def main(args):
# distributed setup
print("initializing...")
dask_mpi.initialize(nthreads=args.cpus_per_node)
client = Client()
print(client)
# get data
print("connecting to data...")
print(client)
container_name = "malware"
storage_options = {"account_name": "azuremlexamples"}
fs = AzureBlobFileSystem(**storage_options)
files = fs.ls(f"{container_name}/processed")
# read into dataframes
print("creating dataframes...")
print(client)
for f in files:
if "train" in f:
df_train = dd.read_parquet(f"az://{f}", storage_options=storage_options)
elif "test" in f:
df_test = dd.read_parquet(f"az://{f}", storage_options=storage_options)
# data processing
print("processing data...")
print(client)
cols = [col for col in df_train.columns if df_train.dtypes[col] != "object"]
X = df_train[cols].drop("HasDetections", axis=1).values.persist()
y = df_train["HasDetections"].persist()
# train xgboost
print("training xgboost...")
print(client)
params = {
"objective": "binary:logistic",
"learning_rate": args.learning_rate,
"gamma": args.gamma,
"max_depth": args.max_depth,
}
mlflow.log_params(params) # log to the run
dtrain = xgb.dask.DaskDMatrix(client, X, y)
model = xgb.dask.train(client, params, dtrain, num_boost_round=args.num_boost_round)
print(model)
# predict on test data
print("making predictions...")
print(client)
X_test = df_test[
[col for col in cols if "HasDetections" not in col]
].values.persist()
y_pred = xgb.dask.predict(client, model, X_test)
y_pred.to_dask_dataframe().to_csv("./outputs/predictions.csv")
# save model
print("saving model...")
print(client)
mlflow.xgboost.log_model(model["booster"], "./outputs/model")
def test_open_file(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
f = fs.open("/data/root/a/file.txt")
result = f.read()
assert result == b"0123456789"
def test_fetch_second_half(storage):
# Verify if length extends beyond the end of file, truncate the read
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR,
)
blob = fs.open("data/top_file.txt")
assert len(blob._fetch_range(start=5, end=10)) == 5
def test_isdir(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
BUCKET = "/name/of/the/bucket"
BASE_PATH = BUCKET + "/" + "012345"
# EMPTY_DIR = BASE_PATH + "/empty_dir"
fs.makedirs(BASE_PATH)
assert fs.isdir(BASE_PATH) is True
def test_open_context_manager(storage, mocker):
"test closing azure client with context manager"
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
with fs.open("/data/root/a/file.txt") as f:
close = mocker.patch.object(f.container_client, "close")
result = f.read()
assert result == b"0123456789"
close.assert_called_once()
def test_open_file(storage, mocker):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
f = fs.open("/data/root/a/file.txt")
result = f.read()
assert result == b"0123456789"
close = mocker.patch.object(f.container_client, "close")
f.close()
close.assert_called_once()
def test_exists(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
assert fs.exists("data/top_file.txt")
assert fs.exists("data")
assert fs.exists("data/")
assert not fs.exists("non-existent-container")
assert not fs.exists("non-existent-container/")
assert fs.exists("")
assert not fs.exists("data/not-a-key")
def test_cat(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("catdir")
data = b"0123456789"
with fs.open("catdir/catfile.txt", "wb") as f:
f.write(data)
assert fs.cat("catdir/catfile.txt") == data
fs.rm("catdir/catfile.txt")
def fs(self):
from adlfs import AzureBlobFileSystem
from azure.core.exceptions import AzureError
try:
file_system = AzureBlobFileSystem(**self.login_info)
if self.bucket not in [
container.rstrip("/") for container in file_system.ls("/")
]:
file_system.mkdir(self.bucket)
except (ValueError, AzureError) as e:
raise AzureAuthError(
f"Authentication to Azure Blob Storage via {self.login_method}"
" failed.\nLearn more about configuration settings at"
f" {format_link('https://man.dvc.org/remote/modify')}") from e
return file_system
def setup(self, stage=None):
data_dir = "datasets/mnist"
storage_options = {"account_name": "azuremlexamples"}
fs = AzureBlobFileSystem(**storage_options)
files = fs.ls(data_dir)
train_len = 60000
test_len = 10000
for f in files:
if "train-images" in f:
self.X_train = self._read_images(gzip.open(fs.open(f)), train_len)
elif "train-labels" in f:
self.y_train = self._read_labels(gzip.open(fs.open(f)), train_len)
elif "images" in f:
self.X_test = self._read_images(gzip.open(fs.open(f)), test_len)
elif "labels" in f:
self.y_test = self._read_labels(gzip.open(fs.open(f)), test_len)
self.ohe = OneHotEncoder().fit(self.y_train.reshape(-1, 1))
self.mnist_train = list(
zip(
self.X_train, self.ohe.transform(self.y_train.reshape(-1, 1)).toarray(),
)
)
self.mnist_test = list(
zip(self.X_test, self.ohe.transform(self.y_test.reshape(-1, 1)).toarray(),)
)
def test_rm_recursive(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
assert "data/root/c/" in fs.ls("/data/root")
assert fs.ls("data/root/c") == [
"data/root/c/file1.txt",
"data/root/c/file2.txt",
]
fs.rm("data/root/c", recursive=True)
assert "data/root/c/" not in fs.ls("/data/root")
with pytest.raises(FileNotFoundError):
fs.ls("data/root/c")
def test_append_operation(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("append-container")
# Check that appending to an existing file works as expected
with fs.open("append-container/append_file.txt", "ab") as f:
f.write(b"0123456789")
with fs.open("append-container/append_file.txt", "ab") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file2.txt", "rb") as f:
outfile = f.read()
assert outfile == b"01234567890123456789"
fs.rm("append-container", recursive=True)
def __init__(
self,
path: str = None,
gen: int = 2,
credentials: Dict[str, Any] = None,
*args,
**kwargs,
):
credentials = credentials or local_config.get("AZURE_ADLS")
super().__init__(*args, credentials=credentials, **kwargs)
storage_account_name = self.credentials["ACCOUNT_NAME"]
tenant_id = self.credentials["AZURE_TENANT_ID"]
client_id = self.credentials["AZURE_CLIENT_ID"]
client_secret = self.credentials["AZURE_CLIENT_SECRET"]
self.path = path
self.gen = gen
self.storage_options = {
"tenant_id": tenant_id,
"client_id": client_id,
"client_secret": client_secret,
}
if gen == 1:
self.fs = AzureDatalakeFileSystem(
store_name=storage_account_name,
tenant_id=tenant_id,
client_id=client_id,
client_secret=client_secret,
)
self.base_url = f"adl://{storage_account_name}"
elif gen == 2:
self.storage_options["account_name"] = storage_account_name
self.fs = AzureBlobFileSystem(
account_name=storage_account_name,
tenant_id=tenant_id,
client_id=client_id,
client_secret=client_secret,
)
self.base_url = f"az://"
def fs(self):
from adlfs import AzureBlobFileSystem
from azure.core.exceptions import AzureError
try:
return AzureBlobFileSystem(**self.fs_args)
except (ValueError, AzureError) as e:
raise AzureAuthError(
f"Authentication to Azure Blob Storage via {self.login_method}"
" failed.\nLearn more about configuration settings at"
f" {format_link('https://man.dvc.org/remote/modify')}") from e
def test_rm(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.rm("/data/root/a/file.txt")
with pytest.raises(FileNotFoundError):
fs.ls("/data/root/a/file.txt", refresh=True)
def test_url(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR, account_key=KEY
)
fs.mkdir("catdir")
data = b"0123456789"
with fs.open("catdir/catfile.txt", "wb") as f:
f.write(data)
import requests
r = requests.get(fs.url("catdir/catfile.txt"))
assert r.status_code == 200
assert r.content == data
fs.rm("catdir/catfile.txt")
def test_dask_parquet(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("test")
STORAGE_OPTIONS = {
"account_name": "devstoreaccount1",
"connection_string": CONN_STR,
}
df = pd.DataFrame({
"col1": [1, 2, 3, 4],
"col2": [2, 4, 6, 8],
"index_key": [1, 1, 2, 2],
"partition_key": [1, 1, 2, 2],
})
dask_dataframe = dd.from_pandas(df, npartitions=1)
for protocol in ["abfs", "az"]:
dask_dataframe.to_parquet(
"{}://[email protected]/test_group.parquet".format(
protocol),
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
fs = AzureBlobFileSystem(**STORAGE_OPTIONS)
assert fs.ls("test/test_group.parquet") == [
"test/test_group.parquet/_common_metadata",
"test/test_group.parquet/_metadata",
"test/test_group.parquet/part.0.parquet",
]
fs.rm("test/test_group.parquet")
df_test = dd.read_parquet(
"abfs://test/test_group.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df, df_test)
def configure_targets(bakery: Bakery, recipe_bakery: RecipeBakery,
recipe_name: str, secrets: Dict, extension: str):
target = bakery.targets[recipe_bakery.target]
repository = os.environ["GITHUB_REPOSITORY"]
if target.private.protocol == S3_PROTOCOL:
if target.private.storage_options:
key = secrets[target.private.storage_options.key]
secret = secrets[target.private.storage_options.secret]
fs = S3FileSystem(
anon=False,
default_cache_type="none",
default_fill_cache=False,
key=key,
secret=secret,
)
target_path = f"s3://{recipe_bakery.target}/{repository}/{recipe_name}.{extension}"
target = FSSpecTarget(fs, target_path)
cache_path = f"s3://{recipe_bakery.target}/{repository}/{recipe_name}/cache"
cache_target = CacheFSSpecTarget(fs, cache_path)
metadata_path = f"s3://{recipe_bakery.target}/{repository}/{recipe_name}/cache/metadata"
metadata_target = MetadataTarget(fs, metadata_path)
return Targets(target=target,
cache=cache_target,
metadata=metadata_target)
elif target.private.protocol == ABFS_PROTOCOL:
if target.private.storage_options:
secret = secrets[target.private.storage_options.secret]
fs = AzureBlobFileSystem(connection_string=secret)
target_path = f"abfs://{recipe_bakery.target}/{repository}/{recipe_name}.{extension}"
target = FSSpecTarget(fs, target_path)
cache_path = f"abfs://{recipe_bakery.target}/{repository}/{recipe_name}/cache"
cache_target = CacheFSSpecTarget(fs, cache_path)
metadata_path = (
f"abfs://{recipe_bakery.target}/{repository}/{recipe_name}"
"/cache/metadata")
metadata_target = MetadataTarget(fs, metadata_path)
return Targets(target=target,
cache=cache_target,
metadata=metadata_target)
else:
raise UnsupportedTarget
def test_info(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
container_info = fs.info("data")
assert container_info == {"name": "data/", "type": "directory", "size": 0}
container2_info = fs.info("data/root")
assert container2_info == {
"name": "data/root/",
"type": "directory",
"size": 0
}
dir_info = fs.info("data/root/c")
assert dir_info == {"name": "data/root/c/", "type": "directory", "size": 0}
file_info = fs.info("data/root/a/file.txt")
assert file_info == {
"name": "data/root/a/file.txt",
"type": "file",
"size": 10
}
def test_deep_paths(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("test_deep")
assert "test_deep/" in fs.ls("")
with fs.open("test_deep/a/b/c/file.txt", "wb") as f:
f.write(b"0123456789")
assert fs.ls("test_deep") == ["test_deep/a/"]
assert fs.ls("test_deep/") == ["test_deep/a/"]
assert fs.ls("test_deep/a") == ["test_deep/a/b/"]
assert fs.ls("test_deep/a/") == ["test_deep/a/b/"]
assert fs.find("test_deep") == ["test_deep/a/b/c/file.txt"]
assert fs.find("test_deep/") == ["test_deep/a/b/c/file.txt"]
assert fs.find("test_deep/a") == ["test_deep/a/b/c/file.txt"]
assert fs.find("test_deep/a/") == ["test_deep/a/b/c/file.txt"]
fs.rm("test_deep", recursive=True)
assert "test_deep/" not in fs.ls("")
assert fs.find("test_deep") == []
def test_fetch_first_half(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR,
)
blob = fs.open("data/top_file.txt")
assert len(blob._fetch_range(start=0, end=5)) == 5
def test_fetch_length_is_none(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR,
)
blob = fs.open("data/top_file.txt")
assert len(blob._fetch_range(start=2, end=None)) == 8
def test_cp_file(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("homedir")
fs.mkdir("homedir/enddir")
fs.touch("homedir/startdir/test_file.txt")
fs.cp_file("homedir/startdir/test_file.txt",
"homedir/enddir/test_file.txt")
files = fs.ls("homedir/enddir")
assert "homedir/enddir/test_file.txt" in files
fs.rm("homedir", recursive=True)
def test_put_file(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
lfs = LocalFileSystem()
fs.mkdir("putdir")
# Check that put on an empty file works
with open("sample.txt", "wb") as f:
f.write(b"")
fs.put("sample.txt", "putdir/sample.txt")
fs.get("putdir/sample.txt", "sample2.txt")
with open("sample.txt", "rb") as f:
f1 = f.read()
with open("sample2.txt", "rb") as f:
f2 = f.read()
assert f1 == f2
lfs.rm("sample.txt")
lfs.rm("sample2.txt")
# Check that put on a file with data works
with open("sample3.txt", "wb") as f:
f.write(b"01234567890")
fs.put("sample3.txt", "putdir/sample3.txt")
fs.get("putdir/sample3.txt", "sample4.txt")
with open("sample3.txt", "rb") as f:
f3 = f.read()
with open("sample4.txt", "rb") as f:
f4 = f.read()
assert f3 == f4
fs.rm("putdir", recursive=True)
def test_dask_parquet(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("test")
STORAGE_OPTIONS = {
"account_name": "devstoreaccount1",
"connection_string": CONN_STR,
}
df = pd.DataFrame({
"col1": [1, 2, 3, 4],
"col2": [2, 4, 6, 8],
"index_key": [1, 1, 2, 2],
"partition_key": [1, 1, 2, 2],
})
dask_dataframe = dd.from_pandas(df, npartitions=1)
for protocol in ["abfs", "az"]:
dask_dataframe.to_parquet(
"{}://test/test_group.parquet".format(protocol),
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
fs = AzureBlobFileSystem(**STORAGE_OPTIONS)
assert fs.ls("test/test_group.parquet") == [
"test/test_group.parquet/_common_metadata",
"test/test_group.parquet/_metadata",
"test/test_group.parquet/part.0.parquet",
]
fs.rm("test/test_group.parquet")
df_test = dd.read_parquet(
"abfs://test/test_group.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df, df_test)
A = np.random.randint(0, 100, size=(10000, 4))
df2 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf2 = dd.from_pandas(df2, npartitions=4)
dd.to_parquet(
ddf2,
"abfs://test/test_group2.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.ls("test/test_group2.parquet") == [
"test/test_group2.parquet/_common_metadata",
"test/test_group2.parquet/_metadata",
"test/test_group2.parquet/part.0.parquet",
"test/test_group2.parquet/part.1.parquet",
"test/test_group2.parquet/part.2.parquet",
"test/test_group2.parquet/part.3.parquet",
]
df2_test = dd.read_parquet(
"abfs://test/test_group2.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df2, df2_test)
a = np.full(shape=(10000, 1), fill_value=1)
b = np.full(shape=(10000, 1), fill_value=2)
c = np.full(shape=(10000, 1), fill_value=3)
d = np.full(shape=(10000, 1), fill_value=4)
B = np.concatenate((a, b, c, d), axis=1)
df3 = pd.DataFrame(data=B, columns=list("ABCD"))
ddf3 = dd.from_pandas(df3, npartitions=4)
dd.to_parquet(
ddf3,
"abfs://test/test_group3.parquet",
partition_on=["A", "B"],
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.glob("test/test_group3.parquet/*") == [
"test/test_group3.parquet/A=1",
"test/test_group3.parquet/_common_metadata",
"test/test_group3.parquet/_metadata",
]
df3_test = dd.read_parquet(
"abfs://test/test_group3.parquet",
filters=[("A", "=", 1)],
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
df3_test = df3_test[["A", "B", "C", "D"]]
df3_test = df3_test[["A", "B", "C", "D"]].astype(int)
assert_frame_equal(df3, df3_test)
A = np.random.randint(0, 100, size=(10000, 4))
df4 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf4 = dd.from_pandas(df4, npartitions=4)
dd.to_parquet(
ddf4,
"abfs://test/test_group4.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
flavor="spark",
write_statistics=False,
)
fs.rmdir("test/test_group4.parquet/_common_metadata", recursive=True)
fs.rmdir("test/test_group4.parquet/_metadata", recursive=True)
fs.rm("test/test_group4.parquet/_common_metadata")
fs.rm("test/test_group4.parquet/_metadata")
assert fs.ls("test/test_group4.parquet") == [
"test/test_group4.parquet/part.0.parquet",
"test/test_group4.parquet/part.1.parquet",
"test/test_group4.parquet/part.2.parquet",
"test/test_group4.parquet/part.3.parquet",
]
df4_test = dd.read_parquet(
"abfs://test/test_group4.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df4, df4_test)
A = np.random.randint(0, 100, size=(10000, 4))
df5 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf5 = dd.from_pandas(df5, npartitions=4)
dd.to_parquet(
ddf5,
"abfs://test/test group5.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.ls("test/test group5.parquet") == [
"test/test group5.parquet/_common_metadata",
"test/test group5.parquet/_metadata",
"test/test group5.parquet/part.0.parquet",
"test/test group5.parquet/part.1.parquet",
"test/test group5.parquet/part.2.parquet",
"test/test group5.parquet/part.3.parquet",
]
df5_test = dd.read_parquet(
"abfs://test/test group5.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df5, df5_test)
def test_large_blob(storage):
import tempfile
import hashlib
import io
import shutil
from pathlib import Path
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
# create a 20MB byte array, ensure it's larger than blocksizes to force a
# chuncked upload
blob_size = 120_000_000
# blob_size = 2_684_354_560
assert blob_size > fs.blocksize
assert blob_size > AzureBlobFile.DEFAULT_BLOCK_SIZE
data = b"1" * blob_size
_hash = hashlib.md5(data)
expected = _hash.hexdigest()
# create container
fs.mkdir("chunk-container")
# upload the data using fs.open
path = "chunk-container/large-blob.bin"
with fs.open(path, "ab") as dst:
dst.write(data)
assert fs.exists(path)
assert fs.size(path) == blob_size
del data
# download with fs.open
bio = io.BytesIO()
with fs.open(path, "rb") as src:
shutil.copyfileobj(src, bio)
# read back the data and calculate md5
bio.seek(0)
data = bio.read()
_hash = hashlib.md5(data)
result = _hash.hexdigest()
assert expected == result
# do the same but using upload/download and a tempdir
path = path = "chunk-container/large_blob2.bin"
with tempfile.TemporaryDirectory() as td:
local_blob: Path = Path(td) / "large_blob2.bin"
with local_blob.open("wb") as fo:
fo.write(data)
assert local_blob.exists()
assert local_blob.stat().st_size == blob_size
fs.upload(str(local_blob), path)
assert fs.exists(path)
assert fs.size(path) == blob_size
# download now
local_blob.unlink()
fs.download(path, str(local_blob))
assert local_blob.exists()
assert local_blob.stat().st_size == blob_size
def test_ls(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
## these are containers
assert fs.ls("") == ["data/"]
assert fs.ls("/") == ["data/"]
assert fs.ls(".") == ["data/"]
## these are top-level directories and files
assert fs.ls("data") == ["data/root/", "data/top_file.txt"]
assert fs.ls("/data") == ["data/root/", "data/top_file.txt"]
# root contains files and directories
assert fs.ls("data/root") == [
"data/root/a/",
"data/root/b/",
"data/root/c/",
"data/root/rfile.txt",
]
assert fs.ls("data/root/") == [
"data/root/a/",
"data/root/b/",
"data/root/c/",
"data/root/rfile.txt",
]
## slashes are not not needed, but accepted
assert fs.ls("data/root/a") == ["data/root/a/file.txt"]
assert fs.ls("data/root/a/") == ["data/root/a/file.txt"]
assert fs.ls("/data/root/a") == ["data/root/a/file.txt"]
assert fs.ls("/data/root/a/") == ["data/root/a/file.txt"]
## file details
assert fs.ls("data/root/a/file.txt", detail=True) == [{
"name": "data/root/a/file.txt",
"size": 10,
"type": "file"
}]
# c has two files
assert fs.ls("data/root/c", detail=True) == [
{
"name": "data/root/c/file1.txt",
"size": 10,
"type": "file"
},
{
"name": "data/root/c/file2.txt",
"size": 10,
"type": "file"
},
]
## if not direct match is found throws error
with pytest.raises(FileNotFoundError):
fs.ls("not-a-container")
with pytest.raises(FileNotFoundError):
fs.ls("data/not-a-directory/")
with pytest.raises(FileNotFoundError):
fs.ls("data/root/not-a-file.txt")
def test_mkdir_rm_recursive(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("test_mkdir_rm_recursive")
assert "test_mkdir_rm_recursive/" in fs.ls("")
with fs.open("test_mkdir_rm_recursive/file.txt", "wb") as f:
f.write(b"0123456789")
with fs.open("test_mkdir_rm_recursive/dir/file.txt", "wb") as f:
f.write(b"ABCD")
with fs.open("test_mkdir_rm_recursive/dir/file2.txt", "wb") as f:
f.write(b"abcdef")
assert fs.find("test_mkdir_rm_recursive") == [
"test_mkdir_rm_recursive/dir/file.txt",
"test_mkdir_rm_recursive/dir/file2.txt",
"test_mkdir_rm_recursive/file.txt",
]
fs.rm("test_mkdir_rm_recursive", recursive=True)
assert "test_mkdir_rm_recursive/" not in fs.ls("")
assert fs.find("test_mkdir_rm_recursive") == []
def test_fetch_entire_blob(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR,
)
blob = fs.open("data/top_file.txt")
assert len(blob._fetch_range(start=0, length=10)) == 10
def test_connect(storage):
AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)