Update tests

Remove beam test

Update test

Unskip

Unskip tests

spacy/tests/parser/test_add_label.py

@@ -44,8 +44,6 @@ def _train_parser(parser):
     return parser
 
 
-# Segfaulting due to refactor. Need to fix.
-@pytest.mark.skip
 def test_add_label(parser):
     parser = _train_parser(parser)
     parser.add_label("right")
@@ -64,8 +62,6 @@ def test_add_label(parser):
     assert doc[2].dep_ == "left"
 
 
-# segfaulting due to refactor. need to fix.
-@pytest.mark.skip
 def test_add_label_deserializes_correctly():
     config = {"learn_tokens": False, "min_action_freq": 30, "beam_width": 1, "beam_update_prob": 1.0}
     ner1 = EntityRecognizer(Vocab(), default_ner(), **config)
@@ -82,8 +78,6 @@ def test_add_label_deserializes_correctly():
     for i in range(ner1.moves.n_moves):
         assert ner1.moves.get_class_name(i) == ner2.moves.get_class_name(i)
 
-# segfaulting due to refactor. need to fix.
-@pytest.mark.skip
 @pytest.mark.parametrize(
     "pipe_cls,n_moves,model",
     [(DependencyParser, 5, default_parser()), (EntityRecognizer, 4, default_ner())],

spacy/tests/parser/test_arc_eager_oracle.py

@@ -13,8 +13,9 @@ from spacy.syntax.arc_eager import ArcEager
 def get_sequence_costs(M, words, heads, deps, transitions):
     doc = Doc(Vocab(), words=words)
     example = Example.from_dict(doc, {"heads": heads, "deps": deps})
-    state = StateClass(doc)
+    states, golds, _ = M.init_gold_batch([example])
-    M.preprocess_gold(example)
+    state = states[0]
+    gold = golds[0]
     cost_history = []
     for gold_action in transitions:
         state_costs = {}
@@ -23,6 +24,7 @@ def get_sequence_costs(M, words, heads, deps, transitions):
             state_costs[name] = M.get_cost(state, gold, i)
         M.transition(state, gold_action)
         cost_history.append(state_costs)
+        gold.update(state)
     return state, cost_history
 
 
@@ -59,7 +61,6 @@ def gold(doc, words):
         raise NotImplementedError
 
 
-@pytest.mark.xfail
 def test_oracle_four_words(arc_eager, vocab):
     words = ["a", "b", "c", "d"]
     heads = [1, 1, 3, 3]
@@ -144,12 +145,11 @@ def test_get_oracle_actions():
     parser.moves.add_action(1, "")
     parser.moves.add_action(1, "")
     parser.moves.add_action(4, "ROOT")
+    heads, deps = projectivize(heads, deps)
     for i, (head, dep) in enumerate(zip(heads, deps)):
         if head > i:
             parser.moves.add_action(2, dep)
         elif head < i:
             parser.moves.add_action(3, dep)
-    heads, deps = projectivize(heads, deps)
     example = Example.from_dict(doc, {"words": words, "tags": tags, "heads": heads, "deps": deps})
-    parser.moves.preprocess_gold(example)
     parser.moves.get_oracle_sequence(example)

spacy/tests/parser/test_nn_beam.py

@@ -1,100 +0,0 @@
-import pytest
-import numpy
-from spacy.vocab import Vocab
-from spacy.language import Language
-from spacy.pipeline.defaults import default_parser
-from spacy.pipeline import DependencyParser
-from spacy.syntax.arc_eager import ArcEager
-from spacy.tokens import Doc
-from spacy.syntax.stateclass import StateClass
-
-
-@pytest.fixture
-def vocab():
-    return Vocab()
-
-
-@pytest.fixture
-def moves(vocab):
-    aeager = ArcEager(vocab.strings, {})
-    aeager.add_action(2, "nsubj")
-    aeager.add_action(3, "dobj")
-    aeager.add_action(2, "aux")
-    return aeager
-
-
-@pytest.fixture
-def docs(vocab):
-    return [Doc(vocab, words=["Rats", "bite", "things"])]
-
-
-@pytest.fixture
-def states(docs):
-    return [StateClass(doc) for doc in docs]
-
-
-@pytest.fixture
-def tokvecs(docs, vector_size):
-    output = []
-    for doc in docs:
-        vec = numpy.random.uniform(-0.1, 0.1, (len(doc), vector_size))
-        output.append(numpy.asarray(vec))
-    return output
-
-
-@pytest.fixture
-def batch_size(docs):
-    return len(docs)
-
-
-@pytest.fixture
-def beam_width():
-    return 4
-
-
-@pytest.fixture
-def vector_size():
-    return 6
-
-
-@pytest.fixture
-def beam(moves, states, golds, beam_width):
-    return ParserBeam(moves, states, golds, width=beam_width, density=0.0)
-
-
-@pytest.fixture
-def scores(moves, batch_size, beam_width):
-    return [
-        numpy.asarray(
-            numpy.random.uniform(-0.1, 0.1, (batch_size, moves.n_moves)), dtype="f"
-        )
-        for _ in range(batch_size)
-    ]
-
-
-# All tests below are skipped after removing Beam stuff during the Example/GoldParse refactor
-@pytest.mark.skip
-def test_create_beam(beam):
-    pass
-
-
-@pytest.mark.skip
-def test_beam_advance(beam, scores):
-    beam.advance(scores)
-
-
-@pytest.mark.skip
-def test_beam_advance_too_few_scores(beam, scores):
-    with pytest.raises(IndexError):
-        beam.advance(scores[:-1])
-
-
-@pytest.mark.skip
-def test_beam_parse():
-    nlp = Language()
-    config = {"learn_tokens": False, "min_action_freq": 30, "beam_width":  1, "beam_update_prob": 1.0}
-    nlp.add_pipe(DependencyParser(nlp.vocab, default_parser(), **config), name="parser")
-    nlp.parser.add_label("nsubj")
-    nlp.parser.begin_training([], token_vector_width=8, hidden_width=8)
-    doc = nlp.make_doc("Australia is a country")
-    nlp.parser(doc, beam_width=2)

spacy/tests/parser/test_parse.py

@@ -22,7 +22,6 @@ TRAIN_DATA = [
 ]
 
 
-@pytest.mark.skip # Segfault
 def test_parser_root(en_tokenizer):
     text = "i don't have other assistance"
     heads = [3, 2, 1, 0, 1, -2]
@@ -33,9 +32,8 @@ def test_parser_root(en_tokenizer):
         assert t.dep != 0, t.text
 
 
-#@pytest.mark.xfail
+@pytest.mark.xfail
 #@pytest.mark.parametrize("text", ["Hello"])
-@pytest.mark.skip # Segfault
 def test_parser_parse_one_word_sentence(en_tokenizer, en_parser, text):
     tokens = en_tokenizer(text)
     doc = get_doc(
@@ -48,7 +46,6 @@ def test_parser_parse_one_word_sentence(en_tokenizer, en_parser, text):
     assert doc[0].dep != 0
 
 
-@pytest.mark.skip # Segfault
 def test_parser_initial(en_tokenizer, en_parser):
     text = "I ate the pizza with anchovies."
     # heads = [1, 0, 1, -2, -3, -1, -5]
@@ -61,7 +58,6 @@ def test_parser_initial(en_tokenizer, en_parser):
     assert tokens[3].head.i == 3
 
 
-@pytest.mark.skip # Segfault
 def test_parser_parse_subtrees(en_tokenizer, en_parser):
     text = "The four wheels on the bus turned quickly"
     heads = [2, 1, 4, -1, 1, -2, 0, -1]
@@ -76,7 +72,6 @@ def test_parser_parse_subtrees(en_tokenizer, en_parser):
     assert len(list(doc[2].subtree)) == 6
 
 
-@pytest.mark.skip # Segfault
 def test_parser_merge_pp(en_tokenizer):
     text = "A phrase with another phrase occurs"
     heads = [1, 4, -1, 1, -2, 0]
@@ -95,7 +90,6 @@ def test_parser_merge_pp(en_tokenizer):
     assert doc[3].text == "occurs"
 
 
-@pytest.mark.skip # Segfault
 def test_parser_arc_eager_finalize_state(en_tokenizer, en_parser):
     text = "a b c d e"
 
@@ -170,7 +164,6 @@ def test_parser_arc_eager_finalize_state(en_tokenizer, en_parser):
     assert tokens[4].head.i == 4
 
 
-@pytest.mark.skip # Segfault
 def test_parser_set_sent_starts(en_vocab):
     # fmt: off
     words = ['Ein', 'Satz', '.', 'Außerdem', 'ist', 'Zimmer', 'davon', 'überzeugt', ',', 'dass', 'auch', 'epige-', '\n', 'netische', 'Mechanismen', 'eine', 'Rolle', 'spielen', ',', 'also', 'Vorgänge', ',', 'die', '\n', 'sich', 'darauf', 'auswirken', ',', 'welche', 'Gene', 'abgelesen', 'werden', 'und', '\n', 'welche', 'nicht', '.', '\n']
@@ -187,7 +180,6 @@ def test_parser_set_sent_starts(en_vocab):
         for token in sent:
             assert token.head in sent
 
-@pytest.mark.skip
 def test_overfitting_IO():
     # Simple test to try and quickly overfit the dependency parser - ensuring the ML models work correctly
     nlp = English()

spacy/tests/parser/test_preset_sbd.py

@@ -33,14 +33,12 @@ def parser(vocab):
     return parser
 
 
-@pytest.mark.skip # Segfaults
 def test_no_sentences(parser):
     doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
     doc = parser(doc)
     assert len(list(doc.sents)) >= 1
 
 
-@pytest.mark.skip # Segfaults
 def test_sents_1(parser):
     doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
     doc[2].sent_start = True
@@ -54,7 +52,6 @@ def test_sents_1(parser):
     assert len(list(doc.sents)) == 2
 
 
-@pytest.mark.skip # Segfaults
 def test_sents_1_2(parser):
     doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
     doc[1].sent_start = True
@@ -63,7 +60,6 @@ def test_sents_1_2(parser):
     assert len(list(doc.sents)) >= 3
 
 
-@pytest.mark.skip # Segfaults
 def test_sents_1_3(parser):
     doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
     doc[1].sent_start = True