Integration and regression tests

batbot/batbot_cli.py

@@ -319,8 +319,7 @@ def preprocess(
                 )
                 data['output_path'].extend(output_paths)
                 data['compressed_path'].extend(compressed_paths)
-                if process_metadata:
-                    data['metadata_path'].append(metadata_path)
+                data['metadata_path'].append(metadata_path)
             except Exception as e:
                 warnings.warn('WARNING: Pipeline failed for file {}'.format(file))
                 data['failed_files'].append((str(file), e))
@@ -356,18 +355,16 @@ def preprocess(
         )
         data['output_path'].extend(output_paths)
         data['compressed_path'].extend(compressed_paths)
-        if process_metadata:
-            data['metadata_path'].extend(metadata_paths)
+        data['metadata_path'].extend(metadata_paths)
         data['failed_files'].extend(failed_files)
 
     if output_json is None:
         print('\nFull spectrogram output paths:')
         pprint.pp(sorted(data['output_path']))
         print('\nCompressed spectrogram output paths:')
         pprint.pp(sorted(data['compressed_path']))
-        if process_metadata:
-            print('\nProcessed metadata paths:')
-            pprint.pp(sorted(data['metadata_path']))
+        print('\nProcessed metadata paths:')
+        pprint.pp(sorted(data['metadata_path']))
         print('\nFiles skipped due to failure, and corresponding exceptions:')
         pprint.pp(sorted(data['failed_files']))
     else:

tests/test_preprocess.py

@@ -0,0 +1,48 @@
+import json
+import os
+
+from click.testing import CliRunner
+
+from batbot.batbot_cli import preprocess
+
+
+def test_preprocess():
+    """Test of batbot preprocess CLI ensuring the example files are processed without error.
+    Additionally, a regression test ensuring that the number of detected bat calls in the examples
+    does not decrease. The minumum numbers of bat call segments listed below correspond to the number
+    of bat call segments detected at the time of writing minus detected noise segments (noise counted by hand).
+    Note that this test uses "fast mode" processing, which is more permissive of low-amplitude calls and noise.
+    """
+    runner = CliRunner()
+    data = runner.invoke(preprocess, ['examples', '-o', './output', '--force-overwrite'])
+    assert data.exit_code == 0
+    # parse stdout to ensure example files were processed properly
+    num_examples = 4
+    output_str = str(data.output).split('\n')
+    for ii in range(num_examples):
+        expected_file = './output/example{}.01of01.compressed.jpg'.format(ii + 1)
+        assert any(
+            [expected_file in x for x in output_str]
+        ), 'Did not find file listed among outputs: {}'.format(expected_file)
+        assert os.path.exists(expected_file), 'Did not find file on filesystem: {}'.format(
+            expected_file
+        )
+    num_min_call_segments = [65, 18, 149, 47]
+    for ii in range(num_examples):
+        expected_file = './output/example{}.metadata.json'.format(ii + 1)
+        assert any(
+            [expected_file in x for x in output_str]
+        ), 'Did not find file listed among outputs: {}'.format(expected_file)
+        assert os.path.exists(expected_file), 'Did not find file on filesystem: {}'.format(
+            expected_file
+        )
+        # load metadata file and ensure minimum number of call segments were detected
+        with open(expected_file) as hf:
+            data = json.load(hf)
+        n_segments = len(data['segments'])
+        err_str = (
+            'Expected at least {} bat call segments in file {}, found only {} segments'.format(
+                num_min_call_segments[ii], expected_file, n_segments
+            )
+        )
+        assert n_segments >= num_min_call_segments[ii], err_str

tests/test_preprocess_parallel.py

@@ -0,0 +1,32 @@
+import os
+
+from click.testing import CliRunner
+
+from batbot.batbot_cli import preprocess
+
+
+def test_preprocess_parallel():
+    runner = CliRunner()
+    data = runner.invoke(
+        preprocess,
+        ['examples', '-o', './output', '--process-metadata', '--force-overwrite', '-n', 4],
+    )
+    # parse stdout to ensure example files were processed properly
+    num_examples = 4
+    output_str = str(data.output).split('\n')
+    for ii in range(num_examples):
+        expected_file = './output/example{}.01of01.compressed.jpg'.format(ii + 1)
+        assert any(
+            [expected_file in x for x in output_str]
+        ), 'Did not find file listed among outputs: {}'.format(expected_file)
+        assert os.path.exists(expected_file), 'Did not find file in filesystem: {}'.format(
+            expected_file
+        )
+    for ii in range(num_examples):
+        expected_file = './output/example{}.metadata.json'.format(ii + 1)
+        assert any(
+            [expected_file in x for x in output_str]
+        ), 'Did not find file listed among outputs: {}'.format(expected_file)
+        assert os.path.exists(expected_file), 'Did not find file in filesystem: {}'.format(
+            expected_file
+        )