junifer 0.0.5.dev93__py3-none-any.whl → 0.0.5.dev110__py3-none-any.whl

junifer/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.5.dev93'
-__version_tuple__ = version_tuple = (0, 0, 5, 'dev93')
+__version__ = version = '0.0.5.dev110'
+__version_tuple__ = version_tuple = (0, 0, 5, 'dev110')

junifer/datagrabber/aomic/id1000.py

@@ -24,8 +24,8 @@ class DataladAOMICID1000(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     native_t1w : bool, optional
@@ -112,6 +112,39 @@ class DataladAOMICID1000(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

junifer/datagrabber/aomic/piop1.py

@@ -26,8 +26,8 @@ class DataladAOMICPIOP1(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     tasks : {"restingstate", "anticipation", "emomatching", "faces", \
@@ -147,6 +147,39 @@ class DataladAOMICPIOP1(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

junifer/datagrabber/aomic/piop2.py

@@ -26,8 +26,8 @@ class DataladAOMICPIOP2(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     tasks : {"restingstate", "stopsignal", "workingmemory"} or \
@@ -144,6 +144,39 @@ class DataladAOMICPIOP2(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

junifer/datagrabber/aomic/tests/test_id1000.py

@@ -7,7 +7,7 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from typing import List, Union
+from typing import List, Optional, Union
 
 import pytest
 
@@ -17,112 +17,58 @@ from junifer.datagrabber.aomic.id1000 import DataladAOMICID1000
 URI = "https://gin.g-node.org/juaml/datalad-example-aomic1000"
 
 
-def test_DataladAOMICID1000() -> None:
-    """Test DataladAOMICID1000 DataGrabber."""
-    dg = DataladAOMICID1000()
+@pytest.mark.parametrize(
+    "type_, nested_types",
+    [
+        ("BOLD", ["confounds", "mask"]),
+        ("T1w", ["mask"]),
+        ("VBM_CSF", None),
+        ("VBM_GM", None),
+        ("VBM_WM", None),
+        ("DWI", None),
+        ("FreeSurfer", None),
+    ],
+)
+def test_DataladAOMICID1000(
+    type_: str,
+    nested_types: Optional[List[str]],
+) -> None:
+    """Test DataladAOMICID1000 DataGrabber.
+
+    Parameters
+    ----------
+    type_ : str
+        The parametrized type.
+    nested_types : list of str or None
+        The parametrized nested types.
+
+    """
+    dg = DataladAOMICID1000(types=type_)
     # Set URI to Gin
     dg.uri = URI
 
     with dg:
+        # Get all elements
         all_elements = dg.get_elements()
+        # Get test element
         test_element = all_elements[0]
-
+        # Get test element data
         out = dg[test_element]
-
-        # asserts type "BOLD"
-        assert "BOLD" in out
-
-        assert (
-            out["BOLD"]["path"].name == f"{test_element}_task-moviewatching_"
-            "space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz"
-        )
-
-        assert out["BOLD"]["path"].exists()
-        assert out["BOLD"]["path"].is_file()
-
-        # asserts type BOLD.confounds
-        assert "confounds" in out["BOLD"]
-
-        assert (
-            out["BOLD"]["confounds"]["path"].name
-            == f"{test_element}_task-moviewatching_"
-            "desc-confounds_regressors.tsv"
-        )
-
-        assert out["BOLD"]["confounds"]["path"].exists()
-        assert out["BOLD"]["confounds"]["path"].is_file()
-
-        # assert BOLD.mask
-        assert out["BOLD"]["mask"]["path"].exists()
-
-        # asserts type "T1w"
-        assert "T1w" in out
-
-        assert (
-            out["T1w"]["path"].name
-            == f"{test_element}_space-MNI152NLin2009cAsym_"
-            "desc-preproc_T1w.nii.gz"
-        )
-
-        assert out["T1w"]["path"].exists()
-        assert out["T1w"]["path"].is_file()
-
-        # asserts T1w.mask
-        assert out["T1w"]["mask"]["path"].exists()
-
-        # asserts type "VBM_CSF"
-        assert "VBM_CSF" in out
-
-        assert (
-            out["VBM_CSF"]["path"].name
-            == f"{test_element}_space-MNI152NLin2009cAsym_label-"
-            "CSF_probseg.nii.gz"
-        )
-
-        assert out["VBM_CSF"]["path"].exists()
-        assert out["VBM_CSF"]["path"].is_file()
-
-        # asserts type "VBM_GM"
-        assert "VBM_GM" in out
-
-        assert (
-            out["VBM_GM"]["path"].name
-            == f"{test_element}_space-MNI152NLin2009cAsym_label-"
-            "GM_probseg.nii.gz"
-        )
-
-        assert out["VBM_GM"]["path"].exists()
-        assert out["VBM_GM"]["path"].is_file()
-
-        # asserts type "VBM_WM"
-        assert "VBM_WM" in out
-
-        assert (
-            out["VBM_WM"]["path"].name
-            == f"{test_element}_space-MNI152NLin2009cAsym_label-"
-            "WM_probseg.nii.gz"
-        )
-
-        assert out["VBM_WM"]["path"].exists()
-        assert out["VBM_WM"]["path"].is_file()
-
-        # asserts type "DWI"
-        assert "DWI" in out
-
-        assert (
-            out["DWI"]["path"].name
-            == f"{test_element}_desc-preproc_dwi.nii.gz"
-        )
-
-        assert out["DWI"]["path"].exists()
-        assert out["DWI"]["path"].is_file()
-
-        # asserts meta
-        assert "meta" in out["BOLD"]
-        meta = out["BOLD"]["meta"]
+        # Assert data type
+        assert type_ in out
+        assert out[type_]["path"].exists()
+        assert out[type_]["path"].is_file()
+        # Asserts data type metadata
+        assert "meta" in out[type_]
+        meta = out[type_]["meta"]
         assert "element" in meta
         assert "subject" in meta["element"]
         assert test_element == meta["element"]["subject"]
+        # Assert nested data type if not None
+        if nested_types is not None:
+            for nested_type in nested_types:
+                assert out[type_][nested_type]["path"].exists()
+                assert out[type_][nested_type]["path"].is_file()
 
 
 @pytest.mark.parametrize(

junifer/datagrabber/aomic/tests/test_piop1.py

@@ -18,129 +18,87 @@ URI = "https://gin.g-node.org/juaml/datalad-example-aomicpiop1"
 
 
 @pytest.mark.parametrize(
-    "tasks",
-    [None, "restingstate"],
+    "type_, nested_types, tasks",
+    [
+        ("BOLD", ["confounds", "mask"], None),
+        ("BOLD", ["confounds", "mask"], ["anticipation"]),
+        ("BOLD", ["confounds", "mask"], ["emomatching", "faces"]),
+        ("BOLD", ["confounds", "mask"], ["restingstate"]),
+        ("BOLD", ["confounds", "mask"], ["workingmemory", "gstroop"]),
+        (
+            "BOLD",
+            ["confounds", "mask"],
+            ["anticipation", "faces", "restingstate"],
+        ),
+        ("T1w", ["mask"], None),
+        ("VBM_CSF", None, None),
+        ("VBM_GM", None, None),
+        ("VBM_WM", None, None),
+        ("DWI", None, None),
+        ("FreeSurfer", None, None),
+    ],
 )
-def test_DataladAOMICPIOP1(tasks: Optional[str]) -> None:
+def test_DataladAOMICPIOP1(
+    type_: str,
+    nested_types: Optional[List[str]],
+    tasks: Optional[List[str]],
+) -> None:
     """Test DataladAOMICPIOP1 DataGrabber.
 
     Parameters
     ----------
-    tasks : str or None
+    type_ : str
+        The parametrized type.
+    nested_types : list of str or None
+        The parametrized nested types.
+    tasks : list of str or None
         The parametrized task values.
 
     """
-    dg = DataladAOMICPIOP1(tasks=tasks)
+    dg = DataladAOMICPIOP1(types=type_, tasks=tasks)
     # Set URI to Gin
     dg.uri = URI
 
     with dg:
+        # Get all elements
         all_elements = dg.get_elements()
+        # Get test element
         test_element = all_elements[0]
-        sub, task = test_element
-
+        # Get test element data
         out = dg[test_element]
-
-        # asserts type "BOLD"
-        assert "BOLD" in out
-
-        # depending on task 'acquisition is different'
-        task_acqs = {
-            "anticipation": "seq",
-            "emomatching": "seq",
-            "faces": "mb3",
-            "gstroop": "seq",
-            "restingstate": "mb3",
-            "workingmemory": "seq",
-        }
-        acq = task_acqs[task]
-        new_task = f"{task}_acq-{acq}"
-        assert (
-            out["BOLD"]["path"].name == f"{sub}_task-{new_task}_"
-            "space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz"
-        )
-
-        assert out["BOLD"]["path"].exists()
-        assert out["BOLD"]["path"].is_file()
-
-        # asserts type BOLD.confounds
-        assert "confounds" in out["BOLD"]
-
-        assert (
-            out["BOLD"]["confounds"]["path"].name == f"{sub}_task-{new_task}_"
-            "desc-confounds_regressors.tsv"
-        )
-
-        assert out["BOLD"]["confounds"]["path"].exists()
-        assert out["BOLD"]["confounds"]["path"].is_file()
-
-        # assert BOLD.mask
-        assert out["BOLD"]["mask"]["path"].exists()
-
-        # asserts type "T1w"
-        assert "T1w" in out
-
-        assert (
-            out["T1w"]["path"].name == f"{sub}_space-MNI152NLin2009cAsym_"
-            "desc-preproc_T1w.nii.gz"
-        )
-
-        assert out["T1w"]["path"].exists()
-        assert out["T1w"]["path"].is_file()
-
-        # asserts T1w.mask
-        assert out["T1w"]["mask"]["path"].exists()
-
-        # asserts type "VBM_CSF"
-        assert "VBM_CSF" in out
-
-        assert (
-            out["VBM_CSF"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "CSF_probseg.nii.gz"
-        )
-
-        assert out["VBM_CSF"]["path"].exists()
-        assert out["VBM_CSF"]["path"].is_file()
-
-        # asserts type "VBM_GM"
-        assert "VBM_GM" in out
-
-        assert (
-            out["VBM_GM"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "GM_probseg.nii.gz"
-        )
-
-        assert out["VBM_GM"]["path"].exists()
-        assert out["VBM_GM"]["path"].is_file()
-
-        # asserts type "VBM_WM"
-        assert "VBM_WM" in out
-
-        assert (
-            out["VBM_WM"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "WM_probseg.nii.gz"
-        )
-
-        assert out["VBM_WM"]["path"].exists()
-        assert out["VBM_WM"]["path"].is_file()
-
-        # asserts type "DWI"
-        assert "DWI" in out
-
-        assert out["DWI"]["path"].name == f"{sub}_desc-preproc_dwi.nii.gz"
-
-        assert out["DWI"]["path"].exists()
-        assert out["DWI"]["path"].is_file()
-
-        # asserts meta
-        assert "meta" in out["BOLD"]
-        meta = out["BOLD"]["meta"]
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Assert data type
+        assert type_ in out
+        # Check task name if BOLD
+        if type_ == "BOLD" and tasks is not None:
+            # Depending on task 'acquisition is different'
+            task_acqs = {
+                "anticipation": "seq",
+                "emomatching": "seq",
+                "faces": "mb3",
+                "gstroop": "seq",
+                "restingstate": "mb3",
+                "workingmemory": "seq",
+            }
+            assert task_acqs[test_element[1]] in out[type_]["path"].name
+        assert out[type_]["path"].exists()
+        assert out[type_]["path"].is_file()
+        # Asserts data type metadata
+        assert "meta" in out[type_]
+        meta = out[type_]["meta"]
         assert "element" in meta
         assert "subject" in meta["element"]
-        assert sub == meta["element"]["subject"]
+        assert test_element[0] == meta["element"]["subject"]
+        # Assert nested data type if not None
+        if nested_types is not None:
+            for nested_type in nested_types:
+                assert out[type_][nested_type]["path"].exists()
+                assert out[type_][nested_type]["path"].is_file()
 
 
 @pytest.mark.parametrize(

junifer/datagrabber/aomic/tests/test_piop2.py

@@ -18,123 +18,67 @@ URI = "https://gin.g-node.org/juaml/datalad-example-aomicpiop2"
 
 
 @pytest.mark.parametrize(
-    "tasks",
-    [None, "restingstate"],
+    "type_, nested_types, tasks",
+    [
+        ("BOLD", ["confounds", "mask"], None),
+        ("BOLD", ["confounds", "mask"], ["restingstate"]),
+        ("BOLD", ["confounds", "mask"], ["restingstate", "stopsignal"]),
+        ("BOLD", ["confounds", "mask"], ["workingmemory", "stopsignal"]),
+        ("BOLD", ["confounds", "mask"], ["workingmemory"]),
+        ("T1w", ["mask"], None),
+        ("VBM_CSF", None, None),
+        ("VBM_GM", None, None),
+        ("VBM_WM", None, None),
+        ("DWI", None, None),
+        ("FreeSurfer", None, None),
+    ],
 )
-def test_DataladAOMICPIOP2(tasks: Optional[str]) -> None:
+def test_DataladAOMICPIOP2(
+    type_: str,
+    nested_types: Optional[List[str]],
+    tasks: Optional[List[str]],
+) -> None:
     """Test DataladAOMICPIOP2 DataGrabber.
 
     Parameters
     ----------
-    tasks : str or None
+    type_ : str
+        The parametrized type.
+    nested_types : list of str or None
+        The parametrized nested types.
+    tasks : list of str or None
         The parametrized task values.
 
     """
-    dg = DataladAOMICPIOP2(tasks=tasks)
+    dg = DataladAOMICPIOP2(types=type_, tasks=tasks)
     # Set URI to Gin
     dg.uri = URI
 
     with dg:
+        # Get all elements
         all_elements = dg.get_elements()
-
-        if tasks == "restingstate":
-            for el in all_elements:
-                assert el[1] == "restingstate"
-
+        # Get test element
         test_element = all_elements[0]
-        sub, task = test_element
+        # Get test element data
         out = dg[test_element]
-
-        # asserts type "BOLD"
-        assert "BOLD" in out
-
-        new_task = f"{task}_acq-seq"
-        assert (
-            out["BOLD"]["path"].name == f"{sub}_task-{new_task}_"
-            "space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz"
-        )
-
-        assert out["BOLD"]["path"].exists()
-        assert out["BOLD"]["path"].is_file()
-
-        # asserts type BOLD.confounds
-        assert "confounds" in out["BOLD"]
-
-        assert (
-            out["BOLD"]["confounds"]["path"].name == f"{sub}_task-{new_task}_"
-            "desc-confounds_regressors.tsv"
-        )
-
-        assert out["BOLD"]["confounds"]["path"].exists()
-        assert out["BOLD"]["confounds"]["path"].is_file()
-
-        # assert BOLD.mask
-        assert out["BOLD"]["mask"]["path"].exists()
-
-        # asserts type "T1w"
-        assert "T1w" in out
-
-        assert (
-            out["T1w"]["path"].name == f"{sub}_space-MNI152NLin2009cAsym_"
-            "desc-preproc_T1w.nii.gz"
-        )
-
-        assert out["T1w"]["path"].exists()
-        assert out["T1w"]["path"].is_file()
-
-        # asserts T1w.mask
-        assert out["T1w"]["mask"]["path"].exists()
-
-        # asserts type "VBM_CSF"
-        assert "VBM_CSF" in out
-
-        assert (
-            out["VBM_CSF"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "CSF_probseg.nii.gz"
-        )
-
-        assert out["VBM_CSF"]["path"].exists()
-        assert out["VBM_CSF"]["path"].is_file()
-
-        # asserts type "VBM_GM"
-        assert "VBM_GM" in out
-
-        assert (
-            out["VBM_GM"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "GM_probseg.nii.gz"
-        )
-
-        assert out["VBM_GM"]["path"].exists()
-        assert out["VBM_GM"]["path"].is_file()
-
-        # asserts type "VBM_WM"
-        assert "VBM_WM" in out
-
-        assert (
-            out["VBM_WM"]["path"].name
-            == f"{sub}_space-MNI152NLin2009cAsym_label-"
-            "WM_probseg.nii.gz"
-        )
-
-        assert out["VBM_WM"]["path"].exists()
-        assert out["VBM_WM"]["path"].is_file()
-
-        # asserts type "DWI"
-        assert "DWI" in out
-
-        assert out["DWI"]["path"].name == f"{sub}_desc-preproc_dwi.nii.gz"
-
-        assert out["DWI"]["path"].exists()
-        assert out["DWI"]["path"].is_file()
-
-        # asserts meta
-        assert "meta" in out["BOLD"]
-        meta = out["BOLD"]["meta"]
+        # Assert data type
+        assert type_ in out
+        # Check task name if BOLD
+        if type_ == "BOLD" and tasks is not None:
+            assert test_element[1] in out[type_]["path"].name
+        assert out[type_]["path"].exists()
+        assert out[type_]["path"].is_file()
+        # Asserts data type metadata
+        assert "meta" in out[type_]
+        meta = out[type_]["meta"]
         assert "element" in meta
         assert "subject" in meta["element"]
-        assert sub == meta["element"]["subject"]
+        assert test_element[0] == meta["element"]["subject"]
+        # Assert nested data type if not None
+        if nested_types is not None:
+            for nested_type in nested_types:
+                assert out[type_][nested_type]["path"].exists()
+                assert out[type_][nested_type]["path"].is_file()
 
 
 @pytest.mark.parametrize(

junifer/datagrabber/pattern.py

@@ -214,18 +214,25 @@ class PatternDataGrabber(BaseDataGrabber):
         t_replacements = [
             x for x in self.replacements if f"{{{x}}}" in pattern
         ]
-
+        # Ops on re_pattern
+        # Remove negated unix glob pattern i.e., [!...] for re_pattern
+        re_pattern = re.sub(r"\[!.?\]", "", re_pattern)
+        # Remove enclosing square brackets from unix glob pattern i.e., [...]
+        # for re_pattern
+        re_pattern = re.sub(r"\[|\]", "", re_pattern)
+        # Iteratively replace the first of each with a named group definition
         for t_r in t_replacements:
-            # Replace the first of each with a named group definition
             re_pattern = re_pattern.replace(f"{{{t_r}}}", f"(?P<{t_r}>.*)", 1)
-
+        # Iteratively replace the second appearance of each with the named
+        # group back reference
         for t_r in t_replacements:
-            # Replace the second appearance of each with the named group
-            # back reference
             re_pattern = re_pattern.replace(f"{{{t_r}}}", f"(?P={t_r})")
-
+        # Ops on glob_pattern
+        # Iteratively replace replacements with wildcard i.e., *
+        # for glob_pattern
         for t_r in t_replacements:
             glob_pattern = glob_pattern.replace(f"{{{t_r}}}", "*")
+
         return re_pattern, glob_pattern, t_replacements
 
     def _replace_patterns_glob(self, element: Dict, pattern: str) -> str:
@@ -254,6 +261,10 @@ class PatternDataGrabber(BaseDataGrabber):
                 f"The element keys must be {self.replacements}, "
                 f"element has {list(element.keys())}."
             )
+        # Remove negated unix glob pattern i.e., [!...]
+        pattern = re.sub(r"\[!.?\]", "", pattern)
+        # Remove enclosing square brackets from unix glob pattern i.e., [...]
+        pattern = re.sub(r"\[|\]", "", pattern)
         return pattern.format(**element)
 
     def _get_path_from_patterns(

junifer/datagrabber/tests/test_pattern.py

@@ -236,6 +236,51 @@ def test_PatternDataGrabber(tmp_path: Path) -> None:
     assert out1["VBM_GM"]["path"] != out2["VBM_GM"]["path"]
 
 
+def test_PatternDataGrabber_unix_path_expansion(tmp_path: Path) -> None:
+    """Test PatterDataGrabber for patterns with unix path expansion.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+
+    """
+    # Create test data root dir
+    freesurfer_dir = tmp_path / "derivatives" / "freesurfer"
+    freesurfer_dir.mkdir(parents=True, exist_ok=True)
+    # Create test data sub dirs and files
+    for dir_name in ["fsaverage", "sub-0001"]:
+        mri_dir = freesurfer_dir / dir_name / "mri"
+        mri_dir.mkdir(parents=True, exist_ok=True)
+        # Create files
+        (mri_dir / "T1.mgz").touch(exist_ok=True)
+        (mri_dir / "aseg.mgz").touch(exist_ok=True)
+    # Create datagrabber
+    dg = PatternDataGrabber(
+        datadir=tmp_path,
+        types=["FreeSurfer"],
+        patterns={
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+            },
+        },
+        replacements=["subject"],
+    )
+    # Check that "fsaverage" is filtered
+    elements = dg.get_elements()
+    assert elements == ["sub-0001"]
+    # Fetch data
+    out = dg["sub-0001"]
+    # Check paths are found
+    assert set(out["FreeSurfer"].keys()) == {"path", "aseg", "meta"}
+    assert list(out["FreeSurfer"]["aseg"].keys()) == ["path"]
+
+
 def test_PatternDataGrabber_confounds_format_error_on_init() -> None:
     """Test PatterDataGrabber confounds format error on initialisation."""
     with pytest.raises(

junifer/datagrabber/utils.py

@@ -53,6 +53,17 @@ PATTERNS_SCHEMA = {
         "mandatory": ["pattern"],
         "optional": {},
     },
+    "FreeSurfer": {
+        "mandatory": ["pattern"],
+        "optional": {
+            "aseg": {"mandatory": ["pattern"], "optional": []},
+            "norm": {"mandatory": ["pattern"], "optional": []},
+            "lh_white": {"mandatory": ["pattern"], "optional": []},
+            "rh_white": {"mandatory": ["pattern"], "optional": []},
+            "lh_pial": {"mandatory": ["pattern"], "optional": []},
+            "rh_pial": {"mandatory": ["pattern"], "optional": []},
+        },
+    },
 }
 
 

junifer/datareader/default.py

@@ -103,8 +103,8 @@ class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
             params = {}
         # For each type of data, try to read it
         for type_key, type_val in input.items():
-            # Skip Warp data type
-            if type_key == "Warp":
+            # Skip Warp and FreeSurfer data type
+            if type_key in ["Warp", "FreeSurfer"]:
                 continue
 
             # Check for malformed datagrabber specification

{junifer-0.0.5.dev93.dist-info → junifer-0.0.5.dev110.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.5.dev93
+Version: 0.0.5.dev110
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

{junifer-0.0.5.dev93.dist-info → junifer-0.0.5.dev110.dist-info}/RECORD

@@ -1,5 +1,5 @@
 junifer/__init__.py,sha256=x1UR2jUcrUdm2HNl-3Qvyi4UUrU6ms5qm2qcmNY7zZk,391
-junifer/_version.py,sha256=OuEXOAHKhbHnm8jc8By5AoScd2qmQjT4HRDoRe1JlYM,426
+junifer/_version.py,sha256=0CYyZtK7X8YB7AsyaklZtJl2q0LTvCx3UPEiwmdAmQU,428
 junifer/stats.py,sha256=jN22_qFvWYBU9ZIMnCSzN4iOscWnWrcrUPIdLeDkV64,6163
 junifer/api/__init__.py,sha256=pSj8V8tmwOAQ3sshWJfRfB-n3z5bcJj3pHOBX4-8ONc,251
 junifer/api/cli.py,sha256=53pews3mXkJ7DUDSkV51PbitYnuVAdQRkWG-gjO08Uw,16142
@@ -94,16 +94,16 @@ junifer/datagrabber/base.py,sha256=KgMSKfkwd4yLW4PhoJDoWMgcDkGmDoIs6jkgKyOJd9A,6
 junifer/datagrabber/datalad_base.py,sha256=gP-DsyCd2F8W-aF2PXOg99Ntp2bj8QEtb535y06q39o,11009
 junifer/datagrabber/dmcc13_benchmark.py,sha256=se9F6QVw9WX22MNld33OQv_BtdW-yPvXXu6kYykxLNw,12225
 junifer/datagrabber/multiple.py,sha256=eXQIsvSNvD8GuEITjMaMoi1GwoeyWXXbQMRi-f2qgc4,4923
-junifer/datagrabber/pattern.py,sha256=w1aTL5xZRH9vq3-RofdmW-d_1t2OrAKRL0McCQErHGE,15273
+junifer/datagrabber/pattern.py,sha256=4OcGSCwBpeQOj6_YZohJjRFC_L69y7MAKsoE4-XO2So,15949
 junifer/datagrabber/pattern_datalad.py,sha256=R3LMeknT7tAXs2AN0XVPRf6tGkCMPgDfkNT2bfi7UNc,4526
-junifer/datagrabber/utils.py,sha256=s0Ife1qKEwXP47GfoxQ0qGqSP8L8ZNAms3HAvrSFoGI,9406
+junifer/datagrabber/utils.py,sha256=2ujwltVc__qPJ2RwnEhSSoC_RkDchGEBNw7bC0a3bvk,9898
 junifer/datagrabber/aomic/__init__.py,sha256=R7yrRVBWsBW25CH0fw-KHpFwb_EC-MlPKDzssGfj5A0,281
-junifer/datagrabber/aomic/id1000.py,sha256=DGQVMgSv8HoUH6qj_WnBQTMunaJNSlVihjfiCmICN2c,5963
-junifer/datagrabber/aomic/piop1.py,sha256=CR4L9VJk-lJnoYTJDOAzs39Z_fgFQAYt2pvAmKfGl-g,8382
-junifer/datagrabber/aomic/piop2.py,sha256=_vrUnFyfhwFjWR3O23-ksVXlj49rc-q-eK1lVytIquo,8001
-junifer/datagrabber/aomic/tests/test_id1000.py,sha256=jKkhvglMsvEK06sSJXj4vuFvH2YR9CfEbcnElX_HU-o,4683
-junifer/datagrabber/aomic/tests/test_piop1.py,sha256=GuNllX8VbEbpGsPcEWf3ssRzcSrIj4RlLCFfTsbF-tU,5449
-junifer/datagrabber/aomic/tests/test_piop2.py,sha256=ydQhrF4fQsp6j6M79p68r8SKmDcwHwQccLKDW4lbztI,5248
+junifer/datagrabber/aomic/id1000.py,sha256=2Lhu3Wf-U3RRLgoWbrSQCGxfri3--OQTsk9nrowK5G4,7184
+junifer/datagrabber/aomic/piop1.py,sha256=r_OsORrVAU6mbOxuergIxo0ZR0Msx_I8MyrfiT_gD3E,9603
+junifer/datagrabber/aomic/piop2.py,sha256=Twu2yN4-h-aR3-ZCg0ERxI54HGxr6C64cmBo6Nq3TAI,9222
+junifer/datagrabber/aomic/tests/test_id1000.py,sha256=AWacDroSxvRjzozFjyRlDpiJpPflYRfhDm_RANrYAKM,3283
+junifer/datagrabber/aomic/tests/test_piop1.py,sha256=J9ei2HLzdJPciysWjRo33cbZsqPF1OEDySmQWWNvYuM,4820
+junifer/datagrabber/aomic/tests/test_piop2.py,sha256=Bk23KvRse4clMTuC88YntSfJnJyTunafC79Y1OJwJI0,4166
 junifer/datagrabber/hcp1200/__init__.py,sha256=zy4Qq1_m3vECEhioG-UDteco2b5cni_8xuElICaRtt4,189
 junifer/datagrabber/hcp1200/datalad_hcp1200.py,sha256=p5Bbg09qoM46km9eFSlspwLwOe6LMJFSIZ9NC9E2lmc,2432
 junifer/datagrabber/hcp1200/hcp1200.py,sha256=ohXHmrQHWjqRZSEXI6E5zla1d_t6LZTbv-cAj79w3PU,6091
@@ -113,10 +113,10 @@ junifer/datagrabber/tests/test_datagrabber_utils.py,sha256=x1nqFiHI9xHBQFwXji0DP
 junifer/datagrabber/tests/test_datalad_base.py,sha256=SYxUB9_4YPMfrb7iJM-aJCWbGa3EJfYz31wAUCNa03s,16285
 junifer/datagrabber/tests/test_dmcc13_benchmark.py,sha256=DcqkDXXBoabHFVbxekGR2NZyGeugGlxpOwXIwy38Ofg,9109
 junifer/datagrabber/tests/test_multiple.py,sha256=Mx3xfDrQiWG2W5MW24P5L2XiSeALpJ2-jFlzWkKtu9w,5659
-junifer/datagrabber/tests/test_pattern.py,sha256=Zmwg79f-qs6AEPVoFpooOquK7rm1hsmgkzuo11BG5PE,8019
+junifer/datagrabber/tests/test_pattern.py,sha256=H55jYRPfT3rMsoIQOAnWJgw3nGrkU7m2xFa3-ed6NQE,9527
 junifer/datagrabber/tests/test_pattern_datalad.py,sha256=hxw_aXBwHjUo-aUrHescBA2dn1bSJxh-0oV8495iIEA,6483
 junifer/datareader/__init__.py,sha256=_vtrLX_vxlHFD90gPa3gWnhTuvfWM7Uzyj6y8ZPaWm8,259
-junifer/datareader/default.py,sha256=_ntvkcF0H089bHwj0VOLTKWp8RvP7qy2HyieWHuRp2c,6680
+junifer/datareader/default.py,sha256=Md2q0hjoh454F-fmFFlyzwZMcu9vmFFT-akR42SSwUs,6711
 junifer/datareader/tests/test_default_reader.py,sha256=9dPZSkba1YQjFsA0XwdUbx5sq8DVIEZoy_WfMAcvRus,5220
 junifer/external/__init__.py,sha256=CBB7eQul2hf-WWwT_PYFV1MS9KkXlZBO7oQWWVLgB_I,110
 junifer/external/h5io/h5io/__init__.py,sha256=LG7ru_Rt3EOE2H4PGYfBhC12Iax3yeTquZkd8TICiKk,469
@@ -253,10 +253,10 @@ junifer/utils/logging.py,sha256=furcU3XIUpUvnpe4PEwzWWIWgmH4j2ZA4MQdvSGWjj0,9216
 junifer/utils/tests/test_fs.py,sha256=WQS7cKlKEZ742CIuiOYYpueeAhY9PqlastfDVpVVtvE,923
 junifer/utils/tests/test_helpers.py,sha256=k5qqfxK8dFyuewTJyR1Qn6-nFaYNuVr0ysc18bfPjyU,929
 junifer/utils/tests/test_logging.py,sha256=l8oo-AiBV7H6_IzlsNcj__cLeZBUvgIGoaMszD9VaJg,7754
-junifer-0.0.5.dev93.dist-info/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
-junifer-0.0.5.dev93.dist-info/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
-junifer-0.0.5.dev93.dist-info/METADATA,sha256=GPQBJL5Fvtivl1q6VYeAV6eoIDVCjubyMZCizh3mn9k,8234
-junifer-0.0.5.dev93.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-junifer-0.0.5.dev93.dist-info/entry_points.txt,sha256=DxFvKq0pOqRunAK0FxwJcoDfV1-dZvsFDpD5HRqSDhw,48
-junifer-0.0.5.dev93.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
-junifer-0.0.5.dev93.dist-info/RECORD,,
+junifer-0.0.5.dev110.dist-info/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
+junifer-0.0.5.dev110.dist-info/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
+junifer-0.0.5.dev110.dist-info/METADATA,sha256=SgyLdexnard9sSn0O75ZjN0DxjMCQ8tElN68xB8KNtw,8235
+junifer-0.0.5.dev110.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+junifer-0.0.5.dev110.dist-info/entry_points.txt,sha256=DxFvKq0pOqRunAK0FxwJcoDfV1-dZvsFDpD5HRqSDhw,48
+junifer-0.0.5.dev110.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
+junifer-0.0.5.dev110.dist-info/RECORD,,