def test_is_image_format(self):
for ext in ['tif', 'tiff', 'jpg', 'jpeg', 'png', 'jp2']:
mime_type = MimeType.from_string(ext)
self.assertTrue(
MimeType.is_image_format(mime_type),
msg="Expected MIME type {} to be an image format".format(
mime_type.value))
def test_is_image_format(self):
image_format_extensions = ('tif', 'tiff', 'jpg', 'jpeg', 'tif', 'tiff',
'png', 'jpg')
for ext in image_format_extensions:
mime_type = MimeType(MimeType.canonical_extension(ext))
self.assertTrue(
MimeType.is_image_format(mime_type),
msg="Expected MIME type {} to be an image format".format(
mime_type.value))
def test_extension_and_from_string(self):
extension_pairs = (('tif', MimeType.TIFF), ('jpeg', MimeType.JPG),
('h5', MimeType.HDF), ('hdf5', MimeType.HDF))
for ext, mime_type in extension_pairs:
parsed_mime_type = MimeType.from_string(ext)
self.assertEqual(mime_type, parsed_mime_type)
for mime_type in MimeType:
if not mime_type.is_tiff_format():
self.assertEqual(MimeType.from_string(mime_type.extension),
mime_type)
with self.assertRaises(ValueError):
MimeType.from_string('unknown ext')
def test_canonical_extension(self):
extension_pairs = (('tiff', 'tiff'), ('tif', 'tiff'), ('jpg', 'jpg'),
('jpeg', 'jpg'), ('png', 'png'), ('jp2', 'jp2'),
('txt', 'txt'), ('h5', 'hdf'), ('hdf', 'hdf'),
('hdf5', 'hdf'))
for ext, canon in extension_pairs:
res = MimeType.canonical_extension(ext)
self.assertEqual(canon,
res,
msg="Expected {}, got {}".format(canon, res))
def _decode(self, file, path):
"""Loads from a file and decodes content."""
file_format = MimeType(fs.path.splitext(path)[1].strip("."))
if file_format is MimeType.NPY:
return np.load(file)
if file_format is MimeType.GPKG:
dataframe = gpd.read_file(file)
if dataframe.crs is not None:
# Trying to preserve a standard CRS and passing otherwise
try:
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=SHUserWarning)
dataframe.crs = CRS(dataframe.crs).pyproj_crs()
except ValueError:
pass
if "TIMESTAMP" in dataframe:
dataframe.TIMESTAMP = pd.to_datetime(dataframe.TIMESTAMP)
return dataframe
if file_format in [MimeType.JSON, MimeType.GEOJSON]:
json_data = json.load(file)
if self.feature_type is FeatureType.BBOX:
return Geometry.from_geojson(json_data).bbox
return json_data
if file_format is MimeType.PICKLE:
warnings.warn(
f"File {self.path} with data of type {self.feature_type} is in pickle format which is deprecated "
"since eo-learn version 1.0. Please re-save this EOPatch with the new eo-learn version to "
"update the format. In newer versions this backward compatibility will be removed.",
EODeprecationWarning,
)
data = pickle.load(file)
# There seems to be an issue in geopandas==0.8.1 where unpickling GeoDataFrames, which were saved with an
# old geopandas version, loads geometry column into a pandas.Series instead geopandas.GeoSeries. Because
# of that it is missing a crs attribute which is only attached to the entire GeoDataFrame
if isinstance(data, GeoDataFrame) and not isinstance(
data.geometry, GeoSeries):
data = data.set_geometry("geometry")
return data
raise ValueError(f"Unsupported data type for file {path}.")
def test_get_string(self):
type_string_pairs = ((MimeType.PNG, 'image/png'),
(MimeType.JPG, 'image/jpeg'), (MimeType.TIFF,
'image/tiff'),
(MimeType.TIFF_d32f, 'image/tiff;depth=32f'),
(MimeType.JSON,
'application/json'), (MimeType.CSV, 'text/csv'),
(MimeType.ZIP,
'application/zip'), (MimeType.HDF,
'application/x-hdf'),
(MimeType.XML, 'application/xml'), (MimeType.TXT,
'text/plain'))
for img_type, img_str in type_string_pairs:
res = MimeType.get_string(img_type)
self.assertEqual(img_str,
res,
msg="Expected {}, got {}".format(img_str, res))
def test_has_value(self):
self.assertTrue(MimeType.has_value('tiff;depth=32f'))
self.assertFalse(MimeType.has_value('unknown value'))