idc-index-data 0.1.0__tar.gz → 17.0.0__tar.gz

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/.github/CONTRIBUTING.md

@@ -99,3 +99,24 @@ pre-commit run -a
 ```
 
 to check all files.
+
+# Updating the IDC index version
+
+You can update the version using:
+
+```bash
+export GCP_PROJECT=idc-external-025
+export GOOGLE_APPLICATION_CREDENTIALS=/path/to/keyfile.json
+nox -s bump -- <version>
+```
+
+And follow the instructions it gives you. Leave off the version to bump to the
+latest version. Add `-–commit` to run the commit procedure.
+
+# Tagging a release
+
+You can print the instructions for tagging a release using:
+
+```bash
+nox -s tag_release
+```

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/.github/workflows/cd.yml

@@ -27,6 +27,13 @@ jobs:
         with:
           fetch-depth: 0
 
+      - name: Authorize Google Cloud
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: "${{ secrets.SERVICE_ACCOUNT_KEY }}"
+          create_credentials_file: true
+          export_environment_variables: true
+
       - uses: hynek/build-and-inspect-python-package@v2
 
   publish:

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/.github/workflows/ci.yml

@@ -22,12 +22,22 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+
+      - name: Authorize Google Cloud
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: "${{ secrets.SERVICE_ACCOUNT_KEY }}"
+          create_credentials_file: true
+          export_environment_variables: true
+
       - uses: actions/setup-python@v5
         with:
           python-version: "3.x"
+
       - uses: pre-commit/action@v3.0.1
         with:
           extra_args: --hook-stage manual --all-files
+
       - name: Run PyLint
         run: |
           echo "::add-matcher::$GITHUB_WORKSPACE/.github/matchers/pylint.json"
@@ -43,15 +53,23 @@ jobs:
         python-version: ["3.8", "3.12"]
         runs-on: [ubuntu-latest, macos-latest, windows-latest]
 
-        include:
-          - python-version: pypy-3.10
-            runs-on: ubuntu-latest
+        #currently not working on pypi-3.10
+        # include:
+        #   - python-version: pypy-3.10
+        #     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
+      - name: Authorize Google Cloud
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: "${{ secrets.SERVICE_ACCOUNT_KEY }}"
+          create_credentials_file: true
+          export_environment_variables: true
+
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}

idc_index_data-17.0.0/.github/workflows/keep-alive.yml

@@ -0,0 +1,18 @@
+name: keep-github-actions-alive
+
+on:
+  schedule:
+    - cron: "0 0 * * *"
+
+permissions:
+  actions: write
+
+jobs:
+  keep-alive:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: gautamkrishnar/keepalive-workflow@v2
+        with:
+          time_elapsed: 50
+          use_api: true

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/.gitignore

@@ -156,3 +156,6 @@ Thumbs.db
 # Common editor files
 *~
 *.swp
+
+# gcp service account keys
+gha-creds-**.json

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/.pre-commit-config.yaml

@@ -54,12 +54,6 @@ repos:
         args: []
         additional_dependencies:
           - pytest
-          # Since the "python_version" set in the "tool.mypy" section of "pyproject.toml" is "3.8",
-          # we ensure type checking also works when running the hook from Python versions above 3.8 by always
-          # installing "importlib_metadata". Note that because the "importlib.metadata.distribution"
-          # module was added in Python version 3.10 and later, this line can be removed when only supporting
-          # Python versions 3.10 and above.
-          - importlib_metadata>=2.0
 
   - repo: https://github.com/codespell-project/codespell
     rev: "v2.2.6"

idc_index_data-17.0.0/CMakeLists.txt

@@ -0,0 +1,37 @@
+cmake_minimum_required(VERSION 3.15...3.26)
+project(${SKBUILD_PROJECT_NAME} LANGUAGES NONE)
+
+find_package(
+  Python
+  COMPONENTS Interpreter
+  REQUIRED)
+
+if(NOT DEFINED ENV{GCP_PROJECT})
+  message(FATAL_ERROR "GCP_PROJECT env. variable is not set")
+endif()
+
+option(IDC_INDEX_DATA_GENERATE_CSV_ARCHIVE "Generate idc_index.csv.zip file" ON)
+option(IDC_INDEX_DATA_GENERATE_PARQUET "Generate idc_index.parquet file" OFF)
+
+set(download_dir "${PROJECT_BINARY_DIR}")
+
+add_custom_command(
+  OUTPUT
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_CSV_ARCHIVE}>:${download_dir}/idc_index.csv.zip>
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_PARQUET}>:${download_dir}/idc_index.parquet>
+  COMMAND python ${CMAKE_CURRENT_SOURCE_DIR}/scripts/python/idc_index_data_manager.py
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_CSV_ARCHIVE}>:--generate-csv-archive>
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_PARQUET}>:--generate-parquet>
+)
+
+add_custom_target(run_idc_index_data_manager ALL
+  DEPENDS
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_CSV_ARCHIVE}>:${download_dir}/idc_index.csv.zip>
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_PARQUET}>:${download_dir}/idc_index.parquet>
+)
+
+install(
+  FILES
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_CSV_ARCHIVE}>:${download_dir}/idc_index.csv.zip>
+    $<$<BOOL:${IDC_INDEX_DATA_GENERATE_PARQUET}>:${download_dir}/idc_index.parquet>
+  DESTINATION "idc_index_data")

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: idc-index-data
-Version: 0.1.0
+Version: 17.0.0
 Summary: ImagingDataCommons index to query and download data.
 Author-Email: Andrey Fedorov <andrey.fedorov@gmail.com>, Vamsi Thiriveedhi <vthiriveedhi@mgh.harvard.edu>, Jean-Christophe Fillion-Robin <jchris.fillionr@kitware.com>
 License: Copyright 2024 Andrey Fedorov
@@ -42,7 +42,9 @@ Project-URL: Bug tracker, https://github.com/ImagingDataCommons/idc-index-data/i
 Project-URL: Discussions, https://discourse.canceridc.dev/
 Project-URL: Changelog, https://github.com/ImagingDataCommons/idc-index-data/releases
 Requires-Python: >=3.8
-Requires-Dist: importlib_metadata>=2.0; python_version < "3.10"
+Provides-Extra: test
+Provides-Extra: dev
+Provides-Extra: docs
 Requires-Dist: pytest>=6; extra == "test"
 Requires-Dist: pytest-cov>=3; extra == "test"
 Requires-Dist: pytest>=6; extra == "dev"
@@ -52,9 +54,6 @@ Requires-Dist: myst_parser>=0.13; extra == "docs"
 Requires-Dist: sphinx_copybutton; extra == "docs"
 Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
 Requires-Dist: furo>=2023.08.17; extra == "docs"
-Provides-Extra: test
-Provides-Extra: dev
-Provides-Extra: docs
 Description-Content-Type: text/markdown
 
 # idc-index-data

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/noxfile.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import argparse
+import re
 import shutil
 from pathlib import Path
 
@@ -8,7 +9,7 @@ import nox
 
 DIR = Path(__file__).parent.resolve()
 
-nox.options.sessions = ["lint", "pylint", "tests"]
+nox.options.sessions = ["lint", "pylint", "tests"]  # Session run by default
 
 
 @nox.session
@@ -115,3 +116,90 @@ def build(session: nox.Session) -> None:
 
     session.install("build")
     session.run("python", "-m", "build")
+
+
+def _bump(session: nox.Session, name: str, script: str, files) -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--commit", action="store_true", help="Make a branch and commit."
+    )
+    parser.add_argument(
+        "version", nargs="?", help="The version to process - leave off for latest."
+    )
+    args = parser.parse_args(session.posargs)
+
+    session.install("db-dtypes")
+    session.install("google-cloud-bigquery")
+    session.install("pandas")
+    session.install("pyarrow")
+
+    if args.version is None:
+        gcp_project = "idc-external-025"
+        idc_index_version = session.run(
+            "python",
+            "scripts/python/idc_index_data_manager.py",
+            "--project",
+            gcp_project,
+            "--retrieve-latest-idc-release-version",
+            external=True,
+            silent=True,
+        ).strip()
+
+    else:
+        idc_index_version = args.version
+
+    extra = ["--quiet"] if args.commit else []
+    session.run("python", script, idc_index_version, *extra)
+
+    if args.commit:
+        session.run(
+            "git",
+            "switch",
+            "-c",
+            f"update-to-{name.replace(' ', '-').lower()}-{idc_index_version}",
+            external=True,
+        )
+        session.run("git", "add", "-u", *files, external=True)
+        session.run(
+            "git",
+            "commit",
+            "-m",
+            f"Update to {name} {idc_index_version}",
+            external=True,
+        )
+        session.log(
+            f'Complete! Now run: gh pr create --fill --body "Created by running `nox -s {session.name} -- --commit`"'
+        )
+
+
+@nox.session
+def bump(session: nox.Session) -> None:
+    """
+    Set to a new IDC index version, use -- <version>, otherwise will use the latest version.
+    """
+    files = (
+        "pyproject.toml",
+        "scripts/sql/idc_index.sql",
+        "tests/test_package.py",
+    )
+    _bump(
+        session,
+        "IDC index",
+        "scripts/python/update_idc_index_version.py",
+        files,
+    )
+
+
+@nox.session(venv_backend="none")
+def tag_release(session: nox.Session) -> None:
+    """
+    Print instructions for tagging a release and pushing it to GitHub.
+    """
+
+    session.log("Run the following commands to make a release:")
+    txt = Path("pyproject.toml").read_text()
+    current_version = next(iter(re.finditer(r'^version = "([\d\.]+)$"', txt))).group(1)
+    print(
+        f"git tag --sign -m 'idc-index-data {current_version}' {current_version} main"
+    )
+    print(f"git push origin {current_version}")

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/pyproject.toml

@@ -1,10 +1,19 @@
 [build-system]
-requires = ["scikit-build-core"]
+requires = [
+  "scikit-build-core",
+  "db-dtypes",
+  "google-cloud-bigquery",
+  "pandas",
+  "pyarrow",
+  "pygithub",
+  "requests"
+]
 build-backend = "scikit_build_core.build"
 
 
 [project]
 name = "idc-index-data"
+version = "17.0.0"
 authors = [
   { name = "Andrey Fedorov", email = "andrey.fedorov@gmail.com" },
   { name = "Vamsi Thiriveedhi", email = "vthiriveedhi@mgh.harvard.edu" },
@@ -31,8 +40,7 @@ classifiers = [
   "Topic :: Scientific/Engineering",
   "Typing :: Typed",
 ]
-dynamic = ["version"]
-dependencies = ["importlib_metadata>=2.0; python_version<'3.10'"]
+dependencies = []
 
 [project.optional-dependencies]
 test = [
@@ -61,14 +69,15 @@ Changelog = "https://github.com/ImagingDataCommons/idc-index-data/releases"
 [tool.scikit-build]
 minimum-version = "0.8.2"
 build-dir = "build/{wheel_tag}"
-metadata.version.provider = "scikit_build_core.metadata.setuptools_scm"
-sdist.include = ["src/idc_index_data/_version.py"]
 wheel.platlib = false
 wheel.py-api = "py3"
 
 
-[tool.setuptools_scm]
-write_to = "src/idc_index_data/_version.py"
+[[tool.scikit-build.generate]]
+path = "idc_index_data/_version.py"
+template = '''
+version = "${version}"
+'''
 
 
 [tool.pytest.ini_options]
@@ -108,7 +117,7 @@ disallow_incomplete_defs = true
 
 
 [tool.ruff]
-src = ["src"]
+src = ["src", "scripts"]
 
 [tool.ruff.lint]
 extend-select = [

idc_index_data-17.0.0/scripts/python/idc_index_data_manager.py

@@ -0,0 +1,136 @@
+from __future__ import annotations
+
+import logging
+import os
+from pathlib import Path
+
+import pandas as pd
+from google.cloud import bigquery
+
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+
+class IDCIndexDataManager:
+    def __init__(self, project_id: str):
+        """
+        Initializes the IDCIndexDataManager using the Google Cloud Platform project ID.
+        """
+        self.project_id = project_id
+        self.client = bigquery.Client(project=project_id)
+        logger.debug("IDCIndexDataManager initialized with project ID: %s", project_id)
+
+    def execute_sql_query(self, file_path: str) -> tuple[pd.DataFrame, str]:
+        """
+        Executes the SQL query in the specified file.
+
+        Returns:
+            Tuple[pd.DataFrame, str]: A tuple containing the DataFrame with query results,
+            the output basename.
+        """
+        with Path(file_path).open("r") as file:
+            sql_query = file.read()
+        index_df = self.client.query(sql_query).to_dataframe()
+        output_basename = Path(file_path).name.split(".")[0]
+        logger.debug("Executed SQL query from file: %s", file_path)
+        return index_df, output_basename
+
+    def generate_index_data_files(
+        self, generate_compressed_csv: bool = True, generate_parquet: bool = False
+    ) -> None:
+        """
+        Generates index-data files locally by executing queries against
+        the Google Cloud Platform IDC project tables.
+
+        This method iterates over SQL files in the 'scripts/sql' directory,
+        executing each query using :func:`execute_sql_query` and generating a DataFrame,
+        'index_df'. The DataFrame is then saved as compressed CSV and/or Parquet file.
+        """
+
+        scripts_dir = Path(__file__).parent.parent
+        sql_dir = scripts_dir / "sql"
+
+        for file_name in os.listdir(sql_dir):
+            if file_name.endswith(".sql"):
+                file_path = Path(sql_dir) / file_name
+                index_df, output_basename = self.execute_sql_query(file_path)
+                logger.debug(
+                    "Executed and processed SQL queries from file: %s", file_path
+                )
+            if generate_compressed_csv:
+                csv_file_name = f"{output_basename}.csv.zip"
+                index_df.to_csv(
+                    csv_file_name, compression={"method": "zip"}, escapechar="\\"
+                )
+                logger.debug("Created CSV zip file: %s", csv_file_name)
+
+            if generate_parquet:
+                parquet_file_name = f"{output_basename}.parquet"
+                index_df.to_parquet(parquet_file_name)
+                logger.debug("Created Parquet file: %s", parquet_file_name)
+
+    def retrieve_latest_idc_release_version(self) -> int:
+        """
+        Retrieves the latest IDC release version.
+
+        This function executes a SQL query on the `version_metadata` table in the
+        `idc_current` dataset of the BigQuery client. It retrieves the maximum
+        `idc_version` and returns it as an integer.
+        """
+        query = """
+        SELECT
+            MAX(idc_version) AS latest_idc_release_version
+        FROM
+            `bigquery-public-data.idc_current.version_metadata`
+        """
+        query_job = self.client.query(query)
+        result = query_job.result()
+        return int(next(result).latest_idc_release_version)
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--project",
+        default=os.environ.get("GCP_PROJECT", None),
+        help="Google Cloud Platform Project ID (default from GCP_PROJECT env. variable)",
+    )
+    parser.add_argument(
+        "--generate-csv-archive",
+        action="store_true",
+        help="Generate idc_index.csv.zip file",
+    )
+    parser.add_argument(
+        "--generate-parquet",
+        action="store_true",
+        help="Generate idc_index.parquet file",
+    )
+    parser.add_argument(
+        "--retrieve-latest-idc-release-version",
+        action="store_true",
+        help="Retrieve and display the latest IDC release version",
+    )
+
+    args = parser.parse_args()
+
+    if not args.project:
+        parser.error(
+            "Set GCP_PROJECT environment variable or specify --project argument"
+        )
+
+    if any([args.generate_csv_archive, args.generate_parquet]):
+        IDCIndexDataManager(args.project).generate_index_data_files(
+            generate_compressed_csv=args.generate_csv_archive,
+            generate_parquet=args.generate_parquet,
+        )
+    elif args.retrieve_latest_idc_release_version:
+        logging.basicConfig(level=logging.ERROR, force=True)
+        logger.setLevel(logging.ERROR)
+        version = IDCIndexDataManager(
+            args.project
+        ).retrieve_latest_idc_release_version()
+        print(f"{version}")  # noqa: T201
+    else:
+        parser.print_help()

idc_index_data-17.0.0/scripts/python/update_idc_index_version.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+"""
+Command line executable allowing to update source files given a IDC index version.
+"""
+
+from __future__ import annotations
+
+import argparse
+import contextlib
+import os
+import re
+import textwrap
+from pathlib import Path
+
+ROOT_DIR = Path(__file__).parent / "../.."
+
+
+@contextlib.contextmanager
+def _log(txt, verbose=True):
+    if verbose:
+        print(txt)  # noqa: T201
+    yield
+    if verbose:
+        print(f"{txt} - done")  # noqa: T201
+
+
+def _update_file(filepath, regex, replacement):
+    msg = "Updating %s" % os.path.relpath(str(filepath), ROOT_DIR)
+    with _log(msg):
+        pattern = re.compile(regex)
+        with filepath.open() as doc_file:
+            lines = doc_file.readlines()
+            updated_content = []
+            for line in lines:
+                updated_content.append(re.sub(pattern, replacement, line))
+        with filepath.open("w") as doc_file:
+            doc_file.writelines(updated_content)
+
+
+def update_pyproject_toml(idc_index_version):
+    pattern = re.compile(r'^version = "[\w\.]+"$')
+    replacement = f'version = "{idc_index_version}.0.0"'
+    _update_file(ROOT_DIR / "pyproject.toml", pattern, replacement)
+
+
+def update_sql_scripts(idc_index_version):
+    pattern = re.compile(r"idc_v\d+")
+    replacement = f"idc_v{idc_index_version}"
+    _update_file(ROOT_DIR / "scripts/sql/idc_index.sql", pattern, replacement)
+
+
+def update_tests(idc_index_version):
+    pattern = re.compile(r"EXPECTED_IDC_INDEX_VERSION = \d+")
+    replacement = f"EXPECTED_IDC_INDEX_VERSION = {idc_index_version}"
+    _update_file(ROOT_DIR / "tests/test_package.py", pattern, replacement)
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "idc_index_version",
+        metavar="IDC_INDEX_VERSION",
+        type=int,
+        help="IDC index version of the form NN",
+    )
+    parser.add_argument(
+        "--quiet",
+        action="store_true",
+        help="Hide the output",
+    )
+
+    args = parser.parse_args()
+
+    update_pyproject_toml(args.idc_index_version)
+    update_sql_scripts(args.idc_index_version)
+    update_tests(args.idc_index_version)
+
+    if not args.quiet:
+        msg = """\
+            Complete! Now run:
+
+            git switch -c update-to-idc-index-{release}
+            git add -u pyproject.toml scripts/sql/idc_index.sql tests/test_package.py
+            git commit -m "Update to IDC index {release}"
+            gh pr create --fill --body "Created by update_idc_index_version.py"
+            """
+        print(textwrap.dedent(msg.format(release=args.idc_index_version)))  # noqa: T201
+
+
+if __name__ == "__main__":
+    main()

idc_index_data-17.0.0/scripts/sql/idc_index.sql

@@ -0,0 +1,34 @@
+SELECT
+  # collection level attributes
+  ANY_VALUE(collection_id) AS collection_id,
+  ANY_VALUE(PatientID) AS PatientID,
+  SeriesInstanceUID,
+  ANY_VALUE(StudyInstanceUID) AS StudyInstanceUID,
+  ANY_VALUE(source_DOI) AS source_DOI,
+  # patient level attributes
+  ANY_VALUE(PatientAge) AS PatientAge,
+  ANY_VALUE(PatientSex) AS PatientSex,
+  # study level attributes
+  ANY_VALUE(StudyDate) AS StudyDate,
+  ANY_VALUE(StudyDescription) AS StudyDescription,
+  ANY_VALUE(dicom_curated.BodyPartExamined) AS BodyPartExamined,
+  # series level attributes
+  ANY_VALUE(Modality) AS Modality,
+  ANY_VALUE(Manufacturer) AS Manufacturer,
+  ANY_VALUE(ManufacturerModelName) AS ManufacturerModelName,
+  ANY_VALUE(SAFE_CAST(SeriesDate AS STRING)) AS SeriesDate,
+  ANY_VALUE(SeriesDescription) AS SeriesDescription,
+  ANY_VALUE(SeriesNumber) AS SeriesNumber,
+  COUNT(dicom_all.SOPInstanceUID) AS instanceCount,
+  ANY_VALUE(license_short_name) as license_short_name,
+  # download related attributes
+  ANY_VALUE(CONCAT("s3://", SPLIT(aws_url,"/")[SAFE_OFFSET(2)], "/", crdc_series_uuid, "/*")) AS series_aws_url,
+  ROUND(SUM(SAFE_CAST(instance_size AS float64))/1000000, 2) AS series_size_MB,
+FROM
+  `bigquery-public-data.idc_v17.dicom_all` AS dicom_all
+JOIN
+  `bigquery-public-data.idc_v17.dicom_metadata_curated` AS dicom_curated
+ON
+  dicom_all.SOPInstanceUID = dicom_curated.SOPInstanceUID
+GROUP BY
+  SeriesInstanceUID

{idc_index_data-0.1.0 → idc_index_data-17.0.0}/src/idc_index_data/__init__.py

@@ -6,28 +6,35 @@ idc-index-data: ImagingDataCommons index to query and download data.
 
 from __future__ import annotations
 
-import sys
+from importlib.metadata import distribution
 from pathlib import Path
 
-if sys.version_info >= (3, 10):
-    from importlib.metadata import distribution
-else:
-    from importlib_metadata import distribution
-
 from ._version import version as __version__
 
-__all__ = ["__version__", "IDC_INDEX_CSV_ARCHIVE_FILEPATH"]
+__all__ = [
+    "__version__",
+    "IDC_INDEX_CSV_ARCHIVE_FILEPATH",
+    "IDC_INDEX_PARQUET_FILEPATH",
+]
 
 
-def _lookup(path: str) -> Path:
+def _lookup(path: str, optional: bool = False) -> Path | None:
     """Support editable installation by looking up path using distribution API."""
     files = distribution("idc_index_data").files
     if files is not None:
         for _file in files:
             if str(_file) == path:
                 return Path(str(_file.locate())).resolve(strict=True)
+    if optional:
+        return None
+
     msg = f"Failed to lookup '{path}`."
     raise FileNotFoundError(msg)
 
 
-IDC_INDEX_CSV_ARCHIVE_FILEPATH: Path = _lookup("idc_index_data/idc_index.csv.zip")
+IDC_INDEX_CSV_ARCHIVE_FILEPATH: Path | None = _lookup(
+    "idc_index_data/idc_index.csv.zip"
+)
+IDC_INDEX_PARQUET_FILEPATH: Path | None = _lookup(
+    "idc_index_data/idc_index.parquet", optional=True
+)

idc_index_data-17.0.0/src/idc_index_data/_version.pyi

@@ -0,0 +1,3 @@
+from __future__ import annotations
+
+version: str

idc_index_data-17.0.0/tests/test_package.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+import importlib.metadata
+
+from packaging.version import Version
+
+import idc_index_data as m
+
+EXPECTED_IDC_INDEX_VERSION = 17
+
+
+def test_version():
+    assert importlib.metadata.version("idc_index_data") == m.__version__
+
+
+def test_idc_index_version():
+    assert Version(m.__version__).major == EXPECTED_IDC_INDEX_VERSION
+
+
+def test_filepath():
+    if m.IDC_INDEX_CSV_ARCHIVE_FILEPATH is not None:
+        assert m.IDC_INDEX_CSV_ARCHIVE_FILEPATH.is_file()
+        assert m.IDC_INDEX_CSV_ARCHIVE_FILEPATH.name == "idc_index.csv.zip"
+
+    if m.IDC_INDEX_PARQUET_FILEPATH is not None:
+        assert m.IDC_INDEX_PARQUET_FILEPATH.is_file()
+        assert m.IDC_INDEX_PARQUET_FILEPATH.name == "idc_index.parquet"

idc_index_data-0.1.0/CMakeLists.txt

@@ -1,20 +0,0 @@
-cmake_minimum_required(VERSION 3.15...3.26)
-project(${SKBUILD_PROJECT_NAME} LANGUAGES NONE)
-
-
-set(idc_index_release_version "0.3.2")
-set(idc_index_data_url "https://github.com/ImagingDataCommons/idc-index/releases/download/${idc_index_release_version}/idc_index.csv.zip")
-set(idc_index_data_sha256 "70ec9f915686a27bee3098163b8695c69c8696c05bfb7bd76943a24024cdeeb9")
-
-#
-# Download and install index
-#
-set(download_dir "${PROJECT_BINARY_DIR}")
-include(FetchContent)
-FetchContent_Populate(s5cmd
-  URL ${idc_index_data_url}
-  URL_HASH SHA256=${idc_index_data_sha256}
-  DOWNLOAD_DIR ${download_dir}
-  DOWNLOAD_NO_EXTRACT TRUE
-  )
-install(FILES "${download_dir}/idc_index.csv.zip" DESTINATION "idc_index_data")

idc_index_data-0.1.0/src/idc_index_data/_version.py

@@ -1,16 +0,0 @@
-# file generated by setuptools_scm
-# don't change, don't track in version control
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple, Union
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-else:
-    VERSION_TUPLE = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-
-__version__ = version = '0.1.0'
-__version_tuple__ = version_tuple = (0, 1, 0)

idc_index_data-0.1.0/src/idc_index_data/_version.pyi

@@ -1,4 +0,0 @@
-from __future__ import annotations
-
-version: str
-version_tuple: tuple[int, int, int] | tuple[int, int, int, str, str]

idc_index_data-0.1.0/tests/test_package.py

@@ -1,14 +0,0 @@
-from __future__ import annotations
-
-import importlib.metadata
-
-import idc_index_data as m
-
-
-def test_version():
-    assert importlib.metadata.version("idc_index_data") == m.__version__
-
-
-def test_filepath():
-    assert m.IDC_INDEX_CSV_ARCHIVE_FILEPATH.is_file()
-    assert m.IDC_INDEX_CSV_ARCHIVE_FILEPATH.name == "idc_index.csv.zip"