os.remove(output.name)