fixed all SPARC-FAIR-Codeathon#106

examples/example_for_create_dataset.py

@@ -103,8 +103,10 @@ def add_values_dataset_description(dataset_description):
     # code_parameters = dataset.get_metadata(metadata_file="code_parameters")
     # code_description = dataset.get_metadata(metadata_file="code_description")
 
-    des_schema = schema.get_schema("dataset_description")
-    des_schema.get('subtitle')
+    print("******************************************")
+    des_schema = schema.get_schema("dataset_description", name_only=False)
+    print(des_schema)
+
 
     # NOTE: Step3.1(optional), remove entire values in dataset_description
     dataset_description.clear_values()
@@ -191,19 +193,49 @@ def add_values_dataset_description(dataset_description):
     # add_values_for_subject_metadata(subject_metadata)
 
     # New function for add subjects and samples
+    # subjects = []
+    # for subject_user_id in [1, 2]:
+    #     samples = []
+    #     for sample_user_id in [1, 2]:
+    #         sample = sm.Sample()
+    #         sample.add_path(
+    #             "./test_data/bids_data/sub-0{0}/sequence{1}/".format(
+    #                 subject_user_id, sample_user_id))
+    #         samples.append(sample)
+    #
+    #     subject = sm.Subject()
+    #     subject.add_samples(samples)
+    #     subjects.append(subject)
+
     subjects = []
-    for subject_user_id in [1, 2]:
-        samples = []
-        for sample_user_id in [1, 2]:
-            sample = sm.Sample()
-            sample.add_path(
-                "./test_data/bids_data/sub-0{0}/sequence{1}/".format(
-                    subject_user_id, sample_user_id))
-            samples.append(sample)
-
-        subject = sm.Subject()
-        subject.add_samples(samples)
-        subjects.append(subject)
+    samples = []
+
+    sample1 = sm.Sample()
+    sample1.add_path("./test_data/bids_data/sub-01/sequence1/")
+    sample1.add_path("./test_data/sample2/raw/dummy_sam2.txt")
+    samples.append(sample1)
+
+    sample2 = sm.Sample()
+    sample2.add_path("./test_data/bids_data/sub-01/sequence2/")
+    samples.append(sample2)
+
+    subject1 = sm.Subject()
+    subject1.add_samples(samples)
+    subjects.append(subject1)
+
+    samples = []
+
+    sample1 = sm.Sample()
+    sample1.add_path("./test_data/bids_data/sub-02/sequence1/")
+    samples.append(sample1)
+
+    sample2 = sm.Sample()
+    sample2.add_path("./test_data/bids_data/sub-02/sequence2/")
+    samples.append(sample2)
+
+    subject2 = sm.Subject()
+    subject2.add_samples(samples)
+    subjects.append(subject2)
 
     dataset.add_subjects(subjects)
 

setup.py

@@ -4,7 +4,7 @@
 
 setup(
     name="sparc_me",
-    version="2.2.3",
+    version="2.2.8",
     description='A python tool to explore, enhance, and expand SPARC datasets and their descriptions in accordance with FAIR principles.',
     author="Thiranja Prasad Babarenda Gamage, Chinchien Lin, Savindi Wijenayaka, Michael Hoffman, Linkun Gao, Haribalan Kumar",
     email="[email protected], [email protected]",

sparc_me/core/metadata.py

@@ -4,6 +4,7 @@
 import shutil
 from sparc_me.core.utils import find_col_element
 from datetime import datetime, timezone
+from typing import List
 
 
 class Metadata:
@@ -406,11 +407,12 @@ class Sample:
     _metadata: Metadata = None
     _manifest_metadata: Metadata = None
 
+
     def __init__(self):
         self.sample_id = ""
         self.subject_id = ""
         self.sample_dir = Path()
-        self.source_sam_dir = Path()
+        self.source_sample_paths: List[Path] = []
         self.index = -1
 
     def set_subject_id(self, sub_id):
@@ -469,16 +471,42 @@ def add_path(self, source_path):
         Add sample source path to sample object
 
         :param source_path: sample folder source path
-        :type source_path: str
+        :type source_path: str | list
 
         """
-        self.source_sam_dir = Path(source_path)
+        if isinstance(source_path, list):
+            for file_path in source_path:
+                self.source_sample_paths.append(Path(file_path))
+        else:
+            self.source_sample_paths.append(Path(source_path))
+
+
+    def set_path(self, source_path):
+        """
+        Add sample source path to sample object
+        Override the Previous path
+
+        :param source_path: sample folder source path
+        :type source_path: str | list
+
+        """
+        if isinstance(source_path, list):
+            self.source_sample_paths = []
+            for file_path in source_path:
+                self.source_sample_paths.append(Path(file_path))
+        else:
+            self.source_sample_paths = [Path(source_path)]
+
 
     def set_values(self, metadata={}):
         """
         :param metadata: key : value dict (element:value)
         :type metadata: dict
         """
+        if not isinstance(metadata, dict):
+            msg = f"You should use a dict here, you provide parameter type is {type(metadata)}"
+            raise TypeError(msg)
+
         for element, value in metadata.items():
             if element == 'sample id' or element == 'subject id':
                 continue
@@ -511,15 +539,19 @@ def move(self):
         if not self.sample_dir.exists():
             self.sample_dir.mkdir(parents=True, exist_ok=True)
 
-        source_sample_files = self.source_sam_dir.rglob("*")
-        for file in source_sample_files:
-            if file.is_file():
-                relative_path = file.relative_to(self.source_sam_dir)
-                target_file = self.sample_dir / relative_path
-                target_file.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copy(str(file), str(target_file))
-                self._update_manifest(sample_path=str(target_file))
-
+        for source_sam in self.source_sample_paths:
+            if source_sam.is_dir():
+                source_sample_files = source_sam.rglob("*")
+                for file in source_sample_files:
+                    if file.is_file():
+                        relative_path = file.relative_to(source_sam)
+                        target_file = self.sample_dir / relative_path
+                        target_file.parent.mkdir(parents=True, exist_ok=True)
+                        shutil.copy(str(file), str(target_file))
+                        self._update_manifest(sample_path=str(target_file))
+            elif source_sam.is_file():
+                shutil.copy(str(source_sam), str(self.sample_dir))
+                self._update_manifest(sample_path=str(self.sample_dir / source_sam.name))
     def _update_manifest(self, sample_path):
         """
         Update manifest metadata, after remove samples
@@ -661,6 +693,10 @@ def set_values(self, metadata={}):
         :param metadata: key : value dict (element:value)
         :type metadata: dict
         """
+        if not isinstance(metadata, dict):
+            msg = f"You should use a dict here, you provide parameter type is {type(metadata)}"
+            raise TypeError(msg)
+
         for element, value in metadata.items():
             if element == 'subject id':
                 continue

sparc_me/core/schema.py

@@ -52,7 +52,6 @@ def validate_dataset(self, dataset):
             data = schema.load_data(metadata.metadata_file_path)
             self.validate(data, metadata_file=metadata_file, version=metadata.version)
 
-
     def validate(self, data, metadata_file, version):
         """
         Validate data instance
@@ -149,9 +148,10 @@ def get_default_schema(version, metadata_file):
 
         return schema
 
-    def get_schema(self, metadata_file, version="2.0.0", print_schema=True):
+    def get_schema(self, metadata_file, version="2.0.0", print_schema=True, required_only=True, name_only=True):
         """
         get a schema via metadata_file/metadate file name
+
         :param metadata_file: the metadata file name
         :type metadata_file: str
         :param version: "2.0.0"|"1.2.3"
@@ -171,7 +171,22 @@ def get_schema(self, metadata_file, version="2.0.0", print_schema=True):
         with open(schema_path, 'r') as file:
             schema_json: Dict = json.load(file)
             if print_schema:
-                print(json.dumps(schema_json.get('properties'), indent=4))
+                if required_only:
+                    if name_only:
+                        print(f"The required elements for {metadata_file}:")
+                        print(json.dumps(schema_json.get('required'), indent=4))
+                    else:
+                        required_items = []
+                        for key, value in schema_json.get('properties').items():
+                            if "required" in value and value["required"] == "Y":
+                                required_items.append({key: value})
+
+                        print(f"The required elements for {metadata_file}:")
+                        print(json.dumps(required_items, indent=4))
+                        return required_items
+                else:
+                    print(json.dumps(schema_json.get('properties'), indent=4))
+
             return CaseInsensitiveDict(schema_json.get('properties'))
 
     def set_schema(self, schema):