def store_path(self, artifact, path, name=None, checksum=True, max_objects=None):
self.init_gcs()
bucket, key = self._parse_uri(path)
max_objects = max_objects or DEFAULT_MAX_OBJECTS
if checksum == False:
return [ArtifactManifestEntry(name or key, path, digest=path)]
start_time = None
obj = self._client.bucket(bucket).get_blob(key)
multi = obj is None
if multi:
start_time = time.time()
termlog(
'Generating checksum for up to %i objects with prefix "%s"... '
% (max_objects, key),
newline=False,
)
objects = self._client.bucket(bucket).list_blobs(
prefix=key, max_results=max_objects
)
else:
objects = [obj]
entries = [
self._entry_from_obj(obj, path, name, prefix=key, multi=multi)
for obj in objects
]
if start_time is not None:
termlog("Done. %.1fs" % (time.time() - start_time), prefix=False)
if len(entries) >= max_objects:
raise ValueError(
"Exceeded %i objects tracked, pass max_objects to add_reference"
% max_objects
)
return entries
def add_dir(self, local_path: str, name: Optional[str] = None):
self._ensure_can_add()
if not os.path.isdir(local_path):
raise ValueError("Path is not a directory: %s" % local_path)
termlog(
"Adding directory to artifact (%s)... " %
os.path.join(".", os.path.normpath(local_path)),
newline=False,
)
start_time = time.time()
paths = []
for dirpath, _, filenames in os.walk(local_path, followlinks=True):
for fname in filenames:
physical_path = os.path.join(dirpath, fname)
logical_path = os.path.relpath(physical_path, start=local_path)
if name is not None:
logical_path = os.path.join(name, logical_path)
paths.append((logical_path, physical_path))
def add_manifest_file(log_phy_path):
logical_path, physical_path = log_phy_path
self._add_local_file(logical_path, physical_path)
import multiprocessing.dummy # this uses threads
NUM_THREADS = 8
pool = multiprocessing.dummy.Pool(NUM_THREADS)
pool.map(add_manifest_file, paths)
pool.close()
pool.join()
termlog("Done. %.1fs" % (time.time() - start_time), prefix=False)
def store_path(self,
artifact,
path,
name=None,
checksum=True,
max_objects=None):
url = urlparse(path)
local_path = "%s%s" % (url.netloc, url.path)
max_objects = max_objects or DEFAULT_MAX_OBJECTS
# We have a single file or directory
# Note, we follow symlinks for files contained within the directory
entries = []
if checksum == False:
return [
ArtifactManifestEntry(name or os.path.basename(path),
path,
digest=path)
]
if os.path.isdir(local_path):
i = 0
start_time = time.time()
termlog(
'Generating checksum for up to %i files in "%s"...\n' %
(max_objects, local_path),
newline=False,
)
for root, dirs, files in os.walk(local_path):
for sub_path in files:
i += 1
if i >= max_objects:
raise ValueError(
"Exceeded %i objects tracked, pass max_objects to add_reference"
% max_objects)
physical_path = os.path.join(root, sub_path)
logical_path = os.path.relpath(physical_path,
start=local_path)
entry = ArtifactManifestEntry(
logical_path,
os.path.join(path, logical_path),
size=os.path.getsize(physical_path),
digest=md5_file_b64(physical_path),
)
entries.append(entry)
termlog("Done. %.1fs" % (time.time() - start_time), prefix=False)
elif os.path.isfile(local_path):
name = name or os.path.basename(local_path)
entry = ArtifactManifestEntry(
name,
path,
size=os.path.getsize(local_path),
digest=md5_file_b64(local_path),
)
entries.append(entry)
else:
# TODO: update error message if we don't allow directories.
raise ValueError(
'Path "%s" must be a valid file or directory path' % path)
return entries
def store_path(self, artifact, path, name=None, checksum=True, max_objects=None):
self.init_boto()
bucket, key = self._parse_uri(path)
max_objects = max_objects or DEFAULT_MAX_OBJECTS
if not checksum:
return [ArtifactManifestEntry(name or key, path, digest=path)]
objs = [self._s3.Object(bucket, key)]
start_time = None
multi = False
try:
objs[0].load()
except self._botocore.exceptions.ClientError as e:
if e.response["Error"]["Code"] == "404":
multi = True
start_time = time.time()
termlog(
'Generating checksum for up to %i objects with prefix "%s"... '
% (max_objects, key),
newline=False,
)
objs = (
self._s3.Bucket(bucket)
.objects.filter(Prefix=key)
.limit(max_objects)
)
else:
raise CommError(
"Unable to connect to S3 (%s): %s"
% (e.response["Error"]["Code"], e.response["Error"]["Message"])
)
# Weird iterator scoping makes us assign this to a local function
size = self._size_from_obj
entries = [
self._entry_from_obj(obj, path, name, prefix=key, multi=multi)
for obj in objs
if size(obj) > 0
]
if start_time is not None:
termlog("Done. %.1fs" % (time.time() - start_time), prefix=False)
if len(entries) >= max_objects:
raise ValueError(
"Exceeded %i objects tracked, pass max_objects to add_reference"
% max_objects
)
return entries
