def file_in_handler(ctx, param, value):
"""Normalize ordinary filesystem and VFS paths"""
try:
path = _parse_path(value)
if isinstance(path, _UnparsedPath):
if os.path.exists(path.path) and rasterio.shutil.exists(value):
return abspath_forward_slashes(path.path)
else:
return path.name
elif path.scheme and path.is_remote:
return path.name
elif path.archive:
if os.path.exists(path.archive) and rasterio.shutil.exists(value):
archive = abspath_forward_slashes(path.archive)
return "{}://{}!{}".format(path.scheme, archive, path.path)
else:
raise OSError("Input archive {} does not exist".format(
path.archive))
else:
if os.path.exists(path.path) and rasterio.shutil.exists(value):
return abspath_forward_slashes(path.path)
else:
raise OSError("Input file {} does not exist".format(path.path))
except Exception:
raise click.BadParameter("{} is not a valid input file".format(value))
def test_parse_path_accept_get_params():
# See https://github.com/rasterio/rasterio/issues/1121
parsed = _parse_path('http://example.com/index?a=1')
assert isinstance(parsed, _ParsedPath)
assert parsed.path == 'example.com/index?a=1'
assert parsed.archive is None
assert parsed.scheme == 'http'
def cls_from_path(path):
"""Find the session class suited to the data at `path`.
Parameters
----------
path : str
A dataset path or identifier.
Returns
-------
class
"""
if not path:
return DummySession
path = _parse_path(path)
if isinstance(path, _UnparsedPath) or path.is_local:
return DummySession
elif (
path.scheme == "s3" or "amazonaws.com" in path.path
) and not "X-Amz-Signature" in path.path:
if boto3 is not None:
return AWSSession
else:
log.info("boto3 not available, falling back to a DummySession.")
return DummySession
elif path.scheme == "oss" or "aliyuncs.com" in path.path:
return OSSSession
elif path.path.startswith("/vsiswift/"):
return SwiftSession
elif path.scheme == "az":
return AzureSession
# This factory can be extended to other cloud providers here.
# elif path.scheme == "cumulonimbus": # for example.
# return CumulonimbusSession(*args, **kwargs)
else:
return DummySession
def test_parse_gdal():
"""GDAL dataset identifiers fall through properly"""
assert _parse_path('GDAL:filepath:varname').path == 'GDAL:filepath:varname'
def test_parse_gdal_vsi():
"""GDAL dataset identifiers fall through properly"""
assert _parse_path('/vsifoo/bar').path == '/vsifoo/bar'
def test_parse_path_file():
"""Correctly parse an ordinary filesystem path"""
parsed = _parse_path('/foo.tif')
assert parsed.path == '/foo.tif'
def test_parse_path_file_scheme():
"""Correctly parse file:// URL"""
parsed = _parse_path('file://foo.tif')
assert parsed.path == 'foo.tif'
assert parsed.archive is None
assert parsed.scheme == 'file'
def test_parse_path_zip_and_file():
"""Correctly parse zip+file scheme URL"""
parsed = _parse_path('zip+file://tests/data/files.zip!foo.tif')
assert parsed.path == 'foo.tif'
assert parsed.archive == 'tests/data/files.zip'
assert parsed.scheme == 'zip+file'
def test_parse_path_win_no_pathlib(monkeypatch):
monkeypatch.setattr(rasterio._path.sys, "platform", "win32")
monkeypatch.setattr(rasterio._path, "pathlib", None)
assert isinstance(_parse_path(r"C:\foo\bar.tif"), _UnparsedPath)
def test_parse_path():
pathlib = pytest.importorskip("pathlib")
assert isinstance(_parse_path(pathlib.Path("/foo/bar.tif")), _ParsedPath)
def test_path_error(path):
with pytest.raises(PathError):
_parse_path(path)
def test_driver_prefixed_path(path):
parsed = _parse_path(path)
assert isinstance(parsed, _UnparsedPath)
def test_vsi_path_zip_plus_https():
"""A zip+https:// URLs vsi path is correct (see #1151)"""
url = 'zip+https://example.com/foo.zip!bar.tif'
assert _vsi_path(_parse_path(url)) == '/vsizip/vsicurl/https://example.com/foo.zip/bar.tif'
def test_vsi_path_zip():
"""A zip:// URLs vsi path is correct (see #1377)"""
url = 'zip:///path/to/zip/some.zip!path/to/file.txt'
assert _vsi_path(_parse_path(url)) == '/vsizip//path/to/zip/some.zip/path/to/file.txt'
def test_parse_windows_path(monkeypatch):
"""Return Windows paths unparsed"""
monkeypatch.setattr(sys, 'platform', 'win32')
assert _parse_path(r'C:\\foo.tif').path == r'C:\\foo.tif'
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
def test_parse_path_win():
pathlib = pytest.importorskip("pathlib")
assert isinstance(_parse_path(pathlib.PureWindowsPath(r"C:\foo\bar.tif")), _ParsedPath)
def _boundless_vrt_doc(src_dataset,
nodata=None,
background=None,
hidenodata=False,
width=None,
height=None,
transform=None,
masked=False):
"""Make a VRT XML document.
Parameters
----------
src_dataset : Dataset
The dataset to wrap.
background : int or float, optional
The background fill value for the boundless VRT.
masked : bool
If True, the src_dataset is replaced by its valid data mask.
Returns
-------
str
An XML text string.
"""
nodata = nodata or src_dataset.nodata
width = width or src_dataset.width
height = height or src_dataset.height
transform = transform or src_dataset.transform
vrtdataset = ET.Element('VRTDataset')
vrtdataset.attrib['rasterYSize'] = str(height)
vrtdataset.attrib['rasterXSize'] = str(width)
srs = ET.SubElement(vrtdataset, 'SRS')
srs.text = src_dataset.crs.wkt if src_dataset.crs else ""
geotransform = ET.SubElement(vrtdataset, 'GeoTransform')
geotransform.text = ','.join([str(v) for v in transform.to_gdal()])
for bidx, ci, block_shape, dtype in zip(src_dataset.indexes,
src_dataset.colorinterp,
src_dataset.block_shapes,
src_dataset.dtypes):
vrtrasterband = ET.SubElement(vrtdataset, 'VRTRasterBand')
vrtrasterband.attrib['dataType'] = _gdal_typename(dtype)
vrtrasterband.attrib['band'] = str(bidx)
if background is not None or nodata is not None:
nodatavalue = ET.SubElement(vrtrasterband, 'NoDataValue')
nodatavalue.text = str(background or nodata)
if hidenodata:
hidenodatavalue = ET.SubElement(vrtrasterband,
'HideNoDataValue')
hidenodatavalue.text = "1"
colorinterp = ET.SubElement(vrtrasterband, 'ColorInterp')
colorinterp.text = ci.name.capitalize()
complexsource = ET.SubElement(vrtrasterband, 'ComplexSource')
sourcefilename = ET.SubElement(complexsource, 'SourceFilename')
sourcefilename.attrib['relativeToVRT'] = "0"
sourcefilename.attrib["shared"] = "0"
sourcefilename.text = _parse_path(src_dataset.name).as_vsi()
sourceband = ET.SubElement(complexsource, 'SourceBand')
sourceband.text = str(bidx)
sourceproperties = ET.SubElement(complexsource, 'SourceProperties')
sourceproperties.attrib['RasterXSize'] = str(width)
sourceproperties.attrib['RasterYSize'] = str(height)
sourceproperties.attrib['dataType'] = _gdal_typename(dtype)
sourceproperties.attrib['BlockYSize'] = str(block_shape[0])
sourceproperties.attrib['BlockXSize'] = str(block_shape[1])
srcrect = ET.SubElement(complexsource, 'SrcRect')
srcrect.attrib['xOff'] = '0'
srcrect.attrib['yOff'] = '0'
srcrect.attrib['xSize'] = str(src_dataset.width)
srcrect.attrib['ySize'] = str(src_dataset.height)
dstrect = ET.SubElement(complexsource, 'DstRect')
dstrect.attrib['xOff'] = str(
(src_dataset.transform.xoff - transform.xoff) / transform.a)
dstrect.attrib['yOff'] = str(
(src_dataset.transform.yoff - transform.yoff) / transform.e)
dstrect.attrib['xSize'] = str(src_dataset.width *
src_dataset.transform.a / transform.a)
dstrect.attrib['ySize'] = str(src_dataset.height *
src_dataset.transform.e / transform.e)
if src_dataset.nodata is not None:
nodata_elem = ET.SubElement(complexsource, 'NODATA')
nodata_elem.text = str(src_dataset.nodata)
if src_dataset.options is not None:
openoptions = ET.SubElement(complexsource, 'OpenOptions')
for ookey, oovalue in src_dataset.options.items():
ooi = ET.SubElement(openoptions, 'OOI')
ooi.attrib['key'] = str(ookey)
ooi.text = str(oovalue)
# Effectively replaces all values of the source dataset with
# 255. Due to GDAL optimizations, the source dataset will not
# be read, so we get a performance improvement.
if masked:
scaleratio = ET.SubElement(complexsource, 'ScaleRatio')
scaleratio.text = '0'
scaleoffset = ET.SubElement(complexsource, 'ScaleOffset')
scaleoffset.text = '255'
if all(MaskFlags.per_dataset in flags
for flags in src_dataset.mask_flag_enums):
maskband = ET.SubElement(vrtdataset, 'MaskBand')
vrtrasterband = ET.SubElement(maskband, 'VRTRasterBand')
vrtrasterband.attrib['dataType'] = 'Byte'
simplesource = ET.SubElement(vrtrasterband, 'SimpleSource')
sourcefilename = ET.SubElement(simplesource, 'SourceFilename')
sourcefilename.attrib['relativeToVRT'] = "0"
sourcefilename.attrib["shared"] = "0"
sourcefilename.text = _parse_path(src_dataset.name).as_vsi()
sourceband = ET.SubElement(simplesource, 'SourceBand')
sourceband.text = 'mask,1'
sourceproperties = ET.SubElement(simplesource, 'SourceProperties')
sourceproperties.attrib['RasterXSize'] = str(width)
sourceproperties.attrib['RasterYSize'] = str(height)
sourceproperties.attrib['dataType'] = 'Byte'
sourceproperties.attrib['BlockYSize'] = str(block_shape[0])
sourceproperties.attrib['BlockXSize'] = str(block_shape[1])
srcrect = ET.SubElement(simplesource, 'SrcRect')
srcrect.attrib['xOff'] = '0'
srcrect.attrib['yOff'] = '0'
srcrect.attrib['xSize'] = str(src_dataset.width)
srcrect.attrib['ySize'] = str(src_dataset.height)
dstrect = ET.SubElement(simplesource, 'DstRect')
dstrect.attrib['xOff'] = str(
(src_dataset.transform.xoff - transform.xoff) / transform.a)
dstrect.attrib['yOff'] = str(
(src_dataset.transform.yoff - transform.yoff) / transform.e)
dstrect.attrib['xSize'] = str(src_dataset.width)
dstrect.attrib['ySize'] = str(src_dataset.height)
return ET.tostring(vrtdataset).decode('ascii')