feat: Add IDC_INDEX_DATA_GENERATE_PARQUET option

ImagingDataCommons · Mar 22, 2024 · 4c2e6ef · 4c2e6ef
1 parent c65f32b
commit 4c2e6ef
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 10 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -10,19 +10,25 @@ if(NOT DEFINED ENV{GCP_PROJECT})
   message(FATAL_ERROR "GCP_PROJECT env. variable is not set")
 endif()
 
+option(IDC_INDEX_DATA_GENERATE_PARQUET "Generate idc_index.parquet file" OFF)
+
 set(download_dir "${PROJECT_BINARY_DIR}")
 
 add_custom_command(
   OUTPUT
     ${download_dir}/idc_index.csv.zip
-    #${download_dir}/idc_index.parquet
+    $<$<BOOL:IDC_INDEX_DATA_GENERATE_PARQUET>:${download_dir}/idc_index.parquet>
   COMMAND python ${CMAKE_CURRENT_SOURCE_DIR}/scripts/python/idc_index_data_manager.py
 )
 
 add_custom_target(run_idc_index_data_manager ALL
-  DEPENDS ${download_dir}/idc_index.csv.zip
-  #${download_dir}/idc_index.parquet
+  DEPENDS
+    ${download_dir}/idc_index.csv.zip
+    $<$<BOOL:IDC_INDEX_DATA_GENERATE_PARQUET>:${download_dir}/idc_index.parquet>
 )
 
-install(FILES ${download_dir}/idc_index.csv.zip DESTINATION "idc_index_data")
-#install(FILES ${download_dir}/idc_index.parquet DESTINATION "idc_index_data")
+install(
+  FILES
+    ${download_dir}/idc_index.csv.zip
+    $<$<BOOL:IDC_INDEX_DATA_GENERATE_PARQUET>:${download_dir}/idc_index.parquet>
+  DESTINATION "idc_index_data")
diff --git a/src/idc_index_data/__init__.py b/src/idc_index_data/__init__.py
@@ -23,16 +23,23 @@
 ]
 
 
-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_PARQUET_FILEPATH: Path = _lookup("idc_index_data/idc_index.parquet")
+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
+)
diff --git a/tests/test_package.py b/tests/test_package.py
@@ -10,7 +10,10 @@ def test_version():
 
 
 def test_filepath():
+    assert 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"
-    # assert m.IDC_INDEX_PARQUET_FILEPATH.is_file()
-    # assert m.IDC_INDEX_PARQUET_FILEPATH.name == "idc_index.parquet"
+
+    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"