diff options
| -rw-r--r-- | benchmarks/benchmarks/bench_io.py | 13 | ||||
| -rw-r--r-- | numpy/lib/format.py | 22 | ||||
| -rw-r--r-- | numpy/lib/tests/test_format.py | 3 |
3 files changed, 31 insertions, 7 deletions
diff --git a/benchmarks/benchmarks/bench_io.py b/benchmarks/benchmarks/bench_io.py index 357adbb87..e316d07f3 100644 --- a/benchmarks/benchmarks/bench_io.py +++ b/benchmarks/benchmarks/bench_io.py @@ -1,7 +1,7 @@ -from .common import Benchmark, get_squares +from .common import Benchmark, get_squares, get_squares_ import numpy as np -from io import StringIO +from io import SEEK_SET, StringIO, BytesIO class Copy(Benchmark): @@ -67,6 +67,15 @@ class Savez(Benchmark): np.savez('tmp.npz', **self.squares) +class LoadNpyOverhead(Benchmark): + def setup(self): + self.buffer = BytesIO() + np.save(self.buffer, get_squares_()['float32']) + + def time_loadnpy_overhead(self): + self.buffer.seek(0, SEEK_SET) + np.load(self.buffer) + class LoadtxtCSVComments(Benchmark): # benchmarks for np.loadtxt comment handling # when reading in CSV files diff --git a/numpy/lib/format.py b/numpy/lib/format.py index 54fd0b0bc..8f3fd694d 100644 --- a/numpy/lib/format.py +++ b/numpy/lib/format.py @@ -623,13 +623,27 @@ def _read_array_header(fp, version, max_header_size=_MAX_HEADER_SIZE): # "descr" : dtype.descr # Versions (2, 0) and (1, 0) could have been created by a Python 2 # implementation before header filtering was implemented. - if version <= (2, 0): - header = _filter_header(header) + # + # For performance reasons, we try without _filter_header first though try: d = safe_eval(header) except SyntaxError as e: - msg = "Cannot parse header: {!r}" - raise ValueError(msg.format(header)) from e + if version <= (2, 0): + header = _filter_header(header) + try: + d = safe_eval(header) + except SyntaxError as e2: + msg = "Cannot parse header: {!r}" + raise ValueError(msg.format(header)) from e2 + else: + warnings.warn( + "Reading `.npy` or `.npz` file required additional " + "header parsing as it was created on Python 2. Save the " + "file again to speed up loading and avoid this warning.", + UserWarning, stacklevel=4) + else: + msg = "Cannot parse header: {!r}" + raise ValueError(msg.format(header)) from e if not isinstance(d, dict): msg = "Header is not a dictionary: {!r}" raise ValueError(msg.format(d)) diff --git a/numpy/lib/tests/test_format.py b/numpy/lib/tests/test_format.py index 6f6406cf8..58d08f1e5 100644 --- a/numpy/lib/tests/test_format.py +++ b/numpy/lib/tests/test_format.py @@ -531,7 +531,8 @@ def test_load_padded_dtype(tmpdir, dt): def test_python2_python3_interoperability(): fname = 'win64python2.npy' path = os.path.join(os.path.dirname(__file__), 'data', fname) - data = np.load(path) + with pytest.warns(UserWarning, match="Reading.*this warning\\."): + data = np.load(path) assert_array_equal(data, np.ones(2)) def test_pickle_python2_python3(): |