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_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_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_mkdir(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name, connection_string=CONN_STR,
)
# Verify mkdir will create a new container when create_parents is True
fs.mkdir("new-container", create_parents=True)
assert "new-container" in fs.ls(".")
fs.rm("new-container")
# Verify a new container will not be created when create_parents
# is False
with pytest.raises(PermissionError):
fs.mkdir("new-container", create_parents=False)
# Test creating subdirectory when container does not exist
# Since mkdir is a no-op, if create_parents=True, it will create
# the top level container, but will NOT create nested directories
fs.mkdir("new-container/dir", create_parents=True)
assert "new-container/dir" not in fs.ls("new-container")
assert "new-container" in fs.ls(".")
fs.rm("new-container", recursive=True)
# Test that creating a directory when already exists passes
fs.mkdir("data")
assert "data" in fs.ls(".")
# Test raising error when container does not exist
with pytest.raises(PermissionError):
fs.mkdir("new-container/dir", create_parents=False)
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 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_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 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_makedir(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
# Verify makedir will create a new container when create_parents is True
with pytest.raises(FileExistsError):
fs.makedir("data", exist_ok=False)
# The container and directory already exist. Should pass
fs.makedir("data", exist_ok=True)
assert "data/" in fs.ls(".")
# Test creating subdirectory when container does not exist
fs.makedir("new-container/dir")
assert "new-container/dir" in fs.ls("new-container")
fs.rm("new-container", recursive=True)
def test_mkdir_rmdir(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
fs.mkdir("new-container")
assert "new-container/" in fs.ls("")
assert fs.ls("new-container") == []
with fs.open(path="new-container/file.txt", mode="wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file.txt", "wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file2.txt", "wb") as f:
f.write(b"0123456789")
# Check to verify you can skip making a directory if the container
# already exists, but still create a file in that directory
fs.mkdir("new-container/dir/file.txt", exist_ok=False)
assert "new-container/" in fs.ls("")
fs.mkdir("new-container/file2.txt", exist_ok=False)
assert "new-container/file2.txt" in fs.ls("new-container")
# Test to verify that the file contains expected contents
with fs.open("new-container/file2.txt", "rb") as f:
outfile = f.read()
assert outfile == b""
# Check that trying to overwrite an existing nested file in append mode works as expected
fs.mkdir("new-container/dir/file2.txt", exist_ok=False)
assert "new-container/dir/file2.txt" in fs.ls("new-container/dir")
# Also verify you can make a nested directory structure
fs.mkdir("new-container/dir2/file.txt", exist_ok=False)
with fs.open("new-container/dir2/file.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/dir2/file.txt" in fs.ls("new-container/dir2")
fs.rm("new-container/dir2", recursive=True)
fs.rm("new-container/dir", recursive=True)
assert fs.ls("new-container") == [
"new-container/file.txt",
"new-container/file2.txt",
]
fs.rm("new-container/file.txt")
fs.rm("new-container/file2.txt")
fs.rmdir("new-container")
assert "new-container/" not in fs.ls("")
def test_mkdir_rmdir(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
fs.mkdir("new-container")
assert "new-container/" in fs.ls("")
assert fs.ls("new-container") == []
with fs.open(path="new-container/file.txt", mode="wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file.txt", "wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file2.txt", "wb") as f:
f.write(b"0123456789")
# Check to verify you can skip making a directory if the container
# already exists, but still create a file in that directory
fs.mkdir("new-container/dir/file.txt", exists_ok=True)
assert "new-container/" in fs.ls("")
fs.mkdir("new-container/file2.txt", exists_ok=True)
with fs.open("new-container/file2.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/file2.txt" in fs.ls("new-container")
fs.mkdir("new-container/dir/file2.txt", exists_ok=True)
with fs.open("new-container/dir/file2.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/dir/file2.txt" in fs.ls("new-container/dir")
# Also verify you can make a nested directory structure
fs.mkdir("new-container/dir2/file.txt", exists_ok=True)
with fs.open("new-container/dir2/file.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/dir2/file.txt" in fs.ls("new-container/dir2")
fs.rm("new-container/dir2", recursive=True)
fs.rm("new-container/dir", recursive=True)
assert fs.ls("new-container") == [
"new-container/file.txt",
"new-container/file2.txt",
]
fs.rm("new-container/file.txt")
fs.rm("new-container/file2.txt")
fs.rmdir("new-container")
assert "new-container/" not in fs.ls("")
def test_makedir_rmdir(storage, caplog):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
fs.makedir("new-container")
assert "new-container" in fs.ls("")
assert fs.ls("new-container") == []
with fs.open(path="new-container/file.txt", mode="wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file.txt", "wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file2.txt", "wb") as f:
f.write(b"0123456789")
# Verify that mkdir will raise an exception if the directory exists
# and exist_ok is False
with pytest.raises(FileExistsError):
fs.makedir("new-container/dir/file.txt", exist_ok=False)
# mkdir should raise an error if the container exists and
# we try to create a nested directory, with exist_ok=False
with pytest.raises(FileExistsError):
fs.makedir("new-container/dir2", exist_ok=False)
# Check that trying to overwrite an existing nested file in append mode works as expected
# if exist_ok is True
fs.makedir("new-container/dir/file2.txt", exist_ok=True)
assert "new-container/dir/file2.txt" in fs.ls("new-container/dir")
# Also verify you can make a nested directory structure
with fs.open("new-container/dir2/file.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/dir2/file.txt" in fs.ls("new-container/dir2")
fs.rm("new-container/dir2", recursive=True)
fs.rm("new-container/dir", recursive=True)
fs.touch("new-container/file2.txt")
assert fs.ls("new-container") == [
"new-container/file.txt",
"new-container/file2.txt",
]
fs.rm("new-container/file.txt")
fs.rm("new-container/file2.txt")
fs.rmdir("new-container")
assert "new-container" not in fs.ls("")
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 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_mkdir(storage):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
# Verify mkdir will create a new container when create_parents is True
fs.mkdir("new-container", create_parents=True)
assert "new-container/" in fs.ls(".")
fs.rm("new-container")
# Verify a new container will not be created when create_parents
# is False
with pytest.raises(PermissionError):
fs.mkdir("new-container", create_parents=False)
# Test creating subdirectory when container does not exist
fs.mkdir("new-container/dir", create_parents=True)
assert "new-container/dir" in fs.ls("new-container")
fs.rm("new-container", recursive=True)
# Test raising error when container does not exist
with pytest.raises(PermissionError):
fs.mkdir("new-container/dir", create_parents=False)
class AzureDataLake(Source):
"""
A class for pulling data from the Azure Data Lakes (gen1 and gen2).
You can either connect to the lake in general or to a particular path,
eg.
lake = AzureDataLake(); lake.exists("a/b/c.csv")
vs
lake = AzureDataLake(path="a/b/c.csv"); lake.exists()
Parameters
----------
credentials : Dict[str, Any], optional
A dictionary containing ACCOUNT_NAME and the following
Service Principal credentials:
- AZURE_TENANT_ID
- AZURE_CLIENT_ID
- AZURE_CLIENT_SECRET
"""
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 upload(
self,
from_path: str,
to_path: str = None,
recursive: bool = False,
overwrite: bool = False,
) -> None:
"""
Upload file(s) to the lake.
Args:
from_path (str): Path to the local file(s) to be uploaded.
to_path (str): Path to the destination file/folder
recursive (bool): Set this to true if working with directories.
overwrite (bool): Whether to overwrite the file(s) if they exist.
Example:
```python
from viadot.sources import AzureDataLake
lake = AzureDataLake()
lake.upload(from_path='tests/test.csv', to_path="sandbox/test.csv")
```
"""
if self.gen == 1:
raise NotImplemented(
"Azure Data Lake Gen1 does not support simple file upload."
)
to_path = to_path or self.path
self.fs.upload(
lpath=from_path,
rpath=to_path,
recursive=recursive,
overwrite=overwrite,
)
def exists(self, path: str = None) -> bool:
"""
Check if a location exists in Azure Data Lake.
Args:
path (str): The path to check. Can be a file or a directory.
Example:
```python
from viadot.sources import AzureDataLake
lake = AzureDataLake(gen=1)
lake.exists("tests/test.csv")
```
Returns:
bool: Whether the paths exists.
"""
path = path or self.path
return self.fs.exists(path)
def download(
self,
to_path: str,
from_path: str = None,
recursive: bool = False,
overwrite: bool = True,
) -> None:
if overwrite is False:
raise NotImplemented(
"Currently, only the default behavior (overwrite) is available."
)
from_path = from_path or self.path
self.fs.download(rpath=from_path, lpath=to_path, recursive=recursive)
def to_df(
self,
path: str = None,
sep: str = "\t",
quoting: int = 0,
lineterminator: str = None,
error_bad_lines: bool = None,
):
if quoting is None:
quoting = 0
path = path or self.path
url = os.path.join(self.base_url, path)
if url.endswith(".csv"):
df = pd.read_csv(
url,
storage_options=self.storage_options,
sep=sep,
quoting=quoting,
lineterminator=lineterminator,
error_bad_lines=error_bad_lines,
)
elif url.endswith(".parquet"):
df = pd.read_parquet(url, storage_options=self.storage_options)
else:
raise ValueError("Only CSV and parquet formats are supported.")
return df
def ls(self, path: str = None) -> List[str]:
path = path or self.path
return self.fs.ls(path)
def rm(self, path: str = None, recursive: bool = False):
path = path or self.path
self.fs.rm(path, recursive=recursive)
def cp(self, from_path: str = None, to_path: str = None, recursive: bool = False):
from_path = from_path or self.path
to_path = to_path
self.fs.cp(from_path, to_path, recursive=recursive)
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_makedir_rmdir(storage, caplog):
fs = AzureBlobFileSystem(
account_name=storage.account_name,
connection_string=CONN_STR,
)
fs.makedir("new-container")
assert "new-container/" in fs.ls("")
assert fs.ls("new-container") == []
with fs.open(path="new-container/file.txt", mode="wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file.txt", "wb") as f:
f.write(b"0123456789")
with fs.open("new-container/dir/file2.txt", "wb") as f:
f.write(b"0123456789")
# Verify that mkdir will raise an exception if the directory exists
# and exist_ok is False
with pytest.raises(FileExistsError):
fs.makedir("new-container/dir/file.txt", exist_ok=False)
# Verify that mkdir creates a directory if exist_ok is False and the
# directory does not exist
fs.makedir("new-container/file2.txt", exist_ok=False)
assert "new-container/file2.txt" in fs.ls("new-container")
# Verify that mkdir will silently ignore an existing directory if
# the directory exists and exist_ok is True
fs.makedir("new-container/dir", exist_ok=True)
assert "new-container/dir/" in fs.ls("new-container")
# Test to verify that the file contains expected contents
with fs.open("new-container/file2.txt", "rb") as f:
outfile = f.read()
assert outfile == b""
# Check that trying to overwrite an existing nested file in append mode works as expected
# if exist_ok is True
fs.makedir("new-container/dir/file2.txt", exist_ok=True)
assert "new-container/dir/file2.txt" in fs.ls("new-container/dir")
# Also verify you can make a nested directory structure
fs.makedir("new-container/dir2/file.txt", exist_ok=False)
with fs.open("new-container/dir2/file.txt", "wb") as f:
f.write(b"0123456789")
assert "new-container/dir2/file.txt" in fs.ls("new-container/dir2")
fs.rm("new-container/dir2", recursive=True)
fs.rm("new-container/dir", recursive=True)
assert fs.ls("new-container") == [
"new-container/file.txt",
"new-container/file2.txt",
]
fs.rm("new-container/file.txt")
fs.rm("new-container/file2.txt")
fs.rmdir("new-container")
assert "new-container/" not in fs.ls("")