General code improvements

pyndl/__init__.py

@@ -62,9 +62,12 @@ def sysinfo():
 
     if uname.sysname == "Linux":
         _, *lines = os.popen("free -m").readlines()
-        for identifier in ["Mem:", "Swap:"]:
-            memory = [line for line in lines if identifier in line][0]
-            _, total, used, *_ = memory.split()
+        for identifier in ("Mem:", "Swap:"):
+            memory = [line for line in lines if identifier in line]
+            if len(memory) > 0:
+                _, total, used, *_ = memory[0].split()
+            else:
+                total, used = '?', '?'
             osinfo += "{} {}MiB/{}MiB\n".format(identifier, used, total)
 
     osinfo += "\n"

pyndl/corpus.py

@@ -68,8 +68,10 @@ def read_clean_gzfile(gz_file_path, *, break_duration=2.0):
                 text = word_tag.text
                 if text in PUNCTUATION:
                     words.append(text)
-                else:
+                elif text is not None:
                     words.extend((' ', text))
+                else:
+                    raise ValueError("Text content of word tag is None.")
             result = ''.join(words)
             result = result.strip()
 

pyndl/ndl.py

@@ -221,6 +221,11 @@ def worker():
 
 def _attributes(event_path, number_events, alpha, betas, lambda_, cpu_time,
                 wall_time, function, method=None, attrs=None):
+    if not isinstance(alpha, (float, int)):
+        alpha_str = 'varying'
+    else:
+        alpha_str = str(alpha)
+
     width = max([len(ss) for ss in (event_path,
                                     str(number_events),
                                     str(alpha),
@@ -235,13 +240,10 @@ def _attributes(event_path, number_events, alpha, betas, lambda_, cpu_time,
     def _format(value):
         return '{0: <{width}}'.format(value, width=width)
 
-    if not isinstance(alpha, (float, int)):
-        alpha = 'varying'
-
     new_attrs = {'date': _format(time.strftime("%Y-%m-%d %H:%M:%S")),
                  'event_path': _format(event_path),
                  'number_events': _format(number_events),
-                 'alpha': _format(str(alpha)),
+                 'alpha': _format(alpha_str),
                  'betas': _format(str(betas)),
                  'lambda': _format(str(lambda_)),
                  'function': _format(function),

tests/conftest.py

@@ -2,11 +2,22 @@
 Configuration for py.test-3.
 
 '''
+import pytest
 
 
 def pytest_addoption(parser):
     """
     adds custom option to the pytest parser
     """
     parser.addoption("--runslow", action="store_true",
-                     help="run slow tests")
+                     default=False, help="run slow tests")
+
+
+def pytest_collection_modifyitems(config, items):
+    if config.getoption("--runslow"):
+        # --runslow given in cli: do not skip slow tests
+        return
+    skip_slow = pytest.mark.skip(reason="need --runslow option to run")
+    for item in items:
+        if "slow" in item.keywords:
+            item.add_marker(skip_slow)

tests/test_activation.py

@@ -15,8 +15,6 @@
 from pyndl import ndl
 from pyndl.activation import activation
 
-slow = pytest.mark.skipif(not pytest.config.getoption("--runslow"),  # pylint: disable=invalid-name
-                          reason="need --runslow option to run")
 
 TEST_ROOT = os.path.join(os.path.pardir, os.path.dirname(__file__))
 FILE_PATH_SIMPLE = os.path.join(TEST_ROOT, "resources/event_file_simple.tab.gz")
@@ -140,7 +138,7 @@ def test_ignore_missing_cues_dict():
         assert np.allclose(reference_activations[outcome], activation_list)
 
 
-@slow
+@pytest.mark.slow
 def test_activation_matrix_large():
     """
     Test with a lot of data. Better run only with at least 12GB free RAM.