Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

list_indices and fetch_index implemented #101

Merged
merged 6 commits into from
Aug 2, 2024
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
66 changes: 59 additions & 7 deletions idc_index/index.py
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@

aws_endpoint_url = "https://s3.amazonaws.com"
gcp_endpoint_url = "https://storage.googleapis.com"
asset_endpoint_url = f"https://github.com/ImagingDataCommons/idc-index-data/releases/download/{idc_index_data.__version__}"

logging.basicConfig(format="%(asctime)s - %(message)s", level=logging.INFO)
logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -58,9 +59,8 @@ def client(cls) -> IDCClient:
return cls._client

def __init__(self):
# Read main index file
file_path = idc_index_data.IDC_INDEX_PARQUET_FILEPATH

# Read index file
logger.debug(f"Reading index file v{idc_index_data.__version__}")
self.index = pd.read_parquet(file_path)
# self.index = self.index.astype(str).replace("nan", "")
Expand All @@ -69,9 +69,26 @@ def __init__(self):
{"Modality": pd.Series.unique, "series_size_MB": "sum"}
)

self.indices_overview = {
"index": {
"description": "Main index containing one row per DICOM series.",
"installed": True,
"url": None,
},
"sm_index": {
"description": "DICOM Slide Microscopy series-level index.",
"installed": False,
"url": f"{asset_endpoint_url}/sm_index.parquet",
},
"sm_instance_index": {
"description": "DICOM Slide Microscopy instance-level index.",
"installed": False,
"url": f"{asset_endpoint_url}/sm_instance_index.parquet",
},
}

# Lookup s5cmd
self.s5cmdPath = shutil.which("s5cmd")

if self.s5cmdPath is None:
# Workaround to support environment without a properly setup PATH
# See https://github.com/Slicer/Slicer/pull/7587
Expand All @@ -80,16 +97,12 @@ def __init__(self):
if str(script).startswith("s5cmd/bin/s5cmd"):
self.s5cmdPath = script.locate().resolve(strict=True)
break

if self.s5cmdPath is None:
raise FileNotFoundError(
"s5cmd executable not found. Please install s5cmd from https://github.com/peak/s5cmd#installation"
)

self.s5cmdPath = str(self.s5cmdPath)

logger.debug(f"Found s5cmd executable: {self.s5cmdPath}")

# ... and check it can be executed
subprocess.check_call([self.s5cmdPath, "--help"], stdout=subprocess.DEVNULL)

Expand Down Expand Up @@ -177,6 +190,45 @@ def get_idc_version():
idc_version = Version(idc_index_data.__version__).major
return f"v{idc_version}"

def list_indices(self):
"""
Lists all available indices including their installation status.

Returns:
indices_overview (pd.DataFrame): DataFrame containing information per index.
"""

return pd.DataFrame.from_dict(self.indices_overview, orient="index")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the motivation to convert to a dataframe here? To me at least, this adds unnecessary complexity.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just to display it in a readable way to the user.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I personally would not this function at all. I think it pollutes the API without good reason. I don't think we would want to have a dedicated function that would make a DF for every other dict class variable, right?

If we want a convenience function that would make a DataFrame from a dict, it is better to add a generic helper function that would do this for any dict.


def fetch_index(self, index) -> None:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In this function I would not just fetch the file, but also load it into the class variable named as the index name - consistent with the main index.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

"""
Downloads requested index.

Args:
index (str): Name of the index to be downloaded.
"""

if index not in self.indices_overview:
logger.error(f"Index {index} is not available and can not be fetched.")
elif self.indices_overview[index]["installed"]:
logger.warning(
f"Index {index} already installed and will not be fetched again."
)
else:
response = requests.get(self.indices_overview[index]["url"], timeout=30)
if response.status_code == 200:
filepath = os.path.join(
idc_index_data.IDC_INDEX_PARQUET_FILEPATH.parents[0],
f"{index}.parquet",
)
with open(filepath, mode="wb") as file:
file.write(response.content)
self.indices_overview[index]["installed"] = True
else:
logger.error(
f"Failed to fetch index from URL {self.indices_overview[index]['url']}: {response.status_code}"
)

def get_collections(self):
"""
Returns the collections present in IDC
Expand Down
10 changes: 10 additions & 0 deletions tests/idcindex.py
Original file line number Diff line number Diff line change
Expand Up @@ -483,6 +483,16 @@ def test_prior_version_manifest(self):
with open(temp_manifest_file) as file:
assert len(file.readlines()) == 0

def test_list_indices(self):
i = IDCClient()
assert i.indices_overview # assert that dict was created

def test_fetch_index(self):
i = IDCClient()
assert i.indices_overview["sm_index"]["installed"] is False
i.fetch_index("sm_index")
assert i.indices_overview["sm_index"]["installed"] is True


if __name__ == "__main__":
unittest.main()
Loading