get id from handle and misc refactoring

Author: ehanson8

.travis.yml

@@ -1,6 +1,6 @@
 language: python
 python:
-  - "3.7"
+  - "3.8"
 install:
   - pipenv install --dev
 script:

Pipfile

@@ -10,12 +10,12 @@ requests-mock = "*"
 [packages]
 requests = "*"
 structlog = "*"
-attr = "*"
+attrs = "*"
 click = "*"
 lxml = "*"
 
 [requires]
-python_version = "3.7"
+python_version = "3.8"
 
 [scripts]
 dsaps = "python -c \"from dsaps.cli import main; main()\""

dsaps/cli.py

@@ -24,6 +24,8 @@
 @click.pass_context
 def main(ctx, url, email, password):
     ctx.obj = {}
+    if os.path.isdir('logs') is False:
+        os.mkdir('logs')
     dt = datetime.datetime.utcnow().isoformat(timespec='seconds')
     log_suffix = f'{dt}.log'
     structlog.configure(processors=[
@@ -47,31 +49,6 @@ 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.')
-@click.option('-s', '--string', prompt='Enter the string',
-              help='The field to search.')
-@click.option('-t', '--search_type', prompt='Enter the type of search',
-              help='The type of search.',
-              type=click.Choice(['exists', 'doesnt_exist', 'equals',
-                                 'not_equals', 'contains', 'doesnt_contain']),
-              default='contains')
-@click.pass_context
-def search(ctx, field, string, search_type):
-    # Temp function for testing
-    client = ctx.obj['client']
-    start_time = ctx.obj['start_time']
-    item_links = client.filtered_item_search(field, string, search_type)
-    logger.info(item_links)
-    models.elapsed_time(start_time, 'Elapsed time')
-
-
 @main.command()
 @click.option('-c', '--comm_handle', prompt='Enter the community handle',
               help='The handle of the community in which to create the ,'
@@ -111,7 +88,7 @@ def newcoll(ctx, comm_handle, coll_name, metadata, file_path, file_type,
     models.elapsed_time(start_time, 'Total runtime:')
 
 
-@aux.command()
+@main.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',
@@ -150,7 +127,7 @@ def reconcile(metadata_csv, file_path, file_type):
     models.create_csv_from_list(metadata_matches, 'metadata_matches.csv')
 
 
-@aux.command()
+@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):
@@ -190,7 +167,5 @@ def metadatajson(metadata_csv):
         json.dump(metadata_group, f)
 
 
-cli = click.CommandCollection(sources=[main, aux])
-
 if __name__ == '__main__':
-    cli()
+    main()

dsaps/models.py

@@ -77,6 +77,13 @@ def filtered_item_search(self, key, string, query_type,
             offset = offset + 200
         return item_links
 
+    def get_id_from_handle(self, handle):
+        """Posts a collection to a specified community."""
+        endpoint = f'{self.url}/handle/{handle}'
+        rec_obj = requests.get(endpoint, headers=self.header,
+                               cookies=self.cookies).json()
+        return rec_obj['uuid']
+
     def post_coll_to_comm(self, comm_handle, coll_name):
         """Posts a collection to a specified community."""
         endpoint = f'{self.url}/handle/{comm_handle}'
@@ -119,13 +126,17 @@ def post_bitstreams_to_item(self, item_id, file_identifier, file_dict,
                                 ingest_type):
         """Posts bitstreams to a specified item."""
         for k, v in file_dict.items():
+            bitstreams = []
             if k.startswith(file_identifier):
-                bitstream = file_dict[k]
-                file_name = os.path.basename(bitstream)
+                bitstreams.append(k)
+            bitstreams.sort()
+            for bitstream in bitstreams:
+                bitstream_path = file_dict[bitstream]
+                file_name = os.path.basename(bitstream_path)
                 if ingest_type == 'local':
-                    data = open(bitstream, 'rb')
+                    data = open(bitstream_path, 'rb')
                 elif ingest_type == 'remote':
-                    data = requests.get(bitstream)
+                    data = requests.get(bitstream_path)
                 endpoint = (f'{self.url}/items/{item_id}'
                             + f'/bitstreams?name={file_name}')
                 header_upload = {'accept': 'application/json'}
@@ -192,7 +203,7 @@ def build_file_dict_remote(directory_url, file_type, file_dict):
     """Build list of files in a remote directory."""
     response = requests.get(directory_url)
     links = html.fromstring(response.content).iterlinks()
-    for link in [l for l in links if l[2].endswith(file_type)]:
+    for link in [i for i in links if i[2].endswith(file_type)]:
         file_identifier = link[2].replace(f'.{file_type}', '')
         file_dict[file_identifier] = f'{directory_url}{link[2]}'
     return file_dict
@@ -213,24 +224,38 @@ def elapsed_time(start_time, label):
     logger.info(f'{label} : {td}')
 
 
-def metadata_csv(row, key, field, language=None):
+def metadata_csv(row, key, field, language=None, delimiter=''):
     """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
+    metadata_elems = []
+    if row[field] != '':
+        if delimiter != '' and delimiter in row[field]:
+            values = row[field].split(delimiter)
+            for value in values:
+                if language is not None:
+                    metadata_elem = {'key': key, 'language': language, 'value':
+                                     value}
+                    metadata_elems.append(metadata_elem)
+                else:
+                    metadata_elem = {'key': key, 'value': value}
+                    metadata_elems.append(metadata_elem)
+        else:
+            value = row[field]
+            if language is not None:
+                metadata_elem = {'key': key, 'language': language, 'value':
+                                 value}
+            else:
+                metadata_elem = {'key': key, 'value': value}
+            metadata_elems.append(metadata_elem)
+    return metadata_elems
 
 
 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])
+        if len(v) == 3:
+            metadata_elems = metadata_csv(row, k, v[0], v[1], v[2])
         else:
-            metadata_elem = metadata_csv(row, k, v[0])
-        if metadata_elem['value'] != '':
+            metadata_elems = metadata_csv(row, k, v[0])
+        for metadata_elem in metadata_elems:
             metadata_rec.append(metadata_elem)
     return metadata_rec

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 
 setup(
-    name='DSpace API Python Scripts',
+    name='dsaps',
     version='1.0.0',
     description='',
     packages=find_packages(exclude=['tests']),
@@ -10,7 +10,7 @@
     install_requires=[
         'requests',
         'structlog',
-        'attr',
+        'attrs',
         'click',
         'lxml',
     ],
@@ -19,5 +19,5 @@
             'dsaps=dsaps.cli:main',
         ]
     },
-    python_requires='>=3.7.1',
+    python_requires='>=3.8',
 )

tests/test_models.py

@@ -30,9 +30,9 @@ def test_authenticate(client):
         email = 'test@test.mock'
         password = '1234'
         cookies = {'JSESSIONID': '11111111'}
-        json_object = {'fullname': 'User Name'}
+        user_json = {'fullname': 'User Name'}
         m.post('mock://example.com/login', cookies=cookies)
-        m.get('mock://example.com/status', json=json_object)
+        m.get('mock://example.com/status', json=user_json)
         client.authenticate(email, password)
         assert client.user_full_name == 'User Name'
         assert client.cookies == cookies
@@ -42,10 +42,10 @@ def test_get_record(client):
     """Test get_record method."""
     with requests_mock.Mocker() as m:
         uri = 'mock://example.com/items/123?expand=all'
-        json_object = {'metadata': {'title': 'Sample title'}, 'type': 'item'}
-        m.get(uri, json=json_object)
+        rec_json = {'metadata': {'title': 'Sample title'}, 'type': 'item'}
+        m.get(uri, json=rec_json)
         rec_obj = client.get_record('123', 'items')
-        assert attr.asdict(rec_obj)['metadata'] == json_object['metadata']
+        assert attr.asdict(rec_obj)['metadata'] == rec_json['metadata']
 
 
 def test_filtered_item_search(client):
@@ -55,25 +55,35 @@ def test_filtered_item_search(client):
         string = 'test'
         query_type = 'contains'
         endpoint = 'mock://example.com/filtered-items?'
-        json_object_1 = {'items': [{'link': '1234'}]}
-        json_object_2 = {'items': []}
-        m.get(endpoint, [{'json': json_object_1}, {'json': json_object_2}])
+        results_json1 = {'items': [{'link': '1234'}]}
+        results_json2 = {'items': []}
+        m.get(endpoint, [{'json': results_json1}, {'json': results_json2}])
 
         item_links = client.filtered_item_search(key, string, query_type,
                                                  selected_collections='')
         assert '1234' in item_links
 
 
+def test_get_id_from_handle(client):
+    """Test get_id_from_handle method."""
+    with requests_mock.Mocker() as m:
+        handle = 'mock://example.com/handle/111.1111'
+        rec_json = {'uuid': '123'}
+        m.get(handle, json=rec_json)
+        id = client.get_id_from_handle('111.1111')
+        assert id == '123'
+
+
 def test_post_coll_to_comm(client):
     """Test post_coll_to_comm method."""
     with requests_mock.Mocker() as m:
         comm_handle = '1234'
         coll_name = 'Test Collection'
-        json_object_1 = {'uuid': 'a1b2'}
-        json_object_2 = {'uuid': '5678'}
-        m.get('mock://example.com/handle/1234', json=json_object_1)
+        comm_json = {'uuid': 'a1b2'}
+        coll_json = {'uuid': '5678'}
+        m.get('mock://example.com/handle/1234', json=comm_json)
         m.post('mock://example.com/communities/a1b2/collections',
-               json=json_object_2)
+               json=coll_json)
         coll_id = client.post_coll_to_comm(comm_handle, coll_name)
         assert coll_id == '5678'
 
@@ -86,15 +96,17 @@ def test_post_items_to_coll(client, sample_content):
                           "value": "123"},
                          {"key": "dc.title", "value":
                           "Monitoring Works: Getting Teachers",
-                          "language": "en_US"}]}]
+                          "language": "en_US"},
+                         {"key": "dc.relation.isversionof",
+                          "value": "repo/0/ao/123"}]}]
         coll_id = '789'
         ingest_type = 'local'
         file_dict = {'123': sample_content}
-        json_object_1 = {'uuid': 'a1b2'}
-        m.post('mock://example.com/collections/789/items', json=json_object_1)
+        item_json = {'uuid': 'a1b2', 'handle': '1111.1/1111'}
+        m.post('mock://example.com/collections/789/items', json=item_json)
         url = 'mock://example.com/items/a1b2/bitstreams?name=123.pdf'
-        json_object_2 = {'uuid': 'c3d4'}
-        m.post(url, json=json_object_2)
+        b_json = {'uuid': 'c3d4'}
+        m.post(url, json=b_json)
         item_ids = client.post_items_to_coll(coll_id, coll_metadata, file_dict,
                                              ingest_type)
         for item_id in item_ids:
@@ -108,9 +120,9 @@ def test_post_bitstreams_to_item(client, sample_content):
         ingest_type = 'local'
         file_identifier = '123'
         file_dict = {'123': sample_content}
-        json_object_1 = {'uuid': 'c3d4'}
+        b_json = {'uuid': 'c3d4'}
         url = 'mock://example.com/items/a1b2/bitstreams?name=123.pdf'
-        m.post(url, json=json_object_1)
+        m.post(url, json=b_json)
         bit_ids = client.post_bitstreams_to_item(item_id, file_identifier,
                                                  file_dict, ingest_type)
         for bit_id in bit_ids:
@@ -161,8 +173,12 @@ 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'
+    assert metadata_elem[0]['key'] == 'dc.title'
+    assert metadata_elem[0]['value'] == 'Test title'
+
+
+# def test_create_ingest_report():
+#     assert False
 
 
 def test_create_metadata_rec():