Merge pull request #13 from MITLibraries/metadata-json

metadata json transform

Author: ehanson8

dsaps/cli.py

@@ -47,6 +47,11 @@ def main(ctx, url, email, password):
     ctx.obj['start_time'] = start_time
 
 
+@click.group()
+def aux():
+    pass
+
+
 @main.command()
 @click.option('-f', '--field', prompt='Enter the field to be searched',
               help='The field to search.')
@@ -106,7 +111,7 @@ def newcoll(ctx, comm_handle, coll_name, metadata, file_path, file_type,
     models.elapsed_time(start_time, 'Total runtime:')
 
 
-@main.command()
+@aux.command()
 @click.option('-m', '--metadata_csv', prompt='Enter the metadata CSV file',
               help='The path of the CSV file of metadata.')
 @click.option('-f', '--file_path', prompt='Enter the path',
@@ -145,5 +150,47 @@ def reconcile(metadata_csv, file_path, file_type):
     models.create_csv_from_list(metadata_matches, 'metadata_matches.csv')
 
 
+@aux.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 = []
+        mapping_dict = {'fileIdentifier': ['file_identifier'],
+                        'dc.contributor.author': ['author name - direct'],
+                        'dc.contributor.advisor': ['supervisor(s)'],
+                        'dc.date.issued': ['pub date'],
+                        'dc.description.abstract': ['Abstract', 'en_US'],
+                        'dc.title': ['Title', 'en_US'],
+                        'dc.relation.ispartofseries': ['file_identifier']}
+        for row in reader:
+            metadata_rec = []
+            metadata_rec = models.create_metadata_rec(mapping_dict, row,
+                                                      metadata_rec)
+            metadata_rec.append({'key': 'dc.format.mimetype', 'language':
+                                'en_US', 'value': 'application/pdf'})
+            metadata_rec.append({'key': 'dc.language.iso', 'language':
+                                'en_US', 'value': 'en_US'})
+            metadata_rec.append({'key': 'dc.publisher', 'language': 'en_US',
+                                 'value': 'Massachusetts Institute of '
+                                 'Technology. Laboratory for Computer'
+                                 'Science'})
+            metadata_rec.append({'key': 'dc.rights', 'language': 'en_US',
+                                'value': 'Educational use permitted'})
+            metadata_rec.append({'key': 'dc.rights.uri', 'language': 'en_US',
+                                 'value': 'http://rightsstatements.org/vocab/'
+                                 'InC-EDU/1.0/'})
+            metadata_rec.append({'key': 'dc.type', 'language': 'en_US',
+                                'value': 'Technical Report'})
+            item = {'metadata': metadata_rec}
+            metadata_group.append(item)
+    file_name = os.path.splitext(os.path.basename(metadata_csv))[0]
+    with open(f'{file_name}.json', 'w') as f:
+        json.dump(metadata_group, f)
+
+
+cli = click.CommandCollection(sources=[main, aux])
+
 if __name__ == '__main__':
-    main()
+    cli()

dsaps/models.py

@@ -211,3 +211,26 @@ 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, key, field, language=None):
+    """Create metadata element from CSV."""
+    value = row[field]
+    if language is not None:
+        metadata_elem = {'key': key, 'language': language, 'value':
+                         value}
+    else:
+        metadata_elem = {'key': key, 'value': value}
+    return metadata_elem
+
+
+def create_metadata_rec(mapping_dict, row, metadata_rec):
+    """Create metadata record from CSV."""
+    for k, v in mapping_dict.items():
+        if len(v) == 2:
+            metadata_elem = metadata_csv(row, k, v[0], v[1])
+        else:
+            metadata_elem = metadata_csv(row, k, v[0])
+        if metadata_elem['value'] != '':
+            metadata_rec.append(metadata_elem)
+    return metadata_rec

tests/test_models.py

@@ -155,3 +155,20 @@ 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."""
+    row = {'title': 'Test title'}
+    metadata_elem = models.metadata_csv(row, 'dc.title', 'title', 'en_US')
+    assert metadata_elem['key'] == 'dc.title'
+    assert metadata_elem['value'] == 'Test title'
+
+
+def test_create_metadata_rec():
+    metadata_rec = []
+    row = {'title': 'Test title'}
+    mapping_dict = {'dc.title': ['title']}
+    metadata_rec = models.create_metadata_rec(mapping_dict, row, metadata_rec)
+    assert metadata_rec[0]['key'] == 'dc.title'
+    assert metadata_rec[0]['value'] == 'Test title'