def func(name, dset):
if isinstance(dset, h5py.Dataset):
tag = dset.name
tag_attribs = required_tags.get(tag)
if tag_attribs is not None:
tag_list.remove(tag)
attrib_list = utils.key_list(tag_attribs)
for key in tag_attribs:
if len(attrib_list) > 0:
if key == 'dim':
attrib_list.remove(key)
check_dim(dset, tag_attribs)
else:
attr = dset.attrs.get(key)
if attr is not None:
attr_str = attr.decode('utf-8')
if attr_str != tag_attribs.get(key):
logger.warning('incorrect attribute in ' +
tag + ': is ' +
key + ':' +
attr_str + ' but should be ' +
key + ':' +
tag_attribs.get(key))
res.res = False
attrib_list.remove(key)
report_items(
attrib_list,
'the following attributes are missing in tag ',
tag,
logger)
def func(name, dset):
if isinstance(dset, h5py.Dataset):
tag = dset.name
tag_attribs = required_tags.get(tag)
if tag_attribs is not None:
tag_list.remove(tag)
attrib_list = utils.key_list(tag_attribs)
for key in tag_attribs:
if len(attrib_list) > 0:
if key == 'dim':
attrib_list.remove(key)
check_dim(dset, tag_attribs)
else:
attr = dset.attrs.get(key)
if attr is not None:
attr_str = attr.decode('utf-8')
if attr_str != tag_attribs.get(key):
logger.warning('incorrect attribute in ' +
tag + ': is ' + key + ':' +
attr_str +
' but should be ' + key +
':' + tag_attribs.get(key))
res.res = False
attrib_list.remove(key)
report_items(attrib_list,
'the following attributes are missing in tag ',
tag, logger)
def tags(file, required_tags, logger):
"""
This method is used when a file of hdf type is given.
All tags from the hdf file are added in the filetags list.
Then the schema is evaluated for tags. With each tag discovered
it checks whether there is matching tag in the filetags list.
If a tag is missing, the function exits with False.
Otherwise, it will return True.
Parameters
----------
file : str
File Name including path
schema : str
Schema file name
logger : Logger
a Logger instance
Returns
-------
True if verified
False if not verified
"""
tag_list = utils.key_list(required_tags)
class Result:
def __init__(self):
self.result = True
def missing_tag(self):
self.result = False
def is_verified(self):
return self.result
result = Result()
filetags = []
def func(name, dset):
if isinstance(dset, h5py.Dataset):
filetags.append(dset.name)
file_h5 = h5py.File(file, 'r')
file_h5.visititems(func)
for tag in tag_list:
if tag not in filetags:
logger.warning('tag ' + tag + ' not found')
result.missing_tag()
return result.is_verified()
def tags(file, required_tags, logger):
"""
This method is used when a file of hdf type is given.
All tags from the hdf file are added in the filetags list.
Then the schema is evaluated for tags. With each tag discovered
it checks whether there is matching tag in the filetags list.
If a tag is missing, the function exits with False.
Otherwise, it will return True.
Parameters
----------
file : str
File Name including path
schema : str
Schema file name
logger : Logger
a Logger instance
Returns
-------
True if verified
False if not verified
"""
tag_list = utils.key_list(required_tags)
class Result:
def __init__(self):
self.result = True
def missing_tag(self):
self.result = False
def is_verified(self):
return self.result
result = Result()
filetags = []
def func(name, dset):
if isinstance(dset, h5py.Dataset):
filetags.append(dset.name)
file_h5 = h5py.File(file, 'r')
file_h5.visititems(func)
for tag in tag_list:
if tag not in filetags:
logger.warning('tag ' + tag + ' not found')
result.missing_tag()
return result.is_verified()
def structure(file, required_tags, logger):
"""
This method is used when a file of hdf type is given.
All tags and array dimensions are verified against a schema.
(see :download:`schemas/tags.json <../../../config/default/schemas/tags.json>`
example file).
Parameters
----------
file : str
File Name including path
schema : str
Schema file name
logger : Logger
a Logger instance
Returns
-------
None
"""
class Result():
res = True
def check_dim(dset, attr):
required_dim = attr.get('dim')
required_dim_copy = utils.copy_list(required_dim)
dim = dset.shape
if len(dim) == len(required_dim):
for i in range(len(dim)):
try:
required_dim_copy.remove(dim[i])
except ValueError:
logger.warning('ValueError: The dataset ' + dset.name +
' dimension ' + str(i) +
' is wrong: it is [' +
str(dset.shape[i]) + '] but should be [' +
str(required_dim[i]) + ']')
res.res = False
else:
logger.warning('The dataset ' + dset.name + ' dimensions: ' +
str(dset.shape) + ' but should be ' + str(required_dim))
res.res = False
def func(name, dset):
if isinstance(dset, h5py.Dataset):
tag = dset.name
tag_attribs = required_tags.get(tag)
if tag_attribs is not None:
tag_list.remove(tag)
attrib_list = utils.key_list(tag_attribs)
for key in tag_attribs:
if len(attrib_list) > 0:
if key == 'dim':
attrib_list.remove(key)
check_dim(dset, tag_attribs)
else:
attr = dset.attrs.get(key)
if attr is not None:
attr_str = attr.decode('utf-8')
if attr_str != tag_attribs.get(key):
logger.warning('incorrect attribute in ' +
tag + ': is ' +
key + ':' +
attr_str + ' but should be ' +
key + ':' +
tag_attribs.get(key))
res.res = False
attrib_list.remove(key)
report_items(
attrib_list,
'the following attributes are missing in tag ',
tag,
logger)
res = Result()
tag_list = utils.key_list(required_tags)
file_h5 = h5py.File(file, 'r')
file_h5.visititems(func)
if res.res:
return True
else:
report_items(tag_list, 'the following tags are missing: ', '', logger)
return False
def structure(file, required_tags, logger):
"""
This method is used when a file of hdf type is given.
All tags and array dimensions are verified against a schema.
(see :download:`schemas/tags.json <../../../config/default/schemas/tags.json>`
example file).
Parameters
----------
file : str
File Name including path
schema : str
Schema file name
logger : Logger
a Logger instance
Returns
-------
None
"""
class Result():
res = True
def check_dim(dset, attr):
required_dim = attr.get('dim')
required_dim_copy = utils.copy_list(required_dim)
dim = dset.shape
if len(dim) == len(required_dim):
for i in range(len(dim)):
try:
required_dim_copy.remove(dim[i])
except ValueError:
logger.warning('ValueError: The dataset ' + dset.name +
' dimension ' + str(i) +
' is wrong: it is [' + str(dset.shape[i]) +
'] but should be [' + str(required_dim[i]) +
']')
res.res = False
else:
logger.warning('The dataset ' + dset.name + ' dimensions: ' +
str(dset.shape) + ' but should be ' +
str(required_dim))
res.res = False
def func(name, dset):
if isinstance(dset, h5py.Dataset):
tag = dset.name
tag_attribs = required_tags.get(tag)
if tag_attribs is not None:
tag_list.remove(tag)
attrib_list = utils.key_list(tag_attribs)
for key in tag_attribs:
if len(attrib_list) > 0:
if key == 'dim':
attrib_list.remove(key)
check_dim(dset, tag_attribs)
else:
attr = dset.attrs.get(key)
if attr is not None:
attr_str = attr.decode('utf-8')
if attr_str != tag_attribs.get(key):
logger.warning('incorrect attribute in ' +
tag + ': is ' + key + ':' +
attr_str +
' but should be ' + key +
':' + tag_attribs.get(key))
res.res = False
attrib_list.remove(key)
report_items(attrib_list,
'the following attributes are missing in tag ',
tag, logger)
res = Result()
tag_list = utils.key_list(required_tags)
file_h5 = h5py.File(file, 'r')
file_h5.visititems(func)
if res.res:
return True
else:
report_items(tag_list, 'the following tags are missing: ', '', logger)
return False
