def clean_functions(functions_data):
file_location = functions_data['file_location']
data = functions_data['data']
executor_id = data['fn_to_clean']
logger.info(f'Going to clean functions from {executor_id}')
storage_config = data['storage_config']
storage = Storage(storage_config=storage_config)
prefix = '/'.join([JOBS_PREFIX, executor_id]) + '/'
key_list = storage.list_keys(storage.bucket, prefix)
storage.delete_objects(storage.bucket, key_list)
if os.path.exists(file_location):
os.remove(file_location)
logger.info('Finished')
def _fill_optional_args(self, function, data):
"""
Fills in those reserved, optional parameters that might be write to the function signature
"""
func_sig = inspect.signature(function)
if 'ibm_cos' in func_sig.parameters:
if 'ibm_cos' in self.lithops_config:
if self.internal_storage.backend == 'ibm_cos':
ibm_boto3_client = self.internal_storage.get_client()
else:
ibm_boto3_client = Storage(
lithops_config=self.lithops_config,
storage_backend='ibm_cos').get_client()
data['ibm_cos'] = ibm_boto3_client
else:
raise Exception(
'Cannot create the ibm_cos client: missing configuration')
if 'storage' in func_sig.parameters:
data['storage'] = self.internal_storage.storage
if 'rabbitmq' in func_sig.parameters:
if 'rabbitmq' in self.lithops_config:
rabbit_amqp_url = self.lithops_config['rabbitmq'].get(
'amqp_url')
params = pika.URLParameters(rabbit_amqp_url)
connection = pika.BlockingConnection(params)
data['rabbitmq'] = connection
else:
raise Exception(
'Cannot create the rabbitmq client: missing configuration')
if 'id' in func_sig.parameters:
data['id'] = int(self.call_id)
def run_tests(test_to_run, config=None, mode=None, backend=None, storage=None):
global CONFIG, STORAGE_CONFIG, STORAGE
mode = mode or get_mode(backend, config)
config_ow = {'lithops': {'mode': mode}}
if storage:
config_ow['lithops']['storage'] = storage
if backend:
config_ow[mode] = {'backend': backend}
CONFIG = default_config(config, config_ow)
STORAGE_CONFIG = extract_storage_config(CONFIG)
STORAGE = Storage(storage_config=STORAGE_CONFIG)
suite = unittest.TestSuite()
if test_to_run == 'all':
suite.addTest(unittest.makeSuite(TestLithops))
else:
try:
suite.addTest(TestLithops(test_to_run))
except ValueError:
print("unknown test, use: --help")
sys.exit()
runner = unittest.TextTestRunner()
runner.run(suite)
def run_tests(tests, config=None, group=None, backend=None, storage=None, fail_fast=False,
keep_datasets=False):
global CONFIG, STORAGE_CONFIG, STORAGE
config_ow = {'lithops': {}}
if storage:
config_ow['lithops']['storage'] = storage
if backend:
config_ow['lithops']['backend'] = backend
CONFIG = default_config(config, config_ow)
STORAGE_CONFIG = extract_storage_config(CONFIG)
STORAGE = Storage(storage_config=STORAGE_CONFIG)
init_test_variables()
suite = unittest.TestSuite()
config_suite(suite, tests, group)
words_in_data_set = upload_data_sets() # uploads datasets and returns word count
main_util.init_config(CONFIG, STORAGE, STORAGE_CONFIG, words_in_data_set, TEST_FILES_URLS)
runner = unittest.TextTestRunner(verbosity=2, failfast=fail_fast)
tests_results = runner.run(suite)
# removes previously uploaded datasets from storage.
if not keep_datasets:
clean_tests(STORAGE, STORAGE_CONFIG, PREFIX)
if not tests_results.wasSuccessful(): # Fails github workflow action to reject merge to repository
sys.tracebacklimit = 0 # avoid displaying redundant stack track-back info
raise Exception("--------Test procedure failed. Merge rejected--------")
def _load_object(self, data):
"""
Loads the object in /tmp in case of object processing
"""
extra_get_args = {}
if 'url' in data:
url = data['url']
logger.info('Getting dataset from {}'.format(url.path))
if url.data_byte_range is not None:
range_str = 'bytes={}-{}'.format(*url.data_byte_range)
extra_get_args['Range'] = range_str
logger.info('Chunk: {} - Range: {}'.format(
url.part, extra_get_args['Range']))
resp = requests.get(url.path, headers=extra_get_args, stream=True)
url.data_stream = resp.raw
if 'obj' in data:
obj = data['obj']
logger.info('Getting dataset from {}://{}/{}'.format(
obj.backend, obj.bucket, obj.key))
if obj.backend == self.internal_storage.backend:
storage = self.internal_storage.storage
else:
storage = Storage(lithops_config=self.lithops_config,
storage_backend=obj.backend)
if obj.data_byte_range is not None:
extra_get_args['Range'] = 'bytes={}-{}'.format(
*obj.data_byte_range)
logger.info('Chunk: {} - Range: {}'.format(
obj.part, extra_get_args['Range']))
sb = storage.get_object(obj.bucket,
obj.key,
stream=True,
extra_get_args=extra_get_args)
wsb = WrappedStreamingBodyPartition(sb, obj.chunk_size,
obj.data_byte_range)
obj.data_stream = wsb
else:
sb = storage.get_object(obj.bucket,
obj.key,
stream=True,
extra_get_args=extra_get_args)
obj.data_stream = sb
def clean_cloudobjects(cloudobjects_data):
file_location = cloudobjects_data['file_location']
data = cloudobjects_data['data']
logger.info('Going to clean cloudobjects')
cos_to_clean = data['cos_to_clean']
storage_config = data['storage_config']
storage = Storage(storage_config=storage_config)
for co in cos_to_clean:
if co.backend == storage.backend:
logging.info('Cleaning {}://{}/{}'.format(co.backend, co.bucket,
co.key))
storage.delete_object(co.bucket, co.key)
if os.path.exists(file_location):
os.remove(file_location)
logger.info('Finished')
def __init__(self, ds_config, db_config, use_db_cache=True, use_ds_cache=True, hybrid_impl='auto'):
self.config = default_config()
self.ds_config = ds_config
self.db_config = db_config
self.use_db_cache = use_db_cache
self.use_ds_cache = use_ds_cache
if hybrid_impl == 'auto':
self.hybrid_impl = (
self.config['lithops']['mode'] == 'localhost'
or self.config['lithops']['mode'] == 'serverless' and 'ibm_vpc' in self.config
)
if self.hybrid_impl:
logger.info(f'Using the Hybrid implementation')
else:
logger.info(f'Using the pure Serverless implementation')
else:
self.hybrid_impl = hybrid_impl
lithops_bucket = self.config['lithops']['storage_bucket']
self.ds_bucket = self.config.get('storage', {}).get('ds_bucket', lithops_bucket)
self.lithops_executor = lithops.FunctionExecutor(config=self.config, runtime_memory=2048)
if self.hybrid_impl:
if self.config['lithops']['mode'] == 'localhost':
self.lithops_vm_executor = self.lithops_executor
else:
self.lithops_vm_executor = lithops.StandaloneExecutor(config=self.config)
self.storage = Storage(config=self.config)
cache_namespace = 'vm' if hybrid_impl else 'function'
self.cacher = PipelineCacher(
self.storage, lithops_bucket, cache_namespace, self.ds_config["name"], self.db_config["name"]
)
if not self.use_db_cache or not self.use_ds_cache:
self.cacher.clean(database=not self.use_db_cache, dataset=not self.use_ds_cache)
stats_path_cache_key = ':ds/:db/stats_path.cache'
if self.cacher.exists(stats_path_cache_key):
self.stats_path = self.cacher.load(stats_path_cache_key)
PipelineStats.path = self.stats_path
logger.info(f'Using cached {self.stats_path} for statistics')
else:
PipelineStats.init()
self.stats_path = PipelineStats.path
self.cacher.save(self.stats_path, stats_path_cache_key)
logger.info(f'Initialised {self.stats_path} for statistics')
self.ds_segm_size_mb = 128
self.image_gen_config = {
"q": 99,
"do_preprocessing": False,
"nlevels": 30,
"ppm": 3.0
}
def __init__(
self,
imzml_file: str,
ibd_file: str,
moldb_files: Union[List[int], List[str]],
ds_config: DSConfig,
sm_config: Optional[Dict] = None,
use_cache=True,
out_dir: Optional[str] = None,
executor: Optional[Executor] = None,
):
sm_config = sm_config or SMConfig.get_conf()
self.storage = Storage(config=sm_config['lithops'])
sm_storage = sm_config['lithops']['sm_storage']
self.imzml_cobj = _upload_if_needed(imzml_file,
self.storage,
sm_storage,
'imzml',
use_db_mutex=False)
self.ibd_cobj = _upload_if_needed(ibd_file,
self.storage,
sm_storage,
'imzml',
use_db_mutex=False)
if isinstance(moldb_files[0], int):
self.moldb_defs = _upload_moldbs_from_db(moldb_files, self.storage,
sm_storage)
else:
self.moldb_defs = _upload_moldbs_from_files(
moldb_files, self.storage, sm_storage)
self.ds_config = ds_config
self.out_dir = Path(out_dir) if out_dir else Path('./result_pngs')
if use_cache:
cache_key: Optional[str] = jsonhash({
'imzml': imzml_file,
'ibd': ibd_file,
'dbs': moldb_files,
'ds': ds_config
})
else:
cache_key = None
self.pipe = Pipeline(
self.imzml_cobj,
self.ibd_cobj,
self.moldb_defs,
self.ds_config,
executor=executor,
cache_key=cache_key,
use_db_cache=use_cache,
use_db_mutex=False,
lithops_config=sm_config['lithops'],
)
def batch_copy(src_cobjs: List[CloudObject], dest_prefix: str, *,
storage: Storage):
# If Lithops' storage supported Copy Object operations, this could be easily optimized.
# Not sure if it's worth the effort yet
result_cobjs = []
for i, data in enumerate(
iter_cobjects_with_prefetch(storage, src_cobjs)):
dest_key = f'{dest_prefix}/{i:06}'
result_cobjs.append(
storage.put_cloudobject(data, dest_bucket, dest_key))
return result_cobjs
def find_shared_objects(calls):
# find and annotate repeated arguments
record = {}
for i, call in enumerate(calls):
for j, arg in enumerate(call[1]):
if id(arg) in record:
record[id(arg)].append((i, j))
else:
record[id(arg)] = [arg, (i, j)]
for k, v in call[2].items():
if id(v) in record:
record[id(v)].append((i, k))
else:
record[id(v)] = [v, (i, k)]
# If we found multiple occurrences of one object, then
# store it in shared memory, pass a proxy as a value
calls = [list(item) for item in calls]
storage = Storage()
thread_pool = ThreadPoolExecutor(max_workers=len(record))
def put_arg_obj(positions):
obj = positions.pop(0)
if len(positions) > 1 and consider_sharing(obj):
logger.debug('Proxying {}'.format(type(obj)))
obj_bin = pickle.dumps(obj)
cloud_object = storage.put_cloudobject(obj_bin)
for pos in positions:
call_n, idx_or_key = pos
call = calls[call_n]
if isinstance(idx_or_key, str):
call[2][idx_or_key] = cloud_object
else:
args_as_list = list(call[1])
args_as_list[idx_or_key] = cloud_object
call[1] = tuple(args_as_list)
try:
call[3].append(idx_or_key)
except IndexError:
call.append([idx_or_key])
fut = []
for positions in record.values():
f = thread_pool.submit(put_arg_obj, positions)
fut.append(f)
[f.result() for f in fut]
return [tuple(item) for item in calls]
def get_arg_obj(idx_or_key):
if isinstance(idx_or_key, str):
obj_id = kwargs[idx_or_key]
else:
obj_id = args_as_list[idx_or_key]
if obj_id in cache:
logger.debug('Get {} (arg {}) from cache'.format(
obj_id, idx_or_key))
obj = cache[obj_id]
else:
logger.debug('Get {} (arg {}) from storage'.format(
obj_id, idx_or_key))
storage = Storage()
obj_bin = storage.get_cloudobject(obj_id)
obj = pickle.loads(obj_bin)
cache[obj_id] = obj
if isinstance(idx_or_key, str):
kwargs[idx_or_key] = obj
else:
args_as_list[idx_or_key] = obj
def __init__(
self,
executor: Executor,
ds: Dataset,
perf: Profiler,
sm_config: Optional[Dict] = None,
use_cache=False,
store_images=True,
):
"""
Args
========
use_cache: For development - cache the results after each pipeline step so that it's easier
to quickly re-run specific steps.
"""
sm_config = sm_config or SMConfig.get_conf()
self.sm_storage = sm_config['lithops']['sm_storage']
self.storage = Storage(sm_config['lithops'])
self.s3_client = get_s3_client()
self.ds = ds
self.perf = perf
self.store_images = store_images
self.db = DB()
self.es = ESExporter(self.db, sm_config)
self.imzml_cobj, self.ibd_cobj = _upload_imzmls_from_prefix_if_needed(
self.ds.input_path, self.storage, self.sm_storage, self.s3_client)
self.moldb_defs = _upload_moldbs_from_db(
self.ds.config['database_ids'], self.storage, self.sm_storage)
if use_cache:
cache_key: Optional[str] = jsonhash({
'input_path': ds.input_path,
'ds': ds.config
})
else:
cache_key = None
self.pipe = Pipeline(
self.imzml_cobj,
self.ibd_cobj,
self.moldb_defs,
self.ds.config,
cache_key=cache_key,
executor=executor,
)
self.results_dfs = None
self.png_cobjs = None
self.db_formula_image_ids = None
def _fill_optional_args(self, function, data):
"""
Fills in those reserved, optional parameters that might be write to the function signature
"""
func_sig = inspect.signature(function)
if len(data) == 1 and 'future' in data:
# Function chaining feature
out = [
data.pop('future').result(
internal_storage=self.internal_storage)
]
data.update(verify_args(function, out, None)[0])
if 'ibm_cos' in func_sig.parameters:
if 'ibm_cos' in self.lithops_config:
if self.internal_storage.backend == 'ibm_cos':
ibm_boto3_client = self.internal_storage.get_client()
else:
ibm_boto3_client = Storage(config=self.lithops_config,
backend='ibm_cos').get_client()
data['ibm_cos'] = ibm_boto3_client
else:
raise Exception(
'Cannot create the ibm_cos client: missing configuration')
if 'storage' in func_sig.parameters:
data['storage'] = self.internal_storage.storage
if 'rabbitmq' in func_sig.parameters:
if 'rabbitmq' in self.lithops_config:
rabbit_amqp_url = self.lithops_config['rabbitmq'].get(
'amqp_url')
params = pika.URLParameters(rabbit_amqp_url)
connection = pika.BlockingConnection(params)
data['rabbitmq'] = connection
else:
raise Exception(
'Cannot create the rabbitmq client: missing configuration')
if 'id' in func_sig.parameters:
data['id'] = int(self.job.call_id)
def clean_executor_jobs(executor_id, executor_data):
storage = None
prefix = '/'.join([JOBS_PREFIX, executor_id])
for file_data in executor_data:
file_location = file_data['file_location']
data = file_data['data']
storage_config = data['storage_config']
clean_cloudobjects = data['clean_cloudobjects']
if not storage:
storage = Storage(storage_config=storage_config)
logger.info(
f'Cleaning jobs {", ".join([job_key for job_key in data["jobs_to_clean"]])}'
)
objects = storage.list_keys(storage.bucket, prefix)
objects_to_delete = [
key for key in objects if '-'.join(
key.split('/')[1].split('-')[0:3]) in data['jobs_to_clean']
]
while objects_to_delete:
storage.delete_objects(storage.bucket, objects_to_delete)
time.sleep(5)
objects = storage.list_keys(storage.bucket, prefix)
objects_to_delete = [
key for key in objects if '-'.join(
key.split('/')[1].split('-')[0:3]) in data['jobs_to_clean']
]
if clean_cloudobjects:
for job_key in data['jobs_to_clean']:
prefix = '/'.join([TEMP_PREFIX, job_key])
clean_bucket(storage, storage.bucket, prefix)
if os.path.exists(file_location):
os.remove(file_location)
logger.info('Finished')
def clean_file(file_name):
file_location = os.path.join(CLEANER_DIR, file_name)
if file_location in [CLEANER_LOG_FILE, CLEANER_PID_FILE]:
return
with open(file_location, 'rb') as pk:
data = pickle.load(pk)
if 'jobs_to_clean' in data:
jobs_to_clean = data['jobs_to_clean']
storage_config = data['storage_config']
clean_cloudobjects = data['clean_cloudobjects']
storage = Storage(storage_config=storage_config)
for job_key in jobs_to_clean:
logger.info('Going to clean: {}'.format(job_key))
prefix = '/'.join([JOBS_PREFIX, job_key])
clean_bucket(storage, storage.bucket, prefix)
if clean_cloudobjects:
prefix = '/'.join([TEMP_PREFIX, job_key])
clean_bucket(storage, storage.bucket, prefix)
if 'cos_to_clean' in data:
logger.info('Going to clean cloudobjects')
cos_to_clean = data['cos_to_clean']
storage_config = data['storage_config']
storage = Storage(storage_config=storage_config)
for co in cos_to_clean:
if co.backend == storage.backend:
logging.info('Cleaning {}://{}/{}'.format(
co.backend, co.bucket, co.key))
storage.delete_object(co.bucket, co.key)
if os.path.exists(file_location):
os.remove(file_location)
def load_cobj(storage: Storage, cobj):
try:
return deserialize(storage.get_cloudobject(cobj))
except Exception:
logger.error(f'Failed to deserialize {cobj}')
raise
def _split_objects_from_object_storage(map_func_args_list, chunk_size,
chunk_number, internal_storage, config):
"""
Create partitions from a list of buckets or object keys
"""
if chunk_number:
logger.debug('Chunk size set to {}'.format(chunk_size))
elif chunk_size:
logger.debug('Chunk number set to {}'.format(chunk_number))
else:
logger.debug('Chunk size and chunk number not set ')
sbs = set()
buckets = set()
prefixes = set()
obj_names = set()
for elem in map_func_args_list:
if type(elem['obj']) == CloudObject:
elem['obj'] = '{}://{}/{}'.format(elem['obj'].backend,
elem['obj'].bucket,
elem['obj'].key)
sb, bucket, prefix, obj_name = utils.split_object_url(elem['obj'])
if sb is None:
sb = internal_storage.backend
elem['obj'] = '{}://{}'.format(sb, elem['obj'])
if obj_name:
obj_names.add((bucket, prefix))
elif prefix:
prefixes.add((bucket, prefix))
else:
buckets.add(bucket)
sbs.add(sb)
if len(sbs) > 1:
raise Exception(
'Process objects from multiple storage backends is not supported. '
'Current storage backends: {}'.format(sbs))
sb = sbs.pop()
if sb == internal_storage.backend:
storage = internal_storage.storage
else:
storage = Storage(config=config, backend=sb)
objects = {}
if obj_names:
for bucket, prefix in obj_names:
logger.debug("Listing objects in '{}://{}'".format(
sb, '/'.join([bucket, prefix])))
if bucket not in objects:
objects[bucket] = []
prefix = prefix + '/' if prefix else prefix
objects[bucket].extend(storage.list_objects(bucket, prefix))
logger.debug("Total objects found: {}".format(len(objects[bucket])))
elif prefixes:
for bucket, prefix in prefixes:
logger.debug("Listing objects in '{}://{}'".format(
sb, '/'.join([bucket, prefix])))
if bucket not in objects:
objects[bucket] = []
prefix = prefix + '/' if prefix else prefix
objects[bucket].extend(storage.list_objects(bucket, prefix))
logger.debug("Total objects found: {}".format(len(objects[bucket])))
elif buckets:
for bucket in buckets:
logger.debug("Listing objects in '{}://{}'".format(sb, bucket))
objects[bucket] = storage.list_objects(bucket)
logger.debug("Total objects found: {}".format(len(objects[bucket])))
if all([len(objects[bucket]) == 0 for bucket in objects]):
raise Exception(
f'No objects found in bucket: {", ".join(objects.keys())}')
keys_dict = {}
for bucket in objects:
keys_dict[bucket] = {}
for obj in objects[bucket]:
keys_dict[bucket][obj['Key']] = obj['Size']
partitions = []
parts_per_object = []
def create_partition(bucket, key, entry):
if key.endswith('/'):
logger.debug(
f'Discarding object "{key}" as it is a prefix folder (0.0B)')
return
obj_size = keys_dict[bucket][key]
if chunk_number:
chunk_rest = obj_size % chunk_number
obj_chunk_size = (obj_size // chunk_number) + \
round((chunk_rest / chunk_number) + 0.5)
elif chunk_size:
obj_chunk_size = chunk_size
else:
obj_chunk_size = obj_size
size = total_partitions = 0
ci = obj_size
cz = obj_chunk_size
parts = ci // cz + (ci % cz > 0)
logger.debug('Creating {} partitions from object {} ({})'.format(
parts, key, sizeof_fmt(obj_size)))
while size < obj_size:
brange = (size, size + obj_chunk_size + CHUNK_THRESHOLD)
brange = None if obj_size == obj_chunk_size else brange
partition = entry.copy()
partition['obj'] = CloudObject(sb, bucket, key)
partition['obj'].data_byte_range = brange
partition['obj'].chunk_size = obj_chunk_size
partition['obj'].part = total_partitions
partitions.append(partition)
total_partitions += 1
size += obj_chunk_size
parts_per_object.append(total_partitions)
for entry in map_func_args_list:
sb, bucket, prefix, obj_name = utils.split_object_url(entry['obj'])
if obj_name:
# each entry is an object key
key = '/'.join([prefix, obj_name]) if prefix else obj_name
create_partition(bucket, key, entry)
else:
# each entry is a bucket
for key in keys_dict[bucket]:
create_partition(bucket, key, entry)
return partitions, parts_per_object
def _load_object(self, data):
"""
Loads the object in /tmp in case of object processing
"""
extra_get_args = {}
obj = data['obj']
if hasattr(obj, 'bucket') and not hasattr(obj, 'path'):
logger.info('Getting dataset from {}://{}/{}'.format(
obj.backend, obj.bucket, obj.key))
if obj.backend == self.internal_storage.backend:
storage = self.internal_storage.storage
else:
storage = Storage(config=self.lithops_config,
backend=obj.backend)
if obj.data_byte_range is not None:
extra_get_args['Range'] = 'bytes={}-{}'.format(
*obj.data_byte_range)
logger.info('Chunk: {} - Range: {}'.format(
obj.part, extra_get_args['Range']))
sb = storage.get_object(obj.bucket,
obj.key,
stream=True,
extra_get_args=extra_get_args)
wsb = WrappedStreamingBodyPartition(sb, obj.chunk_size,
obj.data_byte_range)
obj.data_stream = wsb
else:
sb = storage.get_object(obj.bucket,
obj.key,
stream=True,
extra_get_args=extra_get_args)
obj.data_stream = sb
elif hasattr(obj, 'url'):
logger.info('Getting dataset from {}'.format(obj.url))
if obj.data_byte_range is not None:
range_str = 'bytes={}-{}'.format(*obj.data_byte_range)
extra_get_args['Range'] = range_str
logger.info('Chunk: {} - Range: {}'.format(
obj.part, extra_get_args['Range']))
resp = requests.get(obj.url, headers=extra_get_args, stream=True)
obj.data_stream = resp.raw
elif hasattr(obj, 'path'):
logger.info('Getting dataset from {}'.format(obj.path))
with open(obj.path, "rb") as f:
if obj.data_byte_range is not None:
extra_get_args['Range'] = 'bytes={}-{}'.format(
*obj.data_byte_range)
logger.info('Chunk: {} - Range: {}'.format(
obj.part, extra_get_args['Range']))
first_byte, last_byte = obj.data_byte_range
f.seek(first_byte)
buffer = io.BytesIO(f.read(last_byte - first_byte + 1))
sb = WrappedStreamingBodyPartition(buffer, obj.chunk_size,
obj.data_byte_range)
else:
sb = io.BytesIO(f.read())
obj.data_stream = sb
def create_partitions(config, internal_storage, map_iterdata, chunk_size, chunk_number):
"""
Method that returns the function that will create the partitions of the objects in the Cloud
"""
logger.debug('Starting partitioner')
parts_per_object = None
sbs = set()
buckets = set()
prefixes = set()
obj_names = set()
urls = set()
logger.debug("Parsing input data")
for elem in map_iterdata:
if 'url' in elem:
urls.add(elem['url'])
elif 'obj' in elem:
if type(elem['obj']) == CloudObject:
elem['obj'] = '{}://{}/{}'.format(elem['obj'].backend,
elem['obj'].bucket,
elem['obj'].key)
sb, bucket, prefix, obj_name = utils.split_object_url(elem['obj'])
if sb is None:
sb = internal_storage.backend
elem['obj'] = '{}://{}'.format(sb, elem['obj'])
if obj_name:
obj_names.add((bucket, prefix))
elif prefix:
prefixes.add((bucket, prefix))
else:
buckets.add(bucket)
sbs.add(sb)
if len(sbs) > 1:
raise Exception('Currently we only support to process one storage backend at a time. '
'Current storage backends: {}'.format(sbs))
if [prefixes, obj_names, urls, buckets].count(True) > 1:
raise Exception('You must provide as an input data a list of bucktes, '
'a list of buckets with object prefix, a list of keys '
'or a list of urls. Intermingled types are not allowed.')
if not urls:
# process objects from an object store. No url
sb = sbs.pop()
if sb == internal_storage.backend:
storage = internal_storage.storage
else:
storage = Storage(config=config, backend=sb)
objects = {}
if obj_names:
for bucket, prefix in obj_names:
logger.debug("Listing objects in '{}://{}/'"
.format(sb, '/'.join([bucket, prefix])))
if bucket not in objects:
objects[bucket] = []
prefix = prefix + '/' if prefix else prefix
objects[bucket].extend(storage.list_objects(bucket, prefix))
elif prefixes:
for bucket, prefix in prefixes:
logger.debug("Listing objects in '{}://{}/'"
.format(sb, '/'.join([bucket, prefix])))
if bucket not in objects:
objects[bucket] = []
prefix = prefix + '/' if prefix else prefix
objects[bucket].extend(storage.list_objects(bucket, prefix))
elif buckets:
for bucket in buckets:
logger.debug("Listing objects in '{}://{}'".format(sb, bucket))
objects[bucket] = storage.list_objects(bucket)
keys_dict = {}
for bucket in objects:
keys_dict[bucket] = {}
for obj in objects[bucket]:
keys_dict[bucket][obj['Key']] = obj['Size']
if buckets or prefixes:
partitions, parts_per_object = _split_objects_from_buckets(map_iterdata, keys_dict, chunk_size, chunk_number)
elif obj_names:
partitions, parts_per_object = _split_objects_from_keys(map_iterdata, keys_dict, chunk_size, chunk_number)
elif urls:
partitions, parts_per_object = _split_objects_from_urls(map_iterdata, chunk_size, chunk_number)
else:
raise ValueError('You did not provide any bucket or object key/url')
return partitions, parts_per_object
def save_cobj(storage: Storage, obj: TItem, bucket: str = None, key: str = None) -> CObj[TItem]:
return storage.put_cloudobject(serialize(obj), bucket, key)
def delete_objects_by_prefix(storage: Storage, bucket: str, prefix: str):
keys = storage.list_keys(bucket, prefix)
storage.delete_objects(bucket, keys)
logger.info(f'Removed {len(keys)} objects from {storage.backend}://{bucket}/{prefix}')
