diff --git a/lib/iris/fileformats/_nc_load_rules/helpers.py b/lib/iris/fileformats/_nc_load_rules/helpers.py index 35c2e96924..a2800dc91d 100644 --- a/lib/iris/fileformats/_nc_load_rules/helpers.py +++ b/lib/iris/fileformats/_nc_load_rules/helpers.py @@ -708,13 +708,13 @@ def build_and_add_global_attributes(engine: Engine): ), ) if problem is not None: - stack_notes = problem.stack_trace.__notes__ + stack_notes = problem.stack_trace.__notes__ # type: ignore[attr-defined] if stack_notes is None: stack_notes = [] stack_notes.append( f"Skipping disallowed global attribute '{attr_name}' (see above error)" ) - problem.stack_trace.__notes__ = stack_notes + problem.stack_trace.__notes__ = stack_notes # type: ignore[attr-defined] ################################################################################ @@ -1536,14 +1536,14 @@ def build_and_add_dimension_coordinate( ) if problem is not None: coord_var_name = str(cf_coord_var.cf_name) - stack_notes = problem.stack_trace.__notes__ + stack_notes = problem.stack_trace.__notes__ # type: ignore[attr-defined] if stack_notes is None: stack_notes = [] stack_notes.append( f"Failed to create {coord_var_name} dimension coordinate:\n" f"Gracefully creating {coord_var_name!r} auxiliary coordinate instead." ) - problem.stack_trace.__notes__ = stack_notes + problem.stack_trace.__notes__ = stack_notes # type: ignore[attr-defined] problem.handled = True _ = _add_or_capture( @@ -1643,9 +1643,13 @@ def _add_auxiliary_coordinate( # Determine the name of the dimension/s shared between the CF-netCDF data variable # and the coordinate being built. - common_dims = [ - dim for dim in cf_coord_var.dimensions if dim in engine.cf_var.dimensions - ] + coord_dims = cf_coord_var.dimensions + # if cf._is_str_dtype(cf_coord_var): + # coord_dims = coord_dims[:-1] + datavar_dims = engine.cf_var.dimensions + # if cf._is_str_dtype(engine.cf_var): + # datavar_dims = datavar_dims[:-1] + common_dims = [dim for dim in coord_dims if dim in datavar_dims] data_dims = None if common_dims: # Calculate the offset of each common dimension. diff --git a/lib/iris/fileformats/cf.py b/lib/iris/fileformats/cf.py index 2b6568c315..d32afaacb5 100644 --- a/lib/iris/fileformats/cf.py +++ b/lib/iris/fileformats/cf.py @@ -26,7 +26,7 @@ import iris.exceptions import iris.fileformats._nc_load_rules.helpers as hh -from iris.fileformats.netcdf import _thread_safe_nc +from iris.fileformats.netcdf import _bytecoding_datasets, _thread_safe_nc from iris.mesh.components import Connectivity import iris.util import iris.warnings @@ -67,7 +67,9 @@ # NetCDF returns a different type for strings depending on Python version. def _is_str_dtype(var): - return np.issubdtype(var.dtype, np.bytes_) + # N.B. use 'datatype' not 'dtype', to "look inside" variable wrappers which + # represent 'S1' type data as 'U'. + return isinstance(var.datatype, np.dtype) and np.issubdtype(var.datatype, np.bytes_) ################################################################################ @@ -788,50 +790,63 @@ def cf_label_data(self, cf_data_var): % type(cf_data_var) ) - # Determine the name of the label string (or length) dimension by - # finding the dimension name that doesn't exist within the data dimensions. - str_dim_name = list(set(self.dimensions) - set(cf_data_var.dimensions)) - - if len(str_dim_name) != 1: - raise ValueError( - "Invalid string dimensions for CF-netCDF label variable %r" - % self.cf_name - ) - - str_dim_name = str_dim_name[0] - label_data = self[:] - - if ma.isMaskedArray(label_data): - label_data = label_data.filled() - - # Determine whether we have a string-valued scalar label - # i.e. a character variable that only has one dimension (the length of the string). - if self.ndim == 1: - label_string = b"".join(label_data).strip() - label_string = label_string.decode("utf8") - data = np.array([label_string]) - else: - # Determine the index of the string dimension. - str_dim = self.dimensions.index(str_dim_name) - - # Calculate new label data shape (without string dimension) and create payload array. - new_shape = tuple( - dim_len for i, dim_len in enumerate(self.shape) if i != str_dim - ) - string_basetype = "|U%d" - string_dtype = string_basetype % self.shape[str_dim] - data = np.empty(new_shape, dtype=string_dtype) - - for index in np.ndindex(new_shape): - # Create the slice for the label data. - if str_dim == 0: - label_index = (slice(None, None),) + index - else: - label_index = index + (slice(None, None),) - - label_string = b"".join(label_data[label_index]).strip() - label_string = label_string.decode("utf8") - data[index] = label_string + # # Determine the name of the label string (or length) dimension by + # # finding the dimension name that doesn't exist within the data dimensions. + # str_dim_names = list(set(self.dimensions) - set(cf_data_var.dimensions)) + # n_nondata_dims = len(str_dim_names) + # + # if n_nondata_dims == 0: + # # *All* dims are shared with the data-variable. + # # This is only ok if the data-var is *also* a string type. + # dim_ok = _is_str_dtype(cf_data_var) + # # In this case, we must just *assume* that the last dimension is "the" + # # string dimension + # str_dim_name = self.dimensions[-1] + # else: + # # If there is exactly one non-data dim, that is the one we want + # dim_ok = len(str_dim_names) == 1 + # (str_dim_name,) = str_dim_names + # + # if not dim_ok: + # raise ValueError( + # "Invalid string dimensions for CF-netCDF label variable %r" + # % self.cf_name + # ) + + data = self[:] + # label_data = self[:] + # + # if ma.isMaskedArray(label_data): + # label_data = label_data.filled(b"\0") + # + # # Determine whether we have a string-valued scalar label + # # i.e. a character variable that only has one dimension (the length of the string). + # if self.ndim == 1: + # label_string = b"".join(label_data).strip() + # label_string = label_string.decode("utf8") + # data = np.array([label_string]) + # else: + # # Determine the index of the string dimension. + # str_dim = self.dimensions.index(str_dim_name) + # + # # Calculate new label data shape (without string dimension) and create payload array. + # new_shape = tuple( + # dim_len for i, dim_len in enumerate(self.shape) if i != str_dim + # ) + # string_basetype = "|U%d" + # string_dtype = string_basetype % self.shape[str_dim] + # data = np.empty(new_shape, dtype=string_dtype) + # + # for index in np.ndindex(new_shape): + # # Create the slice for the label data. + # if str_dim == 0: + # label_index = (slice(None, None),) + index + # else: + # label_index = index + (slice(None, None),) + # + # label_string = b"".join(label_data[label_index]).strip() + # label_string = label_string.decode("utf8") + # data[index] = label_string return data @@ -1361,7 +1376,11 @@ def __init__(self, file_source, warn=False, monotonic=False): if isinstance(file_source, str): # Create from filepath : open it + own it (=close when we die). self._filename = os.path.expanduser(file_source) - self._dataset = _thread_safe_nc.DatasetWrapper(self._filename, mode="r") + if _bytecoding_datasets.DECODE_TO_STRINGS_ON_READ: + ds_type = _bytecoding_datasets.EncodedDataset + else: + ds_type = _thread_safe_nc.DatasetWrapper + self._dataset = ds_type(self._filename, mode="r") self._own_file = True else: # We have been passed an open dataset. diff --git a/lib/iris/fileformats/netcdf/_bytecoding_datasets.py b/lib/iris/fileformats/netcdf/_bytecoding_datasets.py new file mode 100644 index 0000000000..22a9011eec --- /dev/null +++ b/lib/iris/fileformats/netcdf/_bytecoding_datasets.py @@ -0,0 +1,347 @@ +# Copyright Iris contributors +# +# This file is part of Iris and is released under the BSD license. +# See LICENSE in the root of the repository for full licensing details. +"""Module providing to netcdf datasets with automatic character encoding. + +The requirement is to convert numpy fixed-width unicode arrays on writing to a variable +which is declared as a byte (character) array with a fixed-length string dimension. + +Numpy unicode string arrays are ones with dtypes of the form "U". +Numpy character variables have the dtype "S1", and map to a fixed-length "string +dimension". + +In principle, netCDF4 already performs these translations, but in practice current +releases are not functional for anything other than "ascii" encoding -- including UTF-8, +which is the most obvious and desirable "general" solution. + +There is also the question of whether we should like to implement UTF-8 as our default. +Current discussions on this are inconclusive and neither CF conventions nor the NetCDF +User Guide are definite on what possible values of "_Encoding" are, or what the effective +default is, even though they do both mention the "_Encoding" attribute as a potential +way to handle the issue. + +Because of this, we interpret as follows: + * when reading bytes : in the absence of an "_Encoding" attribute, we will attempt to + decode bytes as UTF-8 + * when writing strings : in the absence of an "_Encoding" attribute (on the Iris + cube or coord object), we will attempt to encode data with "ascii" : If this fails, + it raise an error prompting the user to supply an "_Encoding" attribute. + +Where an "_Encoding" attribute is provided to Iris, we will honour it where possible, +identifying with "codecs.lookup" : This means we support the encodings in the Python +Standard Library, and the name aliases which it recognises. + +See: + +* known problems https://github.com/Unidata/netcdf4-python/issues/1440 +* suggestions for how this "ought" to work, discussed in the netcdf-c library + * https://github.com/Unidata/netcdf-c/issues/402 + +""" + +import codecs +import contextlib +import dataclasses +import threading +import warnings + +import numpy as np + +from iris.fileformats.netcdf._thread_safe_nc import ( + DatasetWrapper, + NetCDFDataProxy, + NetCDFWriteProxy, + VariableWrapper, +) +import iris.warnings +from iris.warnings import IrisCfLoadWarning, IrisCfSaveWarning + + +def decode_bytesarray_to_stringarray( + byte_array: np.ndarray, encoding: str, string_width: int +) -> np.ndarray: + """Convert an array of bytes to an array of strings, with one less dimension. + + N.B. for now at least, we assume the string dim is **always the last one**. + If 'string_width' is not given, it is set to the final dimension of 'byte_array'. + """ + if np.ma.isMaskedArray(byte_array): + # netCDF4-python sees zeros as "missing" -- we don't need or want that + byte_array = byte_array.data + bytes_shape = byte_array.shape + var_shape = bytes_shape[:-1] + string_dtype = f"U{string_width}" + result = np.empty(var_shape, dtype=string_dtype) + for ndindex in np.ndindex(var_shape): + element_bytes = byte_array[ndindex] + bytes = b"".join([b if b else b"\0" for b in element_bytes]) + string = bytes.decode(encoding) + result[ndindex] = string + return result + + +def encode_stringarray_as_bytearray( + data: np.typing.ArrayLike, encoding: str, string_dimension_length: int +) -> np.ndarray: + """Encode strings as a bytes array.""" + data = np.asanyarray(data) + element_shape = data.shape + result = np.zeros(element_shape + (string_dimension_length,), dtype="S1") + right_pad = b"\0" * string_dimension_length + for index in np.ndindex(element_shape): + string = data[index] + bytes = string.encode(encoding=encoding) + n_bytes = len(bytes) + # TODO: may want to issue warning or error if we overflow the length? + if n_bytes > string_dimension_length: + from iris.exceptions import TranslationError + + msg = ( + f"String {string!r} written to netcdf exceeds string dimension after " + f"encoding : {n_bytes} > {string_dimension_length}." + ) + raise TranslationError(msg) + + # It's all a bit nasty ... + bytes = (bytes + right_pad)[:string_dimension_length] + result[index] = [bytes[i : i + 1] for i in range(string_dimension_length)] + + return result + + +@dataclasses.dataclass +class VariableEncoder: + """A record of encoding details which can apply them to variable data.""" + + varname: str # just for the error messages + dtype: np.dtype + is_chardata: bool # just a shortcut for the dtype test + read_encoding: str # *always* a valid encoding from the codecs package + write_encoding: str # *always* a valid encoding from the codecs package + n_chars_dim: int # length of associated character dimension + string_width: int # string lengths when viewing as strings (i.e. "Uxx") + + def __init__(self, cf_var): + """Get all the info from an netCDF4 variable (or similar wrapper object). + + Most importantly, we do *not* store 'cf_var' : instead we extract the + necessary information and store it in this object. + So, this object has static state + is serialisable. + """ + self.varname = cf_var.name + self.dtype = cf_var.dtype + self.is_chardata = np.issubdtype(self.dtype, np.bytes_) + if self.is_chardata: + self.read_encoding = self._get_encoding(cf_var, writing=False) + self.write_encoding = self._get_encoding(cf_var, writing=True) + self.n_chars_dim = cf_var.group().dimensions[cf_var.dimensions[-1]].size + self.string_width = self._get_string_width(cf_var) + + @staticmethod + def _get_encoding(cf_var, writing=False) -> str: + """Get the byte encoding defined for this variable (or None).""" + result = getattr(cf_var, "_Encoding", None) + if result is not None: + try: + # Accept + normalise naming of encodings + result = codecs.lookup(result).name + # NOTE: if encoding does not suit data, errors can occur. + # For example, _Encoding = "ascii", with non-ascii content. + except LookupError: + # Unrecognised encoding name : handle this as just a warning + msg = ( + f"Ignoring unknown encoding for variable {cf_var.name!r}: " + f"_Encoding = {result!r}." + ) + warntype = IrisCfSaveWarning if writing else IrisCfLoadWarning + warnings.warn(msg, category=warntype) + # Proceed as if there is no specified encoding + result = None + + if result is None: + if writing: + result = DEFAULT_WRITE_ENCODING + else: + result = DEFAULT_READ_ENCODING + return result + + def _get_string_width(self, cf_var) -> int: + """Return the string-length defined for this variable.""" + # Work out the actual byte width from the parent dataset dimensions. + strlen = self.n_chars_dim + # Convert the string dimension length (i.e. bytes) to a sufficiently-long + # string width, depending on the (read) encoding used. + encoding = self.read_encoding + if "utf-16" in encoding: + # Each char needs at least 2 bytes -- including a terminator char + strlen = (strlen // 2) - 1 + elif "utf-32" in encoding: + # Each char needs exactly 4 bytes -- including a terminator char + strlen = (strlen // 4) - 1 + # "ELSE": assume there can be (at most) as many chars as bytes + return strlen + + def decode_bytes_to_stringarray(self, data: np.ndarray) -> np.ndarray: + if self.is_chardata: + # N.B. read encoding default is UTF-8 --> a "usually safe" choice + encoding = self.read_encoding + strlen = self.string_width + try: + data = decode_bytesarray_to_stringarray(data, encoding, strlen) + except UnicodeDecodeError as err: + msg = ( + f"Character data in variable {self.varname!r} could not be decoded " + f"with the {encoding!r} encoding. This can be fixed by setting the " + "variable '_Encoding' attribute to suit the content." + ) + raise ValueError(msg) from err + + return data + + def encode_strings_as_bytearray(self, data: np.ndarray) -> np.ndarray: + if self.is_chardata and data.dtype.kind == "U": + # N.B. it is also possible to pass a byte array (dtype "S1"), + # to be written directly, without processing. + try: + # N.B. write encoding *default* is "ascii" --> fails bad content + encoding = self.write_encoding + strlen = self.n_chars_dim + data = encode_stringarray_as_bytearray(data, encoding, strlen) + except UnicodeEncodeError as err: + msg = ( + f"String data written to netcdf character variable {self.varname!r} " + f"could not be represented in encoding {self.write_encoding!r}. " + "This can be fixed by setting a suitable variable '_Encoding' " + 'attribute, e.g. ._Encoding="UTF-8".' + ) + raise ValueError(msg) from err + return data + + +class NetcdfStringDecodeSetting(threading.local): + def __init__(self, perform_encoding: bool = True): + self.set(perform_encoding) + + def set(self, perform_encoding: bool): + self.perform_encoding = perform_encoding + + def __bool__(self): + return self.perform_encoding + + @contextlib.contextmanager + def context(self, perform_encoding: bool): + old_setting = self.perform_encoding + self.perform_encoding = perform_encoding + yield + self.perform_encoding = old_setting + + +DECODE_TO_STRINGS_ON_READ = NetcdfStringDecodeSetting() +DEFAULT_READ_ENCODING = "utf-8" +DEFAULT_WRITE_ENCODING = "ascii" + + +class EncodedVariable(VariableWrapper): + """A variable wrapper that translates variable data according to byte encodings.""" + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + # Override specific properties of the contained instance, making changes in the case + # that the variable contains char data, which is presented instead as strings + # with one less dimension. + + @property + def shape(self): + shape = self._contained_instance.shape + is_chardata = np.issubdtype(self._contained_instance.dtype, np.bytes_) + if is_chardata: + # Translated char data appears without the final dimension + shape = shape[:-1] # remove final dimension + return shape + + @property + def dimensions(self): + dimensions = self._contained_instance.dimensions + is_chardata = np.issubdtype(self._contained_instance.dtype, np.bytes_) + if is_chardata: + # Translated char data appears without the final dimension + dimensions = dimensions[:-1] # remove final dimension + return dimensions + + @property + def dtype(self): + dtype = self._contained_instance.dtype + is_chardata = np.issubdtype(self._contained_instance.dtype, np.bytes_) + if is_chardata: + # Create a coding spec : redo every time in case "_Encoding" has changed + encoding_spec = VariableEncoder(self._contained_instance) + dtype = np.dtype(f"U{encoding_spec.string_width}") + return dtype + + def __getitem__(self, keys): + self._contained_instance.set_auto_chartostring(False) + data = super().__getitem__(keys) + # Create a coding spec : redo every time in case "_Encoding" has changed + encoding_spec = VariableEncoder(self._contained_instance) + data = encoding_spec.decode_bytes_to_stringarray(data) + return data + + def __setitem__(self, keys, data): + data = np.asanyarray(data) + # Create a coding spec : redo every time in case "_Encoding" has changed + encoding_spec = VariableEncoder(self._contained_instance) + data = encoding_spec.encode_strings_as_bytearray(data) + super().__setitem__(keys, data) + + def set_auto_chartostring(self, onoff: bool): + msg = "auto_chartostring is not supported by Iris 'EncodedVariable' type." + raise TypeError(msg) + + +class EncodedDataset(DatasetWrapper): + """A specialised DatasetWrapper whose variables perform byte encoding.""" + + VAR_WRAPPER_CLS = EncodedVariable + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + def set_auto_chartostring(self, onoff: bool): + msg = "auto_chartostring is not supported by Iris 'EncodedDataset' type." + raise TypeError(msg) + + +class EncodedNetCDFDataProxy(NetCDFDataProxy): + __slots__ = NetCDFDataProxy.__slots__ + ("encoding_details",) + + def __init__(self, cf_var, *args, **kwargs): + # When creating, also capture + record the encoding to be performed. + kwargs["use_byte_data"] = True + super().__init__(cf_var, *args, **kwargs) + if not isinstance(cf_var, EncodedVariable): + msg = ( + f"Unexpected variable type : {type(cf_var)} of variable '{cf_var.name}'" + ": expected EncodedVariable." + ) + raise TypeError(msg) + self.encoding_details = VariableEncoder(cf_var._contained_instance) + + def __getitem__(self, keys): + data = super().__getitem__(keys) + # Apply the optional bytes-to-strings conversion + data = self.encoding_details.decode_bytes_to_stringarray(data) + return data + + +class EncodedNetCDFWriteProxy(NetCDFWriteProxy): + def __init__(self, filepath, cf_var, file_write_lock): + super().__init__(filepath, cf_var, file_write_lock) + self.encoding_details = VariableEncoder(cf_var) + + def __setitem__(self, key, data): + data = np.asanyarray(data) + # Apply the optional strings-to-bytes conversion + data = self.encoding_details.encode_strings_as_bytearray(data) + super().__setitem__(key, data) diff --git a/lib/iris/fileformats/netcdf/_thread_safe_nc.py b/lib/iris/fileformats/netcdf/_thread_safe_nc.py index 33183ef0fa..f96312cf79 100644 --- a/lib/iris/fileformats/netcdf/_thread_safe_nc.py +++ b/lib/iris/fileformats/netcdf/_thread_safe_nc.py @@ -159,6 +159,9 @@ class GroupWrapper(_ThreadSafeWrapper): CONTAINED_CLASS = netCDF4.Group # Note: will also accept a whole Dataset object, but that is OK. _DUCKTYPE_CHECK_PROPERTIES = ["createVariable"] + # Class to use when creating variable wrappers (default=VariableWrapper). + # - needed to support _byte_encoded_data.EncodedDataset. + VAR_WRAPPER_CLS = VariableWrapper # All Group API that returns Dimension(s) is wrapped to instead return # DimensionWrapper(s). @@ -203,7 +206,7 @@ def variables(self) -> typing.Dict[str, VariableWrapper]: """ with _GLOBAL_NETCDF4_LOCK: variables_ = self._contained_instance.variables - return {k: VariableWrapper.from_existing(v) for k, v in variables_.items()} + return {k: self.VAR_WRAPPER_CLS.from_existing(v) for k, v in variables_.items()} def createVariable(self, *args, **kwargs) -> VariableWrapper: """Call createVariable() from netCDF4.Group/Dataset within _GLOBAL_NETCDF4_LOCK. @@ -216,7 +219,7 @@ def createVariable(self, *args, **kwargs) -> VariableWrapper: """ with _GLOBAL_NETCDF4_LOCK: new_variable = self._contained_instance.createVariable(*args, **kwargs) - return VariableWrapper.from_existing(new_variable) + return self.VAR_WRAPPER_CLS.from_existing(new_variable) def get_variables_by_attributes( self, *args, **kwargs @@ -234,7 +237,7 @@ def get_variables_by_attributes( variables_ = list( self._contained_instance.get_variables_by_attributes(*args, **kwargs) ) - return [VariableWrapper.from_existing(v) for v in variables_] + return [self.VAR_WRAPPER_CLS.from_existing(v) for v in variables_] # All Group API that returns Group(s) is wrapped to instead return # GroupWrapper(s). @@ -252,7 +255,7 @@ def groups(self): """ with _GLOBAL_NETCDF4_LOCK: groups_ = self._contained_instance.groups - return {k: GroupWrapper.from_existing(v) for k, v in groups_.items()} + return {k: self.__class__.from_existing(v) for k, v in groups_.items()} @property def parent(self): @@ -268,7 +271,7 @@ def parent(self): """ with _GLOBAL_NETCDF4_LOCK: parent_ = self._contained_instance.parent - return GroupWrapper.from_existing(parent_) + return self.__class__.from_existing(parent_) def createGroup(self, *args, **kwargs): """Call createGroup() from netCDF4.Group/Dataset. @@ -281,7 +284,7 @@ def createGroup(self, *args, **kwargs): """ with _GLOBAL_NETCDF4_LOCK: new_group = self._contained_instance.createGroup(*args, **kwargs) - return GroupWrapper.from_existing(new_group) + return self.__class__.from_existing(new_group) class DatasetWrapper(GroupWrapper): @@ -311,14 +314,22 @@ def fromcdl(cls, *args, **kwargs): class NetCDFDataProxy: """A reference to the data payload of a single NetCDF file variable.""" - __slots__ = ("shape", "dtype", "path", "variable_name", "fill_value") - - def __init__(self, shape, dtype, path, variable_name, fill_value): - self.shape = shape + __slots__ = ( + "shape", + "dtype", + "path", + "variable_name", + "fill_value", + "use_byte_data", + ) + + def __init__(self, cf_var, dtype, path, fill_value, *, use_byte_data=False): + self.shape = cf_var.shape + self.variable_name = cf_var.name self.dtype = dtype self.path = path - self.variable_name = variable_name self.fill_value = fill_value + self.use_byte_data = use_byte_data @property def ndim(self): @@ -337,6 +348,8 @@ def __getitem__(self, keys): dataset = netCDF4.Dataset(self.path) try: variable = dataset.variables[self.variable_name] + if self.use_byte_data: + variable.set_auto_chartostring(False) # Get the NetCDF variable data and slice. var = variable[keys] finally: diff --git a/lib/iris/fileformats/netcdf/loader.py b/lib/iris/fileformats/netcdf/loader.py index 219f681e67..32eea77db8 100644 --- a/lib/iris/fileformats/netcdf/loader.py +++ b/lib/iris/fileformats/netcdf/loader.py @@ -36,7 +36,7 @@ import iris.coord_systems import iris.coords import iris.fileformats.cf -from iris.fileformats.netcdf import _thread_safe_nc +from iris.fileformats.netcdf import _bytecoding_datasets, _thread_safe_nc from iris.fileformats.netcdf.saver import _CF_ATTRS import iris.io import iris.util @@ -50,7 +50,11 @@ # An expected part of the public loader API, but includes thread safety # concerns so is housed in _thread_safe_nc. -NetCDFDataProxy = _thread_safe_nc.NetCDFDataProxy +# NOTE: this is the *default*, as required for public legacy api +# - in practice, when creating our proxies we dynamically choose between this and +# :class:`_thread_safe_nc.DatasetWrapper`, depending on +# :data:`_bytecoding_datasets.DECODE_TO_STRINGS_ON_READ` +NetCDFDataProxy = _bytecoding_datasets.EncodedNetCDFDataProxy class _WarnComboIgnoringBoundsLoad( @@ -279,7 +283,7 @@ def _get_cf_var_data(cf_var): # correct dtype. Note: this is not an issue for masked arrays, # only masked scalar values. if result is np.ma.masked: - result = np.ma.masked_all(1, dtype=cf_var.datatype) + result = np.ma.masked_all(1, dtype=cf_var.dtype) else: # Get lazy chunked data out of a cf variable. # Creates Dask wrappers around data arrays for any cube components which @@ -289,15 +293,27 @@ def _get_cf_var_data(cf_var): # Make a data-proxy that mimics array access and can fetch from the file. # Note: Special handling needed for "variable length string" types which # return a dtype of `str`, rather than a numpy type; use `S1` in this case. - fill_dtype = "S1" if cf_var.dtype is str else cf_var.dtype.str[1:] - fill_value = getattr( - cf_var.cf_data, - "_FillValue", - _thread_safe_nc.default_fillvals[fill_dtype], - ) - proxy = NetCDFDataProxy( - cf_var.shape, dtype, cf_var.filename, cf_var.cf_name, fill_value - ) + if getattr(cf_var.dtype, "kind", None) == "U": + # Special handling for "string variables". + fill_value = "" + else: + fill_dtype = "S1" if cf_var.dtype is str else cf_var.dtype.str[1:] + fill_value = getattr( + cf_var.cf_data, + "_FillValue", + _thread_safe_nc.default_fillvals[fill_dtype], + ) + + # Switch type of proxy, based on type of variable. + # It is done this way, instead of using an instance variable, because the + # limited nature of the wrappers makes a stateful choice awkward, + # e.g. especially, "variable.group()" is *not* the parent DatasetWrapper. + if isinstance(cf_var.cf_data, _bytecoding_datasets.EncodedVariable): + proxy_class = _bytecoding_datasets.EncodedNetCDFDataProxy + else: + proxy_class = _thread_safe_nc.NetCDFDataProxy + + proxy = proxy_class(cf_var.cf_data, dtype, cf_var.filename, fill_value) # Get the chunking specified for the variable : this is either a shape, or # maybe the string "contiguous". if CHUNK_CONTROL.mode is ChunkControl.Modes.AS_DASK: diff --git a/lib/iris/fileformats/netcdf/saver.py b/lib/iris/fileformats/netcdf/saver.py index 5177749c07..3d9f9a91a2 100644 --- a/lib/iris/fileformats/netcdf/saver.py +++ b/lib/iris/fileformats/netcdf/saver.py @@ -14,6 +14,7 @@ """ +import codecs import collections from itertools import repeat, zip_longest import os @@ -48,7 +49,8 @@ from iris.coords import AncillaryVariable, AuxCoord, CellMeasure, DimCoord import iris.exceptions import iris.fileformats.cf -from iris.fileformats.netcdf import _dask_locks, _thread_safe_nc +from iris.fileformats.netcdf import _bytecoding_datasets as bytecoding_datasets +from iris.fileformats.netcdf import _dask_locks from iris.fileformats.netcdf._attribute_handlers import ATTRIBUTE_HANDLERS import iris.io import iris.util @@ -300,7 +302,7 @@ class VariableEmulator(typing.Protocol): shape: tuple[int, ...] -CFVariable = typing.Union[_thread_safe_nc.VariableWrapper, VariableEmulator] +CFVariable = typing.Union[bytecoding_datasets.VariableWrapper, VariableEmulator] class Saver: @@ -403,7 +405,7 @@ def __init__(self, filename, netcdf_format, compute=True): # Put it inside a _thread_safe_nc wrapper to ensure thread-safety. # Except if it already is one, since they forbid "re-wrapping". if not hasattr(self._dataset, "THREAD_SAFE_FLAG"): - self._dataset = _thread_safe_nc.DatasetWrapper.from_existing( + self._dataset = bytecoding_datasets.DatasetWrapper.from_existing( self._dataset ) @@ -414,7 +416,7 @@ def __init__(self, filename, netcdf_format, compute=True): # Given a filepath string/path : create a dataset from that try: self.filepath = os.path.abspath(filename) - self._dataset = _thread_safe_nc.DatasetWrapper( + self._dataset = bytecoding_datasets.EncodedDataset( self.filepath, mode="w", format=netcdf_format ) except RuntimeError: @@ -759,7 +761,7 @@ def _create_cf_dimensions(self, cube, dimension_names, unlimited_dimensions=None # used for a different one pass else: - dim_name = self._get_coord_variable_name(cube, coord) + dim_name = self._get_element_variable_name(cube, coord) unlimited_dim_names.append(dim_name) for dim_name in dimension_names: @@ -990,12 +992,12 @@ def _add_aux_coords( ] # Include any relevant mesh location coordinates. - mesh: MeshXY | None = getattr(cube, "mesh") - mesh_location: str | None = getattr(cube, "location") + mesh: MeshXY | None = getattr(cube, "mesh") # type: ignore[annotation-unchecked] + mesh_location: str | None = getattr(cube, "location") # type: ignore[annotation-unchecked] if mesh and mesh_location: location_coords: MeshNodeCoords | MeshEdgeCoords | MeshFaceCoords = getattr( mesh, f"{mesh_location}_coords" - ) + ) # type: ignore[annotation-unchecked] coords_to_add.extend(list(location_coords)) return self._add_inner_related_vars( @@ -1365,7 +1367,7 @@ def record_dimension(names_list, dim_name, length, matching_coords=None): if dim_name is None: # Not already present : create a unique dimension name # from the coord. - dim_name = self._get_coord_variable_name(cube, coord) + dim_name = self._get_element_variable_name(cube, coord) # Disambiguate if it has the same name as an # existing dimension. # OR if it matches an existing file variable name. @@ -1541,38 +1543,14 @@ def _create_cf_bounds(self, coord, cf_var, cf_name, /, *, compression_kwargs=Non ) self._lazy_stream_data(data=bounds, cf_var=cf_var_bounds) - def _get_cube_variable_name(self, cube): - """Return a CF-netCDF variable name for the given cube. - - Parameters - ---------- - cube : :class:`iris.cube.Cube` - An instance of a cube for which a CF-netCDF variable - name is required. - - Returns - ------- - str - A CF-netCDF variable name as a string. - - """ - if cube.var_name is not None: - cf_name = cube.var_name - else: - # Convert to lower case and replace whitespace by underscores. - cf_name = "_".join(cube.name().lower().split()) - - cf_name = self.cf_valid_var_name(cf_name) - return cf_name - - def _get_coord_variable_name(self, cube_or_mesh, coord): - """Return a CF-netCDF variable name for a given coordinate-like element. + def _get_element_variable_name(self, cube_or_mesh, element): + """Return a CF-netCDF variable name for a given coordinate-like element, or cube. Parameters ---------- cube_or_mesh : :class:`iris.cube.Cube` or :class:`iris.mesh.MeshXY` The Cube or Mesh being saved to the netCDF file. - coord : :class:`iris.coords._DimensionalMetadata` + element : :class:`iris.coords._DimensionalMetadata` | :class:``iris.cube.Cube`` An instance of a coordinate (or similar), for which a CF-netCDF variable name is required. @@ -1592,17 +1570,21 @@ def _get_coord_variable_name(self, cube_or_mesh, coord): cube = None mesh = cube_or_mesh - if coord.var_name is not None: - cf_name = coord.var_name + if element.var_name is not None: + cf_name = element.var_name + elif isinstance(element, Cube): + # Make name for a Cube without a var_name. + cf_name = "_".join(element.name().lower().split()) else: - name = coord.standard_name or coord.long_name + # Make name for a Coord-like element without a var_name + name = element.standard_name or element.long_name if not name or set(name).intersection(string.whitespace): # We need to invent a name, based on its associated dimensions. - if cube is not None and cube.coords(coord): + if cube is not None and cube.coords(element): # It is a regular cube coordinate. # Auto-generate a name based on the dims. name = "" - for dim in cube.coord_dims(coord): + for dim in cube.coord_dims(element): name += f"dim{dim}" # Handle scalar coordinate (dims == ()). if not name: @@ -1616,8 +1598,8 @@ def _get_coord_variable_name(self, cube_or_mesh, coord): # At present, a location-coord cannot be nameless, as the # MeshXY code relies on guess_coord_axis. - assert isinstance(coord, Connectivity) - location = coord.cf_role.split("_")[0] + assert isinstance(element, Connectivity) + location = element.cf_role.split("_")[0] location_dim_attr = f"{location}_dimension" name = getattr(mesh, location_dim_attr) @@ -1693,6 +1675,8 @@ def _create_mesh(self, mesh): return cf_mesh_name def _set_cf_var_attributes(self, cf_var, element): + from iris.cube import Cube + # Deal with CF-netCDF units, and add the name+units properties. if isinstance(element, iris.coords.Coord): # Fix "degree" units if needed. @@ -1700,34 +1684,59 @@ def _set_cf_var_attributes(self, cf_var, element): else: units_str = str(element.units) - if cf_units.as_unit(units_str).is_udunits(): - _setncattr(cf_var, "units", units_str) - - standard_name = element.standard_name - if standard_name is not None: - _setncattr(cf_var, "standard_name", standard_name) - - long_name = element.long_name - if long_name is not None: - _setncattr(cf_var, "long_name", long_name) + # NB this bit is a nasty hack to preserve existing behaviour through a refactor: + # The attributes for Coords are created in the order units, standard_name, + # whereas for data-variables (aka Cubes) it is the other way around. + # Needed now that this routine is also called from _create_cf_data_variable. + # TODO: when we can break things, rationalise these to be the same. + def add_units_attr(): + if cf_units.as_unit(units_str).is_udunits(): + _setncattr(cf_var, "units", units_str) + + def add_names_attrs(): + standard_name = element.standard_name + if standard_name is not None: + _setncattr(cf_var, "standard_name", standard_name) + + long_name = element.long_name + if long_name is not None: + _setncattr(cf_var, "long_name", long_name) + + if isinstance(element, Cube): + add_names_attrs() + add_units_attr() + else: + add_units_attr() + add_names_attrs() # Add the CF-netCDF calendar attribute. if element.units.calendar: _setncattr(cf_var, "calendar", str(element.units.calendar)) - # Add any other custom coordinate attributes. - for name in sorted(element.attributes): - value = element.attributes[name] - - if name == "STASH": - # Adopting provisional Metadata Conventions for representing MO - # Scientific Data encoded in NetCDF Format. - name = "um_stash_source" - value = str(value) - - # Don't clobber existing attributes. - if not hasattr(cf_var, name): - _setncattr(cf_var, name, value) + # Note: when writing UGRID, "element" can be a Mesh which has no "dtype", + # and for dataless cubes it will have a 'None' dtype. + if getattr(element, "dtype", None) is not None: + # Most attributes are dealt with later. But _Encoding needs to be defined + # *before* we can write to a character variable. + if element.dtype.kind in "SU" and "_Encoding" in element.attributes: + encoding = element.attributes.pop("_Encoding") + _setncattr(cf_var, "_Encoding", encoding) + + if not isinstance(element, Cube): + # Add any other custom coordinate attributes. + # N.B. not Cube, which has specific handling in _create_cf_data_variable + for name in sorted(element.attributes): + value = element.attributes[name] + + if name == "STASH": + # Adopting provisional Metadata Conventions for representing MO + # Scientific Data encoded in NetCDF Format. + name = "um_stash_source" + value = str(value) + + # Don't clobber existing attributes. + if not hasattr(cf_var, name): + _setncattr(cf_var, name, value) def _create_generic_cf_array_var( self, @@ -1739,6 +1748,8 @@ def _create_generic_cf_array_var( element_dims=None, fill_value=None, compression_kwargs=None, + packing_controls: dict | None = None, + is_dataless=False, ): """Create theCF-netCDF variable given dimensional_metadata. @@ -1791,7 +1802,7 @@ def _create_generic_cf_array_var( # Work out the var-name to use. # N.B. the only part of this routine that may use a mesh _or_ a cube. - cf_name = self._get_coord_variable_name(cube_or_mesh, element) + cf_name = self._get_element_variable_name(cube_or_mesh, element) while cf_name in self._dataset.variables: cf_name = self._increment_name(cf_name) @@ -1804,18 +1815,29 @@ def _create_generic_cf_array_var( # Get the data values, in a way which works for any element type, as # all are subclasses of _DimensionalMetadata. # (e.g. =points if a coord, =data if an ancillary, etc) - data = element._core_values() + if isinstance(element, Cube): + data = element.core_data() + else: + data = element._core_values() # This compression contract is *not* applicable to a mesh. - if cube and cube.shape != data.shape: + if cube is not None and data is not None and cube.shape != data.shape: compression_kwargs = {} - if np.issubdtype(data.dtype, np.str_): + if not is_dataless and np.issubdtype(data.dtype, np.str_): # Deal with string-type variables. # Typically CF label variables, but also possibly ancil-vars ? string_dimension_depth = data.dtype.itemsize if data.dtype.kind == "U": - string_dimension_depth //= 4 + encoding = element.attributes.get("_Encoding", "ascii") + # TODO: this can fail -- use a sensible warning + default? + encoding = codecs.lookup(encoding).name + if encoding == "utf-32": + # UTF-32 is a special case -- always 4 exactly bytes per char, plus 4 + string_dimension_depth += 4 + else: + # generally, 4 bytes per char in numpy --> make bytewidth = string-width + string_dimension_depth //= 4 string_dimension_name = "string%d" % string_dimension_depth # Determine whether to create the string length dimension. @@ -1834,28 +1856,38 @@ def _create_generic_cf_array_var( # Create the label coordinate variable. cf_var = self._dataset.createVariable(cf_name, "|S1", element_dims) - # Convert data from an array of strings into a character array - # with an extra string-length dimension. - if len(element_dims) == 1: - data_first = data[0] - if is_lazy_data(data_first): - data_first = dask.compute(data_first) - data = list("%- *s" % (string_dimension_depth, data_first)) - else: - orig_shape = data.shape - new_shape = orig_shape + (string_dimension_depth,) - new_data = np.zeros(new_shape, cf_var.dtype) - for index in np.ndindex(orig_shape): - index_slice = tuple(list(index) + [slice(None, None)]) - new_data[index_slice] = list( - "%- *s" % (string_dimension_depth, data[index]) - ) - data = new_data + # # Convert data from an array of strings into a character array + # # with an extra string-length dimension. + # if len(element_dims) == 1: + # # Scalar variable (only has string dimension). + # data_first = data[0] + # if is_lazy_data(data_first): + # data_first = dask.compute(data_first) + # data = list("%- *s" % (string_dimension_depth, data_first)) + # else: + # # NOTE: at present, can't do this lazily?? + # orig_shape = data.shape + # new_shape = orig_shape + (string_dimension_depth,) + # new_data = np.zeros(new_shape, cf_var.dtype) + # for index in np.ndindex(orig_shape): + # index_slice = tuple(list(index) + [slice(None, None)]) + # new_data[index_slice] = list( + # "%- *s" % (string_dimension_depth, data[index]) + # ) + # data = new_data else: # A normal (numeric) variable. # ensure a valid datatype for the file format. - element_type = type(element).__name__ - data = self._ensure_valid_dtype(data, element_type, element) + if is_dataless: + dtype = self._DATALESS_DTYPE + fill_value = self._DATALESS_FILLVALUE + else: + element_type = type(element).__name__ + data = self._ensure_valid_dtype(data, element_type, element) + if not packing_controls: + dtype = data.dtype.newbyteorder("=") + else: + dtype = packing_controls["dtype"] # Check if this is a dim-coord. is_dimcoord = cube is not None and element in cube.dim_coords @@ -1869,7 +1901,7 @@ def _create_generic_cf_array_var( # Create the CF-netCDF variable. cf_var = self._dataset.createVariable( cf_name, - data.dtype.newbyteorder("="), + dtype, element_dims, fill_value=fill_value, **compression_kwargs, @@ -1886,12 +1918,18 @@ def _create_generic_cf_array_var( element, cf_var, cf_name, compression_kwargs=compression_kwargs ) - # Add the data to the CF-netCDF variable. - self._lazy_stream_data(data=data, cf_var=cf_var) - # Add names + units + # NOTE: *must* now do first, as we may need '_Encoding' set to write it ! self._set_cf_var_attributes(cf_var, element) + # Add the data to the CF-netCDF variable. + if not is_dataless: + if packing_controls: + # We must set packing attributes (if any), before assigning values. + for key, value in packing_controls["attributes"]: + _setncattr(cf_var, key, value) + self._lazy_stream_data(data=data, cf_var=cf_var) + return cf_name def _create_cf_cell_methods(self, cube, dimension_names): @@ -2238,9 +2276,9 @@ def _create_cf_grid_mapping(self, cube, cf_var_cube): cfvar = self._name_coord_map.name(coord) if not cfvar: # not found - create and store it: - cfvar = self._get_coord_variable_name(cube, coord) + cfvar = self._get_element_variable_name(cube, coord) self._name_coord_map.append( - cfvar, self._get_coord_variable_name(cube, coord) + cfvar, self._get_element_variable_name(cube, coord) ) cfvar_names.append(cfvar) @@ -2320,18 +2358,10 @@ def _create_cf_data_variable( # be removed. # Get the values in a form which is valid for the file format. is_dataless = cube.is_dataless() - if is_dataless: - data = None - else: - data = self._ensure_valid_dtype(cube.core_data(), "cube", cube) - if is_dataless: - # The variable must have *some* dtype, and it must be maskable - dtype = self._DATALESS_DTYPE - fill_value = self._DATALESS_FILLVALUE - elif not packing: - dtype = data.dtype.newbyteorder("=") - else: + packing_controls = None + if packing and not is_dataless: + data = self._ensure_valid_dtype(cube.core_data(), "cube", cube) if isinstance(packing, dict): if "dtype" not in packing: msg = "The dtype attribute is required for packing." @@ -2370,45 +2400,29 @@ def _create_cf_data_variable( else: add_offset = cmin + 2 ** (n - 1) * scale_factor - def set_packing_ncattrs(cfvar): - """Set netCDF packing attributes. - - NOTE: cfvar needs to be a _thread_safe_nc._ThreadSafeWrapper subclass. - - """ - assert hasattr(cfvar, "THREAD_SAFE_FLAG") - if packing: - if scale_factor: - _setncattr(cfvar, "scale_factor", scale_factor) - if add_offset: - _setncattr(cfvar, "add_offset", add_offset) - - cf_name = self._get_cube_variable_name(cube) - while cf_name in self._dataset.variables: - cf_name = self._increment_name(cf_name) + packing_controls = { + "dtype": dtype, + "attributes": [ + ("scale_factor", scale_factor), + ("add_offset", add_offset), + ], + } # Create the cube CF-netCDF data variable with data payload. - cf_var = self._dataset.createVariable( - cf_name, dtype, dimension_names, fill_value=fill_value, **kwargs + cf_name = self._create_generic_cf_array_var( + cube, + dimension_names, + cube, + element_dims=dimension_names, + fill_value=fill_value, + compression_kwargs=kwargs, + packing_controls=packing_controls, + is_dataless=is_dataless, ) + cf_var = self._dataset.variables[cf_name] - if not is_dataless: - set_packing_ncattrs(cf_var) - self._lazy_stream_data(data=data, cf_var=cf_var) - - if cube.standard_name: - _setncattr(cf_var, "standard_name", cube.standard_name) - - if cube.long_name: - _setncattr(cf_var, "long_name", cube.long_name) - - if cube.units.is_udunits(): - _setncattr(cf_var, "units", str(cube.units)) - - # Add the CF-netCDF calendar attribute. - if cube.units.calendar: - _setncattr(cf_var, "calendar", cube.units.calendar) - + # Set general attrs: NB this part is cube-specific (not the same for components) + # - so 'set_cf_var_attributes' *doesn't* set these, if element is a Cube if iris.FUTURE.save_split_attrs: attr_names = cube.attributes.locals.keys() else: @@ -2535,7 +2549,7 @@ def store( ) -> None: # Create a data-writeable object that we can stream into, which # encapsulates the file to be opened + variable to be written. - write_wrapper = _thread_safe_nc.NetCDFWriteProxy( + write_wrapper = bytecoding_datasets.EncodedNetCDFWriteProxy( self.filepath, cf_var, self.file_write_lock ) # Add to the list of delayed writes, used in delayed_completion(). diff --git a/lib/iris/tests/integration/netcdf/test_chararrays.py b/lib/iris/tests/integration/netcdf/test_chararrays.py new file mode 100644 index 0000000000..496867ee8a --- /dev/null +++ b/lib/iris/tests/integration/netcdf/test_chararrays.py @@ -0,0 +1,266 @@ +# Copyright Iris contributors +# +# This file is part of Iris and is released under the BSD license. +# See LICENSE in the root of the repository for full licensing details. +"""Integration tests for string data handling.""" + +import subprocess + +import numpy as np +import pytest + +import iris +from iris.coords import AuxCoord, DimCoord +from iris.cube import Cube +from iris.fileformats.netcdf import _bytecoding_datasets + +# from iris.fileformats.netcdf import _thread_safe_nc +from iris.tests import env_bin_path + +NX, N_STRLEN = 3, 64 +TEST_STRINGS = ["Münster", "London", "Amsterdam"] +TEST_COORD_VALS = ["bun", "éclair", "sandwich"] + +# VARS_COORDS_SHARE_STRING_DIM = True +VARS_COORDS_SHARE_STRING_DIM = False +if VARS_COORDS_SHARE_STRING_DIM: + # Fix length so that the max coord strlen will be same as data one + TEST_COORD_VALS[-1] = "Xsandwich" + + +# Ensure all tests run with "split attrs" turned on. +@pytest.fixture(scope="module", autouse=True) +def enable_split_attrs(): + with iris.FUTURE.context(save_split_attrs=True): + yield + + +def convert_strings_to_chararray(string_array_1d, maxlen, encoding="utf-8"): + bbytes = [text.encode(encoding) for text in string_array_1d] + pad = b"\0" * maxlen + bbytes = [(x + pad)[:maxlen] for x in bbytes] + chararray = np.array([[bb[i : i + 1] for i in range(maxlen)] for bb in bbytes]) + return chararray + + +def convert_bytesarray_to_strings( + byte_array, encoding="utf-8", string_length: int | None = None +): + """Convert bytes to strings. + + N.B. for now at least, we assume the string dim is **always the last one**. + """ + bytes_shape = byte_array.shape + var_shape = bytes_shape[:-1] + if string_length is None: + string_length = bytes_shape[-1] + string_dtype = f"U{string_length}" + result = np.empty(var_shape, dtype=string_dtype) + for ndindex in np.ndindex(var_shape): + element_bytes = byte_array[ndindex] + bytes = b"".join([b if b else b"\0" for b in element_bytes]) + string = bytes.decode(encoding) + result[ndindex] = string + return result + + +INCLUDE_COORD = True +# INCLUDE_COORD = False + +INCLUDE_NUMERIC_AUXCOORD = True +# INCLUDE_NUMERIC_AUXCOORD = False + + +# DATASET_CLASS = _thread_safe_nc.DatasetWrapper +DATASET_CLASS = _bytecoding_datasets.EncodedDataset + + +def make_testfile(filepath, chararray, coordarray, encoding_str=None): + ds = DATASET_CLASS(filepath, "w") + try: + ds.createDimension("x", NX) + ds.createDimension("nstr", N_STRLEN) + vx = ds.createVariable("x", int, dimensions=("x")) + vx[:] = np.arange(NX) + if INCLUDE_COORD: + ds.createDimension("nstr2", N_STRLEN) + v_co = ds.createVariable( + "v_co", + "S1", + dimensions=( + "x", + "nstr2", + ), + ) + v_co[:] = coordarray + if encoding_str is not None: + v_co._Encoding = encoding_str + if INCLUDE_NUMERIC_AUXCOORD: + v_num = ds.createVariable( + "v_num", + float, + dimensions=("x",), + ) + v_num[:] = np.arange(NX) + v = ds.createVariable( + "v", + "S1", + dimensions=( + "x", + "nstr", + ), + ) + v[:] = chararray + if encoding_str is not None: + v._Encoding = encoding_str + if INCLUDE_COORD: + coords_str = "v_co" + if INCLUDE_NUMERIC_AUXCOORD: + coords_str += " v_num" + v.coordinates = coords_str + finally: + ds.close() + + +def make_testcube( + dataarray, + coordarray, # for now, these are always *string* arrays + encoding_str: str | None = None, +): + cube = Cube(dataarray, var_name="v") + cube.add_dim_coord(DimCoord(np.arange(NX), var_name="x"), 0) + if encoding_str is not None: + cube.attributes["_Encoding"] = encoding_str + if INCLUDE_COORD: + co_x = AuxCoord(coordarray, var_name="v_co") + if encoding_str is not None: + co_x.attributes["_Encoding"] = encoding_str + cube.add_aux_coord(co_x, 0) + return cube + + +NCDUMP_PATHSTR = str(env_bin_path("ncdump")) + + +def ncdump(nc_path: str, *args): + """Call ncdump to print a dump of a file.""" + call_args = [NCDUMP_PATHSTR, nc_path] + list(args) + bytes = subprocess.check_output(call_args) + text = bytes.decode("utf-8") + print(text) + return text + + +def show_result(filepath): + print(f"File {filepath}") + print("NCDUMP:") + ncdump(filepath) + # with nc.Dataset(filepath, "r") as ds: + # v = ds.variables["v"] + # print("\n----\nNetcdf data readback (basic)") + # try: + # print(repr(v[:])) + # except UnicodeDecodeError as err: + # print(repr(err)) + # print("..raw:") + # v.set_auto_chartostring(False) + # print(repr(v[:])) + print("\nAs iris cube..") + try: + iris.loading.LOAD_PROBLEMS.reset() + cube = iris.load_cube(filepath) + print(cube) + if iris.loading.LOAD_PROBLEMS.problems: + print(iris.loading.LOAD_PROBLEMS) + print( + "\n".join(iris.loading.LOAD_PROBLEMS.problems[0].stack_trace.format()) + ) + print("-data-") + print(repr(cube.data)) + print("-numeric auxcoord data-") + print(repr(cube.coord("x").points)) + if INCLUDE_COORD: + print("-string auxcoord data-") + try: + print(repr(cube.coord("v_co").points)) + except Exception as err2: + print(repr(err2)) + except UnicodeDecodeError as err: + print(repr(err)) + + +@pytest.fixture(scope="session") +def save_dir(tmp_path_factory): + return tmp_path_factory.mktemp("save_files") + + +# TODO: the tests don't test things properly yet, they just exercise the code and print +# things for manual debugging. +test_encodings = ( + None, + "ascii", + "utf-8", + "utf-32", +) +# tsts = ("utf-8",) +# tsts = ("utf-8", "utf-32",) +# tsts = ("utf-32",) +# tsts = ("utf-8", "ascii", "utf-8") + + +@pytest.mark.parametrize("encoding", test_encodings) +def test_load_encodings(encoding, save_dir): + """Load exercise. + + Make a testfile with utf-8 content, variously labelled. + Load with Iris + show result (error or cubes). + """ + # small change + print(f"\n=========\nTesting encoding: {encoding}") + filepath = save_dir / f"tmp_load_{str(encoding)}.nc" + # Actual content is always either utf-8 or utf-32 + do_as = encoding + if encoding != "utf-32": + do_as = "utf-8" + TEST_CHARARRAY = convert_strings_to_chararray( + TEST_STRINGS, N_STRLEN, encoding=do_as + ) + TEST_COORDARRAY = convert_strings_to_chararray( + TEST_COORD_VALS, N_STRLEN, encoding=do_as + ) + make_testfile(filepath, TEST_CHARARRAY, TEST_COORDARRAY, encoding_str=encoding) + if encoding == "ascii": + # If explicitly labelled as ascii, 'utf-8' data will fail to load back ... + msg = r"Character data .* could not be decoded with the 'ascii' encoding\." + with pytest.raises(ValueError, match=msg): + show_result(filepath) + else: + # ... otherwise, utf-8 data loads even without a label, as 'utf-8' default used + show_result(filepath) + + +@pytest.mark.parametrize("encoding", test_encodings) +def test_save_encodings(encoding, save_dir): + """Save exercise. + + Make test-cube with non-ascii content, and various '_Encoding' labels. + Save with Iris + show result (error or ncdump). + """ + cube = make_testcube( + dataarray=TEST_STRINGS, coordarray=TEST_COORD_VALS, encoding_str=encoding + ) + print(cube) + filepath = save_dir / f"tmp_save_{str(encoding)}.nc" + if encoding in ("ascii", None): + msg = ( + "String data written to netcdf character variable 'v' " + "could not be represented in encoding 'ascii'" + ) + with pytest.raises( + ValueError, + match=msg, + ): + iris.save(cube, filepath) + else: + iris.save(cube, filepath) + show_result(filepath) diff --git a/lib/iris/tests/integration/netcdf/test_stringdata.py b/lib/iris/tests/integration/netcdf/test_stringdata.py new file mode 100644 index 0000000000..5050152042 --- /dev/null +++ b/lib/iris/tests/integration/netcdf/test_stringdata.py @@ -0,0 +1,412 @@ +# Copyright Iris contributors +# +# This file is part of Iris and is released under the BSD license. +# See LICENSE in the root of the repository for full licensing details. +"""Integration tests for various uses of character/string arrays in netcdf file variables. + +This covers both the loading and saving of variables which are the content of +data-variables, auxiliary coordinates, ancillary variables and -possibly?- cell measures. +""" + +from dataclasses import dataclass +from pathlib import Path +from typing import Iterable + +import numpy as np +from numpy.typing import ArrayLike +import pytest + +import iris +from iris.coords import AuxCoord, DimCoord +from iris.cube import Cube +from iris.fileformats.netcdf import _thread_safe_nc + + +@pytest.fixture(scope="module") +def all_lazy_auxcoords(): + """Ensure that *all* aux-coords are loaded lazily, even really small ones.""" + old_minlazybytes = iris.fileformats.netcdf.loader._LAZYVAR_MIN_BYTES + iris.fileformats.netcdf.loader._LAZYVAR_MIN_BYTES = 0 + yield + iris.fileformats.netcdf.loader._LAZYVAR_MIN_BYTES = old_minlazybytes + + +N_XDIM = 3 +N_CHARS_DIM = 64 +# TODO: remove (debug) +# PERSIST_TESTFILES: str | None = "~/chararray_testfiles" +PERSIST_TESTFILES: str | None = None + +NO_ENCODING_STR = "" +TEST_ENCODINGS = [ + NO_ENCODING_STR, + "ascii", + "utf-8", + # "iso8859-1", # a common one-byte-per-char "codepage" type + # "utf-16", + "utf-32", +] + + +# +# Routines to convert between byte and string arrays. +# Independently defined here, to avoid relying on any code we are testing. +# +def convert_strings_to_chararray( + string_array_1d: ArrayLike, maxlen: int, encoding: str | None = None +) -> np.ndarray: + # Note: this is limited to 1-D arrays of strings. + # Could generalise that if needed, but for now this makes it simpler. + if encoding is None: + encoding = "ascii" + bbytes = [text.encode(encoding) for text in string_array_1d] + pad = b"\0" * maxlen + bbytes = [(x + pad)[:maxlen] for x in bbytes] + chararray = np.array([[bb[i : i + 1] for i in range(maxlen)] for bb in bbytes]) + return chararray + + +def convert_bytearray_to_strings( + byte_array: ArrayLike, encoding: str = "utf-8", string_length: int | None = None +) -> np.ndarray: + """Convert bytes to strings. + + N.B. for now at least, we assume the string dim is **always the last one**. + """ + byte_array = np.asanyarray(byte_array) + bytes_shape = byte_array.shape + var_shape = bytes_shape[:-1] + if string_length is None: + string_length = bytes_shape[-1] + string_dtype = f"U{string_length}" + result = np.empty(var_shape, dtype=string_dtype) + for ndindex in np.ndindex(var_shape): + element_bytes = byte_array[ndindex] + bytes = b"".join([b if b else b"\0" for b in element_bytes]) + string = bytes.decode(encoding) + result[ndindex] = string + return result + + +@dataclass +class SamplefileDetails: + """Convenience container for information about a sample file.""" + + filepath: Path + datavar_data: ArrayLike + stringcoord_data: ArrayLike + numericcoord_data: ArrayLike + + +def make_testfile( + testfile_path: Path, + encoding_str: str, + coords_on_separate_dim: bool, +) -> SamplefileDetails: + """Create a test netcdf file. + + Also returns content information for checking loaded results. + """ + if encoding_str == NO_ENCODING_STR: + encoding = None + else: + encoding = encoding_str + + data_is_ascii = encoding in (None, "ascii") + + numeric_values = np.arange(3.0) + if data_is_ascii: + coordvar_strings = ["mOnster", "London", "Amsterdam"] + datavar_strings = ["bun", "Eclair", "sandwich"] + else: + coordvar_strings = ["Münster", "London", "Amsterdam"] + datavar_strings = ["bun", "éclair", "sandwich"] + + coordvar_bytearray = convert_strings_to_chararray( + string_array_1d=coordvar_strings, maxlen=N_CHARS_DIM, encoding=encoding + ) + datavar_bytearray = convert_strings_to_chararray( + string_array_1d=datavar_strings, maxlen=N_CHARS_DIM, encoding=encoding + ) + + ds = _thread_safe_nc.DatasetWrapper(testfile_path, "w") + try: + ds.createDimension("x", N_XDIM) + ds.createDimension("nstr", N_CHARS_DIM) + if coords_on_separate_dim: + ds.createDimension("nstr2", N_CHARS_DIM) + v_xdim = ds.createVariable("x", int, dimensions=("x")) + v_xdim[:] = np.arange(N_XDIM) + + v_co = ds.createVariable( + "v_co", + "S1", + dimensions=( + "x", + "nstr2" if coords_on_separate_dim else "nstr", + ), + ) + v_co[:] = coordvar_bytearray + + if encoding is not None: + v_co._Encoding = encoding + + v_numeric = ds.createVariable( + "v_numeric", + float, + dimensions=("x",), + ) + v_numeric[:] = numeric_values + + v_datavar = ds.createVariable( + "v", + "S1", + dimensions=( + "x", + "nstr", + ), + ) + v_datavar[:] = datavar_bytearray + + if encoding is not None: + v_datavar._Encoding = encoding + + v_datavar.coordinates = "v_co v_numeric" + finally: + ds.close() + + return SamplefileDetails( + filepath=testfile_path, + datavar_data=datavar_strings, + stringcoord_data=coordvar_strings, + numericcoord_data=numeric_values, + ) + + +@pytest.fixture(params=TEST_ENCODINGS) +def encoding(request): + return request.param + + +def load_problems_list(): + return [str(prob) for prob in iris.loading.LOAD_PROBLEMS.problems] + + +class TestReadEncodings: + """Test loading of testfiles with encoded string data.""" + + @pytest.fixture(autouse=True) + def _clear_load_problems(self): + iris.loading.LOAD_PROBLEMS.reset() + yield + + @pytest.fixture(params=["coordsSameDim", "coordsOwnDim"]) + def use_separate_dims(self, request): + yield request.param == "coordsOwnDim" + + @pytest.fixture() + def readtest_path( + self, + encoding, + tmp_path, + use_separate_dims, + ) -> Iterable[SamplefileDetails]: + """Create a suitable valid testfile, and return expected string content.""" + match PERSIST_TESTFILES: + case str(): + tmp_path = Path(PERSIST_TESTFILES).expanduser() + case _: + pass + if encoding == "": + filetag = "noencoding" + else: + filetag = encoding + dimtag = "diffdims" if use_separate_dims else "samedims" + tempfile_path = tmp_path / f"sample_read_{filetag}_{dimtag}.nc" + yield tempfile_path + + @pytest.fixture() + def readtest_data( + self, + encoding, + readtest_path, + use_separate_dims, + ) -> Iterable[SamplefileDetails]: + """Create a suitable valid testfile, and return expected string content.""" + testdata = make_testfile( + testfile_path=readtest_path, + encoding_str=encoding, + coords_on_separate_dim=use_separate_dims, + ) + + # # TODO: temporary for debug -- TO REMOVE + # from iris.tests.integration.netcdf.test_chararrays import ncdump + # ncdump(str(tempfile_path)) + yield testdata + + def test_valid_encodings(self, encoding, readtest_data: SamplefileDetails): + testfile_path, datavar_strings, coordvar_strings, numeric_data = ( + readtest_data.filepath, + readtest_data.datavar_data, + readtest_data.stringcoord_data, + readtest_data.numericcoord_data, + ) + cube = iris.load_cube(testfile_path) + assert load_problems_list() == [] + assert cube.shape == (N_XDIM,) + + if encoding != "utf-32": + expected_string_width = N_CHARS_DIM + else: + expected_string_width = (N_CHARS_DIM // 4) - 1 + assert cube.dtype == f" SampleCubeDetails: + data_is_ascii = encoding_str in (NO_ENCODING_STR, "ascii") + + numeric_values = np.arange(3.0) + if data_is_ascii: + coordvar_strings = ["mOnster", "London", "Amsterdam"] + datavar_strings = ["bun", "Eclair", "sandwich"] + else: + coordvar_strings = ["Münster", "London", "Amsterdam"] + datavar_strings = ["bun", "éclair", "sandwich"] + + if not byte_data: + charlen = N_CHARS_DIM + if encoding_str == "utf-32": + charlen = charlen // 4 - 1 + strings_dtype = np.dtype(f"U{charlen}") + coordvar_array = np.array(coordvar_strings, dtype=strings_dtype) + datavar_array = np.array(datavar_strings, dtype=strings_dtype) + else: + write_encoding = encoding_str + if write_encoding == NO_ENCODING_STR: + write_encoding = "ascii" + coordvar_array = convert_strings_to_chararray( + coordvar_strings, maxlen=N_CHARS_DIM, encoding=write_encoding + ) + datavar_array = convert_strings_to_chararray( + datavar_strings, maxlen=N_CHARS_DIM, encoding=write_encoding + ) + + cube = Cube(datavar_array, var_name="v") + cube.add_dim_coord(DimCoord(np.arange(N_XDIM), var_name="x"), 0) + if encoding_str != NO_ENCODING_STR: + cube.attributes["_Encoding"] = encoding_str + co_x = AuxCoord(coordvar_array, var_name="v_co") + if encoding_str != NO_ENCODING_STR: + co_x.attributes["_Encoding"] = encoding_str + co_dims = (0, 1) if byte_data else (0,) + cube.add_aux_coord(co_x, co_dims) + + result = SampleCubeDetails( + cube=cube, + datavar_data=datavar_array, + stringcoord_data=coordvar_array, + ) + return result + + +class TestWriteEncodings: + """Test saving of testfiles with encoded string data. + + To avoid circularity, we generate and save *cube* data. + """ + + @pytest.fixture(params=["dataAsStrings", "dataAsBytes"]) + def write_bytes(self, request): + yield request.param == "dataAsBytes" + + @pytest.fixture() + def writetest_path(self, encoding, write_bytes, tmp_path): + """Create a suitable test cube, with either string or byte content.""" + if PERSIST_TESTFILES: + tmp_path = Path(PERSIST_TESTFILES).expanduser() + if encoding == "": + filetag = "noencoding" + else: + filetag = encoding + datatag = "writebytes" if write_bytes else "writestrings" + tempfile_path = tmp_path / f"sample_write_{filetag}_{datatag}.nc" + yield tempfile_path + + @pytest.fixture() + def writetest_data(self, writetest_path, encoding, write_bytes): + """Create a suitable test cube + save to a file. + + Apply the given encoding to both coord and cube data. + Form the data as bytes, or as strings, depending on 'write_bytes'.' + """ + cube_info = make_testcube(encoding_str=encoding, byte_data=write_bytes) + cube_info.save_path = writetest_path + cube = cube_info.cube + iris.save(cube, writetest_path) + yield cube_info + + def test_valid_encodings(self, encoding, writetest_data, write_bytes): + cube_info = writetest_data + cube, path = cube_info.cube, cube_info.save_path + # TODO: not testing the "byte read/write" yet + # Make a quick check for cube equality : but the presentation depends on the read mode + # with DECODE_TO_STRINGS_ON_READ.context(not write_bytes): + # read_cube = iris.load_cube(path) + # assert read_cube == cube + + # N.B. file content should not depend on whether bytes or strings were written + vararray, coordarray = cube_info.datavar_data, cube_info.stringcoord_data + ds = _thread_safe_nc.DatasetWrapper(path) + ds.set_auto_chartostring(False) + v_main = ds.variables["v"] + v_co = ds.variables["v_co"] + assert v_main.shape == (N_XDIM, N_CHARS_DIM) + assert v_co.shape == (N_XDIM, N_CHARS_DIM) + assert v_main.dtype == " 1 + : utf-8 -> 1 or 4 ??? + : utf-16 -> 2 or 4 ??? + : utf-32 -> 4 + + - on LOAD, in absence of strlen controls, how do we choose the result DTYPE (i.e. character length)? + - again, may depend on the encoding: + : ascii = "U" + : UTF-8 = "U" + : UTF-16 = "U" + : UTF-32 = "U" + - N.B. these are ll at least "safe" - i.e. won't lose characters + + +separately from these, there is the question of how the controls affect "normal" +cube operations. + - the easiest approach is to define a "special" attribute, + which can be set on any cube/component + - using the dtype-length of the data would be *possible*, in conjunction with the + above-proposed "default rules" for choosing strlen from the dtype. + But this might not round-trip in all cases. + +within the actual data arrays + - we can't really expect any different to what numpy does + - that is, the dtype-length of any element <= that of the array (and not ==) + this may be tricky, but we can't easily prevent it. + >>> a = np.array(['', 'a', 'bb']) + >>> a + array(['', 'a', 'bb'], dtype='>> a[0].dtype + dtype('>> a[1].dtype + dtype('>> a[2].dtype + dtype('>> a.dtype + dtype('>> + - likewise, we can't assign without possible truncation. + If you **want** to expand the supported width, can use ".astype()" first ? + + +======================== +========================= + +forms in files: + * char chardata(dim1, dim2, strlen_xx); # char data + * string data(dim1, dim2); + +netcdf types: +(netcdf docs terms) + NC_BYTE 8-bit signed integer + NC_UBYTE 8-bit unsigned integer + NC_CHAR 8-bit character + NC_STRING variable length character string + +***NOTE*** there is no NC_UCHAR or "unsigned char" type + + +relevant numpy base types (scalar dtypes): + * "S" bytes : np.bytes_ == np.int8 + * "B" unsigned bytes : np.ubyte == np.uint8 + * 'i' ints : np.int_ + * 'u' unsigned ints : np.int_ + * "U" unicode string : np.str_ + +forms in numpy: + * np.ndarray(dtype="S1") # char data + * np.ndarray(dtype="Snn") # char data + * np.ndarray(dtype="Unn") # strings + * np.ndarray(dtype="") + +possibilities in createVariable: +""" + The datatype can be a numpy datatype object, or a string that describes a numpy dtype object ... + datatype can also be a CompoundType instance (for a structured, or compound array), a VLType instance (for a variable-length array), +** or the python str builtin (for a variable-length string array). +** Numpy string and unicode datatypes with length greater than one are aliases for str. +""" + +test types: + "i1" : np.int8 + "u1" : np.uint8 + "S1" : np.byte_ + "U1" : np.str_ + "S" : + "U" : with/without non-ascii content + +save all these to files... +outputs from "test_nc_dtypes.py" test run: + SPEC:i1 SAVED-AS:int8 byte RELOAD-AS:int8 + SPEC:u1 SAVED-AS:uint8 ubyte RELOAD-AS:uint8 + SPEC:S1 SAVED-AS:|S1 char RELOAD-AS: () + SPEC:U1 SAVED-AS:`) dtype = np.dtype(dtype) cf_var = mock.MagicMock( diff --git a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver.py b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver.py index 0905c3d2a9..374cb4815e 100644 --- a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver.py +++ b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver.py @@ -35,7 +35,8 @@ ) from iris.coords import AncillaryVariable, AuxCoord, DimCoord from iris.cube import Cube -from iris.fileformats.netcdf import Saver, _thread_safe_nc +from iris.fileformats.netcdf import Saver +from iris.fileformats.netcdf import _bytecoding_datasets as ds_wrappers from iris.tests._shared_utils import assert_CDL import iris.tests.stock as stock @@ -219,7 +220,7 @@ def test_big_endian(self): def test_zlib(self): cube = self._simple_cube(">f4") - api = self.patch("iris.fileformats.netcdf.saver._thread_safe_nc") + api = self.patch("iris.fileformats.netcdf.saver.bytecoding_datasets") # Define mocked default fill values to prevent deprecation warning (#4374). api.default_fillvals = collections.defaultdict(lambda: -99.0) # Mock the apparent dtype of mocked variables, to avoid an error. @@ -230,7 +231,7 @@ def test_zlib(self): # a fill-value report on a non-compliant variable in a non-file (!) with Saver("/dummy/path", "NETCDF4", compute=False) as saver: saver.write(cube, zlib=True) - dataset = api.DatasetWrapper.return_value + dataset = api.EncodedDataset.return_value create_var_call = mock.call( "air_pressure_anomaly", np.dtype("float32"), @@ -261,9 +262,6 @@ def test_compression(self): ) cube.add_ancillary_variable(anc_coord, data_dims=data_dims) - patch = self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.createVariable" - ) compression_kwargs = { "complevel": 9, "fletcher32": True, @@ -273,10 +271,20 @@ def test_compression(self): with self.temp_filename(suffix=".nc") as nc_path: with Saver(nc_path, "NETCDF4", compute=False) as saver: + tgt = ( + "iris.fileformats.netcdf.saver.bytecoding_datasets" + ".EncodedDataset.createVariable" + ) + createvar_spy = self.patch( + tgt, + # Use 'wraps' to allow the patched methods to function as normal + # - the patch object just acts as a 'spy' on its calls. + wraps=saver._dataset.createVariable, + ) saver.write(cube, **compression_kwargs) - self.assertEqual(5, patch.call_count) - result = self._filter_compression_calls(patch, compression_kwargs) + self.assertEqual(5, createvar_spy.call_count) + result = self._filter_compression_calls(createvar_spy, compression_kwargs) self.assertEqual(3, len(result)) self.assertEqual({cube.name(), aux_coord.name(), anc_coord.name()}, set(result)) @@ -294,9 +302,6 @@ def test_non_compression__shape(self): ) cube.add_ancillary_variable(anc_coord, data_dims=data_dims[1]) - patch = self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.createVariable" - ) compression_kwargs = { "complevel": 9, "fletcher32": True, @@ -306,11 +311,21 @@ def test_non_compression__shape(self): with self.temp_filename(suffix=".nc") as nc_path: with Saver(nc_path, "NETCDF4", compute=False) as saver: + tgt = ( + "iris.fileformats.netcdf.saver.bytecoding_datasets" + ".EncodedDataset.createVariable" + ) + createvar_spy = self.patch( + tgt, + # Use 'wraps' to allow the patched methods to function as normal + # - the patch object just acts as a 'spy' on its calls. + wraps=saver._dataset.createVariable, + ) saver.write(cube, **compression_kwargs) - self.assertEqual(5, patch.call_count) + self.assertEqual(5, createvar_spy.call_count) result = self._filter_compression_calls( - patch, compression_kwargs, mismatch=True + createvar_spy, compression_kwargs, mismatch=True ) self.assertEqual(4, len(result)) # the aux coord and ancil variable are not compressed due to shape, and @@ -327,10 +342,6 @@ def test_non_compression__dtype(self): aux_coord = AuxCoord(data, var_name="non_compress_aux", units="1") cube.add_aux_coord(aux_coord, data_dims=data_dims) - patch = self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.createVariable" - ) - patch.return_value = mock.MagicMock(dtype=np.dtype("S1")) compression_kwargs = { "complevel": 9, "fletcher32": True, @@ -340,11 +351,21 @@ def test_non_compression__dtype(self): with self.temp_filename(suffix=".nc") as nc_path: with Saver(nc_path, "NETCDF4", compute=False) as saver: + tgt = ( + "iris.fileformats.netcdf.saver.bytecoding_datasets" + ".EncodedDataset.createVariable" + ) + createvar_spy = self.patch( + tgt, + # Use 'wraps' to allow the patched methods to function as normal + # - the patch object just acts as a 'spy' on its calls. + wraps=saver._dataset.createVariable, + ) saver.write(cube, **compression_kwargs) - self.assertEqual(4, patch.call_count) + self.assertEqual(4, createvar_spy.call_count) result = self._filter_compression_calls( - patch, compression_kwargs, mismatch=True + createvar_spy, compression_kwargs, mismatch=True ) self.assertEqual(3, len(result)) # the aux coord is not compressed due to its string dtype, and @@ -374,7 +395,7 @@ def test_default_unlimited_dimensions(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertFalse(ds.dimensions["dim0"].isunlimited()) self.assertFalse(ds.dimensions["dim1"].isunlimited()) ds.close() @@ -384,7 +405,7 @@ def test_no_unlimited_dimensions(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=None) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) for dim in ds.dimensions.values(): self.assertFalse(dim.isunlimited()) ds.close() @@ -406,7 +427,7 @@ def test_custom_unlimited_dimensions(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=unlimited_dimensions) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) for dim in unlimited_dimensions: self.assertTrue(ds.dimensions[dim].isunlimited()) ds.close() @@ -415,7 +436,7 @@ def test_custom_unlimited_dimensions(self): coords = [cube.coord(dim) for dim in unlimited_dimensions] with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=coords) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) for dim in unlimited_dimensions: self.assertTrue(ds.dimensions[dim].isunlimited()) ds.close() @@ -426,7 +447,7 @@ def test_reserved_attributes(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) res = ds.getncattr("dimensions") ds.close() self.assertEqual(res, "something something_else") @@ -448,7 +469,7 @@ def test_dimensional_to_scalar(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) # Confirm that the only dimension is the one denoting the number # of bounds - have successfully saved the 2D bounds array into 1D. self.assertEqual(["bnds"], list(ds.dimensions.keys())) @@ -488,7 +509,7 @@ def _check_bounds_setting(self, climatological=False): saver._ensure_valid_dtype.return_value = mock.Mock( shape=coord.bounds.shape, dtype=coord.bounds.dtype ) - var = mock.MagicMock(spec=_thread_safe_nc.VariableWrapper) + var = mock.MagicMock(spec=ds_wrappers.EncodedVariable) # Make the main call. Saver._create_cf_bounds(saver, coord, var, "time") @@ -529,7 +550,7 @@ def test_valid_range_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.valid_range, vrange) ds.close() @@ -541,7 +562,7 @@ def test_valid_min_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.valid_min, 1) ds.close() @@ -553,7 +574,7 @@ def test_valid_max_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.valid_max, 2) ds.close() @@ -573,7 +594,7 @@ def test_valid_range_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.variables["longitude"].valid_range, vrange) ds.close() @@ -585,7 +606,7 @@ def test_valid_min_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.variables["longitude"].valid_min, 1) ds.close() @@ -597,7 +618,7 @@ def test_valid_max_saved(self): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, unlimited_dimensions=[]) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) self.assertArrayEqual(ds.variables["longitude"].valid_max, 2) ds.close() @@ -629,7 +650,7 @@ def _netCDF_var(self, cube, **kwargs): with self.temp_filename(".nc") as nc_path: with Saver(nc_path, "NETCDF4") as saver: saver.write(cube, **kwargs) - ds = _thread_safe_nc.DatasetWrapper(nc_path) + ds = ds_wrappers.EncodedDataset(nc_path) (var,) = [ var for var in ds.variables.values() @@ -706,7 +727,7 @@ def setUp(self): ) ) patch = mock.patch( - "iris.fileformats.netcdf._thread_safe_nc.DatasetWrapper", + "iris.fileformats.netcdf._bytecoding_datasets.EncodedDataset", dataset_class, ) _ = patch.start() diff --git a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__lazy_stream_data.py b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__lazy_stream_data.py index 7c884e4c22..3b76dca13b 100644 --- a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__lazy_stream_data.py +++ b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__lazy_stream_data.py @@ -30,7 +30,7 @@ def saver_patch(): mock_dataset = mock.MagicMock() mock_dataset_class = mock.Mock(return_value=mock_dataset) # Mock the wrapper within the netcdf saver - target1 = "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper" + target1 = "iris.fileformats.netcdf.saver.bytecoding_datasets.DatasetWrapper" # Mock the real netCDF4.Dataset within the threadsafe-nc module, as this is # used by NetCDFDataProxy and NetCDFWriteProxy. target2 = "iris.fileformats.netcdf._thread_safe_nc.netCDF4.Dataset" diff --git a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__ugrid.py b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__ugrid.py index 9494eabebf..571237512d 100644 --- a/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__ugrid.py +++ b/lib/iris/tests/unit/fileformats/netcdf/saver/test_Saver__ugrid.py @@ -401,12 +401,12 @@ def test_compression(self): # into the iris.fileformats.netcdf.saver. Also we want to check that the # compression kwargs are passed into the NetCDF4 createVariable method patch = self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.createVariable", + "iris.fileformats.netcdf.saver.bytecoding_datasets.EncodedDataset.createVariable", ) # No need to patch this NetCDF4 variable to compensate for the previous patch # on createVariable, which doesn't actually create the variable. self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.variables" + "iris.fileformats.netcdf.saver.bytecoding_datasets.EncodedDataset.variables" ) cube = make_cube(var_name=(var_name := "a")) compression_kwargs = { @@ -785,10 +785,10 @@ def test_compression(self): """ patch = self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.createVariable", + "iris.fileformats.netcdf.saver.bytecoding_datasets.EncodedDataset.createVariable", ) self.patch( - "iris.fileformats.netcdf.saver._thread_safe_nc.DatasetWrapper.variables" + "iris.fileformats.netcdf.saver.bytecoding_datasets.EncodedDataset.variables" ) mesh = make_mesh() compression_kwargs = { diff --git a/lib/iris/tests/unit/fileformats/netcdf/test_bytecoding_datasets.py b/lib/iris/tests/unit/fileformats/netcdf/test_bytecoding_datasets.py new file mode 100644 index 0000000000..f16097bef3 --- /dev/null +++ b/lib/iris/tests/unit/fileformats/netcdf/test_bytecoding_datasets.py @@ -0,0 +1,454 @@ +# Copyright Iris contributors +# +# This file is part of Iris and is released under the BSD license. +# See LICENSE in the root of the repository for full licensing details. +"""Unit tests for :class:`iris.fileformats.netcdf._bytecoding_datasets` module.""" + +from pathlib import Path + +import numpy as np +import pytest + +from iris.exceptions import TranslationError +from iris.fileformats.netcdf._bytecoding_datasets import ( + DECODE_TO_STRINGS_ON_READ, + EncodedDataset, +) +from iris.fileformats.netcdf._thread_safe_nc import DatasetWrapper +from iris.warnings import IrisCfLoadWarning, IrisCfSaveWarning + +encoding_options = [None, "ascii", "utf-8", "utf-32"] + +samples_3_ascii = np.array( + ["one", "", "seven"], # N.B. include empty! +) +samples_3_nonascii = np.array(["two", "", "épéé"]) + + +def strings_maxbytes(strings, encoding): + return max(len(string.encode(encoding)) for string in strings) + + +@pytest.fixture(params=encoding_options) +def encoding(request): + return request.param + + +@pytest.fixture(scope="module") +def tempdir(tmp_path_factory): + path = tmp_path_factory.mktemp("netcdf") + return path + + +def make_encoded_dataset( + path: Path, strlen: int, encoding: str | None = None +) -> EncodedDataset: + """Create a test EncodedDataset linked to an actual file. + + * strlen becomes the string dimension (i.e. a number of *bytes*) + * a variable "vxs" is created + * If 'encoding' is given, the "vxs::_Encoding" attribute is created with this value + """ + ds = EncodedDataset(path, "w") + ds.createDimension("x", 3) + ds.createDimension("strlen", strlen) + v = ds.createVariable("vxs", "S1", ("x", "strlen")) + if encoding is not None: + v.setncattr("_Encoding", encoding) + return ds + + +def fetch_undecoded_var(path, varname): + # Open a path as a "normal" dataset, and return a given variable. + ds_normal = DatasetWrapper(path) + ds_normal._contained_instance.set_auto_chartostring(False) + v = ds_normal.variables[varname] + # Return a variable, rather than its data, so we can check attributes etc. + return v + + +def check_array_matching(arr1, arr2): + """Check for arrays matching shape, dtype and content.""" + assert ( + arr1.shape == arr2.shape and arr1.dtype == arr2.dtype and np.all(arr1 == arr2) + ) + + +def check_raw_content(path, varname, expected_byte_array): + v = fetch_undecoded_var(path, varname) + bytes_result = v[:] + check_array_matching(bytes_result, expected_byte_array) + + +def _make_bytearray_inner(data, bytewidth, encoding): + # Convert to a (list of [lists of..]) strings or bytes to a + # (list of [lists of..]) length-1 bytes with an extra dimension. + if isinstance(data, str): + # Convert input strings to bytes + data = data.encode(encoding) + if isinstance(data, bytes): + # iterate over bytes to get a sequence of length-1 bytes (what np.array wants) + result = [data[i : i + 1] for i in range(len(data))] + # pad or truncate everything to the required bytewidth + result = (result + [b"\0"] * bytewidth)[:bytewidth] + else: + # If not string/bytes, expect the input to be a list. + # N.B. the recursion is inefficient, but we don't care about that here + result = [_make_bytearray_inner(part, bytewidth, encoding) for part in data] + return result + + +def make_bytearray(data, bytewidth, encoding="ascii"): + """Convert bytes or lists of bytes into a numpy byte array. + + This is largely to avoid using "encode_stringarray_as_bytearray", since we don't + want to depend on that when we should be testing it. + So, it mostly replicates the function of that, but it does also support bytes in the + input. + """ + # First, Convert to a (list of [lists of]..) length-1 bytes objects + data = _make_bytearray_inner(data, bytewidth, encoding) + # We should now be able to create an array of single bytes. + result = np.array(data) + assert result.dtype == "S1" + return result + + +class TestWriteStrings: + """Test how string data is saved to a file. + + Mostly, we read back data as a "normal" dataset to avoid relying on the read code, + which is separately tested -- see 'TestReadStrings'. + """ + + def test_encodings(self, encoding, tempdir): + # Create a dataset with the variable + path = tempdir / f"test_writestrings_encoding_{encoding!s}.nc" + + if encoding in [None, "ascii"]: + writedata = samples_3_ascii + write_encoding = "ascii" + else: + writedata = samples_3_nonascii + write_encoding = encoding + + writedata = writedata.copy() # just for safety? + strlen = strings_maxbytes(writedata, write_encoding) + + ds_encoded = make_encoded_dataset(path, strlen, encoding) + v = ds_encoded.variables["vxs"] + + # Effectively, checks that we *can* write strings + v[:] = writedata + + # Close, re-open as an "ordinary" dataset, and check the raw content. + ds_encoded.close() + expected_bytes = make_bytearray(writedata, strlen, write_encoding) + check_raw_content(path, "vxs", expected_bytes) + + # Check also that the "_Encoding" property is as expected + v = fetch_undecoded_var(path, "vxs") + result_attr = v.getncattr("_Encoding") if "_Encoding" in v.ncattrs() else None + assert result_attr == encoding + + def test_scalar(self, tempdir): + # Like 'test_write_strings', but the variable has *only* the string dimension. + path = tempdir / "test_writestrings_scalar.nc" + + strlen = 5 + ds_encoded = make_encoded_dataset(path, strlen=strlen) + v = ds_encoded.createVariable("v0_scalar", "S1", ("strlen",)) + + # Checks that we *can* write a string + v[:] = np.array("stuff", dtype=str) + + # Close, re-open as an "ordinary" dataset, and check the raw content. + ds_encoded.close() + expected_bytes = make_bytearray(b"stuff", strlen) + check_raw_content(path, "v0_scalar", expected_bytes) + + def test_multidim(self, tempdir): + # Like 'test_write_strings', but the variable has additional dimensions. + path = tempdir / "test_writestrings_multidim.nc" + + strlen = 5 + ds_encoded = make_encoded_dataset(path, strlen=strlen) + ds_encoded.createDimension("y", 2) + v = ds_encoded.createVariable( + "vyxn", + "S1", + ( + "y", + "x", + "strlen", + ), + ) + + # Check that we *can* write a multidimensional string array + test_data = [ + ["one", "n", ""], + ["two", "xxxxx", "four"], + ] + v[:] = test_data + + # Close, re-open as an "ordinary" dataset, and check the raw content. + ds_encoded.close() + expected_bytes = make_bytearray(test_data, strlen) + check_raw_content(path, "vyxn", expected_bytes) + + @pytest.mark.parametrize("encoding", [None, "ascii"]) + def test_write_encoding_failure(self, tempdir, encoding): + path = tempdir / f"test_writestrings_encoding_{encoding}_fail.nc" + ds = make_encoded_dataset(path, strlen=5, encoding=encoding) + v = ds.variables["vxs"] + encoding_name = encoding + if encoding_name == None: + encoding_name = "ascii" + msg = ( + "String data written to netcdf character variable 'vxs'.*" + f" could not be represented in encoding '{encoding_name}'. " + ) + with pytest.raises(ValueError, match=msg): + v[:] = samples_3_nonascii + + def test_write_badencoding_ignore(self, tempdir): + path = tempdir / "test_writestrings_badencoding_ignore.nc" + ds = make_encoded_dataset(path, strlen=5, encoding="unknown") + v = ds.variables["vxs"] + msg = r"Ignoring unknown encoding for variable 'vxs': _Encoding = 'unknown'\." + with pytest.warns(IrisCfSaveWarning, match=msg): + v[:] = samples_3_ascii # will work OK + + def test_overlength(self, tempdir): + # Check expected behaviour with over-length data + path = tempdir / "test_writestrings_overlength.nc" + strlen = 5 + ds = make_encoded_dataset(path, strlen=strlen, encoding="ascii") + v = ds.variables["vxs"] + msg = r"String .* written to netcdf exceeds string dimension .* : [0-9]* > 5\." + with pytest.raises(TranslationError, match=msg): + v[:] = ["1", "123456789", "two"] + + def test_overlength_splitcoding(self, tempdir): + # Check expected behaviour when non-ascii multibyte coding gets truncated + path = tempdir / "test_writestrings_overlength_splitcoding.nc" + strlen = 5 + ds = make_encoded_dataset(path, strlen=strlen, encoding="utf-8") + v = ds.variables["vxs"] + # Note: we must do the assignment as a single byte array, to avoid hitting the + # safety check for this exact problem : see previous check. + byte_arrays = [ + string.encode("utf-8")[:strlen] for string in ("1", "1234ü", "two") + ] + nd_bytes_array = np.array( + [ + [bytes[i : i + 1] if i < len(bytes) else b"\0" for i in range(strlen)] + for bytes in byte_arrays + ] + ) + v[:] = nd_bytes_array + # This creates a problem: it won't read back + msg = ( + "Character data in variable 'vxs' could not be decoded " + "with the 'utf-8' encoding." + ) + with pytest.raises(ValueError, match=msg): + v[:] + + # Check also that we *can* read the raw content. + ds.close() + expected_bytes = [ + b"1", + b"1234\xc3", # NOTE: truncated encoding + b"two", + ] + expected_bytearray = make_bytearray(expected_bytes, strlen) + check_raw_content(path, "vxs", expected_bytearray) + + +class TestWriteChars: + @pytest.mark.parametrize("write_form", ["strings", "bytes"]) + def test_write_chars(self, tempdir, write_form): + encoding = "utf-8" + write_strings = samples_3_nonascii + strlen = strings_maxbytes(write_strings, encoding) + write_bytes = make_bytearray(write_strings, strlen, encoding=encoding) + # NOTE: 'flexi' form util decides the width needs to be 7 !! + path = tempdir / f"test_writechars_{write_form}.nc" + ds = make_encoded_dataset(path, encoding=encoding, strlen=strlen) + v = ds.variables["vxs"] + + # assign in *either* way.. + if write_form == "strings": + v[:] = write_strings + else: + v[:] = write_bytes + + # .. the result should be the same + ds.close() + check_raw_content(path, "vxs", write_bytes) + + +class TestRead: + """Test how character data is read and converted to strings. + + N.B. many testcases here parallel the 'TestWriteStrings' : we are creating test + datafiles with 'make_dataset' and assigning raw bytes, as-per 'TestWriteChars'. + + We are mostly checking here that reading back produces string arrays as expected. + However, it is simple + convenient to also check the 'DECODE_TO_STRINGS_ON_READ' + function here, i.e. "raw" bytes reads. So that is also done in this class. + """ + + @pytest.fixture(params=["strings", "bytes"]) + def readmode(self, request): + return request.param + + def undecoded_testvar(self, ds_encoded, varname: str): + path = ds_encoded.filepath() + ds_encoded.close() + ds = DatasetWrapper(path) + v = ds.variables[varname] + v.set_auto_chartostring(False) + return v + + def test_encodings(self, encoding, tempdir, readmode): + # Create a dataset with the variable + path = tempdir / f"test_read_encodings_{encoding!s}_{readmode}.nc" + + if encoding in [None, "ascii"]: + write_strings = samples_3_ascii + write_encoding = "ascii" + else: + write_strings = samples_3_nonascii + write_encoding = encoding + + write_strings = write_strings.copy() # just for safety? + strlen = strings_maxbytes(write_strings, write_encoding) + write_bytes = make_bytearray(write_strings, strlen, encoding=write_encoding) + + ds_encoded = make_encoded_dataset(path, strlen, encoding) + v = ds_encoded.variables["vxs"] + v[:] = write_bytes + + if readmode == "strings": + # Test "normal" read --> string array + result = v[:] + expected = write_strings + if encoding == "utf-8": + # In this case, with the given non-ascii sample data, the + # "default minimum string length" is overestimated. + assert strlen == 7 and result.dtype == "U7" + # correct the result dtype to pass the write_strings comparison below + truncated_result = result.astype("U4") + # Also check that content is the same (i.e. not actually truncated) + assert np.all(truncated_result == result) + result = truncated_result + else: + # Close and re-open as "regular" dataset -- just to check the raw content + v = self.undecoded_testvar(ds_encoded, "vxs") + result = v[:] + expected = write_bytes + + check_array_matching(result, expected) + + def test_scalar(self, tempdir, readmode): + # Like 'test_write_strings', but the variable has *only* the string dimension. + path = tempdir / f"test_read_scalar_{readmode}.nc" + + strlen = 5 + ds_encoded = make_encoded_dataset(path, strlen=strlen) + v = ds_encoded.createVariable("v0_scalar", "S1", ("strlen",)) + + data_string = "stuff" + data_bytes = make_bytearray(data_string, 5) + + # Checks that we *can* write a string + v[:] = data_bytes + + if readmode == "strings": + # Test "normal" read --> string array + result = v[:] + expected = np.array(data_string) + else: + # Test "raw" read --> byte array + v = self.undecoded_testvar(ds_encoded, "v0_scalar") + result = v[:] + expected = data_bytes + + check_array_matching(result, expected) + + def test_multidim(self, tempdir, readmode): + # Like 'test_write_strings', but the variable has additional dimensions. + path = tempdir / f"test_read_multidim_{readmode}.nc" + + strlen = 5 + ds_encoded = make_encoded_dataset(path, strlen=strlen) + ds_encoded.createDimension("y", 2) + v = ds_encoded.createVariable( + "vyxn", + "S1", + ( + "y", + "x", + "strlen", + ), + ) + + # Check that we *can* write a multidimensional string array + test_strings = [ + ["one", "n", ""], + ["two", "xxxxx", "four"], + ] + test_bytes = make_bytearray(test_strings, strlen) + v[:] = test_bytes + + if readmode == "strings": + # Test "normal" read --> string array + result = v[:] + expected = np.array(test_strings) + else: + # Test "raw" read --> byte array + v = self.undecoded_testvar(ds_encoded, "vyxn") + result = v[:] + expected = test_bytes + + check_array_matching(result, expected) + + def test_read_encoding_failure(self, tempdir, readmode): + path = tempdir / f"test_read_encoding_failure_{readmode}.nc" + strlen = 10 + ds_encoded = make_encoded_dataset(path, strlen=strlen, encoding="ascii") + v = ds_encoded.variables["vxs"] + test_utf8_bytes = make_bytearray( + samples_3_nonascii, bytewidth=strlen, encoding="utf-8" + ) + v[:] = test_utf8_bytes + + if readmode == "strings": + msg = ( + "Character data in variable 'vxs' could not be decoded " + "with the 'ascii' encoding." + ) + with pytest.raises(ValueError, match=msg): + v[:] + else: + v = self.undecoded_testvar(ds_encoded, "vxs") + result = v[:] # this ought to be ok! + + assert np.all(result == test_utf8_bytes) + + def test_read_badencoding_ignore(self, tempdir): + path = tempdir / f"test_read_badencoding_ignore.nc" + strlen = 10 + ds = make_encoded_dataset(path, strlen=strlen, encoding="unknown") + v = ds.variables["vxs"] + test_utf8_bytes = make_bytearray( + samples_3_nonascii, bytewidth=strlen, encoding="utf-8" + ) + v[:] = test_utf8_bytes + + msg = r"Ignoring unknown encoding for variable 'vxs': _Encoding = 'unknown'\." + with pytest.warns(IrisCfLoadWarning, match=msg): + # raises warning but succeeds, due to default read encoding of 'utf-8' + v[:]