metadata json transform

Author: ehanson8

dsaps/cli.py

@@ -145,5 +145,50 @@ def reconcile(metadata_csv, file_path, file_type):
     models.create_csv_from_list(metadata_matches, 'metadata_matches.csv')
 
 
+@main.command()
+@click.option('-m', '--metadata_csv', prompt='Enter the metadata CSV file',
+              help='The path of the CSV file of metadata.')
+def metadatajson(metadata_csv):
+    with open(metadata_csv) as csvfile:
+        reader = csv.DictReader(csvfile)
+        metadata_group = []
+        for row in reader:
+            metadata_rec = []
+            models.metadata_csv(row, metadata_rec, 'fileIdentifier',
+                                'file_identifier', '', '')
+            models.metadata_csv(row, metadata_rec, 'dc.contributor.author',
+                                'author name - direct', '', '')
+            models.metadata_csv(row, metadata_rec, 'dc.contributor.advisor',
+                                'supervisor(s)', '', '')
+            models.metadata_csv(row, metadata_rec, 'dc.date.issued',
+                                'pub date', '', '')
+            models.metadata_csv(row, metadata_rec, 'dc.description.abstract',
+                                'Abstract', 'en_US', '')
+            models.metadata_direct(metadata_rec, 'dc.format.mimetype',
+                                   'application/pdf', 'en_US')
+            models.metadata_direct(metadata_rec, 'dc.language.iso', 'en_US',
+                                   'en_US')
+            models.metadata_direct(metadata_rec, 'dc.publisher',
+                                   'Massachusetts Institute of Technology. '
+                                   'Laboratory for Computer Science', 'en_US')
+            models.metadata_csv(row, metadata_rec,
+                                'dc.relation.ispartofseries',
+                                'file_identifier', 'en_US', '')
+            models.metadata_direct(metadata_rec, 'dc.rights',
+                                   'Educational use permitted', 'en_US')
+            models.metadata_direct(metadata_rec, 'dc.rights.uri',
+                                   'http://rightsstatements.org/vocab/'
+                                   'InC-EDU/1.0/', 'en_US')
+            models.metadata_csv(row, metadata_rec, 'dc.title', 'Title',
+                                'en_US', '')
+            models.metadata_direct(metadata_rec, 'dc.type', 'Technical Report',
+                                   'en_US')
+            item = {'metadata': metadata_rec}
+            metadata_group.append(item)
+    file_name = os.path.splitext(os.path.basename(metadata_csv))[0]
+    f = open(f'{file_name}.json', 'w')
+    json.dump(metadata_group, f)
+
+
 if __name__ == '__main__':
     main()

dsaps/models.py

@@ -211,3 +211,39 @@ def elapsed_time(start_time, label):
     """Calculate elapsed time."""
     td = datetime.timedelta(seconds=time.time() - start_time)
     logger.info(f'{label} : {td}')
+
+
+def metadata_csv(row, metadata_rec, key, field, language, delimiter):
+    """Create metadata elements from CSV, including fields with delimiters."""
+    if row[field] != '':
+        if delimiter != '' and delimiter in row[field]:
+            values = row[field].split(delimiter)
+            for value in values:
+                if language != '':
+                    metadata_elem = {'key': key, 'language': language, 'value':
+                                     value}
+                    metadata_rec.append(metadata_elem)
+                else:
+                    metadata_elem = {'key': key, 'value': value}
+                    metadata_rec.append(metadata_elem)
+        else:
+            value = row[field]
+            if language != '':
+                metadata_elem = {'key': key, 'language': language, 'value':
+                                 value}
+                metadata_rec.append(metadata_elem)
+            else:
+                metadata_elem = {'key': key, 'value': value}
+                metadata_rec.append(metadata_elem)
+    else:
+        pass
+
+
+def metadata_direct(metadata_rec, key, value, language):
+    """Create metadata element with specified value."""
+    if language != '':
+        metadata_elem = {'key': key, 'language': language, 'value': value}
+        metadata_rec.append(metadata_elem)
+    else:
+        metadata_elem = {'key': key, 'value': value}
+        metadata_rec.append(metadata_elem)

tests/test_models.py

@@ -155,3 +155,21 @@ def test_build_file_dict_remote():
 # def test_create_csv_from_list():
 #     """Test create_csv_from_list function."""
 #     assert False
+
+
+def test_metadata_csv():
+    """Test metadata_csv function."""
+    metadata_rec = []
+    row = {'title': 'Test title'}
+    models.metadata_csv(row, metadata_rec, 'dc.title', 'title', 'en_US', '')
+    assert metadata_rec[0]['key'] == 'dc.title'
+    assert metadata_rec[0]['value'] == 'Test title'
+
+
+def test_metadata_direct():
+    """Test metadata_direct function."""
+    metadata_rec = []
+    value = 'No one may ever view this content.'
+    models.metadata_direct(metadata_rec, 'dc.rights', value, 'en_US')
+    assert metadata_rec[0]['key'] == 'dc.rights'
+    assert metadata_rec[0]['value'] == 'No one may ever view this content.'