Update tests for pytest 4.x (#2965)

<!--- Provide a general summary of your changes in the title. -->

## Description
- [x] Replace marks in params for pytest 4.0 compat ([see here](https://docs.pytest.org/en/latest/deprecations.html#marks-in-pytest-mark-parametrize))
- [x] Un-xfail passing tests (some fixes in a recent update resolved a bunch of issues, but tests were apparently never updated here)

### Types of change
<!-- What type of change does your PR cover? Is it a bug fix, an enhancement
or new feature, or a change to the documentation? -->

## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.

requirements.txt

@@ -10,6 +10,6 @@ ujson>=1.35
 dill>=0.2,<0.3
 regex>=2017.4.5,<2017.12.1
 requests>=2.13.0,<3.0.0
-pytest>=3.6.0,<4.0.0
+pytest>=4.0.0,<5.0.0
 mock>=2.0.0,<3.0.0
 pathlib==1.0.1; python_version < "3.4"

spacy/tests/lang/de/test_exceptions.py

@@ -33,7 +33,6 @@ def test_de_tokenizer_norm_exceptions(de_tokenizer, text, norms):
     assert [token.norm_ for token in tokens] == norms
 
 
-@pytest.mark.xfail
 @pytest.mark.parametrize('text,norm', [("daß", "dass")])
 def test_de_lex_attrs_norm_exceptions(de_tokenizer, text, norm):
     tokens = de_tokenizer(text)

spacy/tests/lang/en/test_sbd.py

@@ -61,7 +61,7 @@ def test_en_sbd_serialization_projective(EN):
 
 
 TEST_CASES = [
-    pytest.mark.xfail(("Hello World. My name is Jonas.", ["Hello World.", "My name is Jonas."])),
+    pytest.param("Hello World. My name is Jonas.", ["Hello World.", "My name is Jonas."], marks=pytest.mark.xfail()),
     ("What is your name? My name is Jonas.", ["What is your name?", "My name is Jonas."]),
     ("There it is! I found it.", ["There it is!", "I found it."]),
     ("My name is Jonas E. Smith.", ["My name is Jonas E. Smith."]),
@@ -71,48 +71,48 @@ TEST_CASES = [
     ("Let's ask Jane and co. They should know.", ["Let's ask Jane and co.", "They should know."]),
     ("They closed the deal with Pitt, Briggs & Co. It closed yesterday.", ["They closed the deal with Pitt, Briggs & Co.", "It closed yesterday."]),
     ("I can see Mt. Fuji from here.", ["I can see Mt. Fuji from here."]),
-    pytest.mark.xfail(("St. Michael's Church is on 5th st. near the light.", ["St. Michael's Church is on 5th st. near the light."])),
+    pytest.param("St. Michael's Church is on 5th st. near the light.", ["St. Michael's Church is on 5th st. near the light."], marks=pytest.mark.xfail()),
     ("That is JFK Jr.'s book.", ["That is JFK Jr.'s book."]),
     ("I visited the U.S.A. last year.", ["I visited the U.S.A. last year."]),
     ("I live in the E.U. How about you?", ["I live in the E.U.", "How about you?"]),
     ("I live in the U.S. How about you?", ["I live in the U.S.", "How about you?"]),
     ("I work for the U.S. Government in Virginia.", ["I work for the U.S. Government in Virginia."]),
     ("I have lived in the U.S. for 20 years.", ["I have lived in the U.S. for 20 years."]),
-    pytest.mark.xfail(("At 5 a.m. Mr. Smith went to the bank. He left the bank at 6 P.M. Mr. Smith then went to the store.", ["At 5 a.m. Mr. Smith went to the bank.", "He left the bank at 6 P.M.", "Mr. Smith then went to the store."])),
+    pytest.param("At 5 a.m. Mr. Smith went to the bank. He left the bank at 6 P.M. Mr. Smith then went to the store.", ["At 5 a.m. Mr. Smith went to the bank.", "He left the bank at 6 P.M.", "Mr. Smith then went to the store."], marks=pytest.mark.xfail()),
     ("She has $100.00 in her bag.", ["She has $100.00 in her bag."]),
     ("She has $100.00. It is in her bag.", ["She has $100.00.", "It is in her bag."]),
     ("He teaches science (He previously worked for 5 years as an engineer.) at the local University.", ["He teaches science (He previously worked for 5 years as an engineer.) at the local University."]),
     ("Her email is Jane.Doe@example.com. I sent her an email.", ["Her email is Jane.Doe@example.com.", "I sent her an email."]),
     ("The site is: https://www.example.50.com/new-site/awesome_content.html. Please check it out.", ["The site is: https://www.example.50.com/new-site/awesome_content.html.", "Please check it out."]),
-    pytest.mark.xfail(("She turned to him, 'This is great.' she said.", ["She turned to him, 'This is great.' she said."])),
+    pytest.param("She turned to him, 'This is great.' she said.", ["She turned to him, 'This is great.' she said."], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(('She turned to him, "This is great." she said.', ['She turned to him, "This is great." she said.'])),
+    pytest.param('She turned to him, "This is great." she said.', ['She turned to him, "This is great." she said.'], marks=pytest.mark.xfail()),
     ('She turned to him, "This is great." She held the book out to show him.', ['She turned to him, "This is great."', "She held the book out to show him."]),
     ("Hello!! Long time no see.", ["Hello!!", "Long time no see."]),
     ("Hello?? Who is there?", ["Hello??", "Who is there?"]),
     ("Hello!? Is that you?", ["Hello!?", "Is that you?"]),
     ("Hello?! Is that you?", ["Hello?!", "Is that you?"]),
-    pytest.mark.xfail(("1.) The first item 2.) The second item", ["1.) The first item", "2.) The second item"])),
+    pytest.param("1.) The first item 2.) The second item", ["1.) The first item", "2.) The second item"], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("1.) The first item. 2.) The second item.", ["1.) The first item.", "2.) The second item."])),
+    pytest.param("1.) The first item. 2.) The second item.", ["1.) The first item.", "2.) The second item."], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("1) The first item 2) The second item", ["1) The first item", "2) The second item"])),
+    pytest.param("1) The first item 2) The second item", ["1) The first item", "2) The second item"], marks=pytest.mark.xfail()),
     ("1) The first item. 2) The second item.", ["1) The first item.", "2) The second item."]),
-    pytest.mark.xfail(("1. The first item 2. The second item", ["1. The first item", "2. The second item"])),
+    pytest.param("1. The first item 2. The second item", ["1. The first item", "2. The second item"], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("1. The first item. 2. The second item.", ["1. The first item.", "2. The second item."])),
+    pytest.param("1. The first item. 2. The second item.", ["1. The first item.", "2. The second item."], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("• 9. The first item • 10. The second item", ["• 9. The first item", "• 10. The second item"])),
+    pytest.param("• 9. The first item • 10. The second item", ["• 9. The first item", "• 10. The second item"], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("⁃9. The first item ⁃10. The second item", ["⁃9. The first item", "⁃10. The second item"])),
+    pytest.param("⁃9. The first item ⁃10. The second item", ["⁃9. The first item", "⁃10. The second item"], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("a. The first item b. The second item c. The third list item", ["a. The first item", "b. The second item", "c. The third list item"])),
+    pytest.param("a. The first item b. The second item c. The third list item", ["a. The first item", "b. The second item", "c. The third list item"], marks=pytest.mark.xfail()),
     ("This is a sentence\ncut off in the middle because pdf.", ["This is a sentence\ncut off in the middle because pdf."]),
     ("It was a cold \nnight in the city.", ["It was a cold \nnight in the city."]),
-    pytest.mark.xfail(("features\ncontact manager\nevents, activities\n", ["features", "contact manager", "events, activities"])),
+    pytest.param("features\ncontact manager\nevents, activities\n", ["features", "contact manager", "events, activities"], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("You can find it at N°. 1026.253.553. That is where the treasure is.", ["You can find it at N°. 1026.253.553.", "That is where the treasure is."])),
+    pytest.param("You can find it at N°. 1026.253.553. That is where the treasure is.", ["You can find it at N°. 1026.253.553.", "That is where the treasure is."], marks=pytest.mark.xfail()),
     ("She works at Yahoo! in the accounting department.", ["She works at Yahoo! in the accounting department."]),
     ("We make a good team, you and I. Did you see Albert I. Jones yesterday?", ["We make a good team, you and I.", "Did you see Albert I. Jones yesterday?"]),
     ("Thoreau argues that by simplifying one’s life, “the laws of the universe will appear less complex. . . .”", ["Thoreau argues that by simplifying one’s life, “the laws of the universe will appear less complex. . . .”"]),
-    pytest.mark.xfail((""""Bohr [...] used the analogy of parallel stairways [...]" (Smith 55).""", ['"Bohr [...] used the analogy of parallel stairways [...]" (Smith 55).'])),
+    pytest.param(""""Bohr [...] used the analogy of parallel stairways [...]" (Smith 55).""", ['"Bohr [...] used the analogy of parallel stairways [...]" (Smith 55).'], marks=pytest.mark.xfail()),
     ("If words are left off at the end of a sentence, and that is all that is omitted, indicate the omission with ellipsis marks (preceded and followed by a space) and then indicate the end of the sentence with a period . . . . Next sentence.", ["If words are left off at the end of a sentence, and that is all that is omitted, indicate the omission with ellipsis marks (preceded and followed by a space) and then indicate the end of the sentence with a period . . . .", "Next sentence."]),
     ("I never meant that.... She left the store.", ["I never meant that....", "She left the store."]),
-    pytest.mark.xfail(("I wasn’t really ... well, what I mean...see . . . what I'm saying, the thing is . . . I didn’t mean it.", ["I wasn’t really ... well, what I mean...see . . . what I'm saying, the thing is . . . I didn’t mean it."])),
+    pytest.param("I wasn’t really ... well, what I mean...see . . . what I'm saying, the thing is . . . I didn’t mean it.", ["I wasn’t really ... well, what I mean...see . . . what I'm saying, the thing is . . . I didn’t mean it."], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("One further habit which was somewhat weakened . . . was that of combining words into self-interpreting compounds. . . . The practice was not abandoned. . . .", ["One further habit which was somewhat weakened . . . was that of combining words into self-interpreting compounds.", ". . . The practice was not abandoned. . . ."])),
+    pytest.param("One further habit which was somewhat weakened . . . was that of combining words into self-interpreting compounds. . . . The practice was not abandoned. . . .", ["One further habit which was somewhat weakened . . . was that of combining words into self-interpreting compounds.", ". . . The practice was not abandoned. . . ."], marks=pytest.mark.xfail()),
-    pytest.mark.xfail(("Hello world.Today is Tuesday.Mr. Smith went to the store and bought 1,000.That is a lot.", ["Hello world.", "Today is Tuesday.", "Mr. Smith went to the store and bought 1,000.", "That is a lot."]))
+    pytest.param("Hello world.Today is Tuesday.Mr. Smith went to the store and bought 1,000.That is a lot.", ["Hello world.", "Today is Tuesday.", "Mr. Smith went to the store and bought 1,000.", "That is a lot."], marks=pytest.mark.xfail())
 ]
 
 @pytest.mark.skip

spacy/tests/lang/en/test_text.py

@@ -29,7 +29,7 @@ untimely death" of the rapier-tongued Scottish barrister and parliamentarian.
     ("""Yes! "I'd rather have a walk", Ms. Comble sighed. """, 15),
     ("""'Me too!', Mr. P. Delaware cried. """, 11),
     ("They ran about 10km.", 6),
-    pytest.mark.xfail(("But then the 6,000-year ice age came...", 10))])
+    pytest.param("But then the 6,000-year ice age came...", 10, marks=pytest.mark.xfail())])
 def test_en_tokenizer_handles_cnts(en_tokenizer, text, length):
     tokens = en_tokenizer(text)
     assert len(tokens) == length

spacy/tests/lang/hu/test_tokenizer.py

@@ -5,11 +5,11 @@ import pytest
 
 DEFAULT_TESTS = [
     ('N. kormányzósági\nszékhely.', ['N.', 'kormányzósági', 'székhely', '.']),
-    pytest.mark.xfail(('A .hu egy tld.', ['A', '.hu', 'egy', 'tld', '.'])),
+    pytest.param('A .hu egy tld.', ['A', '.hu', 'egy', 'tld', '.'], marks=pytest.mark.xfail()),
     ('Az egy.ketto pelda.', ['Az', 'egy.ketto', 'pelda', '.']),
     ('A pl. rovidites.', ['A', 'pl.', 'rovidites', '.']),
     ('A S.M.A.R.T. szo.', ['A', 'S.M.A.R.T.', 'szo', '.']),
-    pytest.mark.xfail(('A .hu.', ['A', '.hu', '.'])),
+    pytest.param('A .hu.', ['A', '.hu', '.'], marks=pytest.mark.xfail()),
     ('Az egy.ketto.', ['Az', 'egy.ketto', '.']),
     ('A pl.', ['A', 'pl.']),
     ('A S.M.A.R.T.', ['A', 'S.M.A.R.T.']),
@@ -227,11 +227,11 @@ QUOTE_TESTS = [
 
 DOT_TESTS = [
     ('N. kormányzósági\nszékhely.', ['N.', 'kormányzósági', 'székhely', '.']),
-    pytest.mark.xfail(('A .hu egy tld.', ['A', '.hu', 'egy', 'tld', '.'])),
+    pytest.param('A .hu egy tld.', ['A', '.hu', 'egy', 'tld', '.'], marks=pytest.mark.xfail()),
     ('Az egy.ketto pelda.', ['Az', 'egy.ketto', 'pelda', '.']),
     ('A pl. rövidítés.', ['A', 'pl.', 'rövidítés', '.']),
     ('A S.M.A.R.T. szó.', ['A', 'S.M.A.R.T.', 'szó', '.']),
-    pytest.mark.xfail(('A .hu.', ['A', '.hu', '.'])),
+    pytest.param('A .hu.', ['A', '.hu', '.'], marks=pytest.mark.xfail()),
     ('Az egy.ketto.', ['Az', 'egy.ketto', '.']),
     ('A pl.', ['A', 'pl.']),
     ('A S.M.A.R.T.', ['A', 'S.M.A.R.T.']),

spacy/tests/regression/test_issue1547.py

@@ -7,7 +7,6 @@ from ...vocab import Vocab
 from ...tokens import Doc, Span
 
 
-@pytest.mark.xfail
 def test_issue1547():
     """Test that entity labels still match after merging tokens."""
     words = ['\n', 'worda', '.', '\n', 'wordb', '-', 'Biosphere', '2', '-', ' \n']

spacy/tests/regression/test_issue1622.py

@@ -7,7 +7,6 @@ import pytest
 from ...cli.train import train
 
 
-@pytest.mark.xfail
 def test_cli_trained_model_can_be_saved(tmpdir):
     lang = 'nl'
     output_dir = str(tmpdir)

spacy/tests/regression/test_issue1945.py

@@ -6,7 +6,7 @@ from ...vocab import Vocab
 from ...tokens import Doc
 from ...matcher import Matcher
 
-@pytest.mark.xfail
+
 def test_issue1945():
     text = "a a a"
     matcher = Matcher(Vocab())

spacy/tests/regression/test_issue2385.py

@@ -4,7 +4,6 @@ import pytest
 from ...gold import iob_to_biluo
 
 
-@pytest.mark.xfail
 @pytest.mark.parametrize('tags', [('B-ORG', 'L-ORG'),
                                   ('B-PERSON', 'I-PERSON', 'L-PERSON'),
                                   ('U-BRAWLER', 'U-BRAWLER')])
@@ -13,21 +12,18 @@ def test_issue2385_biluo(tags):
     assert iob_to_biluo(tags) == list(tags)
 
 
-@pytest.mark.xfail
 @pytest.mark.parametrize('tags', [('B-BRAWLER', 'I-BRAWLER', 'I-BRAWLER')])
 def test_issue2385_iob_bcharacter(tags):
     """fix bug in labels with a 'b' character"""
     assert iob_to_biluo(tags) == ['B-BRAWLER', 'I-BRAWLER', 'L-BRAWLER']
 
 
-@pytest.mark.xfail
 @pytest.mark.parametrize('tags', [('I-ORG', 'I-ORG', 'B-ORG')])
 def test_issue2385_iob1(tags):
     """maintain support for iob1 format"""
     assert iob_to_biluo(tags) == ['B-ORG', 'L-ORG', 'U-ORG']
 
 
-@pytest.mark.xfail
 @pytest.mark.parametrize('tags', [('B-PERSON', 'I-PERSON', 'B-PERSON')])
 def test_issue2385_iob2(tags):
     """maintain support for iob2 format"""

spacy/tests/tokenizer/test_urls.py

@@ -47,16 +47,16 @@ URLS_SHOULD_MATCH = [
     "http://223.255.255.254",
     "http://a.b--c.de/", # this is a legit domain name see: https://gist.github.com/dperini/729294 comment on 9/9/2014
 
-    pytest.mark.xfail("http://foo.com/blah_blah_(wikipedia)"),
+    pytest.param("http://foo.com/blah_blah_(wikipedia)", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://foo.com/blah_blah_(wikipedia)_(again)"),
+    pytest.param("http://foo.com/blah_blah_(wikipedia)_(again)", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://⌘.ws"),
+    pytest.param("http://⌘.ws", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://⌘.ws/"),
+    pytest.param("http://⌘.ws/", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://☺.damowmow.com/"),
+    pytest.param("http://☺.damowmow.com/", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://✪df.ws/123"),
+    pytest.param("http://✪df.ws/123", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://➡.ws/䨹"),
+    pytest.param("http://➡.ws/䨹", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://مثال.إختبار"),
+    pytest.param("http://مثال.إختبار", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://例子.测试"),
+    pytest.param("http://例子.测试", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://उदाहरण.परीक्षा"),
+    pytest.param("http://उदाहरण.परीक्षा", marks=pytest.mark.xfail()),
 ]
 
 URLS_SHOULD_NOT_MATCH = [
@@ -95,10 +95,10 @@ URLS_SHOULD_NOT_MATCH = [
     "http://10.1.1.1",
     "NASDAQ:GOOG",
 
-    pytest.mark.xfail("foo.com"),
+    pytest.param("foo.com", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://1.1.1.1.1"),
+    pytest.param("http://1.1.1.1.1", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://www.foo.bar./"),
+    pytest.param("http://www.foo.bar./", marks=pytest.mark.xfail()),
-    pytest.mark.xfail("http://-a.b.co"),
+    pytest.param("http://-a.b.co", marks=pytest.mark.xfail()),
 ]