Add --bids-database-dir parameter (PennLINC#1116)

xcp_d/cli/parser.py

@@ -150,6 +150,16 @@ def _bids_filter(value, parser):
             "filtering-inputs-with-bids-filter-files"
         ),
     )
+    g_bids.add_argument(
+        "--bids-database-dir",
+        metavar="PATH",
+        type=Path,
+        help=(
+            "Path to a PyBIDS database folder, for faster indexing "
+            "(especially useful for large datasets). "
+            "Will be created if not present."
+        ),
+    )
 
     g_surfx = parser.add_argument_group("Options for CIFTI processing")
     g_surfx.add_argument(

xcp_d/config.py

@@ -461,10 +461,10 @@ def init(cls):
                     )
                 ),
             ]
-            if cls.participant_label:
+            if cls.participant_label and cls.bids_database_dir is None:
                 # Ignore any subjects who aren't the requested ones.
                 ignore_patterns.append(
-                    re.compile(r"sub-(?!" + "|".join(cls.participant_label) + r")\w+")
+                    re.compile(r"sub-(?!(" + "|".join(cls.participant_label) + r")(\b|_))")
                 )
 
             _indexer = BIDSLayoutIndexer(

xcp_d/tests/tests.py

@@ -56,6 +56,8 @@ def mock_config():
     config.execution.work_dir = Path(mkdtemp())
     config.execution.fmri_dir = Path(doc.download_example_data(out_dir=mkdtemp()))
     config.execution.xcp_d_dir = Path(mkdtemp())
+    config.execution.bids_database_dir = None
+    config.execution._layout = None
     config.execution.init()
 
     yield