Clean up warnings in the test suite (#11331)

.github/azure-steps.yml

@@ -54,12 +54,12 @@ steps:
     condition: eq(${{ parameters.gpu }}, true)
 
   - script: |
-      ${{ parameters.prefix }} python -m pytest --pyargs spacy
+      ${{ parameters.prefix }} python -m pytest --pyargs spacy -W error
     displayName: "Run CPU tests"
     condition: eq(${{ parameters.gpu }}, false)
 
   - script: |
-      ${{ parameters.prefix }} python -m pytest --pyargs spacy -p spacy.tests.enable_gpu
+      ${{ parameters.prefix }} python -m pytest --pyargs spacy -W error -p spacy.tests.enable_gpu
     displayName: "Run GPU tests"
     condition: eq(${{ parameters.gpu }}, true)
 

spacy/tests/doc/test_doc_api.py

@@ -3,6 +3,7 @@
 import numpy
 from numpy.testing import assert_array_equal
 import pytest
+import warnings
 from thinc.api import NumpyOps, get_current_ops
 
 from spacy.attrs import DEP, ENT_IOB, ENT_TYPE, HEAD, IS_ALPHA, MORPH, POS
@@ -529,9 +530,9 @@ def test_doc_from_array_sent_starts(en_vocab):
     # no warning using default attrs
     attrs = doc._get_array_attrs()
     arr = doc.to_array(attrs)
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         new_doc.from_array(attrs, arr)
-        assert len(record) == 0
     # only SENT_START uses SENT_START
     attrs = [SENT_START]
     arr = doc.to_array(attrs)

spacy/tests/lang/ru/test_lemmatizer.py

@@ -2,6 +2,9 @@
 from spacy.tokens import Doc
 
 
+pytestmark = pytest.mark.filterwarnings("ignore::DeprecationWarning")
+
+
 def test_ru_doc_lemmatization(ru_lemmatizer):
     words = ["мама", "мыла", "раму"]
     pos = ["NOUN", "VERB", "NOUN"]

spacy/tests/lang/uk/test_lemmatizer.py

@@ -1,6 +1,10 @@
+import pytest
 from spacy.tokens import Doc
 
 
+pytestmark = pytest.mark.filterwarnings("ignore::DeprecationWarning")
+
+
 def test_uk_lemmatizer(uk_lemmatizer):
     """Check that the default uk lemmatizer runs."""
     doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"])

spacy/tests/matcher/test_phrase_matcher.py

@@ -1,4 +1,5 @@
 import pytest
+import warnings
 import srsly
 from mock import Mock
 
@@ -344,13 +345,13 @@ def test_phrase_matcher_validation(en_vocab):
         matcher.add("TEST1", [doc1])
     with pytest.warns(UserWarning):
         matcher.add("TEST2", [doc2])
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         matcher.add("TEST3", [doc3])
-        assert not record.list
     matcher = PhraseMatcher(en_vocab, attr="POS", validate=True)
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         matcher.add("TEST4", [doc2])
-        assert not record.list
 
 
 def test_attr_validation(en_vocab):

spacy/tests/pipeline/test_entity_linker.py

@@ -1048,6 +1048,10 @@ def test_no_gold_ents(patterns):
     for eg in train_examples:
         eg.predicted = ruler(eg.predicted)
 
+    # Entity ruler is no longer needed (initialization below wipes out the
+    # patterns and causes warnings)
+    nlp.remove_pipe("entity_ruler")
+
     def create_kb(vocab):
         # create artificial KB
         mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)

spacy/training/initialize.py

@@ -337,3 +337,5 @@ def ensure_shape(vectors_loc):
         # store all the results in a list in memory
         lines2 = open_file(vectors_loc)
         yield from lines2
+        lines2.close()
+    lines.close()