Implements the participants table in the bidsmap (GitHub issue #253)

bidscoin/__init__.py

@@ -207,6 +207,7 @@ def trackusage(event: str, dryrun: bool=False) -> dict:
     except Exception as shelveerror:
         warnings.warn(f"Please report the following error to the developers:\n{shelveerror}: {trackfile}", RuntimeWarning)
         for corruptfile in trackfile.parent.glob(trackfile.name + '.*'):
+            print(f"Deleting corrupt file: {corruptfile}")
             corruptfile.unlink()
         data['event'] = 'trackusage_exception'
 

bidscoin/bcoin.py

@@ -316,7 +316,7 @@ def install_plugins(filenames: list[str]=()) -> None:
         LOGGER.success(f"The '{file.name}' plugin was successfully installed")
 
 
-def uninstall_plugins(filenames: list[str]=(), wipe: bool=True) -> None:
+def uninstall_plugins(filenames: list[str]=(), wipe: bool=False) -> None:
     """
     Uninstalls template bidsmaps and plugins and removes the plugin Options and data format section from the default template bidsmap
 
@@ -358,14 +358,15 @@ def uninstall_plugins(filenames: list[str]=(), wipe: bool=True) -> None:
         if not module:
             LOGGER.warning(f"Cannot remove any {file.stem} bidsmap options from the {bidsmap_template.stem} template")
             continue
-        if hasattr(module, 'OPTIONS') or hasattr(module, 'BIDSMAP'):
-            if hasattr(module, 'OPTIONS'):
-                LOGGER.info(f"Removing default {file.stem} bidsmap options from the {bidsmap_template.stem} template")
-                template['Options']['plugins'].pop(file.stem, None)
-            if wipe and hasattr(module, 'BIDSMAP'):
-                for key, value in module.BIDSMAP.items():
-                    LOGGER.info(f"Removing default {key} bidsmappings from the {bidsmap_template.stem} template")
-                    template.pop(key, None)
+        if removed := hasattr(module, 'OPTIONS'):
+            LOGGER.info(f"Removing default {file.stem} bidsmap options from the {bidsmap_template.stem} template")
+            template['Options']['plugins'].pop(file.stem, None)
+        if wipe and hasattr(module, 'BIDSMAP'):
+            removed = True
+            for key, value in module.BIDSMAP.items():
+                LOGGER.info(f"Removing default {key} bidsmappings from the {bidsmap_template.stem} template")
+                template.pop(key, None)
+        if removed:
             with open(bidsmap_template, 'w') as stream:
                 yaml.dump(template, stream)
 

bidscoin/bids.py

@@ -770,7 +770,7 @@ def __init__(self, dataformat: str, data: dict, options: Options, plugins: Plugi
         Reads from a YAML dataformat dictionary
 
         :param dataformat: The name of the dataformat (= section in the bidsmap)
-        :param data:       The YAML dataformat dictionary, i.e. subject and session items + a set of datatypes
+        :param data:       The YAML dataformat dictionary, i.e. participant items + a set of datatypes
         :param options:    The dictionary with the BIDScoin options
         :param plugins:    The plugin dictionaries with their options
         """
@@ -785,7 +785,7 @@ def __init__(self, dataformat: str, data: dict, options: Options, plugins: Plugi
         self.plugins    = plugins
         """The plugin dictionaries with their options"""
         self._data      = data
-        """The YAML dataformat dictionary, i.e. subject and session items + a set of datatypes"""
+        """The YAML dataformat dictionary, i.e. participant items + a set of datatypes"""
 
     def __str__(self):
 
@@ -808,32 +808,43 @@ def __hash__(self):
 
         return hash(str(self))
 
+    @property
+    def participant(self) -> dict:
+        """The data to populate the participants.tsv table"""
+
+        return self._data['participant']
+
+    @participant.setter
+    def participant(self, value: dict):
+
+        self._data['participant'] = value
+
     @property
     def subject(self) -> str:
         """The regular expression for extracting the subject identifier"""
 
-        return self._data['subject']
+        return self._data['participant']['participant_id']
 
     @subject.setter
     def subject(self, value: str):
 
-        self._data['subject'] = value
+        self._data['participant']['participant_id'] = value
 
     @property
     def session(self) -> str:
         """The regular expression for extracting the session identifier"""
 
-        return self._data['session']
+        return self._data['participant']['session_id']
 
     @session.setter
     def session(self, value: str):
-        self._data['session'] = value
+        self._data['participant']['session_id'] = value
 
     @property
     def datatypes(self) -> list[DataType]:
         """Gets a list of DataType objects for the dataformat"""
 
-        return [DataType(self.dataformat, datatype, self._data[datatype], self.options, self.plugins) for datatype in self._data if datatype not in ('subject', 'session')]
+        return [DataType(self.dataformat, datatype, self._data[datatype], self.options, self.plugins) for datatype in self._data if datatype not in ('participant',)]
 
     def datatype(self, datatype: Union[str, DataType]) -> DataType:
         """Gets the DataType object for the dataformat"""
@@ -2100,7 +2111,6 @@ def addparticipant(participants_tsv: Path, subid: str='', sesid: str='', data: d
         if subid not in table.index:
             if sesid:
                 table.loc[subid, 'session_id'] = sesid
-            table.loc[subid, 'group'] = None
             data_added                = True
         for key in data:
             if key not in table or pd.isnull(table.loc[subid, key]) or table.loc[subid, key] == 'n/a':
@@ -2121,9 +2131,6 @@ def addparticipant(participants_tsv: Path, subid: str='', sesid: str='', data: d
             if not meta.get('session_id') and 'session_id' in table.columns:
                 meta['session_id'] = {'Description': 'Session identifier'}
                 key_added          = True
-            if not meta.get('group') and 'group' in table.columns:
-                meta['group'] = {'Description': 'Group identifier'}
-                key_added     = True
             for col in table.columns:
                 if col not in meta:
                     key_added = True

bidscoin/bidscoiner.py

@@ -257,25 +257,26 @@ def bidscoiner(sourcefolder: str, bidsfolder: str, participant: list=(), force:
                 sesfolders, unpacked = unpack(session, bidsmap.options.get('unzip',''))
                 for sesfolder in sesfolders:
 
-                    # Check if we should skip the session-folder
-                    datasource = bids.get_datasource(sesfolder, bidsmap.plugins)
-                    if not datasource.dataformat:
-                        LOGGER.info(f">>> No datasources found in '{sesfolder}'")
-                        continue
-                    LOGGER.info(f">>> Coining datasources in: {sesfolder}")
-                    subid        = bidsmap.dataformat(datasource.dataformat).subject
-                    sesid        = bidsmap.dataformat(datasource.dataformat).session
-                    subid, sesid = datasource.subid_sesid(subid, sesid or '')
-                    bidssession  = bidsfolder/subid/sesid       # TODO: Support DICOMDIR with multiple subjects (as in PYDICOMDIR)
-                    if bidssession.is_dir():
-                        LOGGER.warning(f"Existing BIDS output-directory found, which may result in duplicate data (with increased run-index). Make sure {bidssession} was cleaned-up from old data before (re)running the bidscoiner")
-                    bidssession.mkdir(parents=True, exist_ok=True)
-
                     # Run the bidscoiner plugins
                     for plugin in plugins:
-                        LOGGER.verbose(f"Executing plugin: {Path(plugin.__file__).stem}")
-                        trackusage(Path(plugin.__file__).stem)
-                        personals = plugin.Interface().bidscoiner(sesfolder, bidsmap, bidssession)
+
+                        # Check if we should skip the sesfolder
+                        name       = Path(plugin.__file__).stem
+                        datasource = bids.get_datasource(sesfolder, {name: bidsmap.plugins[name]})
+                        if not datasource.dataformat:
+                            LOGGER.info(f">>> No {name} datasources found in '{sesfolder}'")
+                            continue
+                        LOGGER.info(f">>> Coining {name} datasources in: {sesfolder}")
+                        subid        = bidsmap.dataformat(datasource.dataformat).subject
+                        sesid        = bidsmap.dataformat(datasource.dataformat).session
+                        subid, sesid = datasource.subid_sesid(subid, sesid or '')
+                        bidssession  = bidsfolder/subid/sesid       # TODO: Support DICOMDIR with multiple subjects (as in PYDICOMDIR)
+                        bidssession.mkdir(parents=True, exist_ok=True)
+
+                        LOGGER.verbose(f"Executing plugin: {name}")
+                        trackusage(name)
+                        plugin.Interface().bidscoiner(sesfolder, bidsmap, bidssession)
+                        personals = plugin.Interface().personals(bidsmap, datasource)
 
                         # Add a subject row to the participants table (if there is any data)
                         if next(bidssession.rglob('*.json'), None):

bidscoin/bidseditor.py

@@ -54,6 +54,7 @@
             e.g. extra_data/;myfile.txt;yourfile.csv
 subprefix:  The subject prefix used in the source data folders (e.g. "Pt" is the subprefix if subject folders are named "Pt018", "Pt019", ...)
 sesprefix:  The session prefix used in the source data folders (e.g. "M_" is the subprefix if session folders are named "M_pre", "M_post", ...)
+anon:       Set this anonymization flag to 'y' to round off age and to discard acquisition date from the meta data
 For more information see: {MAIN_HELP_URL}/options.html"""
 
 TOOLTIP_DCM2NIIX = """dcm2niix2bids
@@ -67,8 +68,6 @@
 args: Argument string that is passed to dcm2niix. Click [Test] and see the terminal output for usage
     Tip: SPM users may want to use '-z n', which produces unzipped NIfTI's
     
-anon: Set this anonymization flag to 'y' to round off age and to discard acquisition date from the meta data
-
 meta: The file extensions of the associated / equally named (meta)data sourcefiles that are copied over as
     BIDS (sidecar) files, such as ['.json', '.tsv', '.tsv.gz']. You can use this to enrich json sidecar files,
     or add data that is not supported by this plugin
@@ -958,8 +957,8 @@ def open_inspectwindow(self, index: int):
 
         datafile = Path(self.filesystem.fileInfo(index).absoluteFilePath())
         if datafile.is_file():
-            ext = ''.join(datafile.suffixes).lower()
-            if is_dicomfile(datafile) or is_parfile(datafile) or ext in sum((klass.valid_exts for klass in nib.imageclasses.all_image_classes), ('.nii.gz',)):
+            ext = datafile.suffix.lower()
+            if is_dicomfile(datafile) or is_parfile(datafile) or ext in sum((klass.valid_exts for klass in nib.imageclasses.all_image_classes), ('.7','.spar')) or datafile.name.endswith('.nii.gz'):
                 self.popup = InspectWindow(datafile)
                 self.popup.show()
                 self.popup.scrollbar.setValue(0)  # This can only be done after self.popup.show()
@@ -1006,7 +1005,7 @@ def __init__(self, runitem: RunItem, bidsmap: BidsMap, template_bidsmap: BidsMap
         """The data format of the run-item being edited (bidsmap[dataformat][datatype][run-item])"""
         self.unknowndatatypes: list[str] = [datatype for datatype in bidsmap.options['unknowntypes'] if datatype in template_bidsmap.dataformat(self.dataformat).datatypes]
         self.ignoredatatypes: list[str]  = [datatype for datatype in bidsmap.options['ignoretypes']  if datatype in template_bidsmap.dataformat(self.dataformat).datatypes]
-        self.bidsdatatypes     = [str(datatype) for datatype in template_bidsmap.dataformat(self.dataformat).datatypes if datatype not in self.unknowndatatypes + self.ignoredatatypes + ['subject', 'session']]
+        self.bidsdatatypes     = [str(datatype) for datatype in template_bidsmap.dataformat(self.dataformat).datatypes if datatype not in self.unknowndatatypes + self.ignoredatatypes]
         self.bidsignore        = bidsmap.options['bidsignore']
         self.output_bidsmap    = bidsmap
         """The bidsmap at the start of the edit = output_bidsmap in the MainWindow"""
@@ -2041,14 +2040,13 @@ class InspectWindow(QDialog):
     def __init__(self, filename: Path):
         super().__init__()
 
-        ext = ''.join(filename.suffixes).lower()
         if is_dicomfile(filename):
             if filename.name == 'DICOMDIR':
                 LOGGER.bcdebug(f"Getting DICOM fields from {filename} will raise dcmread error below if pydicom => v3.0")
             text = str(dcmread(filename, force=True))
-        elif is_parfile(filename) or ext in ('.spar', '.txt', '.text', '.log'):
+        elif is_parfile(filename) or filename.suffix.lower() in ('.spar', '.txt', '.text', '.log'):
             text = filename.read_text()
-        elif ext == '.7':
+        elif filename.suffix.lower() == '.7':
             try:
                 from spec2nii.GE.ge_read_pfile import Pfile
                 text = ''
@@ -2062,7 +2060,7 @@ def __init__(self, filename: Path):
             except ImportError as perror:
                 text = f"Could not inspect: {filename}"
                 LOGGER.verbose(f"Could not import spec2nii to read {filename}\n{perror}")
-        elif filename.is_file() and ext in sum((klass.valid_exts for klass in nib.imageclasses.all_image_classes), ('.nii.gz',)):
+        elif filename.is_file() and filename.suffix.lower() in sum((klass.valid_exts for klass in nib.imageclasses.all_image_classes), ('.nii',)) or filename.name.endswith('.nii.gz'):
             text = str(nib.load(filename).header)
         else:
             text = f"Could not inspect: {filename}"

bidscoin/bidsmapper.py

@@ -120,9 +120,8 @@ def bidsmapper(sourcefolder: str, bidsfolder: str, bidsmap: str, template: str,
                 sessions = [subject]
             for session in sessions:
 
-                LOGGER.info(f"Mapping: {session} (subject {n}/{len(subjects)})")
-
                 # Unpack the data in a temporary folder if it is tarballed/zipped and/or contains a DICOMDIR file
+                LOGGER.info(f"Mapping: {session} (subject {n}/{len(subjects)})")
                 sesfolders, unpacked = unpack(session, unzip)
                 for sesfolder in sesfolders:
                     if store:

bidscoin/heuristics/bidsmap_bids2bids.yaml

@@ -29,6 +29,7 @@ Options:
     bidsignore: [extra_data/, sub-*_ct.*]    # List of entries that are added to the .bidsignore file (for more info, see BIDS specifications), e.g. [extra_data/, pet/, myfile.txt, yourfile.csv]
     unknowntypes: [extra_data]      # A list of datatypes that are converted to BIDS-like datatype folders
     ignoretypes: [exclude]          # A list of datatypes that are excluded / not converted to BIDS
+    anon: y                         # Set this anonymization flag to 'y' to round off age and discard acquisition date from the meta data
     unzip:                          # Wildcard pattern to select tarball/zip-files in the source folders that need to be unzipped (in a tempdir) to expose the data, e.g. '*.tar.gz'
   plugins:                          # List of plugins with plugin-specific key-value pairs (that can be used by the plugin)
     nibabel2bids:
@@ -40,8 +41,9 @@ Nibabel:
 # --------------------------------------------------------------------------------
 # Nibabel key-value heuristics (header fields that are mapped to the BIDS labels)
 # --------------------------------------------------------------------------------
-  subject: <<filepath:/sub-(.*?)/>>    # This filesystem property extracts the subject label from the source directory. NB: Any property or attribute can be used as subject-label, e.g. <PatientID>
-  session: <<filepath:/sub-.*?/ses-(.*?)/>>     # This filesystem property extracts the subject label from the source directory. NB: Any property or attribute can be used as session-label, e.g. <StudyID>
+  participant: # Attributes or properties to populate the participants table/tsv-file
+    participant_id: <<filepath:/sub-(.*?)/>>      # This filesystem property extracts the subject label from the source directory. NB: Any property or attribute can be used as subject-label, e.g. <PatientID>
+    session_id: <<filepath:/sub-.*?/ses-(.*?)/>>  # This filesystem property extracts the subject label from the source directory. NB: Any property or attribute can be used as session-label, e.g. <StudyID>
 
   anat:       # ----------------------- All anatomical runs --------------------
   - properties: &fileprop_anat          # This is an optional (stub) entry of properties matching (could be added to any run-item)