Add 'exclude' field

bids2table/__main__.py

@@ -54,6 +54,12 @@ def main():
         default=0,
         help="Increase verbosity level.",
     )
+    parser.add_argument(
+        "--exclude", 
+        nargs='*',
+        default=None,
+        help="List of directory names or glob patterns to exclude from indexing.",
+    )
 
     args = parser.parse_args()
 
@@ -68,6 +74,7 @@ def main():
         overwrite=args.overwrite,
         workers=args.workers,
         worker_id=args.worker_id,
+        exclude=args.exclude,
         return_table=False,
     )
 

bids2table/_b2t.py

@@ -1,7 +1,7 @@
 import logging
 from functools import partial
 from pathlib import Path
-from typing import Optional
+from typing import List, Optional
 
 from elbow.builders import build_parquet, build_table
 from elbow.sources.filesystem import Crawler
@@ -19,6 +19,7 @@ def bids2table(
     with_meta: bool = True,
     persistent: bool = False,
     index_path: Optional[StrOrPath] = None,
+    exclude: Optional[List[str]] = None,
     incremental: bool = False,
     overwrite: bool = False,
     workers: Optional[int] = None,
@@ -35,6 +36,7 @@ def bids2table(
         persistent: whether to save index to disk as a Parquet dataset
         index_path: path to BIDS Parquet index to generate or load. Defaults to `root /
             "index.b2t"`. Index generation requires `persistent=True`.
+        exclude: Optional list of directory names to exclude from indexing.
         incremental: update index incrementally with only new or changed files.
         overwrite: overwrite previous index.
         workers: number of parallel processes. If `None` or 1, run in the main
@@ -56,15 +58,18 @@ def bids2table(
     root = Path(root).expanduser().resolve()
     if not root.is_dir():
         raise FileNotFoundError(f"root directory {root} does not exists")
-
+
+    if exclude is None:
+        exclude = []
+
     source = Crawler(
         root=root,
         include=["sub-*"],  # find subject dirs
-        skip=["sub-*"],  # but don't crawl into subject dirs
+        skip=["sub-*"] + exclude,  # but don't crawl into subject dirs
         dirs_only=True,
         follow_links=True,
     )
-    extract = partial(extract_bids_subdir, with_meta=with_meta)
+    extract = partial(extract_bids_subdir, exclude=exclude, with_meta=with_meta)
 
     if index_path is None:
         index_path = root / "index.b2t"

bids2table/extractors/bids.py

@@ -1,10 +1,11 @@
 import logging
 from glob import iglob
 from pathlib import Path
-from typing import Generator, Optional
+from typing import Generator, List, Optional
 
 from elbow.extractors import extract_file_meta
 from elbow.record import Record, concat
+from elbow.sources.filesystem import Crawler
 from elbow.typing import StrOrPath
 
 from bids2table.entities import BIDSEntities
@@ -42,12 +43,21 @@ def extract_bids_file(path: StrOrPath, with_meta: bool = True) -> Optional[Recor
 
 
 def extract_bids_subdir(
-    path: StrOrPath, with_meta: bool = True
+    path: StrOrPath, exclude: List[str],
+    with_meta: bool = True
 ) -> Generator[Optional[Record], None, None]:
     """
     Extract BIDS records recursively for all files in a sub-directory.
     """
-    for path in iglob(str(Path(path) / "**"), recursive=True):
+
+    # replace glob with crawler
+    source = Crawler(
+        root=path,
+        skip=exclude,
+        follow_links=True,
+    )
+
+    for path in source:
         yield extract_bids_file(path, with_meta=with_meta)
 
 

tests/test_bids2table.py

@@ -61,6 +61,18 @@ def test_bids2table_nonexist(tmp_path: Path):
     with pytest.raises(FileNotFoundError):
         bids2table(root=tmp_path / "nonexistent_dataset")
 
+def test_bids2table_exclude(tmp_path: Path):
+    root = BIDS_EXAMPLES / "ds001"
+    index_path = tmp_path / "index_exclude.b2t"
+    exclude_list = ["anat"]
+
+    tab = bids2table(
+        root=root, with_meta=True, persistent=True, index_path=index_path, exclude=exclude_list
+    )
+
+    # Check that the excluded strings are not in the indexed table
+    assert 'ent__datatype' in tab.columns
+    assert 'anat' not in tab['ent__datatype'].values
 
 if __name__ == "__main__":
     pytest.main([__file__])