def open(fp,
mode='r',
driver=None,
width=None,
height=None,
count=None,
crs=None,
transform=None,
dtype=None,
nodata=None,
sharing=False,
**kwargs):
"""Open a dataset for reading or writing.
The dataset may be located in a local file, in a resource located by
a URL, or contained within a stream of bytes.
In read ('r') or read/write ('r+') mode, no keyword arguments are
required: these attributes are supplied by the opened dataset.
In write ('w' or 'w+') mode, the driver, width, height, count, and dtype
keywords are strictly required.
Parameters
----------
fp : str, file object or pathlib.Path object
A filename or URL, a file object opened in binary ('rb') mode,
or a Path object.
mode : str, optional
'r' (read, the default), 'r+' (read/write), 'w' (write), or
'w+' (write/read).
driver : str, optional
A short format driver name (e.g. "GTiff" or "JPEG") or a list of
such names (see GDAL docs at
http://www.gdal.org/formats_list.html). In 'w' or 'w+' modes
a single name is required. In 'r' or 'r+' modes the driver can
usually be omitted. Registered drivers will be tried
sequentially until a match is found. When multiple drivers are
available for a format such as JPEG2000, one of them can be
selected by using this keyword argument.
width : int, optional
The number of columns of the raster dataset. Required in 'w' or
'w+' modes, it is ignored in 'r' or 'r+' modes.
height : int, optional
The number of rows of the raster dataset. Required in 'w' or
'w+' modes, it is ignored in 'r' or 'r+' modes.
count : int, optional
The count of dataset bands. Required in 'w' or 'w+' modes, it is
ignored in 'r' or 'r+' modes.
crs : str, dict, or CRS; optional
The coordinate reference system. Required in 'w' or 'w+' modes,
it is ignored in 'r' or 'r+' modes.
transform : Affine instance, optional
Affine transformation mapping the pixel space to geographic
space. Required in 'w' or 'w+' modes, it is ignored in 'r' or
'r+' modes.
dtype : str or numpy dtype
The data type for bands. For example: 'uint8' or
``rasterio.uint16``. Required in 'w' or 'w+' modes, it is
ignored in 'r' or 'r+' modes.
nodata : int, float, or nan; optional
Defines the pixel value to be interpreted as not valid data.
Required in 'w' or 'w+' modes, it is ignored in 'r' or 'r+'
modes.
sharing : bool; optional
To reduce overhead and prevent programs from running out of file
descriptors, rasterio maintains a pool of shared low level
dataset handles. When `True` this function will use a shared
handle if one is available. Multithreaded programs must avoid
sharing and should set *sharing* to `False`.
kwargs : optional
These are passed to format drivers as directives for creating or
interpreting datasets. For example: in 'w' or 'w+' modes
a `tiled=True` keyword argument will direct the GeoTIFF format
driver to create a tiled, rather than striped, TIFF.
Returns
-------
A ``DatasetReader`` or ``DatasetWriter`` object.
Examples
--------
To open a GeoTIFF for reading using standard driver discovery and
no directives:
>>> import rasterio
>>> with rasterio.open('example.tif') as dataset:
... print(dataset.profile)
To open a JPEG2000 using only the JP2OpenJPEG driver:
>>> with rasterio.open(
... 'example.jp2', driver='JP2OpenJPEG') as dataset:
... print(dataset.profile)
To create a new 8-band, 16-bit unsigned, tiled, and LZW-compressed
GeoTIFF with a global extent and 0.5 degree resolution:
>>> from rasterio.transform import from_origin
>>> with rasterio.open(
... 'example.tif', 'w', driver='GTiff', dtype='uint16',
... width=720, height=360, count=8, crs='EPSG:4326',
... transform=from_origin(-180.0, 90.0, 0.5, 0.5),
... nodata=0, tiled=True, compress='lzw') as dataset:
... dataset.write(...)
"""
if not isinstance(fp, string_types):
if not (hasattr(fp, 'read') or hasattr(fp, 'write')
or isinstance(fp, Path)):
raise TypeError("invalid path or file: {0!r}".format(fp))
if mode and not isinstance(mode, string_types):
raise TypeError("invalid mode: {0!r}".format(mode))
if driver and not isinstance(driver, string_types):
raise TypeError("invalid driver: {0!r}".format(driver))
if dtype and not check_dtype(dtype):
raise TypeError("invalid dtype: {0!r}".format(dtype))
if nodata is not None:
nodata = float(nodata)
if transform:
transform = guard_transform(transform)
# Check driver/mode blacklist.
if driver and is_blacklisted(driver, mode):
raise RasterioIOError("Blacklisted: file cannot be opened by "
"driver '{0}' in '{1}' mode".format(
driver, mode))
# Special case for file object argument.
if mode == 'r' and hasattr(fp, 'read'):
@contextmanager
def fp_reader(fp):
memfile = MemoryFile(fp.read())
dataset = memfile.open(driver=driver, sharing=sharing)
try:
yield dataset
finally:
dataset.close()
memfile.close()
return fp_reader(fp)
elif mode in ('w', 'w+') and hasattr(fp, 'write'):
@contextmanager
def fp_writer(fp):
memfile = MemoryFile()
dataset = memfile.open(driver=driver,
width=width,
height=height,
count=count,
crs=crs,
transform=transform,
dtype=dtype,
nodata=nodata,
sharing=sharing,
**kwargs)
try:
yield dataset
finally:
dataset.close()
memfile.seek(0)
fp.write(memfile.read())
memfile.close()
return fp_writer(fp)
else:
# If a pathlib.Path instance is given, convert it to a string path.
if isinstance(fp, Path):
fp = str(fp)
# The 'normal' filename or URL path.
path = parse_path(fp)
# Create dataset instances and pass the given env, which will
# be taken over by the dataset's context manager if it is not
# None.
if mode == 'r':
s = DatasetReader(path, driver=driver, sharing=sharing, **kwargs)
elif mode == "r+":
s = get_writer_for_path(path, driver=driver)(path,
mode,
driver=driver,
sharing=sharing,
**kwargs)
elif mode.startswith("w"):
if not driver:
driver = driver_from_extension(path)
writer = get_writer_for_driver(driver)
if writer is not None:
s = writer(path,
mode,
driver=driver,
width=width,
height=height,
count=count,
crs=crs,
transform=transform,
dtype=dtype,
nodata=nodata,
sharing=sharing,
**kwargs)
else:
raise DriverCapabilityError(
"Writer does not exist for driver: %s" % str(driver))
else:
raise DriverCapabilityError(
"mode must be one of 'r', 'r+', or 'w', not %s" % mode)
return s
def open(fp, mode='r', driver=None, width=None, height=None, count=None,
crs=None, transform=None, dtype=None, nodata=None, sharing=False,
**kwargs):
"""Open a dataset for reading or writing.
The dataset may be located in a local file, in a resource located by
a URL, or contained within a stream of bytes.
In read ('r') or read/write ('r+') mode, no keyword arguments are
required: these attributes are supplied by the opened dataset.
In write ('w' or 'w+') mode, the driver, width, height, count, and dtype
keywords are strictly required.
Parameters
----------
fp : str, file object, PathLike object, FilePath, or MemoryFile
A filename or URL, a file object opened in binary ('rb') mode, a
Path object, or one of the rasterio classes that provides the
dataset-opening interface (has an open method that returns a
dataset).
mode : str, optional
'r' (read, the default), 'r+' (read/write), 'w' (write), or
'w+' (write/read).
driver : str, optional
A short format driver name (e.g. "GTiff" or "JPEG") or a list of
such names (see GDAL docs at
https://gdal.org/drivers/raster/index.html). In 'w' or 'w+' modes
a single name is required. In 'r' or 'r+' modes the driver can
usually be omitted. Registered drivers will be tried
sequentially until a match is found. When multiple drivers are
available for a format such as JPEG2000, one of them can be
selected by using this keyword argument.
width : int, optional
The number of columns of the raster dataset. Required in 'w' or
'w+' modes, it is ignored in 'r' or 'r+' modes.
height : int, optional
The number of rows of the raster dataset. Required in 'w' or
'w+' modes, it is ignored in 'r' or 'r+' modes.
count : int, optional
The count of dataset bands. Required in 'w' or 'w+' modes, it is
ignored in 'r' or 'r+' modes.
crs : str, dict, or CRS; optional
The coordinate reference system. Required in 'w' or 'w+' modes,
it is ignored in 'r' or 'r+' modes.
transform : Affine instance, optional
Affine transformation mapping the pixel space to geographic
space. Required in 'w' or 'w+' modes, it is ignored in 'r' or
'r+' modes.
dtype : str or numpy dtype
The data type for bands. For example: 'uint8' or
``rasterio.uint16``. Required in 'w' or 'w+' modes, it is
ignored in 'r' or 'r+' modes.
nodata : int, float, or nan; optional
Defines the pixel value to be interpreted as not valid data.
Required in 'w' or 'w+' modes, it is ignored in 'r' or 'r+'
modes.
sharing : bool; optional
To reduce overhead and prevent programs from running out of file
descriptors, rasterio maintains a pool of shared low level
dataset handles. When `True` this function will use a shared
handle if one is available. Multithreaded programs must avoid
sharing and should set *sharing* to `False`.
kwargs : optional
These are passed to format drivers as directives for creating or
interpreting datasets. For example: in 'w' or 'w+' modes
a `tiled=True` keyword argument will direct the GeoTIFF format
driver to create a tiled, rather than striped, TIFF.
Returns
-------
A ``DatasetReader`` or ``DatasetWriter`` object.
Examples
--------
To open a GeoTIFF for reading using standard driver discovery and
no directives:
>>> import rasterio
>>> with rasterio.open('example.tif') as dataset:
... print(dataset.profile)
To open a JPEG2000 using only the JP2OpenJPEG driver:
>>> with rasterio.open(
... 'example.jp2', driver='JP2OpenJPEG') as dataset:
... print(dataset.profile)
To create a new 8-band, 16-bit unsigned, tiled, and LZW-compressed
GeoTIFF with a global extent and 0.5 degree resolution:
>>> from rasterio.transform import from_origin
>>> with rasterio.open(
... 'example.tif', 'w', driver='GTiff', dtype='uint16',
... width=720, height=360, count=8, crs='EPSG:4326',
... transform=from_origin(-180.0, 90.0, 0.5, 0.5),
... nodata=0, tiled=True, compress='lzw') as dataset:
... dataset.write(...)
"""
if not isinstance(fp, str):
if not (
hasattr(fp, "read")
or hasattr(fp, "write")
or isinstance(fp, (os.PathLike, MemoryFile, FilePath))
):
raise TypeError("invalid path or file: {0!r}".format(fp))
if mode and not isinstance(mode, str):
raise TypeError("invalid mode: {0!r}".format(mode))
if driver and not isinstance(driver, str):
raise TypeError("invalid driver: {0!r}".format(driver))
if dtype and not check_dtype(dtype):
raise TypeError("invalid dtype: {0!r}".format(dtype))
if nodata is not None:
nodata = float(nodata)
if transform:
transform = guard_transform(transform)
# Check driver/mode blacklist.
if driver and is_blacklisted(driver, mode):
raise RasterioIOError(
"Blacklisted: file cannot be opened by "
"driver '{0}' in '{1}' mode".format(driver, mode))
# If the fp argument is a file-like object and can be adapted by
# rasterio's FilePath we do so. Otherwise, we use a MemoryFile to
# hold fp's contents and store that in an ExitStack attached to the
# dataset object that we will return. When a dataset's close method
# is called, this ExitStack will be unwound and the MemoryFile's
# storage will be cleaned up.
if mode == 'r' and hasattr(fp, 'read'):
if have_vsi_plugin:
return FilePath(fp).open(driver=driver, sharing=sharing, **kwargs)
else:
memfile = MemoryFile(fp.read())
dataset = memfile.open(driver=driver, sharing=sharing, **kwargs)
dataset._env.enter_context(memfile)
return dataset
elif mode in ('w', 'w+') and hasattr(fp, 'write'):
memfile = MemoryFile()
dataset = memfile.open(
driver=driver,
width=width,
height=height,
count=count,
crs=crs,
transform=transform,
dtype=dtype,
nodata=nodata,
sharing=sharing,
**kwargs
)
dataset._env.enter_context(memfile)
# For the writing case we push an extra callback onto the
# ExitStack. It ensures that the MemoryFile's contents are
# copied to the open file object.
def func(*args, **kwds):
memfile.seek(0)
fp.write(memfile.read())
dataset._env.callback(func)
return dataset
# TODO: test for a shared base class or abstract type.
elif isinstance(fp, (FilePath, MemoryFile)):
if mode.startswith("r"):
dataset = fp.open(driver=driver, sharing=sharing, **kwargs)
# Note: FilePath does not support writing and an exception will
# result from this.
elif mode.startswith("w"):
dataset = fp.open(
driver=driver,
width=width,
height=height,
count=count,
crs=crs,
transform=transform,
dtype=dtype,
nodata=nodata,
sharing=sharing,
**kwargs
)
return dataset
# At this point, the fp argument is a string or path-like object
# which can be converted to a string.
else:
raw_dataset_path = os.fspath(fp)
path = _parse_path(raw_dataset_path)
if mode == "r":
dataset = DatasetReader(path, driver=driver, sharing=sharing, **kwargs)
elif mode == "r+":
dataset = get_writer_for_path(path, driver=driver)(
path, mode, driver=driver, sharing=sharing, **kwargs
)
elif mode.startswith("w"):
if not driver:
driver = driver_from_extension(path)
writer = get_writer_for_driver(driver)
if writer is not None:
dataset = writer(
path,
mode,
driver=driver,
width=width,
height=height,
count=count,
crs=crs,
transform=transform,
dtype=dtype,
nodata=nodata,
sharing=sharing,
**kwargs
)
else:
raise DriverCapabilityError(
"Writer does not exist for driver: %s" % str(driver)
)
else:
raise DriverCapabilityError(
"mode must be one of 'r', 'r+', or 'w', not %s" % mode)
return dataset