Skip to content

Make Geant4 dataset downloads resumable and fail loudly #97

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.

Sign up for GitHub

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

Open
kavyawadhwa134 wants to merge 2 commits into
base: datasets
Choose a base branch
from
Open

Make Geant4 dataset downloads resumable and fail loudly #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e08117c
Make Geant4 dataset downloads resumable and fail loudly
kavyawadhwa134 Sep 5, 2026
3b4826d
style: pre-commit fixes
pre-commit-ci[bot] Sep 5, 2026
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
2 changes: 0 additions & 2 deletions src/geant4_python_application/files/2datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@
import tarfile
import tempfile
from collections import namedtuple
from pathlib import Path

import requests
from tqdm import tqdm
Expand Down Expand Up @@ -200,4 +199,3 @@ def reinstall_datasets():
# Uninstall and reinstall datasets
uninstall_datasets()
install_datasets(force=True)

109 changes: 92 additions & 17 deletions src/geant4_python_application/files/alt_datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,20 +18,81 @@

# List of all Geant4 datasets and their download links
datasets = (
Dataset(name="G4NDL", version="4.7.1", url="https://cern.ch/geant4-data/datasets/G4NDL.4.7.1.tar.gz", env="G4NEUTRONHPDATA"),
Dataset(name="G4EMLOW", version="8.5", url="https://cern.ch/geant4-data/datasets/G4EMLOW.8.5.tar.gz", env="G4LEDATA"),
Dataset(name="PhotonEvaporation", version="5.7", url="https://cern.ch/geant4-data/datasets/G4PhotonEvaporation.5.7.tar.gz", env="G4LEVELGAMMADATA"),
Dataset(name="RadioactiveDecay", version="5.6", url="https://cern.ch/geant4-data/datasets/G4RadioactiveDecay.5.6.tar.gz", env="G4RADIOACTIVEDATA"),
Dataset(name="G4PARTICLEXS", version="4.0", url="https://cern.ch/geant4-data/datasets/G4PARTICLEXS.4.0.tar.gz", env="G4PARTICLEXSDATA"),
Dataset(name="G4PII", version="1.3", url="https://cern.ch/geant4-data/datasets/G4PII.1.3.tar.gz", env="G4PIIDATA"),
Dataset(name="RealSurface", version="2.2", url="https://cern.ch/geant4-data/datasets/G4RealSurface.2.2.tar.gz", env="G4REALSURFACEDATA"),
Dataset(name="G4SAIDDATA", version="2.0", url="https://cern.ch/geant4-data/datasets/G4SAIDDATA.2.0.tar.gz", env="G4SAIDXSDATA"),
Dataset(name="G4ABLA", version="3.3", url="https://cern.ch/geant4-data/datasets/G4ABLA.3.3.tar.gz", env="G4ABLADATA"),
Dataset(name="G4INCL", version="1.2", url="https://cern.ch/geant4-data/datasets/G4INCL.1.2.tar.gz", env="G4INCLDATA"),
Dataset(name="G4ENSDFSTATE", version="2.3", url="https://cern.ch/geant4-data/datasets/G4ENSDFSTATE.2.3.tar.gz", env="G4ENSDFSTATEDATA"),
Dataset(name="G4TENDL", version="1.4", url="https://cern.ch/geant4-data/datasets/G4TENDL.1.4.tar.gz", env="G4TENDLDATA"),
Dataset(
name="G4NDL",
version="4.7.1",
url="https://cern.ch/geant4-data/datasets/G4NDL.4.7.1.tar.gz",
env="G4NEUTRONHPDATA",
),
Dataset(
name="G4EMLOW",
version="8.5",
url="https://cern.ch/geant4-data/datasets/G4EMLOW.8.5.tar.gz",
env="G4LEDATA",
),
Dataset(
name="PhotonEvaporation",
version="5.7",
url="https://cern.ch/geant4-data/datasets/G4PhotonEvaporation.5.7.tar.gz",
env="G4LEVELGAMMADATA",
),
Dataset(
name="RadioactiveDecay",
version="5.6",
url="https://cern.ch/geant4-data/datasets/G4RadioactiveDecay.5.6.tar.gz",
env="G4RADIOACTIVEDATA",
),
Dataset(
name="G4PARTICLEXS",
version="4.0",
url="https://cern.ch/geant4-data/datasets/G4PARTICLEXS.4.0.tar.gz",
env="G4PARTICLEXSDATA",
),
Dataset(
name="G4PII",
version="1.3",
url="https://cern.ch/geant4-data/datasets/G4PII.1.3.tar.gz",
env="G4PIIDATA",
),
Dataset(
name="RealSurface",
version="2.2",
url="https://cern.ch/geant4-data/datasets/G4RealSurface.2.2.tar.gz",
env="G4REALSURFACEDATA",
),
Dataset(
name="G4SAIDDATA",
version="2.0",
url="https://cern.ch/geant4-data/datasets/G4SAIDDATA.2.0.tar.gz",
env="G4SAIDXSDATA",
),
Dataset(
name="G4ABLA",
version="3.3",
url="https://cern.ch/geant4-data/datasets/G4ABLA.3.3.tar.gz",
env="G4ABLADATA",
),
Dataset(
name="G4INCL",
version="1.2",
url="https://cern.ch/geant4-data/datasets/G4INCL.1.2.tar.gz",
env="G4INCLDATA",
),
Dataset(
name="G4ENSDFSTATE",
version="2.3",
url="https://cern.ch/geant4-data/datasets/G4ENSDFSTATE.2.3.tar.gz",
env="G4ENSDFSTATEDATA",
),
Dataset(
name="G4TENDL",
version="1.4",
url="https://cern.ch/geant4-data/datasets/G4TENDL.1.4.tar.gz",
env="G4TENDLDATA",
),
)


# Function to determine the data directory dynamically
def data_directory() -> str:
return os.path.join(
Expand All @@ -42,23 +103,32 @@ def data_directory() -> str:
"data",
)


# Check if a dataset is already installed
def is_dataset_installed(dataset: Dataset) -> bool:
dataset_path = os.path.join(data_directory(), f"{dataset.name}.{dataset.version}")
return os.path.exists(dataset_path) and os.path.isdir(dataset_path)


# Get the size of the dataset for progress tracking
def _get_dataset_download_size(dataset: Dataset) -> int:
r = requests.head(dataset.url)
r.raise_for_status()
return int(r.headers.get("content-length", 0))


# Get the total download size for all selected datasets
def _get_total_download_size(datasets_to_download: list[Dataset] = datasets) -> int:
with concurrent.futures.ThreadPoolExecutor(max_workers=len(datasets_to_download)) as executor:
futures = [executor.submit(_get_dataset_download_size, dataset) for dataset in datasets_to_download]
with concurrent.futures.ThreadPoolExecutor(
max_workers=len(datasets_to_download)
) as executor:
futures = [
executor.submit(_get_dataset_download_size, dataset)
for dataset in datasets_to_download
]
return sum(f.result() for f in concurrent.futures.as_completed(futures))


# Download and extract the dataset with progress tracking
def _download_extract_dataset(dataset: Dataset, pbar: tqdm):
r = requests.get(dataset.url, stream=True)
Expand All @@ -74,14 +144,17 @@ def _download_extract_dataset(dataset: Dataset, pbar: tqdm):
with tarfile.open(fileobj=f, mode="r:gz") as tar:
tar.extractall(data_directory())


# Main function to handle the installation of datasets
def install_datasets(force: bool = False, show_progress: bool = True):
os.environ["GEANT4_DATA_DIR"] = data_directory()
datasets_to_download = []

# Check if datasets are already downloaded, unless force is True
for dataset in datasets:
dataset_path = os.path.join(data_directory(), f"{dataset.name}.{dataset.version}")
dataset_path = os.path.join(
data_directory(), f"{dataset.name}.{dataset.version}"
)
os.environ[dataset.env] = dataset_path
if not is_dataset_installed(dataset) or force:
datasets_to_download.append(dataset)
Expand All @@ -91,7 +164,7 @@ def install_datasets(force: bool = False, show_progress: bool = True):
return # All datasets are already installed

os.makedirs(data_directory(), exist_ok=True)

# Show progress for the dataset download and extraction
if show_progress:
print(
Expand Down Expand Up @@ -124,6 +197,7 @@ def install_datasets(force: bool = False, show_progress: bool = True):
) / (1024**3)
print(f"Geant4 datasets size on disk after extraction: {total_size_gb:.2f}GB")


# Uninstall datasets (remove the dataset directory)
def uninstall_datasets():
dir_to_remove = os.path.dirname(data_directory())
Expand All @@ -135,6 +209,7 @@ def uninstall_datasets():
)
shutil.rmtree(dir_to_remove, ignore_errors=True)


# Reinstall datasets (uninstall first, then reinstall)
def reinstall_datasets():
uninstall_datasets()
Expand Down
59 changes: 50 additions & 9 deletions src/geant4_python_application/files/dataset1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@

url = "https://cern.ch/geant4-data/datasets"


def data_directory() -> str:
return os.path.join(
geant4_python_application.application_directory(),
Expand All @@ -24,35 +25,72 @@ def data_directory() -> str:
"data",
)


Dataset = namedtuple("Dataset", ["name", "version", "filename", "env"])

datasets = (
Dataset(name="G4NDL", version="4.7.1", filename="G4NDL", env="G4NEUTRONHPDATA"),
Dataset(name="G4EMLOW", version="8.5", filename="G4EMLOW", env="G4LEDATA"),
Dataset(name="PhotonEvaporation", version="5.7", filename="G4PhotonEvaporation", env="G4LEVELGAMMADATA"),
Dataset(name="RadioactiveDecay", version="5.6", filename="G4RadioactiveDecay", env="G4RADIOACTIVEDATA"),
Dataset(name="G4PARTICLEXS", version="4.0", filename="G4PARTICLEXS", env="G4PARTICLEXSDATA"),
Dataset(
name="PhotonEvaporation",
version="5.7",
filename="G4PhotonEvaporation",
env="G4LEVELGAMMADATA",
),
Dataset(
name="RadioactiveDecay",
version="5.6",
filename="G4RadioactiveDecay",
env="G4RADIOACTIVEDATA",
),
Dataset(
name="G4PARTICLEXS",
version="4.0",
filename="G4PARTICLEXS",
env="G4PARTICLEXSDATA",
),
Dataset(name="G4PII", version="1.3", filename="G4PII", env="G4PIIDATA"),
Dataset(name="RealSurface", version="2.2", filename="G4RealSurface", env="G4REALSURFACEDATA"),
Dataset(name="G4SAIDDATA", version="2.0", filename="G4SAIDDATA", env="G4SAIDXSDATA"),
Dataset(
name="RealSurface",
version="2.2",
filename="G4RealSurface",
env="G4REALSURFACEDATA",
),
Dataset(
name="G4SAIDDATA", version="2.0", filename="G4SAIDDATA", env="G4SAIDXSDATA"
),
Dataset(name="G4ABLA", version="3.3", filename="G4ABLA", env="G4ABLADATA"),
Dataset(name="G4INCL", version="1.2", filename="G4INCL", env="G4INCLDATA"),
Dataset(name="G4ENSDFSTATE", version="2.3", filename="G4ENSDFSTATE", env="G4ENSDFSTATEDATA"),
Dataset(
name="G4ENSDFSTATE",
version="2.3",
filename="G4ENSDFSTATE",
env="G4ENSDFSTATEDATA",
),
)


def _dataset_url(dataset: Dataset) -> str:
return f"{url}/{dataset.filename}.{dataset.version}.tar.gz"


def _get_dataset_download_size(dataset: Dataset) -> int:
r = requests.head(_dataset_url(dataset))
r.raise_for_status()
return int(r.headers.get("content-length", 0))


def _get_total_download_size(datasets_to_download: list[Dataset] = datasets) -> int:
with concurrent.futures.ThreadPoolExecutor(max_workers=len(datasets_to_download)) as executor:
futures = [executor.submit(_get_dataset_download_size, dataset) for dataset in datasets_to_download]
with concurrent.futures.ThreadPoolExecutor(
max_workers=len(datasets_to_download)
) as executor:
futures = [
executor.submit(_get_dataset_download_size, dataset)
for dataset in datasets_to_download
]
return sum(f.result() for f in concurrent.futures.as_completed(futures))


def _download_extract_dataset(dataset: Dataset, pbar: tqdm):
filename = dataset.filename
urlpath = f"{url}/{filename}.{dataset.version}.tar.gz"
Expand All @@ -69,10 +107,11 @@ def _download_extract_dataset(dataset: Dataset, pbar: tqdm):
with tarfile.open(fileobj=f, mode="r:gz") as tar:
tar.extractall(data_directory())


def install_datasets(force: bool = False, show_progress: bool = True):
os.environ["GEANT4_DATA_DIR"] = data_directory()
datasets_to_download = []

# Check if datasets are already downloaded
for dataset in datasets:
path = os.path.join(data_directory(), dataset.name + dataset.version)
Expand Down Expand Up @@ -115,6 +154,7 @@ def install_datasets(force: bool = False, show_progress: bool = True):
) / (1024**3)
print(f"Geant4 datasets size on disk after extraction: {total_size_gb:.2f}GB")


def uninstall_datasets():
dir_to_remove = os.path.dirname(data_directory())
package_dir = os.path.dirname(__file__)
Expand All @@ -125,6 +165,7 @@ def uninstall_datasets():
)
shutil.rmtree(dir_to_remove, ignore_errors=True)


def reinstall_datasets():
uninstall_datasets()
install_datasets(force=True)
Loading
Loading