reconcile refactor

dsaps/cli.py

@@ -14,6 +14,14 @@
 logger = structlog.get_logger()
 
 
+def validate_path(ctx, param, value):
+    """Validates th formatting of The submitted path"""
+    if value[-1] == '/':
+        return value
+    else:
+        raise click.BadParameter('Include / at the end of the path.')
+
+
 @click.group(chain=True)
 @click.option('--url', envvar='DSPACE_URL', required=True,)
 @click.option('-e', '--email', envvar='TEST_EMAIL', required=True,
@@ -51,11 +59,13 @@ def main(ctx, url, email, password):
 
 @main.command()
 @click.option('-m', '--metadata-csv', required=True,
-              type=click.Path(exists=True),
-              help='The full path to the CSV file of metadata for the items.')
-@click.option('--field-map', required=True, type=click.Path(exists=True),
-              help='Path to JSON field mapping file')
-@click.option('-d', '--directory', required=True,
+              type=click.Path(exists=True, file_okay=True, dir_okay=False),
+              help='The path to the CSV file of metadata for the items.')
+@click.option('--field-map', required=True,
+              type=click.Path(exists=True, file_okay=True, dir_okay=False),
+              help='The path to JSON field mapping file.')
+@click.option('-d', '--content-directory', required=True,
+              type=click.Path(exists=True, dir_okay=True, file_okay=False),
               help='The full path to the content, either a directory of files '
               'or a URL for the storage location.')
 @click.option('-t', '--file-type',
@@ -67,11 +77,11 @@ def main(ctx, url, email, password):
               help='The handle of the collection to which items are being '
               'added.', default=None)
 @click.pass_context
-def additems(ctx, metadata_csv, field_map, directory, file_type, ingest_report,
-             collection_handle):
+def additems(ctx, metadata_csv, field_map, content_directory, file_type,
+             ingest_report, collection_handle):
     """Adds items to a specified collection from a metadata CSV, a field
      mapping file, and a directory of files. May be run in conjunction with the
-     newcollection CLI commands."""
+     newcollection CLI command."""
     client = ctx.obj['client']
     start_time = ctx.obj['start_time']
     if 'collection_uuid' not in ctx.obj and collection_handle is None:
@@ -87,7 +97,7 @@ def additems(ctx, metadata_csv, field_map, directory, file_type, ingest_report,
         mapping = json.load(jsonfile)
         collection = Collection.from_csv(metadata, mapping)
     for item in collection.items:
-        item.bitstreams_from_directory(directory, file_type)
+        item.bitstreams_from_directory(content_directory, file_type)
     collection.uuid = collection_uuid
     items = collection.post_items(client)
     if ingest_report:
@@ -114,20 +124,38 @@ def newcollection(ctx, community_handle, collection_name):
     ctx.obj['collection_uuid'] = collection_uuid
 
 
-# @main.command()
-# @click.option('-m', '--metadata_csv', prompt='Enter the metadata CSV file',
-#               help='The path of the CSV file of metadata.')
-# @click.option('-o', '--output_path', prompt='Enter the output path',
-#               default='', help='The path of the output files, include '
-#               '/ at the end of the path')
-# @click.option('-f', '--file_path', prompt='Enter the path',
-#               help='The path of the content, a URL or local drive path.'
-#               'Include / at the end of a local drive path.')
-# @click.option('-t', '--file_type', prompt='Enter the file type',
-#               help='The file type to be uploaded.')
-# def reconcile(metadata_csv, file_path, file_type, output_path):
-#     workflows.reconcile_files_and_metadata(metadata_csv, output_path,
-#                                            file_path, file_type)
+@main.command()
+@click.option('-m', '--metadata-csv', required=True,
+              type=click.Path(exists=True, file_okay=True, dir_okay=False),
+              help='The path of the CSV file of metadata.')
+@click.option('-o', '--output-directory',
+              type=click.Path(exists=True, file_okay=False),
+              default=f'{os.getcwd()}/', callback=validate_path,
+              help='The path of the output files, include / at the end of the '
+              'path.')
+@click.option('-d', '--content-directory', required=True,
+              help='The full path to the content, either a directory of files '
+              'or a URL for the storage location.')
+@click.option('-t', '--file-type',
+              help='The file type to be uploaded, if limited to one file '
+              'type.', default='*')
+def reconcile(metadata_csv, output_directory, content_directory, file_type):
+    """Runs a reconciliation of the specified files and metadata that produces
+     reports of files with no metadata, metadata with no files, metadata
+     matched to files, and an updated version of the metadata CSV with only
+     the records that have matching files."""
+    file_ids = helpers.create_file_list(content_directory, file_type)
+    metadata_ids = helpers.create_metadata_id_list(metadata_csv)
+    metadata_matches = helpers.match_metadata_to_files(file_ids, metadata_ids)
+    file_matches = helpers.match_files_to_metadata(file_ids, metadata_ids)
+    no_files = set(metadata_ids) - set(metadata_matches)
+    no_metadata = set(file_ids) - set(file_matches)
+    helpers.create_csv_from_list(no_metadata, f'{output_directory}no_metadata')
+    helpers.create_csv_from_list(no_files, f'{output_directory}no_files')
+    helpers.create_csv_from_list(metadata_matches,
+                                 f'{output_directory}metadata_matches')
+    helpers.update_metadata_csv(metadata_csv, output_directory,
+                                metadata_matches)
 
 
 if __name__ == '__main__':

dsaps/helpers.py

@@ -2,11 +2,6 @@
 import glob
 import os
 
-import structlog
-
-
-logger = structlog.get_logger()
-
 
 def create_csv_from_list(list_name, output):
     """Creates CSV file from list content."""
@@ -17,14 +12,11 @@ def create_csv_from_list(list_name, output):
             writer.writerow([item])
 
 
-def create_file_dict(file_path, file_type):
-    """Creates a dict of file IDs and file paths."""
+def create_file_list(file_path, file_type):
+    """Creates a list of file names."""
     files = glob.glob(f'{file_path}/**/*.{file_type}', recursive=True)
-    file_dict = {}
-    for file in files:
-        file_name = os.path.splitext(os.path.basename(file))[0]
-        file_dict[file_name] = file
-    return file_dict
+    file_list = [os.path.basename(file) for file in files]
+    return file_list
 
 
 def create_ingest_report(items, file_name):
@@ -43,37 +35,32 @@ def create_metadata_id_list(metadata_csv):
     metadata_ids = []
     with open(metadata_csv) as csvfile:
         reader = csv.DictReader(csvfile)
-        for row in [r for r in reader if r['file_identifier'] != '']:
-            metadata_ids.append(row['file_identifier'])
+        metadata_ids = [row['file_identifier'] for row in reader
+                        if row['file_identifier'] != '']
     return metadata_ids
 
 
-def match_files_to_metadata(file_dict, metadata_ids):
+def match_files_to_metadata(file_list, metadata_ids):
     """Creates a list of files matched to metadata records."""
-    file_matches = []
-    for file_id, v in file_dict.items():
-        for metadata_id in [m for m in metadata_ids
-                            if file_id.startswith(m)]:
-            file_matches.append(file_id)
+    file_matches = [file_id for metadata_id in metadata_ids
+                    for file_id in file_list
+                    if file_id.startswith(metadata_id)]
     return file_matches
 
 
-def match_metadata_to_files(file_dict, metadata_ids):
+def match_metadata_to_files(file_list, metadata_ids):
     """Creates a list of metadata records matched to files."""
-    metadata_matches = []
-    for metadata_id in metadata_ids:
-        for file_id in [f for f in file_dict
-                        if f.startswith(metadata_id)]:
-            metadata_matches.append(metadata_id)
+    metadata_matches = [metadata_id for f in file_list for metadata_id in
+                        metadata_ids if f.startswith(metadata_id)]
     return metadata_matches
 
 
-def update_metadata_csv(metadata_csv, output_path, metadata_matches):
+def update_metadata_csv(metadata_csv, output_directory, metadata_matches):
     """Creates an updated CSV of metadata records with matching files."""
     with open(metadata_csv) as csvfile:
         reader = csv.DictReader(csvfile)
         upd_md_file_name = f'updated-{os.path.basename(metadata_csv)}'
-        with open(f'{output_path}{upd_md_file_name}', 'w') as updated_csv:
+        with open(f'{output_directory}{upd_md_file_name}', 'w') as updated_csv:
             writer = csv.DictWriter(updated_csv, fieldnames=reader.fieldnames)
             writer.writeheader()
             for row in reader:

tests/conftest.py

@@ -5,7 +5,7 @@
 import pytest
 import requests_mock
 
-from dsaps import metadata, models
+from dsaps import models
 
 
 @pytest.fixture()
@@ -41,14 +41,6 @@ def aspace_delimited_csv():
         yield reader
 
 
-@pytest.fixture()
-def json_metadata_delim():
-    json_metadata = metadata.create_json_metadata(
-        'tests/fixtures/metadata_delim.csv', 'delimited'
-    )
-    return json_metadata
-
-
 @pytest.fixture()
 def aspace_mapping():
     with open('config/aspace_mapping.json') as f:
@@ -63,14 +55,6 @@ def standard_mapping():
         yield mapping
 
 
-@pytest.fixture()
-def json_metadata_num_col():
-    json_metadata = metadata.create_json_metadata(
-        'tests/fixtures/metadata_num_col.csv', 'num_columns'
-    )
-    return json_metadata
-
-
 @pytest.fixture()
 def output_dir(tmp_path):
     output_dir = tmp_path / 'output'
@@ -84,7 +68,7 @@ def runner():
 
 
 @pytest.fixture(autouse=True)
-def web_mock(input_dir):
+def web_mock():
     with requests_mock.Mocker() as m:
         cookies = {'JSESSIONID': '11111111'}
         m.post('mock://example.com/login', cookies=cookies)

tests/test_cli.py

@@ -12,7 +12,7 @@ def test_additems(runner, input_dir):
                             'tests/fixtures/metadata_delim.csv',
                             '--field-map',
                             'tests/fixtures/standard_mapping.json',
-                            '--directory', input_dir,
+                            '--content-directory', input_dir,
                             '--file-type', 'pdf',
                             '--collection-handle', '333.3333'])
     assert result.exit_code == 0
@@ -28,7 +28,7 @@ def test_additems(runner, input_dir):
                             'tests/fixtures/metadata_delim.csv',
                             '--field-map',
                             'tests/fixtures/standard_mapping.json',
-                            '--directory', input_dir,
+                            '--content-directory', input_dir,
                             '--file-type', 'pdf'])
     assert result.exit_code == 0
 
@@ -45,16 +45,17 @@ def test_newcollection(runner, input_dir):
     assert result.exit_code == 0
 
 
-# def test_reconcile(runner, input_dir, output_dir):
-#     """Test reconcile command."""
-#     result = runner.invoke(main,
-#                            ['--url', 'mock://example.com/',
-#                             '--email', 'test@test.mock',
-#                             '--password', '1234',
-#                             'reconcile',
-#                             '--metadata_csv', 'tests/fixtures/metadata_delim.csv',
-#                             '--file_path', input_dir,
-#                             '--file_type', 'pdf',
-#                             '--output_path', output_dir
-#                             ])
-#     assert result.exit_code == 0
+def test_reconcile(runner, input_dir, output_dir):
+    """Test reconcile command."""
+    result = runner.invoke(main,
+                           ['--url', 'mock://example.com/',
+                            '--email', 'test@test.mock',
+                            '--password', '1234',
+                            'reconcile',
+                            '--metadata-csv',
+                            'tests/fixtures/metadata_delim.csv',
+                            '--output-directory', output_dir,
+                            '--content-directory', input_dir,
+                            '--file-type', 'pdf'
+                            ])
+    assert result.exit_code == 0