Issue251 cli init command

annif/cli.py

@@ -123,6 +123,17 @@ def run_show_project(project_id):
     click.echo(template.format('Access:', proj.access.name))
 
 
+@cli.command('clear')
+@click.argument('project_id')
+@common_options
+def run_clear_project(project_id):
+    """
+    Initialize the project to its original, untrained state.
+    """
+    proj = get_project(project_id)
+    proj.remove_model_data()
+
+
 @cli.command('loadvoc')
 @click.argument('project_id')
 @click.argument('subjectfile', type=click.Path(dir_okay=False))

annif/project.py

@@ -7,6 +7,7 @@
 import joblib
 from sklearn.feature_extraction.text import TfidfVectorizer
 from flask import current_app
+from shutil import rmtree
 import annif
 import annif.analyzer
 import annif.corpus
@@ -217,6 +218,17 @@ def dump(self):
                 'backend': {'backend_id': self.config['backend']}
                 }
 
+    def remove_model_data(self):
+        """remove the data of this project"""
+        datadir_path = self._datadir_path
+        if os.path.isdir(datadir_path):
+            rmtree(datadir_path)
+            logger.info('Removed model data for project {}.'
+                        .format(self.project_id))
+        else:
+            logger.warning('No model data to remove for project {}.'
+                           .format(self.project_id))
+
 
 def _create_projects(projects_file, datadir, init_projects):
     if not os.path.exists(projects_file):

tests/test_cli.py

@@ -84,6 +84,29 @@ def test_show_project_nonexistent():
     assert failed_result.exception
 
 
+def test_clear_project(testdatadir):
+    dirpath = os.path.join(str(testdatadir), 'projects', 'dummy-fi')
+    fpath = os.path.join(str(dirpath), 'test_clear_project_datafile')
+    os.makedirs(dirpath)
+    open(fpath, 'a').close()
+
+    assert runner.invoke(
+        annif.cli.cli,
+        ['clear', 'dummy-fi']).exit_code == 0
+    assert not os.path.isdir(dirpath)
+
+
+def test_clear_project_nonexistent_data(testdatadir, caplog):
+    logger = annif.logger
+    logger.propagate = True
+    runner.invoke(
+        annif.cli.cli,
+        ['clear', 'dummy-fi']).exit_code != 0
+    assert len(caplog.records) == 1
+    expected_msg = 'No model data to remove for project dummy-fi.'
+    assert expected_msg == caplog.records[0].message
+
+
 def test_loadvoc_tsv(testdatadir):
     with contextlib.suppress(FileNotFoundError):
         os.remove(str(testdatadir.join('projects/tfidf-fi/subjects')))