From 199943deb4da7c68f08f578b404dbc6208cc41ac Mon Sep 17 00:00:00 2001
From: Lj Miranda <ljvmiranda@gmail.com>
Date: Fri, 5 Nov 2021 10:33:53 +0800
Subject: [PATCH 01/37] Add simple script to add pytest marks

---
 spacy/tests/regression/util_add_marker.py | 41 +++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 spacy/tests/regression/util_add_marker.py

diff --git a/spacy/tests/regression/util_add_marker.py b/spacy/tests/regression/util_add_marker.py
new file mode 100644
index 000000000..94fa415bc
--- /dev/null
+++ b/spacy/tests/regression/util_add_marker.py
@@ -0,0 +1,41 @@
+import re
+from pathlib import Path
+from typing import Optional
+
+import typer
+
+
+def main(
+    filename: Path, out_file: Optional[Path] = typer.Option(None), dry_run: bool = False
+):
+    """Add pytest issue markers on regression tests
+
+    If --out-file is not used, it will overwrite the original file. You can set
+    the --dry-run flag to just see the changeset and not write to disk.
+    """
+    lines = []
+    with filename.open() as f:
+        lines = f.readlines()
+
+    # Regex pattern for matching common regression formats (e.g. test_issue1234)
+    pattern = r"def test_issue\d{1,4}"
+    regex = re.compile(pattern)
+
+    new_lines = []
+    for line_text in lines:
+        if regex.search(line_text):  # if match, append marker first
+            issue_num = int(re.findall(r"\d+", line_text)[0])  # Simple heuristic
+            typer.echo(f"Found: {line_text} with issue number: {issue_num}")
+            new_lines.append(f"@pytest.mark.issue({issue_num})\n")
+        new_lines.append(line_text)
+
+    # Save to file
+    if not dry_run:
+        out = out_file or filename
+        with out.open("w") as f:
+            for new_line in new_lines:
+                f.write(new_line)
+
+
+if __name__ == "__main__":
+    typer.run(main)

From 91dec2c76e9affbaafb62cc6a95b317db583c569 Mon Sep 17 00:00:00 2001
From: Lj Miranda <ljvmiranda@gmail.com>
Date: Fri, 5 Nov 2021 09:27:08 +0800
Subject: [PATCH 02/37] Decorate non-regression tests

---
 spacy/tests/lang/en/test_prefix_suffix_infix.py  | 1 +
 spacy/tests/lang/fr/test_prefix_suffix_infix.py  | 1 +
 spacy/tests/matcher/test_dependency_matcher.py   | 2 ++
 spacy/tests/matcher/test_matcher_logic.py        | 1 +
 spacy/tests/serialize/test_serialize_pipeline.py | 1 +
 5 files changed, 6 insertions(+)

diff --git a/spacy/tests/lang/en/test_prefix_suffix_infix.py b/spacy/tests/lang/en/test_prefix_suffix_infix.py
index 9dfb54fd6..a903496e8 100644
--- a/spacy/tests/lang/en/test_prefix_suffix_infix.py
+++ b/spacy/tests/lang/en/test_prefix_suffix_infix.py
@@ -119,6 +119,7 @@ def test_en_tokenizer_splits_period_abbr(en_tokenizer):
     assert tokens[4].text == "Mr."
 
 
+@pytest.mark.issue(225)
 @pytest.mark.xfail(reason="Issue #225 - not yet implemented")
 def test_en_tokenizer_splits_em_dash_infix(en_tokenizer):
     tokens = en_tokenizer(
diff --git a/spacy/tests/lang/fr/test_prefix_suffix_infix.py b/spacy/tests/lang/fr/test_prefix_suffix_infix.py
index 7770f807b..272531b63 100644
--- a/spacy/tests/lang/fr/test_prefix_suffix_infix.py
+++ b/spacy/tests/lang/fr/test_prefix_suffix_infix.py
@@ -4,6 +4,7 @@ from spacy.lang.punctuation import TOKENIZER_INFIXES
 from spacy.lang.char_classes import ALPHA
 
 
+@pytest.mark.issue(768)
 @pytest.mark.parametrize(
     "text,expected_tokens", [("l'avion", ["l'", "avion"]), ("j'ai", ["j'", "ai"])]
 )
diff --git a/spacy/tests/matcher/test_dependency_matcher.py b/spacy/tests/matcher/test_dependency_matcher.py
index 61ae43c52..1728c82af 100644
--- a/spacy/tests/matcher/test_dependency_matcher.py
+++ b/spacy/tests/matcher/test_dependency_matcher.py
@@ -370,6 +370,7 @@ def test_dependency_matcher_span_user_data(en_tokenizer):
             assert doc_t_i == span_t_i + offset
 
 
+@pytest.mark.issue(9263)
 def test_dependency_matcher_order_issue(en_tokenizer):
     # issue from #9263
     doc = en_tokenizer("I like text")
@@ -415,6 +416,7 @@ def test_dependency_matcher_order_issue(en_tokenizer):
     assert matches == []
 
 
+@pytest.mark.issue(9263)
 def test_dependency_matcher_remove(en_tokenizer):
     # issue from #9263
     doc = en_tokenizer("The red book")
diff --git a/spacy/tests/matcher/test_matcher_logic.py b/spacy/tests/matcher/test_matcher_logic.py
index dcbe1ff33..b96bb2032 100644
--- a/spacy/tests/matcher/test_matcher_logic.py
+++ b/spacy/tests/matcher/test_matcher_logic.py
@@ -152,6 +152,7 @@ def test_operator_combos(en_vocab):
             assert not matches, (string, pattern_str)
 
 
+@pytest.mark.issue(1450)
 def test_matcher_end_zero_plus(en_vocab):
     """Test matcher works when patterns end with * operator. (issue 1450)"""
     matcher = Matcher(en_vocab)
diff --git a/spacy/tests/serialize/test_serialize_pipeline.py b/spacy/tests/serialize/test_serialize_pipeline.py
index 05871a524..eebf72638 100644
--- a/spacy/tests/serialize/test_serialize_pipeline.py
+++ b/spacy/tests/serialize/test_serialize_pipeline.py
@@ -162,6 +162,7 @@ def test_serialize_tagger_strings(en_vocab, de_vocab, taggers):
         assert label in tagger2.vocab.strings
 
 
+@pytest.mark.issue(1105)
 def test_serialize_textcat_empty(en_vocab):
     # See issue #1105
     cfg = {"model": DEFAULT_SINGLE_TEXTCAT_MODEL}

From addeb34bc4538cada8f373a16ea89c46dcf63f07 Mon Sep 17 00:00:00 2001
From: Lj Miranda <ljvmiranda@gmail.com>
Date: Fri, 5 Nov 2021 09:27:19 +0800
Subject: [PATCH 03/37] Decorate regression tests

Even if the issue number is already in the file, I still
decorated them just to follow the convention found in test_issue8168.py
---
 spacy/tests/regression/test_issue1-1000.py    | 33 +++++++++++++++++++
 spacy/tests/regression/test_issue1001-1500.py | 10 ++++++
 spacy/tests/regression/test_issue1501-2000.py | 24 ++++++++++++++
 spacy/tests/regression/test_issue2001-2500.py | 10 ++++++
 spacy/tests/regression/test_issue2501-3000.py | 15 +++++++++
 spacy/tests/regression/test_issue3001-3500.py | 17 ++++++++++
 spacy/tests/regression/test_issue3501-4000.py | 20 +++++++++++
 spacy/tests/regression/test_issue4001-4500.py | 15 +++++++++
 spacy/tests/regression/test_issue4501-5000.py | 11 +++++++
 spacy/tests/regression/test_issue5001-5500.py |  6 ++++
 spacy/tests/regression/test_issue5501-6000.py |  3 ++
 spacy/tests/regression/test_issue6001-6500.py |  2 ++
 spacy/tests/regression/test_issue6501-7000.py |  8 +++++
 spacy/tests/regression/test_issue7001-8000.py |  6 ++++
 spacy/tests/regression/test_issue7716.py      |  1 +
 spacy/tests/regression/test_issue8190.py      |  1 +
 spacy/tests/regression/test_issue8216.py      |  1 +
 17 files changed, 183 insertions(+)

diff --git a/spacy/tests/regression/test_issue1-1000.py b/spacy/tests/regression/test_issue1-1000.py
index 6bb71f6f4..4846d2075 100644
--- a/spacy/tests/regression/test_issue1-1000.py
+++ b/spacy/tests/regression/test_issue1-1000.py
@@ -12,6 +12,7 @@ from spacy.tokens import Doc, Span
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(118)
 @pytest.mark.parametrize(
     "patterns",
     [
@@ -39,6 +40,7 @@ def test_issue118(en_tokenizer, patterns):
     assert ents[0].end == 11
 
 
+@pytest.mark.issue(118)
 @pytest.mark.parametrize(
     "patterns",
     [
@@ -66,6 +68,7 @@ def test_issue118_prefix_reorder(en_tokenizer, patterns):
     assert ents[0].end == 11
 
 
+@pytest.mark.issue(242)
 def test_issue242(en_tokenizer):
     """Test overlapping multi-word phrases."""
     text = "There are different food safety standards in different countries."
@@ -88,6 +91,7 @@ def test_issue242(en_tokenizer):
         doc.ents += tuple(matches)
 
 
+@pytest.mark.issue(309)
 def test_issue309(en_vocab):
     """Test Issue #309: SBD fails on empty string"""
     doc = Doc(en_vocab, words=[" "], heads=[0], deps=["ROOT"])
@@ -96,6 +100,7 @@ def test_issue309(en_vocab):
     assert len(sents) == 1
 
 
+@pytest.mark.issue(351)
 def test_issue351(en_tokenizer):
     doc = en_tokenizer("   This is a cat.")
     assert doc[0].idx == 0
@@ -103,12 +108,14 @@ def test_issue351(en_tokenizer):
     assert doc[1].idx == 3
 
 
+@pytest.mark.issue(360)
 def test_issue360(en_tokenizer):
     """Test tokenization of big ellipsis"""
     tokens = en_tokenizer("$45...............Asking")
     assert len(tokens) > 2
 
 
+@pytest.mark.issue(361)
 @pytest.mark.parametrize("text1,text2", [("cat", "dog")])
 def test_issue361(en_vocab, text1, text2):
     """Test Issue #361: Equality of lexemes"""
@@ -116,6 +123,7 @@ def test_issue361(en_vocab, text1, text2):
     assert en_vocab[text1] != en_vocab[text2]
 
 
+@pytest.mark.issue(587)
 def test_issue587(en_tokenizer):
     """Test that Matcher doesn't segfault on particular input"""
     doc = en_tokenizer("a b; c")
@@ -131,12 +139,14 @@ def test_issue587(en_tokenizer):
     assert len(matches) == 2
 
 
+@pytest.mark.issue(588)
 def test_issue588(en_vocab):
     matcher = Matcher(en_vocab)
     with pytest.raises(ValueError):
         matcher.add("TEST", [[]])
 
 
+@pytest.mark.issue(590)
 def test_issue590(en_vocab):
     """Test overlapping matches"""
     doc = Doc(en_vocab, words=["n", "=", "1", ";", "a", ":", "5", "%"])
@@ -149,6 +159,7 @@ def test_issue590(en_vocab):
     assert len(matches) == 2
 
 
+@pytest.mark.issue(595)
 @pytest.mark.skip(reason="Old vocab-based lemmatization")
 def test_issue595():
     """Test lemmatization of base forms"""
@@ -164,6 +175,7 @@ def test_issue595():
     assert doc[2].lemma_ == "feed"
 
 
+@pytest.mark.issue(599)
 def test_issue599(en_vocab):
     doc = Doc(en_vocab)
     doc2 = Doc(doc.vocab)
@@ -171,12 +183,14 @@ def test_issue599(en_vocab):
     assert doc2.has_annotation("DEP")
 
 
+@pytest.mark.issue(600)
 def test_issue600():
     vocab = Vocab(tag_map={"NN": {"pos": "NOUN"}})
     doc = Doc(vocab, words=["hello"])
     doc[0].tag_ = "NN"
 
 
+@pytest.mark.issue(615)
 def test_issue615(en_tokenizer):
     def merge_phrases(matcher, doc, i, matches):
         """Merge a phrase. We have to be careful here because we'll change the
@@ -204,6 +218,7 @@ def test_issue615(en_tokenizer):
     assert entities[0].label != 0
 
 
+@pytest.mark.issue(736)
 @pytest.mark.parametrize("text,number", [("7am", "7"), ("11p.m.", "11")])
 def test_issue736(en_tokenizer, text, number):
     """Test that times like "7am" are tokenized correctly and that numbers are
@@ -213,6 +228,7 @@ def test_issue736(en_tokenizer, text, number):
     assert tokens[0].text == number
 
 
+@pytest.mark.issue(740)
 @pytest.mark.parametrize("text", ["3/4/2012", "01/12/1900"])
 def test_issue740(en_tokenizer, text):
     """Test that dates are not split and kept as one token. This behaviour is
@@ -222,6 +238,7 @@ def test_issue740(en_tokenizer, text):
     assert len(tokens) == 1
 
 
+@pytest.mark.issue(743)
 def test_issue743():
     doc = Doc(Vocab(), ["hello", "world"])
     token = doc[0]
@@ -230,6 +247,7 @@ def test_issue743():
     assert items[0] is token
 
 
+@pytest.mark.issue(744)
 @pytest.mark.parametrize("text", ["We were scared", "We Were Scared"])
 def test_issue744(en_tokenizer, text):
     """Test that 'were' and 'Were' are excluded from the contractions
@@ -239,6 +257,7 @@ def test_issue744(en_tokenizer, text):
     assert tokens[1].text.lower() == "were"
 
 
+@pytest.mark.issue(759)
 @pytest.mark.parametrize(
     "text,is_num", [("one", True), ("ten", True), ("teneleven", False)]
 )
@@ -247,6 +266,7 @@ def test_issue759(en_tokenizer, text, is_num):
     assert tokens[0].like_num == is_num
 
 
+@pytest.mark.issue(775)
 @pytest.mark.parametrize("text", ["Shell", "shell", "Shed", "shed"])
 def test_issue775(en_tokenizer, text):
     """Test that 'Shell' and 'shell' are excluded from the contractions
@@ -256,6 +276,7 @@ def test_issue775(en_tokenizer, text):
     assert tokens[0].text == text
 
 
+@pytest.mark.issue(792)
 @pytest.mark.parametrize("text", ["This is a string ", "This is a string\u0020"])
 def test_issue792(en_tokenizer, text):
     """Test for Issue #792: Trailing whitespace is removed after tokenization."""
@@ -263,6 +284,7 @@ def test_issue792(en_tokenizer, text):
     assert "".join([token.text_with_ws for token in doc]) == text
 
 
+@pytest.mark.issue(792)
 @pytest.mark.parametrize("text", ["This is a string", "This is a string\n"])
 def test_control_issue792(en_tokenizer, text):
     """Test base case for Issue #792: Non-trailing whitespace"""
@@ -270,6 +292,7 @@ def test_control_issue792(en_tokenizer, text):
     assert "".join([token.text_with_ws for token in doc]) == text
 
 
+@pytest.mark.issue(801)
 @pytest.mark.skip(
     reason="Can not be fixed unless with variable-width lookbehinds, cf. PR #3218"
 )
@@ -292,6 +315,7 @@ def test_issue801(en_tokenizer, text, tokens):
     assert [t.text for t in doc] == tokens
 
 
+@pytest.mark.issue(805)
 @pytest.mark.parametrize(
     "text,expected_tokens",
     [
@@ -311,6 +335,7 @@ def test_issue805(sv_tokenizer, text, expected_tokens):
     assert expected_tokens == token_list
 
 
+@pytest.mark.issue(850)
 def test_issue850():
     """The variable-length pattern matches the succeeding token. Check we
     handle the ambiguity correctly."""
@@ -326,6 +351,7 @@ def test_issue850():
     assert end == 4
 
 
+@pytest.mark.issue(850)
 def test_issue850_basic():
     """Test Matcher matches with '*' operator and Boolean flag"""
     vocab = Vocab(lex_attr_getters={LOWER: lambda string: string.lower()})
@@ -340,6 +366,7 @@ def test_issue850_basic():
     assert end == 4
 
 
+@pytest.mark.issue(852)
 @pytest.mark.skip(
     reason="French exception list is not enabled in the default tokenizer anymore"
 )
@@ -352,6 +379,7 @@ def test_issue852(fr_tokenizer, text):
     assert len(tokens) == 1
 
 
+@pytest.mark.issue(859)
 @pytest.mark.parametrize(
     "text", ["aaabbb@ccc.com\nThank you!", "aaabbb@ccc.com \nThank you!"]
 )
@@ -361,6 +389,7 @@ def test_issue859(en_tokenizer, text):
     assert doc.text == text
 
 
+@pytest.mark.issue(886)
 @pytest.mark.parametrize("text", ["Datum:2014-06-02\nDokument:76467"])
 def test_issue886(en_tokenizer, text):
     """Test that token.idx matches the original text index for texts with newlines."""
@@ -370,6 +399,7 @@ def test_issue886(en_tokenizer, text):
         assert text[token.idx] == token.text[0]
 
 
+@pytest.mark.issue(891)
 @pytest.mark.parametrize("text", ["want/need"])
 def test_issue891(en_tokenizer, text):
     """Test that / infixes are split correctly."""
@@ -378,6 +408,7 @@ def test_issue891(en_tokenizer, text):
     assert tokens[1].text == "/"
 
 
+@pytest.mark.issue(912)
 @pytest.mark.skip(reason="Old vocab-based lemmatization")
 @pytest.mark.parametrize(
     "text,tag,lemma",
@@ -390,6 +421,7 @@ def test_issue912(en_vocab, text, tag, lemma):
     assert doc[0].lemma_ == lemma
 
 
+@pytest.mark.issue(957)
 @pytest.mark.slow
 def test_issue957(en_tokenizer):
     """Test that spaCy doesn't hang on many punctuation characters.
@@ -405,6 +437,7 @@ def test_issue957(en_tokenizer):
         assert doc
 
 
+@pytest.mark.issue(999)
 def test_issue999():
     """Test that adding entities and resuming training works passably OK.
     There are two issues here:
diff --git a/spacy/tests/regression/test_issue1001-1500.py b/spacy/tests/regression/test_issue1001-1500.py
index d6a4600e3..0a60e4477 100644
--- a/spacy/tests/regression/test_issue1001-1500.py
+++ b/spacy/tests/regression/test_issue1001-1500.py
@@ -9,6 +9,7 @@ from spacy.tokenizer import Tokenizer
 from spacy.symbols import ORTH, LEMMA, POS
 
 
+@pytest.mark.issue(1061)
 def test_issue1061():
     """Test special-case works after tokenizing. Was caching problem."""
     text = "I like _MATH_ even _MATH_ when _MATH_, except when _MATH_ is _MATH_! but not _MATH_."
@@ -33,6 +34,7 @@ def test_issue1061():
 @pytest.mark.skip(
     reason="Can not be fixed without variable-width look-behind (which we don't want)"
 )
+@pytest.mark.issue(1235)
 def test_issue1235():
     """Test that g is not split of if preceded by a number and a letter"""
     nlp = English()
@@ -46,6 +48,7 @@ def test_issue1235():
     assert doc[4].text == "g"
 
 
+@pytest.mark.issue(1242)
 def test_issue1242():
     nlp = English()
     doc = nlp("")
@@ -56,6 +59,7 @@ def test_issue1242():
 
 
 @pytest.mark.skip(reason="v3 no longer supports LEMMA/POS in tokenizer special cases")
+@pytest.mark.issue(1250)
 def test_issue1250():
     """Test cached special cases."""
     special_case = [{ORTH: "reimbur", LEMMA: "reimburse", POS: "VERB"}]
@@ -67,6 +71,7 @@ def test_issue1250():
     assert lemmas == ["reimburse", ",", "reimburse", "..."]
 
 
+@pytest.mark.issue(1257)
 def test_issue1257():
     """Test that tokens compare correctly."""
     doc1 = Doc(Vocab(), words=["a", "b", "c"])
@@ -75,6 +80,7 @@ def test_issue1257():
     assert not doc1[0] == doc2[0]
 
 
+@pytest.mark.issue(1375)
 def test_issue1375():
     """Test that token.nbor() raises IndexError for out-of-bounds access."""
     doc = Doc(Vocab(), words=["0", "1", "2"])
@@ -86,6 +92,7 @@ def test_issue1375():
     assert doc[1].nbor(1).text == "2"
 
 
+@pytest.mark.issue(1434)
 def test_issue1434():
     """Test matches occur when optional element at end of short doc."""
     pattern = [{"ORTH": "Hello"}, {"IS_ALPHA": True, "OP": "?"}]
@@ -111,6 +118,7 @@ def test_issue1434():
         ("a b b", 0, 3),
     ],
 )
+@pytest.mark.issue(1450)
 def test_issue1450(string, start, end):
     """Test matcher works when patterns end with * operator."""
     pattern = [{"ORTH": "a"}, {"ORTH": "b", "OP": "*"}]
@@ -124,6 +132,7 @@ def test_issue1450(string, start, end):
     assert matches[-1][2] == end
 
 
+@pytest.mark.issue(1488)
 def test_issue1488():
     prefix_re = re.compile(r"""[\[\("']""")
     suffix_re = re.compile(r"""[\]\)"']""")
@@ -147,6 +156,7 @@ def test_issue1488():
         assert token.text
 
 
+@pytest.mark.issue(1494)
 def test_issue1494():
     infix_re = re.compile(r"""[^a-z]""")
     test_cases = [
diff --git a/spacy/tests/regression/test_issue1501-2000.py b/spacy/tests/regression/test_issue1501-2000.py
index f85ec70e1..07f173843 100644
--- a/spacy/tests/regression/test_issue1501-2000.py
+++ b/spacy/tests/regression/test_issue1501-2000.py
@@ -17,6 +17,7 @@ from spacy.matcher import Matcher
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(1506)
 def test_issue1506():
     def string_generator():
         for _ in range(10001):
@@ -40,6 +41,7 @@ def test_issue1506():
             str(t.lemma_)
 
 
+@pytest.mark.issue(1518)
 def test_issue1518():
     """Test vectors.resize() works."""
     vectors = Vectors(shape=(10, 10))
@@ -47,6 +49,7 @@ def test_issue1518():
     vectors.resize((5, 9))
 
 
+@pytest.mark.issue(1537)
 def test_issue1537():
     """Test that Span.as_doc() doesn't segfault."""
     string = "The sky is blue . The man is pink . The dog is purple ."
@@ -65,6 +68,7 @@ def test_issue1537():
 
 
 # TODO: Currently segfaulting, due to l_edge and r_edge misalignment
+@pytest.mark.issue(1537)
 # def test_issue1537_model():
 #    nlp = load_spacy('en')
 #    doc = nlp('The sky is blue. The man is pink. The dog is purple.')
@@ -73,12 +77,14 @@ def test_issue1537():
 #    print(list(sents[1].noun_chunks))
 
 
+@pytest.mark.issue(1539)
 def test_issue1539():
     """Ensure vectors.resize() doesn't try to modify dictionary during iteration."""
     v = Vectors(shape=(10, 10), keys=[5, 3, 98, 100])
     v.resize((100, 100))
 
 
+@pytest.mark.issue(1547)
 def test_issue1547():
     """Test that entity labels still match after merging tokens."""
     words = ["\n", "worda", ".", "\n", "wordb", "-", "Biosphere", "2", "-", " \n"]
@@ -89,12 +95,14 @@ def test_issue1547():
     assert [ent.text for ent in doc.ents]
 
 
+@pytest.mark.issue(1612)
 def test_issue1612(en_tokenizer):
     doc = en_tokenizer("The black cat purrs.")
     span = doc[1:3]
     assert span.orth_ == span.text
 
 
+@pytest.mark.issue(1654)
 def test_issue1654():
     nlp = Language(Vocab())
     assert not nlp.pipeline
@@ -116,12 +124,14 @@ def test_issue1654():
 
 
 @pytest.mark.parametrize("text", ["test@example.com", "john.doe@example.co.uk"])
+@pytest.mark.issue(1698)
 def test_issue1698(en_tokenizer, text):
     doc = en_tokenizer(text)
     assert len(doc) == 1
     assert not doc[0].like_url
 
 
+@pytest.mark.issue(1727)
 def test_issue1727():
     """Test that models with no pretrained vectors can be deserialized
     correctly after vectors are added."""
@@ -138,6 +148,7 @@ def test_issue1727():
         assert tagger.cfg.get("pretrained_dims", 0) == 0
 
 
+@pytest.mark.issue(1757)
 def test_issue1757():
     """Test comparison against None doesn't cause segfault."""
     doc = Doc(Vocab(), words=["a", "b", "c"])
@@ -151,12 +162,14 @@ def test_issue1757():
     assert not doc.vocab["a"] < None
 
 
+@pytest.mark.issue(1758)
 def test_issue1758(en_tokenizer):
     """Test that "would've" is handled by the English tokenizer exceptions."""
     tokens = en_tokenizer("would've")
     assert len(tokens) == 2
 
 
+@pytest.mark.issue(1773)
 def test_issue1773(en_tokenizer):
     """Test that spaces don't receive a POS but no TAG. This is the root cause
     of the serialization issue reported in #1773."""
@@ -165,6 +178,7 @@ def test_issue1773(en_tokenizer):
         assert doc[0].tag_ != ""
 
 
+@pytest.mark.issue(1799)
 def test_issue1799():
     """Test sentence boundaries are deserialized correctly, even for
     non-projective sentences."""
@@ -186,6 +200,7 @@ def test_issue1799():
     assert len(list(doc.sents)) == 1
 
 
+@pytest.mark.issue(1807)
 def test_issue1807():
     """Test vocab.set_vector also adds the word to the vocab."""
     vocab = Vocab(vectors_name="test_issue1807")
@@ -194,6 +209,7 @@ def test_issue1807():
     assert "hello" in vocab
 
 
+@pytest.mark.issue(1834)
 def test_issue1834():
     """Test that sentence boundaries & parse/tag flags are not lost
     during serialization."""
@@ -217,6 +233,7 @@ def test_issue1834():
     assert new_doc.has_annotation("TAG")
 
 
+@pytest.mark.issue(1868)
 def test_issue1868():
     """Test Vocab.__contains__ works with int keys."""
     vocab = Vocab()
@@ -228,6 +245,7 @@ def test_issue1868():
     assert int_id not in vocab
 
 
+@pytest.mark.issue(1883)
 def test_issue1883():
     matcher = Matcher(Vocab())
     matcher.add("pat1", [[{"orth": "hello"}]])
@@ -239,11 +257,13 @@ def test_issue1883():
 
 
 @pytest.mark.parametrize("word", ["the"])
+@pytest.mark.issue(1889)
 def test_issue1889(word):
     assert is_stop(word, STOP_WORDS) == is_stop(word.upper(), STOP_WORDS)
 
 
 @pytest.mark.skip(reason="obsolete with the config refactor of v.3")
+@pytest.mark.issue(1915)
 def test_issue1915():
     cfg = {"hidden_depth": 2}  # should error out
     nlp = Language()
@@ -253,6 +273,7 @@ def test_issue1915():
         nlp.initialize(**cfg)
 
 
+@pytest.mark.issue(1945)
 def test_issue1945():
     """Test regression in Matcher introduced in v2.0.6."""
     matcher = Matcher(Vocab())
@@ -264,6 +285,7 @@ def test_issue1945():
     assert matches[1][1:] == (1, 3)
 
 
+@pytest.mark.issue(1963)
 def test_issue1963(en_tokenizer):
     """Test that doc.merge() resizes doc.tensor"""
     doc = en_tokenizer("a b c d")
@@ -275,6 +297,7 @@ def test_issue1963(en_tokenizer):
 
 
 @pytest.mark.parametrize("label", ["U-JOB-NAME"])
+@pytest.mark.issue(1967)
 def test_issue1967(label):
     nlp = Language()
     config = {}
@@ -293,6 +316,7 @@ def test_issue1967(label):
     assert "JOB-NAME" in ner.moves.get_actions(examples=[example])[1]
 
 
+@pytest.mark.issue(1971)
 def test_issue1971(en_vocab):
     # Possibly related to #2675 and #2671?
     matcher = Matcher(en_vocab)
diff --git a/spacy/tests/regression/test_issue2001-2500.py b/spacy/tests/regression/test_issue2001-2500.py
index 09baab4d8..a07360c2c 100644
--- a/spacy/tests/regression/test_issue2001-2500.py
+++ b/spacy/tests/regression/test_issue2001-2500.py
@@ -13,6 +13,7 @@ from ..util import add_vecs_to_vocab
 @pytest.mark.skip(
     reason="Can not be fixed without iterative looping between prefix/suffix and infix"
 )
+@pytest.mark.issue(2070)
 def test_issue2070():
     """Test that checks that a dot followed by a quote is handled
     appropriately.
@@ -25,6 +26,7 @@ def test_issue2070():
     assert len(doc) == 11
 
 
+@pytest.mark.issue(2179)
 def test_issue2179():
     """Test that spurious 'extra_labels' aren't created when initializing NER."""
     nlp = Italian()
@@ -41,6 +43,7 @@ def test_issue2179():
     assert nlp2.get_pipe("ner").labels == ("CITIZENSHIP",)
 
 
+@pytest.mark.issue(2203)
 def test_issue2203(en_vocab):
     """Test that lemmas are set correctly in doc.from_array."""
     words = ["I", "'ll", "survive"]
@@ -61,6 +64,7 @@ def test_issue2203(en_vocab):
     assert [t.lemma_ for t in new_doc] == lemmas
 
 
+@pytest.mark.issue(2219)
 def test_issue2219(en_vocab):
     vectors = [("a", [1, 2, 3]), ("letter", [4, 5, 6])]
     add_vecs_to_vocab(en_vocab, vectors)
@@ -69,6 +73,7 @@ def test_issue2219(en_vocab):
     assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
 
 
+@pytest.mark.issue(2361)
 def test_issue2361(de_vocab):
     chars = ("&lt;", "&gt;", "&amp;", "&quot;")
     words = ["<", ">", "&", '"']
@@ -78,6 +83,7 @@ def test_issue2361(de_vocab):
         assert char in html
 
 
+@pytest.mark.issue(2385)
 def test_issue2385():
     """Test that IOB tags are correctly converted to BILUO tags."""
     # fix bug in labels with a 'b' character
@@ -99,11 +105,13 @@ def test_issue2385():
         ("U-BRAWLER", "U-BRAWLER"),
     ],
 )
+@pytest.mark.issue(2385)
 def test_issue2385_biluo(tags):
     """Test that BILUO-compatible tags aren't modified."""
     assert iob_to_biluo(tags) == list(tags)
 
 
+@pytest.mark.issue(2396)
 def test_issue2396(en_vocab):
     words = ["She", "created", "a", "test", "for", "spacy"]
     heads = [1, 1, 3, 1, 3, 4]
@@ -125,6 +133,7 @@ def test_issue2396(en_vocab):
     assert (span.get_lca_matrix() == matrix).all()
 
 
+@pytest.mark.issue(2464)
 def test_issue2464(en_vocab):
     """Test problem with successive ?. This is the same bug, so putting it here."""
     matcher = Matcher(en_vocab)
@@ -134,6 +143,7 @@ def test_issue2464(en_vocab):
     assert len(matches) == 3
 
 
+@pytest.mark.issue(2482)
 def test_issue2482():
     """Test we can serialize and deserialize a blank NER or parser model."""
     nlp = Italian()
diff --git a/spacy/tests/regression/test_issue2501-3000.py b/spacy/tests/regression/test_issue2501-3000.py
index 4952a545d..cbb7f0621 100644
--- a/spacy/tests/regression/test_issue2501-3000.py
+++ b/spacy/tests/regression/test_issue2501-3000.py
@@ -13,6 +13,7 @@ import numpy
 import random
 
 
+@pytest.mark.issue(2564)
 def test_issue2564():
     """Test the tagger sets has_annotation("TAG") correctly when used via Language.pipe."""
     nlp = Language()
@@ -26,6 +27,7 @@ def test_issue2564():
     assert piped_doc.has_annotation("TAG")
 
 
+@pytest.mark.issue(2569)
 def test_issue2569(en_tokenizer):
     """Test that operator + is greedy."""
     doc = en_tokenizer("It is May 15, 1993.")
@@ -46,12 +48,14 @@ def test_issue2569(en_tokenizer):
         "oow.jspsearch.eventoracleopenworldsearch.technologyoraclesolarissearch.technologystoragesearch.technologylinuxsearch.technologyserverssearch.technologyvirtualizationsearch.technologyengineeredsystemspcodewwmkmppscem:",
     ],
 )
+@pytest.mark.issue(2626)
 def test_issue2626_2835(en_tokenizer, text):
     """Check that sentence doesn't cause an infinite loop in the tokenizer."""
     doc = en_tokenizer(text)
     assert doc
 
 
+@pytest.mark.issue(2656)
 def test_issue2656(en_tokenizer):
     """Test that tokenizer correctly splits off punctuation after numbers with
     decimal points.
@@ -71,6 +75,7 @@ def test_issue2656(en_tokenizer):
     assert doc[10].text == "."
 
 
+@pytest.mark.issue(2671)
 def test_issue2671():
     """Ensure the correct entity ID is returned for matches with quantifiers.
     See also #2675
@@ -94,6 +99,7 @@ def test_issue2671():
         assert nlp.vocab.strings[match_id] == pattern_id
 
 
+@pytest.mark.issue(2728)
 def test_issue2728(en_vocab):
     """Test that displaCy ENT visualizer escapes HTML correctly."""
     doc = Doc(en_vocab, words=["test", "<RELEASE>", "test"])
@@ -105,6 +111,7 @@ def test_issue2728(en_vocab):
     assert "&lt;RELEASE&gt;" in html
 
 
+@pytest.mark.issue(2754)
 def test_issue2754(en_tokenizer):
     """Test that words like 'a' and 'a.m.' don't get exceptional norm values."""
     a = en_tokenizer("a")
@@ -113,6 +120,7 @@ def test_issue2754(en_tokenizer):
     assert am[0].norm_ == "am"
 
 
+@pytest.mark.issue(2772)
 def test_issue2772(en_vocab):
     """Test that deprojectivization doesn't mess up sentence boundaries."""
     # fmt: off
@@ -128,6 +136,7 @@ def test_issue2772(en_vocab):
 
 @pytest.mark.parametrize("text", ["-0.23", "+123,456", "±1"])
 @pytest.mark.parametrize("lang_cls", [English, MultiLanguage])
+@pytest.mark.issue(2782)
 def test_issue2782(text, lang_cls):
     """Check that like_num handles + and - before number."""
     nlp = lang_cls()
@@ -136,6 +145,7 @@ def test_issue2782(text, lang_cls):
     assert doc[0].like_num
 
 
+@pytest.mark.issue(2800)
 def test_issue2800():
     """Test issue that arises when too many labels are added to NER model.
     Used to cause segfault.
@@ -157,6 +167,7 @@ def test_issue2800():
             nlp.update([example], sgd=optimizer, losses=losses, drop=0.5)
 
 
+@pytest.mark.issue(2822)
 def test_issue2822(it_tokenizer):
     """Test that the abbreviation of poco is kept as one word."""
     doc = it_tokenizer("Vuoi un po' di zucchero?")
@@ -169,6 +180,7 @@ def test_issue2822(it_tokenizer):
     assert doc[5].text == "?"
 
 
+@pytest.mark.issue(2833)
 def test_issue2833(en_vocab):
     """Test that a custom error is raised if a token or span is pickled."""
     doc = Doc(en_vocab, words=["Hello", "world"])
@@ -178,6 +190,7 @@ def test_issue2833(en_vocab):
         pickle.dumps(doc[0:2])
 
 
+@pytest.mark.issue(2871)
 def test_issue2871():
     """Test that vectors recover the correct key for spaCy reserved words."""
     words = ["dog", "cat", "SUFFIX"]
@@ -196,6 +209,7 @@ def test_issue2871():
     assert vocab.vectors.find(key="SUFFIX") == 2
 
 
+@pytest.mark.issue(2901)
 def test_issue2901():
     """Test that `nlp` doesn't fail."""
     try:
@@ -207,6 +221,7 @@ def test_issue2901():
     assert doc
 
 
+@pytest.mark.issue(2926)
 def test_issue2926(fr_tokenizer):
     """Test that the tokenizer correctly splits tokens separated by a slash (/)
     ending in a digit.
diff --git a/spacy/tests/regression/test_issue3001-3500.py b/spacy/tests/regression/test_issue3001-3500.py
index e123d2df9..6220003dc 100644
--- a/spacy/tests/regression/test_issue3001-3500.py
+++ b/spacy/tests/regression/test_issue3001-3500.py
@@ -14,6 +14,7 @@ from spacy.vectors import Vectors
 import numpy
 
 
+@pytest.mark.issue(3002)
 def test_issue3002():
     """Test that the tokenizer doesn't hang on a long list of dots"""
     nlp = German()
@@ -23,6 +24,7 @@ def test_issue3002():
     assert len(doc) == 5
 
 
+@pytest.mark.issue(3009)
 def test_issue3009(en_vocab):
     """Test problem with matcher quantifiers"""
     patterns = [
@@ -53,6 +55,7 @@ def test_issue3009(en_vocab):
         assert matches
 
 
+@pytest.mark.issue(3012)
 def test_issue3012(en_vocab):
     """Test that the is_tagged attribute doesn't get overwritten when we from_array
     without tag information."""
@@ -74,6 +77,7 @@ def test_issue3012(en_vocab):
     assert (doc2[2].text, doc2[2].pos_, doc2[2].tag_, doc2[2].ent_type_) == expected
 
 
+@pytest.mark.issue(3199)
 def test_issue3199():
     """Test that Span.noun_chunks works correctly if no noun chunks iterator
     is available. To make this test future-proof, we're constructing a Doc
@@ -85,6 +89,7 @@ def test_issue3199():
         list(doc[0:3].noun_chunks)
 
 
+@pytest.mark.issue(3209)
 def test_issue3209():
     """Test issue that occurred in spaCy nightly where NER labels were being
     mapped to classes incorrectly after loading the model, when the labels
@@ -104,6 +109,7 @@ def test_issue3209():
     assert ner2.move_names == move_names
 
 
+@pytest.mark.issue(3248)
 def test_issue3248_1():
     """Test that the PhraseMatcher correctly reports its number of rules, not
     total number of patterns."""
@@ -114,6 +120,7 @@ def test_issue3248_1():
     assert len(matcher) == 2
 
 
+@pytest.mark.issue(3248)
 def test_issue3248_2():
     """Test that the PhraseMatcher can be pickled correctly."""
     nlp = English()
@@ -125,6 +132,7 @@ def test_issue3248_2():
     assert len(new_matcher) == len(matcher)
 
 
+@pytest.mark.issue(3277)
 def test_issue3277(es_tokenizer):
     """Test that hyphens are split correctly as prefixes."""
     doc = es_tokenizer("—Yo me llamo... –murmuró el niño– Emilio Sánchez Pérez.")
@@ -134,6 +142,7 @@ def test_issue3277(es_tokenizer):
     assert doc[9].text == "\u2013"
 
 
+@pytest.mark.issue(3288)
 def test_issue3288(en_vocab):
     """Test that retokenization works correctly via displaCy when punctuation
     is merged onto the preceeding token and tensor is resized."""
@@ -145,6 +154,7 @@ def test_issue3288(en_vocab):
     displacy.render(doc)
 
 
+@pytest.mark.issue(3289)
 def test_issue3289():
     """Test that Language.to_bytes handles serializing a pipeline component
     with an uninitialized model."""
@@ -156,6 +166,7 @@ def test_issue3289():
     new_nlp.from_bytes(bytes_data)
 
 
+@pytest.mark.issue(3328)
 def test_issue3328(en_vocab):
     doc = Doc(en_vocab, words=["Hello", ",", "how", "are", "you", "doing", "?"])
     matcher = Matcher(en_vocab)
@@ -170,6 +181,7 @@ def test_issue3328(en_vocab):
     assert matched_texts == ["Hello", "how", "you", "doing"]
 
 
+@pytest.mark.issue(3331)
 def test_issue3331(en_vocab):
     """Test that duplicate patterns for different rules result in multiple
     matches, one per rule.
@@ -184,6 +196,7 @@ def test_issue3331(en_vocab):
     assert sorted(match_ids) == ["A", "B"]
 
 
+@pytest.mark.issue(3345)
 def test_issue3345():
     """Test case where preset entity crosses sentence boundary."""
     nlp = English()
@@ -206,6 +219,7 @@ def test_issue3345():
     assert ner.moves.is_valid(state, "B-GPE")
 
 
+@pytest.mark.issue(3412)
 def test_issue3412():
     data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f")
     vectors = Vectors(data=data, keys=["A", "B", "C"])
@@ -216,6 +230,7 @@ def test_issue3412():
 
 
 @pytest.mark.skip(reason="default suffix rules avoid one upper-case letter before dot")
+@pytest.mark.issue(3449)
 def test_issue3449():
     nlp = English()
     nlp.add_pipe("sentencizer")
@@ -230,6 +245,7 @@ def test_issue3449():
     assert t3[5].text == "I"
 
 
+@pytest.mark.issue(3456)
 def test_issue3456():
     # this crashed because of a padding error in layer.ops.unflatten in thinc
     nlp = English()
@@ -239,6 +255,7 @@ def test_issue3456():
     list(nlp.pipe(["hi", ""]))
 
 
+@pytest.mark.issue(3468)
 def test_issue3468():
     """Test that sentence boundaries are set correctly so Doc.has_annotation("SENT_START") can
     be restored after serialization."""
diff --git a/spacy/tests/regression/test_issue3501-4000.py b/spacy/tests/regression/test_issue3501-4000.py
index 71c3768dd..5d9bc4e83 100644
--- a/spacy/tests/regression/test_issue3501-4000.py
+++ b/spacy/tests/regression/test_issue3501-4000.py
@@ -24,6 +24,7 @@ from ..util import make_tempdir
 
 
 @pytest.mark.parametrize("word", ["don't", "don’t", "I'd", "I’d"])
+@pytest.mark.issue(3521)
 def test_issue3521(en_tokenizer, word):
     tok = en_tokenizer(word)[1]
     # 'not' and 'would' should be stopwords, also in their abbreviated forms
@@ -108,6 +109,7 @@ def test_issue_3526_4(en_vocab):
         assert new_ruler.overwrite is True
 
 
+@pytest.mark.issue(3531)
 def test_issue3531():
     """Test that displaCy renderer doesn't require "settings" key."""
     example_dep = {
@@ -137,6 +139,7 @@ def test_issue3531():
     assert ent_html
 
 
+@pytest.mark.issue(3540)
 def test_issue3540(en_vocab):
     words = ["I", "live", "in", "NewYork", "right", "now"]
     tensor = numpy.asarray(
@@ -176,6 +179,7 @@ def test_issue3540(en_vocab):
     assert vectors_1[5].tolist() == vectors_2[6].tolist()
 
 
+@pytest.mark.issue(3549)
 def test_issue3549(en_vocab):
     """Test that match pattern validation doesn't raise on empty errors."""
     matcher = Matcher(en_vocab, validate=True)
@@ -186,6 +190,7 @@ def test_issue3549(en_vocab):
 
 
 @pytest.mark.skip("Matching currently only works on strings and integers")
+@pytest.mark.issue(3555)
 def test_issue3555(en_vocab):
     """Test that custom extensions with default None don't break matcher."""
     Token.set_extension("issue3555", default=None)
@@ -196,6 +201,7 @@ def test_issue3555(en_vocab):
     matcher(doc)
 
 
+@pytest.mark.issue(3611)
 def test_issue3611():
     """Test whether adding n-grams in the textcat works even when n > token length of some docs"""
     unique_classes = ["offensive", "inoffensive"]
@@ -232,6 +238,7 @@ def test_issue3611():
                 nlp.update(examples=batch, sgd=optimizer, drop=0.1, losses=losses)
 
 
+@pytest.mark.issue(3625)
 def test_issue3625():
     """Test that default punctuation rules applies to hindi unicode characters"""
     nlp = Hindi()
@@ -240,6 +247,7 @@ def test_issue3625():
     assert [token.text for token in doc] == expected
 
 
+@pytest.mark.issue(3803)
 def test_issue3803():
     """Test that spanish num-like tokens have True for like_num attribute."""
     nlp = Spanish()
@@ -255,6 +263,7 @@ def _parser_example(parser):
     return Example.from_dict(doc, gold)
 
 
+@pytest.mark.issue(3830)
 def test_issue3830_no_subtok():
     """Test that the parser doesn't have subtok label if not learn_tokens"""
     config = {
@@ -268,6 +277,7 @@ def test_issue3830_no_subtok():
     assert "subtok" not in parser.labels
 
 
+@pytest.mark.issue(3830)
 def test_issue3830_with_subtok():
     """Test that the parser does have subtok label if learn_tokens=True."""
     config = {
@@ -281,6 +291,7 @@ def test_issue3830_with_subtok():
     assert "subtok" in parser.labels
 
 
+@pytest.mark.issue(3839)
 def test_issue3839(en_vocab):
     """Test that match IDs returned by the matcher are correct, are in the string"""
     doc = Doc(en_vocab, words=["terrific", "group", "of", "people"])
@@ -307,6 +318,7 @@ def test_issue3839(en_vocab):
         "It was a missed assignment, but it shouldn't have resulted in a turnover ...",
     ],
 )
+@pytest.mark.issue(3869)
 def test_issue3869(sentence):
     """Test that the Doc's count_by function works consistently"""
     nlp = English()
@@ -317,6 +329,7 @@ def test_issue3869(sentence):
     assert count == doc.count_by(IS_ALPHA).get(1, 0)
 
 
+@pytest.mark.issue(3879)
 def test_issue3879(en_vocab):
     doc = Doc(en_vocab, words=["This", "is", "a", "test", "."])
     assert len(doc) == 5
@@ -326,6 +339,7 @@ def test_issue3879(en_vocab):
     assert len(matcher(doc)) == 2  # fails because of a FP match 'is a test'
 
 
+@pytest.mark.issue(3880)
 def test_issue3880():
     """Test that `nlp.pipe()` works when an empty string ends the batch.
 
@@ -341,6 +355,7 @@ def test_issue3880():
         pass
 
 
+@pytest.mark.issue(3882)
 def test_issue3882(en_vocab):
     """Test that displaCy doesn't serialize the doc.user_data when making a
     copy of the Doc.
@@ -350,6 +365,7 @@ def test_issue3882(en_vocab):
     parse_deps(doc)
 
 
+@pytest.mark.issue(3951)
 def test_issue3951(en_vocab):
     """Test that combinations of optional rules are matched correctly."""
     matcher = Matcher(en_vocab)
@@ -365,6 +381,7 @@ def test_issue3951(en_vocab):
     assert len(matches) == 0
 
 
+@pytest.mark.issue(3959)
 def test_issue3959():
     """Ensure that a modified pos attribute is serialized correctly."""
     nlp = English()
@@ -383,6 +400,7 @@ def test_issue3959():
         assert doc2[0].pos_ == "NOUN"
 
 
+@pytest.mark.issue(3962)
 def test_issue3962(en_vocab):
     """Ensure that as_doc does not result in out-of-bound access of tokens.
     This is achieved by setting the head to itself if it would lie out of the span otherwise."""
@@ -421,6 +439,7 @@ def test_issue3962(en_vocab):
     assert len(list(doc3.sents)) == 1
 
 
+@pytest.mark.issue(3962)
 def test_issue3962_long(en_vocab):
     """Ensure that as_doc does not result in out-of-bound access of tokens.
     This is achieved by setting the head to itself if it would lie out of the span otherwise."""
@@ -456,6 +475,7 @@ def test_issue3962_long(en_vocab):
     assert sents[1].text == "They never"
 
 
+@pytest.mark.issue(3972)
 def test_issue3972(en_vocab):
     """Test that the PhraseMatcher returns duplicates for duplicate match IDs."""
     matcher = PhraseMatcher(en_vocab)
diff --git a/spacy/tests/regression/test_issue4001-4500.py b/spacy/tests/regression/test_issue4001-4500.py
index 4410e6236..7b7c304a3 100644
--- a/spacy/tests/regression/test_issue4001-4500.py
+++ b/spacy/tests/regression/test_issue4001-4500.py
@@ -17,6 +17,7 @@ from thinc.api import compounding
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(4002)
 def test_issue4002(en_vocab):
     """Test that the PhraseMatcher can match on overwritten NORM attributes."""
     matcher = PhraseMatcher(en_vocab, attr="NORM")
@@ -37,6 +38,7 @@ def test_issue4002(en_vocab):
     assert len(matches) == 1
 
 
+@pytest.mark.issue(4030)
 def test_issue4030():
     """Test whether textcat works fine with empty doc"""
     unique_classes = ["offensive", "inoffensive"]
@@ -77,6 +79,7 @@ def test_issue4030():
     assert doc.cats["inoffensive"] == 0.0
 
 
+@pytest.mark.issue(4042)
 def test_issue4042():
     """Test that serialization of an EntityRuler before NER works fine."""
     nlp = English()
@@ -105,6 +108,7 @@ def test_issue4042():
         assert doc2.ents[0].label_ == "MY_ORG"
 
 
+@pytest.mark.issue(4042)
 def test_issue4042_bug2():
     """
     Test that serialization of an NER works fine when new labels were added.
@@ -139,6 +143,7 @@ def test_issue4042_bug2():
         assert len(ner2.labels) == 2
 
 
+@pytest.mark.issue(4054)
 def test_issue4054(en_vocab):
     """Test that a new blank model can be made with a vocab from file,
     and that serialization does not drop the language at any point."""
@@ -159,6 +164,7 @@ def test_issue4054(en_vocab):
         assert nlp3.lang == "en"
 
 
+@pytest.mark.issue(4120)
 def test_issue4120(en_vocab):
     """Test that matches without a final {OP: ?} token are returned."""
     matcher = Matcher(en_vocab)
@@ -177,6 +183,7 @@ def test_issue4120(en_vocab):
     assert len(matcher(doc4)) == 3  # fixed
 
 
+@pytest.mark.issue(4133)
 def test_issue4133(en_vocab):
     nlp = English()
     vocab_bytes = nlp.vocab.to_bytes()
@@ -196,6 +203,7 @@ def test_issue4133(en_vocab):
     assert actual == pos
 
 
+@pytest.mark.issue(4190)
 def test_issue4190():
     def customize_tokenizer(nlp):
         prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
@@ -236,6 +244,7 @@ def test_issue4190():
     assert result_1b == result_2
 
 
+@pytest.mark.issue(4267)
 def test_issue4267():
     """Test that running an entity_ruler after ner gives consistent results"""
     nlp = English()
@@ -262,6 +271,7 @@ def test_issue4267():
 
 
 @pytest.mark.skip(reason="lemmatizer lookups no longer in vocab")
+@pytest.mark.issue(4272)
 def test_issue4272():
     """Test that lookup table can be accessed from Token.lemma if no POS tags
     are available."""
@@ -287,6 +297,7 @@ def test_multiple_predictions():
     dummy_pipe(doc)
 
 
+@pytest.mark.issue(4313)
 def test_issue4313():
     """This should not crash or exit with some strange error code"""
     beam_width = 16
@@ -313,6 +324,7 @@ def test_issue4313():
     assert "MY_ORG" in ner.labels
 
 
+@pytest.mark.issue(4348)
 def test_issue4348():
     """Test that training the tagger with empty data, doesn't throw errors"""
     nlp = English()
@@ -328,6 +340,7 @@ def test_issue4348():
             nlp.update(batch, sgd=optimizer, losses=losses)
 
 
+@pytest.mark.issue(4367)
 def test_issue4367():
     """Test that docbin init goes well"""
     DocBin()
@@ -335,6 +348,7 @@ def test_issue4367():
     DocBin(attrs=["LEMMA", "ENT_IOB", "ENT_TYPE"])
 
 
+@pytest.mark.issue(4373)
 def test_issue4373():
     """Test that PhraseMatcher.vocab can be accessed (like Matcher.vocab)."""
     matcher = Matcher(Vocab())
@@ -343,6 +357,7 @@ def test_issue4373():
     assert isinstance(matcher.vocab, Vocab)
 
 
+@pytest.mark.issue(4402)
 def test_issue4402():
     json_data = {
         "id": 0,
diff --git a/spacy/tests/regression/test_issue4501-5000.py b/spacy/tests/regression/test_issue4501-5000.py
index effd67306..07a00d2b7 100644
--- a/spacy/tests/regression/test_issue4501-5000.py
+++ b/spacy/tests/regression/test_issue4501-5000.py
@@ -14,6 +14,7 @@ from thinc.api import NumpyOps, get_current_ops
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(4528)
 def test_issue4528(en_vocab):
     """Test that user_data is correctly serialized in DocBin."""
     doc = Doc(en_vocab, words=["hello", "world"])
@@ -37,6 +38,7 @@ def test_gold_misaligned(en_tokenizer, text, words):
     Example.from_dict(doc, {"words": words})
 
 
+@pytest.mark.issue(4651)
 def test_issue4651_with_phrase_matcher_attr():
     """Test that the EntityRuler PhraseMatcher is deserialized correctly using
     the method from_disk when the EntityRuler argument phrase_matcher_attr is
@@ -59,6 +61,7 @@ def test_issue4651_with_phrase_matcher_attr():
     assert res == res_reloaded
 
 
+@pytest.mark.issue(4651)
 def test_issue4651_without_phrase_matcher_attr():
     """Test that the EntityRuler PhraseMatcher is deserialized correctly using
     the method from_disk when the EntityRuler argument phrase_matcher_attr is
@@ -81,6 +84,7 @@ def test_issue4651_without_phrase_matcher_attr():
     assert res == res_reloaded
 
 
+@pytest.mark.issue(4665)
 def test_issue4665():
     """
     conllu_to_docs should not raise an exception if the HEAD column contains an
@@ -109,6 +113,7 @@ def test_issue4665():
     conllu_to_docs(input_data)
 
 
+@pytest.mark.issue(4674)
 def test_issue4674():
     """Test that setting entities with overlapping identifiers does not mess up IO"""
     nlp = English()
@@ -135,6 +140,7 @@ def test_issue4674():
 
 
 @pytest.mark.skip(reason="API change: disable just disables, new exclude arg")
+@pytest.mark.issue(4707)
 def test_issue4707():
     """Tests that disabled component names are also excluded from nlp.from_disk
     by default when loading a model.
@@ -151,6 +157,7 @@ def test_issue4707():
     assert "entity_ruler" in new_nlp.pipe_names
 
 
+@pytest.mark.issue(4725)
 def test_issue4725_1():
     """Ensure the pickling of the NER goes well"""
     vocab = Vocab(vectors_name="test_vocab_add_vector")
@@ -169,6 +176,7 @@ def test_issue4725_1():
             assert ner2.cfg["update_with_oracle_cut_size"] == 111
 
 
+@pytest.mark.issue(4725)
 def test_issue4725_2():
     if isinstance(get_current_ops, NumpyOps):
         # ensures that this runs correctly and doesn't hang or crash because of the global vectors
@@ -188,6 +196,7 @@ def test_issue4725_2():
             pass
 
 
+@pytest.mark.issue(4849)
 def test_issue4849():
     nlp = English()
     patterns = [
@@ -235,6 +244,7 @@ class CustomPipe:
         return str(span.end)
 
 
+@pytest.mark.issue(4903)
 def test_issue4903():
     """Ensure that this runs correctly and doesn't hang or crash on Windows /
     macOS."""
@@ -249,6 +259,7 @@ def test_issue4903():
         assert docs[2].text == "No, I prefer wasabi."
 
 
+@pytest.mark.issue(4924)
 def test_issue4924():
     nlp = Language()
     example = Example.from_dict(nlp.make_doc(""), {})
diff --git a/spacy/tests/regression/test_issue5001-5500.py b/spacy/tests/regression/test_issue5001-5500.py
index bc9bcb982..e1f5231e7 100644
--- a/spacy/tests/regression/test_issue5001-5500.py
+++ b/spacy/tests/regression/test_issue5001-5500.py
@@ -12,6 +12,7 @@ import pytest
 from ...util import make_tempdir
 
 
+@pytest.mark.issue(5048)
 def test_issue5048(en_vocab):
     words = ["This", "is", "a", "sentence"]
     pos_s = ["DET", "VERB", "DET", "NOUN"]
@@ -34,6 +35,7 @@ def test_issue5048(en_vocab):
     assert v1 == v2
 
 
+@pytest.mark.issue(5082)
 def test_issue5082():
     # Ensure the 'merge_entities' pipeline does something sensible for the vectors of the merged tokens
     nlp = English()
@@ -68,6 +70,7 @@ def test_issue5082():
     numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[2]), array34)
 
 
+@pytest.mark.issue(5137)
 def test_issue5137():
     factory_name = "test_issue5137"
     pipe_name = "my_component"
@@ -98,6 +101,7 @@ def test_issue5137():
         assert nlp2.get_pipe(pipe_name).categories == "my_categories"
 
 
+@pytest.mark.issue(5141)
 def test_issue5141(en_vocab):
     """Ensure an empty DocBin does not crash on serialization"""
     doc_bin = DocBin(attrs=["DEP", "HEAD"])
@@ -107,6 +111,7 @@ def test_issue5141(en_vocab):
     assert list(doc_bin_2.get_docs(en_vocab)) == []
 
 
+@pytest.mark.issue(5152)
 def test_issue5152():
     # Test that the comparison between a Span and a Token, goes well
     # There was a bug when the number of tokens in the span equaled the number of characters in the token (!)
@@ -125,6 +130,7 @@ def test_issue5152():
         assert span_2.similarity(span_3) < 1.0
 
 
+@pytest.mark.issue(5458)
 def test_issue5458():
     # Test that the noun chuncker does not generate overlapping spans
     # fmt: off
diff --git a/spacy/tests/regression/test_issue5501-6000.py b/spacy/tests/regression/test_issue5501-6000.py
index 355ffffeb..87c40ec2a 100644
--- a/spacy/tests/regression/test_issue5501-6000.py
+++ b/spacy/tests/regression/test_issue5501-6000.py
@@ -25,6 +25,7 @@ from spacy.training import Example
         multi_label_cnn_config,
     ],
 )
+@pytest.mark.issue(5551)
 def test_issue5551(textcat_config):
     """Test that after fixing the random seed, the results of the pipeline are truly identical"""
     component = "textcat"
@@ -53,6 +54,7 @@ def test_issue5551(textcat_config):
     assert_almost_equal(ops.to_numpy(results[0]), ops.to_numpy(results[2]), decimal=5)
 
 
+@pytest.mark.issue(5838)
 def test_issue5838():
     # Displacy's EntityRenderer break line
     # not working after last entity
@@ -65,6 +67,7 @@ def test_issue5838():
     assert found == 4
 
 
+@pytest.mark.issue(5918)
 def test_issue5918():
     # Test edge case when merging entities.
     nlp = English()
diff --git a/spacy/tests/regression/test_issue6001-6500.py b/spacy/tests/regression/test_issue6001-6500.py
index 470b2f388..cb27d39e4 100644
--- a/spacy/tests/regression/test_issue6001-6500.py
+++ b/spacy/tests/regression/test_issue6001-6500.py
@@ -4,6 +4,7 @@ from spacy.schemas import TokenPattern, TokenPatternSchema
 import pytest
 
 
+@pytest.mark.issue(6207)
 def test_issue6207(en_tokenizer):
     doc = en_tokenizer("zero one two three four five six")
 
@@ -18,6 +19,7 @@ def test_issue6207(en_tokenizer):
     assert s3 in result
 
 
+@pytest.mark.issue(6258)
 def test_issue6258():
     """Test that the non-empty constraint pattern field is respected"""
     # These one is valid
diff --git a/spacy/tests/regression/test_issue6501-7000.py b/spacy/tests/regression/test_issue6501-7000.py
index f57e4085c..84517d79b 100644
--- a/spacy/tests/regression/test_issue6501-7000.py
+++ b/spacy/tests/regression/test_issue6501-7000.py
@@ -13,6 +13,7 @@ import pickle
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(6730)
 def test_issue6730(en_vocab):
     """Ensure that the KB does not accept empty strings, but otherwise IO works fine."""
     from spacy.kb import KnowledgeBase
@@ -34,6 +35,7 @@ def test_issue6730(en_vocab):
     assert set(kb.get_alias_strings()) == {"x", "y"}
 
 
+@pytest.mark.issue(6755)
 def test_issue6755(en_tokenizer):
     doc = en_tokenizer("This is a magnificent sentence.")
     span = doc[:0]
@@ -45,6 +47,7 @@ def test_issue6755(en_tokenizer):
     "sentence, start_idx,end_idx,label",
     [("Welcome to Mumbai, my friend", 11, 17, "GPE")],
 )
+@pytest.mark.issue(6815)
 def test_issue6815_1(sentence, start_idx, end_idx, label):
     nlp = English()
     doc = nlp(sentence)
@@ -55,6 +58,7 @@ def test_issue6815_1(sentence, start_idx, end_idx, label):
 @pytest.mark.parametrize(
     "sentence, start_idx,end_idx,kb_id", [("Welcome to Mumbai, my friend", 11, 17, 5)]
 )
+@pytest.mark.issue(6815)
 def test_issue6815_2(sentence, start_idx, end_idx, kb_id):
     nlp = English()
     doc = nlp(sentence)
@@ -66,6 +70,7 @@ def test_issue6815_2(sentence, start_idx, end_idx, kb_id):
     "sentence, start_idx,end_idx,vector",
     [("Welcome to Mumbai, my friend", 11, 17, np.array([0.1, 0.2, 0.3]))],
 )
+@pytest.mark.issue(6815)
 def test_issue6815_3(sentence, start_idx, end_idx, vector):
     nlp = English()
     doc = nlp(sentence)
@@ -73,6 +78,7 @@ def test_issue6815_3(sentence, start_idx, end_idx, vector):
     assert (span.vector == vector).all()
 
 
+@pytest.mark.issue(6839)
 def test_issue6839(en_vocab):
     """Ensure that PhraseMatcher accepts Span as input"""
     # fmt: off
@@ -155,6 +161,7 @@ labels = ['label1', 'label2']
     "component_name",
     ["textcat", "textcat_multilabel"],
 )
+@pytest.mark.issue(6908)
 def test_issue6908(component_name):
     """Test intializing textcat with labels in a list"""
 
@@ -219,6 +226,7 @@ upstream = "*"
 """
 
 
+@pytest.mark.issue(6950)
 def test_issue6950():
     """Test that the nlp object with initialized tok2vec with listeners pickles
     correctly (and doesn't have lambdas).
diff --git a/spacy/tests/regression/test_issue7001-8000.py b/spacy/tests/regression/test_issue7001-8000.py
index 5bb7cc08e..17b8a6839 100644
--- a/spacy/tests/regression/test_issue7001-8000.py
+++ b/spacy/tests/regression/test_issue7001-8000.py
@@ -13,6 +13,7 @@ from wasabi import msg
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(7019)
 def test_issue7019():
     scores = {"LABEL_A": 0.39829102, "LABEL_B": 0.938298329382, "LABEL_C": None}
     print_textcats_auc_per_cat(msg, scores)
@@ -64,6 +65,7 @@ upstream = "*"
 """
 
 
+@pytest.mark.issue(7029)
 def test_issue7029():
     """Test that an empty document doesn't mess up an entire batch."""
     TRAIN_DATA = [
@@ -84,6 +86,7 @@ def test_issue7029():
     assert [doc[0].tag_ for doc in docs1[:-1]] == [doc[0].tag_ for doc in docs2[:-1]]
 
 
+@pytest.mark.issue(7055)
 def test_issue7055():
     """Test that fill-config doesn't turn sourced components into factories."""
     source_cfg = {
@@ -118,6 +121,7 @@ def test_issue7055():
     assert "model" in filled_cfg["components"]["ner"]
 
 
+@pytest.mark.issue(7056)
 def test_issue7056():
     """Test that the Unshift transition works properly, and doesn't cause
     sentence segmentation errors."""
@@ -190,6 +194,7 @@ def test_partial_links():
     assert "ORG" not in results["nel_f_per_type"]
 
 
+@pytest.mark.issue(7065)
 def test_issue7065():
     text = "Kathleen Battle sang in Mahler 's Symphony No. 8 at the Cincinnati Symphony Orchestra 's May Festival."
     nlp = English()
@@ -217,6 +222,7 @@ def test_issue7065():
     assert sentences.index(ent.sent) == 0
 
 
+@pytest.mark.issue(7065)
 def test_issue7065_b():
     # Test that the NEL doesn't crash when an entity crosses a sentence boundary
     nlp = English()
diff --git a/spacy/tests/regression/test_issue7716.py b/spacy/tests/regression/test_issue7716.py
index 811952792..d9b3967ff 100644
--- a/spacy/tests/regression/test_issue7716.py
+++ b/spacy/tests/regression/test_issue7716.py
@@ -43,6 +43,7 @@ def parser(vocab):
     return parser
 
 
+@pytest.mark.issue(7716)
 @pytest.mark.xfail(reason="Not fixed yet")
 def test_partial_annotation(parser):
     doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
diff --git a/spacy/tests/regression/test_issue8190.py b/spacy/tests/regression/test_issue8190.py
index 6ddbe53e0..1168630b6 100644
--- a/spacy/tests/regression/test_issue8190.py
+++ b/spacy/tests/regression/test_issue8190.py
@@ -3,6 +3,7 @@ from spacy.lang.en import English
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(8190)
 def test_issue8190():
     """Test that config overrides are not lost after load is complete."""
     source_cfg = {
diff --git a/spacy/tests/regression/test_issue8216.py b/spacy/tests/regression/test_issue8216.py
index 00cd6da3b..0370074fe 100644
--- a/spacy/tests/regression/test_issue8216.py
+++ b/spacy/tests/regression/test_issue8216.py
@@ -22,6 +22,7 @@ def patterns():
     ]
 
 
+@pytest.mark.issue(8216)
 def test_entity_ruler_fix8216(nlp, patterns):
     """Test that patterns don't get added excessively."""
     ruler = nlp.add_pipe("entity_ruler", config={"validate": True})

From 8e7deaf210988ed87f72144dc7a75f9c27885f41 Mon Sep 17 00:00:00 2001
From: Lj Miranda <ljvmiranda@gmail.com>
Date: Fri, 5 Nov 2021 10:49:48 +0800
Subject: [PATCH 04/37] Add missing imports in some regression tests

- test_issue7001-8000.py
- test_issue8190.py
---
 spacy/tests/regression/test_issue7001-8000.py | 1 +
 spacy/tests/regression/test_issue8190.py      | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/spacy/tests/regression/test_issue7001-8000.py b/spacy/tests/regression/test_issue7001-8000.py
index 17b8a6839..1164e85b9 100644
--- a/spacy/tests/regression/test_issue7001-8000.py
+++ b/spacy/tests/regression/test_issue7001-8000.py
@@ -1,3 +1,4 @@
+import pytest
 from spacy.cli.evaluate import print_textcats_auc_per_cat, print_prf_per_type
 from spacy.lang.en import English
 from spacy.training import Example
diff --git a/spacy/tests/regression/test_issue8190.py b/spacy/tests/regression/test_issue8190.py
index 1168630b6..0b2f2824b 100644
--- a/spacy/tests/regression/test_issue8190.py
+++ b/spacy/tests/regression/test_issue8190.py
@@ -1,3 +1,5 @@
+import pytest
+
 import spacy
 from spacy.lang.en import English
 from ..util import make_tempdir

From 86af0234abfd2d3d2a609bd46eaa4b475477eb3b Mon Sep 17 00:00:00 2001
From: Ines Montani <ines@ines.io>
Date: Fri, 5 Nov 2021 19:02:35 +0100
Subject: [PATCH 05/37] Update version [ci skip]

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 61d5449a4..57d76fb45 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@ production-ready [**training system**](https://spacy.io/usage/training) and easy
 model packaging, deployment and workflow management. spaCy is commercial
 open-source software, released under the MIT license.
 
-💫 **Version 3.0 out now!**
+💫 **Version 3.2 out now!**
 [Check out the release notes here.](https://github.com/explosion/spaCy/releases)
 
 [![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8)

From 909177589dcdbde1cd4770f9f744d4d57d08d7e0 Mon Sep 17 00:00:00 2001
From: Lj Miranda <ljvmiranda@gmail.com>
Date: Sat, 6 Nov 2021 06:35:58 +0800
Subject: [PATCH 06/37] Remove utility script

---
 spacy/tests/regression/util_add_marker.py | 41 -----------------------
 1 file changed, 41 deletions(-)
 delete mode 100644 spacy/tests/regression/util_add_marker.py

diff --git a/spacy/tests/regression/util_add_marker.py b/spacy/tests/regression/util_add_marker.py
deleted file mode 100644
index 94fa415bc..000000000
--- a/spacy/tests/regression/util_add_marker.py
+++ /dev/null
@@ -1,41 +0,0 @@
-import re
-from pathlib import Path
-from typing import Optional
-
-import typer
-
-
-def main(
-    filename: Path, out_file: Optional[Path] = typer.Option(None), dry_run: bool = False
-):
-    """Add pytest issue markers on regression tests
-
-    If --out-file is not used, it will overwrite the original file. You can set
-    the --dry-run flag to just see the changeset and not write to disk.
-    """
-    lines = []
-    with filename.open() as f:
-        lines = f.readlines()
-
-    # Regex pattern for matching common regression formats (e.g. test_issue1234)
-    pattern = r"def test_issue\d{1,4}"
-    regex = re.compile(pattern)
-
-    new_lines = []
-    for line_text in lines:
-        if regex.search(line_text):  # if match, append marker first
-            issue_num = int(re.findall(r"\d+", line_text)[0])  # Simple heuristic
-            typer.echo(f"Found: {line_text} with issue number: {issue_num}")
-            new_lines.append(f"@pytest.mark.issue({issue_num})\n")
-        new_lines.append(line_text)
-
-    # Save to file
-    if not dry_run:
-        out = out_file or filename
-        with out.open("w") as f:
-            for new_line in new_lines:
-                f.write(new_line)
-
-
-if __name__ == "__main__":
-    typer.run(main)

From 141f12b92e8a3ace4e3ba019f35ee2ff2fd8e7e3 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Sun, 7 Nov 2021 18:56:23 +0900
Subject: [PATCH 07/37] Make Jsonl Corpus reader optional again

---
 spacy/training/corpus.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/training/corpus.py b/spacy/training/corpus.py
index b30d918fd..733fc267e 100644
--- a/spacy/training/corpus.py
+++ b/spacy/training/corpus.py
@@ -41,7 +41,7 @@ def create_docbin_reader(
 
 @util.registry.readers("spacy.JsonlCorpus.v1")
 def create_jsonl_reader(
-    path: Union[str, Path], min_length: int = 0, max_length: int = 0, limit: int = 0
+    path: Union[None, str, Path], min_length: int = 0, max_length: int = 0, limit: int = 0
 ) -> Callable[["Language"], Iterable[Example]]:
     return JsonlCorpus(path, min_length=min_length, max_length=max_length, limit=limit)
 

From 71fb00ed954fd758cc743d80dc52e77f3e9bc689 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Mon, 8 Nov 2021 10:02:29 +0000
Subject: [PATCH 08/37] Update spacy/training/corpus.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/training/corpus.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/training/corpus.py b/spacy/training/corpus.py
index 733fc267e..aab2eae94 100644
--- a/spacy/training/corpus.py
+++ b/spacy/training/corpus.py
@@ -41,7 +41,7 @@ def create_docbin_reader(
 
 @util.registry.readers("spacy.JsonlCorpus.v1")
 def create_jsonl_reader(
-    path: Union[None, str, Path], min_length: int = 0, max_length: int = 0, limit: int = 0
+    path: Optional[Union[str, Path]], min_length: int = 0, max_length: int = 0, limit: int = 0
 ) -> Callable[["Language"], Iterable[Example]]:
     return JsonlCorpus(path, min_length=min_length, max_length=max_length, limit=limit)
 

From 8aa2d32ca92d3501695cdb057bcc7d479a0ab1df Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Mon, 8 Nov 2021 19:03:47 +0900
Subject: [PATCH 09/37] Update jsonlcorpus constructor types

---
 spacy/training/corpus.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/training/corpus.py b/spacy/training/corpus.py
index aab2eae94..cf643feec 100644
--- a/spacy/training/corpus.py
+++ b/spacy/training/corpus.py
@@ -221,7 +221,7 @@ class JsonlCorpus:
 
     def __init__(
         self,
-        path: Union[str, Path],
+        path: Optional[Union[str, Path]],
         *,
         limit: int = 0,
         min_length: int = 0,

From 67d8c8a081fa87763184e5fc794dc8542e3eb63e Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 12 Nov 2021 10:00:03 +0100
Subject: [PATCH 10/37] Auto-format code with black (#9664)

Co-authored-by: explosion-bot <explosion-bot@users.noreply.github.com>
---
 spacy/training/corpus.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/spacy/training/corpus.py b/spacy/training/corpus.py
index cf643feec..b9f929fcd 100644
--- a/spacy/training/corpus.py
+++ b/spacy/training/corpus.py
@@ -41,7 +41,10 @@ def create_docbin_reader(
 
 @util.registry.readers("spacy.JsonlCorpus.v1")
 def create_jsonl_reader(
-    path: Optional[Union[str, Path]], min_length: int = 0, max_length: int = 0, limit: int = 0
+    path: Optional[Union[str, Path]],
+    min_length: int = 0,
+    max_length: int = 0,
+    limit: int = 0,
 ) -> Callable[["Language"], Iterable[Example]]:
     return JsonlCorpus(path, min_length=min_length, max_length=max_length, limit=limit)
 

From c9baf9d196cba07fe1b1c636bcab3c80c6b81b44 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Mon, 15 Nov 2021 12:40:55 +0100
Subject: [PATCH 11/37] Fix spancat for empty docs and zero suggestions (#9654)

* Fix spancat for empty docs and zero suggestions

* Use ops.xp.zeros in test
---
 spacy/ml/extract_spans.py            | 10 +++++++--
 spacy/pipeline/spancat.py            |  2 +-
 spacy/tests/pipeline/test_spancat.py | 31 +++++++++++++++++++++++++++-
 3 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/spacy/ml/extract_spans.py b/spacy/ml/extract_spans.py
index 9bc972032..edc86ff9c 100644
--- a/spacy/ml/extract_spans.py
+++ b/spacy/ml/extract_spans.py
@@ -28,7 +28,13 @@ def forward(
     X, spans = source_spans
     assert spans.dataXd.ndim == 2
     indices = _get_span_indices(ops, spans, X.lengths)
-    Y = Ragged(X.dataXd[indices], spans.dataXd[:, 1] - spans.dataXd[:, 0])  # type: ignore[arg-type, index]
+    if len(indices) > 0:
+        Y = Ragged(X.dataXd[indices], spans.dataXd[:, 1] - spans.dataXd[:, 0])  # type: ignore[arg-type, index]
+    else:
+        Y = Ragged(
+            ops.xp.zeros(X.dataXd.shape, dtype=X.dataXd.dtype),
+            ops.xp.zeros((len(X.lengths),), dtype="i"),
+        )
     x_shape = X.dataXd.shape
     x_lengths = X.lengths
 
@@ -53,7 +59,7 @@ def _get_span_indices(ops, spans: Ragged, lengths: Ints1d) -> Ints1d:
         for j in range(spans_i.shape[0]):
             indices.append(ops.xp.arange(spans_i[j, 0], spans_i[j, 1]))  # type: ignore[call-overload, index]
         offset += length
-    return ops.flatten(indices)
+    return ops.flatten(indices, dtype="i", ndim_if_empty=1)
 
 
 def _ensure_cpu(spans: Ragged, lengths: Ints1d) -> Tuple[Ragged, Ints1d]:
diff --git a/spacy/pipeline/spancat.py b/spacy/pipeline/spancat.py
index 5b84ce8fb..829def1eb 100644
--- a/spacy/pipeline/spancat.py
+++ b/spacy/pipeline/spancat.py
@@ -78,7 +78,7 @@ def build_ngram_suggester(sizes: List[int]) -> Suggester:
         if len(spans) > 0:
             output = Ragged(ops.xp.vstack(spans), lengths_array)
         else:
-            output = Ragged(ops.xp.zeros((0, 0)), lengths_array)
+            output = Ragged(ops.xp.zeros((0, 0), dtype="i"), lengths_array)
 
         assert output.dataXd.ndim == 2
         return output
diff --git a/spacy/tests/pipeline/test_spancat.py b/spacy/tests/pipeline/test_spancat.py
index 5c3a9d27d..2f7e952d3 100644
--- a/spacy/tests/pipeline/test_spancat.py
+++ b/spacy/tests/pipeline/test_spancat.py
@@ -1,7 +1,7 @@
 import pytest
 import numpy
 from numpy.testing import assert_array_equal, assert_almost_equal
-from thinc.api import get_current_ops
+from thinc.api import get_current_ops, Ragged
 
 from spacy import util
 from spacy.lang.en import English
@@ -29,6 +29,7 @@ TRAIN_DATA_OVERLAPPING = [
         "I like London and Berlin",
         {"spans": {SPAN_KEY: [(7, 13, "LOC"), (18, 24, "LOC"), (7, 24, "DOUBLE_LOC")]}},
     ),
+    ("", {"spans": {SPAN_KEY: []}}),
 ]
 
 
@@ -365,3 +366,31 @@ def test_overfitting_IO_overlapping():
             "London and Berlin",
         }
         assert set([span.label_ for span in spans2]) == {"LOC", "DOUBLE_LOC"}
+
+
+def test_zero_suggestions():
+    # Test with a suggester that returns 0 suggestions
+
+    @registry.misc("test_zero_suggester")
+    def make_zero_suggester():
+        def zero_suggester(docs, *, ops=None):
+            if ops is None:
+                ops = get_current_ops()
+            return Ragged(
+                ops.xp.zeros((0, 0), dtype="i"), ops.xp.zeros((len(docs),), dtype="i")
+            )
+
+        return zero_suggester
+
+    fix_random_seed(0)
+    nlp = English()
+    spancat = nlp.add_pipe(
+        "spancat",
+        config={"suggester": {"@misc": "test_zero_suggester"}, "spans_key": SPAN_KEY},
+    )
+    train_examples = make_examples(nlp)
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    assert spancat.model.get_dim("nO") == 2
+    assert set(spancat.labels) == {"LOC", "PERSON"}
+
+    nlp.update(train_examples, sgd=optimizer)

From 86fa37e8baf631348ec712a174c19c3ca7fb88cd Mon Sep 17 00:00:00 2001
From: Vishnu Nandakumar <38393302+Vishnunkumar@users.noreply.github.com>
Date: Tue, 16 Nov 2021 10:36:19 +0530
Subject: [PATCH 12/37] Update universe.json with new library
 eng_spacysentiment (#9679)

* Update universe.json

* Update universe.json

* Cleanup fields

Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com>
---
 website/meta/universe.json | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/website/meta/universe.json b/website/meta/universe.json
index 9b7484a13..7f3813a95 100644
--- a/website/meta/universe.json
+++ b/website/meta/universe.json
@@ -3592,6 +3592,32 @@
                 "github": "xxyzz"
             },
             "category": ["standalone"]
+        },
+        {
+            "id": "eng_spacysentiment",
+            "title": "eng_spacysentiment",
+            "slogan": "Simple sentiment analysis using spaCy pipelines",
+            "description": "Sentiment analysis for simple english sentences using pre-trained spaCy pipelines",
+            "github": "vishnunkumar/spacysentiment",
+            "pip": "eng-spacysentiment",
+            "code_example": [
+                "import eng_spacysentiment",
+                "nlp = eng_spacysentiment.load()",
+                "text = \"Welcome to Arsenals official YouTube channel Watch as we take you closer and show you the personality of the club\"",
+                "doc = nlp(text)",
+                "print(doc.cats)",
+                "# {'positive': 0.29878824949264526, 'negative': 0.7012117505073547}"
+            ],
+            "thumb": "",
+            "image": "",
+            "code_language": "python",
+            "author": "Vishnu Nandakumar",
+            "author_links": {
+                "github": "Vishnunkumar",
+                "twitter": "vishnun_uchiha"
+            },
+            "category": ["pipeline"],
+            "tags": ["pipeline", "nlp", "sentiment"]
         }
     ],
 

From f3981bd0c87b5f686593e51a53825b2c718eac6e Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Thu, 18 Nov 2021 14:38:30 +0000
Subject: [PATCH 13/37] Clarify how to fill in init_tok2vec after pretraining
 (#9639)

* Clarify how to fill in init_tok2vec after pretraining

* Ignore init_tok2vec arg in pretraining

* Update docs, config setting

* Remove obsolete note about not filling init_tok2vec early

This seems to have also caught some lines that needed cleanup.
---
 spacy/training/pretrain.py                    |  2 ++
 website/docs/api/data-formats.md              |  2 +-
 website/docs/usage/embeddings-transformers.md | 35 +++++++++----------
 3 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/spacy/training/pretrain.py b/spacy/training/pretrain.py
index 465406a49..52af84aaf 100644
--- a/spacy/training/pretrain.py
+++ b/spacy/training/pretrain.py
@@ -31,6 +31,8 @@ def pretrain(
     allocator = config["training"]["gpu_allocator"]
     if use_gpu >= 0 and allocator:
         set_gpu_allocator(allocator)
+    # ignore in pretraining because we're creating it now
+    config["initialize"]["init_tok2vec"] = None
     nlp = load_model_from_config(config)
     _config = nlp.config.interpolate()
     P = registry.resolve(_config["pretraining"], schema=ConfigSchemaPretrain)
diff --git a/website/docs/api/data-formats.md b/website/docs/api/data-formats.md
index 001455f33..c6cd92799 100644
--- a/website/docs/api/data-formats.md
+++ b/website/docs/api/data-formats.md
@@ -248,7 +248,7 @@ Also see the usage guides on the
 | `after_init`   | Optional callback to modify the `nlp` object after initialization. ~~Optional[Callable[[Language], Language]]~~                                                                                                                                                                                                                                                                                                |
 | `before_init`  | Optional callback to modify the `nlp` object before initialization. ~~Optional[Callable[[Language], Language]]~~                                                                                                                                                                                                                                                                                               |
 | `components`   | Additional arguments passed to the `initialize` method of a pipeline component, keyed by component name. If type annotations are available on the method, the config will be validated against them. The `initialize` methods will always receive the `get_examples` callback and the current `nlp` object. ~~Dict[str, Dict[str, Any]]~~                                                                      |
-| `init_tok2vec` | Optional path to pretrained tok2vec weights created with [`spacy pretrain`](/api/cli#pretrain). Defaults to variable `${paths.init_tok2vec}`. ~~Optional[str]~~                                                                                                                                                                                                                                                |
+| `init_tok2vec` | Optional path to pretrained tok2vec weights created with [`spacy pretrain`](/api/cli#pretrain). Defaults to variable `${paths.init_tok2vec}`. Ignored when actually running pretraining, as you're creating the file to be used later. ~~Optional[str]~~                                                                                                                                                       |
 | `lookups`      | Additional lexeme and vocab data from [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data). Defaults to `null`. ~~Optional[Lookups]~~                                                                                                                                                                                                                                                       |
 | `tokenizer`    | Additional arguments passed to the `initialize` method of the specified tokenizer. Can be used for languages like Chinese that depend on dictionaries or trained models for tokenization. If type annotations are available on the method, the config will be validated against them. The `initialize` method will always receive the `get_examples` callback and the current `nlp` object. ~~Dict[str, Any]~~ |
 | `vectors`      | Name or path of pipeline containing pretrained word vectors to use, e.g. created with [`init vectors`](/api/cli#init-vectors). Defaults to `null`. ~~Optional[str]~~                                                                                                                                                                                                                                           |
diff --git a/website/docs/usage/embeddings-transformers.md b/website/docs/usage/embeddings-transformers.md
index febed6f2f..708cdd8bf 100644
--- a/website/docs/usage/embeddings-transformers.md
+++ b/website/docs/usage/embeddings-transformers.md
@@ -391,8 +391,8 @@ A wide variety of PyTorch models are supported, but some might not work. If a
 model doesn't seem to work feel free to open an
 [issue](https://github.com/explosion/spacy/issues). Additionally note that
 Transformers loaded in spaCy can only be used for tensors, and pretrained
-task-specific heads or text generation features cannot be used as part of 
-the `transformer` pipeline component.
+task-specific heads or text generation features cannot be used as part of the
+`transformer` pipeline component.
 
 <Infobox variant="warning">
 
@@ -715,8 +715,8 @@ network for a temporary task that forces the model to learn something about
 sentence structure and word cooccurrence statistics.
 
 Pretraining produces a **binary weights file** that can be loaded back in at the
-start of training, using the configuration option `initialize.init_tok2vec`.
-The weights file specifies an initial set of weights. Training then proceeds as
+start of training, using the configuration option `initialize.init_tok2vec`. The
+weights file specifies an initial set of weights. Training then proceeds as
 normal.
 
 You can only pretrain one subnetwork from your pipeline at a time, and the
@@ -751,15 +751,14 @@ layer = "tok2vec"
 
 #### Connecting pretraining to training {#pretraining-training}
 
-To benefit from pretraining, your training step needs to know to initialize
-its `tok2vec` component with the weights learned from the pretraining step.
-You do this by setting `initialize.init_tok2vec` to the filename of the
-`.bin` file that you want to use from pretraining.
+To benefit from pretraining, your training step needs to know to initialize its
+`tok2vec` component with the weights learned from the pretraining step. You do
+this by setting `initialize.init_tok2vec` to the filename of the `.bin` file
+that you want to use from pretraining.
 
-A pretraining step that runs for 5 epochs with an output path of `pretrain/`,
-as an example, produces `pretrain/model0.bin` through `pretrain/model4.bin`.
-To make use of the final output, you could fill in this value in your config
-file:
+A pretraining step that runs for 5 epochs with an output path of `pretrain/`, as
+an example, produces `pretrain/model0.bin` through `pretrain/model4.bin`. To
+make use of the final output, you could fill in this value in your config file:
 
 ```ini
 ### config.cfg
@@ -773,16 +772,14 @@ init_tok2vec = ${paths.init_tok2vec}
 
 <Infobox variant="warning">
 
-The outputs of `spacy pretrain` are not the same data format as the
-pre-packaged static word vectors that would go into 
-[`initialize.vectors`](/api/data-formats#config-initialize).
-The pretraining output consists of the weights that the `tok2vec`
-component should start with in an existing pipeline, so it goes in
-`initialize.init_tok2vec`.
+The outputs of `spacy pretrain` are not the same data format as the pre-packaged
+static word vectors that would go into
+[`initialize.vectors`](/api/data-formats#config-initialize). The pretraining
+output consists of the weights that the `tok2vec` component should start with in
+an existing pipeline, so it goes in `initialize.init_tok2vec`.
 
 </Infobox>
 
-
 #### Pretraining objectives {#pretraining-objectives}
 
 > ```ini

From ea450d652c32f65b947a1e1a498b45f29ed4dc29 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 19 Nov 2021 08:51:19 +0100
Subject: [PATCH 14/37] Exclude strings from v3.2+ source vector checks (#9697)

Exclude strings from `Vector.to_bytes()` comparions for v3.2+ `Vectors`
that now include the string store so that the source vector comparison
is only comparing the vectors and not the strings.
---
 spacy/language.py            | 7 +++++--
 spacy/training/initialize.py | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/spacy/language.py b/spacy/language.py
index aa57989ac..204b24ecb 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -701,7 +701,8 @@ class Language:
         if (
             self.vocab.vectors.shape != source.vocab.vectors.shape
             or self.vocab.vectors.key2row != source.vocab.vectors.key2row
-            or self.vocab.vectors.to_bytes() != source.vocab.vectors.to_bytes()
+            or self.vocab.vectors.to_bytes(exclude=["strings"])
+            != source.vocab.vectors.to_bytes(exclude=["strings"])
         ):
             warnings.warn(Warnings.W113.format(name=source_name))
         if source_name not in source.component_names:
@@ -1822,7 +1823,9 @@ class Language:
                         )
                     if model not in source_nlp_vectors_hashes:
                         source_nlp_vectors_hashes[model] = hash(
-                            source_nlps[model].vocab.vectors.to_bytes()
+                            source_nlps[model].vocab.vectors.to_bytes(
+                                exclude=["strings"]
+                            )
                         )
                     if "_sourced_vectors_hashes" not in nlp.meta:
                         nlp.meta["_sourced_vectors_hashes"] = {}
diff --git a/spacy/training/initialize.py b/spacy/training/initialize.py
index 13ccfeb93..084204389 100644
--- a/spacy/training/initialize.py
+++ b/spacy/training/initialize.py
@@ -132,7 +132,7 @@ def init_vocab(
         logger.info(f"Added vectors: {vectors}")
     # warn if source model vectors are not identical
     sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {})
-    vectors_hash = hash(nlp.vocab.vectors.to_bytes())
+    vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
     for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items():
         if vectors_hash != sourced_vectors_hash:
             warnings.warn(Warnings.W113.format(name=sourced_component))

From 0e93b315f3a5f96f2190d7eae7f6085bafe9c747 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 19 Nov 2021 08:51:46 +0100
Subject: [PATCH 15/37] Convert labels to strings for README in package CLI
 (#9694)

---
 spacy/cli/package.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/cli/package.py b/spacy/cli/package.py
index e76343dc3..76e14daf5 100644
--- a/spacy/cli/package.py
+++ b/spacy/cli/package.py
@@ -397,7 +397,7 @@ def _format_label_scheme(data: Dict[str, Any]) -> str:
             continue
         col1 = md.bold(md.code(pipe))
         col2 = ", ".join(
-            [md.code(label.replace("|", "\\|")) for label in labels]
+            [md.code(str(label).replace("|", "\\|")) for label in labels]
         )  # noqa: W605
         label_data.append((col1, col2))
         n_labels += len(labels)

From 13645dcbf5b2fe567be41d039c4cc4ebdae79ed6 Mon Sep 17 00:00:00 2001
From: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Date: Mon, 22 Nov 2021 06:43:11 +0100
Subject: [PATCH 16/37] add note that annotating components is new since 3.1
 (#9678)

---
 website/docs/api/data-formats.md | 38 ++++++++++++++++----------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/website/docs/api/data-formats.md b/website/docs/api/data-formats.md
index c6cd92799..c51a6dbca 100644
--- a/website/docs/api/data-formats.md
+++ b/website/docs/api/data-formats.md
@@ -181,25 +181,25 @@ single corpus once and then divide it up into `train` and `dev` partitions.
 This section defines settings and controls for the training and evaluation
 process that are used when you run [`spacy train`](/api/cli#train).
 
-| Name                    | Description                                                                                                                                                                                                                                                                                                                         |
-| ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `accumulate_gradient`   | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~                                                                                                                                                                                                                                                              |
-| `batcher`               | Callable that takes an iterator of [`Doc`](/api/doc) objects and yields batches of `Doc`s. Defaults to [`batch_by_words`](/api/top-level#batch_by_words). ~~Callable[[Iterator[Doc], Iterator[List[Doc]]]]~~                                                                                                                        |
-| `before_to_disk`        | Optional callback to modify `nlp` object right before it is saved to disk during and after training. Can be used to remove or reset config values or disable components. Defaults to `null`. ~~Optional[Callable[[Language], Language]]~~                                                                                           |
-| `dev_corpus`            | Dot notation of the config location defining the dev corpus. Defaults to `corpora.dev`. ~~str~~                                                                                                                                                                                                                                     |
-| `dropout`               | The dropout rate. Defaults to `0.1`. ~~float~~                                                                                                                                                                                                                                                                                      |
-| `eval_frequency`        | How often to evaluate during training (steps). Defaults to `200`. ~~int~~                                                                                                                                                                                                                                                           |
-| `frozen_components`     | Pipeline component names that are "frozen" and shouldn't be initialized or updated during training. See [here](/usage/training#config-components) for details. Defaults to `[]`. ~~List[str]~~                                                                                                                                      |
-| `annotating_components` | Pipeline component names that should set annotations on the predicted docs during training. See [here](/usage/training#annotating-components) for details. Defaults to `[]`. ~~List[str]~~                                                                                                                                          |
-| `gpu_allocator`         | Library for cupy to route GPU memory allocation to. Can be `"pytorch"` or `"tensorflow"`. Defaults to variable `${system.gpu_allocator}`. ~~str~~                                                                                                                                                                                   |
-| `logger`                | Callable that takes the `nlp` and stdout and stderr `IO` objects, sets up the logger, and returns two new callables to log a training step and to finalize the logger. Defaults to [`ConsoleLogger`](/api/top-level#ConsoleLogger). ~~Callable[[Language, IO, IO], [Tuple[Callable[[Dict[str, Any]], None], Callable[[], None]]]]~~ |
-| `max_epochs`            | Maximum number of epochs to train for. `0` means an unlimited number of epochs. `-1` means that the train corpus should be streamed rather than loaded into memory with no shuffling within the training loop. Defaults to `0`. ~~int~~                                                                                             |
-| `max_steps`             | Maximum number of update steps to train for. `0` means an unlimited number of steps. Defaults to `20000`. ~~int~~                                                                                                                                                                                                                   |
-| `optimizer`             | The optimizer. The learning rate schedule and other settings can be configured as part of the optimizer. Defaults to [`Adam`](https://thinc.ai/docs/api-optimizers#adam). ~~Optimizer~~                                                                                                                                             |
-| `patience`              | How many steps to continue without improvement in evaluation score. `0` disables early stopping. Defaults to `1600`. ~~int~~                                                                                                                                                                                                        |
-| `score_weights`         | Score names shown in metrics mapped to their weight towards the final weighted score. See [here](/usage/training#metrics) for details. Defaults to `{}`. ~~Dict[str, float]~~                                                                                                                                                       |
-| `seed`                  | The random seed. Defaults to variable `${system.seed}`. ~~int~~                                                                                                                                                                                                                                                                     |
-| `train_corpus`          | Dot notation of the config location defining the train corpus. Defaults to `corpora.train`. ~~str~~                                                                                                                                                                                                                                 |
+| Name                                                 | Description                                                                                                                                                                                                                                                                                                                         |
+| ---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `accumulate_gradient`                                | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~                                                                                                                                                                                                                                                              |
+| `batcher`                                            | Callable that takes an iterator of [`Doc`](/api/doc) objects and yields batches of `Doc`s. Defaults to [`batch_by_words`](/api/top-level#batch_by_words). ~~Callable[[Iterator[Doc], Iterator[List[Doc]]]]~~                                                                                                                        |
+| `before_to_disk`                                     | Optional callback to modify `nlp` object right before it is saved to disk during and after training. Can be used to remove or reset config values or disable components. Defaults to `null`. ~~Optional[Callable[[Language], Language]]~~                                                                                           |
+| `dev_corpus`                                         | Dot notation of the config location defining the dev corpus. Defaults to `corpora.dev`. ~~str~~                                                                                                                                                                                                                                     |
+| `dropout`                                            | The dropout rate. Defaults to `0.1`. ~~float~~                                                                                                                                                                                                                                                                                      |
+| `eval_frequency`                                     | How often to evaluate during training (steps). Defaults to `200`. ~~int~~                                                                                                                                                                                                                                                           |
+| `frozen_components`                                  | Pipeline component names that are "frozen" and shouldn't be initialized or updated during training. See [here](/usage/training#config-components) for details. Defaults to `[]`. ~~List[str]~~                                                                                                                                      |
+| `annotating_components` <Tag variant="new">3.1</Tag> | Pipeline component names that should set annotations on the predicted docs during training. See [here](/usage/training#annotating-components) for details. Defaults to `[]`. ~~List[str]~~                                                                                                                                          |
+| `gpu_allocator`                                      | Library for cupy to route GPU memory allocation to. Can be `"pytorch"` or `"tensorflow"`. Defaults to variable `${system.gpu_allocator}`. ~~str~~                                                                                                                                                                                   |
+| `logger`                                             | Callable that takes the `nlp` and stdout and stderr `IO` objects, sets up the logger, and returns two new callables to log a training step and to finalize the logger. Defaults to [`ConsoleLogger`](/api/top-level#ConsoleLogger). ~~Callable[[Language, IO, IO], [Tuple[Callable[[Dict[str, Any]], None], Callable[[], None]]]]~~ |
+| `max_epochs`                                         | Maximum number of epochs to train for. `0` means an unlimited number of epochs. `-1` means that the train corpus should be streamed rather than loaded into memory with no shuffling within the training loop. Defaults to `0`. ~~int~~                                                                                             |
+| `max_steps`                                          | Maximum number of update steps to train for. `0` means an unlimited number of steps. Defaults to `20000`. ~~int~~                                                                                                                                                                                                                   |
+| `optimizer`                                          | The optimizer. The learning rate schedule and other settings can be configured as part of the optimizer. Defaults to [`Adam`](https://thinc.ai/docs/api-optimizers#adam). ~~Optimizer~~                                                                                                                                             |
+| `patience`                                           | How many steps to continue without improvement in evaluation score. `0` disables early stopping. Defaults to `1600`. ~~int~~                                                                                                                                                                                                        |
+| `score_weights`                                      | Score names shown in metrics mapped to their weight towards the final weighted score. See [here](/usage/training#metrics) for details. Defaults to `{}`. ~~Dict[str, float]~~                                                                                                                                                       |
+| `seed`                                               | The random seed. Defaults to variable `${system.seed}`. ~~int~~                                                                                                                                                                                                                                                                     |
+| `train_corpus`                                       | Dot notation of the config location defining the train corpus. Defaults to `corpora.train`. ~~str~~                                                                                                                                                                                                                                 |
 
 ### pretraining {#config-pretraining tag="section,optional"}
 

From 52b8c2d2e0241e1c515131c5e5f576d5dad65059 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Mon, 22 Nov 2021 10:06:07 +0000
Subject: [PATCH 17/37] Add note on batch contract for listeners (#9691)

* Add note on batch contract

Using listeners requires batches to be consistent. This is obvious if
you understand how the listener works, but it wasn't clearly stated in
the Docs, and was subtle enough that the EntityLinker missed it.

There is probably a clearer way to explain what the actual requirement
is, but I figure this is a good start.

* Rewrite to clarify role of caching
---
 website/docs/api/architectures.md | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/website/docs/api/architectures.md b/website/docs/api/architectures.md
index 01ca4540b..44ba94d9e 100644
--- a/website/docs/api/architectures.md
+++ b/website/docs/api/architectures.md
@@ -124,6 +124,14 @@ Instead of defining its own `Tok2Vec` instance, a model architecture like
 [Tagger](/api/architectures#tagger) can define a listener as its `tok2vec`
 argument that connects to the shared `tok2vec` component in the pipeline.
 
+Listeners work by caching the `Tok2Vec` output for a given batch of `Doc`s. This
+means that in order for a component to work with the listener, the batch of
+`Doc`s passed to the listener must be the same as the batch of `Doc`s passed to
+the `Tok2Vec`. As a result, any manipulation of the `Doc`s which would affect
+`Tok2Vec` output, such as to create special contexts or remove `Doc`s for which
+no prediction can be made, must happen inside the model, **after** the call to
+the `Tok2Vec` component.
+
 | Name        | Description                                                                                                                                                                                                                                                                                                                          |
 | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `width`     | The width of the vectors produced by the "upstream" [`Tok2Vec`](/api/tok2vec) component. ~~int~~                                                                                                                                                                                                                                     |

From 36c70479468b10e1c8578a5a75dec9e908340a6f Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 23 Nov 2021 14:55:55 +0100
Subject: [PATCH 18/37] Use reference parse to initialize parser moves (#9722)

---
 spacy/pipeline/_parser_internals/arc_eager.pyx | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/spacy/pipeline/_parser_internals/arc_eager.pyx b/spacy/pipeline/_parser_internals/arc_eager.pyx
index f34975858..ddcc911c8 100644
--- a/spacy/pipeline/_parser_internals/arc_eager.pyx
+++ b/spacy/pipeline/_parser_internals/arc_eager.pyx
@@ -585,7 +585,10 @@ cdef class ArcEager(TransitionSystem):
             actions[RIGHT][label] = 1
             actions[REDUCE][label] = 1
         for example in kwargs.get('examples', []):
-            heads, labels = example.get_aligned_parse(projectivize=True)
+            # use heads and labels from the reference parse (without regard to
+            # misalignments between the predicted and reference)
+            example_gold_preproc = Example(example.reference, example.reference)
+            heads, labels = example_gold_preproc.get_aligned_parse(projectivize=True)
             for child, (head, label) in enumerate(zip(heads, labels)):
                 if head is None or label is None:
                     continue

From a77f50baa43029d3676fdaa6079e0635444de21b Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 23 Nov 2021 15:17:19 +0100
Subject: [PATCH 19/37] Allow Scorer.score_spans to handle pred docs with
 missing annotation (#9701)

If the predicted docs are missing annotation according to
`has_annotation`, treat the docs as having no predictions rather than
raising errors when the annotation is missing.

The motivation for this is a combined tokenization+sents scorer for a
component where the sents annotation is optional. To provide a single
scorer in the component factory, it needs to be possible for the scorer
to continue despite missing sents annotation in the case where the
component is not annotating sents.
---
 spacy/scorer.py | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/spacy/scorer.py b/spacy/scorer.py
index cfdf34e62..4d596b5e1 100644
--- a/spacy/scorer.py
+++ b/spacy/scorer.py
@@ -359,14 +359,15 @@ class Scorer:
             pred_doc = example.predicted
             gold_doc = example.reference
             # Option to handle docs without annotation for this attribute
-            if has_annotation is not None:
-                if not has_annotation(gold_doc):
-                    continue
-            # Find all labels in gold and doc
-            labels = set(
-                [k.label_ for k in getter(gold_doc, attr)]
-                + [k.label_ for k in getter(pred_doc, attr)]
-            )
+            if has_annotation is not None and not has_annotation(gold_doc):
+                continue
+            # Find all labels in gold
+            labels = set([k.label_ for k in getter(gold_doc, attr)])
+            # If labeled, find all labels in pred
+            if has_annotation is None or (
+                has_annotation is not None and has_annotation(pred_doc)
+            ):
+                labels |= set([k.label_ for k in getter(pred_doc, attr)])
             # Set up all labels for per type scoring and prepare gold per type
             gold_per_type: Dict[str, Set] = {label: set() for label in labels}
             for label in labels:
@@ -384,16 +385,19 @@ class Scorer:
                 gold_spans.add(gold_span)
                 gold_per_type[span.label_].add(gold_span)
             pred_per_type: Dict[str, Set] = {label: set() for label in labels}
-            for span in example.get_aligned_spans_x2y(
-                getter(pred_doc, attr), allow_overlap
+            if has_annotation is None or (
+                has_annotation is not None and has_annotation(pred_doc)
             ):
-                pred_span: Tuple
-                if labeled:
-                    pred_span = (span.label_, span.start, span.end - 1)
-                else:
-                    pred_span = (span.start, span.end - 1)
-                pred_spans.add(pred_span)
-                pred_per_type[span.label_].add(pred_span)
+                for span in example.get_aligned_spans_x2y(
+                    getter(pred_doc, attr), allow_overlap
+                ):
+                    pred_span: Tuple
+                    if labeled:
+                        pred_span = (span.label_, span.start, span.end - 1)
+                    else:
+                        pred_span = (span.start, span.end - 1)
+                    pred_spans.add(pred_span)
+                    pred_per_type[span.label_].add(pred_span)
             # Scores per label
             if labeled:
                 for k, v in score_per_type.items():

From 9ac6d4991eb34d47f2e42bf7418918d49cf76219 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 23 Nov 2021 15:33:33 +0100
Subject: [PATCH 20/37] Add doc_cleaner component (#9659)

* Add doc_cleaner component

* Fix types

* Fix loop

* Rephrase method description
---
 spacy/errors.py                        |  1 +
 spacy/pipeline/functions.py            | 64 ++++++++++++++++++++++++++
 spacy/tests/pipeline/test_functions.py | 25 ++++++++++
 website/docs/api/pipeline-functions.md | 22 +++++++++
 4 files changed, 112 insertions(+)

diff --git a/spacy/errors.py b/spacy/errors.py
index 5fe550145..84c407422 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -191,6 +191,7 @@ class Warnings(metaclass=ErrorsWithCodes):
             "lead to errors.")
     W115 = ("Skipping {method}: the floret vector table cannot be modified. "
             "Vectors are calculated from character ngrams.")
+    W116 = ("Unable to clean attribute '{attr}'.")
 
 
 class Errors(metaclass=ErrorsWithCodes):
diff --git a/spacy/pipeline/functions.py b/spacy/pipeline/functions.py
index f0a75dc2c..c005395bf 100644
--- a/spacy/pipeline/functions.py
+++ b/spacy/pipeline/functions.py
@@ -1,6 +1,8 @@
 from typing import Dict, Any
 import srsly
+import warnings
 
+from ..errors import Warnings
 from ..language import Language
 from ..matcher import Matcher
 from ..tokens import Doc
@@ -136,3 +138,65 @@ class TokenSplitter:
             "cfg": lambda p: self._set_config(srsly.read_json(p)),
         }
         util.from_disk(path, serializers, [])
+
+
+@Language.factory(
+    "doc_cleaner",
+    default_config={"attrs": {"tensor": None, "_.trf_data": None}, "silent": True},
+)
+def make_doc_cleaner(nlp: Language, name: str, *, attrs: Dict[str, Any], silent: bool):
+    return DocCleaner(attrs, silent=silent)
+
+
+class DocCleaner:
+    def __init__(self, attrs: Dict[str, Any], *, silent: bool = True):
+        self.cfg: Dict[str, Any] = {"attrs": dict(attrs), "silent": silent}
+
+    def __call__(self, doc: Doc) -> Doc:
+        attrs: dict = self.cfg["attrs"]
+        silent: bool = self.cfg["silent"]
+        for attr, value in attrs.items():
+            obj = doc
+            parts = attr.split(".")
+            skip = False
+            for part in parts[:-1]:
+                if hasattr(obj, part):
+                    obj = getattr(obj, part)
+                else:
+                    skip = True
+                    if not silent:
+                        warnings.warn(Warnings.W116.format(attr=attr))
+            if not skip:
+                if hasattr(obj, parts[-1]):
+                    setattr(obj, parts[-1], value)
+                else:
+                    if not silent:
+                        warnings.warn(Warnings.W116.format(attr=attr))
+        return doc
+
+    def to_bytes(self, **kwargs):
+        serializers = {
+            "cfg": lambda: srsly.json_dumps(self.cfg),
+        }
+        return util.to_bytes(serializers, [])
+
+    def from_bytes(self, data, **kwargs):
+        deserializers = {
+            "cfg": lambda b: self.cfg.update(srsly.json_loads(b)),
+        }
+        util.from_bytes(data, deserializers, [])
+        return self
+
+    def to_disk(self, path, **kwargs):
+        path = util.ensure_path(path)
+        serializers = {
+            "cfg": lambda p: srsly.write_json(p, self.cfg),
+        }
+        return util.to_disk(path, serializers, [])
+
+    def from_disk(self, path, **kwargs):
+        path = util.ensure_path(path)
+        serializers = {
+            "cfg": lambda p: self.cfg.update(srsly.read_json(p)),
+        }
+        util.from_disk(path, serializers, [])
diff --git a/spacy/tests/pipeline/test_functions.py b/spacy/tests/pipeline/test_functions.py
index 454d7b08b..e4adfe2fe 100644
--- a/spacy/tests/pipeline/test_functions.py
+++ b/spacy/tests/pipeline/test_functions.py
@@ -3,6 +3,8 @@ from spacy.pipeline.functions import merge_subtokens
 from spacy.language import Language
 from spacy.tokens import Span, Doc
 
+from ..doc.test_underscore import clean_underscore  # noqa: F401
+
 
 @pytest.fixture
 def doc(en_vocab):
@@ -74,3 +76,26 @@ def test_token_splitter():
         "i",
     ]
     assert all(len(t.text) <= token_splitter.split_length for t in doc)
+
+
+@pytest.mark.usefixtures("clean_underscore")
+def test_factories_doc_cleaner():
+    nlp = Language()
+    nlp.add_pipe("doc_cleaner")
+    doc = nlp.make_doc("text")
+    doc.tensor = [1, 2, 3]
+    doc = nlp(doc)
+    assert doc.tensor is None
+
+    nlp = Language()
+    nlp.add_pipe("doc_cleaner", config={"silent": False})
+    with pytest.warns(UserWarning):
+        doc = nlp("text")
+
+    Doc.set_extension("test_attr", default=-1)
+    nlp = Language()
+    nlp.add_pipe("doc_cleaner", config={"attrs": {"_.test_attr": 0}})
+    doc = nlp.make_doc("text")
+    doc._.test_attr = 100
+    doc = nlp(doc)
+    assert doc._.test_attr == 0
diff --git a/website/docs/api/pipeline-functions.md b/website/docs/api/pipeline-functions.md
index a776eca9b..ff19d3e71 100644
--- a/website/docs/api/pipeline-functions.md
+++ b/website/docs/api/pipeline-functions.md
@@ -130,3 +130,25 @@ exceed the transformer model max length.
 | `min_length`   | The minimum length for a token to be split. Defaults to `25`. ~~int~~ |
 | `split_length` | The length of the split tokens. Defaults to `5`. ~~int~~              |
 | **RETURNS**    | The modified `Doc` with the split tokens. ~~Doc~~                     |
+
+## doc_cleaner {#doc_cleaner tag="function" new="3.2.1"}
+
+Clean up `Doc` attributes. Intended for use at the end of pipelines with
+`tok2vec` or `transformer` pipeline components that store tensors and other
+values that can require a lot of memory and frequently aren't needed after the
+whole pipeline has run.
+
+> #### Example
+>
+> ```python
+> config = {"attrs": {"tensor": None}}
+> nlp.add_pipe("doc_cleaner", config=config)
+> doc = nlp("text")
+> assert doc.tensor is None
+> ```
+
+| Setting     | Description                                                                                                                                                                         |
+| ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `attrs`     | A dict of the `Doc` attributes and the values to set them to. Defaults to `{"tensor": None, "_.trf_data": None}` to clean up after `tok2vec` and `transformer` components. ~~dict~~ |
+| `silent`    | If `False`, show warnings if attributes aren't found or can't be set. Defaults to `True`. ~~bool~~                                                                                  |
+| **RETURNS** | The modified `Doc` with the modified attributes. ~~Doc~~                                                                                                                            |

From a7d7e80adb9f325efa209ef0deb7365bdc76ee04 Mon Sep 17 00:00:00 2001
From: Duygu Altinok <duygu@explosion.ai>
Date: Tue, 23 Nov 2021 16:26:05 +0100
Subject: [PATCH 21/37] EntityRuler improve disk load error message  (#9658)

* added error string

* added serialization test

* added more to if statements

* wrote file to tempdir

* added tempdir

* changed parameter a bit

* Update spacy/tests/pipeline/test_entity_ruler.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/errors.py                           |  1 +
 spacy/pipeline/entityruler.py             | 12 ++++++++++--
 spacy/tests/pipeline/test_entity_ruler.py | 22 ++++++++++++++++++++++
 3 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/spacy/errors.py b/spacy/errors.py
index 84c407422..c5e364013 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -888,6 +888,7 @@ class Errors(metaclass=ErrorsWithCodes):
     E1021 = ("`pos` value \"{pp}\" is not a valid Universal Dependencies tag. "
              "Non-UD tags should use the `tag` property.")
     E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
+    E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't exist.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings
diff --git a/spacy/pipeline/entityruler.py b/spacy/pipeline/entityruler.py
index 2c3db2575..78d7a0be2 100644
--- a/spacy/pipeline/entityruler.py
+++ b/spacy/pipeline/entityruler.py
@@ -431,10 +431,16 @@ class EntityRuler(Pipe):
         path = ensure_path(path)
         self.clear()
         depr_patterns_path = path.with_suffix(".jsonl")
-        if depr_patterns_path.is_file():
+        if path.suffix == ".jsonl":  # user provides a jsonl
+            if path.is_file:
+                patterns = srsly.read_jsonl(path)
+                self.add_patterns(patterns)
+            else:
+                raise ValueError(Errors.E1023.format(path=path))
+        elif depr_patterns_path.is_file():
             patterns = srsly.read_jsonl(depr_patterns_path)
             self.add_patterns(patterns)
-        else:
+        elif path.is_dir():  # path is a valid directory
             cfg = {}
             deserializers_patterns = {
                 "patterns": lambda p: self.add_patterns(
@@ -451,6 +457,8 @@ class EntityRuler(Pipe):
                 self.nlp.vocab, attr=self.phrase_matcher_attr
             )
             from_disk(path, deserializers_patterns, {})
+        else:  # path is not a valid directory or file
+            raise ValueError(Errors.E146.format(path=path))
         return self
 
     def to_disk(
diff --git a/spacy/tests/pipeline/test_entity_ruler.py b/spacy/tests/pipeline/test_entity_ruler.py
index dc0ca0301..e66b49518 100644
--- a/spacy/tests/pipeline/test_entity_ruler.py
+++ b/spacy/tests/pipeline/test_entity_ruler.py
@@ -5,6 +5,8 @@ from spacy.tokens import Span
 from spacy.language import Language
 from spacy.pipeline import EntityRuler
 from spacy.errors import MatchPatternError
+from spacy.tests.util import make_tempdir
+
 from thinc.api import NumpyOps, get_current_ops
 
 
@@ -238,3 +240,23 @@ def test_entity_ruler_multiprocessing(nlp, n_process):
         for doc in nlp.pipe(texts, n_process=2):
             for ent in doc.ents:
                 assert ent.ent_id_ == "1234"
+
+
+def test_entity_ruler_serialize_jsonl(nlp, patterns):
+    ruler = nlp.add_pipe("entity_ruler")
+    ruler.add_patterns(patterns)
+    with make_tempdir() as d:
+        ruler.to_disk(d / "test_ruler.jsonl")
+        ruler.from_disk(d / "test_ruler.jsonl")  # read from an existing jsonl file
+        with pytest.raises(ValueError):
+            ruler.from_disk(d / "non_existing.jsonl")  # read from a bad jsonl file
+
+
+def test_entity_ruler_serialize_dir(nlp, patterns):
+    ruler = nlp.add_pipe("entity_ruler")
+    ruler.add_patterns(patterns)
+    with make_tempdir() as d:
+        ruler.to_disk(d / "test_ruler")
+        ruler.from_disk(d / "test_ruler")  # read from an existing directory
+        with pytest.raises(ValueError):
+            ruler.from_disk(d / "non_existing_dir")  # read from a bad directory

From 0bbf86bba8f596f0cbf0132527ab2f767343c488 Mon Sep 17 00:00:00 2001
From: Valentin-Gabriel Soumah <60576980+Pantalaymon@users.noreply.github.com>
Date: Tue, 23 Nov 2021 17:29:23 +0100
Subject: [PATCH 22/37] Create Pantalaymon.md

Submitting agreement to spacy in order to contribute to Coreferee project .
---
 .github/contributors/Pantalaymon.md | 106 ++++++++++++++++++++++++++++
 1 file changed, 106 insertions(+)
 create mode 100644 .github/contributors/Pantalaymon.md

diff --git a/.github/contributors/Pantalaymon.md b/.github/contributors/Pantalaymon.md
new file mode 100644
index 000000000..f017f2947
--- /dev/null
+++ b/.github/contributors/Pantalaymon.md
@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           |Valentin-Gabriel Soumah|
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           |    2021-11-23        |
+| GitHub username                |     Pantalaymon      |
+| Website (optional)             |                      |

From a4c43e5c577d7a143ef7e2fd74ccea33aace96b7 Mon Sep 17 00:00:00 2001
From: Natalia Rodnova <4512370+nrodnova@users.noreply.github.com>
Date: Wed, 24 Nov 2021 02:37:10 -0700
Subject: [PATCH 23/37] Allow Matcher to match on ENT_ID and ENT_KB_ID  (#9688)

* Added ENT_ID and ENT_KB_ID into the list of the attributes that Matcher matches on

* Added ENT_ID and ENT_KB_ID to TEST_PATTERNS in test_pattern_validation.py. Disabled tests that I added before

* Update website/docs/api/matcher.md

* Format

* Remove skipped tests

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
---
 spacy/schemas.py                               | 2 ++
 spacy/tests/matcher/test_pattern_validation.py | 4 ++++
 website/docs/api/matcher.md                    | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/spacy/schemas.py b/spacy/schemas.py
index b3ea11d8b..cf58688ef 100644
--- a/spacy/schemas.py
+++ b/spacy/schemas.py
@@ -222,6 +222,8 @@ class TokenPattern(BaseModel):
     lemma: Optional[StringValue] = None
     shape: Optional[StringValue] = None
     ent_type: Optional[StringValue] = None
+    ent_id: Optional[StringValue] = None
+    ent_kb_id: Optional[StringValue] = None
     norm: Optional[StringValue] = None
     length: Optional[NumberValue] = None
     spacy: Optional[StrictBool] = None
diff --git a/spacy/tests/matcher/test_pattern_validation.py b/spacy/tests/matcher/test_pattern_validation.py
index 4d21aea81..74feb7c5d 100644
--- a/spacy/tests/matcher/test_pattern_validation.py
+++ b/spacy/tests/matcher/test_pattern_validation.py
@@ -22,6 +22,8 @@ TEST_PATTERNS = [
     ([{"TEXT": {"VALUE": "foo"}}], 2, 0),  # prev: (1, 0)
     ([{"IS_DIGIT": -1}], 1, 0),
     ([{"ORTH": -1}], 1, 0),
+    ([{"ENT_ID": -1}], 1, 0),
+    ([{"ENT_KB_ID": -1}], 1, 0),
     # Good patterns
     ([{"TEXT": "foo"}, {"LOWER": "bar"}], 0, 0),
     ([{"LEMMA": {"IN": ["love", "like"]}}, {"POS": "DET", "OP": "?"}], 0, 0),
@@ -33,6 +35,8 @@ TEST_PATTERNS = [
     ([{"orth": "foo"}], 0, 0),  # prev: xfail
     ([{"IS_SENT_START": True}], 0, 0),
     ([{"SENT_START": True}], 0, 0),
+    ([{"ENT_ID": "STRING"}], 0, 0),
+    ([{"ENT_KB_ID": "STRING"}], 0, 0),
 ]
 
 
diff --git a/website/docs/api/matcher.md b/website/docs/api/matcher.md
index c34560dec..803105ba2 100644
--- a/website/docs/api/matcher.md
+++ b/website/docs/api/matcher.md
@@ -44,6 +44,8 @@ rule-based matching are:
 | `SPACY`                                         | Token has a trailing space. ~~bool~~                                                                                      |
 |  `POS`, `TAG`, `MORPH`, `DEP`, `LEMMA`, `SHAPE` | The token's simple and extended part-of-speech tag, morphological analysis, dependency label, lemma, shape. ~~str~~       |
 | `ENT_TYPE`                                      | The token's entity label. ~~str~~                                                                                         |
+| `ENT_ID`                                        | The token's entity ID (`ent_id`). ~~str~~                                                                                 |
+| `ENT_KB_ID`                                     | The token's entity knowledge base ID (`ent_kb_id`). ~~str~~                                                               |
 | `_` <Tag variant="new">2.1</Tag>                | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ |
 | `OP`                                            | Operator or quantifier to determine how often to match a token pattern. ~~str~~                                           |
 

From 5c445332632079489acf214a675f0a193b383915 Mon Sep 17 00:00:00 2001
From: Tuomo Hiippala <tuomo.hiippala@iki.fi>
Date: Sun, 28 Nov 2021 12:33:16 +0200
Subject: [PATCH 24/37] add entry for Applied Language Technology under
 "Courses" (#9755)

Added the following entry into `universe.json`:

```
        {
            "type": "education",
            "id": "applt-course",
            "title": "Applied Language Technology",
            "slogan": "NLP for newcomers using spaCy and Stanza",
            "description": "These learning materials provide an introduction to applied language technology for audiences who are unfamiliar with language technology and programming. The learning materials assume no previous knowledge of the Python programming language.",
            "url": "https://applied-language-technology.readthedocs.io/",
            "image": "https://www.mv.helsinki.fi/home/thiippal/images/applt-preview.jpg",
            "thumb": "https://applied-language-technology.readthedocs.io/en/latest/_static/logo.png",
            "author": "Tuomo Hiippala",
            "author_links": {
                "twitter": "tuomo_h",
                "github": "thiippal",
                "website": "https://www.mv.helsinki.fi/home/thiippal/"
            },
            "category": ["courses"]
        },
```
---
 website/meta/universe.json | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/website/meta/universe.json b/website/meta/universe.json
index 7f3813a95..d11b0e8c5 100644
--- a/website/meta/universe.json
+++ b/website/meta/universe.json
@@ -1752,6 +1752,23 @@
             },
             "category": ["courses"]
         },
+        {
+            "type": "education",
+            "id": "applt-course",
+            "title": "Applied Language Technology",
+            "slogan": "NLP for newcomers using spaCy and Stanza",
+            "description": "These learning materials provide an introduction to applied language technology for audiences who are unfamiliar with language technology and programming. The learning materials assume no previous knowledge of the Python programming language.",
+            "url": "https://applied-language-technology.readthedocs.io/",
+            "image": "https://www.mv.helsinki.fi/home/thiippal/images/applt-preview.jpg",
+            "thumb": "https://applied-language-technology.readthedocs.io/en/latest/_static/logo.png",
+            "author": "Tuomo Hiippala",
+            "author_links": {
+                "twitter": "tuomo_h",
+                "github": "thiippal",
+                "website": "https://www.mv.helsinki.fi/home/thiippal/"
+            },
+            "category": ["courses"]
+        },
         {
             "type": "education",
             "id": "video-spacys-ner-model",

From 7b134b8fbd64bd8cfad2a0ecd7be9b6a7d7a907d Mon Sep 17 00:00:00 2001
From: Richard Hudson <richard@explosion.ai>
Date: Sun, 28 Nov 2021 21:59:23 +0100
Subject: [PATCH 25/37] New tests for a number of alpha languages (#9703)

* Added Slovak

* Added Slovenian tests

* Added Estonian tests

* Added Croatian tests

* Added Latvian tests

* Added Icelandic tests

* Added Afrikaans tests

* Added language-independent tests

* Added Kannada tests

* Tidied up

* Added Albanian tests

* Formatted with black

* Added failing tests for anomalies

* Update spacy/tests/lang/af/test_text.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Estonian tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Croatian tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Icelandic tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Latvian tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Slovak tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Added context to failing Slovenian tokenizer test

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/tests/conftest.py               | 40 ++++++++++++++++++++++
 spacy/tests/lang/af/__init__.py       |  0
 spacy/tests/lang/af/test_text.py      | 22 ++++++++++++
 spacy/tests/lang/af/test_tokenizer.py | 29 ++++++++++++++++
 spacy/tests/lang/et/__init__.py       |  0
 spacy/tests/lang/et/test_text.py      | 26 +++++++++++++++
 spacy/tests/lang/et/test_tokenizer.py | 29 ++++++++++++++++
 spacy/tests/lang/hr/__init__.py       |  0
 spacy/tests/lang/hr/test_text.py      | 26 +++++++++++++++
 spacy/tests/lang/hr/test_tokenizer.py | 31 +++++++++++++++++
 spacy/tests/lang/is/__init__.py       |  0
 spacy/tests/lang/is/test_text.py      | 26 +++++++++++++++
 spacy/tests/lang/is/test_tokenizer.py | 30 +++++++++++++++++
 spacy/tests/lang/lv/__init__.py       |  0
 spacy/tests/lang/lv/test_text.py      | 27 +++++++++++++++
 spacy/tests/lang/lv/test_tokenizer.py | 30 +++++++++++++++++
 spacy/tests/lang/sk/__init__.py       |  0
 spacy/tests/lang/sk/test_text.py      | 48 +++++++++++++++++++++++++++
 spacy/tests/lang/sk/test_tokenizer.py | 15 +++++++++
 spacy/tests/lang/sl/__init__.py       |  0
 spacy/tests/lang/sl/test_text.py      | 27 +++++++++++++++
 spacy/tests/lang/sl/test_tokenizer.py | 32 ++++++++++++++++++
 spacy/tests/lang/sq/__init__.py       |  0
 spacy/tests/lang/sq/test_text.py      | 25 ++++++++++++++
 spacy/tests/lang/sq/test_tokenizer.py | 31 +++++++++++++++++
 spacy/tests/lang/xx/__init__.py       |  0
 spacy/tests/lang/xx/test_text.py      | 24 ++++++++++++++
 spacy/tests/lang/xx/test_tokenizer.py | 25 ++++++++++++++
 28 files changed, 543 insertions(+)
 create mode 100644 spacy/tests/lang/af/__init__.py
 create mode 100644 spacy/tests/lang/af/test_text.py
 create mode 100644 spacy/tests/lang/af/test_tokenizer.py
 create mode 100644 spacy/tests/lang/et/__init__.py
 create mode 100644 spacy/tests/lang/et/test_text.py
 create mode 100644 spacy/tests/lang/et/test_tokenizer.py
 create mode 100644 spacy/tests/lang/hr/__init__.py
 create mode 100644 spacy/tests/lang/hr/test_text.py
 create mode 100644 spacy/tests/lang/hr/test_tokenizer.py
 create mode 100644 spacy/tests/lang/is/__init__.py
 create mode 100644 spacy/tests/lang/is/test_text.py
 create mode 100644 spacy/tests/lang/is/test_tokenizer.py
 create mode 100644 spacy/tests/lang/lv/__init__.py
 create mode 100644 spacy/tests/lang/lv/test_text.py
 create mode 100644 spacy/tests/lang/lv/test_tokenizer.py
 create mode 100644 spacy/tests/lang/sk/__init__.py
 create mode 100644 spacy/tests/lang/sk/test_text.py
 create mode 100644 spacy/tests/lang/sk/test_tokenizer.py
 create mode 100644 spacy/tests/lang/sl/__init__.py
 create mode 100644 spacy/tests/lang/sl/test_text.py
 create mode 100644 spacy/tests/lang/sl/test_tokenizer.py
 create mode 100644 spacy/tests/lang/sq/__init__.py
 create mode 100644 spacy/tests/lang/sq/test_text.py
 create mode 100644 spacy/tests/lang/sq/test_tokenizer.py
 create mode 100644 spacy/tests/lang/xx/__init__.py
 create mode 100644 spacy/tests/lang/xx/test_text.py
 create mode 100644 spacy/tests/lang/xx/test_tokenizer.py

diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py
index 88c7adfe3..ffca79bb9 100644
--- a/spacy/tests/conftest.py
+++ b/spacy/tests/conftest.py
@@ -49,6 +49,11 @@ def tokenizer():
     return get_lang_class("xx")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def af_tokenizer():
+    return get_lang_class("af")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def am_tokenizer():
     return get_lang_class("am")().tokenizer
@@ -125,6 +130,11 @@ def es_vocab():
     return get_lang_class("es")().vocab
 
 
+@pytest.fixture(scope="session")
+def et_tokenizer():
+    return get_lang_class("et")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def eu_tokenizer():
     return get_lang_class("eu")().tokenizer
@@ -185,6 +195,11 @@ def id_tokenizer():
     return get_lang_class("id")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def is_tokenizer():
+    return get_lang_class("is")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def it_tokenizer():
     return get_lang_class("it")().tokenizer
@@ -212,6 +227,11 @@ def lt_tokenizer():
     return get_lang_class("lt")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def lv_tokenizer():
+    return get_lang_class("lv")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def mk_tokenizer():
     return get_lang_class("mk")().tokenizer
@@ -279,11 +299,26 @@ def sa_tokenizer():
     return get_lang_class("sa")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def sk_tokenizer():
+    return get_lang_class("sk")().tokenizer
+
+
+@pytest.fixture(scope="session")
+def sl_tokenizer():
+    return get_lang_class("sl")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def sr_tokenizer():
     return get_lang_class("sr")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def sq_tokenizer():
+    return get_lang_class("sq")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def sv_tokenizer():
     return get_lang_class("sv")().tokenizer
@@ -344,6 +379,11 @@ def vi_tokenizer():
     return get_lang_class("vi")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def xx_tokenizer():
+    return get_lang_class("xx")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def yo_tokenizer():
     return get_lang_class("yo")().tokenizer
diff --git a/spacy/tests/lang/af/__init__.py b/spacy/tests/lang/af/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/af/test_text.py b/spacy/tests/lang/af/test_text.py
new file mode 100644
index 000000000..99c2a9f4c
--- /dev/null
+++ b/spacy/tests/lang/af/test_text.py
@@ -0,0 +1,22 @@
+import pytest
+
+
+def test_long_text(af_tokenizer):
+    # Excerpt: Universal Declaration of Human Rights; “'n” changed to “die” in first sentence
+    text = """
+Hierdie Universele Verklaring van Menseregte as die algemene standaard vir die verwesenliking deur alle mense en nasies, 
+om te verseker dat elke individu en elke deel van die gemeenskap hierdie Verklaring in ag sal neem en deur opvoeding, 
+respek vir hierdie regte en vryhede te bevorder, op nasionale en internasionale vlak, daarna sal strewe om die universele 
+en effektiewe erkenning en agting van hierdie regte te verseker, nie net vir die mense van die Lidstate nie, maar ook vir 
+die mense in die gebiede onder hul jurisdiksie.
+
+"""
+    tokens = af_tokenizer(text)
+    assert len(tokens) == 100
+
+
+@pytest.mark.xfail
+def test_indefinite_article(af_tokenizer):
+    text = "as 'n algemene standaard"
+    tokens = af_tokenizer(text)
+    assert len(tokens) == 4
diff --git a/spacy/tests/lang/af/test_tokenizer.py b/spacy/tests/lang/af/test_tokenizer.py
new file mode 100644
index 000000000..db52db5e3
--- /dev/null
+++ b/spacy/tests/lang/af/test_tokenizer.py
@@ -0,0 +1,29 @@
+import pytest
+
+AF_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Elkeen het die reg tot lewe, vryheid en sekuriteit van persoon.",
+        [
+            "Elkeen",
+            "het",
+            "die",
+            "reg",
+            "tot",
+            "lewe",
+            ",",
+            "vryheid",
+            "en",
+            "sekuriteit",
+            "van",
+            "persoon",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", AF_BASIC_TOKENIZATION_TESTS)
+def test_af_tokenizer_basic(af_tokenizer, text, expected_tokens):
+    tokens = af_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/et/__init__.py b/spacy/tests/lang/et/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/et/test_text.py b/spacy/tests/lang/et/test_text.py
new file mode 100644
index 000000000..9515a7cc1
--- /dev/null
+++ b/spacy/tests/lang/et/test_text.py
@@ -0,0 +1,26 @@
+import pytest
+
+
+def test_long_text(et_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+arvestades, et nimetatud deklaratsiooni eesmärk on tagada selles
+kuulutatud õiguste üldine ja tõhus tunnustamine ning järgimine;
+arvestades, et Euroopa Nõukogu eesmärk on saavutada tema
+liikmete suurem ühtsus ning et üheks selle eesmärgi saavutamise
+vahendiks on inimõiguste ja põhivabaduste järgimine ning
+elluviimine;
+taaskinnitades oma sügavat usku neisse põhivabadustesse, mis
+on õigluse ja rahu aluseks maailmas ning mida kõige paremini
+tagab ühelt poolt tõhus poliitiline demokraatia ning teiselt poolt
+inimõiguste, millest nad sõltuvad, üldine mõistmine ja järgimine;
+"""
+    tokens = et_tokenizer(text)
+    assert len(tokens) == 94
+
+
+@pytest.mark.xfail
+def test_ordinal_number(et_tokenizer):
+    text = "10. detsembril 1948"
+    tokens = et_tokenizer(text)
+    assert len(tokens) == 3
diff --git a/spacy/tests/lang/et/test_tokenizer.py b/spacy/tests/lang/et/test_tokenizer.py
new file mode 100644
index 000000000..f0f8079ca
--- /dev/null
+++ b/spacy/tests/lang/et/test_tokenizer.py
@@ -0,0 +1,29 @@
+import pytest
+
+ET_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Kedagi ei või piinata ega ebainimlikult või alandavalt kohelda "
+        "ega karistada.",
+        [
+            "Kedagi",
+            "ei",
+            "või",
+            "piinata",
+            "ega",
+            "ebainimlikult",
+            "või",
+            "alandavalt",
+            "kohelda",
+            "ega",
+            "karistada",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", ET_BASIC_TOKENIZATION_TESTS)
+def test_et_tokenizer_basic(et_tokenizer, text, expected_tokens):
+    tokens = et_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/hr/__init__.py b/spacy/tests/lang/hr/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/hr/test_text.py b/spacy/tests/lang/hr/test_text.py
new file mode 100644
index 000000000..82e65afe7
--- /dev/null
+++ b/spacy/tests/lang/hr/test_text.py
@@ -0,0 +1,26 @@
+import pytest
+
+
+def test_long_text(hr_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+uzimajući u obzir da ta deklaracija nastoji osigurati opće i djelotvorno
+priznanje i poštovanje u njoj proglašenih prava;
+uzimajući u obzir da je cilj Vijeća Europe postizanje većeg jedinstva
+njegovih članica, i da je jedan od načina postizanja toga cilja
+očuvanje i daljnje ostvarivanje ljudskih prava i temeljnih sloboda;
+potvrđujući svoju duboku privrženost tim temeljnim slobodama
+koje su osnova pravde i mira u svijetu i koje su najbolje zaštićene
+istinskom političkom demokracijom s jedne strane te zajedničkim
+razumijevanjem i poštovanjem ljudskih prava o kojima te slobode
+ovise s druge strane;
+"""
+    tokens = hr_tokenizer(text)
+    assert len(tokens) == 105
+
+
+@pytest.mark.xfail
+def test_ordinal_number(hr_tokenizer):
+    text = "10. prosinca 1948"
+    tokens = hr_tokenizer(text)
+    assert len(tokens) == 3
diff --git a/spacy/tests/lang/hr/test_tokenizer.py b/spacy/tests/lang/hr/test_tokenizer.py
new file mode 100644
index 000000000..dace33b2d
--- /dev/null
+++ b/spacy/tests/lang/hr/test_tokenizer.py
@@ -0,0 +1,31 @@
+import pytest
+
+HR_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Nitko se ne smije podvrgnuti mučenju ni nečovječnom ili "
+        "ponižavajućem postupanju ili kazni.",
+        [
+            "Nitko",
+            "se",
+            "ne",
+            "smije",
+            "podvrgnuti",
+            "mučenju",
+            "ni",
+            "nečovječnom",
+            "ili",
+            "ponižavajućem",
+            "postupanju",
+            "ili",
+            "kazni",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", HR_BASIC_TOKENIZATION_TESTS)
+def test_hr_tokenizer_basic(hr_tokenizer, text, expected_tokens):
+    tokens = hr_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/is/__init__.py b/spacy/tests/lang/is/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/is/test_text.py b/spacy/tests/lang/is/test_text.py
new file mode 100644
index 000000000..6e3654a6e
--- /dev/null
+++ b/spacy/tests/lang/is/test_text.py
@@ -0,0 +1,26 @@
+import pytest
+
+
+def test_long_text(is_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+hafa í huga, að yfirlýsing þessi hefur það markmið að tryggja
+almenna og raunhæfa viðurkenningu og vernd þeirra réttinda,
+sem þar er lýst;
+hafa í huga, að markmið Evrópuráðs er að koma á nánari einingu
+aðildarríkjanna og að ein af leiðunum að því marki er sú, að
+mannréttindi og mannfrelsi séu í heiðri höfð og efld;
+lýsa á ný eindreginni trú sinni á það mannfrelsi, sem er undirstaða
+réttlætis og friðar í heiminum og best er tryggt, annars vegar með
+virku, lýðræðislegu stjórnarfari og, hins vegar, almennum skilningi
+og varðveislu þeirra mannréttinda, sem eru grundvöllur frelsisins;
+"""
+    tokens = is_tokenizer(text)
+    assert len(tokens) == 120
+
+
+@pytest.mark.xfail
+def test_ordinal_number(is_tokenizer):
+    text = "10. desember 1948"
+    tokens = is_tokenizer(text)
+    assert len(tokens) == 3
diff --git a/spacy/tests/lang/is/test_tokenizer.py b/spacy/tests/lang/is/test_tokenizer.py
new file mode 100644
index 000000000..0c05a6050
--- /dev/null
+++ b/spacy/tests/lang/is/test_tokenizer.py
@@ -0,0 +1,30 @@
+import pytest
+
+IS_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Enginn maður skal sæta pyndingum eða ómannlegri eða "
+        "vanvirðandi meðferð eða refsingu. ",
+        [
+            "Enginn",
+            "maður",
+            "skal",
+            "sæta",
+            "pyndingum",
+            "eða",
+            "ómannlegri",
+            "eða",
+            "vanvirðandi",
+            "meðferð",
+            "eða",
+            "refsingu",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", IS_BASIC_TOKENIZATION_TESTS)
+def test_is_tokenizer_basic(is_tokenizer, text, expected_tokens):
+    tokens = is_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/lv/__init__.py b/spacy/tests/lang/lv/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/lv/test_text.py b/spacy/tests/lang/lv/test_text.py
new file mode 100644
index 000000000..5ca5fd0a7
--- /dev/null
+++ b/spacy/tests/lang/lv/test_text.py
@@ -0,0 +1,27 @@
+import pytest
+
+
+def test_long_text(lv_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+Ievērodamas, ka šī deklarācija paredz nodrošināt vispārēju un
+efektīvu tajā pasludināto tiesību atzīšanu un ievērošanu;
+Ievērodamas, ka Eiropas Padomes mērķis ir panākt lielāku vienotību
+tās dalībvalstu starpā un ka viens no līdzekļiem, kā šo mērķi
+sasniegt, ir cilvēka tiesību un pamatbrīvību ievērošana un turpmāka
+īstenošana;
+No jauna apliecinādamas patiesu pārliecību, ka šīs pamatbrīvības
+ir taisnīguma un miera pamats visā pasaulē un ka tās vislabāk var
+nodrošināt patiess demokrātisks politisks režīms no vienas puses un
+vispārējo cilvēktiesību, uz kurām tās pamatojas, kopīga izpratne un
+ievērošana no otras puses;
+"""
+    tokens = lv_tokenizer(text)
+    assert len(tokens) == 109
+
+
+@pytest.mark.xfail
+def test_ordinal_number(lv_tokenizer):
+    text = "10. decembrī"
+    tokens = lv_tokenizer(text)
+    assert len(tokens) == 2
diff --git a/spacy/tests/lang/lv/test_tokenizer.py b/spacy/tests/lang/lv/test_tokenizer.py
new file mode 100644
index 000000000..3ce7ad5fa
--- /dev/null
+++ b/spacy/tests/lang/lv/test_tokenizer.py
@@ -0,0 +1,30 @@
+import pytest
+
+LV_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Nevienu nedrīkst spīdzināt vai cietsirdīgi vai pazemojoši ar viņu "
+        "apieties vai sodīt.",
+        [
+            "Nevienu",
+            "nedrīkst",
+            "spīdzināt",
+            "vai",
+            "cietsirdīgi",
+            "vai",
+            "pazemojoši",
+            "ar",
+            "viņu",
+            "apieties",
+            "vai",
+            "sodīt",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", LV_BASIC_TOKENIZATION_TESTS)
+def test_lv_tokenizer_basic(lv_tokenizer, text, expected_tokens):
+    tokens = lv_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/sk/__init__.py b/spacy/tests/lang/sk/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/sk/test_text.py b/spacy/tests/lang/sk/test_text.py
new file mode 100644
index 000000000..62ea2a783
--- /dev/null
+++ b/spacy/tests/lang/sk/test_text.py
@@ -0,0 +1,48 @@
+import pytest
+
+
+def test_long_text(sk_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+majúc na zreteli, že cieľom tejto deklarácie je zabezpečiť všeobecné
+a účinné uznávanie a dodržiavanie práv v nej vyhlásených;
+majúc na zreteli, že cieľom Rady Európy je dosiahnutie väčšej
+jednoty medzi jej členmi, a že jedným zo spôsobov, ktorým sa
+má tento cieľ napĺňať, je ochrana a ďalší rozvoj ľudských práv
+a základných slobôd;
+znovu potvrdzujúc svoju hlbokú vieru v tie základné slobody, ktoré
+sú základom spravodlivosti a mieru vo svete, a ktoré sú najlepšie
+zachovávané na jednej strane účinnou politickou demokraciou
+a na strane druhej spoločným poňatím a dodržiavaním ľudských
+práv, od ktorých závisia;
+    """
+    tokens = sk_tokenizer(text)
+    assert len(tokens) == 118
+
+
+@pytest.mark.parametrize(
+    "text,match",
+    [
+        ("10", True),
+        ("1", True),
+        ("10,000", True),
+        ("10,00", True),
+        ("štyri", True),
+        ("devätnásť", True),
+        ("milión", True),
+        ("pes", False),
+        (",", False),
+        ("1/2", True),
+    ],
+)
+def test_lex_attrs_like_number(sk_tokenizer, text, match):
+    tokens = sk_tokenizer(text)
+    assert len(tokens) == 1
+    assert tokens[0].like_num == match
+
+
+@pytest.mark.xfail
+def test_ordinal_number(sk_tokenizer):
+    text = "10. decembra 1948"
+    tokens = sk_tokenizer(text)
+    assert len(tokens) == 3
diff --git a/spacy/tests/lang/sk/test_tokenizer.py b/spacy/tests/lang/sk/test_tokenizer.py
new file mode 100644
index 000000000..247847284
--- /dev/null
+++ b/spacy/tests/lang/sk/test_tokenizer.py
@@ -0,0 +1,15 @@
+import pytest
+
+SK_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Kedy sa narodil Andrej Kiska?",
+        ["Kedy", "sa", "narodil", "Andrej", "Kiska", "?"],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", SK_BASIC_TOKENIZATION_TESTS)
+def test_sk_tokenizer_basic(sk_tokenizer, text, expected_tokens):
+    tokens = sk_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/sl/__init__.py b/spacy/tests/lang/sl/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/sl/test_text.py b/spacy/tests/lang/sl/test_text.py
new file mode 100644
index 000000000..ddc5b6b5d
--- /dev/null
+++ b/spacy/tests/lang/sl/test_text.py
@@ -0,0 +1,27 @@
+import pytest
+
+
+def test_long_text(sl_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+upoštevajoč, da si ta deklaracija prizadeva zagotoviti splošno in
+učinkovito priznavanje in spoštovanje v njej razglašenih pravic,
+upoštevajoč, da je cilj Sveta Evrope doseči večjo enotnost med
+njegovimi članicami, in da je eden izmed načinov za zagotavljanje
+tega cilja varstvo in nadaljnji razvoj človekovih pravic in temeljnih
+svoboščin,
+ponovno potrjujoč svojo globoko vero v temeljne svoboščine, na
+katerih temeljita pravičnost in mir v svetu, in ki jih je mogoče najbolje
+zavarovati na eni strani z dejansko politično demokracijo in na drugi
+strani s skupnim razumevanjem in spoštovanjem človekovih pravic,
+od katerih so te svoboščine odvisne,    
+"""
+    tokens = sl_tokenizer(text)
+    assert len(tokens) == 116
+
+
+@pytest.mark.xfail
+def test_ordinal_number(sl_tokenizer):
+    text = "10. decembra 1948"
+    tokens = sl_tokenizer(text)
+    assert len(tokens) == 3
diff --git a/spacy/tests/lang/sl/test_tokenizer.py b/spacy/tests/lang/sl/test_tokenizer.py
new file mode 100644
index 000000000..f2b15b0ff
--- /dev/null
+++ b/spacy/tests/lang/sl/test_tokenizer.py
@@ -0,0 +1,32 @@
+import pytest
+
+SL_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Vsakdo ima pravico do spoštovanja njegovega zasebnega in "
+        "družinskega življenja, doma in dopisovanja.",
+        [
+            "Vsakdo",
+            "ima",
+            "pravico",
+            "do",
+            "spoštovanja",
+            "njegovega",
+            "zasebnega",
+            "in",
+            "družinskega",
+            "življenja",
+            ",",
+            "doma",
+            "in",
+            "dopisovanja",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", SL_BASIC_TOKENIZATION_TESTS)
+def test_sl_tokenizer_basic(sl_tokenizer, text, expected_tokens):
+    tokens = sl_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/sq/__init__.py b/spacy/tests/lang/sq/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/sq/test_text.py b/spacy/tests/lang/sq/test_text.py
new file mode 100644
index 000000000..44eedaa54
--- /dev/null
+++ b/spacy/tests/lang/sq/test_text.py
@@ -0,0 +1,25 @@
+import pytest
+
+
+def test_long_text(sq_tokenizer):
+    # Excerpt: European Convention on Human Rights
+    text = """
+Qeveritë nënshkruese, anëtare të Këshillit të Evropës,
+Duke pasur parasysh Deklaratën Universale të të Drejtave të
+Njeriut, të shpallur nga Asambleja e Përgjithshme e Kombeve të
+Bashkuara më 10 dhjetor 1948;
+Duke pasur parasysh, se kjo Deklaratë ka për qëllim të sigurojë
+njohjen dhe zbatimin universal dhe efektiv të të drejtave të
+shpallura në të;
+Duke pasur parasysh se qëllimi i Këshillit të Evropës është që të
+realizojë një bashkim më të ngushtë midis anëtarëve të tij dhe
+se një nga mjetet për të arritur këtë qëllim është mbrojtja dhe
+zhvillimi i të drejtave të njeriut dhe i lirive themelore;
+Duke ripohuar besimin e tyre të thellë në këto liri themelore që
+përbëjnë themelet e drejtësisë dhe të paqes në botë, ruajtja e të
+cilave mbështetet kryesisht mbi një regjim politik demokratik nga
+njëra anë, dhe nga ana tjetër mbi një kuptim dhe respektim të
+përbashkët të të drejtave të njeriut nga të cilat varen;
+"""
+    tokens = sq_tokenizer(text)
+    assert len(tokens) == 182
diff --git a/spacy/tests/lang/sq/test_tokenizer.py b/spacy/tests/lang/sq/test_tokenizer.py
new file mode 100644
index 000000000..8fd25f588
--- /dev/null
+++ b/spacy/tests/lang/sq/test_tokenizer.py
@@ -0,0 +1,31 @@
+import pytest
+
+SQ_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Askush nuk mund t’i nënshtrohet torturës ose dënimeve ose "
+        "trajtimeve çnjerëzore ose poshtëruese.",
+        [
+            "Askush",
+            "nuk",
+            "mund",
+            "t’i",
+            "nënshtrohet",
+            "torturës",
+            "ose",
+            "dënimeve",
+            "ose",
+            "trajtimeve",
+            "çnjerëzore",
+            "ose",
+            "poshtëruese",
+            ".",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", SQ_BASIC_TOKENIZATION_TESTS)
+def test_sq_tokenizer_basic(sq_tokenizer, text, expected_tokens):
+    tokens = sq_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
diff --git a/spacy/tests/lang/xx/__init__.py b/spacy/tests/lang/xx/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/xx/test_text.py b/spacy/tests/lang/xx/test_text.py
new file mode 100644
index 000000000..477f0ebe2
--- /dev/null
+++ b/spacy/tests/lang/xx/test_text.py
@@ -0,0 +1,24 @@
+import pytest
+
+
+def test_long_text(xx_tokenizer):
+    # Excerpt: Text in Skolt Sami taken from https://www.samediggi.fi
+    text = """
+Säʹmmla lie Euroopp unioon oʹdinakai alggmeer. Säʹmmlai alggmeerstatus lij raʹvvjum Lääʹddjânnam vuâđđlääʹjjest.  
+Alggmeer kriteeʹr vuâđđâʹvve meeraikõskksaž tuâjjorganisaatio, ILO, suåppmõʹšše nââmar 169. 
+Suåppmõõžž mieʹldd jiõččvälddsaž jânnmin jälsteei meeraid ââʹnet alggmeeran, 
+ko sij puõlvvâʹvve naroodâst, kååʹtt jânnam välddmõõžž leʹbe aazztummuž leʹbe ânnʼjõž riikkraaʹji šõddâm ääiʹj jälste 
+jânnmest leʹbe tõn mäddtiõđlaž vuuʹdest, koozz jânnam kooll. Alggmeer ij leäkku mieʹrreei sââʹjest jiiʹjjes jälstemvuuʹdest. 
+Alggmeer âlgg jiõčč ââʹnned jiiʹjjes alggmeeran leʹbe leeʹd tõn miõlâst, što sij lie alggmeer. 
+Alggmeer lij õlggâm seeilted vuõiggâdvuõđlaž sââʹjest huõlǩâni obbnes leʹbe vueʹzzi jiiʹjjes sosiaalʼlaž, täälʼlaž, 
+kulttuurlaž da poliittlaž instituutioid.
+
+Säʹmmlai statuuzz ǩeeʹrjteš Lääʹddjânnam vuâđđläkka eeʹjj 1995. Säʹmmlain alggmeeran lij vuõiggâdvuõtt tuõʹllʼjed da 
+ooudâsviikkâd ǩiõlâz da kulttuurâz di tõõzz kuulli ääʹrbvuâlaž jieʹllemvueʹjjeez. Sääʹmǩiõl ââʹnnmest veʹrǧǧniiʹǩǩi 
+åʹrnn lij šiõttuum jiiʹjjes lääʹǩǩ. Säʹmmlain lij leämmaž eeʹjjest 1996 vueʹljeeʹl dommvuuʹdsteez ǩiõlâz da kulttuurâz kuõskki 
+vuâđđlääʹjj meâldlaž jiõččvaaldâšm. Säʹmmlai jiõččvaldšma kuulli tuâjaid håidd säʹmmlai vaalin vaʹlljääm parlameʹntt, 
+Sääʹmteʹǧǧ.
+"""
+
+    tokens = xx_tokenizer(text)
+    assert len(tokens) == 179
diff --git a/spacy/tests/lang/xx/test_tokenizer.py b/spacy/tests/lang/xx/test_tokenizer.py
new file mode 100644
index 000000000..15c760a6b
--- /dev/null
+++ b/spacy/tests/lang/xx/test_tokenizer.py
@@ -0,0 +1,25 @@
+import pytest
+
+XX_BASIC_TOKENIZATION_TESTS = [
+    (
+        "Lääʹddjânnmest lie nuʹtt 10 000 säʹmmliʹžžed. Seeʹst pâʹjjel",
+        [
+            "Lääʹddjânnmest",
+            "lie",
+            "nuʹtt",
+            "10",
+            "000",
+            "säʹmmliʹžžed",
+            ".",
+            "Seeʹst",
+            "pâʹjjel",
+        ],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", XX_BASIC_TOKENIZATION_TESTS)
+def test_xx_tokenizer_basic(xx_tokenizer, text, expected_tokens):
+    tokens = xx_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list

From ac05de2c6c708e33ebad6c901e674e1e8bdc0688 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Mon, 29 Nov 2021 07:31:02 +0000
Subject: [PATCH 26/37] Fix Language-specific factory handling in package
 command (#9674)

* Use internal names for factories

If a component factory is registered like `@French.factory(...)` instead
of `@Language.factory(...)`, the name in the factories registry will be
prefixed with the language code. However in the nlp.config object the
factory will be listed without the language code. The `add_pipe` code
has fallback logic to handle this, but packaging code and the registry
itself don't.

This change makes it so that the factory name in nlp.config is the
language-specific form. It's not clear if this will break anything else,
but it does seem to fix the inconsistency and resolve the specific user
issue that brought this to our attention.

* Change approach to use fallback in package lookup

This adds fallback logic to the package lookup, so it doesn't have to
touch the way the config is built. It seems to fix the tests too.

* Remove unecessary line

* Add test

Thsi also adds an assert that seems to have been forgotten.
---
 spacy/cli/package.py    | 12 +++++++++++-
 spacy/tests/test_cli.py | 11 ++++++++++-
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/spacy/cli/package.py b/spacy/cli/package.py
index 76e14daf5..f9d2a9af2 100644
--- a/spacy/cli/package.py
+++ b/spacy/cli/package.py
@@ -4,6 +4,7 @@ from pathlib import Path
 from wasabi import Printer, MarkdownRenderer, get_raw_input
 from thinc.api import Config
 from collections import defaultdict
+from catalogue import RegistryError
 import srsly
 import sys
 
@@ -212,9 +213,18 @@ def get_third_party_dependencies(
         if "factory" in component:
             funcs["factories"].add(component["factory"])
     modules = set()
+    lang = config["nlp"]["lang"]
     for reg_name, func_names in funcs.items():
         for func_name in func_names:
-            func_info = util.registry.find(reg_name, func_name)
+            # Try the lang-specific version and fall back
+            try:
+                func_info = util.registry.find(reg_name, lang + "." + func_name)
+            except RegistryError:
+                try:
+                    func_info = util.registry.find(reg_name, func_name)
+                except RegistryError as regerr:
+                    # lang-specific version being absent is not actually an issue
+                    raise regerr from None
             module_name = func_info.get("module")  # type: ignore[attr-defined]
             if module_name:  # the code is part of a module, not a --code file
                 modules.add(func_info["module"].split(".")[0])  # type: ignore[index]
diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py
index 3243d426b..c6b00b140 100644
--- a/spacy/tests/test_cli.py
+++ b/spacy/tests/test_cli.py
@@ -565,7 +565,16 @@ def test_get_third_party_dependencies():
             }
         },
     )
-    get_third_party_dependencies(nlp.config) == []
+    assert get_third_party_dependencies(nlp.config) == []
+
+    # Test with lang-specific factory
+    @Dutch.factory("third_party_test")
+    def test_factory(nlp, name):
+        return lambda x: x
+
+    nlp.add_pipe("third_party_test")
+    # Before #9674 this would throw an exception
+    get_third_party_dependencies(nlp.config)
 
 
 @pytest.mark.parametrize(

From 6763cbfdc03ed801576c99a5d35623cf55925e22 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Mon, 29 Nov 2021 14:14:21 +0100
Subject: [PATCH 27/37] Update Catalan acknowledgements for v3.2 (#9763)

---
 website/docs/usage/v3-2.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/website/docs/usage/v3-2.md b/website/docs/usage/v3-2.md
index 766d1c0a9..d1d45c7ba 100644
--- a/website/docs/usage/v3-2.md
+++ b/website/docs/usage/v3-2.md
@@ -159,7 +159,7 @@ their contributions!
 
 - All Universal Dependencies training data has been updated to v2.8.
 - The Catalan data, tokenizer and lemmatizer have been updated, thanks to Carlos
-  Rodriguez and the Barcelona Supercomputing Center!
+  Rodriguez, Carme Armentano and the Barcelona Supercomputing Center!
 - The transformer pipelines are trained using spacy-transformers v1.1, with
   improved IO and more options for
   [model config and output](/api/architectures#TransformerModel).

From 1be8a4dab305466cc731f1bd9124ae13df274d54 Mon Sep 17 00:00:00 2001
From: Narayan Acharya <narayan.acharya6@gmail.com>
Date: Mon, 29 Nov 2021 11:13:26 -0500
Subject: [PATCH 28/37] Displacy serve entity linking support without
 `manual=True` support. (#9748)

* Add support for kb_id to be displayed via displacy.serve. The current support is only limited to the manual option in displacy.render

* Commit to check pre-commit hooks are run.

* Update spacy/displacy/__init__.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Changes as per suggestions on the PR.

* Update website/docs/api/top-level.md

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update website/docs/api/top-level.md

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* tag option as new from 3.2.1 onwards

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
---
 spacy/displacy/__init__.py    | 12 ++++++++++--
 spacy/tests/test_displacy.py  | 36 +++++++++++++++++++++++++++++++++--
 website/docs/api/top-level.md | 26 ++++++++++++++++---------
 3 files changed, 61 insertions(+), 13 deletions(-)

diff --git a/spacy/displacy/__init__.py b/spacy/displacy/__init__.py
index d9418f675..25d530c83 100644
--- a/spacy/displacy/__init__.py
+++ b/spacy/displacy/__init__.py
@@ -181,11 +181,19 @@ def parse_deps(orig_doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
 def parse_ents(doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
     """Generate named entities in [{start: i, end: i, label: 'label'}] format.
 
-    doc (Doc): Document do parse.
+    doc (Doc): Document to parse.
+    options (Dict[str, Any]): NER-specific visualisation options.
     RETURNS (dict): Generated entities keyed by text (original text) and ents.
     """
+    kb_url_template = options.get("kb_url_template", None)
     ents = [
-        {"start": ent.start_char, "end": ent.end_char, "label": ent.label_}
+        {
+            "start": ent.start_char,
+            "end": ent.end_char,
+            "label": ent.label_,
+            "kb_id": ent.kb_id_ if ent.kb_id_ else "",
+            "kb_url": kb_url_template.format(ent.kb_id_) if kb_url_template else "#",
+        }
         for ent in doc.ents
     ]
     if not ents:
diff --git a/spacy/tests/test_displacy.py b/spacy/tests/test_displacy.py
index 040dd657f..790925888 100644
--- a/spacy/tests/test_displacy.py
+++ b/spacy/tests/test_displacy.py
@@ -1,8 +1,9 @@
 import pytest
+
 from spacy import displacy
 from spacy.displacy.render import DependencyRenderer, EntityRenderer
-from spacy.tokens import Span, Doc
 from spacy.lang.fa import Persian
+from spacy.tokens import Span, Doc
 
 
 def test_displacy_parse_ents(en_vocab):
@@ -12,7 +13,38 @@ def test_displacy_parse_ents(en_vocab):
     ents = displacy.parse_ents(doc)
     assert isinstance(ents, dict)
     assert ents["text"] == "But Google is starting from behind "
-    assert ents["ents"] == [{"start": 4, "end": 10, "label": "ORG"}]
+    assert ents["ents"] == [
+        {"start": 4, "end": 10, "label": "ORG", "kb_id": "", "kb_url": "#"}
+    ]
+
+    doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"], kb_id="Q95")]
+    ents = displacy.parse_ents(doc)
+    assert isinstance(ents, dict)
+    assert ents["text"] == "But Google is starting from behind "
+    assert ents["ents"] == [
+        {"start": 4, "end": 10, "label": "ORG", "kb_id": "Q95", "kb_url": "#"}
+    ]
+
+
+def test_displacy_parse_ents_with_kb_id_options(en_vocab):
+    """Test that named entities with kb_id on a Doc are converted into displaCy's format."""
+    doc = Doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
+    doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"], kb_id="Q95")]
+
+    ents = displacy.parse_ents(
+        doc, {"kb_url_template": "https://www.wikidata.org/wiki/{}"}
+    )
+    assert isinstance(ents, dict)
+    assert ents["text"] == "But Google is starting from behind "
+    assert ents["ents"] == [
+        {
+            "start": 4,
+            "end": 10,
+            "label": "ORG",
+            "kb_id": "Q95",
+            "kb_url": "https://www.wikidata.org/wiki/Q95",
+        }
+    ]
 
 
 def test_displacy_parse_deps(en_vocab):
diff --git a/website/docs/api/top-level.md b/website/docs/api/top-level.md
index 4361db4c0..be19f9c3a 100644
--- a/website/docs/api/top-level.md
+++ b/website/docs/api/top-level.md
@@ -313,11 +313,12 @@ If a setting is not present in the options, the default value will be used.
 > displacy.serve(doc, style="ent", options=options)
 > ```
 
-| Name                                    | Description                                                                                                                                                                                                                                 |
-| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `ents`                                  | Entity types to highlight or `None` for all types (default). ~~Optional[List[str]]~~                                                                                                                                                        |
-| `colors`                                | Color overrides. Entity types should be mapped to color names or values. ~~Dict[str, str]~~                                                                                                                                                 |
-| `template` <Tag variant="new">2.2</Tag> | Optional template to overwrite the HTML used to render entity spans. Should be a format string and can use `{bg}`, `{text}` and `{label}`. See [`templates.py`](%%GITHUB_SPACY/spacy/displacy/templates.py) for examples. ~~Optional[str]~~ |
+| Name                                             | Description                                                                                                                                                                                                                                 |
+| ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `ents`                                           | Entity types to highlight or `None` for all types (default). ~~Optional[List[str]]~~                                                                                                                                                        |
+| `colors`                                         | Color overrides. Entity types should be mapped to color names or values. ~~Dict[str, str]~~                                                                                                                                                 |
+| `template` <Tag variant="new">2.2</Tag>          | Optional template to overwrite the HTML used to render entity spans. Should be a format string and can use `{bg}`, `{text}` and `{label}`. See [`templates.py`](%%GITHUB_SPACY/spacy/displacy/templates.py) for examples. ~~Optional[str]~~ |
+| `kb_url_template` <Tag variant="new">3.2.1</Tag> | Optional template to construct the KB url for the entity to link to. Expects a python f-string format with single field to fill in. ~~Optional[str]~~                                                                                       |
 
 By default, displaCy comes with colors for all entity types used by
 [spaCy's trained pipelines](/models). If you're using custom entity types, you
@@ -326,6 +327,14 @@ or pipeline package can also expose a
 [`spacy_displacy_colors` entry point](/usage/saving-loading#entry-points-displacy)
 to add custom labels and their colors automatically.
 
+By default, displaCy links to `#` for entities without a `kb_id` set on their
+span. If you wish to link an entity to their URL then consider using the
+`kb_url_template` option from above. For example if the `kb_id` on a span is
+`Q95` and this is a Wikidata identifier then this option can be set to
+`https://www.wikidata.org/wiki/{}`. Clicking on your entity in the rendered HTML
+should redirect you to their Wikidata page, in this case
+`https://www.wikidata.org/wiki/Q95`.
+
 ## registry {#registry source="spacy/util.py" new="3"}
 
 spaCy's function registry extends
@@ -412,10 +421,10 @@ finished. To log each training step, a
 and the accuracy scores on the development set.
 
 The built-in, default logger is the ConsoleLogger, which prints results to the
-console in tabular format. The 
+console in tabular format. The
 [spacy-loggers](https://github.com/explosion/spacy-loggers) package, included as
-a dependency of spaCy, enables other loggers: currently it provides one that sends
-results to a [Weights & Biases](https://www.wandb.com/) dashboard.
+a dependency of spaCy, enables other loggers: currently it provides one that
+sends results to a [Weights & Biases](https://www.wandb.com/) dashboard.
 
 Instead of using one of the built-in loggers, you can
 [implement your own](/usage/training#custom-logging).
@@ -466,7 +475,6 @@ start decreasing across epochs.
 
  </Accordion>
 
-
 ## Readers {#readers}
 
 ### File readers {#file-readers source="github.com/explosion/srsly" new="3"}

From c19f0c1604f7141a050292bf79d6eae3997b18c5 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 30 Nov 2021 10:08:51 +0100
Subject: [PATCH 29/37] Switch to latest CI images (#9773)

---
 azure-pipelines.yml | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index 4291b6e0a..71a793911 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -23,7 +23,7 @@ jobs:
   # defined in .flake8 and overwrites the selected codes.
   - job: "Validate"
     pool:
-      vmImage: "ubuntu-18.04"
+      vmImage: "ubuntu-latest"
     steps:
       - task: UsePythonVersion@0
         inputs:
@@ -39,49 +39,49 @@ jobs:
       matrix:
         # We're only running one platform per Python version to speed up builds
         Python36Linux:
-          imageName: "ubuntu-18.04"
+          imageName: "ubuntu-latest"
           python.version: "3.6"
         #        Python36Windows:
-        #          imageName: "windows-2019"
+        #          imageName: "windows-latest"
         #          python.version: "3.6"
         #        Python36Mac:
-        #          imageName: "macos-10.14"
+        #          imageName: "macos-latest"
         #          python.version: "3.6"
         #        Python37Linux:
-        #          imageName: "ubuntu-18.04"
+        #          imageName: "ubuntu-latest"
         #          python.version: "3.7"
         Python37Windows:
-          imageName: "windows-2019"
+          imageName: "windows-latest"
           python.version: "3.7"
         #        Python37Mac:
-        #          imageName: "macos-10.14"
+        #          imageName: "macos-latest"
         #          python.version: "3.7"
         #        Python38Linux:
-        #          imageName: "ubuntu-18.04"
+        #          imageName: "ubuntu-latest"
         #          python.version: "3.8"
         #        Python38Windows:
-        #          imageName: "windows-2019"
+        #          imageName: "windows-latest"
         #          python.version: "3.8"
         Python38Mac:
-          imageName: "macos-10.14"
+          imageName: "macos-latest"
           python.version: "3.8"
         Python39Linux:
-          imageName: "ubuntu-18.04"
+          imageName: "ubuntu-latest"
           python.version: "3.9"
         #        Python39Windows:
-        #          imageName: "windows-2019"
+        #          imageName: "windows-latest"
         #          python.version: "3.9"
         #        Python39Mac:
-        #          imageName: "macos-10.14"
+        #          imageName: "macos-latest"
         #          python.version: "3.9"
         Python310Linux:
-          imageName: "ubuntu-20.04"
+          imageName: "ubuntu-latest"
           python.version: "3.10"
         Python310Windows:
-          imageName: "windows-2019"
+          imageName: "windows-latest"
           python.version: "3.10"
         Python310Mac:
-          imageName: "macos-10.15"
+          imageName: "macos-latest"
           python.version: "3.10"
       maxParallel: 4
     pool:

From 72f7f4e68a5076a87dd9402812bfb72e479237ed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dani=C3=ABl=20de=20Kok?= <me@danieldk.eu>
Date: Tue, 30 Nov 2021 11:58:59 +0100
Subject: [PATCH 30/37] morphologizer: avoid recreating label tuple for each
 token (#9764)

* morphologizer: avoid recreating label tuple for each token

The `labels` property converts the dictionary key set to a tuple. This
property was used for every annotated token, recreating the tuple over
and over again.

Construct the tuple once in the set_annotations function and reuse it.

On a Finnish pipeline that I was experimenting with, this results in a
speedup of ~15% (~13000 -> ~15000 WPS).

* tagger: avoid recreating label tuple for each token
---
 spacy/pipeline/morphologizer.pyx | 3 ++-
 spacy/pipeline/tagger.pyx        | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/spacy/pipeline/morphologizer.pyx b/spacy/pipeline/morphologizer.pyx
index db425b69a..73d3799b1 100644
--- a/spacy/pipeline/morphologizer.pyx
+++ b/spacy/pipeline/morphologizer.pyx
@@ -231,12 +231,13 @@ class Morphologizer(Tagger):
         cdef Vocab vocab = self.vocab
         cdef bint overwrite = self.cfg["overwrite"]
         cdef bint extend = self.cfg["extend"]
+        labels = self.labels
         for i, doc in enumerate(docs):
             doc_tag_ids = batch_tag_ids[i]
             if hasattr(doc_tag_ids, "get"):
                 doc_tag_ids = doc_tag_ids.get()
             for j, tag_id in enumerate(doc_tag_ids):
-                morph = self.labels[tag_id]
+                morph = labels[tag_id]
                 # set morph
                 if doc.c[j].morph == 0 or overwrite or extend:
                     if overwrite and extend:
diff --git a/spacy/pipeline/tagger.pyx b/spacy/pipeline/tagger.pyx
index a9cbac37a..c0768dfec 100644
--- a/spacy/pipeline/tagger.pyx
+++ b/spacy/pipeline/tagger.pyx
@@ -166,13 +166,14 @@ class Tagger(TrainablePipe):
         cdef Doc doc
         cdef Vocab vocab = self.vocab
         cdef bint overwrite = self.cfg["overwrite"]
+        labels = self.labels
         for i, doc in enumerate(docs):
             doc_tag_ids = batch_tag_ids[i]
             if hasattr(doc_tag_ids, "get"):
                 doc_tag_ids = doc_tag_ids.get()
             for j, tag_id in enumerate(doc_tag_ids):
                 if doc.c[j].tag == 0 or overwrite:
-                    doc.c[j].tag = self.vocab.strings[self.labels[tag_id]]
+                    doc.c[j].tag = self.vocab.strings[labels[tag_id]]
 
     def update(self, examples, *, drop=0., sgd=None, losses=None):
         """Learn from a batch of documents and gold-standard information,

From 7d50804644eccb3dabd421ce413d1d2f748814a5 Mon Sep 17 00:00:00 2001
From: Lj Miranda <12949683+ljvmiranda921@users.noreply.github.com>
Date: Sun, 5 Dec 2021 03:34:48 +0800
Subject: [PATCH 31/37] Migrate regression tests into the main test suite
 (#9655)

* Migrate regressions 1-1000

* Move serialize test to correct file

* Remove tests that won't work in v3

* Migrate regressions 1000-1500

Removed regression test 1250 because v3 doesn't support the old LEX
scheme anymore.

* Add missing imports in serializer tests

* Migrate tests 1500-2000

* Migrate regressions from 2000-2500

* Migrate regressions from 2501-3000

* Migrate regressions from 3000-3501

* Migrate regressions from 3501-4000

* Migrate regressions from 4001-4500

* Migrate regressions from 4501-5000

* Migrate regressions from 5001-5501

* Migrate regressions from 5501 to 7000

* Migrate regressions from 7001 to 8000

* Migrate remaining regression tests

* Fixing missing imports

* Update docs with new system [ci skip]

* Update CONTRIBUTING.md

- Fix formatting
- Update wording

* Remove lemmatizer tests in el lang

* Move a few tests into the general tokenizer

* Separate Doc and DocBin tests
---
 CONTRIBUTING.md                               |  24 +-
 extra/DEVELOPER_DOCS/Code Conventions.md      |   2 +-
 spacy/tests/doc/test_array.py                 |  23 +
 spacy/tests/doc/test_doc_api.py               | 225 +++++++-
 spacy/tests/doc/test_retokenize_split.py      |  42 ++
 spacy/tests/doc/test_span.py                  | 102 ++++
 spacy/tests/lang/en/test_sbd.py               |   9 +
 spacy/tests/lang/en/test_tokenizer.py         | 169 ++++++
 spacy/tests/lang/es/test_text.py              |  11 +
 spacy/tests/lang/hi/test_text.py              |  11 +
 spacy/tests/lang/it/test_text.py              |  14 +
 spacy/tests/lang/ja/test_tokenizer.py         |  12 +
 spacy/tests/lang/sv/test_exceptions.py        |  21 +-
 spacy/tests/lang/test_attrs.py                |  13 +-
 spacy/tests/matcher/test_matcher_logic.py     | 479 ++++++++++++++++-
 spacy/tests/matcher/test_phrase_matcher.py    | 119 ++++-
 spacy/tests/parser/test_arc_eager_oracle.py   |  22 +
 spacy/tests/parser/test_ner.py                | 153 +++++-
 spacy/tests/parser/test_parse.py              |  98 +++-
 spacy/tests/pipeline/test_entity_linker.py    | 206 +++++++-
 spacy/tests/pipeline/test_entity_ruler.py     | 117 ++++-
 spacy/tests/pipeline/test_pipe_factories.py   |  33 ++
 spacy/tests/pipeline/test_pipe_methods.py     | 142 ++++-
 spacy/tests/pipeline/test_tagger.py           |  17 +
 spacy/tests/pipeline/test_textcat.py          | 237 ++++++++-
 spacy/tests/regression/__init__.py            |   0
 spacy/tests/regression/test_issue1-1000.py    | 486 -----------------
 spacy/tests/regression/test_issue1001-1500.py | 174 -------
 spacy/tests/regression/test_issue1501-2000.py | 375 -------------
 spacy/tests/regression/test_issue2001-2500.py | 152 ------
 spacy/tests/regression/test_issue2501-3000.py | 238 ---------
 spacy/tests/regression/test_issue3001-3500.py | 272 ----------
 spacy/tests/regression/test_issue3501-4000.py | 492 ------------------
 spacy/tests/regression/test_issue4001-4500.py | 447 ----------------
 spacy/tests/regression/test_issue4501-5000.py | 266 ----------
 spacy/tests/regression/test_issue5001-5500.py | 149 ------
 spacy/tests/regression/test_issue5501-6000.py |  95 ----
 spacy/tests/regression/test_issue6001-6500.py |  30 --
 spacy/tests/regression/test_issue6501-7000.py | 238 ---------
 spacy/tests/regression/test_issue7001-8000.py | 288 ----------
 spacy/tests/regression/test_issue7716.py      |  55 --
 spacy/tests/regression/test_issue8168.py      |  24 -
 spacy/tests/regression/test_issue8190.py      |  24 -
 spacy/tests/regression/test_issue8216.py      |  34 --
 .../tests/serialize/test_serialize_config.py  |  44 +-
 spacy/tests/serialize/test_serialize_doc.py   | 229 +++++---
 .../tests/serialize/test_serialize_docbin.py  | 106 ++++
 .../serialize/test_serialize_language.py      |  73 ++-
 .../serialize/test_serialize_pipeline.py      | 198 ++++++-
 .../serialize/test_serialize_tokenizer.py     |  88 +++-
 .../serialize/test_serialize_vocab_strings.py |  60 ++-
 spacy/tests/test_cli.py                       | 119 ++++-
 spacy/tests/test_displacy.py                  |  90 ++++
 spacy/tests/test_misc.py                      |  29 +-
 spacy/tests/tokenizer/test_tokenizer.py       | 282 +++++++++-
 spacy/tests/training/test_training.py         | 222 +++++++-
 spacy/tests/vocab_vectors/test_lexeme.py      |  20 +-
 spacy/tests/vocab_vectors/test_similarity.py  |  10 +
 spacy/tests/vocab_vectors/test_vectors.py     |  86 ++-
 spacy/tests/vocab_vectors/test_vocab_api.py   |  15 +-
 60 files changed, 3789 insertions(+), 4022 deletions(-)
 create mode 100644 spacy/tests/lang/en/test_tokenizer.py
 create mode 100644 spacy/tests/lang/hi/test_text.py
 create mode 100644 spacy/tests/lang/it/test_text.py
 delete mode 100644 spacy/tests/regression/__init__.py
 delete mode 100644 spacy/tests/regression/test_issue1-1000.py
 delete mode 100644 spacy/tests/regression/test_issue1001-1500.py
 delete mode 100644 spacy/tests/regression/test_issue1501-2000.py
 delete mode 100644 spacy/tests/regression/test_issue2001-2500.py
 delete mode 100644 spacy/tests/regression/test_issue2501-3000.py
 delete mode 100644 spacy/tests/regression/test_issue3001-3500.py
 delete mode 100644 spacy/tests/regression/test_issue3501-4000.py
 delete mode 100644 spacy/tests/regression/test_issue4001-4500.py
 delete mode 100644 spacy/tests/regression/test_issue4501-5000.py
 delete mode 100644 spacy/tests/regression/test_issue5001-5500.py
 delete mode 100644 spacy/tests/regression/test_issue5501-6000.py
 delete mode 100644 spacy/tests/regression/test_issue6001-6500.py
 delete mode 100644 spacy/tests/regression/test_issue6501-7000.py
 delete mode 100644 spacy/tests/regression/test_issue7001-8000.py
 delete mode 100644 spacy/tests/regression/test_issue7716.py
 delete mode 100644 spacy/tests/regression/test_issue8168.py
 delete mode 100644 spacy/tests/regression/test_issue8190.py
 delete mode 100644 spacy/tests/regression/test_issue8216.py
 create mode 100644 spacy/tests/serialize/test_serialize_docbin.py

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index a4d321aa3..9a7d0744a 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -143,15 +143,25 @@ Changes to `.py` files will be effective immediately.
 ### Fixing bugs
 
 When fixing a bug, first create an
-[issue](https://github.com/explosion/spaCy/issues) if one does not already exist.
-The description text can be very short – we don't want to make this too
+[issue](https://github.com/explosion/spaCy/issues) if one does not already
+exist.  The description text can be very short – we don't want to make this too
 bureaucratic.
 
-Next, create a test file named `test_issue[ISSUE NUMBER].py` in the
-[`spacy/tests/regression`](spacy/tests/regression) folder. Test for the bug
-you're fixing, and make sure the test fails. Next, add and commit your test file
-referencing the issue number in the commit message. Finally, fix the bug, make
-sure your test passes and reference the issue in your commit message.
+Next, add a test to the relevant file in the
+[`spacy/tests`](spacy/tests)folder. Then add a [pytest
+mark](https://docs.pytest.org/en/6.2.x/example/markers.html#working-with-custom-markers),
+`@pytest.mark.issue(NUMBER)`, to reference the issue number.
+
+```python
+# Assume you're fixing Issue #1234
+@pytest.mark.issue(1234)
+def test_issue1234():
+    ...
+```
+
+Test for the bug you're fixing, and make sure the test fails. Next, add and
+commit your test file. Finally, fix the bug, make sure your test passes and
+reference the issue number in your pull request description.
 
 📖 **For more information on how to add tests, check out the [tests README](spacy/tests/README.md).**
 
diff --git a/extra/DEVELOPER_DOCS/Code Conventions.md b/extra/DEVELOPER_DOCS/Code Conventions.md
index 7a3f6996f..eba466c46 100644
--- a/extra/DEVELOPER_DOCS/Code Conventions.md	
+++ b/extra/DEVELOPER_DOCS/Code Conventions.md	
@@ -444,7 +444,7 @@ spaCy uses the [`pytest`](http://doc.pytest.org/) framework for testing. Tests f
 
 When adding tests, make sure to use descriptive names and only test for one behavior at a time. Tests should be grouped into modules dedicated to the same type of functionality and some test modules are organized as directories of test files related to the same larger area of the library, e.g. `matcher` or `tokenizer`.
 
-Regression tests are tests that refer to bugs reported in specific issues. They should live in the `regression` module and are named according to the issue number (e.g. `test_issue1234.py`). This system allows us to relate tests for specific bugs back to the original reported issue, which is especially useful if we introduce a regression and a previously passing regression tests suddenly fails again. When fixing a bug, it's often useful to create a regression test for it first. Every once in a while, we go through the `regression` module and group tests together into larger files by issue number, in groups of 500 to 1000 numbers. This prevents us from ending up with too many individual files over time.
+Regression tests are tests that refer to bugs reported in specific issues. They should live in the relevant module of the test suite, named according to the issue number (e.g., `test_issue1234.py`), and [marked](https://docs.pytest.org/en/6.2.x/example/markers.html#working-with-custom-markers) appropriately (e.g. `@pytest.mark.issue(1234)`). This system allows us to relate tests for specific bugs back to the original reported issue, which is especially useful if we introduce a regression and a previously passing regression tests suddenly fails again. When fixing a bug, it's often useful to create a regression test for it first. 
 
 The test suite also provides [fixtures](https://github.com/explosion/spaCy/blob/master/spacy/tests/conftest.py) for different language tokenizers that can be used as function arguments of the same name and will be passed in automatically. Those should only be used for tests related to those specific languages. We also have [test utility functions](https://github.com/explosion/spaCy/blob/master/spacy/tests/util.py) for common operations, like creating a temporary file.
 
diff --git a/spacy/tests/doc/test_array.py b/spacy/tests/doc/test_array.py
index ef54c581c..c334cc6eb 100644
--- a/spacy/tests/doc/test_array.py
+++ b/spacy/tests/doc/test_array.py
@@ -1,8 +1,31 @@
+import numpy
 import pytest
+
 from spacy.tokens import Doc
 from spacy.attrs import ORTH, SHAPE, POS, DEP, MORPH
 
 
+@pytest.mark.issue(2203)
+def test_issue2203(en_vocab):
+    """Test that lemmas are set correctly in doc.from_array."""
+    words = ["I", "'ll", "survive"]
+    tags = ["PRP", "MD", "VB"]
+    lemmas = ["-PRON-", "will", "survive"]
+    tag_ids = [en_vocab.strings.add(tag) for tag in tags]
+    lemma_ids = [en_vocab.strings.add(lemma) for lemma in lemmas]
+    doc = Doc(en_vocab, words=words)
+    # Work around lemma corruption problem and set lemmas after tags
+    doc.from_array("TAG", numpy.array(tag_ids, dtype="uint64"))
+    doc.from_array("LEMMA", numpy.array(lemma_ids, dtype="uint64"))
+    assert [t.tag_ for t in doc] == tags
+    assert [t.lemma_ for t in doc] == lemmas
+    # We need to serialize both tag and lemma, since this is what causes the bug
+    doc_array = doc.to_array(["TAG", "LEMMA"])
+    new_doc = Doc(doc.vocab, words=words).from_array(["TAG", "LEMMA"], doc_array)
+    assert [t.tag_ for t in new_doc] == tags
+    assert [t.lemma_ for t in new_doc] == lemmas
+
+
 def test_doc_array_attr_of_token(en_vocab):
     doc = Doc(en_vocab, words=["An", "example", "sentence"])
     example = doc.vocab["example"]
diff --git a/spacy/tests/doc/test_doc_api.py b/spacy/tests/doc/test_doc_api.py
index 57df87642..c6195d7e2 100644
--- a/spacy/tests/doc/test_doc_api.py
+++ b/spacy/tests/doc/test_doc_api.py
@@ -1,14 +1,17 @@
 import weakref
 
-import pytest
 import numpy
+import pytest
+from thinc.api import NumpyOps, get_current_ops
 
+from spacy.attrs import DEP, ENT_IOB, ENT_TYPE, HEAD, IS_ALPHA, MORPH, POS
+from spacy.attrs import SENT_START, TAG
+from spacy.lang.en import English
 from spacy.lang.xx import MultiLanguage
+from spacy.language import Language
+from spacy.lexeme import Lexeme
 from spacy.tokens import Doc, Span, Token
 from spacy.vocab import Vocab
-from spacy.lexeme import Lexeme
-from spacy.lang.en import English
-from spacy.attrs import ENT_TYPE, ENT_IOB, SENT_START, HEAD, DEP, MORPH
 
 from .test_underscore import clean_underscore  # noqa: F401
 
@@ -30,6 +33,220 @@ def test_doc_api_init(en_vocab):
     assert [t.is_sent_start for t in doc] == [True, False, True, False]
 
 
+@pytest.mark.issue(1547)
+def test_issue1547():
+    """Test that entity labels still match after merging tokens."""
+    words = ["\n", "worda", ".", "\n", "wordb", "-", "Biosphere", "2", "-", " \n"]
+    doc = Doc(Vocab(), words=words)
+    doc.ents = [Span(doc, 6, 8, label=doc.vocab.strings["PRODUCT"])]
+    with doc.retokenize() as retokenizer:
+        retokenizer.merge(doc[5:7])
+    assert [ent.text for ent in doc.ents]
+
+
+@pytest.mark.issue(1757)
+def test_issue1757():
+    """Test comparison against None doesn't cause segfault."""
+    doc = Doc(Vocab(), words=["a", "b", "c"])
+    assert not doc[0] < None
+    assert not doc[0] is None
+    assert doc[0] >= None
+    assert not doc[:2] < None
+    assert not doc[:2] is None
+    assert doc[:2] >= None
+    assert not doc.vocab["a"] is None
+    assert not doc.vocab["a"] < None
+
+
+@pytest.mark.issue(2396)
+def test_issue2396(en_vocab):
+    words = ["She", "created", "a", "test", "for", "spacy"]
+    heads = [1, 1, 3, 1, 3, 4]
+    deps = ["dep"] * len(heads)
+    matrix = numpy.array(
+        [
+            [0, 1, 1, 1, 1, 1],
+            [1, 1, 1, 1, 1, 1],
+            [1, 1, 2, 3, 3, 3],
+            [1, 1, 3, 3, 3, 3],
+            [1, 1, 3, 3, 4, 4],
+            [1, 1, 3, 3, 4, 5],
+        ],
+        dtype=numpy.int32,
+    )
+    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
+    span = doc[:]
+    assert (doc.get_lca_matrix() == matrix).all()
+    assert (span.get_lca_matrix() == matrix).all()
+
+
+@pytest.mark.parametrize("text", ["-0.23", "+123,456", "±1"])
+@pytest.mark.parametrize("lang_cls", [English, MultiLanguage])
+@pytest.mark.issue(2782)
+def test_issue2782(text, lang_cls):
+    """Check that like_num handles + and - before number."""
+    nlp = lang_cls()
+    doc = nlp(text)
+    assert len(doc) == 1
+    assert doc[0].like_num
+
+
+@pytest.mark.parametrize(
+    "sentence",
+    [
+        "The story was to the effect that a young American student recently called on Professor Christlieb with a letter of introduction.",
+        "The next month Barry Siddall joined Stoke City on a free transfer, after Chris Pearce had established himself as the Vale's #1.",
+        "The next month Barry Siddall joined Stoke City on a free transfer, after Chris Pearce had established himself as the Vale's number one",
+        "Indeed, making the one who remains do all the work has installed him into a position of such insolent tyranny, it will take a month at least to reduce him to his proper proportions.",
+        "It was a missed assignment, but it shouldn't have resulted in a turnover ...",
+    ],
+)
+@pytest.mark.issue(3869)
+def test_issue3869(sentence):
+    """Test that the Doc's count_by function works consistently"""
+    nlp = English()
+    doc = nlp(sentence)
+    count = 0
+    for token in doc:
+        count += token.is_alpha
+    assert count == doc.count_by(IS_ALPHA).get(1, 0)
+
+
+@pytest.mark.issue(3962)
+def test_issue3962(en_vocab):
+    """Ensure that as_doc does not result in out-of-bound access of tokens.
+    This is achieved by setting the head to itself if it would lie out of the span otherwise."""
+    # fmt: off
+    words = ["He", "jests", "at", "scars", ",", "that", "never", "felt", "a", "wound", "."]
+    heads = [1, 7, 1, 2, 7, 7, 7, 7, 9, 7, 7]
+    deps = ["nsubj", "ccomp", "prep", "pobj", "punct", "nsubj", "neg", "ROOT", "det", "dobj", "punct"]
+    # fmt: on
+    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
+    span2 = doc[1:5]  # "jests at scars ,"
+    doc2 = span2.as_doc()
+    doc2_json = doc2.to_json()
+    assert doc2_json
+    # head set to itself, being the new artificial root
+    assert doc2[0].head.text == "jests"
+    assert doc2[0].dep_ == "dep"
+    assert doc2[1].head.text == "jests"
+    assert doc2[1].dep_ == "prep"
+    assert doc2[2].head.text == "at"
+    assert doc2[2].dep_ == "pobj"
+    assert doc2[3].head.text == "jests"  # head set to the new artificial root
+    assert doc2[3].dep_ == "dep"
+    # We should still have 1 sentence
+    assert len(list(doc2.sents)) == 1
+    span3 = doc[6:9]  # "never felt a"
+    doc3 = span3.as_doc()
+    doc3_json = doc3.to_json()
+    assert doc3_json
+    assert doc3[0].head.text == "felt"
+    assert doc3[0].dep_ == "neg"
+    assert doc3[1].head.text == "felt"
+    assert doc3[1].dep_ == "ROOT"
+    assert doc3[2].head.text == "felt"  # head set to ancestor
+    assert doc3[2].dep_ == "dep"
+    # We should still have 1 sentence as "a" can be attached to "felt" instead of "wound"
+    assert len(list(doc3.sents)) == 1
+
+
+@pytest.mark.issue(3962)
+def test_issue3962_long(en_vocab):
+    """Ensure that as_doc does not result in out-of-bound access of tokens.
+    This is achieved by setting the head to itself if it would lie out of the span otherwise."""
+    # fmt: off
+    words = ["He", "jests", "at", "scars", ".", "They", "never", "felt", "a", "wound", "."]
+    heads = [1, 1, 1, 2, 1, 7, 7, 7, 9, 7, 7]
+    deps = ["nsubj", "ROOT", "prep", "pobj", "punct", "nsubj", "neg", "ROOT", "det", "dobj", "punct"]
+    # fmt: on
+    two_sent_doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
+    span2 = two_sent_doc[1:7]  # "jests at scars. They never"
+    doc2 = span2.as_doc()
+    doc2_json = doc2.to_json()
+    assert doc2_json
+    # head set to itself, being the new artificial root (in sentence 1)
+    assert doc2[0].head.text == "jests"
+    assert doc2[0].dep_ == "ROOT"
+    assert doc2[1].head.text == "jests"
+    assert doc2[1].dep_ == "prep"
+    assert doc2[2].head.text == "at"
+    assert doc2[2].dep_ == "pobj"
+    assert doc2[3].head.text == "jests"
+    assert doc2[3].dep_ == "punct"
+    # head set to itself, being the new artificial root (in sentence 2)
+    assert doc2[4].head.text == "They"
+    assert doc2[4].dep_ == "dep"
+    # head set to the new artificial head (in sentence 2)
+    assert doc2[4].head.text == "They"
+    assert doc2[4].dep_ == "dep"
+    # We should still have 2 sentences
+    sents = list(doc2.sents)
+    assert len(sents) == 2
+    assert sents[0].text == "jests at scars ."
+    assert sents[1].text == "They never"
+
+
+@Language.factory("my_pipe")
+class CustomPipe:
+    def __init__(self, nlp, name="my_pipe"):
+        self.name = name
+        Span.set_extension("my_ext", getter=self._get_my_ext)
+        Doc.set_extension("my_ext", default=None)
+
+    def __call__(self, doc):
+        gathered_ext = []
+        for sent in doc.sents:
+            sent_ext = self._get_my_ext(sent)
+            sent._.set("my_ext", sent_ext)
+            gathered_ext.append(sent_ext)
+
+        doc._.set("my_ext", "\n".join(gathered_ext))
+        return doc
+
+    @staticmethod
+    def _get_my_ext(span):
+        return str(span.end)
+
+
+@pytest.mark.issue(4903)
+def test_issue4903():
+    """Ensure that this runs correctly and doesn't hang or crash on Windows /
+    macOS."""
+    nlp = English()
+    nlp.add_pipe("sentencizer")
+    nlp.add_pipe("my_pipe", after="sentencizer")
+    text = ["I like bananas.", "Do you like them?", "No, I prefer wasabi."]
+    if isinstance(get_current_ops(), NumpyOps):
+        docs = list(nlp.pipe(text, n_process=2))
+        assert docs[0].text == "I like bananas."
+        assert docs[1].text == "Do you like them?"
+        assert docs[2].text == "No, I prefer wasabi."
+
+
+@pytest.mark.issue(5048)
+def test_issue5048(en_vocab):
+    words = ["This", "is", "a", "sentence"]
+    pos_s = ["DET", "VERB", "DET", "NOUN"]
+    spaces = [" ", " ", " ", ""]
+    deps_s = ["dep", "adj", "nn", "atm"]
+    tags_s = ["DT", "VBZ", "DT", "NN"]
+    strings = en_vocab.strings
+    for w in words:
+        strings.add(w)
+    deps = [strings.add(d) for d in deps_s]
+    pos = [strings.add(p) for p in pos_s]
+    tags = [strings.add(t) for t in tags_s]
+    attrs = [POS, DEP, TAG]
+    array = numpy.array(list(zip(pos, deps, tags)), dtype="uint64")
+    doc = Doc(en_vocab, words=words, spaces=spaces)
+    doc.from_array(attrs, array)
+    v1 = [(token.text, token.pos_, token.tag_) for token in doc]
+    doc2 = Doc(en_vocab, words=words, pos=pos_s, deps=deps_s, tags=tags_s)
+    v2 = [(token.text, token.pos_, token.tag_) for token in doc2]
+    assert v1 == v2
+
+
 @pytest.mark.parametrize("text", [["one", "two", "three"]])
 def test_doc_api_compare_by_string_position(en_vocab, text):
     doc = Doc(en_vocab, words=text)
diff --git a/spacy/tests/doc/test_retokenize_split.py b/spacy/tests/doc/test_retokenize_split.py
index 16df1713d..ec4deb033 100644
--- a/spacy/tests/doc/test_retokenize_split.py
+++ b/spacy/tests/doc/test_retokenize_split.py
@@ -1,8 +1,50 @@
+import numpy
 import pytest
+
 from spacy.vocab import Vocab
 from spacy.tokens import Doc, Token
 
 
+@pytest.mark.issue(3540)
+def test_issue3540(en_vocab):
+    words = ["I", "live", "in", "NewYork", "right", "now"]
+    tensor = numpy.asarray(
+        [[1.0, 1.1], [2.0, 2.1], [3.0, 3.1], [4.0, 4.1], [5.0, 5.1], [6.0, 6.1]],
+        dtype="f",
+    )
+    doc = Doc(en_vocab, words=words)
+    doc.tensor = tensor
+    gold_text = ["I", "live", "in", "NewYork", "right", "now"]
+    assert [token.text for token in doc] == gold_text
+    gold_lemma = ["I", "live", "in", "NewYork", "right", "now"]
+    for i, lemma in enumerate(gold_lemma):
+        doc[i].lemma_ = lemma
+    assert [token.lemma_ for token in doc] == gold_lemma
+    vectors_1 = [token.vector for token in doc]
+    assert len(vectors_1) == len(doc)
+
+    with doc.retokenize() as retokenizer:
+        heads = [(doc[3], 1), doc[2]]
+        attrs = {
+            "POS": ["PROPN", "PROPN"],
+            "LEMMA": ["New", "York"],
+            "DEP": ["pobj", "compound"],
+        }
+        retokenizer.split(doc[3], ["New", "York"], heads=heads, attrs=attrs)
+
+    gold_text = ["I", "live", "in", "New", "York", "right", "now"]
+    assert [token.text for token in doc] == gold_text
+    gold_lemma = ["I", "live", "in", "New", "York", "right", "now"]
+    assert [token.lemma_ for token in doc] == gold_lemma
+    vectors_2 = [token.vector for token in doc]
+    assert len(vectors_2) == len(doc)
+    assert vectors_1[0].tolist() == vectors_2[0].tolist()
+    assert vectors_1[1].tolist() == vectors_2[1].tolist()
+    assert vectors_1[2].tolist() == vectors_2[2].tolist()
+    assert vectors_1[4].tolist() == vectors_2[5].tolist()
+    assert vectors_1[5].tolist() == vectors_2[6].tolist()
+
+
 def test_doc_retokenize_split(en_vocab):
     words = ["LosAngeles", "start", "."]
     heads = [1, 2, 2]
diff --git a/spacy/tests/doc/test_span.py b/spacy/tests/doc/test_span.py
index 2503ad94c..d18293d3f 100644
--- a/spacy/tests/doc/test_span.py
+++ b/spacy/tests/doc/test_span.py
@@ -1,7 +1,9 @@
 import pytest
 import numpy
 from numpy.testing import assert_array_equal
+
 from spacy.attrs import ORTH, LENGTH
+from spacy.lang.en import English
 from spacy.tokens import Doc, Span, Token
 from spacy.vocab import Vocab
 from spacy.util import filter_spans
@@ -43,6 +45,106 @@ def doc_not_parsed(en_tokenizer):
     return doc
 
 
+@pytest.mark.issue(1537)
+def test_issue1537():
+    """Test that Span.as_doc() doesn't segfault."""
+    string = "The sky is blue . The man is pink . The dog is purple ."
+    doc = Doc(Vocab(), words=string.split())
+    doc[0].sent_start = True
+    for word in doc[1:]:
+        if word.nbor(-1).text == ".":
+            word.sent_start = True
+        else:
+            word.sent_start = False
+    sents = list(doc.sents)
+    sent0 = sents[0].as_doc()
+    sent1 = sents[1].as_doc()
+    assert isinstance(sent0, Doc)
+    assert isinstance(sent1, Doc)
+
+
+@pytest.mark.issue(1612)
+def test_issue1612(en_tokenizer):
+    """Test that span.orth_ is identical to span.text"""
+    doc = en_tokenizer("The black cat purrs.")
+    span = doc[1:3]
+    assert span.orth_ == span.text
+
+
+@pytest.mark.issue(3199)
+def test_issue3199():
+    """Test that Span.noun_chunks works correctly if no noun chunks iterator
+    is available. To make this test future-proof, we're constructing a Doc
+    with a new Vocab here and a parse tree to make sure the noun chunks run.
+    """
+    words = ["This", "is", "a", "sentence"]
+    doc = Doc(Vocab(), words=words, heads=[0] * len(words), deps=["dep"] * len(words))
+    with pytest.raises(NotImplementedError):
+        list(doc[0:3].noun_chunks)
+
+
+@pytest.mark.issue(5152)
+def test_issue5152():
+    # Test that the comparison between a Span and a Token, goes well
+    # There was a bug when the number of tokens in the span equaled the number of characters in the token (!)
+    nlp = English()
+    text = nlp("Talk about being boring!")
+    text_var = nlp("Talk of being boring!")
+    y = nlp("Let")
+    span = text[0:3]  # Talk about being
+    span_2 = text[0:3]  # Talk about being
+    span_3 = text_var[0:3]  # Talk of being
+    token = y[0]  # Let
+    with pytest.warns(UserWarning):
+        assert span.similarity(token) == 0.0
+    assert span.similarity(span_2) == 1.0
+    with pytest.warns(UserWarning):
+        assert span_2.similarity(span_3) < 1.0
+
+
+@pytest.mark.issue(6755)
+def test_issue6755(en_tokenizer):
+    doc = en_tokenizer("This is a magnificent sentence.")
+    span = doc[:0]
+    assert span.text_with_ws == ""
+    assert span.text == ""
+
+
+@pytest.mark.parametrize(
+    "sentence, start_idx,end_idx,label",
+    [("Welcome to Mumbai, my friend", 11, 17, "GPE")],
+)
+@pytest.mark.issue(6815)
+def test_issue6815_1(sentence, start_idx, end_idx, label):
+    nlp = English()
+    doc = nlp(sentence)
+    span = doc[:].char_span(start_idx, end_idx, label=label)
+    assert span.label_ == label
+
+
+@pytest.mark.parametrize(
+    "sentence, start_idx,end_idx,kb_id", [("Welcome to Mumbai, my friend", 11, 17, 5)]
+)
+@pytest.mark.issue(6815)
+def test_issue6815_2(sentence, start_idx, end_idx, kb_id):
+    nlp = English()
+    doc = nlp(sentence)
+    span = doc[:].char_span(start_idx, end_idx, kb_id=kb_id)
+    assert span.kb_id == kb_id
+
+
+@pytest.mark.parametrize(
+    "sentence, start_idx,end_idx,vector",
+    [("Welcome to Mumbai, my friend", 11, 17, numpy.array([0.1, 0.2, 0.3]))],
+)
+@pytest.mark.issue(6815)
+def test_issue6815_3(sentence, start_idx, end_idx, vector):
+    nlp = English()
+    doc = nlp(sentence)
+    span = doc[:].char_span(start_idx, end_idx, vector=vector)
+    assert (span.vector == vector).all()
+
+
 @pytest.mark.parametrize(
     "i_sent,i,j,text",
     [
diff --git a/spacy/tests/lang/en/test_sbd.py b/spacy/tests/lang/en/test_sbd.py
index 39d8d3b59..d30c72750 100644
--- a/spacy/tests/lang/en/test_sbd.py
+++ b/spacy/tests/lang/en/test_sbd.py
@@ -4,6 +4,15 @@ from spacy.tokens import Doc
 from ...util import apply_transition_sequence
 
 
+@pytest.mark.issue(309)
+def test_issue309(en_vocab):
+    """Test Issue #309: SBD fails on empty string"""
+    doc = Doc(en_vocab, words=[" "], heads=[0], deps=["ROOT"])
+    assert len(doc) == 1
+    sents = list(doc.sents)
+    assert len(sents) == 1
+
+
 @pytest.mark.parametrize("words", [["A", "test", "sentence"]])
 @pytest.mark.parametrize("punct", [".", "!", "?", ""])
 def test_en_sbd_single_punct(en_vocab, words, punct):
diff --git a/spacy/tests/lang/en/test_tokenizer.py b/spacy/tests/lang/en/test_tokenizer.py
new file mode 100644
index 000000000..e6d1d7d85
--- /dev/null
+++ b/spacy/tests/lang/en/test_tokenizer.py
@@ -0,0 +1,169 @@
+import pytest
+
+
+@pytest.mark.issue(351)
+def test_issue351(en_tokenizer):
+    doc = en_tokenizer("   This is a cat.")
+    assert doc[0].idx == 0
+    assert len(doc[0]) == 3
+    assert doc[1].idx == 3
+
+
+@pytest.mark.issue(360)
+def test_issue360(en_tokenizer):
+    """Test tokenization of big ellipsis"""
+    tokens = en_tokenizer("$45...............Asking")
+    assert len(tokens) > 2
+
+
+@pytest.mark.issue(736)
+@pytest.mark.parametrize("text,number", [("7am", "7"), ("11p.m.", "11")])
+def test_issue736(en_tokenizer, text, number):
+    """Test that times like "7am" are tokenized correctly and that numbers are
+    converted to string."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 2
+    assert tokens[0].text == number
+
+
+@pytest.mark.issue(740)
+@pytest.mark.parametrize("text", ["3/4/2012", "01/12/1900"])
+def test_issue740(en_tokenizer, text):
+    """Test that dates are not split and kept as one token. This behaviour is
+    currently inconsistent, since dates separated by hyphens are still split.
+    This will be hard to prevent without causing clashes with numeric ranges."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 1
+
+
+@pytest.mark.issue(744)
+@pytest.mark.parametrize("text", ["We were scared", "We Were Scared"])
+def test_issue744(en_tokenizer, text):
+    """Test that 'were' and 'Were' are excluded from the contractions
+    generated by the English tokenizer exceptions."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 3
+    assert tokens[1].text.lower() == "were"
+
+
+@pytest.mark.issue(759)
+@pytest.mark.parametrize(
+    "text,is_num", [("one", True), ("ten", True), ("teneleven", False)]
+)
+def test_issue759(en_tokenizer, text, is_num):
+    tokens = en_tokenizer(text)
+    assert tokens[0].like_num == is_num
+
+
+@pytest.mark.issue(775)
+@pytest.mark.parametrize("text", ["Shell", "shell", "Shed", "shed"])
+def test_issue775(en_tokenizer, text):
+    """Test that 'Shell' and 'shell' are excluded from the contractions
+    generated by the English tokenizer exceptions."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 1
+    assert tokens[0].text == text
+
+
+@pytest.mark.issue(792)
+@pytest.mark.parametrize("text", ["This is a string ", "This is a string\u0020"])
+def test_issue792(en_tokenizer, text):
+    """Test for Issue #792: Trailing whitespace is removed after tokenization."""
+    doc = en_tokenizer(text)
+    assert "".join([token.text_with_ws for token in doc]) == text
+
+
+@pytest.mark.issue(792)
+@pytest.mark.parametrize("text", ["This is a string", "This is a string\n"])
+def test_control_issue792(en_tokenizer, text):
+    """Test base case for Issue #792: Non-trailing whitespace"""
+    doc = en_tokenizer(text)
+    assert "".join([token.text_with_ws for token in doc]) == text
+
+
+@pytest.mark.issue(859)
+@pytest.mark.parametrize(
+    "text", ["aaabbb@ccc.com\nThank you!", "aaabbb@ccc.com \nThank you!"]
+)
+def test_issue859(en_tokenizer, text):
+    """Test that no extra space is added in doc.text method."""
+    doc = en_tokenizer(text)
+    assert doc.text == text
+
+
+@pytest.mark.issue(886)
+@pytest.mark.parametrize("text", ["Datum:2014-06-02\nDokument:76467"])
+def test_issue886(en_tokenizer, text):
+    """Test that token.idx matches the original text index for texts with newlines."""
+    doc = en_tokenizer(text)
+    for token in doc:
+        assert len(token.text) == len(token.text_with_ws)
+        assert text[token.idx] == token.text[0]
+
+
+@pytest.mark.issue(891)
+@pytest.mark.parametrize("text", ["want/need"])
+def test_issue891(en_tokenizer, text):
+    """Test that / infixes are split correctly."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 3
+    assert tokens[1].text == "/"
+
+
+@pytest.mark.issue(957)
+@pytest.mark.slow
+def test_issue957(en_tokenizer):
+    """Test that spaCy doesn't hang on many punctuation characters.
+    If this test hangs, check (new) regular expressions for conflicting greedy operators
+    """
+    # Skip test if pytest-timeout is not installed
+    pytest.importorskip("pytest_timeout")
+    for punct in [".", ",", "'", '"', ":", "?", "!", ";", "-"]:
+        string = "0"
+        for i in range(1, 100):
+            string += punct + str(i)
+        doc = en_tokenizer(string)
+        assert doc
+
+
+@pytest.mark.parametrize("text", ["test@example.com", "john.doe@example.co.uk"])
+@pytest.mark.issue(1698)
+def test_issue1698(en_tokenizer, text):
+    """Test that doc doesn't identify email-addresses as URLs"""
+    doc = en_tokenizer(text)
+    assert len(doc) == 1
+    assert not doc[0].like_url
+
+
+@pytest.mark.issue(1758)
+def test_issue1758(en_tokenizer):
+    """Test that "would've" is handled by the English tokenizer exceptions."""
+    tokens = en_tokenizer("would've")
+    assert len(tokens) == 2
+
+
+@pytest.mark.issue(1773)
+def test_issue1773(en_tokenizer):
+    """Test that spaces don't receive a POS but no TAG. This is the root cause
+    of the serialization issue reported in #1773."""
+    doc = en_tokenizer("\n")
+    if doc[0].pos_ == "SPACE":
+        assert doc[0].tag_ != ""
+
+
+@pytest.mark.issue(3277)
+def test_issue3277(es_tokenizer):
+    """Test that hyphens are split correctly as prefixes."""
+    doc = es_tokenizer("—Yo me llamo... –murmuró el niño– Emilio Sánchez Pérez.")
+    assert len(doc) == 14
+    assert doc[0].text == "\u2014"
+    assert doc[5].text == "\u2013"
+    assert doc[9].text == "\u2013"
+
+
+@pytest.mark.parametrize("word", ["don't", "don’t", "I'd", "I’d"])
+@pytest.mark.issue(3521)
+def test_issue3521(en_tokenizer, word):
+    tok = en_tokenizer(word)[1]
+    # 'not' and 'would' should be stopwords, also in their abbreviated forms
+    assert tok.is_stop
diff --git a/spacy/tests/lang/es/test_text.py b/spacy/tests/lang/es/test_text.py
index 96f6bcab5..d95f6d26b 100644
--- a/spacy/tests/lang/es/test_text.py
+++ b/spacy/tests/lang/es/test_text.py
@@ -1,5 +1,16 @@
 import pytest
 from spacy.lang.es.lex_attrs import like_num
+from spacy.lang.es import Spanish
+
+
+@pytest.mark.issue(3803)
+def test_issue3803():
+    """Test that spanish num-like tokens have True for like_num attribute."""
+    nlp = Spanish()
+    text = "2 dos 1000 mil 12 doce"
+    doc = nlp(text)
+
+    assert [t.like_num for t in doc] == [True, True, True, True, True, True]
 
 
 def test_es_tokenizer_handles_long_text(es_tokenizer):
diff --git a/spacy/tests/lang/hi/test_text.py b/spacy/tests/lang/hi/test_text.py
new file mode 100644
index 000000000..791cc3822
--- /dev/null
+++ b/spacy/tests/lang/hi/test_text.py
@@ -0,0 +1,11 @@
+import pytest
+from spacy.lang.hi import Hindi
+
+
+@pytest.mark.issue(3625)
+def test_issue3625():
+    """Test that default punctuation rules applies to hindi unicode characters"""
+    nlp = Hindi()
+    doc = nlp("hi. how हुए. होटल, होटल")
+    expected = ["hi", ".", "how", "हुए", ".", "होटल", ",", "होटल"]
+    assert [token.text for token in doc] == expected
diff --git a/spacy/tests/lang/it/test_text.py b/spacy/tests/lang/it/test_text.py
new file mode 100644
index 000000000..6023a20b1
--- /dev/null
+++ b/spacy/tests/lang/it/test_text.py
@@ -0,0 +1,14 @@
+import pytest
+
+
+@pytest.mark.issue(2822)
+def test_issue2822(it_tokenizer):
+    """Test that the abbreviation of poco is kept as one word."""
+    doc = it_tokenizer("Vuoi un po' di zucchero?")
+    assert len(doc) == 6
+    assert doc[0].text == "Vuoi"
+    assert doc[1].text == "un"
+    assert doc[2].text == "po'"
+    assert doc[3].text == "di"
+    assert doc[4].text == "zucchero"
+    assert doc[5].text == "?"
diff --git a/spacy/tests/lang/ja/test_tokenizer.py b/spacy/tests/lang/ja/test_tokenizer.py
index 3437ea283..ef7bed06d 100644
--- a/spacy/tests/lang/ja/test_tokenizer.py
+++ b/spacy/tests/lang/ja/test_tokenizer.py
@@ -54,6 +54,18 @@ SUB_TOKEN_TESTS = [
 # fmt: on
 
 
+@pytest.mark.issue(2901)
+def test_issue2901():
+    """Test that `nlp` doesn't fail."""
+    try:
+        nlp = Japanese()
+    except ImportError:
+        pytest.skip()
+
+    doc = nlp("pythonが大好きです")
+    assert doc
+
+
 @pytest.mark.parametrize("text,expected_tokens", TOKENIZER_TESTS)
 def test_ja_tokenizer(ja_tokenizer, text, expected_tokens):
     tokens = [token.text for token in ja_tokenizer(text)]
diff --git a/spacy/tests/lang/sv/test_exceptions.py b/spacy/tests/lang/sv/test_exceptions.py
index e6cae4d2b..b49a0c832 100644
--- a/spacy/tests/lang/sv/test_exceptions.py
+++ b/spacy/tests/lang/sv/test_exceptions.py
@@ -1,6 +1,5 @@
 import pytest
 
-
 SV_TOKEN_EXCEPTION_TESTS = [
     (
         "Smörsåsen används bl.a. till fisk",
@@ -17,6 +16,26 @@ SV_TOKEN_EXCEPTION_TESTS = [
 ]
 
 
+@pytest.mark.issue(805)
+@pytest.mark.parametrize(
+    "text,expected_tokens",
+    [
+        (
+            "Smörsåsen används bl.a. till fisk",
+            ["Smörsåsen", "används", "bl.a.", "till", "fisk"],
+        ),
+        (
+            "Jag kommer först kl. 13 p.g.a. diverse förseningar",
+            ["Jag", "kommer", "först", "kl.", "13", "p.g.a.", "diverse", "förseningar"],
+        ),
+    ],
+)
+def test_issue805(sv_tokenizer, text, expected_tokens):
+    tokens = sv_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
+
+
 @pytest.mark.parametrize("text,expected_tokens", SV_TOKEN_EXCEPTION_TESTS)
 def test_sv_tokenizer_handles_exception_cases(sv_tokenizer, text, expected_tokens):
     tokens = sv_tokenizer(text)
diff --git a/spacy/tests/lang/test_attrs.py b/spacy/tests/lang/test_attrs.py
index 6a7a404fd..5350c1fe5 100644
--- a/spacy/tests/lang/test_attrs.py
+++ b/spacy/tests/lang/test_attrs.py
@@ -1,6 +1,15 @@
 import pytest
-from spacy.attrs import intify_attrs, ORTH, NORM, LEMMA, IS_ALPHA
-from spacy.lang.lex_attrs import is_punct, is_ascii, is_currency, like_url, word_shape
+
+from spacy.attrs import IS_ALPHA, LEMMA, NORM, ORTH, intify_attrs
+from spacy.lang.en.stop_words import STOP_WORDS
+from spacy.lang.lex_attrs import is_ascii, is_currency, is_punct, is_stop
+from spacy.lang.lex_attrs import like_url, word_shape
+
+
+@pytest.mark.parametrize("word", ["the"])
+@pytest.mark.issue(1889)
+def test_issue1889(word):
+    assert is_stop(word, STOP_WORDS) == is_stop(word.upper(), STOP_WORDS)
 
 
 @pytest.mark.parametrize("text", ["dog"])
diff --git a/spacy/tests/matcher/test_matcher_logic.py b/spacy/tests/matcher/test_matcher_logic.py
index b96bb2032..3649b07ed 100644
--- a/spacy/tests/matcher/test_matcher_logic.py
+++ b/spacy/tests/matcher/test_matcher_logic.py
@@ -1,10 +1,14 @@
-import pytest
 import re
 
-from spacy.lang.en import English
-from spacy.matcher import Matcher
-from spacy.tokens import Doc, Span
+import pytest
 
+from spacy.attrs import IS_PUNCT, LOWER, ORTH
+from spacy.errors import MatchPatternError
+from spacy.lang.en import English
+from spacy.lang.lex_attrs import LEX_ATTRS
+from spacy.matcher import Matcher
+from spacy.tokens import Doc, Span, Token
+from spacy.vocab import Vocab
 
 pattern1 = [{"ORTH": "A"}, {"ORTH": "A", "OP": "*"}]
 pattern2 = [{"ORTH": "A", "OP": "*"}, {"ORTH": "A"}]
@@ -36,6 +40,473 @@ def doc(en_tokenizer, text):
     return doc
 
 
+@pytest.mark.issue(118)
+@pytest.mark.parametrize(
+    "patterns",
+    [
+        [[{"LOWER": "celtics"}], [{"LOWER": "boston"}, {"LOWER": "celtics"}]],
+        [[{"LOWER": "boston"}, {"LOWER": "celtics"}], [{"LOWER": "celtics"}]],
+    ],
+)
+def test_issue118(en_tokenizer, patterns):
+    """Test a bug that arose from having overlapping matches"""
+    text = (
+        "how many points did lebron james score against the boston celtics last night"
+    )
+    doc = en_tokenizer(text)
+    ORG = doc.vocab.strings["ORG"]
+    matcher = Matcher(doc.vocab)
+    matcher.add("BostonCeltics", patterns)
+    assert len(list(doc.ents)) == 0
+    matches = [(ORG, start, end) for _, start, end in matcher(doc)]
+    assert matches == [(ORG, 9, 11), (ORG, 10, 11)]
+    doc.ents = matches[:1]
+    ents = list(doc.ents)
+    assert len(ents) == 1
+    assert ents[0].label == ORG
+    assert ents[0].start == 9
+    assert ents[0].end == 11
+
+
+@pytest.mark.issue(118)
+@pytest.mark.parametrize(
+    "patterns",
+    [
+        [[{"LOWER": "boston"}], [{"LOWER": "boston"}, {"LOWER": "celtics"}]],
+        [[{"LOWER": "boston"}, {"LOWER": "celtics"}], [{"LOWER": "boston"}]],
+    ],
+)
+def test_issue118_prefix_reorder(en_tokenizer, patterns):
+    """Test a bug that arose from having overlapping matches"""
+    text = (
+        "how many points did lebron james score against the boston celtics last night"
+    )
+    doc = en_tokenizer(text)
+    ORG = doc.vocab.strings["ORG"]
+    matcher = Matcher(doc.vocab)
+    matcher.add("BostonCeltics", patterns)
+    assert len(list(doc.ents)) == 0
+    matches = [(ORG, start, end) for _, start, end in matcher(doc)]
+    doc.ents += tuple(matches)[1:]
+    assert matches == [(ORG, 9, 10), (ORG, 9, 11)]
+    ents = doc.ents
+    assert len(ents) == 1
+    assert ents[0].label == ORG
+    assert ents[0].start == 9
+    assert ents[0].end == 11
+
+
+@pytest.mark.issue(242)
+def test_issue242(en_tokenizer):
+    """Test overlapping multi-word phrases."""
+    text = "There are different food safety standards in different countries."
+    patterns = [
+        [{"LOWER": "food"}, {"LOWER": "safety"}],
+        [{"LOWER": "safety"}, {"LOWER": "standards"}],
+    ]
+    doc = en_tokenizer(text)
+    matcher = Matcher(doc.vocab)
+    matcher.add("FOOD", patterns)
+    matches = [(ent_type, start, end) for ent_type, start, end in matcher(doc)]
+    match1, match2 = matches
+    assert match1[1] == 3
+    assert match1[2] == 5
+    assert match2[1] == 4
+    assert match2[2] == 6
+    with pytest.raises(ValueError):
+        # One token can only be part of one entity, so test that the matches
+        # can't be added as entities
+        doc.ents += tuple(matches)
+
+
+@pytest.mark.issue(587)
+def test_issue587(en_tokenizer):
+    """Test that Matcher doesn't segfault on particular input"""
+    doc = en_tokenizer("a b; c")
+    matcher = Matcher(doc.vocab)
+    matcher.add("TEST1", [[{ORTH: "a"}, {ORTH: "b"}]])
+    matches = matcher(doc)
+    assert len(matches) == 1
+    matcher.add("TEST2", [[{ORTH: "a"}, {ORTH: "b"}, {IS_PUNCT: True}, {ORTH: "c"}]])
+    matches = matcher(doc)
+    assert len(matches) == 2
+    matcher.add("TEST3", [[{ORTH: "a"}, {ORTH: "b"}, {IS_PUNCT: True}, {ORTH: "d"}]])
+    matches = matcher(doc)
+    assert len(matches) == 2
+
+
+@pytest.mark.issue(588)
+def test_issue588(en_vocab):
+    """Test if empty specs still cause an error when adding patterns"""
+    matcher = Matcher(en_vocab)
+    with pytest.raises(ValueError):
+        matcher.add("TEST", [[]])
+
+
+@pytest.mark.issue(590)
+def test_issue590(en_vocab):
+    """Test overlapping matches"""
+    doc = Doc(en_vocab, words=["n", "=", "1", ";", "a", ":", "5", "%"])
+    matcher = Matcher(en_vocab)
+    matcher.add(
+        "ab", [[{"IS_ALPHA": True}, {"ORTH": ":"}, {"LIKE_NUM": True}, {"ORTH": "%"}]]
+    )
+    matcher.add("ab", [[{"IS_ALPHA": True}, {"ORTH": "="}, {"LIKE_NUM": True}]])
+    matches = matcher(doc)
+    assert len(matches) == 2
+
+
+@pytest.mark.issue(615)
+def test_issue615(en_tokenizer):
+    def merge_phrases(matcher, doc, i, matches):
+        """Merge a phrase. We have to be careful here because we'll change the
+        token indices. To avoid problems, merge all the phrases once we're called
+        on the last match."""
+        if i != len(matches) - 1:
+            return None
+        spans = [Span(doc, start, end, label=label) for label, start, end in matches]
+        with doc.retokenize() as retokenizer:
+            for span in spans:
+                tag = "NNP" if span.label_ else span.root.tag_
+                attrs = {"tag": tag, "lemma": span.text}
+                retokenizer.merge(span, attrs=attrs)
+                doc.ents = doc.ents + (span,)
+
+    text = "The golf club is broken"
+    pattern = [{"ORTH": "golf"}, {"ORTH": "club"}]
+    label = "Sport_Equipment"
+    doc = en_tokenizer(text)
+    matcher = Matcher(doc.vocab)
+    matcher.add(label, [pattern], on_match=merge_phrases)
+    matcher(doc)
+    entities = list(doc.ents)
+    assert entities != []
+    assert entities[0].label != 0
+
+
+@pytest.mark.issue(850)
+def test_issue850():
+    """The variable-length pattern matches the succeeding token. Check we
+    handle the ambiguity correctly."""
+    vocab = Vocab(lex_attr_getters={LOWER: lambda string: string.lower()})
+    matcher = Matcher(vocab)
+    pattern = [{"LOWER": "bob"}, {"OP": "*"}, {"LOWER": "frank"}]
+    matcher.add("FarAway", [pattern])
+    doc = Doc(matcher.vocab, words=["bob", "and", "and", "frank"])
+    match = matcher(doc)
+    assert len(match) == 1
+    ent_id, start, end = match[0]
+    assert start == 0
+    assert end == 4
+
+
+@pytest.mark.issue(850)
+def test_issue850_basic():
+    """Test Matcher matches with '*' operator and Boolean flag"""
+    vocab = Vocab(lex_attr_getters={LOWER: lambda string: string.lower()})
+    matcher = Matcher(vocab)
+    pattern = [{"LOWER": "bob"}, {"OP": "*", "LOWER": "and"}, {"LOWER": "frank"}]
+    matcher.add("FarAway", [pattern])
+    doc = Doc(matcher.vocab, words=["bob", "and", "and", "frank"])
+    match = matcher(doc)
+    assert len(match) == 1
+    ent_id, start, end = match[0]
+    assert start == 0
+    assert end == 4
+
+
+@pytest.mark.issue(1434)
+def test_issue1434():
+    """Test matches occur when optional element at end of short doc."""
+    pattern = [{"ORTH": "Hello"}, {"IS_ALPHA": True, "OP": "?"}]
+    vocab = Vocab(lex_attr_getters=LEX_ATTRS)
+    hello_world = Doc(vocab, words=["Hello", "World"])
+    hello = Doc(vocab, words=["Hello"])
+    matcher = Matcher(vocab)
+    matcher.add("MyMatcher", [pattern])
+    matches = matcher(hello_world)
+    assert matches
+    matches = matcher(hello)
+    assert matches
+
+
+@pytest.mark.parametrize(
+    "string,start,end",
+    [
+        ("a", 0, 1),
+        ("a b", 0, 2),
+        ("a c", 0, 1),
+        ("a b c", 0, 2),
+        ("a b b c", 0, 3),
+        ("a b b", 0, 3),
+    ],
+)
+@pytest.mark.issue(1450)
+def test_issue1450(string, start, end):
+    """Test matcher works when patterns end with * operator."""
+    pattern = [{"ORTH": "a"}, {"ORTH": "b", "OP": "*"}]
+    matcher = Matcher(Vocab())
+    matcher.add("TSTEND", [pattern])
+    doc = Doc(Vocab(), words=string.split())
+    matches = matcher(doc)
+    if start is None or end is None:
+        assert matches == []
+    assert matches[-1][1] == start
+    assert matches[-1][2] == end
+
+
+@pytest.mark.issue(1945)
+def test_issue1945():
+    """Test regression in Matcher introduced in v2.0.6."""
+    matcher = Matcher(Vocab())
+    matcher.add("MWE", [[{"orth": "a"}, {"orth": "a"}]])
+    doc = Doc(matcher.vocab, words=["a", "a", "a"])
+    matches = matcher(doc)  # we should see two overlapping matches here
+    assert len(matches) == 2
+    assert matches[0][1:] == (0, 2)
+    assert matches[1][1:] == (1, 3)
+
+
+@pytest.mark.issue(1971)
+def test_issue1971(en_vocab):
+    # Possibly related to #2675 and #2671?
+    matcher = Matcher(en_vocab)
+    pattern = [
+        {"ORTH": "Doe"},
+        {"ORTH": "!", "OP": "?"},
+        {"_": {"optional": True}, "OP": "?"},
+        {"ORTH": "!", "OP": "?"},
+    ]
+    Token.set_extension("optional", default=False)
+    matcher.add("TEST", [pattern])
+    doc = Doc(en_vocab, words=["Hello", "John", "Doe", "!"])
+    # We could also assert length 1 here, but this is more conclusive, because
+    # the real problem here is that it returns a duplicate match for a match_id
+    # that's not actually in the vocab!
+    matches = matcher(doc)
+    assert all([match_id in en_vocab.strings for match_id, start, end in matches])
+
+
+@pytest.mark.issue(1971)
+def test_issue_1971_2(en_vocab):
+    matcher = Matcher(en_vocab)
+    pattern1 = [{"ORTH": "EUR", "LOWER": {"IN": ["eur"]}}, {"LIKE_NUM": True}]
+    pattern2 = [{"LIKE_NUM": True}, {"ORTH": "EUR"}]  # {"IN": ["EUR"]}}]
+    doc = Doc(en_vocab, words=["EUR", "10", "is", "10", "EUR"])
+    matcher.add("TEST1", [pattern1, pattern2])
+    matches = matcher(doc)
+    assert len(matches) == 2
+
+
+@pytest.mark.issue(1971)
+def test_issue_1971_3(en_vocab):
+    """Test that pattern matches correctly for multiple extension attributes."""
+    Token.set_extension("a", default=1, force=True)
+    Token.set_extension("b", default=2, force=True)
+    doc = Doc(en_vocab, words=["hello", "world"])
+    matcher = Matcher(en_vocab)
+    matcher.add("A", [[{"_": {"a": 1}}]])
+    matcher.add("B", [[{"_": {"b": 2}}]])
+    matches = sorted((en_vocab.strings[m_id], s, e) for m_id, s, e in matcher(doc))
+    assert len(matches) == 4
+    assert matches == sorted([("A", 0, 1), ("A", 1, 2), ("B", 0, 1), ("B", 1, 2)])
+
+
+@pytest.mark.issue(1971)
+def test_issue_1971_4(en_vocab):
+    """Test that pattern matches correctly with multiple extension attribute
+    values on a single token.
+    """
+    Token.set_extension("ext_a", default="str_a", force=True)
+    Token.set_extension("ext_b", default="str_b", force=True)
+    matcher = Matcher(en_vocab)
+    doc = Doc(en_vocab, words=["this", "is", "text"])
+    pattern = [{"_": {"ext_a": "str_a", "ext_b": "str_b"}}] * 3
+    matcher.add("TEST", [pattern])
+    matches = matcher(doc)
+    # Uncommenting this caused a segmentation fault
+    assert len(matches) == 1
+    assert matches[0] == (en_vocab.strings["TEST"], 0, 3)
+
+
+@pytest.mark.issue(2464)
+def test_issue2464(en_vocab):
+    """Test problem with successive ?. This is the same bug, so putting it here."""
+    matcher = Matcher(en_vocab)
+    doc = Doc(en_vocab, words=["a", "b"])
+    matcher.add("4", [[{"OP": "?"}, {"OP": "?"}]])
+    matches = matcher(doc)
+    assert len(matches) == 3
+
+
+@pytest.mark.issue(2569)
+def test_issue2569(en_tokenizer):
+    """Test that operator + is greedy."""
+    doc = en_tokenizer("It is May 15, 1993.")
+    doc.ents = [Span(doc, 2, 6, label=doc.vocab.strings["DATE"])]
+    matcher = Matcher(doc.vocab)
+    matcher.add("RULE", [[{"ENT_TYPE": "DATE", "OP": "+"}]])
+    matched = [doc[start:end] for _, start, end in matcher(doc)]
+    matched = sorted(matched, key=len, reverse=True)
+    assert len(matched) == 10
+    assert len(matched[0]) == 4
+    assert matched[0].text == "May 15, 1993"
+
+
+@pytest.mark.issue(2671)
+def test_issue2671():
+    """Ensure the correct entity ID is returned for matches with quantifiers.
+    See also #2675
+    """
+    nlp = English()
+    matcher = Matcher(nlp.vocab)
+    pattern_id = "test_pattern"
+    pattern = [
+        {"LOWER": "high"},
+        {"IS_PUNCT": True, "OP": "?"},
+        {"LOWER": "adrenaline"},
+    ]
+    matcher.add(pattern_id, [pattern])
+    doc1 = nlp("This is a high-adrenaline situation.")
+    doc2 = nlp("This is a high adrenaline situation.")
+    matches1 = matcher(doc1)
+    for match_id, start, end in matches1:
+        assert nlp.vocab.strings[match_id] == pattern_id
+    matches2 = matcher(doc2)
+    for match_id, start, end in matches2:
+        assert nlp.vocab.strings[match_id] == pattern_id
+
+
+@pytest.mark.issue(3009)
+def test_issue3009(en_vocab):
+    """Test problem with matcher quantifiers"""
+    patterns = [
+        [{"ORTH": "has"}, {"LOWER": "to"}, {"LOWER": "do"}, {"TAG": "IN"}],
+        [
+            {"ORTH": "has"},
+            {"IS_ASCII": True, "IS_PUNCT": False, "OP": "*"},
+            {"LOWER": "to"},
+            {"LOWER": "do"},
+            {"TAG": "IN"},
+        ],
+        [
+            {"ORTH": "has"},
+            {"IS_ASCII": True, "IS_PUNCT": False, "OP": "?"},
+            {"LOWER": "to"},
+            {"LOWER": "do"},
+            {"TAG": "IN"},
+        ],
+    ]
+    words = ["also", "has", "to", "do", "with"]
+    tags = ["RB", "VBZ", "TO", "VB", "IN"]
+    pos = ["ADV", "VERB", "ADP", "VERB", "ADP"]
+    doc = Doc(en_vocab, words=words, tags=tags, pos=pos)
+    matcher = Matcher(en_vocab)
+    for i, pattern in enumerate(patterns):
+        matcher.add(str(i), [pattern])
+        matches = matcher(doc)
+        assert matches
+
+
+@pytest.mark.issue(3328)
+def test_issue3328(en_vocab):
+    doc = Doc(en_vocab, words=["Hello", ",", "how", "are", "you", "doing", "?"])
+    matcher = Matcher(en_vocab)
+    patterns = [
+        [{"LOWER": {"IN": ["hello", "how"]}}],
+        [{"LOWER": {"IN": ["you", "doing"]}}],
+    ]
+    matcher.add("TEST", patterns)
+    matches = matcher(doc)
+    assert len(matches) == 4
+    matched_texts = [doc[start:end].text for _, start, end in matches]
+    assert matched_texts == ["Hello", "how", "you", "doing"]
+
+
+@pytest.mark.issue(3549)
+def test_issue3549(en_vocab):
+    """Test that match pattern validation doesn't raise on empty errors."""
+    matcher = Matcher(en_vocab, validate=True)
+    pattern = [{"LOWER": "hello"}, {"LOWER": "world"}]
+    matcher.add("GOOD", [pattern])
+    with pytest.raises(MatchPatternError):
+        matcher.add("BAD", [[{"X": "Y"}]])
+
+
+@pytest.mark.skip("Matching currently only works on strings and integers")
+@pytest.mark.issue(3555)
+def test_issue3555(en_vocab):
+    """Test that custom extensions with default None don't break matcher."""
+    Token.set_extension("issue3555", default=None)
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": "have"}, {"_": {"issue3555": True}}]
+    matcher.add("TEST", [pattern])
+    doc = Doc(en_vocab, words=["have", "apple"])
+    matcher(doc)
+
+
+@pytest.mark.issue(3839)
+def test_issue3839(en_vocab):
+    """Test that match IDs returned by the matcher are correct, are in the string"""
+    doc = Doc(en_vocab, words=["terrific", "group", "of", "people"])
+    matcher = Matcher(en_vocab)
+    match_id = "PATTERN"
+    pattern1 = [{"LOWER": "terrific"}, {"OP": "?"}, {"LOWER": "group"}]
+    pattern2 = [{"LOWER": "terrific"}, {"OP": "?"}, {"OP": "?"}, {"LOWER": "group"}]
+    matcher.add(match_id, [pattern1])
+    matches = matcher(doc)
+    assert matches[0][0] == en_vocab.strings[match_id]
+    matcher = Matcher(en_vocab)
+    matcher.add(match_id, [pattern2])
+    matches = matcher(doc)
+    assert matches[0][0] == en_vocab.strings[match_id]
+
+
+@pytest.mark.issue(3879)
+def test_issue3879(en_vocab):
+    doc = Doc(en_vocab, words=["This", "is", "a", "test", "."])
+    assert len(doc) == 5
+    pattern = [{"ORTH": "This", "OP": "?"}, {"OP": "?"}, {"ORTH": "test"}]
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", [pattern])
+    assert len(matcher(doc)) == 2  # fails because of a FP match 'is a test'
+
+
+@pytest.mark.issue(3951)
+def test_issue3951(en_vocab):
+    """Test that combinations of optional rules are matched correctly."""
+    matcher = Matcher(en_vocab)
+    pattern = [
+        {"LOWER": "hello"},
+        {"LOWER": "this", "OP": "?"},
+        {"OP": "?"},
+        {"LOWER": "world"},
+    ]
+    matcher.add("TEST", [pattern])
+    doc = Doc(en_vocab, words=["Hello", "my", "new", "world"])
+    matches = matcher(doc)
+    assert len(matches) == 0
+
+
+@pytest.mark.issue(4120)
+def test_issue4120(en_vocab):
+    """Test that matches without a final {OP: ?} token are returned."""
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}]])
+    doc1 = Doc(en_vocab, words=["a"])
+    assert len(matcher(doc1)) == 1  # works
+    doc2 = Doc(en_vocab, words=["a", "b", "c"])
+    assert len(matcher(doc2)) == 2  # fixed
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b"}]])
+    doc3 = Doc(en_vocab, words=["a", "b", "b", "c"])
+    assert len(matcher(doc3)) == 2  # works
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b", "OP": "?"}]])
+    doc4 = Doc(en_vocab, words=["a", "b", "b", "c"])
+    assert len(matcher(doc4)) == 3  # fixed
+
+
 @pytest.mark.parametrize(
     "pattern,re_pattern",
     [
diff --git a/spacy/tests/matcher/test_phrase_matcher.py b/spacy/tests/matcher/test_phrase_matcher.py
index 478949601..f893d81f8 100644
--- a/spacy/tests/matcher/test_phrase_matcher.py
+++ b/spacy/tests/matcher/test_phrase_matcher.py
@@ -1,8 +1,125 @@
 import pytest
 import srsly
 from mock import Mock
-from spacy.matcher import PhraseMatcher
+
+from spacy.lang.en import English
+from spacy.matcher import PhraseMatcher, Matcher
 from spacy.tokens import Doc, Span
+from spacy.vocab import Vocab
+
+
+from ..util import make_tempdir
+
+
+@pytest.mark.issue(3248)
+def test_issue3248_1():
+    """Test that the PhraseMatcher correctly reports its number of rules, not
+    total number of patterns."""
+    nlp = English()
+    matcher = PhraseMatcher(nlp.vocab)
+    matcher.add("TEST1", [nlp("a"), nlp("b"), nlp("c")])
+    matcher.add("TEST2", [nlp("d")])
+    assert len(matcher) == 2
+
+
+@pytest.mark.issue(3331)
+def test_issue3331(en_vocab):
+    """Test that duplicate patterns for different rules result in multiple
+    matches, one per rule.
+    """
+    matcher = PhraseMatcher(en_vocab)
+    matcher.add("A", [Doc(en_vocab, words=["Barack", "Obama"])])
+    matcher.add("B", [Doc(en_vocab, words=["Barack", "Obama"])])
+    doc = Doc(en_vocab, words=["Barack", "Obama", "lifts", "America"])
+    matches = matcher(doc)
+    assert len(matches) == 2
+    match_ids = [en_vocab.strings[matches[0][0]], en_vocab.strings[matches[1][0]]]
+    assert sorted(match_ids) == ["A", "B"]
+
+
+@pytest.mark.issue(3972)
+def test_issue3972(en_vocab):
+    """Test that the PhraseMatcher returns duplicates for duplicate match IDs."""
+    matcher = PhraseMatcher(en_vocab)
+    matcher.add("A", [Doc(en_vocab, words=["New", "York"])])
+    matcher.add("B", [Doc(en_vocab, words=["New", "York"])])
+    doc = Doc(en_vocab, words=["I", "live", "in", "New", "York"])
+    matches = matcher(doc)
+
+    assert len(matches) == 2
+
+    # We should have a match for each of the two rules
+    found_ids = [en_vocab.strings[ent_id] for (ent_id, _, _) in matches]
+    assert "A" in found_ids
+    assert "B" in found_ids
+
+
+@pytest.mark.issue(4002)
+def test_issue4002(en_vocab):
+    """Test that the PhraseMatcher can match on overwritten NORM attributes."""
+    matcher = PhraseMatcher(en_vocab, attr="NORM")
+    pattern1 = Doc(en_vocab, words=["c", "d"])
+    assert [t.norm_ for t in pattern1] == ["c", "d"]
+    matcher.add("TEST", [pattern1])
+    doc = Doc(en_vocab, words=["a", "b", "c", "d"])
+    assert [t.norm_ for t in doc] == ["a", "b", "c", "d"]
+    matches = matcher(doc)
+    assert len(matches) == 1
+    matcher = PhraseMatcher(en_vocab, attr="NORM")
+    pattern2 = Doc(en_vocab, words=["1", "2"])
+    pattern2[0].norm_ = "c"
+    pattern2[1].norm_ = "d"
+    assert [t.norm_ for t in pattern2] == ["c", "d"]
+    matcher.add("TEST", [pattern2])
+    matches = matcher(doc)
+    assert len(matches) == 1
+
+
+@pytest.mark.issue(4373)
+def test_issue4373():
+    """Test that PhraseMatcher.vocab can be accessed (like Matcher.vocab)."""
+    matcher = Matcher(Vocab())
+    assert isinstance(matcher.vocab, Vocab)
+    matcher = PhraseMatcher(Vocab())
+    assert isinstance(matcher.vocab, Vocab)
+
+
+@pytest.mark.issue(4651)
+def test_issue4651_with_phrase_matcher_attr():
+    """Test that the EntityRuler PhraseMatcher is deserialized correctly using
+    the method from_disk when the EntityRuler argument phrase_matcher_attr is
+    specified.
+    """
+    text = "Spacy is a python library for nlp"
+    nlp = English()
+    patterns = [{"label": "PYTHON_LIB", "pattern": "spacy", "id": "spaCy"}]
+    ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
+    ruler.add_patterns(patterns)
+    doc = nlp(text)
+    res = [(ent.text, ent.label_, ent.ent_id_) for ent in doc.ents]
+    nlp_reloaded = English()
+    with make_tempdir() as d:
+        file_path = d / "entityruler"
+        ruler.to_disk(file_path)
+        nlp_reloaded.add_pipe("entity_ruler").from_disk(file_path)
+    doc_reloaded = nlp_reloaded(text)
+    res_reloaded = [(ent.text, ent.label_, ent.ent_id_) for ent in doc_reloaded.ents]
+    assert res == res_reloaded
+
+
+@pytest.mark.issue(6839)
+def test_issue6839(en_vocab):
+    """Ensure that PhraseMatcher accepts Span as input"""
+    # fmt: off
+    words = ["I", "like", "Spans", "and", "Docs", "in", "my", "input", ",", "and", "nothing", "else", "."]
+    # fmt: on
+    doc = Doc(en_vocab, words=words)
+    span = doc[:8]
+    pattern = Doc(en_vocab, words=["Spans", "and", "Docs"])
+    matcher = PhraseMatcher(en_vocab)
+    matcher.add("SPACY", [pattern])
+    matches = matcher(span)
+    assert matches
 
 
 def test_matcher_phrase_matcher(en_vocab):
diff --git a/spacy/tests/parser/test_arc_eager_oracle.py b/spacy/tests/parser/test_arc_eager_oracle.py
index cba6fa81e..bb226f9c5 100644
--- a/spacy/tests/parser/test_arc_eager_oracle.py
+++ b/spacy/tests/parser/test_arc_eager_oracle.py
@@ -40,6 +40,28 @@ def arc_eager(vocab):
     return moves
 
 
+@pytest.mark.issue(7056)
+def test_issue7056():
+    """Test that the Unshift transition works properly, and doesn't cause
+    sentence segmentation errors."""
+    vocab = Vocab()
+    ae = ArcEager(
+        vocab.strings, ArcEager.get_actions(left_labels=["amod"], right_labels=["pobj"])
+    )
+    doc = Doc(vocab, words="Severe pain , after trauma".split())
+    state = ae.init_batch([doc])[0]
+    ae.apply_transition(state, "S")
+    ae.apply_transition(state, "L-amod")
+    ae.apply_transition(state, "S")
+    ae.apply_transition(state, "S")
+    ae.apply_transition(state, "S")
+    ae.apply_transition(state, "R-pobj")
+    ae.apply_transition(state, "D")
+    ae.apply_transition(state, "D")
+    ae.apply_transition(state, "D")
+    assert not state.eol()
+
+
 def test_oracle_four_words(arc_eager, vocab):
     words = ["a", "b", "c", "d"]
     heads = [1, 1, 3, 3]
diff --git a/spacy/tests/parser/test_ner.py b/spacy/tests/parser/test_ner.py
index 21094bcb1..b3b29d1f9 100644
--- a/spacy/tests/parser/test_ner.py
+++ b/spacy/tests/parser/test_ner.py
@@ -1,13 +1,16 @@
+import random
+
 import pytest
 from numpy.testing import assert_equal
-from spacy.attrs import ENT_IOB
 
+from spacy.attrs import ENT_IOB
 from spacy import util, registry
 from spacy.lang.en import English
+from spacy.lang.it import Italian
 from spacy.language import Language
 from spacy.lookups import Lookups
 from spacy.pipeline._parser_internals.ner import BiluoPushDown
-from spacy.training import Example
+from spacy.training import Example, iob_to_biluo
 from spacy.tokens import Doc, Span
 from spacy.vocab import Vocab
 import logging
@@ -58,6 +61,152 @@ def tsys(vocab, entity_types):
     return BiluoPushDown(vocab.strings, actions)
 
 
+@pytest.mark.parametrize("label", ["U-JOB-NAME"])
+@pytest.mark.issue(1967)
+def test_issue1967(label):
+    nlp = Language()
+    config = {}
+    ner = nlp.create_pipe("ner", config=config)
+    example = Example.from_dict(
+        Doc(ner.vocab, words=["word"]),
+        {
+            "ids": [0],
+            "words": ["word"],
+            "tags": ["tag"],
+            "heads": [0],
+            "deps": ["dep"],
+            "entities": [label],
+        },
+    )
+    assert "JOB-NAME" in ner.moves.get_actions(examples=[example])[1]
+
+
+@pytest.mark.issue(2179)
+def test_issue2179():
+    """Test that spurious 'extra_labels' aren't created when initializing NER."""
+    nlp = Italian()
+    ner = nlp.add_pipe("ner")
+    ner.add_label("CITIZENSHIP")
+    nlp.initialize()
+    nlp2 = Italian()
+    nlp2.add_pipe("ner")
+    assert len(nlp2.get_pipe("ner").labels) == 0
+    model = nlp2.get_pipe("ner").model
+    model.attrs["resize_output"](model, nlp.get_pipe("ner").moves.n_moves)
+    nlp2.from_bytes(nlp.to_bytes())
+    assert "extra_labels" not in nlp2.get_pipe("ner").cfg
+    assert nlp2.get_pipe("ner").labels == ("CITIZENSHIP",)
+
+
+@pytest.mark.issue(2385)
+def test_issue2385():
+    """Test that IOB tags are correctly converted to BILUO tags."""
+    # fix bug in labels with a 'b' character
+    tags1 = ("B-BRAWLER", "I-BRAWLER", "I-BRAWLER")
+    assert iob_to_biluo(tags1) == ["B-BRAWLER", "I-BRAWLER", "L-BRAWLER"]
+    # maintain support for iob1 format
+    tags2 = ("I-ORG", "I-ORG", "B-ORG")
+    assert iob_to_biluo(tags2) == ["B-ORG", "L-ORG", "U-ORG"]
+    # maintain support for iob2 format
+    tags3 = ("B-PERSON", "I-PERSON", "B-PERSON")
+    assert iob_to_biluo(tags3) == ["B-PERSON", "L-PERSON", "U-PERSON"]
+
+
+@pytest.mark.issue(2800)
+def test_issue2800():
+    """Test issue that arises when too many labels are added to NER model.
+    Used to cause segfault.
+    """
+    nlp = English()
+    train_data = []
+    train_data.extend(
+        [Example.from_dict(nlp.make_doc("One sentence"), {"entities": []})]
+    )
+    entity_types = [str(i) for i in range(1000)]
+    ner = nlp.add_pipe("ner")
+    for entity_type in list(entity_types):
+        ner.add_label(entity_type)
+    optimizer = nlp.initialize()
+    for i in range(20):
+        losses = {}
+        random.shuffle(train_data)
+        for example in train_data:
+            nlp.update([example], sgd=optimizer, losses=losses, drop=0.5)
+
+
+@pytest.mark.issue(3209)
+def test_issue3209():
+    """Test issue that occurred in spaCy nightly where NER labels were being
+    mapped to classes incorrectly after loading the model, when the labels
+    were added using ner.add_label().
+    """
+    nlp = English()
+    ner = nlp.add_pipe("ner")
+    ner.add_label("ANIMAL")
+    nlp.initialize()
+    move_names = ["O", "B-ANIMAL", "I-ANIMAL", "L-ANIMAL", "U-ANIMAL"]
+    assert ner.move_names == move_names
+    nlp2 = English()
+    ner2 = nlp2.add_pipe("ner")
+    model = ner2.model
+    model.attrs["resize_output"](model, ner.moves.n_moves)
+    nlp2.from_bytes(nlp.to_bytes())
+    assert ner2.move_names == move_names
+
+
+@pytest.mark.issue(4267)
+def test_issue4267():
+    """Test that running an entity_ruler after ner gives consistent results"""
+    nlp = English()
+    ner = nlp.add_pipe("ner")
+    ner.add_label("PEOPLE")
+    nlp.initialize()
+    assert "ner" in nlp.pipe_names
+    # assert that we have correct IOB annotations
+    doc1 = nlp("hi")
+    assert doc1.has_annotation("ENT_IOB")
+    for token in doc1:
+        assert token.ent_iob == 2
+    # add entity ruler and run again
+    patterns = [{"label": "SOFTWARE", "pattern": "spacy"}]
+    ruler = nlp.add_pipe("entity_ruler")
+    ruler.add_patterns(patterns)
+    assert "entity_ruler" in nlp.pipe_names
+    assert "ner" in nlp.pipe_names
+    # assert that we still have correct IOB annotations
+    doc2 = nlp("hi")
+    assert doc2.has_annotation("ENT_IOB")
+    for token in doc2:
+        assert token.ent_iob == 2
+
+
+@pytest.mark.issue(4313)
+def test_issue4313():
+    """This should not crash or exit with some strange error code"""
+    beam_width = 16
+    beam_density = 0.0001
+    nlp = English()
+    config = {
+        "beam_width": beam_width,
+        "beam_density": beam_density,
+    }
+    ner = nlp.add_pipe("beam_ner", config=config)
+    ner.add_label("SOME_LABEL")
+    nlp.initialize()
+    # add a new label to the doc
+    doc = nlp("What do you think about Apple ?")
+    assert len(ner.labels) == 1
+    assert "SOME_LABEL" in ner.labels
+    apple_ent = Span(doc, 5, 6, label="MY_ORG")
+    doc.ents = list(doc.ents) + [apple_ent]
+
+    # ensure the beam_parse still works with the new label
+    docs = [doc]
+    ner.beam_parse(docs, drop=0.0, beam_width=beam_width, beam_density=beam_density)
+    assert len(ner.labels) == 2
+    assert "MY_ORG" in ner.labels
+
+
 def test_get_oracle_moves(tsys, doc, entity_annots):
     example = Example.from_dict(doc, {"entities": entity_annots})
     act_classes = tsys.get_oracle_sequence(example, _debug=False)
diff --git a/spacy/tests/parser/test_parse.py b/spacy/tests/parser/test_parse.py
index b7575d063..7bbb30d8e 100644
--- a/spacy/tests/parser/test_parse.py
+++ b/spacy/tests/parser/test_parse.py
@@ -1,15 +1,17 @@
 import pytest
 from numpy.testing import assert_equal
-from spacy.attrs import DEP
+from thinc.api import Adam
 
+from spacy import registry, util
+from spacy.attrs import DEP, NORM
 from spacy.lang.en import English
-from spacy.training import Example
 from spacy.tokens import Doc
-from spacy import util, registry
+from spacy.training import Example
+from spacy.vocab import Vocab
 
-from ..util import apply_transition_sequence, make_tempdir
 from ...pipeline import DependencyParser
 from ...pipeline.dep_parser import DEFAULT_PARSER_MODEL
+from ..util import apply_transition_sequence, make_tempdir
 
 TRAIN_DATA = [
     (
@@ -59,6 +61,94 @@ PARTIAL_DATA = [
 eps = 0.1
 
 
+@pytest.fixture
+def vocab():
+    return Vocab(lex_attr_getters={NORM: lambda s: s})
+
+
+@pytest.fixture
+def parser(vocab):
+    vocab.strings.add("ROOT")
+    cfg = {"model": DEFAULT_PARSER_MODEL}
+    model = registry.resolve(cfg, validate=True)["model"]
+    parser = DependencyParser(vocab, model)
+    parser.cfg["token_vector_width"] = 4
+    parser.cfg["hidden_width"] = 32
+    # parser.add_label('right')
+    parser.add_label("left")
+    parser.initialize(lambda: [_parser_example(parser)])
+    sgd = Adam(0.001)
+
+    for i in range(10):
+        losses = {}
+        doc = Doc(vocab, words=["a", "b", "c", "d"])
+        example = Example.from_dict(
+            doc, {"heads": [1, 1, 3, 3], "deps": ["left", "ROOT", "left", "ROOT"]}
+        )
+        parser.update([example], sgd=sgd, losses=losses)
+    return parser
+
+
+def _parser_example(parser):
+    doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
+    gold = {"heads": [1, 1, 3, 3], "deps": ["right", "ROOT", "left", "ROOT"]}
+    return Example.from_dict(doc, gold)
+
+
+@pytest.mark.issue(2772)
+def test_issue2772(en_vocab):
+    """Test that deprojectivization doesn't mess up sentence boundaries."""
+    # fmt: off
+    words = ["When", "we", "write", "or", "communicate", "virtually", ",", "we", "can", "hide", "our", "true", "feelings", "."]
+    # fmt: on
+    # A tree with a non-projective (i.e. crossing) arc
+    # The arcs (0, 4) and (2, 9) cross.
+    heads = [4, 2, 9, 2, 2, 4, 9, 9, 9, 9, 12, 12, 9, 9]
+    deps = ["dep"] * len(heads)
+    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
+    assert doc[1].is_sent_start is False
+
+
+@pytest.mark.issue(3830)
+def test_issue3830_no_subtok():
+    """Test that the parser doesn't have subtok label if not learn_tokens"""
+    config = {
+        "learn_tokens": False,
+    }
+    model = registry.resolve({"model": DEFAULT_PARSER_MODEL}, validate=True)["model"]
+    parser = DependencyParser(Vocab(), model, **config)
+    parser.add_label("nsubj")
+    assert "subtok" not in parser.labels
+    parser.initialize(lambda: [_parser_example(parser)])
+    assert "subtok" not in parser.labels
+
+
+@pytest.mark.issue(3830)
+def test_issue3830_with_subtok():
+    """Test that the parser does have subtok label if learn_tokens=True."""
+    config = {
+        "learn_tokens": True,
+    }
+    model = registry.resolve({"model": DEFAULT_PARSER_MODEL}, validate=True)["model"]
+    parser = DependencyParser(Vocab(), model, **config)
+    parser.add_label("nsubj")
+    assert "subtok" not in parser.labels
+    parser.initialize(lambda: [_parser_example(parser)])
+    assert "subtok" in parser.labels
+
+
+@pytest.mark.issue(7716)
+@pytest.mark.xfail(reason="Not fixed yet")
+def test_partial_annotation(parser):
+    doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
+    doc[2].is_sent_start = False
+    # Note that if the following line is used, then doc[2].is_sent_start == False
+    # doc[3].is_sent_start = False
+
+    doc = parser(doc)
+    assert doc[2].is_sent_start == False
+
+
 def test_parser_root(en_vocab):
     words = ["i", "do", "n't", "have", "other", "assistance"]
     heads = [3, 3, 3, 3, 5, 3]
diff --git a/spacy/tests/pipeline/test_entity_linker.py b/spacy/tests/pipeline/test_entity_linker.py
index a98d01964..3740e430e 100644
--- a/spacy/tests/pipeline/test_entity_linker.py
+++ b/spacy/tests/pipeline/test_entity_linker.py
@@ -1,18 +1,20 @@
 from typing import Callable, Iterable
+
 import pytest
 from numpy.testing import assert_equal
+
+from spacy import registry, util
 from spacy.attrs import ENT_KB_ID
 from spacy.compat import pickle
-from spacy.kb import KnowledgeBase, get_candidates, Candidate
-from spacy.vocab import Vocab
-
-from spacy import util, registry
+from spacy.kb import Candidate, KnowledgeBase, get_candidates
+from spacy.lang.en import English
 from spacy.ml import load_kb
 from spacy.scorer import Scorer
-from spacy.training import Example
-from spacy.lang.en import English
 from spacy.tests.util import make_tempdir
 from spacy.tokens import Span
+from spacy.training import Example
+from spacy.util import ensure_path
+from spacy.vocab import Vocab
 
 
 @pytest.fixture
@@ -25,6 +27,198 @@ def assert_almost_equal(a, b):
     assert a - delta <= b <= a + delta
 
 
+@pytest.mark.issue(4674)
+def test_issue4674():
+    """Test that setting entities with overlapping identifiers does not mess up IO"""
+    nlp = English()
+    kb = KnowledgeBase(nlp.vocab, entity_vector_length=3)
+    vector1 = [0.9, 1.1, 1.01]
+    vector2 = [1.8, 2.25, 2.01]
+    with pytest.warns(UserWarning):
+        kb.set_entities(
+            entity_list=["Q1", "Q1"],
+            freq_list=[32, 111],
+            vector_list=[vector1, vector2],
+        )
+    assert kb.get_size_entities() == 1
+    # dumping to file & loading back in
+    with make_tempdir() as d:
+        dir_path = ensure_path(d)
+        if not dir_path.exists():
+            dir_path.mkdir()
+        file_path = dir_path / "kb"
+        kb.to_disk(str(file_path))
+        kb2 = KnowledgeBase(nlp.vocab, entity_vector_length=3)
+        kb2.from_disk(str(file_path))
+    assert kb2.get_size_entities() == 1
+
+
+@pytest.mark.issue(6730)
+def test_issue6730(en_vocab):
+    """Ensure that the KB does not accept empty strings, but otherwise IO works fine."""
+    from spacy.kb import KnowledgeBase
+
+    kb = KnowledgeBase(en_vocab, entity_vector_length=3)
+    kb.add_entity(entity="1", freq=148, entity_vector=[1, 2, 3])
+
+    with pytest.raises(ValueError):
+        kb.add_alias(alias="", entities=["1"], probabilities=[0.4])
+    assert kb.contains_alias("") is False
+
+    kb.add_alias(alias="x", entities=["1"], probabilities=[0.2])
+    kb.add_alias(alias="y", entities=["1"], probabilities=[0.1])
+
+    with make_tempdir() as tmp_dir:
+        kb.to_disk(tmp_dir)
+        kb.from_disk(tmp_dir)
+    assert kb.get_size_aliases() == 2
+    assert set(kb.get_alias_strings()) == {"x", "y"}
+
+
+@pytest.mark.issue(7065)
+def test_issue7065():
+    text = "Kathleen Battle sang in Mahler 's Symphony No. 8 at the Cincinnati Symphony Orchestra 's May Festival."
+    nlp = English()
+    nlp.add_pipe("sentencizer")
+    ruler = nlp.add_pipe("entity_ruler")
+    patterns = [
+        {
+            "label": "THING",
+            "pattern": [
+                {"LOWER": "symphony"},
+                {"LOWER": "no"},
+                {"LOWER": "."},
+                {"LOWER": "8"},
+            ],
+        }
+    ]
+    ruler.add_patterns(patterns)
+
+    doc = nlp(text)
+    sentences = [s for s in doc.sents]
+    assert len(sentences) == 2
+    sent0 = sentences[0]
+    ent = doc.ents[0]
+    assert ent.start < sent0.end < ent.end
+    assert sentences.index(ent.sent) == 0
+
+
+@pytest.mark.issue(7065)
+def test_issue7065_b():
+    # Test that the NEL doesn't crash when an entity crosses a sentence boundary
+    nlp = English()
+    vector_length = 3
+    nlp.add_pipe("sentencizer")
+    text = "Mahler 's Symphony No. 8 was beautiful."
+    entities = [(0, 6, "PERSON"), (10, 24, "WORK")]
+    links = {
+        (0, 6): {"Q7304": 1.0, "Q270853": 0.0},
+        (10, 24): {"Q7304": 0.0, "Q270853": 1.0},
+    }
+    sent_starts = [1, -1, 0, 0, 0, 0, 0, 0, 0]
+    doc = nlp(text)
+    example = Example.from_dict(
+        doc, {"entities": entities, "links": links, "sent_starts": sent_starts}
+    )
+    train_examples = [example]
+
+    def create_kb(vocab):
+        # create artificial KB
+        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
+        mykb.add_entity(entity="Q270853", freq=12, entity_vector=[9, 1, -7])
+        mykb.add_alias(
+            alias="No. 8",
+            entities=["Q270853"],
+            probabilities=[1.0],
+        )
+        mykb.add_entity(entity="Q7304", freq=12, entity_vector=[6, -4, 3])
+        mykb.add_alias(
+            alias="Mahler",
+            entities=["Q7304"],
+            probabilities=[1.0],
+        )
+        return mykb
+
+    # Create the Entity Linker component and add it to the pipeline
+    entity_linker = nlp.add_pipe("entity_linker", last=True)
+    entity_linker.set_kb(create_kb)
+    # train the NEL pipe
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    for i in range(2):
+        losses = {}
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
+
+    # Add a custom rule-based component to mimick NER
+    patterns = [
+        {"label": "PERSON", "pattern": [{"LOWER": "mahler"}]},
+        {
+            "label": "WORK",
+            "pattern": [
+                {"LOWER": "symphony"},
+                {"LOWER": "no"},
+                {"LOWER": "."},
+                {"LOWER": "8"},
+            ],
+        },
+    ]
+    ruler = nlp.add_pipe("entity_ruler", before="entity_linker")
+    ruler.add_patterns(patterns)
+    # test the trained model - this should not throw E148
+    doc = nlp(text)
+    assert doc
+
+
+def test_partial_links():
+    # Test that having some entities on the doc without gold links, doesn't crash
+    TRAIN_DATA = [
+        (
+            "Russ Cochran his reprints include EC Comics.",
+            {
+                "links": {(0, 12): {"Q2146908": 1.0}},
+                "entities": [(0, 12, "PERSON")],
+                "sent_starts": [1, -1, 0, 0, 0, 0, 0, 0],
+            },
+        )
+    ]
+    nlp = English()
+    vector_length = 3
+    train_examples = []
+    for text, annotation in TRAIN_DATA:
+        doc = nlp(text)
+        train_examples.append(Example.from_dict(doc, annotation))
+
+    def create_kb(vocab):
+        # create artificial KB
+        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
+        mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3])
+        mykb.add_alias("Russ Cochran", ["Q2146908"], [0.9])
+        return mykb
+
+    # Create and train the Entity Linker
+    entity_linker = nlp.add_pipe("entity_linker", last=True)
+    entity_linker.set_kb(create_kb)
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    for i in range(2):
+        losses = {}
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
+
+    # adding additional components that are required for the entity_linker
+    nlp.add_pipe("sentencizer", first=True)
+    patterns = [
+        {"label": "PERSON", "pattern": [{"LOWER": "russ"}, {"LOWER": "cochran"}]},
+        {"label": "ORG", "pattern": [{"LOWER": "ec"}, {"LOWER": "comics"}]},
+    ]
+    ruler = nlp.add_pipe("entity_ruler", before="entity_linker")
+    ruler.add_patterns(patterns)
+
+    # this will run the pipeline on the examples and shouldn't crash
+    results = nlp.evaluate(train_examples)
+    assert "PERSON" in results["ents_per_type"]
+    assert "PERSON" in results["nel_f_per_type"]
+    assert "ORG" in results["ents_per_type"]
+    assert "ORG" not in results["nel_f_per_type"]
+
+
 def test_kb_valid_entities(nlp):
     """Test the valid construction of a KB with 3 entities and two aliases"""
     mykb = KnowledgeBase(nlp.vocab, entity_vector_length=3)
diff --git a/spacy/tests/pipeline/test_entity_ruler.py b/spacy/tests/pipeline/test_entity_ruler.py
index e66b49518..0cecafff3 100644
--- a/spacy/tests/pipeline/test_entity_ruler.py
+++ b/spacy/tests/pipeline/test_entity_ruler.py
@@ -1,9 +1,11 @@
 import pytest
 
 from spacy import registry
-from spacy.tokens import Span
+from spacy.tokens import Doc, Span
 from spacy.language import Language
-from spacy.pipeline import EntityRuler
+from spacy.lang.en import English
+from spacy.pipeline import EntityRuler, EntityRecognizer, merge_entities
+from spacy.pipeline.ner import DEFAULT_NER_MODEL
 from spacy.errors import MatchPatternError
 from spacy.tests.util import make_tempdir
 
@@ -34,6 +36,117 @@ def add_ent_component(doc):
     return doc
 
 
+@pytest.mark.issue(3345)
+def test_issue3345():
+    """Test case where preset entity crosses sentence boundary."""
+    nlp = English()
+    doc = Doc(nlp.vocab, words=["I", "live", "in", "New", "York"])
+    doc[4].is_sent_start = True
+    ruler = EntityRuler(nlp, patterns=[{"label": "GPE", "pattern": "New York"}])
+    cfg = {"model": DEFAULT_NER_MODEL}
+    model = registry.resolve(cfg, validate=True)["model"]
+    ner = EntityRecognizer(doc.vocab, model)
+    # Add the OUT action. I wouldn't have thought this would be necessary...
+    ner.moves.add_action(5, "")
+    ner.add_label("GPE")
+    doc = ruler(doc)
+    # Get into the state just before "New"
+    state = ner.moves.init_batch([doc])[0]
+    ner.moves.apply_transition(state, "O")
+    ner.moves.apply_transition(state, "O")
+    ner.moves.apply_transition(state, "O")
+    # Check that B-GPE is valid.
+    assert ner.moves.is_valid(state, "B-GPE")
+
+
+@pytest.mark.issue(4849)
+def test_issue4849():
+    nlp = English()
+    patterns = [
+        {"label": "PERSON", "pattern": "joe biden", "id": "joe-biden"},
+        {"label": "PERSON", "pattern": "bernie sanders", "id": "bernie-sanders"},
+    ]
+    ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
+    ruler.add_patterns(patterns)
+    text = """
+    The left is starting to take aim at Democratic front-runner Joe Biden.
+    Sen. Bernie Sanders joined in her criticism: "There is no 'middle ground' when it comes to climate policy."
+    """
+    # USING 1 PROCESS
+    count_ents = 0
+    for doc in nlp.pipe([text], n_process=1):
+        count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
+    assert count_ents == 2
+    # USING 2 PROCESSES
+    if isinstance(get_current_ops, NumpyOps):
+        count_ents = 0
+        for doc in nlp.pipe([text], n_process=2):
+            count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
+        assert count_ents == 2
+
+
+@pytest.mark.issue(5918)
+def test_issue5918():
+    # Test edge case when merging entities.
+    nlp = English()
+    ruler = nlp.add_pipe("entity_ruler")
+    patterns = [
+        {"label": "ORG", "pattern": "Digicon Inc"},
+        {"label": "ORG", "pattern": "Rotan Mosle Inc's"},
+        {"label": "ORG", "pattern": "Rotan Mosle Technology Partners Ltd"},
+    ]
+    ruler.add_patterns(patterns)
+
+    text = """
+        Digicon Inc said it has completed the previously-announced disposition
+        of its computer systems division to an investment group led by
+        Rotan Mosle Inc's Rotan Mosle Technology Partners Ltd affiliate.
+        """
+    doc = nlp(text)
+    assert len(doc.ents) == 3
+    # make it so that the third span's head is within the entity (ent_iob=I)
+    # bug #5918 would wrongly transfer that I to the full entity, resulting in 2 instead of 3 final ents.
+    # TODO: test for logging here
+    # with pytest.warns(UserWarning):
+    #     doc[29].head = doc[33]
+    doc = merge_entities(doc)
+    assert len(doc.ents) == 3
+
+
+@pytest.mark.issue(8168)
+def test_issue8168():
+    nlp = English()
+    ruler = nlp.add_pipe("entity_ruler")
+    patterns = [
+        {"label": "ORG", "pattern": "Apple"},
+        {
+            "label": "GPE",
+            "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}],
+            "id": "san-francisco",
+        },
+        {
+            "label": "GPE",
+            "pattern": [{"LOWER": "san"}, {"LOWER": "fran"}],
+            "id": "san-francisco",
+        },
+    ]
+    ruler.add_patterns(patterns)
+
+    assert ruler._ent_ids == {8043148519967183733: ("GPE", "san-francisco")}
+
+
+@pytest.mark.issue(8216)
+def test_entity_ruler_fix8216(nlp, patterns):
+    """Test that patterns don't get added excessively."""
+    ruler = nlp.add_pipe("entity_ruler", config={"validate": True})
+    ruler.add_patterns(patterns)
+    pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
+    assert pattern_count > 0
+    ruler.add_patterns([])
+    after_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
+    assert after_count == pattern_count
+
+
 def test_entity_ruler_init(nlp, patterns):
     ruler = EntityRuler(nlp, patterns=patterns)
     assert len(ruler) == len(patterns)
diff --git a/spacy/tests/pipeline/test_pipe_factories.py b/spacy/tests/pipeline/test_pipe_factories.py
index 0c2554727..4128e2a48 100644
--- a/spacy/tests/pipeline/test_pipe_factories.py
+++ b/spacy/tests/pipeline/test_pipe_factories.py
@@ -1,4 +1,6 @@
 import pytest
+
+import spacy
 from spacy.language import Language
 from spacy.lang.en import English
 from spacy.lang.de import German
@@ -11,6 +13,37 @@ from pydantic import StrictInt, StrictStr
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(5137)
+def test_issue5137():
+    factory_name = "test_issue5137"
+    pipe_name = "my_component"
+
+    @Language.factory(factory_name)
+    class MyComponent:
+        def __init__(self, nlp, name=pipe_name, categories="all_categories"):
+            self.nlp = nlp
+            self.categories = categories
+            self.name = name
+
+        def __call__(self, doc):
+            pass
+
+        def to_disk(self, path, **kwargs):
+            pass
+
+        def from_disk(self, path, **cfg):
+            pass
+
+    nlp = English()
+    my_component = nlp.add_pipe(factory_name, name=pipe_name)
+    assert my_component.categories == "all_categories"
+    with make_tempdir() as tmpdir:
+        nlp.to_disk(tmpdir)
+        overrides = {"components": {pipe_name: {"categories": "my_categories"}}}
+        nlp2 = spacy.load(tmpdir, config=overrides)
+        assert nlp2.get_pipe(pipe_name).categories == "my_categories"
+
+
 def test_pipe_function_component():
     name = "test_component"
 
diff --git a/spacy/tests/pipeline/test_pipe_methods.py b/spacy/tests/pipeline/test_pipe_methods.py
index 87fd64307..4b8fb8ebc 100644
--- a/spacy/tests/pipeline/test_pipe_methods.py
+++ b/spacy/tests/pipeline/test_pipe_methods.py
@@ -1,9 +1,17 @@
+import gc
+
+import numpy
 import pytest
+from thinc.api import get_current_ops
+
+from spacy.lang.en import English
+from spacy.lang.en.syntax_iterators import noun_chunks
 from spacy.language import Language
 from spacy.pipeline import TrainablePipe
+from spacy.tokens import Doc
 from spacy.training import Example
 from spacy.util import SimpleFrozenList, get_arg_names
-from spacy.lang.en import English
+from spacy.vocab import Vocab
 
 
 @pytest.fixture
@@ -21,6 +29,138 @@ def other_pipe(doc):
     return doc
 
 
+@pytest.mark.issue(1506)
+def test_issue1506():
+    def string_generator():
+        for _ in range(10001):
+            yield "It's sentence produced by that bug."
+        for _ in range(10001):
+            yield "I erase some hbdsaj lemmas."
+        for _ in range(10001):
+            yield "I erase lemmas."
+        for _ in range(10001):
+            yield "It's sentence produced by that bug."
+        for _ in range(10001):
+            yield "It's sentence produced by that bug."
+
+    nlp = English()
+    for i, d in enumerate(nlp.pipe(string_generator())):
+        # We should run cleanup more than one time to actually cleanup data.
+        # In first run — clean up only mark strings as «not hitted».
+        if i == 10000 or i == 20000 or i == 30000:
+            gc.collect()
+        for t in d:
+            str(t.lemma_)
+
+
+@pytest.mark.issue(1654)
+def test_issue1654():
+    nlp = Language(Vocab())
+    assert not nlp.pipeline
+
+    @Language.component("component")
+    def component(doc):
+        return doc
+
+    nlp.add_pipe("component", name="1")
+    nlp.add_pipe("component", name="2", after="1")
+    nlp.add_pipe("component", name="3", after="2")
+    assert nlp.pipe_names == ["1", "2", "3"]
+    nlp2 = Language(Vocab())
+    assert not nlp2.pipeline
+    nlp2.add_pipe("component", name="3")
+    nlp2.add_pipe("component", name="2", before="3")
+    nlp2.add_pipe("component", name="1", before="2")
+    assert nlp2.pipe_names == ["1", "2", "3"]
+
+
+@pytest.mark.issue(3880)
+def test_issue3880():
+    """Test that `nlp.pipe()` works when an empty string ends the batch.
+
+    Fixed in v7.0.5 of Thinc.
+    """
+    texts = ["hello", "world", "", ""]
+    nlp = English()
+    nlp.add_pipe("parser").add_label("dep")
+    nlp.add_pipe("ner").add_label("PERSON")
+    nlp.add_pipe("tagger").add_label("NN")
+    nlp.initialize()
+    for doc in nlp.pipe(texts):
+        pass
+
+
+@pytest.mark.issue(5082)
+def test_issue5082():
+    # Ensure the 'merge_entities' pipeline does something sensible for the vectors of the merged tokens
+    nlp = English()
+    vocab = nlp.vocab
+    array1 = numpy.asarray([0.1, 0.5, 0.8], dtype=numpy.float32)
+    array2 = numpy.asarray([-0.2, -0.6, -0.9], dtype=numpy.float32)
+    array3 = numpy.asarray([0.3, -0.1, 0.7], dtype=numpy.float32)
+    array4 = numpy.asarray([0.5, 0, 0.3], dtype=numpy.float32)
+    array34 = numpy.asarray([0.4, -0.05, 0.5], dtype=numpy.float32)
+    vocab.set_vector("I", array1)
+    vocab.set_vector("like", array2)
+    vocab.set_vector("David", array3)
+    vocab.set_vector("Bowie", array4)
+    text = "I like David Bowie"
+    patterns = [
+        {"label": "PERSON", "pattern": [{"LOWER": "david"}, {"LOWER": "bowie"}]}
+    ]
+    ruler = nlp.add_pipe("entity_ruler")
+    ruler.add_patterns(patterns)
+    parsed_vectors_1 = [t.vector for t in nlp(text)]
+    assert len(parsed_vectors_1) == 4
+    ops = get_current_ops()
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[0]), array1)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[1]), array2)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[2]), array3)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[3]), array4)
+    nlp.add_pipe("merge_entities")
+    parsed_vectors_2 = [t.vector for t in nlp(text)]
+    assert len(parsed_vectors_2) == 3
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[0]), array1)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[1]), array2)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[2]), array34)
+
+
+@pytest.mark.issue(5458)
+def test_issue5458():
+    # Test that the noun chuncker does not generate overlapping spans
+    # fmt: off
+    words = ["In", "an", "era", "where", "markets", "have", "brought", "prosperity", "and", "empowerment", "."]
+    vocab = Vocab(strings=words)
+    deps = ["ROOT", "det", "pobj", "advmod", "nsubj", "aux", "relcl", "dobj", "cc", "conj", "punct"]
+    pos = ["ADP", "DET", "NOUN", "ADV", "NOUN", "AUX", "VERB", "NOUN", "CCONJ", "NOUN", "PUNCT"]
+    heads = [0, 2, 0, 9, 6, 6, 2, 6, 7, 7, 0]
+    # fmt: on
+    en_doc = Doc(vocab, words=words, pos=pos, heads=heads, deps=deps)
+    en_doc.noun_chunks_iterator = noun_chunks
+
+    # if there are overlapping spans, this will fail with an E102 error "Can't merge non-disjoint spans"
+    nlp = English()
+    merge_nps = nlp.create_pipe("merge_noun_chunks")
+    merge_nps(en_doc)
+
+
+def test_multiple_predictions():
+    class DummyPipe(TrainablePipe):
+        def __init__(self):
+            self.model = "dummy_model"
+
+        def predict(self, docs):
+            return ([1, 2, 3], [4, 5, 6])
+
+        def set_annotations(self, docs, scores):
+            return docs
+
+    nlp = Language()
+    doc = nlp.make_doc("foo")
+    dummy_pipe = DummyPipe()
+    dummy_pipe(doc)
+
+
 def test_add_pipe_no_name(nlp):
     nlp.add_pipe("new_pipe")
     assert "new_pipe" in nlp.pipe_names
diff --git a/spacy/tests/pipeline/test_tagger.py b/spacy/tests/pipeline/test_tagger.py
index ec14b70da..96e75851e 100644
--- a/spacy/tests/pipeline/test_tagger.py
+++ b/spacy/tests/pipeline/test_tagger.py
@@ -6,10 +6,27 @@ from spacy import util
 from spacy.training import Example
 from spacy.lang.en import English
 from spacy.language import Language
+from thinc.api import compounding
 
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(4348)
+def test_issue4348():
+    """Test that training the tagger with empty data, doesn't throw errors"""
+    nlp = English()
+    example = Example.from_dict(nlp.make_doc(""), {"tags": []})
+    TRAIN_DATA = [example, example]
+    tagger = nlp.add_pipe("tagger")
+    tagger.add_label("A")
+    optimizer = nlp.initialize()
+    for i in range(5):
+        losses = {}
+        batches = util.minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
+        for batch in batches:
+            nlp.update(batch, sgd=optimizer, losses=losses)
+
+
 def test_label_types():
     nlp = Language()
     tagger = nlp.add_pipe("tagger")
diff --git a/spacy/tests/pipeline/test_textcat.py b/spacy/tests/pipeline/test_textcat.py
index b134b8508..282789f2b 100644
--- a/spacy/tests/pipeline/test_textcat.py
+++ b/spacy/tests/pipeline/test_textcat.py
@@ -1,20 +1,31 @@
-import pytest
 import random
+
 import numpy.random
+import pytest
 from numpy.testing import assert_almost_equal
-from thinc.api import fix_random_seed
+from thinc.api import Config, compounding, fix_random_seed, get_current_ops
+from wasabi import msg
+
+import spacy
 from spacy import util
+from spacy.cli.evaluate import print_prf_per_type, print_textcats_auc_per_cat
 from spacy.lang.en import English
 from spacy.language import Language
 from spacy.pipeline import TextCategorizer
-from spacy.tokens import Doc
+from spacy.pipeline.textcat import single_label_bow_config
+from spacy.pipeline.textcat import single_label_cnn_config
+from spacy.pipeline.textcat import single_label_default_config
+from spacy.pipeline.textcat_multilabel import multi_label_bow_config
+from spacy.pipeline.textcat_multilabel import multi_label_cnn_config
+from spacy.pipeline.textcat_multilabel import multi_label_default_config
 from spacy.pipeline.tok2vec import DEFAULT_TOK2VEC_MODEL
 from spacy.scorer import Scorer
+from spacy.tokens import Doc, DocBin
 from spacy.training import Example
+from spacy.training.initialize import init_nlp
 
 from ..util import make_tempdir
 
-
 TRAIN_DATA_SINGLE_LABEL = [
     ("I'm so happy.", {"cats": {"POSITIVE": 1.0, "NEGATIVE": 0.0}}),
     ("I'm so angry", {"cats": {"POSITIVE": 0.0, "NEGATIVE": 1.0}}),
@@ -48,6 +59,224 @@ def make_get_examples_multi_label(nlp):
     return get_examples
 
 
+@pytest.mark.issue(3611)
+def test_issue3611():
+    """Test whether adding n-grams in the textcat works even when n > token length of some docs"""
+    unique_classes = ["offensive", "inoffensive"]
+    x_train = [
+        "This is an offensive text",
+        "This is the second offensive text",
+        "inoff",
+    ]
+    y_train = ["offensive", "offensive", "inoffensive"]
+    nlp = spacy.blank("en")
+    # preparing the data
+    train_data = []
+    for text, train_instance in zip(x_train, y_train):
+        cat_dict = {label: label == train_instance for label in unique_classes}
+        train_data.append(Example.from_dict(nlp.make_doc(text), {"cats": cat_dict}))
+    # add a text categorizer component
+    model = {
+        "@architectures": "spacy.TextCatBOW.v1",
+        "exclusive_classes": True,
+        "ngram_size": 2,
+        "no_output_layer": False,
+    }
+    textcat = nlp.add_pipe("textcat", config={"model": model}, last=True)
+    for label in unique_classes:
+        textcat.add_label(label)
+    # training the network
+    with nlp.select_pipes(enable="textcat"):
+        optimizer = nlp.initialize()
+        for i in range(3):
+            losses = {}
+            batches = util.minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
+
+            for batch in batches:
+                nlp.update(examples=batch, sgd=optimizer, drop=0.1, losses=losses)
+
+
+@pytest.mark.issue(4030)
+def test_issue4030():
+    """Test whether textcat works fine with empty doc"""
+    unique_classes = ["offensive", "inoffensive"]
+    x_train = [
+        "This is an offensive text",
+        "This is the second offensive text",
+        "inoff",
+    ]
+    y_train = ["offensive", "offensive", "inoffensive"]
+    nlp = spacy.blank("en")
+    # preparing the data
+    train_data = []
+    for text, train_instance in zip(x_train, y_train):
+        cat_dict = {label: label == train_instance for label in unique_classes}
+        train_data.append(Example.from_dict(nlp.make_doc(text), {"cats": cat_dict}))
+    # add a text categorizer component
+    model = {
+        "@architectures": "spacy.TextCatBOW.v1",
+        "exclusive_classes": True,
+        "ngram_size": 2,
+        "no_output_layer": False,
+    }
+    textcat = nlp.add_pipe("textcat", config={"model": model}, last=True)
+    for label in unique_classes:
+        textcat.add_label(label)
+    # training the network
+    with nlp.select_pipes(enable="textcat"):
+        optimizer = nlp.initialize()
+        for i in range(3):
+            losses = {}
+            batches = util.minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
+
+            for batch in batches:
+                nlp.update(examples=batch, sgd=optimizer, drop=0.1, losses=losses)
+    # processing of an empty doc should result in 0.0 for all categories
+    doc = nlp("")
+    assert doc.cats["offensive"] == 0.0
+    assert doc.cats["inoffensive"] == 0.0
+
+
+@pytest.mark.parametrize(
+    "textcat_config",
+    [
+        single_label_default_config,
+        single_label_bow_config,
+        single_label_cnn_config,
+        multi_label_default_config,
+        multi_label_bow_config,
+        multi_label_cnn_config,
+    ],
+)
+@pytest.mark.issue(5551)
+def test_issue5551(textcat_config):
+    """Test that after fixing the random seed, the results of the pipeline are truly identical"""
+    component = "textcat"
+
+    pipe_cfg = Config().from_str(textcat_config)
+    results = []
+    for i in range(3):
+        fix_random_seed(0)
+        nlp = English()
+        text = "Once hot, form ping-pong-ball-sized balls of the mixture, each weighing roughly 25 g."
+        annots = {"cats": {"Labe1": 1.0, "Label2": 0.0, "Label3": 0.0}}
+        pipe = nlp.add_pipe(component, config=pipe_cfg, last=True)
+        for label in set(annots["cats"]):
+            pipe.add_label(label)
+        # Train
+        nlp.initialize()
+        doc = nlp.make_doc(text)
+        nlp.update([Example.from_dict(doc, annots)])
+        # Store the result of each iteration
+        result = pipe.model.predict([doc])
+        results.append(result[0])
+    # All results should be the same because of the fixed seed
+    assert len(results) == 3
+    ops = get_current_ops()
+    assert_almost_equal(ops.to_numpy(results[0]), ops.to_numpy(results[1]), decimal=5)
+    assert_almost_equal(ops.to_numpy(results[0]), ops.to_numpy(results[2]), decimal=5)
+
+
+CONFIG_ISSUE_6908 = """
+[paths]
+train = "TRAIN_PLACEHOLDER"
+raw = null
+init_tok2vec = null
+vectors = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "en"
+pipeline = ["textcat"]
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 1000
+
+[components]
+
+[components.textcat]
+factory = "TEXTCAT_PLACEHOLDER"
+
+[corpora]
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths:train}
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths:train}
+
+
+[training]
+train_corpus = "corpora.train"
+dev_corpus = "corpora.dev"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+frozen_components = []
+before_to_disk = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.components.textcat]
+labels = ['label1', 'label2']
+
+[initialize.tokenizer]
+"""
+
+
+@pytest.mark.parametrize(
+    "component_name",
+    ["textcat", "textcat_multilabel"],
+)
+@pytest.mark.issue(6908)
+def test_issue6908(component_name):
+    """Test intializing textcat with labels in a list"""
+
+    def create_data(out_file):
+        nlp = spacy.blank("en")
+        doc = nlp.make_doc("Some text")
+        doc.cats = {"label1": 0, "label2": 1}
+        out_data = DocBin(docs=[doc]).to_bytes()
+        with out_file.open("wb") as file_:
+            file_.write(out_data)
+
+    with make_tempdir() as tmp_path:
+        train_path = tmp_path / "train.spacy"
+        create_data(train_path)
+        config_str = CONFIG_ISSUE_6908.replace("TEXTCAT_PLACEHOLDER", component_name)
+        config_str = config_str.replace("TRAIN_PLACEHOLDER", train_path.as_posix())
+        config = util.load_config_from_str(config_str)
+        init_nlp(config)
+
+
+@pytest.mark.issue(7019)
+def test_issue7019():
+    scores = {"LABEL_A": 0.39829102, "LABEL_B": 0.938298329382, "LABEL_C": None}
+    print_textcats_auc_per_cat(msg, scores)
+    scores = {
+        "LABEL_A": {"p": 0.3420302, "r": 0.3929020, "f": 0.49823928932},
+        "LABEL_B": {"p": None, "r": None, "f": None},
+    }
+    print_prf_per_type(msg, scores, name="foo", type="bar")
+
+
 @pytest.mark.skip(reason="Test is flakey when run with others")
 def test_simple_train():
     nlp = Language()
diff --git a/spacy/tests/regression/__init__.py b/spacy/tests/regression/__init__.py
deleted file mode 100644
index e69de29bb..000000000
diff --git a/spacy/tests/regression/test_issue1-1000.py b/spacy/tests/regression/test_issue1-1000.py
deleted file mode 100644
index 4846d2075..000000000
--- a/spacy/tests/regression/test_issue1-1000.py
+++ /dev/null
@@ -1,486 +0,0 @@
-import pytest
-import random
-from spacy import util
-from spacy.training import Example
-from spacy.matcher import Matcher
-from spacy.attrs import IS_PUNCT, ORTH, LOWER
-from spacy.vocab import Vocab
-from spacy.lang.en import English
-from spacy.lookups import Lookups
-from spacy.tokens import Doc, Span
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(118)
-@pytest.mark.parametrize(
-    "patterns",
-    [
-        [[{"LOWER": "celtics"}], [{"LOWER": "boston"}, {"LOWER": "celtics"}]],
-        [[{"LOWER": "boston"}, {"LOWER": "celtics"}], [{"LOWER": "celtics"}]],
-    ],
-)
-def test_issue118(en_tokenizer, patterns):
-    """Test a bug that arose from having overlapping matches"""
-    text = (
-        "how many points did lebron james score against the boston celtics last night"
-    )
-    doc = en_tokenizer(text)
-    ORG = doc.vocab.strings["ORG"]
-    matcher = Matcher(doc.vocab)
-    matcher.add("BostonCeltics", patterns)
-    assert len(list(doc.ents)) == 0
-    matches = [(ORG, start, end) for _, start, end in matcher(doc)]
-    assert matches == [(ORG, 9, 11), (ORG, 10, 11)]
-    doc.ents = matches[:1]
-    ents = list(doc.ents)
-    assert len(ents) == 1
-    assert ents[0].label == ORG
-    assert ents[0].start == 9
-    assert ents[0].end == 11
-
-
-@pytest.mark.issue(118)
-@pytest.mark.parametrize(
-    "patterns",
-    [
-        [[{"LOWER": "boston"}], [{"LOWER": "boston"}, {"LOWER": "celtics"}]],
-        [[{"LOWER": "boston"}, {"LOWER": "celtics"}], [{"LOWER": "boston"}]],
-    ],
-)
-def test_issue118_prefix_reorder(en_tokenizer, patterns):
-    """Test a bug that arose from having overlapping matches"""
-    text = (
-        "how many points did lebron james score against the boston celtics last night"
-    )
-    doc = en_tokenizer(text)
-    ORG = doc.vocab.strings["ORG"]
-    matcher = Matcher(doc.vocab)
-    matcher.add("BostonCeltics", patterns)
-    assert len(list(doc.ents)) == 0
-    matches = [(ORG, start, end) for _, start, end in matcher(doc)]
-    doc.ents += tuple(matches)[1:]
-    assert matches == [(ORG, 9, 10), (ORG, 9, 11)]
-    ents = doc.ents
-    assert len(ents) == 1
-    assert ents[0].label == ORG
-    assert ents[0].start == 9
-    assert ents[0].end == 11
-
-
-@pytest.mark.issue(242)
-def test_issue242(en_tokenizer):
-    """Test overlapping multi-word phrases."""
-    text = "There are different food safety standards in different countries."
-    patterns = [
-        [{"LOWER": "food"}, {"LOWER": "safety"}],
-        [{"LOWER": "safety"}, {"LOWER": "standards"}],
-    ]
-    doc = en_tokenizer(text)
-    matcher = Matcher(doc.vocab)
-    matcher.add("FOOD", patterns)
-    matches = [(ent_type, start, end) for ent_type, start, end in matcher(doc)]
-    match1, match2 = matches
-    assert match1[1] == 3
-    assert match1[2] == 5
-    assert match2[1] == 4
-    assert match2[2] == 6
-    with pytest.raises(ValueError):
-        # One token can only be part of one entity, so test that the matches
-        # can't be added as entities
-        doc.ents += tuple(matches)
-
-
-@pytest.mark.issue(309)
-def test_issue309(en_vocab):
-    """Test Issue #309: SBD fails on empty string"""
-    doc = Doc(en_vocab, words=[" "], heads=[0], deps=["ROOT"])
-    assert len(doc) == 1
-    sents = list(doc.sents)
-    assert len(sents) == 1
-
-
-@pytest.mark.issue(351)
-def test_issue351(en_tokenizer):
-    doc = en_tokenizer("   This is a cat.")
-    assert doc[0].idx == 0
-    assert len(doc[0]) == 3
-    assert doc[1].idx == 3
-
-
-@pytest.mark.issue(360)
-def test_issue360(en_tokenizer):
-    """Test tokenization of big ellipsis"""
-    tokens = en_tokenizer("$45...............Asking")
-    assert len(tokens) > 2
-
-
-@pytest.mark.issue(361)
-@pytest.mark.parametrize("text1,text2", [("cat", "dog")])
-def test_issue361(en_vocab, text1, text2):
-    """Test Issue #361: Equality of lexemes"""
-    assert en_vocab[text1] == en_vocab[text1]
-    assert en_vocab[text1] != en_vocab[text2]
-
-
-@pytest.mark.issue(587)
-def test_issue587(en_tokenizer):
-    """Test that Matcher doesn't segfault on particular input"""
-    doc = en_tokenizer("a b; c")
-    matcher = Matcher(doc.vocab)
-    matcher.add("TEST1", [[{ORTH: "a"}, {ORTH: "b"}]])
-    matches = matcher(doc)
-    assert len(matches) == 1
-    matcher.add("TEST2", [[{ORTH: "a"}, {ORTH: "b"}, {IS_PUNCT: True}, {ORTH: "c"}]])
-    matches = matcher(doc)
-    assert len(matches) == 2
-    matcher.add("TEST3", [[{ORTH: "a"}, {ORTH: "b"}, {IS_PUNCT: True}, {ORTH: "d"}]])
-    matches = matcher(doc)
-    assert len(matches) == 2
-
-
-@pytest.mark.issue(588)
-def test_issue588(en_vocab):
-    matcher = Matcher(en_vocab)
-    with pytest.raises(ValueError):
-        matcher.add("TEST", [[]])
-
-
-@pytest.mark.issue(590)
-def test_issue590(en_vocab):
-    """Test overlapping matches"""
-    doc = Doc(en_vocab, words=["n", "=", "1", ";", "a", ":", "5", "%"])
-    matcher = Matcher(en_vocab)
-    matcher.add(
-        "ab", [[{"IS_ALPHA": True}, {"ORTH": ":"}, {"LIKE_NUM": True}, {"ORTH": "%"}]]
-    )
-    matcher.add("ab", [[{"IS_ALPHA": True}, {"ORTH": "="}, {"LIKE_NUM": True}]])
-    matches = matcher(doc)
-    assert len(matches) == 2
-
-
-@pytest.mark.issue(595)
-@pytest.mark.skip(reason="Old vocab-based lemmatization")
-def test_issue595():
-    """Test lemmatization of base forms"""
-    words = ["Do", "n't", "feed", "the", "dog"]
-    lookups = Lookups()
-    lookups.add_table("lemma_rules", {"verb": [["ed", "e"]]})
-    lookups.add_table("lemma_index", {"verb": {}})
-    lookups.add_table("lemma_exc", {"verb": {}})
-    vocab = Vocab()
-    doc = Doc(vocab, words=words)
-    doc[2].tag_ = "VB"
-    assert doc[2].text == "feed"
-    assert doc[2].lemma_ == "feed"
-
-
-@pytest.mark.issue(599)
-def test_issue599(en_vocab):
-    doc = Doc(en_vocab)
-    doc2 = Doc(doc.vocab)
-    doc2.from_bytes(doc.to_bytes())
-    assert doc2.has_annotation("DEP")
-
-
-@pytest.mark.issue(600)
-def test_issue600():
-    vocab = Vocab(tag_map={"NN": {"pos": "NOUN"}})
-    doc = Doc(vocab, words=["hello"])
-    doc[0].tag_ = "NN"
-
-
-@pytest.mark.issue(615)
-def test_issue615(en_tokenizer):
-    def merge_phrases(matcher, doc, i, matches):
-        """Merge a phrase. We have to be careful here because we'll change the
-        token indices. To avoid problems, merge all the phrases once we're called
-        on the last match."""
-        if i != len(matches) - 1:
-            return None
-        spans = [Span(doc, start, end, label=label) for label, start, end in matches]
-        with doc.retokenize() as retokenizer:
-            for span in spans:
-                tag = "NNP" if span.label_ else span.root.tag_
-                attrs = {"tag": tag, "lemma": span.text}
-                retokenizer.merge(span, attrs=attrs)
-                doc.ents = doc.ents + (span,)
-
-    text = "The golf club is broken"
-    pattern = [{"ORTH": "golf"}, {"ORTH": "club"}]
-    label = "Sport_Equipment"
-    doc = en_tokenizer(text)
-    matcher = Matcher(doc.vocab)
-    matcher.add(label, [pattern], on_match=merge_phrases)
-    matcher(doc)
-    entities = list(doc.ents)
-    assert entities != []
-    assert entities[0].label != 0
-
-
-@pytest.mark.issue(736)
-@pytest.mark.parametrize("text,number", [("7am", "7"), ("11p.m.", "11")])
-def test_issue736(en_tokenizer, text, number):
-    """Test that times like "7am" are tokenized correctly and that numbers are
-    converted to string."""
-    tokens = en_tokenizer(text)
-    assert len(tokens) == 2
-    assert tokens[0].text == number
-
-
-@pytest.mark.issue(740)
-@pytest.mark.parametrize("text", ["3/4/2012", "01/12/1900"])
-def test_issue740(en_tokenizer, text):
-    """Test that dates are not split and kept as one token. This behaviour is
-    currently inconsistent, since dates separated by hyphens are still split.
-    This will be hard to prevent without causing clashes with numeric ranges."""
-    tokens = en_tokenizer(text)
-    assert len(tokens) == 1
-
-
-@pytest.mark.issue(743)
-def test_issue743():
-    doc = Doc(Vocab(), ["hello", "world"])
-    token = doc[0]
-    s = set([token])
-    items = list(s)
-    assert items[0] is token
-
-
-@pytest.mark.issue(744)
-@pytest.mark.parametrize("text", ["We were scared", "We Were Scared"])
-def test_issue744(en_tokenizer, text):
-    """Test that 'were' and 'Were' are excluded from the contractions
-    generated by the English tokenizer exceptions."""
-    tokens = en_tokenizer(text)
-    assert len(tokens) == 3
-    assert tokens[1].text.lower() == "were"
-
-
-@pytest.mark.issue(759)
-@pytest.mark.parametrize(
-    "text,is_num", [("one", True), ("ten", True), ("teneleven", False)]
-)
-def test_issue759(en_tokenizer, text, is_num):
-    tokens = en_tokenizer(text)
-    assert tokens[0].like_num == is_num
-
-
-@pytest.mark.issue(775)
-@pytest.mark.parametrize("text", ["Shell", "shell", "Shed", "shed"])
-def test_issue775(en_tokenizer, text):
-    """Test that 'Shell' and 'shell' are excluded from the contractions
-    generated by the English tokenizer exceptions."""
-    tokens = en_tokenizer(text)
-    assert len(tokens) == 1
-    assert tokens[0].text == text
-
-
-@pytest.mark.issue(792)
-@pytest.mark.parametrize("text", ["This is a string ", "This is a string\u0020"])
-def test_issue792(en_tokenizer, text):
-    """Test for Issue #792: Trailing whitespace is removed after tokenization."""
-    doc = en_tokenizer(text)
-    assert "".join([token.text_with_ws for token in doc]) == text
-
-
-@pytest.mark.issue(792)
-@pytest.mark.parametrize("text", ["This is a string", "This is a string\n"])
-def test_control_issue792(en_tokenizer, text):
-    """Test base case for Issue #792: Non-trailing whitespace"""
-    doc = en_tokenizer(text)
-    assert "".join([token.text_with_ws for token in doc]) == text
-
-
-@pytest.mark.issue(801)
-@pytest.mark.skip(
-    reason="Can not be fixed unless with variable-width lookbehinds, cf. PR #3218"
-)
-@pytest.mark.parametrize(
-    "text,tokens",
-    [
-        ('"deserve,"--and', ['"', "deserve", ',"--', "and"]),
-        ("exception;--exclusive", ["exception", ";--", "exclusive"]),
-        ("day.--Is", ["day", ".--", "Is"]),
-        ("refinement:--just", ["refinement", ":--", "just"]),
-        ("memories?--To", ["memories", "?--", "To"]),
-        ("Useful.=--Therefore", ["Useful", ".=--", "Therefore"]),
-        ("=Hope.=--Pandora", ["=", "Hope", ".=--", "Pandora"]),
-    ],
-)
-def test_issue801(en_tokenizer, text, tokens):
-    """Test that special characters + hyphens are split correctly."""
-    doc = en_tokenizer(text)
-    assert len(doc) == len(tokens)
-    assert [t.text for t in doc] == tokens
-
-
-@pytest.mark.issue(805)
-@pytest.mark.parametrize(
-    "text,expected_tokens",
-    [
-        (
-            "Smörsåsen används bl.a. till fisk",
-            ["Smörsåsen", "används", "bl.a.", "till", "fisk"],
-        ),
-        (
-            "Jag kommer först kl. 13 p.g.a. diverse förseningar",
-            ["Jag", "kommer", "först", "kl.", "13", "p.g.a.", "diverse", "förseningar"],
-        ),
-    ],
-)
-def test_issue805(sv_tokenizer, text, expected_tokens):
-    tokens = sv_tokenizer(text)
-    token_list = [token.text for token in tokens if not token.is_space]
-    assert expected_tokens == token_list
-
-
-@pytest.mark.issue(850)
-def test_issue850():
-    """The variable-length pattern matches the succeeding token. Check we
-    handle the ambiguity correctly."""
-    vocab = Vocab(lex_attr_getters={LOWER: lambda string: string.lower()})
-    matcher = Matcher(vocab)
-    pattern = [{"LOWER": "bob"}, {"OP": "*"}, {"LOWER": "frank"}]
-    matcher.add("FarAway", [pattern])
-    doc = Doc(matcher.vocab, words=["bob", "and", "and", "frank"])
-    match = matcher(doc)
-    assert len(match) == 1
-    ent_id, start, end = match[0]
-    assert start == 0
-    assert end == 4
-
-
-@pytest.mark.issue(850)
-def test_issue850_basic():
-    """Test Matcher matches with '*' operator and Boolean flag"""
-    vocab = Vocab(lex_attr_getters={LOWER: lambda string: string.lower()})
-    matcher = Matcher(vocab)
-    pattern = [{"LOWER": "bob"}, {"OP": "*", "LOWER": "and"}, {"LOWER": "frank"}]
-    matcher.add("FarAway", [pattern])
-    doc = Doc(matcher.vocab, words=["bob", "and", "and", "frank"])
-    match = matcher(doc)
-    assert len(match) == 1
-    ent_id, start, end = match[0]
-    assert start == 0
-    assert end == 4
-
-
-@pytest.mark.issue(852)
-@pytest.mark.skip(
-    reason="French exception list is not enabled in the default tokenizer anymore"
-)
-@pytest.mark.parametrize(
-    "text", ["au-delàs", "pair-programmâmes", "terra-formées", "σ-compacts"]
-)
-def test_issue852(fr_tokenizer, text):
-    """Test that French tokenizer exceptions are imported correctly."""
-    tokens = fr_tokenizer(text)
-    assert len(tokens) == 1
-
-
-@pytest.mark.issue(859)
-@pytest.mark.parametrize(
-    "text", ["aaabbb@ccc.com\nThank you!", "aaabbb@ccc.com \nThank you!"]
-)
-def test_issue859(en_tokenizer, text):
-    """Test that no extra space is added in doc.text method."""
-    doc = en_tokenizer(text)
-    assert doc.text == text
-
-
-@pytest.mark.issue(886)
-@pytest.mark.parametrize("text", ["Datum:2014-06-02\nDokument:76467"])
-def test_issue886(en_tokenizer, text):
-    """Test that token.idx matches the original text index for texts with newlines."""
-    doc = en_tokenizer(text)
-    for token in doc:
-        assert len(token.text) == len(token.text_with_ws)
-        assert text[token.idx] == token.text[0]
-
-
-@pytest.mark.issue(891)
-@pytest.mark.parametrize("text", ["want/need"])
-def test_issue891(en_tokenizer, text):
-    """Test that / infixes are split correctly."""
-    tokens = en_tokenizer(text)
-    assert len(tokens) == 3
-    assert tokens[1].text == "/"
-
-
-@pytest.mark.issue(912)
-@pytest.mark.skip(reason="Old vocab-based lemmatization")
-@pytest.mark.parametrize(
-    "text,tag,lemma",
-    [("anus", "NN", "anus"), ("princess", "NN", "princess"), ("inner", "JJ", "inner")],
-)
-def test_issue912(en_vocab, text, tag, lemma):
-    """Test base-forms are preserved."""
-    doc = Doc(en_vocab, words=[text])
-    doc[0].tag_ = tag
-    assert doc[0].lemma_ == lemma
-
-
-@pytest.mark.issue(957)
-@pytest.mark.slow
-def test_issue957(en_tokenizer):
-    """Test that spaCy doesn't hang on many punctuation characters.
-    If this test hangs, check (new) regular expressions for conflicting greedy operators
-    """
-    # Skip test if pytest-timeout is not installed
-    pytest.importorskip("pytest_timeout")
-    for punct in [".", ",", "'", '"', ":", "?", "!", ";", "-"]:
-        string = "0"
-        for i in range(1, 100):
-            string += punct + str(i)
-        doc = en_tokenizer(string)
-        assert doc
-
-
-@pytest.mark.issue(999)
-def test_issue999():
-    """Test that adding entities and resuming training works passably OK.
-    There are two issues here:
-    1) We have to re-add labels. This isn't very nice.
-    2) There's no way to set the learning rate for the weight update, so we
-        end up out-of-scale, causing it to learn too fast.
-    """
-    TRAIN_DATA = [
-        ["hey", []],
-        ["howdy", []],
-        ["hey there", []],
-        ["hello", []],
-        ["hi", []],
-        ["i'm looking for a place to eat", []],
-        ["i'm looking for a place in the north of town", [(31, 36, "LOCATION")]],
-        ["show me chinese restaurants", [(8, 15, "CUISINE")]],
-        ["show me chines restaurants", [(8, 14, "CUISINE")]],
-    ]
-    nlp = English()
-    ner = nlp.add_pipe("ner")
-    for _, offsets in TRAIN_DATA:
-        for start, end, label in offsets:
-            ner.add_label(label)
-    nlp.initialize()
-    for itn in range(20):
-        random.shuffle(TRAIN_DATA)
-        for raw_text, entity_offsets in TRAIN_DATA:
-            example = Example.from_dict(
-                nlp.make_doc(raw_text), {"entities": entity_offsets}
-            )
-            nlp.update([example])
-
-    with make_tempdir() as model_dir:
-        nlp.to_disk(model_dir)
-        nlp2 = util.load_model_from_path(model_dir)
-
-    for raw_text, entity_offsets in TRAIN_DATA:
-        doc = nlp2(raw_text)
-        ents = {(ent.start_char, ent.end_char): ent.label_ for ent in doc.ents}
-        for start, end, label in entity_offsets:
-            if (start, end) in ents:
-                assert ents[(start, end)] == label
-                break
-            else:
-                if entity_offsets:
-                    raise Exception(ents)
diff --git a/spacy/tests/regression/test_issue1001-1500.py b/spacy/tests/regression/test_issue1001-1500.py
deleted file mode 100644
index 0a60e4477..000000000
--- a/spacy/tests/regression/test_issue1001-1500.py
+++ /dev/null
@@ -1,174 +0,0 @@
-import pytest
-import re
-from spacy.tokens import Doc
-from spacy.vocab import Vocab
-from spacy.lang.en import English
-from spacy.lang.lex_attrs import LEX_ATTRS
-from spacy.matcher import Matcher
-from spacy.tokenizer import Tokenizer
-from spacy.symbols import ORTH, LEMMA, POS
-
-
-@pytest.mark.issue(1061)
-def test_issue1061():
-    """Test special-case works after tokenizing. Was caching problem."""
-    text = "I like _MATH_ even _MATH_ when _MATH_, except when _MATH_ is _MATH_! but not _MATH_."
-    tokenizer = English().tokenizer
-    doc = tokenizer(text)
-    assert "MATH" in [w.text for w in doc]
-    assert "_MATH_" not in [w.text for w in doc]
-
-    tokenizer.add_special_case("_MATH_", [{ORTH: "_MATH_"}])
-    doc = tokenizer(text)
-    assert "_MATH_" in [w.text for w in doc]
-    assert "MATH" not in [w.text for w in doc]
-
-    # For sanity, check it works when pipeline is clean.
-    tokenizer = English().tokenizer
-    tokenizer.add_special_case("_MATH_", [{ORTH: "_MATH_"}])
-    doc = tokenizer(text)
-    assert "_MATH_" in [w.text for w in doc]
-    assert "MATH" not in [w.text for w in doc]
-
-
-@pytest.mark.skip(
-    reason="Can not be fixed without variable-width look-behind (which we don't want)"
-)
-@pytest.mark.issue(1235)
-def test_issue1235():
-    """Test that g is not split of if preceded by a number and a letter"""
-    nlp = English()
-    testwords = "e2g 2g 52g"
-    doc = nlp(testwords)
-    assert len(doc) == 5
-    assert doc[0].text == "e2g"
-    assert doc[1].text == "2"
-    assert doc[2].text == "g"
-    assert doc[3].text == "52"
-    assert doc[4].text == "g"
-
-
-@pytest.mark.issue(1242)
-def test_issue1242():
-    nlp = English()
-    doc = nlp("")
-    assert len(doc) == 0
-    docs = list(nlp.pipe(["", "hello"]))
-    assert len(docs[0]) == 0
-    assert len(docs[1]) == 1
-
-
-@pytest.mark.skip(reason="v3 no longer supports LEMMA/POS in tokenizer special cases")
-@pytest.mark.issue(1250)
-def test_issue1250():
-    """Test cached special cases."""
-    special_case = [{ORTH: "reimbur", LEMMA: "reimburse", POS: "VERB"}]
-    nlp = English()
-    nlp.tokenizer.add_special_case("reimbur", special_case)
-    lemmas = [w.lemma_ for w in nlp("reimbur, reimbur...")]
-    assert lemmas == ["reimburse", ",", "reimburse", "..."]
-    lemmas = [w.lemma_ for w in nlp("reimbur, reimbur...")]
-    assert lemmas == ["reimburse", ",", "reimburse", "..."]
-
-
-@pytest.mark.issue(1257)
-def test_issue1257():
-    """Test that tokens compare correctly."""
-    doc1 = Doc(Vocab(), words=["a", "b", "c"])
-    doc2 = Doc(Vocab(), words=["a", "c", "e"])
-    assert doc1[0] != doc2[0]
-    assert not doc1[0] == doc2[0]
-
-
-@pytest.mark.issue(1375)
-def test_issue1375():
-    """Test that token.nbor() raises IndexError for out-of-bounds access."""
-    doc = Doc(Vocab(), words=["0", "1", "2"])
-    with pytest.raises(IndexError):
-        assert doc[0].nbor(-1)
-    assert doc[1].nbor(-1).text == "0"
-    with pytest.raises(IndexError):
-        assert doc[2].nbor(1)
-    assert doc[1].nbor(1).text == "2"
-
-
-@pytest.mark.issue(1434)
-def test_issue1434():
-    """Test matches occur when optional element at end of short doc."""
-    pattern = [{"ORTH": "Hello"}, {"IS_ALPHA": True, "OP": "?"}]
-    vocab = Vocab(lex_attr_getters=LEX_ATTRS)
-    hello_world = Doc(vocab, words=["Hello", "World"])
-    hello = Doc(vocab, words=["Hello"])
-    matcher = Matcher(vocab)
-    matcher.add("MyMatcher", [pattern])
-    matches = matcher(hello_world)
-    assert matches
-    matches = matcher(hello)
-    assert matches
-
-
-@pytest.mark.parametrize(
-    "string,start,end",
-    [
-        ("a", 0, 1),
-        ("a b", 0, 2),
-        ("a c", 0, 1),
-        ("a b c", 0, 2),
-        ("a b b c", 0, 3),
-        ("a b b", 0, 3),
-    ],
-)
-@pytest.mark.issue(1450)
-def test_issue1450(string, start, end):
-    """Test matcher works when patterns end with * operator."""
-    pattern = [{"ORTH": "a"}, {"ORTH": "b", "OP": "*"}]
-    matcher = Matcher(Vocab())
-    matcher.add("TSTEND", [pattern])
-    doc = Doc(Vocab(), words=string.split())
-    matches = matcher(doc)
-    if start is None or end is None:
-        assert matches == []
-    assert matches[-1][1] == start
-    assert matches[-1][2] == end
-
-
-@pytest.mark.issue(1488)
-def test_issue1488():
-    prefix_re = re.compile(r"""[\[\("']""")
-    suffix_re = re.compile(r"""[\]\)"']""")
-    infix_re = re.compile(r"""[-~\.]""")
-    simple_url_re = re.compile(r"""^https?://""")
-
-    def my_tokenizer(nlp):
-        return Tokenizer(
-            nlp.vocab,
-            {},
-            prefix_search=prefix_re.search,
-            suffix_search=suffix_re.search,
-            infix_finditer=infix_re.finditer,
-            token_match=simple_url_re.match,
-        )
-
-    nlp = English()
-    nlp.tokenizer = my_tokenizer(nlp)
-    doc = nlp("This is a test.")
-    for token in doc:
-        assert token.text
-
-
-@pytest.mark.issue(1494)
-def test_issue1494():
-    infix_re = re.compile(r"""[^a-z]""")
-    test_cases = [
-        ("token 123test", ["token", "1", "2", "3", "test"]),
-        ("token 1test", ["token", "1test"]),
-        ("hello...test", ["hello", ".", ".", ".", "test"]),
-    ]
-
-    def new_tokenizer(nlp):
-        return Tokenizer(nlp.vocab, {}, infix_finditer=infix_re.finditer)
-
-    nlp = English()
-    nlp.tokenizer = new_tokenizer(nlp)
-    for text, expected in test_cases:
-        assert [token.text for token in nlp(text)] == expected
diff --git a/spacy/tests/regression/test_issue1501-2000.py b/spacy/tests/regression/test_issue1501-2000.py
deleted file mode 100644
index 07f173843..000000000
--- a/spacy/tests/regression/test_issue1501-2000.py
+++ /dev/null
@@ -1,375 +0,0 @@
-import pytest
-import gc
-import numpy
-import copy
-
-from spacy.training import Example
-from spacy.lang.en import English
-from spacy.lang.en.stop_words import STOP_WORDS
-from spacy.lang.lex_attrs import is_stop
-from spacy.vectors import Vectors
-from spacy.vocab import Vocab
-from spacy.language import Language
-from spacy.tokens import Doc, Span, Token
-from spacy.attrs import HEAD, DEP
-from spacy.matcher import Matcher
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(1506)
-def test_issue1506():
-    def string_generator():
-        for _ in range(10001):
-            yield "It's sentence produced by that bug."
-        for _ in range(10001):
-            yield "I erase some hbdsaj lemmas."
-        for _ in range(10001):
-            yield "I erase lemmas."
-        for _ in range(10001):
-            yield "It's sentence produced by that bug."
-        for _ in range(10001):
-            yield "It's sentence produced by that bug."
-
-    nlp = English()
-    for i, d in enumerate(nlp.pipe(string_generator())):
-        # We should run cleanup more than one time to actually cleanup data.
-        # In first run — clean up only mark strings as «not hitted».
-        if i == 10000 or i == 20000 or i == 30000:
-            gc.collect()
-        for t in d:
-            str(t.lemma_)
-
-
-@pytest.mark.issue(1518)
-def test_issue1518():
-    """Test vectors.resize() works."""
-    vectors = Vectors(shape=(10, 10))
-    vectors.add("hello", row=2)
-    vectors.resize((5, 9))
-
-
-@pytest.mark.issue(1537)
-def test_issue1537():
-    """Test that Span.as_doc() doesn't segfault."""
-    string = "The sky is blue . The man is pink . The dog is purple ."
-    doc = Doc(Vocab(), words=string.split())
-    doc[0].sent_start = True
-    for word in doc[1:]:
-        if word.nbor(-1).text == ".":
-            word.sent_start = True
-        else:
-            word.sent_start = False
-    sents = list(doc.sents)
-    sent0 = sents[0].as_doc()
-    sent1 = sents[1].as_doc()
-    assert isinstance(sent0, Doc)
-    assert isinstance(sent1, Doc)
-
-
-# TODO: Currently segfaulting, due to l_edge and r_edge misalignment
-@pytest.mark.issue(1537)
-# def test_issue1537_model():
-#    nlp = load_spacy('en')
-#    doc = nlp('The sky is blue. The man is pink. The dog is purple.')
-#    sents = [s.as_doc() for s in doc.sents]
-#    print(list(sents[0].noun_chunks))
-#    print(list(sents[1].noun_chunks))
-
-
-@pytest.mark.issue(1539)
-def test_issue1539():
-    """Ensure vectors.resize() doesn't try to modify dictionary during iteration."""
-    v = Vectors(shape=(10, 10), keys=[5, 3, 98, 100])
-    v.resize((100, 100))
-
-
-@pytest.mark.issue(1547)
-def test_issue1547():
-    """Test that entity labels still match after merging tokens."""
-    words = ["\n", "worda", ".", "\n", "wordb", "-", "Biosphere", "2", "-", " \n"]
-    doc = Doc(Vocab(), words=words)
-    doc.ents = [Span(doc, 6, 8, label=doc.vocab.strings["PRODUCT"])]
-    with doc.retokenize() as retokenizer:
-        retokenizer.merge(doc[5:7])
-    assert [ent.text for ent in doc.ents]
-
-
-@pytest.mark.issue(1612)
-def test_issue1612(en_tokenizer):
-    doc = en_tokenizer("The black cat purrs.")
-    span = doc[1:3]
-    assert span.orth_ == span.text
-
-
-@pytest.mark.issue(1654)
-def test_issue1654():
-    nlp = Language(Vocab())
-    assert not nlp.pipeline
-
-    @Language.component("component")
-    def component(doc):
-        return doc
-
-    nlp.add_pipe("component", name="1")
-    nlp.add_pipe("component", name="2", after="1")
-    nlp.add_pipe("component", name="3", after="2")
-    assert nlp.pipe_names == ["1", "2", "3"]
-    nlp2 = Language(Vocab())
-    assert not nlp2.pipeline
-    nlp2.add_pipe("component", name="3")
-    nlp2.add_pipe("component", name="2", before="3")
-    nlp2.add_pipe("component", name="1", before="2")
-    assert nlp2.pipe_names == ["1", "2", "3"]
-
-
-@pytest.mark.parametrize("text", ["test@example.com", "john.doe@example.co.uk"])
-@pytest.mark.issue(1698)
-def test_issue1698(en_tokenizer, text):
-    doc = en_tokenizer(text)
-    assert len(doc) == 1
-    assert not doc[0].like_url
-
-
-@pytest.mark.issue(1727)
-def test_issue1727():
-    """Test that models with no pretrained vectors can be deserialized
-    correctly after vectors are added."""
-    nlp = Language(Vocab())
-    data = numpy.ones((3, 300), dtype="f")
-    vectors = Vectors(data=data, keys=["I", "am", "Matt"])
-    tagger = nlp.create_pipe("tagger")
-    tagger.add_label("PRP")
-    assert tagger.cfg.get("pretrained_dims", 0) == 0
-    tagger.vocab.vectors = vectors
-    with make_tempdir() as path:
-        tagger.to_disk(path)
-        tagger = nlp.create_pipe("tagger").from_disk(path)
-        assert tagger.cfg.get("pretrained_dims", 0) == 0
-
-
-@pytest.mark.issue(1757)
-def test_issue1757():
-    """Test comparison against None doesn't cause segfault."""
-    doc = Doc(Vocab(), words=["a", "b", "c"])
-    assert not doc[0] < None
-    assert not doc[0] is None
-    assert doc[0] >= None
-    assert not doc[:2] < None
-    assert not doc[:2] is None
-    assert doc[:2] >= None
-    assert not doc.vocab["a"] is None
-    assert not doc.vocab["a"] < None
-
-
-@pytest.mark.issue(1758)
-def test_issue1758(en_tokenizer):
-    """Test that "would've" is handled by the English tokenizer exceptions."""
-    tokens = en_tokenizer("would've")
-    assert len(tokens) == 2
-
-
-@pytest.mark.issue(1773)
-def test_issue1773(en_tokenizer):
-    """Test that spaces don't receive a POS but no TAG. This is the root cause
-    of the serialization issue reported in #1773."""
-    doc = en_tokenizer("\n")
-    if doc[0].pos_ == "SPACE":
-        assert doc[0].tag_ != ""
-
-
-@pytest.mark.issue(1799)
-def test_issue1799():
-    """Test sentence boundaries are deserialized correctly, even for
-    non-projective sentences."""
-    heads_deps = numpy.asarray(
-        [
-            [1, 397],
-            [4, 436],
-            [2, 426],
-            [1, 402],
-            [0, 8206900633647566924],
-            [18446744073709551615, 440],
-            [18446744073709551614, 442],
-        ],
-        dtype="uint64",
-    )
-    doc = Doc(Vocab(), words="Just what I was looking for .".split())
-    doc.vocab.strings.add("ROOT")
-    doc = doc.from_array([HEAD, DEP], heads_deps)
-    assert len(list(doc.sents)) == 1
-
-
-@pytest.mark.issue(1807)
-def test_issue1807():
-    """Test vocab.set_vector also adds the word to the vocab."""
-    vocab = Vocab(vectors_name="test_issue1807")
-    assert "hello" not in vocab
-    vocab.set_vector("hello", numpy.ones((50,), dtype="f"))
-    assert "hello" in vocab
-
-
-@pytest.mark.issue(1834)
-def test_issue1834():
-    """Test that sentence boundaries & parse/tag flags are not lost
-    during serialization."""
-    words = ["This", "is", "a", "first", "sentence", ".", "And", "another", "one"]
-    doc = Doc(Vocab(), words=words)
-    doc[6].is_sent_start = True
-    new_doc = Doc(doc.vocab).from_bytes(doc.to_bytes())
-    assert new_doc[6].sent_start
-    assert not new_doc.has_annotation("DEP")
-    assert not new_doc.has_annotation("TAG")
-    doc = Doc(
-        Vocab(),
-        words=words,
-        tags=["TAG"] * len(words),
-        heads=[0, 0, 0, 0, 0, 0, 6, 6, 6],
-        deps=["dep"] * len(words),
-    )
-    new_doc = Doc(doc.vocab).from_bytes(doc.to_bytes())
-    assert new_doc[6].sent_start
-    assert new_doc.has_annotation("DEP")
-    assert new_doc.has_annotation("TAG")
-
-
-@pytest.mark.issue(1868)
-def test_issue1868():
-    """Test Vocab.__contains__ works with int keys."""
-    vocab = Vocab()
-    lex = vocab["hello"]
-    assert lex.orth in vocab
-    assert lex.orth_ in vocab
-    assert "some string" not in vocab
-    int_id = vocab.strings.add("some string")
-    assert int_id not in vocab
-
-
-@pytest.mark.issue(1883)
-def test_issue1883():
-    matcher = Matcher(Vocab())
-    matcher.add("pat1", [[{"orth": "hello"}]])
-    doc = Doc(matcher.vocab, words=["hello"])
-    assert len(matcher(doc)) == 1
-    new_matcher = copy.deepcopy(matcher)
-    new_doc = Doc(new_matcher.vocab, words=["hello"])
-    assert len(new_matcher(new_doc)) == 1
-
-
-@pytest.mark.parametrize("word", ["the"])
-@pytest.mark.issue(1889)
-def test_issue1889(word):
-    assert is_stop(word, STOP_WORDS) == is_stop(word.upper(), STOP_WORDS)
-
-
-@pytest.mark.skip(reason="obsolete with the config refactor of v.3")
-@pytest.mark.issue(1915)
-def test_issue1915():
-    cfg = {"hidden_depth": 2}  # should error out
-    nlp = Language()
-    ner = nlp.add_pipe("ner")
-    ner.add_label("answer")
-    with pytest.raises(ValueError):
-        nlp.initialize(**cfg)
-
-
-@pytest.mark.issue(1945)
-def test_issue1945():
-    """Test regression in Matcher introduced in v2.0.6."""
-    matcher = Matcher(Vocab())
-    matcher.add("MWE", [[{"orth": "a"}, {"orth": "a"}]])
-    doc = Doc(matcher.vocab, words=["a", "a", "a"])
-    matches = matcher(doc)  # we should see two overlapping matches here
-    assert len(matches) == 2
-    assert matches[0][1:] == (0, 2)
-    assert matches[1][1:] == (1, 3)
-
-
-@pytest.mark.issue(1963)
-def test_issue1963(en_tokenizer):
-    """Test that doc.merge() resizes doc.tensor"""
-    doc = en_tokenizer("a b c d")
-    doc.tensor = numpy.ones((len(doc), 128), dtype="f")
-    with doc.retokenize() as retokenizer:
-        retokenizer.merge(doc[0:2])
-    assert len(doc) == 3
-    assert doc.tensor.shape == (3, 128)
-
-
-@pytest.mark.parametrize("label", ["U-JOB-NAME"])
-@pytest.mark.issue(1967)
-def test_issue1967(label):
-    nlp = Language()
-    config = {}
-    ner = nlp.create_pipe("ner", config=config)
-    example = Example.from_dict(
-        Doc(ner.vocab, words=["word"]),
-        {
-            "ids": [0],
-            "words": ["word"],
-            "tags": ["tag"],
-            "heads": [0],
-            "deps": ["dep"],
-            "entities": [label],
-        },
-    )
-    assert "JOB-NAME" in ner.moves.get_actions(examples=[example])[1]
-
-
-@pytest.mark.issue(1971)
-def test_issue1971(en_vocab):
-    # Possibly related to #2675 and #2671?
-    matcher = Matcher(en_vocab)
-    pattern = [
-        {"ORTH": "Doe"},
-        {"ORTH": "!", "OP": "?"},
-        {"_": {"optional": True}, "OP": "?"},
-        {"ORTH": "!", "OP": "?"},
-    ]
-    Token.set_extension("optional", default=False)
-    matcher.add("TEST", [pattern])
-    doc = Doc(en_vocab, words=["Hello", "John", "Doe", "!"])
-    # We could also assert length 1 here, but this is more conclusive, because
-    # the real problem here is that it returns a duplicate match for a match_id
-    # that's not actually in the vocab!
-    matches = matcher(doc)
-    assert all([match_id in en_vocab.strings for match_id, start, end in matches])
-
-
-def test_issue_1971_2(en_vocab):
-    matcher = Matcher(en_vocab)
-    pattern1 = [{"ORTH": "EUR", "LOWER": {"IN": ["eur"]}}, {"LIKE_NUM": True}]
-    pattern2 = [{"LIKE_NUM": True}, {"ORTH": "EUR"}]  # {"IN": ["EUR"]}}]
-    doc = Doc(en_vocab, words=["EUR", "10", "is", "10", "EUR"])
-    matcher.add("TEST1", [pattern1, pattern2])
-    matches = matcher(doc)
-    assert len(matches) == 2
-
-
-def test_issue_1971_3(en_vocab):
-    """Test that pattern matches correctly for multiple extension attributes."""
-    Token.set_extension("a", default=1, force=True)
-    Token.set_extension("b", default=2, force=True)
-    doc = Doc(en_vocab, words=["hello", "world"])
-    matcher = Matcher(en_vocab)
-    matcher.add("A", [[{"_": {"a": 1}}]])
-    matcher.add("B", [[{"_": {"b": 2}}]])
-    matches = sorted((en_vocab.strings[m_id], s, e) for m_id, s, e in matcher(doc))
-    assert len(matches) == 4
-    assert matches == sorted([("A", 0, 1), ("A", 1, 2), ("B", 0, 1), ("B", 1, 2)])
-
-
-def test_issue_1971_4(en_vocab):
-    """Test that pattern matches correctly with multiple extension attribute
-    values on a single token.
-    """
-    Token.set_extension("ext_a", default="str_a", force=True)
-    Token.set_extension("ext_b", default="str_b", force=True)
-    matcher = Matcher(en_vocab)
-    doc = Doc(en_vocab, words=["this", "is", "text"])
-    pattern = [{"_": {"ext_a": "str_a", "ext_b": "str_b"}}] * 3
-    matcher.add("TEST", [pattern])
-    matches = matcher(doc)
-    # Uncommenting this caused a segmentation fault
-    assert len(matches) == 1
-    assert matches[0] == (en_vocab.strings["TEST"], 0, 3)
diff --git a/spacy/tests/regression/test_issue2001-2500.py b/spacy/tests/regression/test_issue2001-2500.py
deleted file mode 100644
index a07360c2c..000000000
--- a/spacy/tests/regression/test_issue2001-2500.py
+++ /dev/null
@@ -1,152 +0,0 @@
-import pytest
-import numpy
-from spacy.tokens import Doc
-from spacy.matcher import Matcher
-from spacy.displacy import render
-from spacy.training import iob_to_biluo
-from spacy.lang.it import Italian
-from spacy.lang.en import English
-
-from ..util import add_vecs_to_vocab
-
-
-@pytest.mark.skip(
-    reason="Can not be fixed without iterative looping between prefix/suffix and infix"
-)
-@pytest.mark.issue(2070)
-def test_issue2070():
-    """Test that checks that a dot followed by a quote is handled
-    appropriately.
-    """
-    # Problem: The dot is now properly split off, but the prefix/suffix rules
-    # are not applied again afterwards. This means that the quote will still be
-    # attached to the remaining token.
-    nlp = English()
-    doc = nlp('First sentence."A quoted sentence" he said ...')
-    assert len(doc) == 11
-
-
-@pytest.mark.issue(2179)
-def test_issue2179():
-    """Test that spurious 'extra_labels' aren't created when initializing NER."""
-    nlp = Italian()
-    ner = nlp.add_pipe("ner")
-    ner.add_label("CITIZENSHIP")
-    nlp.initialize()
-    nlp2 = Italian()
-    nlp2.add_pipe("ner")
-    assert len(nlp2.get_pipe("ner").labels) == 0
-    model = nlp2.get_pipe("ner").model
-    model.attrs["resize_output"](model, nlp.get_pipe("ner").moves.n_moves)
-    nlp2.from_bytes(nlp.to_bytes())
-    assert "extra_labels" not in nlp2.get_pipe("ner").cfg
-    assert nlp2.get_pipe("ner").labels == ("CITIZENSHIP",)
-
-
-@pytest.mark.issue(2203)
-def test_issue2203(en_vocab):
-    """Test that lemmas are set correctly in doc.from_array."""
-    words = ["I", "'ll", "survive"]
-    tags = ["PRP", "MD", "VB"]
-    lemmas = ["-PRON-", "will", "survive"]
-    tag_ids = [en_vocab.strings.add(tag) for tag in tags]
-    lemma_ids = [en_vocab.strings.add(lemma) for lemma in lemmas]
-    doc = Doc(en_vocab, words=words)
-    # Work around lemma corruption problem and set lemmas after tags
-    doc.from_array("TAG", numpy.array(tag_ids, dtype="uint64"))
-    doc.from_array("LEMMA", numpy.array(lemma_ids, dtype="uint64"))
-    assert [t.tag_ for t in doc] == tags
-    assert [t.lemma_ for t in doc] == lemmas
-    # We need to serialize both tag and lemma, since this is what causes the bug
-    doc_array = doc.to_array(["TAG", "LEMMA"])
-    new_doc = Doc(doc.vocab, words=words).from_array(["TAG", "LEMMA"], doc_array)
-    assert [t.tag_ for t in new_doc] == tags
-    assert [t.lemma_ for t in new_doc] == lemmas
-
-
-@pytest.mark.issue(2219)
-def test_issue2219(en_vocab):
-    vectors = [("a", [1, 2, 3]), ("letter", [4, 5, 6])]
-    add_vecs_to_vocab(en_vocab, vectors)
-    [(word1, vec1), (word2, vec2)] = vectors
-    doc = Doc(en_vocab, words=[word1, word2])
-    assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
-
-
-@pytest.mark.issue(2361)
-def test_issue2361(de_vocab):
-    chars = ("&lt;", "&gt;", "&amp;", "&quot;")
-    words = ["<", ">", "&", '"']
-    doc = Doc(de_vocab, words=words, deps=["dep"] * len(words))
-    html = render(doc)
-    for char in chars:
-        assert char in html
-
-
-@pytest.mark.issue(2385)
-def test_issue2385():
-    """Test that IOB tags are correctly converted to BILUO tags."""
-    # fix bug in labels with a 'b' character
-    tags1 = ("B-BRAWLER", "I-BRAWLER", "I-BRAWLER")
-    assert iob_to_biluo(tags1) == ["B-BRAWLER", "I-BRAWLER", "L-BRAWLER"]
-    # maintain support for iob1 format
-    tags2 = ("I-ORG", "I-ORG", "B-ORG")
-    assert iob_to_biluo(tags2) == ["B-ORG", "L-ORG", "U-ORG"]
-    # maintain support for iob2 format
-    tags3 = ("B-PERSON", "I-PERSON", "B-PERSON")
-    assert iob_to_biluo(tags3) == ["B-PERSON", "L-PERSON", "U-PERSON"]
-
-
-@pytest.mark.parametrize(
-    "tags",
-    [
-        ("B-ORG", "L-ORG"),
-        ("B-PERSON", "I-PERSON", "L-PERSON"),
-        ("U-BRAWLER", "U-BRAWLER"),
-    ],
-)
-@pytest.mark.issue(2385)
-def test_issue2385_biluo(tags):
-    """Test that BILUO-compatible tags aren't modified."""
-    assert iob_to_biluo(tags) == list(tags)
-
-
-@pytest.mark.issue(2396)
-def test_issue2396(en_vocab):
-    words = ["She", "created", "a", "test", "for", "spacy"]
-    heads = [1, 1, 3, 1, 3, 4]
-    deps = ["dep"] * len(heads)
-    matrix = numpy.array(
-        [
-            [0, 1, 1, 1, 1, 1],
-            [1, 1, 1, 1, 1, 1],
-            [1, 1, 2, 3, 3, 3],
-            [1, 1, 3, 3, 3, 3],
-            [1, 1, 3, 3, 4, 4],
-            [1, 1, 3, 3, 4, 5],
-        ],
-        dtype=numpy.int32,
-    )
-    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
-    span = doc[:]
-    assert (doc.get_lca_matrix() == matrix).all()
-    assert (span.get_lca_matrix() == matrix).all()
-
-
-@pytest.mark.issue(2464)
-def test_issue2464(en_vocab):
-    """Test problem with successive ?. This is the same bug, so putting it here."""
-    matcher = Matcher(en_vocab)
-    doc = Doc(en_vocab, words=["a", "b"])
-    matcher.add("4", [[{"OP": "?"}, {"OP": "?"}]])
-    matches = matcher(doc)
-    assert len(matches) == 3
-
-
-@pytest.mark.issue(2482)
-def test_issue2482():
-    """Test we can serialize and deserialize a blank NER or parser model."""
-    nlp = Italian()
-    nlp.add_pipe("ner")
-    b = nlp.to_bytes()
-    Italian().from_bytes(b)
diff --git a/spacy/tests/regression/test_issue2501-3000.py b/spacy/tests/regression/test_issue2501-3000.py
deleted file mode 100644
index cbb7f0621..000000000
--- a/spacy/tests/regression/test_issue2501-3000.py
+++ /dev/null
@@ -1,238 +0,0 @@
-import pytest
-from spacy import displacy
-from spacy.training import Example
-from spacy.lang.en import English
-from spacy.lang.ja import Japanese
-from spacy.lang.xx import MultiLanguage
-from spacy.language import Language
-from spacy.matcher import Matcher
-from spacy.tokens import Doc, Span
-from spacy.vocab import Vocab
-from spacy.compat import pickle
-import numpy
-import random
-
-
-@pytest.mark.issue(2564)
-def test_issue2564():
-    """Test the tagger sets has_annotation("TAG") correctly when used via Language.pipe."""
-    nlp = Language()
-    tagger = nlp.add_pipe("tagger")
-    tagger.add_label("A")
-    nlp.initialize()
-    doc = nlp("hello world")
-    assert doc.has_annotation("TAG")
-    docs = nlp.pipe(["hello", "world"])
-    piped_doc = next(docs)
-    assert piped_doc.has_annotation("TAG")
-
-
-@pytest.mark.issue(2569)
-def test_issue2569(en_tokenizer):
-    """Test that operator + is greedy."""
-    doc = en_tokenizer("It is May 15, 1993.")
-    doc.ents = [Span(doc, 2, 6, label=doc.vocab.strings["DATE"])]
-    matcher = Matcher(doc.vocab)
-    matcher.add("RULE", [[{"ENT_TYPE": "DATE", "OP": "+"}]])
-    matched = [doc[start:end] for _, start, end in matcher(doc)]
-    matched = sorted(matched, key=len, reverse=True)
-    assert len(matched) == 10
-    assert len(matched[0]) == 4
-    assert matched[0].text == "May 15, 1993"
-
-
-@pytest.mark.parametrize(
-    "text",
-    [
-        "ABLEItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume TABLE ItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume ItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume",
-        "oow.jspsearch.eventoracleopenworldsearch.technologyoraclesolarissearch.technologystoragesearch.technologylinuxsearch.technologyserverssearch.technologyvirtualizationsearch.technologyengineeredsystemspcodewwmkmppscem:",
-    ],
-)
-@pytest.mark.issue(2626)
-def test_issue2626_2835(en_tokenizer, text):
-    """Check that sentence doesn't cause an infinite loop in the tokenizer."""
-    doc = en_tokenizer(text)
-    assert doc
-
-
-@pytest.mark.issue(2656)
-def test_issue2656(en_tokenizer):
-    """Test that tokenizer correctly splits off punctuation after numbers with
-    decimal points.
-    """
-    doc = en_tokenizer("I went for 40.3, and got home by 10.0.")
-    assert len(doc) == 11
-    assert doc[0].text == "I"
-    assert doc[1].text == "went"
-    assert doc[2].text == "for"
-    assert doc[3].text == "40.3"
-    assert doc[4].text == ","
-    assert doc[5].text == "and"
-    assert doc[6].text == "got"
-    assert doc[7].text == "home"
-    assert doc[8].text == "by"
-    assert doc[9].text == "10.0"
-    assert doc[10].text == "."
-
-
-@pytest.mark.issue(2671)
-def test_issue2671():
-    """Ensure the correct entity ID is returned for matches with quantifiers.
-    See also #2675
-    """
-    nlp = English()
-    matcher = Matcher(nlp.vocab)
-    pattern_id = "test_pattern"
-    pattern = [
-        {"LOWER": "high"},
-        {"IS_PUNCT": True, "OP": "?"},
-        {"LOWER": "adrenaline"},
-    ]
-    matcher.add(pattern_id, [pattern])
-    doc1 = nlp("This is a high-adrenaline situation.")
-    doc2 = nlp("This is a high adrenaline situation.")
-    matches1 = matcher(doc1)
-    for match_id, start, end in matches1:
-        assert nlp.vocab.strings[match_id] == pattern_id
-    matches2 = matcher(doc2)
-    for match_id, start, end in matches2:
-        assert nlp.vocab.strings[match_id] == pattern_id
-
-
-@pytest.mark.issue(2728)
-def test_issue2728(en_vocab):
-    """Test that displaCy ENT visualizer escapes HTML correctly."""
-    doc = Doc(en_vocab, words=["test", "<RELEASE>", "test"])
-    doc.ents = [Span(doc, 0, 1, label="TEST")]
-    html = displacy.render(doc, style="ent")
-    assert "&lt;RELEASE&gt;" in html
-    doc.ents = [Span(doc, 1, 2, label="TEST")]
-    html = displacy.render(doc, style="ent")
-    assert "&lt;RELEASE&gt;" in html
-
-
-@pytest.mark.issue(2754)
-def test_issue2754(en_tokenizer):
-    """Test that words like 'a' and 'a.m.' don't get exceptional norm values."""
-    a = en_tokenizer("a")
-    assert a[0].norm_ == "a"
-    am = en_tokenizer("am")
-    assert am[0].norm_ == "am"
-
-
-@pytest.mark.issue(2772)
-def test_issue2772(en_vocab):
-    """Test that deprojectivization doesn't mess up sentence boundaries."""
-    # fmt: off
-    words = ["When", "we", "write", "or", "communicate", "virtually", ",", "we", "can", "hide", "our", "true", "feelings", "."]
-    # fmt: on
-    # A tree with a non-projective (i.e. crossing) arc
-    # The arcs (0, 4) and (2, 9) cross.
-    heads = [4, 2, 9, 2, 2, 4, 9, 9, 9, 9, 12, 12, 9, 9]
-    deps = ["dep"] * len(heads)
-    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
-    assert doc[1].is_sent_start is False
-
-
-@pytest.mark.parametrize("text", ["-0.23", "+123,456", "±1"])
-@pytest.mark.parametrize("lang_cls", [English, MultiLanguage])
-@pytest.mark.issue(2782)
-def test_issue2782(text, lang_cls):
-    """Check that like_num handles + and - before number."""
-    nlp = lang_cls()
-    doc = nlp(text)
-    assert len(doc) == 1
-    assert doc[0].like_num
-
-
-@pytest.mark.issue(2800)
-def test_issue2800():
-    """Test issue that arises when too many labels are added to NER model.
-    Used to cause segfault.
-    """
-    nlp = English()
-    train_data = []
-    train_data.extend(
-        [Example.from_dict(nlp.make_doc("One sentence"), {"entities": []})]
-    )
-    entity_types = [str(i) for i in range(1000)]
-    ner = nlp.add_pipe("ner")
-    for entity_type in list(entity_types):
-        ner.add_label(entity_type)
-    optimizer = nlp.initialize()
-    for i in range(20):
-        losses = {}
-        random.shuffle(train_data)
-        for example in train_data:
-            nlp.update([example], sgd=optimizer, losses=losses, drop=0.5)
-
-
-@pytest.mark.issue(2822)
-def test_issue2822(it_tokenizer):
-    """Test that the abbreviation of poco is kept as one word."""
-    doc = it_tokenizer("Vuoi un po' di zucchero?")
-    assert len(doc) == 6
-    assert doc[0].text == "Vuoi"
-    assert doc[1].text == "un"
-    assert doc[2].text == "po'"
-    assert doc[3].text == "di"
-    assert doc[4].text == "zucchero"
-    assert doc[5].text == "?"
-
-
-@pytest.mark.issue(2833)
-def test_issue2833(en_vocab):
-    """Test that a custom error is raised if a token or span is pickled."""
-    doc = Doc(en_vocab, words=["Hello", "world"])
-    with pytest.raises(NotImplementedError):
-        pickle.dumps(doc[0])
-    with pytest.raises(NotImplementedError):
-        pickle.dumps(doc[0:2])
-
-
-@pytest.mark.issue(2871)
-def test_issue2871():
-    """Test that vectors recover the correct key for spaCy reserved words."""
-    words = ["dog", "cat", "SUFFIX"]
-    vocab = Vocab(vectors_name="test_issue2871")
-    vocab.vectors.resize(shape=(3, 10))
-    vector_data = numpy.zeros((3, 10), dtype="f")
-    for word in words:
-        _ = vocab[word]  # noqa: F841
-        vocab.set_vector(word, vector_data[0])
-    vocab.vectors.name = "dummy_vectors"
-    assert vocab["dog"].rank == 0
-    assert vocab["cat"].rank == 1
-    assert vocab["SUFFIX"].rank == 2
-    assert vocab.vectors.find(key="dog") == 0
-    assert vocab.vectors.find(key="cat") == 1
-    assert vocab.vectors.find(key="SUFFIX") == 2
-
-
-@pytest.mark.issue(2901)
-def test_issue2901():
-    """Test that `nlp` doesn't fail."""
-    try:
-        nlp = Japanese()
-    except ImportError:
-        pytest.skip()
-
-    doc = nlp("pythonが大好きです")
-    assert doc
-
-
-@pytest.mark.issue(2926)
-def test_issue2926(fr_tokenizer):
-    """Test that the tokenizer correctly splits tokens separated by a slash (/)
-    ending in a digit.
-    """
-    doc = fr_tokenizer("Learn html5/css3/javascript/jquery")
-    assert len(doc) == 8
-    assert doc[0].text == "Learn"
-    assert doc[1].text == "html5"
-    assert doc[2].text == "/"
-    assert doc[3].text == "css3"
-    assert doc[4].text == "/"
-    assert doc[5].text == "javascript"
-    assert doc[6].text == "/"
-    assert doc[7].text == "jquery"
diff --git a/spacy/tests/regression/test_issue3001-3500.py b/spacy/tests/regression/test_issue3001-3500.py
deleted file mode 100644
index 6220003dc..000000000
--- a/spacy/tests/regression/test_issue3001-3500.py
+++ /dev/null
@@ -1,272 +0,0 @@
-import pytest
-from spacy import registry
-from spacy.lang.en import English
-from spacy.lang.de import German
-from spacy.pipeline.ner import DEFAULT_NER_MODEL
-from spacy.pipeline import EntityRuler, EntityRecognizer
-from spacy.matcher import Matcher, PhraseMatcher
-from spacy.tokens import Doc
-from spacy.vocab import Vocab
-from spacy.attrs import ENT_IOB, ENT_TYPE
-from spacy.compat import pickle
-from spacy import displacy
-from spacy.vectors import Vectors
-import numpy
-
-
-@pytest.mark.issue(3002)
-def test_issue3002():
-    """Test that the tokenizer doesn't hang on a long list of dots"""
-    nlp = German()
-    doc = nlp(
-        "880.794.982.218.444.893.023.439.794.626.120.190.780.624.990.275.671 ist eine lange Zahl"
-    )
-    assert len(doc) == 5
-
-
-@pytest.mark.issue(3009)
-def test_issue3009(en_vocab):
-    """Test problem with matcher quantifiers"""
-    patterns = [
-        [{"ORTH": "has"}, {"LOWER": "to"}, {"LOWER": "do"}, {"TAG": "IN"}],
-        [
-            {"ORTH": "has"},
-            {"IS_ASCII": True, "IS_PUNCT": False, "OP": "*"},
-            {"LOWER": "to"},
-            {"LOWER": "do"},
-            {"TAG": "IN"},
-        ],
-        [
-            {"ORTH": "has"},
-            {"IS_ASCII": True, "IS_PUNCT": False, "OP": "?"},
-            {"LOWER": "to"},
-            {"LOWER": "do"},
-            {"TAG": "IN"},
-        ],
-    ]
-    words = ["also", "has", "to", "do", "with"]
-    tags = ["RB", "VBZ", "TO", "VB", "IN"]
-    pos = ["ADV", "VERB", "ADP", "VERB", "ADP"]
-    doc = Doc(en_vocab, words=words, tags=tags, pos=pos)
-    matcher = Matcher(en_vocab)
-    for i, pattern in enumerate(patterns):
-        matcher.add(str(i), [pattern])
-        matches = matcher(doc)
-        assert matches
-
-
-@pytest.mark.issue(3012)
-def test_issue3012(en_vocab):
-    """Test that the is_tagged attribute doesn't get overwritten when we from_array
-    without tag information."""
-    words = ["This", "is", "10", "%", "."]
-    tags = ["DT", "VBZ", "CD", "NN", "."]
-    pos = ["DET", "VERB", "NUM", "NOUN", "PUNCT"]
-    ents = ["O", "O", "B-PERCENT", "I-PERCENT", "O"]
-    doc = Doc(en_vocab, words=words, tags=tags, pos=pos, ents=ents)
-    assert doc.has_annotation("TAG")
-    expected = ("10", "NUM", "CD", "PERCENT")
-    assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
-    header = [ENT_IOB, ENT_TYPE]
-    ent_array = doc.to_array(header)
-    doc.from_array(header, ent_array)
-    assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
-    # Serializing then deserializing
-    doc_bytes = doc.to_bytes()
-    doc2 = Doc(en_vocab).from_bytes(doc_bytes)
-    assert (doc2[2].text, doc2[2].pos_, doc2[2].tag_, doc2[2].ent_type_) == expected
-
-
-@pytest.mark.issue(3199)
-def test_issue3199():
-    """Test that Span.noun_chunks works correctly if no noun chunks iterator
-    is available. To make this test future-proof, we're constructing a Doc
-    with a new Vocab here and a parse tree to make sure the noun chunks run.
-    """
-    words = ["This", "is", "a", "sentence"]
-    doc = Doc(Vocab(), words=words, heads=[0] * len(words), deps=["dep"] * len(words))
-    with pytest.raises(NotImplementedError):
-        list(doc[0:3].noun_chunks)
-
-
-@pytest.mark.issue(3209)
-def test_issue3209():
-    """Test issue that occurred in spaCy nightly where NER labels were being
-    mapped to classes incorrectly after loading the model, when the labels
-    were added using ner.add_label().
-    """
-    nlp = English()
-    ner = nlp.add_pipe("ner")
-    ner.add_label("ANIMAL")
-    nlp.initialize()
-    move_names = ["O", "B-ANIMAL", "I-ANIMAL", "L-ANIMAL", "U-ANIMAL"]
-    assert ner.move_names == move_names
-    nlp2 = English()
-    ner2 = nlp2.add_pipe("ner")
-    model = ner2.model
-    model.attrs["resize_output"](model, ner.moves.n_moves)
-    nlp2.from_bytes(nlp.to_bytes())
-    assert ner2.move_names == move_names
-
-
-@pytest.mark.issue(3248)
-def test_issue3248_1():
-    """Test that the PhraseMatcher correctly reports its number of rules, not
-    total number of patterns."""
-    nlp = English()
-    matcher = PhraseMatcher(nlp.vocab)
-    matcher.add("TEST1", [nlp("a"), nlp("b"), nlp("c")])
-    matcher.add("TEST2", [nlp("d")])
-    assert len(matcher) == 2
-
-
-@pytest.mark.issue(3248)
-def test_issue3248_2():
-    """Test that the PhraseMatcher can be pickled correctly."""
-    nlp = English()
-    matcher = PhraseMatcher(nlp.vocab)
-    matcher.add("TEST1", [nlp("a"), nlp("b"), nlp("c")])
-    matcher.add("TEST2", [nlp("d")])
-    data = pickle.dumps(matcher)
-    new_matcher = pickle.loads(data)
-    assert len(new_matcher) == len(matcher)
-
-
-@pytest.mark.issue(3277)
-def test_issue3277(es_tokenizer):
-    """Test that hyphens are split correctly as prefixes."""
-    doc = es_tokenizer("—Yo me llamo... –murmuró el niño– Emilio Sánchez Pérez.")
-    assert len(doc) == 14
-    assert doc[0].text == "\u2014"
-    assert doc[5].text == "\u2013"
-    assert doc[9].text == "\u2013"
-
-
-@pytest.mark.issue(3288)
-def test_issue3288(en_vocab):
-    """Test that retokenization works correctly via displaCy when punctuation
-    is merged onto the preceeding token and tensor is resized."""
-    words = ["Hello", "World", "!", "When", "is", "this", "breaking", "?"]
-    heads = [1, 1, 1, 4, 4, 6, 4, 4]
-    deps = ["intj", "ROOT", "punct", "advmod", "ROOT", "det", "nsubj", "punct"]
-    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
-    doc.tensor = numpy.zeros((len(words), 96), dtype="float32")
-    displacy.render(doc)
-
-
-@pytest.mark.issue(3289)
-def test_issue3289():
-    """Test that Language.to_bytes handles serializing a pipeline component
-    with an uninitialized model."""
-    nlp = English()
-    nlp.add_pipe("textcat")
-    bytes_data = nlp.to_bytes()
-    new_nlp = English()
-    new_nlp.add_pipe("textcat")
-    new_nlp.from_bytes(bytes_data)
-
-
-@pytest.mark.issue(3328)
-def test_issue3328(en_vocab):
-    doc = Doc(en_vocab, words=["Hello", ",", "how", "are", "you", "doing", "?"])
-    matcher = Matcher(en_vocab)
-    patterns = [
-        [{"LOWER": {"IN": ["hello", "how"]}}],
-        [{"LOWER": {"IN": ["you", "doing"]}}],
-    ]
-    matcher.add("TEST", patterns)
-    matches = matcher(doc)
-    assert len(matches) == 4
-    matched_texts = [doc[start:end].text for _, start, end in matches]
-    assert matched_texts == ["Hello", "how", "you", "doing"]
-
-
-@pytest.mark.issue(3331)
-def test_issue3331(en_vocab):
-    """Test that duplicate patterns for different rules result in multiple
-    matches, one per rule.
-    """
-    matcher = PhraseMatcher(en_vocab)
-    matcher.add("A", [Doc(en_vocab, words=["Barack", "Obama"])])
-    matcher.add("B", [Doc(en_vocab, words=["Barack", "Obama"])])
-    doc = Doc(en_vocab, words=["Barack", "Obama", "lifts", "America"])
-    matches = matcher(doc)
-    assert len(matches) == 2
-    match_ids = [en_vocab.strings[matches[0][0]], en_vocab.strings[matches[1][0]]]
-    assert sorted(match_ids) == ["A", "B"]
-
-
-@pytest.mark.issue(3345)
-def test_issue3345():
-    """Test case where preset entity crosses sentence boundary."""
-    nlp = English()
-    doc = Doc(nlp.vocab, words=["I", "live", "in", "New", "York"])
-    doc[4].is_sent_start = True
-    ruler = EntityRuler(nlp, patterns=[{"label": "GPE", "pattern": "New York"}])
-    cfg = {"model": DEFAULT_NER_MODEL}
-    model = registry.resolve(cfg, validate=True)["model"]
-    ner = EntityRecognizer(doc.vocab, model)
-    # Add the OUT action. I wouldn't have thought this would be necessary...
-    ner.moves.add_action(5, "")
-    ner.add_label("GPE")
-    doc = ruler(doc)
-    # Get into the state just before "New"
-    state = ner.moves.init_batch([doc])[0]
-    ner.moves.apply_transition(state, "O")
-    ner.moves.apply_transition(state, "O")
-    ner.moves.apply_transition(state, "O")
-    # Check that B-GPE is valid.
-    assert ner.moves.is_valid(state, "B-GPE")
-
-
-@pytest.mark.issue(3412)
-def test_issue3412():
-    data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f")
-    vectors = Vectors(data=data, keys=["A", "B", "C"])
-    keys, best_rows, scores = vectors.most_similar(
-        numpy.asarray([[9, 8, 7], [0, 0, 0]], dtype="f")
-    )
-    assert best_rows[0] == 2
-
-
-@pytest.mark.skip(reason="default suffix rules avoid one upper-case letter before dot")
-@pytest.mark.issue(3449)
-def test_issue3449():
-    nlp = English()
-    nlp.add_pipe("sentencizer")
-    text1 = "He gave the ball to I. Do you want to go to the movies with I?"
-    text2 = "He gave the ball to I.  Do you want to go to the movies with I?"
-    text3 = "He gave the ball to I.\nDo you want to go to the movies with I?"
-    t1 = nlp(text1)
-    t2 = nlp(text2)
-    t3 = nlp(text3)
-    assert t1[5].text == "I"
-    assert t2[5].text == "I"
-    assert t3[5].text == "I"
-
-
-@pytest.mark.issue(3456)
-def test_issue3456():
-    # this crashed because of a padding error in layer.ops.unflatten in thinc
-    nlp = English()
-    tagger = nlp.add_pipe("tagger")
-    tagger.add_label("A")
-    nlp.initialize()
-    list(nlp.pipe(["hi", ""]))
-
-
-@pytest.mark.issue(3468)
-def test_issue3468():
-    """Test that sentence boundaries are set correctly so Doc.has_annotation("SENT_START") can
-    be restored after serialization."""
-    nlp = English()
-    nlp.add_pipe("sentencizer")
-    doc = nlp("Hello world")
-    assert doc[0].is_sent_start
-    assert doc.has_annotation("SENT_START")
-    assert len(list(doc.sents)) == 1
-    doc_bytes = doc.to_bytes()
-    new_doc = Doc(nlp.vocab).from_bytes(doc_bytes)
-    assert new_doc[0].is_sent_start
-    assert new_doc.has_annotation("SENT_START")
-    assert len(list(new_doc.sents)) == 1
diff --git a/spacy/tests/regression/test_issue3501-4000.py b/spacy/tests/regression/test_issue3501-4000.py
deleted file mode 100644
index 5d9bc4e83..000000000
--- a/spacy/tests/regression/test_issue3501-4000.py
+++ /dev/null
@@ -1,492 +0,0 @@
-import pytest
-from spacy.language import Language
-from spacy.vocab import Vocab
-from spacy.pipeline import EntityRuler, DependencyParser
-from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
-from spacy import displacy, load
-from spacy.displacy import parse_deps
-from spacy.tokens import Doc, Token
-from spacy.matcher import Matcher, PhraseMatcher
-from spacy.errors import MatchPatternError
-from spacy.util import minibatch
-from spacy.training import Example
-from spacy.lang.hi import Hindi
-from spacy.lang.es import Spanish
-from spacy.lang.en import English
-from spacy.attrs import IS_ALPHA
-from spacy import registry
-from thinc.api import compounding
-import spacy
-import srsly
-import numpy
-
-from ..util import make_tempdir
-
-
-@pytest.mark.parametrize("word", ["don't", "don’t", "I'd", "I’d"])
-@pytest.mark.issue(3521)
-def test_issue3521(en_tokenizer, word):
-    tok = en_tokenizer(word)[1]
-    # 'not' and 'would' should be stopwords, also in their abbreviated forms
-    assert tok.is_stop
-
-
-def test_issue_3526_1(en_vocab):
-    patterns = [
-        {"label": "HELLO", "pattern": "hello world"},
-        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
-        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
-        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
-        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
-    ]
-    nlp = Language(vocab=en_vocab)
-    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
-    ruler_bytes = ruler.to_bytes()
-    assert len(ruler) == len(patterns)
-    assert len(ruler.labels) == 4
-    assert ruler.overwrite
-    new_ruler = EntityRuler(nlp)
-    new_ruler = new_ruler.from_bytes(ruler_bytes)
-    assert len(new_ruler) == len(ruler)
-    assert len(new_ruler.labels) == 4
-    assert new_ruler.overwrite == ruler.overwrite
-    assert new_ruler.ent_id_sep == ruler.ent_id_sep
-
-
-def test_issue_3526_2(en_vocab):
-    patterns = [
-        {"label": "HELLO", "pattern": "hello world"},
-        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
-        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
-        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
-        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
-    ]
-    nlp = Language(vocab=en_vocab)
-    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
-    bytes_old_style = srsly.msgpack_dumps(ruler.patterns)
-    new_ruler = EntityRuler(nlp)
-    new_ruler = new_ruler.from_bytes(bytes_old_style)
-    assert len(new_ruler) == len(ruler)
-    for pattern in ruler.patterns:
-        assert pattern in new_ruler.patterns
-    assert new_ruler.overwrite is not ruler.overwrite
-
-
-def test_issue_3526_3(en_vocab):
-    patterns = [
-        {"label": "HELLO", "pattern": "hello world"},
-        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
-        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
-        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
-        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
-    ]
-    nlp = Language(vocab=en_vocab)
-    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
-    with make_tempdir() as tmpdir:
-        out_file = tmpdir / "entity_ruler"
-        srsly.write_jsonl(out_file.with_suffix(".jsonl"), ruler.patterns)
-        new_ruler = EntityRuler(nlp).from_disk(out_file)
-        for pattern in ruler.patterns:
-            assert pattern in new_ruler.patterns
-        assert len(new_ruler) == len(ruler)
-        assert new_ruler.overwrite is not ruler.overwrite
-
-
-def test_issue_3526_4(en_vocab):
-    nlp = Language(vocab=en_vocab)
-    patterns = [{"label": "ORG", "pattern": "Apple"}]
-    config = {"overwrite_ents": True}
-    ruler = nlp.add_pipe("entity_ruler", config=config)
-    ruler.add_patterns(patterns)
-    with make_tempdir() as tmpdir:
-        nlp.to_disk(tmpdir)
-        ruler = nlp.get_pipe("entity_ruler")
-        assert ruler.patterns == [{"label": "ORG", "pattern": "Apple"}]
-        assert ruler.overwrite is True
-        nlp2 = load(tmpdir)
-        new_ruler = nlp2.get_pipe("entity_ruler")
-        assert new_ruler.patterns == [{"label": "ORG", "pattern": "Apple"}]
-        assert new_ruler.overwrite is True
-
-
-@pytest.mark.issue(3531)
-def test_issue3531():
-    """Test that displaCy renderer doesn't require "settings" key."""
-    example_dep = {
-        "words": [
-            {"text": "But", "tag": "CCONJ"},
-            {"text": "Google", "tag": "PROPN"},
-            {"text": "is", "tag": "VERB"},
-            {"text": "starting", "tag": "VERB"},
-            {"text": "from", "tag": "ADP"},
-            {"text": "behind.", "tag": "ADV"},
-        ],
-        "arcs": [
-            {"start": 0, "end": 3, "label": "cc", "dir": "left"},
-            {"start": 1, "end": 3, "label": "nsubj", "dir": "left"},
-            {"start": 2, "end": 3, "label": "aux", "dir": "left"},
-            {"start": 3, "end": 4, "label": "prep", "dir": "right"},
-            {"start": 4, "end": 5, "label": "pcomp", "dir": "right"},
-        ],
-    }
-    example_ent = {
-        "text": "But Google is starting from behind.",
-        "ents": [{"start": 4, "end": 10, "label": "ORG"}],
-    }
-    dep_html = displacy.render(example_dep, style="dep", manual=True)
-    assert dep_html
-    ent_html = displacy.render(example_ent, style="ent", manual=True)
-    assert ent_html
-
-
-@pytest.mark.issue(3540)
-def test_issue3540(en_vocab):
-    words = ["I", "live", "in", "NewYork", "right", "now"]
-    tensor = numpy.asarray(
-        [[1.0, 1.1], [2.0, 2.1], [3.0, 3.1], [4.0, 4.1], [5.0, 5.1], [6.0, 6.1]],
-        dtype="f",
-    )
-    doc = Doc(en_vocab, words=words)
-    doc.tensor = tensor
-    gold_text = ["I", "live", "in", "NewYork", "right", "now"]
-    assert [token.text for token in doc] == gold_text
-    gold_lemma = ["I", "live", "in", "NewYork", "right", "now"]
-    for i, lemma in enumerate(gold_lemma):
-        doc[i].lemma_ = lemma
-    assert [token.lemma_ for token in doc] == gold_lemma
-    vectors_1 = [token.vector for token in doc]
-    assert len(vectors_1) == len(doc)
-
-    with doc.retokenize() as retokenizer:
-        heads = [(doc[3], 1), doc[2]]
-        attrs = {
-            "POS": ["PROPN", "PROPN"],
-            "LEMMA": ["New", "York"],
-            "DEP": ["pobj", "compound"],
-        }
-        retokenizer.split(doc[3], ["New", "York"], heads=heads, attrs=attrs)
-
-    gold_text = ["I", "live", "in", "New", "York", "right", "now"]
-    assert [token.text for token in doc] == gold_text
-    gold_lemma = ["I", "live", "in", "New", "York", "right", "now"]
-    assert [token.lemma_ for token in doc] == gold_lemma
-    vectors_2 = [token.vector for token in doc]
-    assert len(vectors_2) == len(doc)
-    assert vectors_1[0].tolist() == vectors_2[0].tolist()
-    assert vectors_1[1].tolist() == vectors_2[1].tolist()
-    assert vectors_1[2].tolist() == vectors_2[2].tolist()
-    assert vectors_1[4].tolist() == vectors_2[5].tolist()
-    assert vectors_1[5].tolist() == vectors_2[6].tolist()
-
-
-@pytest.mark.issue(3549)
-def test_issue3549(en_vocab):
-    """Test that match pattern validation doesn't raise on empty errors."""
-    matcher = Matcher(en_vocab, validate=True)
-    pattern = [{"LOWER": "hello"}, {"LOWER": "world"}]
-    matcher.add("GOOD", [pattern])
-    with pytest.raises(MatchPatternError):
-        matcher.add("BAD", [[{"X": "Y"}]])
-
-
-@pytest.mark.skip("Matching currently only works on strings and integers")
-@pytest.mark.issue(3555)
-def test_issue3555(en_vocab):
-    """Test that custom extensions with default None don't break matcher."""
-    Token.set_extension("issue3555", default=None)
-    matcher = Matcher(en_vocab)
-    pattern = [{"ORTH": "have"}, {"_": {"issue3555": True}}]
-    matcher.add("TEST", [pattern])
-    doc = Doc(en_vocab, words=["have", "apple"])
-    matcher(doc)
-
-
-@pytest.mark.issue(3611)
-def test_issue3611():
-    """Test whether adding n-grams in the textcat works even when n > token length of some docs"""
-    unique_classes = ["offensive", "inoffensive"]
-    x_train = [
-        "This is an offensive text",
-        "This is the second offensive text",
-        "inoff",
-    ]
-    y_train = ["offensive", "offensive", "inoffensive"]
-    nlp = spacy.blank("en")
-    # preparing the data
-    train_data = []
-    for text, train_instance in zip(x_train, y_train):
-        cat_dict = {label: label == train_instance for label in unique_classes}
-        train_data.append(Example.from_dict(nlp.make_doc(text), {"cats": cat_dict}))
-    # add a text categorizer component
-    model = {
-        "@architectures": "spacy.TextCatBOW.v1",
-        "exclusive_classes": True,
-        "ngram_size": 2,
-        "no_output_layer": False,
-    }
-    textcat = nlp.add_pipe("textcat", config={"model": model}, last=True)
-    for label in unique_classes:
-        textcat.add_label(label)
-    # training the network
-    with nlp.select_pipes(enable="textcat"):
-        optimizer = nlp.initialize()
-        for i in range(3):
-            losses = {}
-            batches = minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
-
-            for batch in batches:
-                nlp.update(examples=batch, sgd=optimizer, drop=0.1, losses=losses)
-
-
-@pytest.mark.issue(3625)
-def test_issue3625():
-    """Test that default punctuation rules applies to hindi unicode characters"""
-    nlp = Hindi()
-    doc = nlp("hi. how हुए. होटल, होटल")
-    expected = ["hi", ".", "how", "हुए", ".", "होटल", ",", "होटल"]
-    assert [token.text for token in doc] == expected
-
-
-@pytest.mark.issue(3803)
-def test_issue3803():
-    """Test that spanish num-like tokens have True for like_num attribute."""
-    nlp = Spanish()
-    text = "2 dos 1000 mil 12 doce"
-    doc = nlp(text)
-
-    assert [t.like_num for t in doc] == [True, True, True, True, True, True]
-
-
-def _parser_example(parser):
-    doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
-    gold = {"heads": [1, 1, 3, 3], "deps": ["right", "ROOT", "left", "ROOT"]}
-    return Example.from_dict(doc, gold)
-
-
-@pytest.mark.issue(3830)
-def test_issue3830_no_subtok():
-    """Test that the parser doesn't have subtok label if not learn_tokens"""
-    config = {
-        "learn_tokens": False,
-    }
-    model = registry.resolve({"model": DEFAULT_PARSER_MODEL}, validate=True)["model"]
-    parser = DependencyParser(Vocab(), model, **config)
-    parser.add_label("nsubj")
-    assert "subtok" not in parser.labels
-    parser.initialize(lambda: [_parser_example(parser)])
-    assert "subtok" not in parser.labels
-
-
-@pytest.mark.issue(3830)
-def test_issue3830_with_subtok():
-    """Test that the parser does have subtok label if learn_tokens=True."""
-    config = {
-        "learn_tokens": True,
-    }
-    model = registry.resolve({"model": DEFAULT_PARSER_MODEL}, validate=True)["model"]
-    parser = DependencyParser(Vocab(), model, **config)
-    parser.add_label("nsubj")
-    assert "subtok" not in parser.labels
-    parser.initialize(lambda: [_parser_example(parser)])
-    assert "subtok" in parser.labels
-
-
-@pytest.mark.issue(3839)
-def test_issue3839(en_vocab):
-    """Test that match IDs returned by the matcher are correct, are in the string"""
-    doc = Doc(en_vocab, words=["terrific", "group", "of", "people"])
-    matcher = Matcher(en_vocab)
-    match_id = "PATTERN"
-    pattern1 = [{"LOWER": "terrific"}, {"OP": "?"}, {"LOWER": "group"}]
-    pattern2 = [{"LOWER": "terrific"}, {"OP": "?"}, {"OP": "?"}, {"LOWER": "group"}]
-    matcher.add(match_id, [pattern1])
-    matches = matcher(doc)
-    assert matches[0][0] == en_vocab.strings[match_id]
-    matcher = Matcher(en_vocab)
-    matcher.add(match_id, [pattern2])
-    matches = matcher(doc)
-    assert matches[0][0] == en_vocab.strings[match_id]
-
-
-@pytest.mark.parametrize(
-    "sentence",
-    [
-        "The story was to the effect that a young American student recently called on Professor Christlieb with a letter of introduction.",
-        "The next month Barry Siddall joined Stoke City on a free transfer, after Chris Pearce had established himself as the Vale's #1.",
-        "The next month Barry Siddall joined Stoke City on a free transfer, after Chris Pearce had established himself as the Vale's number one",
-        "Indeed, making the one who remains do all the work has installed him into a position of such insolent tyranny, it will take a month at least to reduce him to his proper proportions.",
-        "It was a missed assignment, but it shouldn't have resulted in a turnover ...",
-    ],
-)
-@pytest.mark.issue(3869)
-def test_issue3869(sentence):
-    """Test that the Doc's count_by function works consistently"""
-    nlp = English()
-    doc = nlp(sentence)
-    count = 0
-    for token in doc:
-        count += token.is_alpha
-    assert count == doc.count_by(IS_ALPHA).get(1, 0)
-
-
-@pytest.mark.issue(3879)
-def test_issue3879(en_vocab):
-    doc = Doc(en_vocab, words=["This", "is", "a", "test", "."])
-    assert len(doc) == 5
-    pattern = [{"ORTH": "This", "OP": "?"}, {"OP": "?"}, {"ORTH": "test"}]
-    matcher = Matcher(en_vocab)
-    matcher.add("TEST", [pattern])
-    assert len(matcher(doc)) == 2  # fails because of a FP match 'is a test'
-
-
-@pytest.mark.issue(3880)
-def test_issue3880():
-    """Test that `nlp.pipe()` works when an empty string ends the batch.
-
-    Fixed in v7.0.5 of Thinc.
-    """
-    texts = ["hello", "world", "", ""]
-    nlp = English()
-    nlp.add_pipe("parser").add_label("dep")
-    nlp.add_pipe("ner").add_label("PERSON")
-    nlp.add_pipe("tagger").add_label("NN")
-    nlp.initialize()
-    for doc in nlp.pipe(texts):
-        pass
-
-
-@pytest.mark.issue(3882)
-def test_issue3882(en_vocab):
-    """Test that displaCy doesn't serialize the doc.user_data when making a
-    copy of the Doc.
-    """
-    doc = Doc(en_vocab, words=["Hello", "world"], deps=["dep", "dep"])
-    doc.user_data["test"] = set()
-    parse_deps(doc)
-
-
-@pytest.mark.issue(3951)
-def test_issue3951(en_vocab):
-    """Test that combinations of optional rules are matched correctly."""
-    matcher = Matcher(en_vocab)
-    pattern = [
-        {"LOWER": "hello"},
-        {"LOWER": "this", "OP": "?"},
-        {"OP": "?"},
-        {"LOWER": "world"},
-    ]
-    matcher.add("TEST", [pattern])
-    doc = Doc(en_vocab, words=["Hello", "my", "new", "world"])
-    matches = matcher(doc)
-    assert len(matches) == 0
-
-
-@pytest.mark.issue(3959)
-def test_issue3959():
-    """Ensure that a modified pos attribute is serialized correctly."""
-    nlp = English()
-    doc = nlp(
-        "displaCy uses JavaScript, SVG and CSS to show you how computers understand language"
-    )
-    assert doc[0].pos_ == ""
-    doc[0].pos_ = "NOUN"
-    assert doc[0].pos_ == "NOUN"
-    # usually this is already True when starting from proper models instead of blank English
-    with make_tempdir() as tmp_dir:
-        file_path = tmp_dir / "my_doc"
-        doc.to_disk(file_path)
-        doc2 = nlp("")
-        doc2.from_disk(file_path)
-        assert doc2[0].pos_ == "NOUN"
-
-
-@pytest.mark.issue(3962)
-def test_issue3962(en_vocab):
-    """Ensure that as_doc does not result in out-of-bound access of tokens.
-    This is achieved by setting the head to itself if it would lie out of the span otherwise."""
-    # fmt: off
-    words = ["He", "jests", "at", "scars", ",", "that", "never", "felt", "a", "wound", "."]
-    heads = [1, 7, 1, 2, 7, 7, 7, 7, 9, 7, 7]
-    deps = ["nsubj", "ccomp", "prep", "pobj", "punct", "nsubj", "neg", "ROOT", "det", "dobj", "punct"]
-    # fmt: on
-    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
-    span2 = doc[1:5]  # "jests at scars ,"
-    doc2 = span2.as_doc()
-    doc2_json = doc2.to_json()
-    assert doc2_json
-    # head set to itself, being the new artificial root
-    assert doc2[0].head.text == "jests"
-    assert doc2[0].dep_ == "dep"
-    assert doc2[1].head.text == "jests"
-    assert doc2[1].dep_ == "prep"
-    assert doc2[2].head.text == "at"
-    assert doc2[2].dep_ == "pobj"
-    assert doc2[3].head.text == "jests"  # head set to the new artificial root
-    assert doc2[3].dep_ == "dep"
-    # We should still have 1 sentence
-    assert len(list(doc2.sents)) == 1
-    span3 = doc[6:9]  # "never felt a"
-    doc3 = span3.as_doc()
-    doc3_json = doc3.to_json()
-    assert doc3_json
-    assert doc3[0].head.text == "felt"
-    assert doc3[0].dep_ == "neg"
-    assert doc3[1].head.text == "felt"
-    assert doc3[1].dep_ == "ROOT"
-    assert doc3[2].head.text == "felt"  # head set to ancestor
-    assert doc3[2].dep_ == "dep"
-    # We should still have 1 sentence as "a" can be attached to "felt" instead of "wound"
-    assert len(list(doc3.sents)) == 1
-
-
-@pytest.mark.issue(3962)
-def test_issue3962_long(en_vocab):
-    """Ensure that as_doc does not result in out-of-bound access of tokens.
-    This is achieved by setting the head to itself if it would lie out of the span otherwise."""
-    # fmt: off
-    words = ["He", "jests", "at", "scars", ".", "They", "never", "felt", "a", "wound", "."]
-    heads = [1, 1, 1, 2, 1, 7, 7, 7, 9, 7, 7]
-    deps = ["nsubj", "ROOT", "prep", "pobj", "punct", "nsubj", "neg", "ROOT", "det", "dobj", "punct"]
-    # fmt: on
-    two_sent_doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
-    span2 = two_sent_doc[1:7]  # "jests at scars. They never"
-    doc2 = span2.as_doc()
-    doc2_json = doc2.to_json()
-    assert doc2_json
-    # head set to itself, being the new artificial root (in sentence 1)
-    assert doc2[0].head.text == "jests"
-    assert doc2[0].dep_ == "ROOT"
-    assert doc2[1].head.text == "jests"
-    assert doc2[1].dep_ == "prep"
-    assert doc2[2].head.text == "at"
-    assert doc2[2].dep_ == "pobj"
-    assert doc2[3].head.text == "jests"
-    assert doc2[3].dep_ == "punct"
-    # head set to itself, being the new artificial root (in sentence 2)
-    assert doc2[4].head.text == "They"
-    assert doc2[4].dep_ == "dep"
-    # head set to the new artificial head (in sentence 2)
-    assert doc2[4].head.text == "They"
-    assert doc2[4].dep_ == "dep"
-    # We should still have 2 sentences
-    sents = list(doc2.sents)
-    assert len(sents) == 2
-    assert sents[0].text == "jests at scars ."
-    assert sents[1].text == "They never"
-
-
-@pytest.mark.issue(3972)
-def test_issue3972(en_vocab):
-    """Test that the PhraseMatcher returns duplicates for duplicate match IDs."""
-    matcher = PhraseMatcher(en_vocab)
-    matcher.add("A", [Doc(en_vocab, words=["New", "York"])])
-    matcher.add("B", [Doc(en_vocab, words=["New", "York"])])
-    doc = Doc(en_vocab, words=["I", "live", "in", "New", "York"])
-    matches = matcher(doc)
-
-    assert len(matches) == 2
-
-    # We should have a match for each of the two rules
-    found_ids = [en_vocab.strings[ent_id] for (ent_id, _, _) in matches]
-    assert "A" in found_ids
-    assert "B" in found_ids
diff --git a/spacy/tests/regression/test_issue4001-4500.py b/spacy/tests/regression/test_issue4001-4500.py
deleted file mode 100644
index 7b7c304a3..000000000
--- a/spacy/tests/regression/test_issue4001-4500.py
+++ /dev/null
@@ -1,447 +0,0 @@
-import pytest
-from spacy.pipeline import TrainablePipe
-from spacy.matcher import PhraseMatcher, Matcher
-from spacy.tokens import Doc, Span, DocBin
-from spacy.training import Example, Corpus
-from spacy.training.converters import json_to_docs
-from spacy.vocab import Vocab
-from spacy.lang.en import English
-from spacy.util import minibatch, ensure_path, load_model
-from spacy.util import compile_prefix_regex, compile_suffix_regex, compile_infix_regex
-from spacy.tokenizer import Tokenizer
-from spacy.lang.el import Greek
-from spacy.language import Language
-import spacy
-from thinc.api import compounding
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(4002)
-def test_issue4002(en_vocab):
-    """Test that the PhraseMatcher can match on overwritten NORM attributes."""
-    matcher = PhraseMatcher(en_vocab, attr="NORM")
-    pattern1 = Doc(en_vocab, words=["c", "d"])
-    assert [t.norm_ for t in pattern1] == ["c", "d"]
-    matcher.add("TEST", [pattern1])
-    doc = Doc(en_vocab, words=["a", "b", "c", "d"])
-    assert [t.norm_ for t in doc] == ["a", "b", "c", "d"]
-    matches = matcher(doc)
-    assert len(matches) == 1
-    matcher = PhraseMatcher(en_vocab, attr="NORM")
-    pattern2 = Doc(en_vocab, words=["1", "2"])
-    pattern2[0].norm_ = "c"
-    pattern2[1].norm_ = "d"
-    assert [t.norm_ for t in pattern2] == ["c", "d"]
-    matcher.add("TEST", [pattern2])
-    matches = matcher(doc)
-    assert len(matches) == 1
-
-
-@pytest.mark.issue(4030)
-def test_issue4030():
-    """Test whether textcat works fine with empty doc"""
-    unique_classes = ["offensive", "inoffensive"]
-    x_train = [
-        "This is an offensive text",
-        "This is the second offensive text",
-        "inoff",
-    ]
-    y_train = ["offensive", "offensive", "inoffensive"]
-    nlp = spacy.blank("en")
-    # preparing the data
-    train_data = []
-    for text, train_instance in zip(x_train, y_train):
-        cat_dict = {label: label == train_instance for label in unique_classes}
-        train_data.append(Example.from_dict(nlp.make_doc(text), {"cats": cat_dict}))
-    # add a text categorizer component
-    model = {
-        "@architectures": "spacy.TextCatBOW.v1",
-        "exclusive_classes": True,
-        "ngram_size": 2,
-        "no_output_layer": False,
-    }
-    textcat = nlp.add_pipe("textcat", config={"model": model}, last=True)
-    for label in unique_classes:
-        textcat.add_label(label)
-    # training the network
-    with nlp.select_pipes(enable="textcat"):
-        optimizer = nlp.initialize()
-        for i in range(3):
-            losses = {}
-            batches = minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
-
-            for batch in batches:
-                nlp.update(examples=batch, sgd=optimizer, drop=0.1, losses=losses)
-    # processing of an empty doc should result in 0.0 for all categories
-    doc = nlp("")
-    assert doc.cats["offensive"] == 0.0
-    assert doc.cats["inoffensive"] == 0.0
-
-
-@pytest.mark.issue(4042)
-def test_issue4042():
-    """Test that serialization of an EntityRuler before NER works fine."""
-    nlp = English()
-    # add ner pipe
-    ner = nlp.add_pipe("ner")
-    ner.add_label("SOME_LABEL")
-    nlp.initialize()
-    # Add entity ruler
-    patterns = [
-        {"label": "MY_ORG", "pattern": "Apple"},
-        {"label": "MY_GPE", "pattern": [{"lower": "san"}, {"lower": "francisco"}]},
-    ]
-    # works fine with "after"
-    ruler = nlp.add_pipe("entity_ruler", before="ner")
-    ruler.add_patterns(patterns)
-    doc1 = nlp("What do you think about Apple ?")
-    assert doc1.ents[0].label_ == "MY_ORG"
-
-    with make_tempdir() as d:
-        output_dir = ensure_path(d)
-        if not output_dir.exists():
-            output_dir.mkdir()
-        nlp.to_disk(output_dir)
-        nlp2 = load_model(output_dir)
-        doc2 = nlp2("What do you think about Apple ?")
-        assert doc2.ents[0].label_ == "MY_ORG"
-
-
-@pytest.mark.issue(4042)
-def test_issue4042_bug2():
-    """
-    Test that serialization of an NER works fine when new labels were added.
-    This is the second bug of two bugs underlying the issue 4042.
-    """
-    nlp1 = English()
-    # add ner pipe
-    ner1 = nlp1.add_pipe("ner")
-    ner1.add_label("SOME_LABEL")
-    nlp1.initialize()
-    # add a new label to the doc
-    doc1 = nlp1("What do you think about Apple ?")
-    assert len(ner1.labels) == 1
-    assert "SOME_LABEL" in ner1.labels
-    apple_ent = Span(doc1, 5, 6, label="MY_ORG")
-    doc1.ents = list(doc1.ents) + [apple_ent]
-    # Add the label explicitly. Previously we didn't require this.
-    ner1.add_label("MY_ORG")
-    ner1(doc1)
-    assert len(ner1.labels) == 2
-    assert "SOME_LABEL" in ner1.labels
-    assert "MY_ORG" in ner1.labels
-    with make_tempdir() as d:
-        # assert IO goes fine
-        output_dir = ensure_path(d)
-        if not output_dir.exists():
-            output_dir.mkdir()
-        ner1.to_disk(output_dir)
-        config = {}
-        ner2 = nlp1.create_pipe("ner", config=config)
-        ner2.from_disk(output_dir)
-        assert len(ner2.labels) == 2
-
-
-@pytest.mark.issue(4054)
-def test_issue4054(en_vocab):
-    """Test that a new blank model can be made with a vocab from file,
-    and that serialization does not drop the language at any point."""
-    nlp1 = English()
-    vocab1 = nlp1.vocab
-    with make_tempdir() as d:
-        vocab_dir = ensure_path(d / "vocab")
-        if not vocab_dir.exists():
-            vocab_dir.mkdir()
-        vocab1.to_disk(vocab_dir)
-        vocab2 = Vocab().from_disk(vocab_dir)
-        nlp2 = spacy.blank("en", vocab=vocab2)
-        nlp_dir = ensure_path(d / "nlp")
-        if not nlp_dir.exists():
-            nlp_dir.mkdir()
-        nlp2.to_disk(nlp_dir)
-        nlp3 = load_model(nlp_dir)
-        assert nlp3.lang == "en"
-
-
-@pytest.mark.issue(4120)
-def test_issue4120(en_vocab):
-    """Test that matches without a final {OP: ?} token are returned."""
-    matcher = Matcher(en_vocab)
-    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}]])
-    doc1 = Doc(en_vocab, words=["a"])
-    assert len(matcher(doc1)) == 1  # works
-    doc2 = Doc(en_vocab, words=["a", "b", "c"])
-    assert len(matcher(doc2)) == 2  # fixed
-    matcher = Matcher(en_vocab)
-    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b"}]])
-    doc3 = Doc(en_vocab, words=["a", "b", "b", "c"])
-    assert len(matcher(doc3)) == 2  # works
-    matcher = Matcher(en_vocab)
-    matcher.add("TEST", [[{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b", "OP": "?"}]])
-    doc4 = Doc(en_vocab, words=["a", "b", "b", "c"])
-    assert len(matcher(doc4)) == 3  # fixed
-
-
-@pytest.mark.issue(4133)
-def test_issue4133(en_vocab):
-    nlp = English()
-    vocab_bytes = nlp.vocab.to_bytes()
-    words = ["Apple", "is", "looking", "at", "buying", "a", "startup"]
-    pos = ["NOUN", "VERB", "ADP", "VERB", "PROPN", "NOUN", "ADP"]
-    doc = Doc(en_vocab, words=words)
-    for i, token in enumerate(doc):
-        token.pos_ = pos[i]
-    # usually this is already True when starting from proper models instead of blank English
-    doc_bytes = doc.to_bytes()
-    vocab = Vocab()
-    vocab = vocab.from_bytes(vocab_bytes)
-    doc = Doc(vocab).from_bytes(doc_bytes)
-    actual = []
-    for token in doc:
-        actual.append(token.pos_)
-    assert actual == pos
-
-
-@pytest.mark.issue(4190)
-def test_issue4190():
-    def customize_tokenizer(nlp):
-        prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
-        suffix_re = compile_suffix_regex(nlp.Defaults.suffixes)
-        infix_re = compile_infix_regex(nlp.Defaults.infixes)
-        # Remove all exceptions where a single letter is followed by a period (e.g. 'h.')
-        exceptions = {
-            k: v
-            for k, v in dict(nlp.Defaults.tokenizer_exceptions).items()
-            if not (len(k) == 2 and k[1] == ".")
-        }
-        new_tokenizer = Tokenizer(
-            nlp.vocab,
-            exceptions,
-            prefix_search=prefix_re.search,
-            suffix_search=suffix_re.search,
-            infix_finditer=infix_re.finditer,
-            token_match=nlp.tokenizer.token_match,
-        )
-        nlp.tokenizer = new_tokenizer
-
-    test_string = "Test c."
-    # Load default language
-    nlp_1 = English()
-    doc_1a = nlp_1(test_string)
-    result_1a = [token.text for token in doc_1a]  # noqa: F841
-    # Modify tokenizer
-    customize_tokenizer(nlp_1)
-    doc_1b = nlp_1(test_string)
-    result_1b = [token.text for token in doc_1b]
-    # Save and Reload
-    with make_tempdir() as model_dir:
-        nlp_1.to_disk(model_dir)
-        nlp_2 = load_model(model_dir)
-    # This should be the modified tokenizer
-    doc_2 = nlp_2(test_string)
-    result_2 = [token.text for token in doc_2]
-    assert result_1b == result_2
-
-
-@pytest.mark.issue(4267)
-def test_issue4267():
-    """Test that running an entity_ruler after ner gives consistent results"""
-    nlp = English()
-    ner = nlp.add_pipe("ner")
-    ner.add_label("PEOPLE")
-    nlp.initialize()
-    assert "ner" in nlp.pipe_names
-    # assert that we have correct IOB annotations
-    doc1 = nlp("hi")
-    assert doc1.has_annotation("ENT_IOB")
-    for token in doc1:
-        assert token.ent_iob == 2
-    # add entity ruler and run again
-    patterns = [{"label": "SOFTWARE", "pattern": "spacy"}]
-    ruler = nlp.add_pipe("entity_ruler")
-    ruler.add_patterns(patterns)
-    assert "entity_ruler" in nlp.pipe_names
-    assert "ner" in nlp.pipe_names
-    # assert that we still have correct IOB annotations
-    doc2 = nlp("hi")
-    assert doc2.has_annotation("ENT_IOB")
-    for token in doc2:
-        assert token.ent_iob == 2
-
-
-@pytest.mark.skip(reason="lemmatizer lookups no longer in vocab")
-@pytest.mark.issue(4272)
-def test_issue4272():
-    """Test that lookup table can be accessed from Token.lemma if no POS tags
-    are available."""
-    nlp = Greek()
-    doc = nlp("Χθες")
-    assert doc[0].lemma_
-
-
-def test_multiple_predictions():
-    class DummyPipe(TrainablePipe):
-        def __init__(self):
-            self.model = "dummy_model"
-
-        def predict(self, docs):
-            return ([1, 2, 3], [4, 5, 6])
-
-        def set_annotations(self, docs, scores):
-            return docs
-
-    nlp = Language()
-    doc = nlp.make_doc("foo")
-    dummy_pipe = DummyPipe()
-    dummy_pipe(doc)
-
-
-@pytest.mark.issue(4313)
-def test_issue4313():
-    """This should not crash or exit with some strange error code"""
-    beam_width = 16
-    beam_density = 0.0001
-    nlp = English()
-    config = {
-        "beam_width": beam_width,
-        "beam_density": beam_density,
-    }
-    ner = nlp.add_pipe("beam_ner", config=config)
-    ner.add_label("SOME_LABEL")
-    nlp.initialize()
-    # add a new label to the doc
-    doc = nlp("What do you think about Apple ?")
-    assert len(ner.labels) == 1
-    assert "SOME_LABEL" in ner.labels
-    apple_ent = Span(doc, 5, 6, label="MY_ORG")
-    doc.ents = list(doc.ents) + [apple_ent]
-
-    # ensure the beam_parse still works with the new label
-    docs = [doc]
-    ner.beam_parse(docs, drop=0.0, beam_width=beam_width, beam_density=beam_density)
-    assert len(ner.labels) == 2
-    assert "MY_ORG" in ner.labels
-
-
-@pytest.mark.issue(4348)
-def test_issue4348():
-    """Test that training the tagger with empty data, doesn't throw errors"""
-    nlp = English()
-    example = Example.from_dict(nlp.make_doc(""), {"tags": []})
-    TRAIN_DATA = [example, example]
-    tagger = nlp.add_pipe("tagger")
-    tagger.add_label("A")
-    optimizer = nlp.initialize()
-    for i in range(5):
-        losses = {}
-        batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
-        for batch in batches:
-            nlp.update(batch, sgd=optimizer, losses=losses)
-
-
-@pytest.mark.issue(4367)
-def test_issue4367():
-    """Test that docbin init goes well"""
-    DocBin()
-    DocBin(attrs=["LEMMA"])
-    DocBin(attrs=["LEMMA", "ENT_IOB", "ENT_TYPE"])
-
-
-@pytest.mark.issue(4373)
-def test_issue4373():
-    """Test that PhraseMatcher.vocab can be accessed (like Matcher.vocab)."""
-    matcher = Matcher(Vocab())
-    assert isinstance(matcher.vocab, Vocab)
-    matcher = PhraseMatcher(Vocab())
-    assert isinstance(matcher.vocab, Vocab)
-
-
-@pytest.mark.issue(4402)
-def test_issue4402():
-    json_data = {
-        "id": 0,
-        "paragraphs": [
-            {
-                "raw": "How should I cook bacon in an oven?\nI've heard of people cooking bacon in an oven.",
-                "sentences": [
-                    {
-                        "tokens": [
-                            {"id": 0, "orth": "How", "ner": "O"},
-                            {"id": 1, "orth": "should", "ner": "O"},
-                            {"id": 2, "orth": "I", "ner": "O"},
-                            {"id": 3, "orth": "cook", "ner": "O"},
-                            {"id": 4, "orth": "bacon", "ner": "O"},
-                            {"id": 5, "orth": "in", "ner": "O"},
-                            {"id": 6, "orth": "an", "ner": "O"},
-                            {"id": 7, "orth": "oven", "ner": "O"},
-                            {"id": 8, "orth": "?", "ner": "O"},
-                        ],
-                        "brackets": [],
-                    },
-                    {
-                        "tokens": [
-                            {"id": 9, "orth": "\n", "ner": "O"},
-                            {"id": 10, "orth": "I", "ner": "O"},
-                            {"id": 11, "orth": "'ve", "ner": "O"},
-                            {"id": 12, "orth": "heard", "ner": "O"},
-                            {"id": 13, "orth": "of", "ner": "O"},
-                            {"id": 14, "orth": "people", "ner": "O"},
-                            {"id": 15, "orth": "cooking", "ner": "O"},
-                            {"id": 16, "orth": "bacon", "ner": "O"},
-                            {"id": 17, "orth": "in", "ner": "O"},
-                            {"id": 18, "orth": "an", "ner": "O"},
-                            {"id": 19, "orth": "oven", "ner": "O"},
-                            {"id": 20, "orth": ".", "ner": "O"},
-                        ],
-                        "brackets": [],
-                    },
-                ],
-                "cats": [
-                    {"label": "baking", "value": 1.0},
-                    {"label": "not_baking", "value": 0.0},
-                ],
-            },
-            {
-                "raw": "What is the difference between white and brown eggs?\n",
-                "sentences": [
-                    {
-                        "tokens": [
-                            {"id": 0, "orth": "What", "ner": "O"},
-                            {"id": 1, "orth": "is", "ner": "O"},
-                            {"id": 2, "orth": "the", "ner": "O"},
-                            {"id": 3, "orth": "difference", "ner": "O"},
-                            {"id": 4, "orth": "between", "ner": "O"},
-                            {"id": 5, "orth": "white", "ner": "O"},
-                            {"id": 6, "orth": "and", "ner": "O"},
-                            {"id": 7, "orth": "brown", "ner": "O"},
-                            {"id": 8, "orth": "eggs", "ner": "O"},
-                            {"id": 9, "orth": "?", "ner": "O"},
-                        ],
-                        "brackets": [],
-                    },
-                    {"tokens": [{"id": 10, "orth": "\n", "ner": "O"}], "brackets": []},
-                ],
-                "cats": [
-                    {"label": "baking", "value": 0.0},
-                    {"label": "not_baking", "value": 1.0},
-                ],
-            },
-        ],
-    }
-    nlp = English()
-    attrs = ["ORTH", "SENT_START", "ENT_IOB", "ENT_TYPE"]
-    with make_tempdir() as tmpdir:
-        output_file = tmpdir / "test4402.spacy"
-        docs = json_to_docs([json_data])
-        data = DocBin(docs=docs, attrs=attrs).to_bytes()
-        with output_file.open("wb") as file_:
-            file_.write(data)
-        reader = Corpus(output_file)
-        train_data = list(reader(nlp))
-        assert len(train_data) == 2
-
-        split_train_data = []
-        for eg in train_data:
-            split_train_data.extend(eg.split_sents())
-        assert len(split_train_data) == 4
diff --git a/spacy/tests/regression/test_issue4501-5000.py b/spacy/tests/regression/test_issue4501-5000.py
deleted file mode 100644
index 07a00d2b7..000000000
--- a/spacy/tests/regression/test_issue4501-5000.py
+++ /dev/null
@@ -1,266 +0,0 @@
-import pytest
-from spacy.tokens import Doc, Span, DocBin
-from spacy.training import Example
-from spacy.training.converters.conllu_to_docs import conllu_to_docs
-from spacy.lang.en import English
-from spacy.kb import KnowledgeBase
-from spacy.vocab import Vocab
-from spacy.language import Language
-from spacy.util import ensure_path, load_model_from_path
-import numpy
-import pickle
-from thinc.api import NumpyOps, get_current_ops
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(4528)
-def test_issue4528(en_vocab):
-    """Test that user_data is correctly serialized in DocBin."""
-    doc = Doc(en_vocab, words=["hello", "world"])
-    doc.user_data["foo"] = "bar"
-    # This is how extension attribute values are stored in the user data
-    doc.user_data[("._.", "foo", None, None)] = "bar"
-    doc_bin = DocBin(store_user_data=True)
-    doc_bin.add(doc)
-    doc_bin_bytes = doc_bin.to_bytes()
-    new_doc_bin = DocBin(store_user_data=True).from_bytes(doc_bin_bytes)
-    new_doc = list(new_doc_bin.get_docs(en_vocab))[0]
-    assert new_doc.user_data["foo"] == "bar"
-    assert new_doc.user_data[("._.", "foo", None, None)] == "bar"
-
-
-@pytest.mark.parametrize(
-    "text,words", [("A'B C", ["A", "'", "B", "C"]), ("A-B", ["A-B"])]
-)
-def test_gold_misaligned(en_tokenizer, text, words):
-    doc = en_tokenizer(text)
-    Example.from_dict(doc, {"words": words})
-
-
-@pytest.mark.issue(4651)
-def test_issue4651_with_phrase_matcher_attr():
-    """Test that the EntityRuler PhraseMatcher is deserialized correctly using
-    the method from_disk when the EntityRuler argument phrase_matcher_attr is
-    specified.
-    """
-    text = "Spacy is a python library for nlp"
-    nlp = English()
-    patterns = [{"label": "PYTHON_LIB", "pattern": "spacy", "id": "spaCy"}]
-    ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
-    ruler.add_patterns(patterns)
-    doc = nlp(text)
-    res = [(ent.text, ent.label_, ent.ent_id_) for ent in doc.ents]
-    nlp_reloaded = English()
-    with make_tempdir() as d:
-        file_path = d / "entityruler"
-        ruler.to_disk(file_path)
-        nlp_reloaded.add_pipe("entity_ruler").from_disk(file_path)
-    doc_reloaded = nlp_reloaded(text)
-    res_reloaded = [(ent.text, ent.label_, ent.ent_id_) for ent in doc_reloaded.ents]
-    assert res == res_reloaded
-
-
-@pytest.mark.issue(4651)
-def test_issue4651_without_phrase_matcher_attr():
-    """Test that the EntityRuler PhraseMatcher is deserialized correctly using
-    the method from_disk when the EntityRuler argument phrase_matcher_attr is
-    not specified.
-    """
-    text = "Spacy is a python library for nlp"
-    nlp = English()
-    patterns = [{"label": "PYTHON_LIB", "pattern": "spacy", "id": "spaCy"}]
-    ruler = nlp.add_pipe("entity_ruler")
-    ruler.add_patterns(patterns)
-    doc = nlp(text)
-    res = [(ent.text, ent.label_, ent.ent_id_) for ent in doc.ents]
-    nlp_reloaded = English()
-    with make_tempdir() as d:
-        file_path = d / "entityruler"
-        ruler.to_disk(file_path)
-        nlp_reloaded.add_pipe("entity_ruler").from_disk(file_path)
-    doc_reloaded = nlp_reloaded(text)
-    res_reloaded = [(ent.text, ent.label_, ent.ent_id_) for ent in doc_reloaded.ents]
-    assert res == res_reloaded
-
-
-@pytest.mark.issue(4665)
-def test_issue4665():
-    """
-    conllu_to_docs should not raise an exception if the HEAD column contains an
-    underscore
-    """
-    input_data = """
-1	[	_	PUNCT	-LRB-	_	_	punct	_	_
-2	This	_	DET	DT	_	_	det	_	_
-3	killing	_	NOUN	NN	_	_	nsubj	_	_
-4	of	_	ADP	IN	_	_	case	_	_
-5	a	_	DET	DT	_	_	det	_	_
-6	respected	_	ADJ	JJ	_	_	amod	_	_
-7	cleric	_	NOUN	NN	_	_	nmod	_	_
-8	will	_	AUX	MD	_	_	aux	_	_
-9	be	_	AUX	VB	_	_	aux	_	_
-10	causing	_	VERB	VBG	_	_	root	_	_
-11	us	_	PRON	PRP	_	_	iobj	_	_
-12	trouble	_	NOUN	NN	_	_	dobj	_	_
-13	for	_	ADP	IN	_	_	case	_	_
-14	years	_	NOUN	NNS	_	_	nmod	_	_
-15	to	_	PART	TO	_	_	mark	_	_
-16	come	_	VERB	VB	_	_	acl	_	_
-17	.	_	PUNCT	.	_	_	punct	_	_
-18	]	_	PUNCT	-RRB-	_	_	punct	_	_
-"""
-    conllu_to_docs(input_data)
-
-
-@pytest.mark.issue(4674)
-def test_issue4674():
-    """Test that setting entities with overlapping identifiers does not mess up IO"""
-    nlp = English()
-    kb = KnowledgeBase(nlp.vocab, entity_vector_length=3)
-    vector1 = [0.9, 1.1, 1.01]
-    vector2 = [1.8, 2.25, 2.01]
-    with pytest.warns(UserWarning):
-        kb.set_entities(
-            entity_list=["Q1", "Q1"],
-            freq_list=[32, 111],
-            vector_list=[vector1, vector2],
-        )
-    assert kb.get_size_entities() == 1
-    # dumping to file & loading back in
-    with make_tempdir() as d:
-        dir_path = ensure_path(d)
-        if not dir_path.exists():
-            dir_path.mkdir()
-        file_path = dir_path / "kb"
-        kb.to_disk(str(file_path))
-        kb2 = KnowledgeBase(nlp.vocab, entity_vector_length=3)
-        kb2.from_disk(str(file_path))
-    assert kb2.get_size_entities() == 1
-
-
-@pytest.mark.skip(reason="API change: disable just disables, new exclude arg")
-@pytest.mark.issue(4707)
-def test_issue4707():
-    """Tests that disabled component names are also excluded from nlp.from_disk
-    by default when loading a model.
-    """
-    nlp = English()
-    nlp.add_pipe("sentencizer")
-    nlp.add_pipe("entity_ruler")
-    assert nlp.pipe_names == ["sentencizer", "entity_ruler"]
-    exclude = ["tokenizer", "sentencizer"]
-    with make_tempdir() as tmpdir:
-        nlp.to_disk(tmpdir, exclude=exclude)
-        new_nlp = load_model_from_path(tmpdir, disable=exclude)
-    assert "sentencizer" not in new_nlp.pipe_names
-    assert "entity_ruler" in new_nlp.pipe_names
-
-
-@pytest.mark.issue(4725)
-def test_issue4725_1():
-    """Ensure the pickling of the NER goes well"""
-    vocab = Vocab(vectors_name="test_vocab_add_vector")
-    nlp = English(vocab=vocab)
-    config = {
-        "update_with_oracle_cut_size": 111,
-    }
-    ner = nlp.create_pipe("ner", config=config)
-    with make_tempdir() as tmp_path:
-        with (tmp_path / "ner.pkl").open("wb") as file_:
-            pickle.dump(ner, file_)
-            assert ner.cfg["update_with_oracle_cut_size"] == 111
-
-        with (tmp_path / "ner.pkl").open("rb") as file_:
-            ner2 = pickle.load(file_)
-            assert ner2.cfg["update_with_oracle_cut_size"] == 111
-
-
-@pytest.mark.issue(4725)
-def test_issue4725_2():
-    if isinstance(get_current_ops, NumpyOps):
-        # ensures that this runs correctly and doesn't hang or crash because of the global vectors
-        # if it does crash, it's usually because of calling 'spawn' for multiprocessing (e.g. on Windows),
-        # or because of issues with pickling the NER (cf test_issue4725_1)
-        vocab = Vocab(vectors_name="test_vocab_add_vector")
-        data = numpy.ndarray((5, 3), dtype="f")
-        data[0] = 1.0
-        data[1] = 2.0
-        vocab.set_vector("cat", data[0])
-        vocab.set_vector("dog", data[1])
-        nlp = English(vocab=vocab)
-        nlp.add_pipe("ner")
-        nlp.initialize()
-        docs = ["Kurt is in London."] * 10
-        for _ in nlp.pipe(docs, batch_size=2, n_process=2):
-            pass
-
-
-@pytest.mark.issue(4849)
-def test_issue4849():
-    nlp = English()
-    patterns = [
-        {"label": "PERSON", "pattern": "joe biden", "id": "joe-biden"},
-        {"label": "PERSON", "pattern": "bernie sanders", "id": "bernie-sanders"},
-    ]
-    ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
-    ruler.add_patterns(patterns)
-    text = """
-    The left is starting to take aim at Democratic front-runner Joe Biden.
-    Sen. Bernie Sanders joined in her criticism: "There is no 'middle ground' when it comes to climate policy."
-    """
-    # USING 1 PROCESS
-    count_ents = 0
-    for doc in nlp.pipe([text], n_process=1):
-        count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
-    assert count_ents == 2
-    # USING 2 PROCESSES
-    if isinstance(get_current_ops, NumpyOps):
-        count_ents = 0
-        for doc in nlp.pipe([text], n_process=2):
-            count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
-        assert count_ents == 2
-
-
-@Language.factory("my_pipe")
-class CustomPipe:
-    def __init__(self, nlp, name="my_pipe"):
-        self.name = name
-        Span.set_extension("my_ext", getter=self._get_my_ext)
-        Doc.set_extension("my_ext", default=None)
-
-    def __call__(self, doc):
-        gathered_ext = []
-        for sent in doc.sents:
-            sent_ext = self._get_my_ext(sent)
-            sent._.set("my_ext", sent_ext)
-            gathered_ext.append(sent_ext)
-
-        doc._.set("my_ext", "\n".join(gathered_ext))
-        return doc
-
-    @staticmethod
-    def _get_my_ext(span):
-        return str(span.end)
-
-
-@pytest.mark.issue(4903)
-def test_issue4903():
-    """Ensure that this runs correctly and doesn't hang or crash on Windows /
-    macOS."""
-    nlp = English()
-    nlp.add_pipe("sentencizer")
-    nlp.add_pipe("my_pipe", after="sentencizer")
-    text = ["I like bananas.", "Do you like them?", "No, I prefer wasabi."]
-    if isinstance(get_current_ops(), NumpyOps):
-        docs = list(nlp.pipe(text, n_process=2))
-        assert docs[0].text == "I like bananas."
-        assert docs[1].text == "Do you like them?"
-        assert docs[2].text == "No, I prefer wasabi."
-
-
-@pytest.mark.issue(4924)
-def test_issue4924():
-    nlp = Language()
-    example = Example.from_dict(nlp.make_doc(""), {})
-    nlp.evaluate([example])
diff --git a/spacy/tests/regression/test_issue5001-5500.py b/spacy/tests/regression/test_issue5001-5500.py
deleted file mode 100644
index e1f5231e7..000000000
--- a/spacy/tests/regression/test_issue5001-5500.py
+++ /dev/null
@@ -1,149 +0,0 @@
-import numpy
-from spacy.tokens import Doc, DocBin
-from spacy.attrs import DEP, POS, TAG
-from spacy.lang.en import English
-from spacy.language import Language
-from spacy.lang.en.syntax_iterators import noun_chunks
-from spacy.vocab import Vocab
-import spacy
-from thinc.api import get_current_ops
-import pytest
-
-from ...util import make_tempdir
-
-
-@pytest.mark.issue(5048)
-def test_issue5048(en_vocab):
-    words = ["This", "is", "a", "sentence"]
-    pos_s = ["DET", "VERB", "DET", "NOUN"]
-    spaces = [" ", " ", " ", ""]
-    deps_s = ["dep", "adj", "nn", "atm"]
-    tags_s = ["DT", "VBZ", "DT", "NN"]
-    strings = en_vocab.strings
-    for w in words:
-        strings.add(w)
-    deps = [strings.add(d) for d in deps_s]
-    pos = [strings.add(p) for p in pos_s]
-    tags = [strings.add(t) for t in tags_s]
-    attrs = [POS, DEP, TAG]
-    array = numpy.array(list(zip(pos, deps, tags)), dtype="uint64")
-    doc = Doc(en_vocab, words=words, spaces=spaces)
-    doc.from_array(attrs, array)
-    v1 = [(token.text, token.pos_, token.tag_) for token in doc]
-    doc2 = Doc(en_vocab, words=words, pos=pos_s, deps=deps_s, tags=tags_s)
-    v2 = [(token.text, token.pos_, token.tag_) for token in doc2]
-    assert v1 == v2
-
-
-@pytest.mark.issue(5082)
-def test_issue5082():
-    # Ensure the 'merge_entities' pipeline does something sensible for the vectors of the merged tokens
-    nlp = English()
-    vocab = nlp.vocab
-    array1 = numpy.asarray([0.1, 0.5, 0.8], dtype=numpy.float32)
-    array2 = numpy.asarray([-0.2, -0.6, -0.9], dtype=numpy.float32)
-    array3 = numpy.asarray([0.3, -0.1, 0.7], dtype=numpy.float32)
-    array4 = numpy.asarray([0.5, 0, 0.3], dtype=numpy.float32)
-    array34 = numpy.asarray([0.4, -0.05, 0.5], dtype=numpy.float32)
-    vocab.set_vector("I", array1)
-    vocab.set_vector("like", array2)
-    vocab.set_vector("David", array3)
-    vocab.set_vector("Bowie", array4)
-    text = "I like David Bowie"
-    patterns = [
-        {"label": "PERSON", "pattern": [{"LOWER": "david"}, {"LOWER": "bowie"}]}
-    ]
-    ruler = nlp.add_pipe("entity_ruler")
-    ruler.add_patterns(patterns)
-    parsed_vectors_1 = [t.vector for t in nlp(text)]
-    assert len(parsed_vectors_1) == 4
-    ops = get_current_ops()
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[0]), array1)
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[1]), array2)
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[2]), array3)
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[3]), array4)
-    nlp.add_pipe("merge_entities")
-    parsed_vectors_2 = [t.vector for t in nlp(text)]
-    assert len(parsed_vectors_2) == 3
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[0]), array1)
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[1]), array2)
-    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[2]), array34)
-
-
-@pytest.mark.issue(5137)
-def test_issue5137():
-    factory_name = "test_issue5137"
-    pipe_name = "my_component"
-
-    @Language.factory(factory_name)
-    class MyComponent:
-        def __init__(self, nlp, name=pipe_name, categories="all_categories"):
-            self.nlp = nlp
-            self.categories = categories
-            self.name = name
-
-        def __call__(self, doc):
-            pass
-
-        def to_disk(self, path, **kwargs):
-            pass
-
-        def from_disk(self, path, **cfg):
-            pass
-
-    nlp = English()
-    my_component = nlp.add_pipe(factory_name, name=pipe_name)
-    assert my_component.categories == "all_categories"
-    with make_tempdir() as tmpdir:
-        nlp.to_disk(tmpdir)
-        overrides = {"components": {pipe_name: {"categories": "my_categories"}}}
-        nlp2 = spacy.load(tmpdir, config=overrides)
-        assert nlp2.get_pipe(pipe_name).categories == "my_categories"
-
-
-@pytest.mark.issue(5141)
-def test_issue5141(en_vocab):
-    """Ensure an empty DocBin does not crash on serialization"""
-    doc_bin = DocBin(attrs=["DEP", "HEAD"])
-    assert list(doc_bin.get_docs(en_vocab)) == []
-    doc_bin_bytes = doc_bin.to_bytes()
-    doc_bin_2 = DocBin().from_bytes(doc_bin_bytes)
-    assert list(doc_bin_2.get_docs(en_vocab)) == []
-
-
-@pytest.mark.issue(5152)
-def test_issue5152():
-    # Test that the comparison between a Span and a Token, goes well
-    # There was a bug when the number of tokens in the span equaled the number of characters in the token (!)
-    nlp = English()
-    text = nlp("Talk about being boring!")
-    text_var = nlp("Talk of being boring!")
-    y = nlp("Let")
-    span = text[0:3]  # Talk about being
-    span_2 = text[0:3]  # Talk about being
-    span_3 = text_var[0:3]  # Talk of being
-    token = y[0]  # Let
-    with pytest.warns(UserWarning):
-        assert span.similarity(token) == 0.0
-    assert span.similarity(span_2) == 1.0
-    with pytest.warns(UserWarning):
-        assert span_2.similarity(span_3) < 1.0
-
-
-@pytest.mark.issue(5458)
-def test_issue5458():
-    # Test that the noun chuncker does not generate overlapping spans
-    # fmt: off
-    words = ["In", "an", "era", "where", "markets", "have", "brought", "prosperity", "and", "empowerment", "."]
-    vocab = Vocab(strings=words)
-    deps = ["ROOT", "det", "pobj", "advmod", "nsubj", "aux", "relcl", "dobj", "cc", "conj", "punct"]
-    pos = ["ADP", "DET", "NOUN", "ADV", "NOUN", "AUX", "VERB", "NOUN", "CCONJ", "NOUN", "PUNCT"]
-    heads = [0, 2, 0, 9, 6, 6, 2, 6, 7, 7, 0]
-    # fmt: on
-    en_doc = Doc(vocab, words=words, pos=pos, heads=heads, deps=deps)
-    en_doc.noun_chunks_iterator = noun_chunks
-
-    # if there are overlapping spans, this will fail with an E102 error "Can't merge non-disjoint spans"
-    nlp = English()
-    merge_nps = nlp.create_pipe("merge_noun_chunks")
-    merge_nps(en_doc)
diff --git a/spacy/tests/regression/test_issue5501-6000.py b/spacy/tests/regression/test_issue5501-6000.py
deleted file mode 100644
index 87c40ec2a..000000000
--- a/spacy/tests/regression/test_issue5501-6000.py
+++ /dev/null
@@ -1,95 +0,0 @@
-import pytest
-from numpy.testing import assert_almost_equal
-from thinc.api import Config, fix_random_seed, get_current_ops
-
-from spacy.lang.en import English
-from spacy.pipeline.textcat import single_label_default_config, single_label_bow_config
-from spacy.pipeline.textcat import single_label_cnn_config
-from spacy.pipeline.textcat_multilabel import multi_label_default_config
-from spacy.pipeline.textcat_multilabel import multi_label_bow_config
-from spacy.pipeline.textcat_multilabel import multi_label_cnn_config
-from spacy.tokens import Span
-from spacy import displacy
-from spacy.pipeline import merge_entities
-from spacy.training import Example
-
-
-@pytest.mark.parametrize(
-    "textcat_config",
-    [
-        single_label_default_config,
-        single_label_bow_config,
-        single_label_cnn_config,
-        multi_label_default_config,
-        multi_label_bow_config,
-        multi_label_cnn_config,
-    ],
-)
-@pytest.mark.issue(5551)
-def test_issue5551(textcat_config):
-    """Test that after fixing the random seed, the results of the pipeline are truly identical"""
-    component = "textcat"
-
-    pipe_cfg = Config().from_str(textcat_config)
-    results = []
-    for i in range(3):
-        fix_random_seed(0)
-        nlp = English()
-        text = "Once hot, form ping-pong-ball-sized balls of the mixture, each weighing roughly 25 g."
-        annots = {"cats": {"Labe1": 1.0, "Label2": 0.0, "Label3": 0.0}}
-        pipe = nlp.add_pipe(component, config=pipe_cfg, last=True)
-        for label in set(annots["cats"]):
-            pipe.add_label(label)
-        # Train
-        nlp.initialize()
-        doc = nlp.make_doc(text)
-        nlp.update([Example.from_dict(doc, annots)])
-        # Store the result of each iteration
-        result = pipe.model.predict([doc])
-        results.append(result[0])
-    # All results should be the same because of the fixed seed
-    assert len(results) == 3
-    ops = get_current_ops()
-    assert_almost_equal(ops.to_numpy(results[0]), ops.to_numpy(results[1]), decimal=5)
-    assert_almost_equal(ops.to_numpy(results[0]), ops.to_numpy(results[2]), decimal=5)
-
-
-@pytest.mark.issue(5838)
-def test_issue5838():
-    # Displacy's EntityRenderer break line
-    # not working after last entity
-    sample_text = "First line\nSecond line, with ent\nThird line\nFourth line\n"
-    nlp = English()
-    doc = nlp(sample_text)
-    doc.ents = [Span(doc, 7, 8, label="test")]
-    html = displacy.render(doc, style="ent")
-    found = html.count("</br>")
-    assert found == 4
-
-
-@pytest.mark.issue(5918)
-def test_issue5918():
-    # Test edge case when merging entities.
-    nlp = English()
-    ruler = nlp.add_pipe("entity_ruler")
-    patterns = [
-        {"label": "ORG", "pattern": "Digicon Inc"},
-        {"label": "ORG", "pattern": "Rotan Mosle Inc's"},
-        {"label": "ORG", "pattern": "Rotan Mosle Technology Partners Ltd"},
-    ]
-    ruler.add_patterns(patterns)
-
-    text = """
-        Digicon Inc said it has completed the previously-announced disposition
-        of its computer systems division to an investment group led by
-        Rotan Mosle Inc's Rotan Mosle Technology Partners Ltd affiliate.
-        """
-    doc = nlp(text)
-    assert len(doc.ents) == 3
-    # make it so that the third span's head is within the entity (ent_iob=I)
-    # bug #5918 would wrongly transfer that I to the full entity, resulting in 2 instead of 3 final ents.
-    # TODO: test for logging here
-    # with pytest.warns(UserWarning):
-    #     doc[29].head = doc[33]
-    doc = merge_entities(doc)
-    assert len(doc.ents) == 3
diff --git a/spacy/tests/regression/test_issue6001-6500.py b/spacy/tests/regression/test_issue6001-6500.py
deleted file mode 100644
index cb27d39e4..000000000
--- a/spacy/tests/regression/test_issue6001-6500.py
+++ /dev/null
@@ -1,30 +0,0 @@
-from spacy.util import filter_spans
-from pydantic import ValidationError
-from spacy.schemas import TokenPattern, TokenPatternSchema
-import pytest
-
-
-@pytest.mark.issue(6207)
-def test_issue6207(en_tokenizer):
-    doc = en_tokenizer("zero one two three four five six")
-
-    # Make spans
-    s1 = doc[:4]
-    s2 = doc[3:6]  # overlaps with s1
-    s3 = doc[5:7]  # overlaps with s2, not s1
-
-    result = filter_spans((s1, s2, s3))
-    assert s1 in result
-    assert s2 not in result
-    assert s3 in result
-
-
-@pytest.mark.issue(6258)
-def test_issue6258():
-    """Test that the non-empty constraint pattern field is respected"""
-    # These one is valid
-    TokenPatternSchema(pattern=[TokenPattern()])
-    # But an empty pattern list should fail to validate
-    # based on the schema's constraint
-    with pytest.raises(ValidationError):
-        TokenPatternSchema(pattern=[])
diff --git a/spacy/tests/regression/test_issue6501-7000.py b/spacy/tests/regression/test_issue6501-7000.py
deleted file mode 100644
index 84517d79b..000000000
--- a/spacy/tests/regression/test_issue6501-7000.py
+++ /dev/null
@@ -1,238 +0,0 @@
-import pytest
-from spacy.lang.en import English
-import numpy as np
-import spacy
-from spacy.tokens import Doc
-from spacy.matcher import PhraseMatcher
-from spacy.tokens import DocBin
-from spacy.util import load_config_from_str
-from spacy.training import Example
-from spacy.training.initialize import init_nlp
-import pickle
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(6730)
-def test_issue6730(en_vocab):
-    """Ensure that the KB does not accept empty strings, but otherwise IO works fine."""
-    from spacy.kb import KnowledgeBase
-
-    kb = KnowledgeBase(en_vocab, entity_vector_length=3)
-    kb.add_entity(entity="1", freq=148, entity_vector=[1, 2, 3])
-
-    with pytest.raises(ValueError):
-        kb.add_alias(alias="", entities=["1"], probabilities=[0.4])
-    assert kb.contains_alias("") is False
-
-    kb.add_alias(alias="x", entities=["1"], probabilities=[0.2])
-    kb.add_alias(alias="y", entities=["1"], probabilities=[0.1])
-
-    with make_tempdir() as tmp_dir:
-        kb.to_disk(tmp_dir)
-        kb.from_disk(tmp_dir)
-    assert kb.get_size_aliases() == 2
-    assert set(kb.get_alias_strings()) == {"x", "y"}
-
-
-@pytest.mark.issue(6755)
-def test_issue6755(en_tokenizer):
-    doc = en_tokenizer("This is a magnificent sentence.")
-    span = doc[:0]
-    assert span.text_with_ws == ""
-    assert span.text == ""
-
-
-@pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,label",
-    [("Welcome to Mumbai, my friend", 11, 17, "GPE")],
-)
-@pytest.mark.issue(6815)
-def test_issue6815_1(sentence, start_idx, end_idx, label):
-    nlp = English()
-    doc = nlp(sentence)
-    span = doc[:].char_span(start_idx, end_idx, label=label)
-    assert span.label_ == label
-
-
-@pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,kb_id", [("Welcome to Mumbai, my friend", 11, 17, 5)]
-)
-@pytest.mark.issue(6815)
-def test_issue6815_2(sentence, start_idx, end_idx, kb_id):
-    nlp = English()
-    doc = nlp(sentence)
-    span = doc[:].char_span(start_idx, end_idx, kb_id=kb_id)
-    assert span.kb_id == kb_id
-
-
-@pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,vector",
-    [("Welcome to Mumbai, my friend", 11, 17, np.array([0.1, 0.2, 0.3]))],
-)
-@pytest.mark.issue(6815)
-def test_issue6815_3(sentence, start_idx, end_idx, vector):
-    nlp = English()
-    doc = nlp(sentence)
-    span = doc[:].char_span(start_idx, end_idx, vector=vector)
-    assert (span.vector == vector).all()
-
-
-@pytest.mark.issue(6839)
-def test_issue6839(en_vocab):
-    """Ensure that PhraseMatcher accepts Span as input"""
-    # fmt: off
-    words = ["I", "like", "Spans", "and", "Docs", "in", "my", "input", ",", "and", "nothing", "else", "."]
-    # fmt: on
-    doc = Doc(en_vocab, words=words)
-    span = doc[:8]
-    pattern = Doc(en_vocab, words=["Spans", "and", "Docs"])
-    matcher = PhraseMatcher(en_vocab)
-    matcher.add("SPACY", [pattern])
-    matches = matcher(span)
-    assert matches
-
-
-CONFIG_ISSUE_6908 = """
-[paths]
-train = "TRAIN_PLACEHOLDER"
-raw = null
-init_tok2vec = null
-vectors = null
-
-[system]
-seed = 0
-gpu_allocator = null
-
-[nlp]
-lang = "en"
-pipeline = ["textcat"]
-tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
-disabled = []
-before_creation = null
-after_creation = null
-after_pipeline_creation = null
-batch_size = 1000
-
-[components]
-
-[components.textcat]
-factory = "TEXTCAT_PLACEHOLDER"
-
-[corpora]
-
-[corpora.train]
-@readers = "spacy.Corpus.v1"
-path = ${paths:train}
-
-[corpora.dev]
-@readers = "spacy.Corpus.v1"
-path = ${paths:train}
-
-
-[training]
-train_corpus = "corpora.train"
-dev_corpus = "corpora.dev"
-seed = ${system.seed}
-gpu_allocator = ${system.gpu_allocator}
-frozen_components = []
-before_to_disk = null
-
-[pretraining]
-
-[initialize]
-vectors = ${paths.vectors}
-init_tok2vec = ${paths.init_tok2vec}
-vocab_data = null
-lookups = null
-before_init = null
-after_init = null
-
-[initialize.components]
-
-[initialize.components.textcat]
-labels = ['label1', 'label2']
-
-[initialize.tokenizer]
-"""
-
-
-@pytest.mark.parametrize(
-    "component_name",
-    ["textcat", "textcat_multilabel"],
-)
-@pytest.mark.issue(6908)
-def test_issue6908(component_name):
-    """Test intializing textcat with labels in a list"""
-
-    def create_data(out_file):
-        nlp = spacy.blank("en")
-        doc = nlp.make_doc("Some text")
-        doc.cats = {"label1": 0, "label2": 1}
-        out_data = DocBin(docs=[doc]).to_bytes()
-        with out_file.open("wb") as file_:
-            file_.write(out_data)
-
-    with make_tempdir() as tmp_path:
-        train_path = tmp_path / "train.spacy"
-        create_data(train_path)
-        config_str = CONFIG_ISSUE_6908.replace("TEXTCAT_PLACEHOLDER", component_name)
-        config_str = config_str.replace("TRAIN_PLACEHOLDER", train_path.as_posix())
-        config = load_config_from_str(config_str)
-        init_nlp(config)
-
-
-CONFIG_ISSUE_6950 = """
-[nlp]
-lang = "en"
-pipeline = ["tok2vec", "tagger"]
-
-[components]
-
-[components.tok2vec]
-factory = "tok2vec"
-
-[components.tok2vec.model]
-@architectures = "spacy.Tok2Vec.v1"
-
-[components.tok2vec.model.embed]
-@architectures = "spacy.MultiHashEmbed.v1"
-width = ${components.tok2vec.model.encode:width}
-attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
-rows = [5000,2500,2500,2500]
-include_static_vectors = false
-
-[components.tok2vec.model.encode]
-@architectures = "spacy.MaxoutWindowEncoder.v1"
-width = 96
-depth = 4
-window_size = 1
-maxout_pieces = 3
-
-[components.ner]
-factory = "ner"
-
-[components.tagger]
-factory = "tagger"
-
-[components.tagger.model]
-@architectures = "spacy.Tagger.v1"
-nO = null
-
-[components.tagger.model.tok2vec]
-@architectures = "spacy.Tok2VecListener.v1"
-width = ${components.tok2vec.model.encode:width}
-upstream = "*"
-"""
-
-
-@pytest.mark.issue(6950)
-def test_issue6950():
-    """Test that the nlp object with initialized tok2vec with listeners pickles
-    correctly (and doesn't have lambdas).
-    """
-    nlp = English.from_config(load_config_from_str(CONFIG_ISSUE_6950))
-    nlp.initialize(lambda: [Example.from_dict(nlp.make_doc("hello"), {"tags": ["V"]})])
-    pickle.dumps(nlp)
-    nlp("hello")
-    pickle.dumps(nlp)
diff --git a/spacy/tests/regression/test_issue7001-8000.py b/spacy/tests/regression/test_issue7001-8000.py
deleted file mode 100644
index 1164e85b9..000000000
--- a/spacy/tests/regression/test_issue7001-8000.py
+++ /dev/null
@@ -1,288 +0,0 @@
-import pytest
-from spacy.cli.evaluate import print_textcats_auc_per_cat, print_prf_per_type
-from spacy.lang.en import English
-from spacy.training import Example
-from spacy.tokens.doc import Doc
-from spacy.vocab import Vocab
-from spacy.kb import KnowledgeBase
-from spacy.pipeline._parser_internals.arc_eager import ArcEager
-from spacy.util import load_config_from_str, load_config
-from spacy.cli.init_config import fill_config
-from thinc.api import Config
-from wasabi import msg
-
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(7019)
-def test_issue7019():
-    scores = {"LABEL_A": 0.39829102, "LABEL_B": 0.938298329382, "LABEL_C": None}
-    print_textcats_auc_per_cat(msg, scores)
-    scores = {
-        "LABEL_A": {"p": 0.3420302, "r": 0.3929020, "f": 0.49823928932},
-        "LABEL_B": {"p": None, "r": None, "f": None},
-    }
-    print_prf_per_type(msg, scores, name="foo", type="bar")
-
-
-CONFIG_7029 = """
-[nlp]
-lang = "en"
-pipeline = ["tok2vec", "tagger"]
-
-[components]
-
-[components.tok2vec]
-factory = "tok2vec"
-
-[components.tok2vec.model]
-@architectures = "spacy.Tok2Vec.v1"
-
-[components.tok2vec.model.embed]
-@architectures = "spacy.MultiHashEmbed.v1"
-width = ${components.tok2vec.model.encode:width}
-attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
-rows = [5000,2500,2500,2500]
-include_static_vectors = false
-
-[components.tok2vec.model.encode]
-@architectures = "spacy.MaxoutWindowEncoder.v1"
-width = 96
-depth = 4
-window_size = 1
-maxout_pieces = 3
-
-[components.tagger]
-factory = "tagger"
-
-[components.tagger.model]
-@architectures = "spacy.Tagger.v1"
-nO = null
-
-[components.tagger.model.tok2vec]
-@architectures = "spacy.Tok2VecListener.v1"
-width = ${components.tok2vec.model.encode:width}
-upstream = "*"
-"""
-
-
-@pytest.mark.issue(7029)
-def test_issue7029():
-    """Test that an empty document doesn't mess up an entire batch."""
-    TRAIN_DATA = [
-        ("I like green eggs", {"tags": ["N", "V", "J", "N"]}),
-        ("Eat blue ham", {"tags": ["V", "J", "N"]}),
-    ]
-    nlp = English.from_config(load_config_from_str(CONFIG_7029))
-    train_examples = []
-    for t in TRAIN_DATA:
-        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
-    optimizer = nlp.initialize(get_examples=lambda: train_examples)
-    for i in range(50):
-        losses = {}
-        nlp.update(train_examples, sgd=optimizer, losses=losses)
-    texts = ["first", "second", "third", "fourth", "and", "then", "some", ""]
-    docs1 = list(nlp.pipe(texts, batch_size=1))
-    docs2 = list(nlp.pipe(texts, batch_size=4))
-    assert [doc[0].tag_ for doc in docs1[:-1]] == [doc[0].tag_ for doc in docs2[:-1]]
-
-
-@pytest.mark.issue(7055)
-def test_issue7055():
-    """Test that fill-config doesn't turn sourced components into factories."""
-    source_cfg = {
-        "nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger"]},
-        "components": {
-            "tok2vec": {"factory": "tok2vec"},
-            "tagger": {"factory": "tagger"},
-        },
-    }
-    source_nlp = English.from_config(source_cfg)
-    with make_tempdir() as dir_path:
-        # We need to create a loadable source pipeline
-        source_path = dir_path / "test_model"
-        source_nlp.to_disk(source_path)
-        base_cfg = {
-            "nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger", "ner"]},
-            "components": {
-                "tok2vec": {"source": str(source_path)},
-                "tagger": {"source": str(source_path)},
-                "ner": {"factory": "ner"},
-            },
-        }
-        base_cfg = Config(base_cfg)
-        base_path = dir_path / "base.cfg"
-        base_cfg.to_disk(base_path)
-        output_path = dir_path / "config.cfg"
-        fill_config(output_path, base_path, silent=True)
-        filled_cfg = load_config(output_path)
-    assert filled_cfg["components"]["tok2vec"]["source"] == str(source_path)
-    assert filled_cfg["components"]["tagger"]["source"] == str(source_path)
-    assert filled_cfg["components"]["ner"]["factory"] == "ner"
-    assert "model" in filled_cfg["components"]["ner"]
-
-
-@pytest.mark.issue(7056)
-def test_issue7056():
-    """Test that the Unshift transition works properly, and doesn't cause
-    sentence segmentation errors."""
-    vocab = Vocab()
-    ae = ArcEager(
-        vocab.strings, ArcEager.get_actions(left_labels=["amod"], right_labels=["pobj"])
-    )
-    doc = Doc(vocab, words="Severe pain , after trauma".split())
-    state = ae.init_batch([doc])[0]
-    ae.apply_transition(state, "S")
-    ae.apply_transition(state, "L-amod")
-    ae.apply_transition(state, "S")
-    ae.apply_transition(state, "S")
-    ae.apply_transition(state, "S")
-    ae.apply_transition(state, "R-pobj")
-    ae.apply_transition(state, "D")
-    ae.apply_transition(state, "D")
-    ae.apply_transition(state, "D")
-    assert not state.eol()
-
-
-def test_partial_links():
-    # Test that having some entities on the doc without gold links, doesn't crash
-    TRAIN_DATA = [
-        (
-            "Russ Cochran his reprints include EC Comics.",
-            {
-                "links": {(0, 12): {"Q2146908": 1.0}},
-                "entities": [(0, 12, "PERSON")],
-                "sent_starts": [1, -1, 0, 0, 0, 0, 0, 0],
-            },
-        )
-    ]
-    nlp = English()
-    vector_length = 3
-    train_examples = []
-    for text, annotation in TRAIN_DATA:
-        doc = nlp(text)
-        train_examples.append(Example.from_dict(doc, annotation))
-
-    def create_kb(vocab):
-        # create artificial KB
-        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
-        mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3])
-        mykb.add_alias("Russ Cochran", ["Q2146908"], [0.9])
-        return mykb
-
-    # Create and train the Entity Linker
-    entity_linker = nlp.add_pipe("entity_linker", last=True)
-    entity_linker.set_kb(create_kb)
-    optimizer = nlp.initialize(get_examples=lambda: train_examples)
-    for i in range(2):
-        losses = {}
-        nlp.update(train_examples, sgd=optimizer, losses=losses)
-
-    # adding additional components that are required for the entity_linker
-    nlp.add_pipe("sentencizer", first=True)
-    patterns = [
-        {"label": "PERSON", "pattern": [{"LOWER": "russ"}, {"LOWER": "cochran"}]},
-        {"label": "ORG", "pattern": [{"LOWER": "ec"}, {"LOWER": "comics"}]},
-    ]
-    ruler = nlp.add_pipe("entity_ruler", before="entity_linker")
-    ruler.add_patterns(patterns)
-
-    # this will run the pipeline on the examples and shouldn't crash
-    results = nlp.evaluate(train_examples)
-    assert "PERSON" in results["ents_per_type"]
-    assert "PERSON" in results["nel_f_per_type"]
-    assert "ORG" in results["ents_per_type"]
-    assert "ORG" not in results["nel_f_per_type"]
-
-
-@pytest.mark.issue(7065)
-def test_issue7065():
-    text = "Kathleen Battle sang in Mahler 's Symphony No. 8 at the Cincinnati Symphony Orchestra 's May Festival."
-    nlp = English()
-    nlp.add_pipe("sentencizer")
-    ruler = nlp.add_pipe("entity_ruler")
-    patterns = [
-        {
-            "label": "THING",
-            "pattern": [
-                {"LOWER": "symphony"},
-                {"LOWER": "no"},
-                {"LOWER": "."},
-                {"LOWER": "8"},
-            ],
-        }
-    ]
-    ruler.add_patterns(patterns)
-
-    doc = nlp(text)
-    sentences = [s for s in doc.sents]
-    assert len(sentences) == 2
-    sent0 = sentences[0]
-    ent = doc.ents[0]
-    assert ent.start < sent0.end < ent.end
-    assert sentences.index(ent.sent) == 0
-
-
-@pytest.mark.issue(7065)
-def test_issue7065_b():
-    # Test that the NEL doesn't crash when an entity crosses a sentence boundary
-    nlp = English()
-    vector_length = 3
-    nlp.add_pipe("sentencizer")
-    text = "Mahler 's Symphony No. 8 was beautiful."
-    entities = [(0, 6, "PERSON"), (10, 24, "WORK")]
-    links = {
-        (0, 6): {"Q7304": 1.0, "Q270853": 0.0},
-        (10, 24): {"Q7304": 0.0, "Q270853": 1.0},
-    }
-    sent_starts = [1, -1, 0, 0, 0, 0, 0, 0, 0]
-    doc = nlp(text)
-    example = Example.from_dict(
-        doc, {"entities": entities, "links": links, "sent_starts": sent_starts}
-    )
-    train_examples = [example]
-
-    def create_kb(vocab):
-        # create artificial KB
-        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
-        mykb.add_entity(entity="Q270853", freq=12, entity_vector=[9, 1, -7])
-        mykb.add_alias(
-            alias="No. 8",
-            entities=["Q270853"],
-            probabilities=[1.0],
-        )
-        mykb.add_entity(entity="Q7304", freq=12, entity_vector=[6, -4, 3])
-        mykb.add_alias(
-            alias="Mahler",
-            entities=["Q7304"],
-            probabilities=[1.0],
-        )
-        return mykb
-
-    # Create the Entity Linker component and add it to the pipeline
-    entity_linker = nlp.add_pipe("entity_linker", last=True)
-    entity_linker.set_kb(create_kb)
-    # train the NEL pipe
-    optimizer = nlp.initialize(get_examples=lambda: train_examples)
-    for i in range(2):
-        losses = {}
-        nlp.update(train_examples, sgd=optimizer, losses=losses)
-
-    # Add a custom rule-based component to mimick NER
-    patterns = [
-        {"label": "PERSON", "pattern": [{"LOWER": "mahler"}]},
-        {
-            "label": "WORK",
-            "pattern": [
-                {"LOWER": "symphony"},
-                {"LOWER": "no"},
-                {"LOWER": "."},
-                {"LOWER": "8"},
-            ],
-        },
-    ]
-    ruler = nlp.add_pipe("entity_ruler", before="entity_linker")
-    ruler.add_patterns(patterns)
-    # test the trained model - this should not throw E148
-    doc = nlp(text)
-    assert doc
diff --git a/spacy/tests/regression/test_issue7716.py b/spacy/tests/regression/test_issue7716.py
deleted file mode 100644
index d9b3967ff..000000000
--- a/spacy/tests/regression/test_issue7716.py
+++ /dev/null
@@ -1,55 +0,0 @@
-import pytest
-from thinc.api import Adam
-from spacy.attrs import NORM
-from spacy.vocab import Vocab
-from spacy import registry
-from spacy.training import Example
-from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
-from spacy.tokens import Doc
-from spacy.pipeline import DependencyParser
-
-
-@pytest.fixture
-def vocab():
-    return Vocab(lex_attr_getters={NORM: lambda s: s})
-
-
-def _parser_example(parser):
-    doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
-    gold = {"heads": [1, 1, 3, 3], "deps": ["right", "ROOT", "left", "ROOT"]}
-    return Example.from_dict(doc, gold)
-
-
-@pytest.fixture
-def parser(vocab):
-    vocab.strings.add("ROOT")
-    cfg = {"model": DEFAULT_PARSER_MODEL}
-    model = registry.resolve(cfg, validate=True)["model"]
-    parser = DependencyParser(vocab, model)
-    parser.cfg["token_vector_width"] = 4
-    parser.cfg["hidden_width"] = 32
-    # parser.add_label('right')
-    parser.add_label("left")
-    parser.initialize(lambda: [_parser_example(parser)])
-    sgd = Adam(0.001)
-
-    for i in range(10):
-        losses = {}
-        doc = Doc(vocab, words=["a", "b", "c", "d"])
-        example = Example.from_dict(
-            doc, {"heads": [1, 1, 3, 3], "deps": ["left", "ROOT", "left", "ROOT"]}
-        )
-        parser.update([example], sgd=sgd, losses=losses)
-    return parser
-
-
-@pytest.mark.issue(7716)
-@pytest.mark.xfail(reason="Not fixed yet")
-def test_partial_annotation(parser):
-    doc = Doc(parser.vocab, words=["a", "b", "c", "d"])
-    doc[2].is_sent_start = False
-    # Note that if the following line is used, then doc[2].is_sent_start == False
-    # doc[3].is_sent_start = False
-
-    doc = parser(doc)
-    assert doc[2].is_sent_start == False
diff --git a/spacy/tests/regression/test_issue8168.py b/spacy/tests/regression/test_issue8168.py
deleted file mode 100644
index e3f3b5cfa..000000000
--- a/spacy/tests/regression/test_issue8168.py
+++ /dev/null
@@ -1,24 +0,0 @@
-import pytest
-from spacy.lang.en import English
-
-
-@pytest.mark.issue(8168)
-def test_issue8168():
-    nlp = English()
-    ruler = nlp.add_pipe("entity_ruler")
-    patterns = [
-        {"label": "ORG", "pattern": "Apple"},
-        {
-            "label": "GPE",
-            "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}],
-            "id": "san-francisco",
-        },
-        {
-            "label": "GPE",
-            "pattern": [{"LOWER": "san"}, {"LOWER": "fran"}],
-            "id": "san-francisco",
-        },
-    ]
-    ruler.add_patterns(patterns)
-
-    assert ruler._ent_ids == {8043148519967183733: ("GPE", "san-francisco")}
diff --git a/spacy/tests/regression/test_issue8190.py b/spacy/tests/regression/test_issue8190.py
deleted file mode 100644
index 0b2f2824b..000000000
--- a/spacy/tests/regression/test_issue8190.py
+++ /dev/null
@@ -1,24 +0,0 @@
-import pytest
-
-import spacy
-from spacy.lang.en import English
-from ..util import make_tempdir
-
-
-@pytest.mark.issue(8190)
-def test_issue8190():
-    """Test that config overrides are not lost after load is complete."""
-    source_cfg = {
-        "nlp": {
-            "lang": "en",
-        },
-        "custom": {"key": "value"},
-    }
-    source_nlp = English.from_config(source_cfg)
-    with make_tempdir() as dir_path:
-        # We need to create a loadable source pipeline
-        source_path = dir_path / "test_model"
-        source_nlp.to_disk(source_path)
-        nlp = spacy.load(source_path, config={"custom": {"key": "updated_value"}})
-
-        assert nlp.config["custom"]["key"] == "updated_value"
diff --git a/spacy/tests/regression/test_issue8216.py b/spacy/tests/regression/test_issue8216.py
deleted file mode 100644
index 0370074fe..000000000
--- a/spacy/tests/regression/test_issue8216.py
+++ /dev/null
@@ -1,34 +0,0 @@
-import pytest
-
-from spacy import registry
-from spacy.language import Language
-
-
-@pytest.fixture
-def nlp():
-    return Language()
-
-
-@pytest.fixture
-@registry.misc("entity_ruler_patterns")
-def patterns():
-    return [
-        {"label": "HELLO", "pattern": "hello world"},
-        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
-        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
-        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
-        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
-        {"label": "TECH_ORG", "pattern": "Microsoft", "id": "a2"},
-    ]
-
-
-@pytest.mark.issue(8216)
-def test_entity_ruler_fix8216(nlp, patterns):
-    """Test that patterns don't get added excessively."""
-    ruler = nlp.add_pipe("entity_ruler", config={"validate": True})
-    ruler.add_patterns(patterns)
-    pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
-    assert pattern_count > 0
-    ruler.add_patterns([])
-    after_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
-    assert after_count == pattern_count
diff --git a/spacy/tests/serialize/test_serialize_config.py b/spacy/tests/serialize/test_serialize_config.py
index 102989705..1d50fd1d1 100644
--- a/spacy/tests/serialize/test_serialize_config.py
+++ b/spacy/tests/serialize/test_serialize_config.py
@@ -1,20 +1,17 @@
 import pytest
-from thinc.api import Config, ConfigValidationError
-import spacy
-from spacy.lang.en import English
-from spacy.lang.de import German
-from spacy.language import Language, DEFAULT_CONFIG, DEFAULT_CONFIG_PRETRAIN_PATH
-from spacy.util import (
-    registry,
-    load_model_from_config,
-    load_config,
-    load_config_from_str,
-)
-from spacy.ml.models import build_Tok2Vec_model, build_tb_parser_model
-from spacy.ml.models import MultiHashEmbed, MaxoutWindowEncoder
-from spacy.schemas import ConfigSchema, ConfigSchemaPretrain
 from catalogue import RegistryError
+from thinc.api import Config, ConfigValidationError
 
+import spacy
+from spacy.lang.de import German
+from spacy.lang.en import English
+from spacy.language import DEFAULT_CONFIG, DEFAULT_CONFIG_PRETRAIN_PATH
+from spacy.language import Language
+from spacy.ml.models import MaxoutWindowEncoder, MultiHashEmbed
+from spacy.ml.models import build_tb_parser_model, build_Tok2Vec_model
+from spacy.schemas import ConfigSchema, ConfigSchemaPretrain
+from spacy.util import load_config, load_config_from_str
+from spacy.util import load_model_from_config, registry
 
 from ..util import make_tempdir
 
@@ -187,6 +184,25 @@ def my_parser():
     return parser
 
 
+@pytest.mark.issue(8190)
+def test_issue8190():
+    """Test that config overrides are not lost after load is complete."""
+    source_cfg = {
+        "nlp": {
+            "lang": "en",
+        },
+        "custom": {"key": "value"},
+    }
+    source_nlp = English.from_config(source_cfg)
+    with make_tempdir() as dir_path:
+        # We need to create a loadable source pipeline
+        source_path = dir_path / "test_model"
+        source_nlp.to_disk(source_path)
+        nlp = spacy.load(source_path, config={"custom": {"key": "updated_value"}})
+
+        assert nlp.config["custom"]["key"] == "updated_value"
+
+
 def test_create_nlp_from_config():
     config = Config().from_str(nlp_config_string)
     with pytest.raises(ConfigValidationError):
diff --git a/spacy/tests/serialize/test_serialize_doc.py b/spacy/tests/serialize/test_serialize_doc.py
index 23afaf26c..15bf67bfd 100644
--- a/spacy/tests/serialize/test_serialize_doc.py
+++ b/spacy/tests/serialize/test_serialize_doc.py
@@ -1,13 +1,168 @@
-import pytest
-from spacy.tokens.underscore import Underscore
+import copy
+import pickle
 
-import spacy
+import numpy
+import pytest
+
+from spacy.attrs import DEP, HEAD
 from spacy.lang.en import English
-from spacy.tokens import Doc, DocBin
+from spacy.language import Language
+from spacy.matcher import Matcher, PhraseMatcher
+from spacy.tokens import Doc
+from spacy.vectors import Vectors
+from spacy.vocab import Vocab
 
 from ..util import make_tempdir
 
 
+@pytest.mark.issue(1727)
+def test_issue1727():
+    """Test that models with no pretrained vectors can be deserialized
+    correctly after vectors are added."""
+    nlp = Language(Vocab())
+    data = numpy.ones((3, 300), dtype="f")
+    vectors = Vectors(data=data, keys=["I", "am", "Matt"])
+    tagger = nlp.create_pipe("tagger")
+    tagger.add_label("PRP")
+    assert tagger.cfg.get("pretrained_dims", 0) == 0
+    tagger.vocab.vectors = vectors
+    with make_tempdir() as path:
+        tagger.to_disk(path)
+        tagger = nlp.create_pipe("tagger").from_disk(path)
+        assert tagger.cfg.get("pretrained_dims", 0) == 0
+
+
+@pytest.mark.issue(1799)
+def test_issue1799():
+    """Test sentence boundaries are deserialized correctly, even for
+    non-projective sentences."""
+    heads_deps = numpy.asarray(
+        [
+            [1, 397],
+            [4, 436],
+            [2, 426],
+            [1, 402],
+            [0, 8206900633647566924],
+            [18446744073709551615, 440],
+            [18446744073709551614, 442],
+        ],
+        dtype="uint64",
+    )
+    doc = Doc(Vocab(), words="Just what I was looking for .".split())
+    doc.vocab.strings.add("ROOT")
+    doc = doc.from_array([HEAD, DEP], heads_deps)
+    assert len(list(doc.sents)) == 1
+
+
+@pytest.mark.issue(1834)
+def test_issue1834():
+    """Test that sentence boundaries & parse/tag flags are not lost
+    during serialization."""
+    words = ["This", "is", "a", "first", "sentence", ".", "And", "another", "one"]
+    doc = Doc(Vocab(), words=words)
+    doc[6].is_sent_start = True
+    new_doc = Doc(doc.vocab).from_bytes(doc.to_bytes())
+    assert new_doc[6].sent_start
+    assert not new_doc.has_annotation("DEP")
+    assert not new_doc.has_annotation("TAG")
+    doc = Doc(
+        Vocab(),
+        words=words,
+        tags=["TAG"] * len(words),
+        heads=[0, 0, 0, 0, 0, 0, 6, 6, 6],
+        deps=["dep"] * len(words),
+    )
+    new_doc = Doc(doc.vocab).from_bytes(doc.to_bytes())
+    assert new_doc[6].sent_start
+    assert new_doc.has_annotation("DEP")
+    assert new_doc.has_annotation("TAG")
+
+
+@pytest.mark.issue(1883)
+def test_issue1883():
+    matcher = Matcher(Vocab())
+    matcher.add("pat1", [[{"orth": "hello"}]])
+    doc = Doc(matcher.vocab, words=["hello"])
+    assert len(matcher(doc)) == 1
+    new_matcher = copy.deepcopy(matcher)
+    new_doc = Doc(new_matcher.vocab, words=["hello"])
+    assert len(new_matcher(new_doc)) == 1
+
+
+@pytest.mark.issue(2564)
+def test_issue2564():
+    """Test the tagger sets has_annotation("TAG") correctly when used via Language.pipe."""
+    nlp = Language()
+    tagger = nlp.add_pipe("tagger")
+    tagger.add_label("A")
+    nlp.initialize()
+    doc = nlp("hello world")
+    assert doc.has_annotation("TAG")
+    docs = nlp.pipe(["hello", "world"])
+    piped_doc = next(docs)
+    assert piped_doc.has_annotation("TAG")
+
+
+@pytest.mark.issue(3248)
+def test_issue3248_2():
+    """Test that the PhraseMatcher can be pickled correctly."""
+    nlp = English()
+    matcher = PhraseMatcher(nlp.vocab)
+    matcher.add("TEST1", [nlp("a"), nlp("b"), nlp("c")])
+    matcher.add("TEST2", [nlp("d")])
+    data = pickle.dumps(matcher)
+    new_matcher = pickle.loads(data)
+    assert len(new_matcher) == len(matcher)
+
+
+@pytest.mark.issue(3289)
+def test_issue3289():
+    """Test that Language.to_bytes handles serializing a pipeline component
+    with an uninitialized model."""
+    nlp = English()
+    nlp.add_pipe("textcat")
+    bytes_data = nlp.to_bytes()
+    new_nlp = English()
+    new_nlp.add_pipe("textcat")
+    new_nlp.from_bytes(bytes_data)
+
+
+@pytest.mark.issue(3468)
+def test_issue3468():
+    """Test that sentence boundaries are set correctly so Doc.has_annotation("SENT_START") can
+    be restored after serialization."""
+    nlp = English()
+    nlp.add_pipe("sentencizer")
+    doc = nlp("Hello world")
+    assert doc[0].is_sent_start
+    assert doc.has_annotation("SENT_START")
+    assert len(list(doc.sents)) == 1
+    doc_bytes = doc.to_bytes()
+    new_doc = Doc(nlp.vocab).from_bytes(doc_bytes)
+    assert new_doc[0].is_sent_start
+    assert new_doc.has_annotation("SENT_START")
+    assert len(list(new_doc.sents)) == 1
+
+
+@pytest.mark.issue(3959)
+def test_issue3959():
+    """Ensure that a modified pos attribute is serialized correctly."""
+    nlp = English()
+    doc = nlp(
+        "displaCy uses JavaScript, SVG and CSS to show you how computers understand language"
+    )
+    assert doc[0].pos_ == ""
+    doc[0].pos_ = "NOUN"
+    assert doc[0].pos_ == "NOUN"
+    # usually this is already True when starting from proper models instead of blank English
+    with make_tempdir() as tmp_dir:
+        file_path = tmp_dir / "my_doc"
+        doc.to_disk(file_path)
+        doc2 = nlp("")
+        doc2.from_disk(file_path)
+        assert doc2[0].pos_ == "NOUN"
+
+
 def test_serialize_empty_doc(en_vocab):
     doc = Doc(en_vocab)
     data = doc.to_bytes()
@@ -61,69 +216,3 @@ def test_serialize_doc_span_groups(en_vocab):
     doc.spans["content"] = [doc[0:2]]
     new_doc = Doc(en_vocab).from_bytes(doc.to_bytes())
     assert len(new_doc.spans["content"]) == 1
-
-
-def test_serialize_doc_bin():
-    doc_bin = DocBin(
-        attrs=["LEMMA", "ENT_IOB", "ENT_TYPE", "NORM", "ENT_ID"], store_user_data=True
-    )
-    texts = ["Some text", "Lots of texts...", "..."]
-    cats = {"A": 0.5}
-    nlp = English()
-    for doc in nlp.pipe(texts):
-        doc.cats = cats
-        doc.spans["start"] = [doc[0:2]]
-        doc[0].norm_ = "UNUSUAL_TOKEN_NORM"
-        doc[0].ent_id_ = "UNUSUAL_TOKEN_ENT_ID"
-        doc_bin.add(doc)
-    bytes_data = doc_bin.to_bytes()
-
-    # Deserialize later, e.g. in a new process
-    nlp = spacy.blank("en")
-    doc_bin = DocBin().from_bytes(bytes_data)
-    reloaded_docs = list(doc_bin.get_docs(nlp.vocab))
-    for i, doc in enumerate(reloaded_docs):
-        assert doc.text == texts[i]
-        assert doc.cats == cats
-        assert len(doc.spans) == 1
-        assert doc[0].norm_ == "UNUSUAL_TOKEN_NORM"
-        assert doc[0].ent_id_ == "UNUSUAL_TOKEN_ENT_ID"
-
-
-def test_serialize_doc_bin_unknown_spaces(en_vocab):
-    doc1 = Doc(en_vocab, words=["that", "'s"])
-    assert doc1.has_unknown_spaces
-    assert doc1.text == "that 's "
-    doc2 = Doc(en_vocab, words=["that", "'s"], spaces=[False, False])
-    assert not doc2.has_unknown_spaces
-    assert doc2.text == "that's"
-
-    doc_bin = DocBin().from_bytes(DocBin(docs=[doc1, doc2]).to_bytes())
-    re_doc1, re_doc2 = doc_bin.get_docs(en_vocab)
-    assert re_doc1.has_unknown_spaces
-    assert re_doc1.text == "that 's "
-    assert not re_doc2.has_unknown_spaces
-    assert re_doc2.text == "that's"
-
-
-@pytest.mark.parametrize(
-    "writer_flag,reader_flag,reader_value",
-    [
-        (True, True, "bar"),
-        (True, False, "bar"),
-        (False, True, "nothing"),
-        (False, False, "nothing"),
-    ],
-)
-def test_serialize_custom_extension(en_vocab, writer_flag, reader_flag, reader_value):
-    """Test that custom extensions are correctly serialized in DocBin."""
-    Doc.set_extension("foo", default="nothing")
-    doc = Doc(en_vocab, words=["hello", "world"])
-    doc._.foo = "bar"
-    doc_bin_1 = DocBin(store_user_data=writer_flag)
-    doc_bin_1.add(doc)
-    doc_bin_bytes = doc_bin_1.to_bytes()
-    doc_bin_2 = DocBin(store_user_data=reader_flag).from_bytes(doc_bin_bytes)
-    doc_2 = list(doc_bin_2.get_docs(en_vocab))[0]
-    assert doc_2._.foo == reader_value
-    Underscore.doc_extensions = {}
diff --git a/spacy/tests/serialize/test_serialize_docbin.py b/spacy/tests/serialize/test_serialize_docbin.py
new file mode 100644
index 000000000..9f8e5e06b
--- /dev/null
+++ b/spacy/tests/serialize/test_serialize_docbin.py
@@ -0,0 +1,106 @@
+import pytest
+
+import spacy
+from spacy.lang.en import English
+from spacy.tokens import Doc, DocBin
+from spacy.tokens.underscore import Underscore
+
+
+@pytest.mark.issue(4367)
+def test_issue4367():
+    """Test that docbin init goes well"""
+    DocBin()
+    DocBin(attrs=["LEMMA"])
+    DocBin(attrs=["LEMMA", "ENT_IOB", "ENT_TYPE"])
+
+
+@pytest.mark.issue(4528)
+def test_issue4528(en_vocab):
+    """Test that user_data is correctly serialized in DocBin."""
+    doc = Doc(en_vocab, words=["hello", "world"])
+    doc.user_data["foo"] = "bar"
+    # This is how extension attribute values are stored in the user data
+    doc.user_data[("._.", "foo", None, None)] = "bar"
+    doc_bin = DocBin(store_user_data=True)
+    doc_bin.add(doc)
+    doc_bin_bytes = doc_bin.to_bytes()
+    new_doc_bin = DocBin(store_user_data=True).from_bytes(doc_bin_bytes)
+    new_doc = list(new_doc_bin.get_docs(en_vocab))[0]
+    assert new_doc.user_data["foo"] == "bar"
+    assert new_doc.user_data[("._.", "foo", None, None)] == "bar"
+
+
+@pytest.mark.issue(5141)
+def test_issue5141(en_vocab):
+    """Ensure an empty DocBin does not crash on serialization"""
+    doc_bin = DocBin(attrs=["DEP", "HEAD"])
+    assert list(doc_bin.get_docs(en_vocab)) == []
+    doc_bin_bytes = doc_bin.to_bytes()
+    doc_bin_2 = DocBin().from_bytes(doc_bin_bytes)
+    assert list(doc_bin_2.get_docs(en_vocab)) == []
+
+
+def test_serialize_doc_bin():
+    doc_bin = DocBin(
+        attrs=["LEMMA", "ENT_IOB", "ENT_TYPE", "NORM", "ENT_ID"], store_user_data=True
+    )
+    texts = ["Some text", "Lots of texts...", "..."]
+    cats = {"A": 0.5}
+    nlp = English()
+    for doc in nlp.pipe(texts):
+        doc.cats = cats
+        doc.spans["start"] = [doc[0:2]]
+        doc[0].norm_ = "UNUSUAL_TOKEN_NORM"
+        doc[0].ent_id_ = "UNUSUAL_TOKEN_ENT_ID"
+        doc_bin.add(doc)
+    bytes_data = doc_bin.to_bytes()
+
+    # Deserialize later, e.g. in a new process
+    nlp = spacy.blank("en")
+    doc_bin = DocBin().from_bytes(bytes_data)
+    reloaded_docs = list(doc_bin.get_docs(nlp.vocab))
+    for i, doc in enumerate(reloaded_docs):
+        assert doc.text == texts[i]
+        assert doc.cats == cats
+        assert len(doc.spans) == 1
+        assert doc[0].norm_ == "UNUSUAL_TOKEN_NORM"
+        assert doc[0].ent_id_ == "UNUSUAL_TOKEN_ENT_ID"
+
+
+def test_serialize_doc_bin_unknown_spaces(en_vocab):
+    doc1 = Doc(en_vocab, words=["that", "'s"])
+    assert doc1.has_unknown_spaces
+    assert doc1.text == "that 's "
+    doc2 = Doc(en_vocab, words=["that", "'s"], spaces=[False, False])
+    assert not doc2.has_unknown_spaces
+    assert doc2.text == "that's"
+
+    doc_bin = DocBin().from_bytes(DocBin(docs=[doc1, doc2]).to_bytes())
+    re_doc1, re_doc2 = doc_bin.get_docs(en_vocab)
+    assert re_doc1.has_unknown_spaces
+    assert re_doc1.text == "that 's "
+    assert not re_doc2.has_unknown_spaces
+    assert re_doc2.text == "that's"
+
+
+@pytest.mark.parametrize(
+    "writer_flag,reader_flag,reader_value",
+    [
+        (True, True, "bar"),
+        (True, False, "bar"),
+        (False, True, "nothing"),
+        (False, False, "nothing"),
+    ],
+)
+def test_serialize_custom_extension(en_vocab, writer_flag, reader_flag, reader_value):
+    """Test that custom extensions are correctly serialized in DocBin."""
+    Doc.set_extension("foo", default="nothing")
+    doc = Doc(en_vocab, words=["hello", "world"])
+    doc._.foo = "bar"
+    doc_bin_1 = DocBin(store_user_data=writer_flag)
+    doc_bin_1.add(doc)
+    doc_bin_bytes = doc_bin_1.to_bytes()
+    doc_bin_2 = DocBin(store_user_data=reader_flag).from_bytes(doc_bin_bytes)
+    doc_2 = list(doc_bin_2.get_docs(en_vocab))[0]
+    assert doc_2._.foo == reader_value
+    Underscore.doc_extensions = {}
diff --git a/spacy/tests/serialize/test_serialize_language.py b/spacy/tests/serialize/test_serialize_language.py
index 05529f9d1..6e7fa0e4e 100644
--- a/spacy/tests/serialize/test_serialize_language.py
+++ b/spacy/tests/serialize/test_serialize_language.py
@@ -1,8 +1,14 @@
-import pytest
 import re
+import pickle
+
+import pytest
 
 from spacy.language import Language
+from spacy.lang.it import Italian
+from spacy.lang.en import English
 from spacy.tokenizer import Tokenizer
+from spacy.training import Example
+from spacy.util import load_config_from_str
 
 from ..util import make_tempdir
 
@@ -21,6 +27,71 @@ def meta_data():
     }
 
 
+@pytest.mark.issue(2482)
+def test_issue2482():
+    """Test we can serialize and deserialize a blank NER or parser model."""
+    nlp = Italian()
+    nlp.add_pipe("ner")
+    b = nlp.to_bytes()
+    Italian().from_bytes(b)
+
+
+CONFIG_ISSUE_6950 = """
+[nlp]
+lang = "en"
+pipeline = ["tok2vec", "tagger"]
+
+[components]
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v1"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v1"
+width = ${components.tok2vec.model.encode:width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,2500,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v1"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[components.ner]
+factory = "ner"
+
+[components.tagger]
+factory = "tagger"
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode:width}
+upstream = "*"
+"""
+
+
+@pytest.mark.issue(6950)
+def test_issue6950():
+    """Test that the nlp object with initialized tok2vec with listeners pickles
+    correctly (and doesn't have lambdas).
+    """
+    nlp = English.from_config(load_config_from_str(CONFIG_ISSUE_6950))
+    nlp.initialize(lambda: [Example.from_dict(nlp.make_doc("hello"), {"tags": ["V"]})])
+    pickle.dumps(nlp)
+    nlp("hello")
+    pickle.dumps(nlp)
+
+
 def test_serialize_language_meta_disk(meta_data):
     language = Language(meta=meta_data)
     with make_tempdir() as d:
diff --git a/spacy/tests/serialize/test_serialize_pipeline.py b/spacy/tests/serialize/test_serialize_pipeline.py
index eebf72638..9fcf18e2d 100644
--- a/spacy/tests/serialize/test_serialize_pipeline.py
+++ b/spacy/tests/serialize/test_serialize_pipeline.py
@@ -1,18 +1,25 @@
+import pickle
+
 import pytest
-from spacy import registry, Vocab, load
-from spacy.pipeline import Tagger, DependencyParser, EntityRecognizer
-from spacy.pipeline import TextCategorizer, SentenceRecognizer, TrainablePipe
+import srsly
+from thinc.api import Linear
+
+import spacy
+from spacy import Vocab, load, registry
+from spacy.lang.en import English
+from spacy.language import Language
+from spacy.pipeline import DependencyParser, EntityRecognizer, EntityRuler
+from spacy.pipeline import SentenceRecognizer, Tagger, TextCategorizer
+from spacy.pipeline import TrainablePipe
 from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
+from spacy.pipeline.senter import DEFAULT_SENTER_MODEL
 from spacy.pipeline.tagger import DEFAULT_TAGGER_MODEL
 from spacy.pipeline.textcat import DEFAULT_SINGLE_TEXTCAT_MODEL
-from spacy.pipeline.senter import DEFAULT_SENTER_MODEL
-from spacy.lang.en import English
-from thinc.api import Linear
-import spacy
+from spacy.util import ensure_path, load_model
+from spacy.tokens import Span
 
 from ..util import make_tempdir
 
-
 test_parsers = [DependencyParser, EntityRecognizer]
 
 
@@ -58,6 +65,181 @@ def taggers(en_vocab):
     return tagger1, tagger2
 
 
+@pytest.mark.issue(3456)
+def test_issue3456():
+    # this crashed because of a padding error in layer.ops.unflatten in thinc
+    nlp = English()
+    tagger = nlp.add_pipe("tagger")
+    tagger.add_label("A")
+    nlp.initialize()
+    list(nlp.pipe(["hi", ""]))
+
+
+@pytest.mark.issue(3526)
+def test_issue_3526_1(en_vocab):
+    patterns = [
+        {"label": "HELLO", "pattern": "hello world"},
+        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
+        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
+        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
+        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
+    ]
+    nlp = Language(vocab=en_vocab)
+    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
+    ruler_bytes = ruler.to_bytes()
+    assert len(ruler) == len(patterns)
+    assert len(ruler.labels) == 4
+    assert ruler.overwrite
+    new_ruler = EntityRuler(nlp)
+    new_ruler = new_ruler.from_bytes(ruler_bytes)
+    assert len(new_ruler) == len(ruler)
+    assert len(new_ruler.labels) == 4
+    assert new_ruler.overwrite == ruler.overwrite
+    assert new_ruler.ent_id_sep == ruler.ent_id_sep
+
+
+@pytest.mark.issue(3526)
+def test_issue_3526_2(en_vocab):
+    patterns = [
+        {"label": "HELLO", "pattern": "hello world"},
+        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
+        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
+        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
+        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
+    ]
+    nlp = Language(vocab=en_vocab)
+    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
+    bytes_old_style = srsly.msgpack_dumps(ruler.patterns)
+    new_ruler = EntityRuler(nlp)
+    new_ruler = new_ruler.from_bytes(bytes_old_style)
+    assert len(new_ruler) == len(ruler)
+    for pattern in ruler.patterns:
+        assert pattern in new_ruler.patterns
+    assert new_ruler.overwrite is not ruler.overwrite
+
+
+@pytest.mark.issue(3526)
+def test_issue_3526_3(en_vocab):
+    patterns = [
+        {"label": "HELLO", "pattern": "hello world"},
+        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
+        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
+        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
+        {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
+    ]
+    nlp = Language(vocab=en_vocab)
+    ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
+    with make_tempdir() as tmpdir:
+        out_file = tmpdir / "entity_ruler"
+        srsly.write_jsonl(out_file.with_suffix(".jsonl"), ruler.patterns)
+        new_ruler = EntityRuler(nlp).from_disk(out_file)
+        for pattern in ruler.patterns:
+            assert pattern in new_ruler.patterns
+        assert len(new_ruler) == len(ruler)
+        assert new_ruler.overwrite is not ruler.overwrite
+
+
+@pytest.mark.issue(3526)
+def test_issue_3526_4(en_vocab):
+    nlp = Language(vocab=en_vocab)
+    patterns = [{"label": "ORG", "pattern": "Apple"}]
+    config = {"overwrite_ents": True}
+    ruler = nlp.add_pipe("entity_ruler", config=config)
+    ruler.add_patterns(patterns)
+    with make_tempdir() as tmpdir:
+        nlp.to_disk(tmpdir)
+        ruler = nlp.get_pipe("entity_ruler")
+        assert ruler.patterns == [{"label": "ORG", "pattern": "Apple"}]
+        assert ruler.overwrite is True
+        nlp2 = load(tmpdir)
+        new_ruler = nlp2.get_pipe("entity_ruler")
+        assert new_ruler.patterns == [{"label": "ORG", "pattern": "Apple"}]
+        assert new_ruler.overwrite is True
+
+
+@pytest.mark.issue(4042)
+def test_issue4042():
+    """Test that serialization of an EntityRuler before NER works fine."""
+    nlp = English()
+    # add ner pipe
+    ner = nlp.add_pipe("ner")
+    ner.add_label("SOME_LABEL")
+    nlp.initialize()
+    # Add entity ruler
+    patterns = [
+        {"label": "MY_ORG", "pattern": "Apple"},
+        {"label": "MY_GPE", "pattern": [{"lower": "san"}, {"lower": "francisco"}]},
+    ]
+    # works fine with "after"
+    ruler = nlp.add_pipe("entity_ruler", before="ner")
+    ruler.add_patterns(patterns)
+    doc1 = nlp("What do you think about Apple ?")
+    assert doc1.ents[0].label_ == "MY_ORG"
+
+    with make_tempdir() as d:
+        output_dir = ensure_path(d)
+        if not output_dir.exists():
+            output_dir.mkdir()
+        nlp.to_disk(output_dir)
+        nlp2 = load_model(output_dir)
+        doc2 = nlp2("What do you think about Apple ?")
+        assert doc2.ents[0].label_ == "MY_ORG"
+
+
+@pytest.mark.issue(4042)
+def test_issue4042_bug2():
+    """
+    Test that serialization of an NER works fine when new labels were added.
+    This is the second bug of two bugs underlying the issue 4042.
+    """
+    nlp1 = English()
+    # add ner pipe
+    ner1 = nlp1.add_pipe("ner")
+    ner1.add_label("SOME_LABEL")
+    nlp1.initialize()
+    # add a new label to the doc
+    doc1 = nlp1("What do you think about Apple ?")
+    assert len(ner1.labels) == 1
+    assert "SOME_LABEL" in ner1.labels
+    apple_ent = Span(doc1, 5, 6, label="MY_ORG")
+    doc1.ents = list(doc1.ents) + [apple_ent]
+    # Add the label explicitly. Previously we didn't require this.
+    ner1.add_label("MY_ORG")
+    ner1(doc1)
+    assert len(ner1.labels) == 2
+    assert "SOME_LABEL" in ner1.labels
+    assert "MY_ORG" in ner1.labels
+    with make_tempdir() as d:
+        # assert IO goes fine
+        output_dir = ensure_path(d)
+        if not output_dir.exists():
+            output_dir.mkdir()
+        ner1.to_disk(output_dir)
+        config = {}
+        ner2 = nlp1.create_pipe("ner", config=config)
+        ner2.from_disk(output_dir)
+        assert len(ner2.labels) == 2
+
+
+@pytest.mark.issue(4725)
+def test_issue4725_1():
+    """Ensure the pickling of the NER goes well"""
+    vocab = Vocab(vectors_name="test_vocab_add_vector")
+    nlp = English(vocab=vocab)
+    config = {
+        "update_with_oracle_cut_size": 111,
+    }
+    ner = nlp.create_pipe("ner", config=config)
+    with make_tempdir() as tmp_path:
+        with (tmp_path / "ner.pkl").open("wb") as file_:
+            pickle.dump(ner, file_)
+            assert ner.cfg["update_with_oracle_cut_size"] == 111
+
+        with (tmp_path / "ner.pkl").open("rb") as file_:
+            ner2 = pickle.load(file_)
+            assert ner2.cfg["update_with_oracle_cut_size"] == 111
+
+
 @pytest.mark.parametrize("Parser", test_parsers)
 def test_serialize_parser_roundtrip_bytes(en_vocab, Parser):
     cfg = {"model": DEFAULT_PARSER_MODEL}
diff --git a/spacy/tests/serialize/test_serialize_tokenizer.py b/spacy/tests/serialize/test_serialize_tokenizer.py
index a9450cd04..e271f7707 100644
--- a/spacy/tests/serialize/test_serialize_tokenizer.py
+++ b/spacy/tests/serialize/test_serialize_tokenizer.py
@@ -1,9 +1,16 @@
-import pytest
+import pickle
 import re
-from spacy.util import get_lang_class
-from spacy.tokenizer import Tokenizer
 
-from ..util import make_tempdir, assert_packed_msg_equal
+import pytest
+
+from spacy.attrs import ENT_IOB, ENT_TYPE
+from spacy.lang.en import English
+from spacy.tokenizer import Tokenizer
+from spacy.tokens import Doc
+from spacy.util import compile_infix_regex, compile_prefix_regex
+from spacy.util import compile_suffix_regex, get_lang_class, load_model
+
+from ..util import assert_packed_msg_equal, make_tempdir
 
 
 def load_tokenizer(b):
@@ -12,6 +19,79 @@ def load_tokenizer(b):
     return tok
 
 
+@pytest.mark.issue(2833)
+def test_issue2833(en_vocab):
+    """Test that a custom error is raised if a token or span is pickled."""
+    doc = Doc(en_vocab, words=["Hello", "world"])
+    with pytest.raises(NotImplementedError):
+        pickle.dumps(doc[0])
+    with pytest.raises(NotImplementedError):
+        pickle.dumps(doc[0:2])
+
+
+@pytest.mark.issue(3012)
+def test_issue3012(en_vocab):
+    """Test that the is_tagged attribute doesn't get overwritten when we from_array
+    without tag information."""
+    words = ["This", "is", "10", "%", "."]
+    tags = ["DT", "VBZ", "CD", "NN", "."]
+    pos = ["DET", "VERB", "NUM", "NOUN", "PUNCT"]
+    ents = ["O", "O", "B-PERCENT", "I-PERCENT", "O"]
+    doc = Doc(en_vocab, words=words, tags=tags, pos=pos, ents=ents)
+    assert doc.has_annotation("TAG")
+    expected = ("10", "NUM", "CD", "PERCENT")
+    assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
+    header = [ENT_IOB, ENT_TYPE]
+    ent_array = doc.to_array(header)
+    doc.from_array(header, ent_array)
+    assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
+    # Serializing then deserializing
+    doc_bytes = doc.to_bytes()
+    doc2 = Doc(en_vocab).from_bytes(doc_bytes)
+    assert (doc2[2].text, doc2[2].pos_, doc2[2].tag_, doc2[2].ent_type_) == expected
+
+
+@pytest.mark.issue(4190)
+def test_issue4190():
+    def customize_tokenizer(nlp):
+        prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
+        suffix_re = compile_suffix_regex(nlp.Defaults.suffixes)
+        infix_re = compile_infix_regex(nlp.Defaults.infixes)
+        # Remove all exceptions where a single letter is followed by a period (e.g. 'h.')
+        exceptions = {
+            k: v
+            for k, v in dict(nlp.Defaults.tokenizer_exceptions).items()
+            if not (len(k) == 2 and k[1] == ".")
+        }
+        new_tokenizer = Tokenizer(
+            nlp.vocab,
+            exceptions,
+            prefix_search=prefix_re.search,
+            suffix_search=suffix_re.search,
+            infix_finditer=infix_re.finditer,
+            token_match=nlp.tokenizer.token_match,
+        )
+        nlp.tokenizer = new_tokenizer
+
+    test_string = "Test c."
+    # Load default language
+    nlp_1 = English()
+    doc_1a = nlp_1(test_string)
+    result_1a = [token.text for token in doc_1a]  # noqa: F841
+    # Modify tokenizer
+    customize_tokenizer(nlp_1)
+    doc_1b = nlp_1(test_string)
+    result_1b = [token.text for token in doc_1b]
+    # Save and Reload
+    with make_tempdir() as model_dir:
+        nlp_1.to_disk(model_dir)
+        nlp_2 = load_model(model_dir)
+    # This should be the modified tokenizer
+    doc_2 = nlp_2(test_string)
+    result_2 = [token.text for token in doc_2]
+    assert result_1b == result_2
+
+
 def test_serialize_custom_tokenizer(en_vocab, en_tokenizer):
     """Test that custom tokenizer with not all functions defined or empty
     properties can be serialized and deserialized correctly (see #2494,
diff --git a/spacy/tests/serialize/test_serialize_vocab_strings.py b/spacy/tests/serialize/test_serialize_vocab_strings.py
index ab403ab54..fd80c3d8e 100644
--- a/spacy/tests/serialize/test_serialize_vocab_strings.py
+++ b/spacy/tests/serialize/test_serialize_vocab_strings.py
@@ -1,17 +1,71 @@
-import pytest
 import pickle
+
+import pytest
 from thinc.api import get_current_ops
-from spacy.vocab import Vocab
+
+import spacy
+from spacy.lang.en import English
 from spacy.strings import StringStore
+from spacy.tokens import Doc
+from spacy.util import ensure_path, load_model
 from spacy.vectors import Vectors
+from spacy.vocab import Vocab
 
 from ..util import make_tempdir
 
-
 test_strings = [([], []), (["rats", "are", "cute"], ["i", "like", "rats"])]
 test_strings_attrs = [(["rats", "are", "cute"], "Hello")]
 
 
+@pytest.mark.issue(599)
+def test_issue599(en_vocab):
+    doc = Doc(en_vocab)
+    doc2 = Doc(doc.vocab)
+    doc2.from_bytes(doc.to_bytes())
+    assert doc2.has_annotation("DEP")
+
+
+@pytest.mark.issue(4054)
+def test_issue4054(en_vocab):
+    """Test that a new blank model can be made with a vocab from file,
+    and that serialization does not drop the language at any point."""
+    nlp1 = English()
+    vocab1 = nlp1.vocab
+    with make_tempdir() as d:
+        vocab_dir = ensure_path(d / "vocab")
+        if not vocab_dir.exists():
+            vocab_dir.mkdir()
+        vocab1.to_disk(vocab_dir)
+        vocab2 = Vocab().from_disk(vocab_dir)
+        nlp2 = spacy.blank("en", vocab=vocab2)
+        nlp_dir = ensure_path(d / "nlp")
+        if not nlp_dir.exists():
+            nlp_dir.mkdir()
+        nlp2.to_disk(nlp_dir)
+        nlp3 = load_model(nlp_dir)
+        assert nlp3.lang == "en"
+
+
+@pytest.mark.issue(4133)
+def test_issue4133(en_vocab):
+    nlp = English()
+    vocab_bytes = nlp.vocab.to_bytes()
+    words = ["Apple", "is", "looking", "at", "buying", "a", "startup"]
+    pos = ["NOUN", "VERB", "ADP", "VERB", "PROPN", "NOUN", "ADP"]
+    doc = Doc(en_vocab, words=words)
+    for i, token in enumerate(doc):
+        token.pos_ = pos[i]
+    # usually this is already True when starting from proper models instead of blank English
+    doc_bytes = doc.to_bytes()
+    vocab = Vocab()
+    vocab = vocab.from_bytes(vocab_bytes)
+    doc = Doc(vocab).from_bytes(doc_bytes)
+    actual = []
+    for token in doc:
+        actual.append(token.pos_)
+    assert actual == pos
+
+
 @pytest.mark.parametrize("text", ["rat"])
 def test_serialize_vocab(en_vocab, text):
     text_hash = en_vocab.strings.add(text)
diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py
index c6b00b140..b0862eab6 100644
--- a/spacy/tests/test_cli.py
+++ b/spacy/tests/test_cli.py
@@ -1,28 +1,103 @@
-import pytest
-from click import NoSuchOption
-from packaging.specifiers import SpecifierSet
-from spacy.training import docs_to_json, offsets_to_biluo_tags
-from spacy.training.converters import iob_to_docs, conll_ner_to_docs, conllu_to_docs
-from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate
-from spacy.lang.nl import Dutch
-from spacy.util import ENV_VARS, load_model_from_config
-from spacy.cli import info
-from spacy.cli.init_config import init_config, RECOMMENDATIONS
-from spacy.cli._util import validate_project_commands, parse_config_overrides
-from spacy.cli._util import load_project_config, substitute_project_variables
-from spacy.cli._util import is_subpath_of
-from spacy.cli._util import string_to_list
-from spacy import about
-from spacy.util import get_minor_version
-from spacy.cli.validate import get_model_pkgs
-from spacy.cli.download import get_compatibility, get_version
-from spacy.cli.package import get_third_party_dependencies
-from thinc.api import ConfigValidationError, Config
-import srsly
 import os
 
-from .util import make_tempdir
+import pytest
+import srsly
+from click import NoSuchOption
+from packaging.specifiers import SpecifierSet
+from thinc.api import Config, ConfigValidationError
+
+from spacy import about
+from spacy.cli import info
+from spacy.cli._util import is_subpath_of, load_project_config
+from spacy.cli._util import parse_config_overrides, string_to_list
+from spacy.cli._util import substitute_project_variables
+from spacy.cli._util import validate_project_commands
+from spacy.cli.download import get_compatibility, get_version
+from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
+from spacy.cli.package import get_third_party_dependencies
+from spacy.cli.validate import get_model_pkgs
+from spacy.lang.en import English
+from spacy.lang.nl import Dutch
+from spacy.language import Language
+from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate
+from spacy.training import Example, docs_to_json, offsets_to_biluo_tags
+from spacy.training.converters import conll_ner_to_docs, conllu_to_docs
+from spacy.training.converters import iob_to_docs
+from spacy.util import ENV_VARS, get_minor_version, load_model_from_config, load_config
+
 from ..cli.init_pipeline import _init_labels
+from .util import make_tempdir
+
+
+@pytest.mark.issue(4665)
+def test_issue4665():
+    """
+    conllu_to_docs should not raise an exception if the HEAD column contains an
+    underscore
+    """
+    input_data = """
+1	[	_	PUNCT	-LRB-	_	_	punct	_	_
+2	This	_	DET	DT	_	_	det	_	_
+3	killing	_	NOUN	NN	_	_	nsubj	_	_
+4	of	_	ADP	IN	_	_	case	_	_
+5	a	_	DET	DT	_	_	det	_	_
+6	respected	_	ADJ	JJ	_	_	amod	_	_
+7	cleric	_	NOUN	NN	_	_	nmod	_	_
+8	will	_	AUX	MD	_	_	aux	_	_
+9	be	_	AUX	VB	_	_	aux	_	_
+10	causing	_	VERB	VBG	_	_	root	_	_
+11	us	_	PRON	PRP	_	_	iobj	_	_
+12	trouble	_	NOUN	NN	_	_	dobj	_	_
+13	for	_	ADP	IN	_	_	case	_	_
+14	years	_	NOUN	NNS	_	_	nmod	_	_
+15	to	_	PART	TO	_	_	mark	_	_
+16	come	_	VERB	VB	_	_	acl	_	_
+17	.	_	PUNCT	.	_	_	punct	_	_
+18	]	_	PUNCT	-RRB-	_	_	punct	_	_
+"""
+    conllu_to_docs(input_data)
+
+
+@pytest.mark.issue(4924)
+def test_issue4924():
+    nlp = Language()
+    example = Example.from_dict(nlp.make_doc(""), {})
+    nlp.evaluate([example])
+
+
+@pytest.mark.issue(7055)
+def test_issue7055():
+    """Test that fill-config doesn't turn sourced components into factories."""
+    source_cfg = {
+        "nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger"]},
+        "components": {
+            "tok2vec": {"factory": "tok2vec"},
+            "tagger": {"factory": "tagger"},
+        },
+    }
+    source_nlp = English.from_config(source_cfg)
+    with make_tempdir() as dir_path:
+        # We need to create a loadable source pipeline
+        source_path = dir_path / "test_model"
+        source_nlp.to_disk(source_path)
+        base_cfg = {
+            "nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger", "ner"]},
+            "components": {
+                "tok2vec": {"source": str(source_path)},
+                "tagger": {"source": str(source_path)},
+                "ner": {"factory": "ner"},
+            },
+        }
+        base_cfg = Config(base_cfg)
+        base_path = dir_path / "base.cfg"
+        base_cfg.to_disk(base_path)
+        output_path = dir_path / "config.cfg"
+        fill_config(output_path, base_path, silent=True)
+        filled_cfg = load_config(output_path)
+    assert filled_cfg["components"]["tok2vec"]["source"] == str(source_path)
+    assert filled_cfg["components"]["tagger"]["source"] == str(source_path)
+    assert filled_cfg["components"]["ner"]["factory"] == "ner"
+    assert "model" in filled_cfg["components"]["ner"]
 
 
 def test_cli_info():
diff --git a/spacy/tests/test_displacy.py b/spacy/tests/test_displacy.py
index 790925888..392c95e42 100644
--- a/spacy/tests/test_displacy.py
+++ b/spacy/tests/test_displacy.py
@@ -1,11 +1,101 @@
+import numpy
 import pytest
 
 from spacy import displacy
 from spacy.displacy.render import DependencyRenderer, EntityRenderer
+from spacy.lang.en import English
 from spacy.lang.fa import Persian
 from spacy.tokens import Span, Doc
 
 
+@pytest.mark.issue(2361)
+def test_issue2361(de_vocab):
+    """Test if < is escaped when rendering"""
+    chars = ("&lt;", "&gt;", "&amp;", "&quot;")
+    words = ["<", ">", "&", '"']
+    doc = Doc(de_vocab, words=words, deps=["dep"] * len(words))
+    html = displacy.render(doc)
+    for char in chars:
+        assert char in html
+
+
+@pytest.mark.issue(2728)
+def test_issue2728(en_vocab):
+    """Test that displaCy ENT visualizer escapes HTML correctly."""
+    doc = Doc(en_vocab, words=["test", "<RELEASE>", "test"])
+    doc.ents = [Span(doc, 0, 1, label="TEST")]
+    html = displacy.render(doc, style="ent")
+    assert "&lt;RELEASE&gt;" in html
+    doc.ents = [Span(doc, 1, 2, label="TEST")]
+    html = displacy.render(doc, style="ent")
+    assert "&lt;RELEASE&gt;" in html
+
+
+@pytest.mark.issue(3288)
+def test_issue3288(en_vocab):
+    """Test that retokenization works correctly via displaCy when punctuation
+    is merged onto the preceeding token and tensor is resized."""
+    words = ["Hello", "World", "!", "When", "is", "this", "breaking", "?"]
+    heads = [1, 1, 1, 4, 4, 6, 4, 4]
+    deps = ["intj", "ROOT", "punct", "advmod", "ROOT", "det", "nsubj", "punct"]
+    doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
+    doc.tensor = numpy.zeros((len(words), 96), dtype="float32")
+    displacy.render(doc)
+
+
+@pytest.mark.issue(3531)
+def test_issue3531():
+    """Test that displaCy renderer doesn't require "settings" key."""
+    example_dep = {
+        "words": [
+            {"text": "But", "tag": "CCONJ"},
+            {"text": "Google", "tag": "PROPN"},
+            {"text": "is", "tag": "VERB"},
+            {"text": "starting", "tag": "VERB"},
+            {"text": "from", "tag": "ADP"},
+            {"text": "behind.", "tag": "ADV"},
+        ],
+        "arcs": [
+            {"start": 0, "end": 3, "label": "cc", "dir": "left"},
+            {"start": 1, "end": 3, "label": "nsubj", "dir": "left"},
+            {"start": 2, "end": 3, "label": "aux", "dir": "left"},
+            {"start": 3, "end": 4, "label": "prep", "dir": "right"},
+            {"start": 4, "end": 5, "label": "pcomp", "dir": "right"},
+        ],
+    }
+    example_ent = {
+        "text": "But Google is starting from behind.",
+        "ents": [{"start": 4, "end": 10, "label": "ORG"}],
+    }
+    dep_html = displacy.render(example_dep, style="dep", manual=True)
+    assert dep_html
+    ent_html = displacy.render(example_ent, style="ent", manual=True)
+    assert ent_html
+
+
+@pytest.mark.issue(3882)
+def test_issue3882(en_vocab):
+    """Test that displaCy doesn't serialize the doc.user_data when making a
+    copy of the Doc.
+    """
+    doc = Doc(en_vocab, words=["Hello", "world"], deps=["dep", "dep"])
+    doc.user_data["test"] = set()
+    displacy.parse_deps(doc)
+
+
+@pytest.mark.issue(5838)
+def test_issue5838():
+    # Displacy's EntityRenderer break line
+    # not working after last entity
+    sample_text = "First line\nSecond line, with ent\nThird line\nFourth line\n"
+    nlp = English()
+    doc = nlp(sample_text)
+    doc.ents = [Span(doc, 7, 8, label="test")]
+    html = displacy.render(doc, style="ent")
+    found = html.count("</br>")
+    assert found == 4
+
+
 def test_displacy_parse_ents(en_vocab):
     """Test that named entities on a Doc are converted into displaCy's format."""
     doc = Doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
diff --git a/spacy/tests/test_misc.py b/spacy/tests/test_misc.py
index f17d5e62e..d8743d322 100644
--- a/spacy/tests/test_misc.py
+++ b/spacy/tests/test_misc.py
@@ -15,7 +15,8 @@ from spacy.training.batchers import minibatch_by_words
 from spacy.lang.en import English
 from spacy.lang.nl import Dutch
 from spacy.language import DEFAULT_CONFIG_PATH
-from spacy.schemas import ConfigSchemaTraining
+from spacy.schemas import ConfigSchemaTraining, TokenPattern, TokenPatternSchema
+from pydantic import ValidationError
 
 from thinc.api import get_current_ops, NumpyOps, CupyOps
 
@@ -33,6 +34,32 @@ def is_admin():
     return admin
 
 
+@pytest.mark.issue(6207)
+def test_issue6207(en_tokenizer):
+    doc = en_tokenizer("zero one two three four five six")
+
+    # Make spans
+    s1 = doc[:4]
+    s2 = doc[3:6]  # overlaps with s1
+    s3 = doc[5:7]  # overlaps with s2, not s1
+
+    result = util.filter_spans((s1, s2, s3))
+    assert s1 in result
+    assert s2 not in result
+    assert s3 in result
+
+
+@pytest.mark.issue(6258)
+def test_issue6258():
+    """Test that the non-empty constraint pattern field is respected"""
+    # These one is valid
+    TokenPatternSchema(pattern=[TokenPattern()])
+    # But an empty pattern list should fail to validate
+    # based on the schema's constraint
+    with pytest.raises(ValidationError):
+        TokenPatternSchema(pattern=[])
+
+
 @pytest.mark.parametrize("text", ["hello/world", "hello world"])
 def test_util_ensure_path_succeeds(text):
     path = util.ensure_path(text)
diff --git a/spacy/tests/tokenizer/test_tokenizer.py b/spacy/tests/tokenizer/test_tokenizer.py
index 452bcc079..c2aeffcb5 100644
--- a/spacy/tests/tokenizer/test_tokenizer.py
+++ b/spacy/tests/tokenizer/test_tokenizer.py
@@ -1,9 +1,283 @@
-import pytest
 import re
-from spacy.vocab import Vocab
-from spacy.tokenizer import Tokenizer
-from spacy.util import ensure_path, compile_prefix_regex, compile_suffix_regex
+
+import numpy
+import pytest
+
 from spacy.lang.en import English
+from spacy.lang.de import German
+from spacy.tokenizer import Tokenizer
+from spacy.tokens import Doc
+from spacy.training import Example
+from spacy.util import compile_prefix_regex, compile_suffix_regex, ensure_path
+from spacy.vocab import Vocab
+from spacy.symbols import ORTH
+
+
+@pytest.mark.issue(743)
+def test_issue743():
+    doc = Doc(Vocab(), ["hello", "world"])
+    token = doc[0]
+    s = set([token])
+    items = list(s)
+    assert items[0] is token
+
+
+@pytest.mark.issue(801)
+@pytest.mark.skip(
+    reason="Can not be fixed unless with variable-width lookbehinds, cf. PR #3218"
+)
+@pytest.mark.parametrize(
+    "text,tokens",
+    [
+        ('"deserve,"--and', ['"', "deserve", ',"--', "and"]),
+        ("exception;--exclusive", ["exception", ";--", "exclusive"]),
+        ("day.--Is", ["day", ".--", "Is"]),
+        ("refinement:--just", ["refinement", ":--", "just"]),
+        ("memories?--To", ["memories", "?--", "To"]),
+        ("Useful.=--Therefore", ["Useful", ".=--", "Therefore"]),
+        ("=Hope.=--Pandora", ["=", "Hope", ".=--", "Pandora"]),
+    ],
+)
+def test_issue801(en_tokenizer, text, tokens):
+    """Test that special characters + hyphens are split correctly."""
+    doc = en_tokenizer(text)
+    assert len(doc) == len(tokens)
+    assert [t.text for t in doc] == tokens
+
+
+@pytest.mark.issue(1061)
+def test_issue1061():
+    """Test special-case works after tokenizing. Was caching problem."""
+    text = "I like _MATH_ even _MATH_ when _MATH_, except when _MATH_ is _MATH_! but not _MATH_."
+    tokenizer = English().tokenizer
+    doc = tokenizer(text)
+    assert "MATH" in [w.text for w in doc]
+    assert "_MATH_" not in [w.text for w in doc]
+
+    tokenizer.add_special_case("_MATH_", [{ORTH: "_MATH_"}])
+    doc = tokenizer(text)
+    assert "_MATH_" in [w.text for w in doc]
+    assert "MATH" not in [w.text for w in doc]
+
+    # For sanity, check it works when pipeline is clean.
+    tokenizer = English().tokenizer
+    tokenizer.add_special_case("_MATH_", [{ORTH: "_MATH_"}])
+    doc = tokenizer(text)
+    assert "_MATH_" in [w.text for w in doc]
+    assert "MATH" not in [w.text for w in doc]
+
+
+@pytest.mark.issue(1963)
+def test_issue1963(en_tokenizer):
+    """Test that doc.merge() resizes doc.tensor"""
+    doc = en_tokenizer("a b c d")
+    doc.tensor = numpy.ones((len(doc), 128), dtype="f")
+    with doc.retokenize() as retokenizer:
+        retokenizer.merge(doc[0:2])
+    assert len(doc) == 3
+    assert doc.tensor.shape == (3, 128)
+
+
+@pytest.mark.skip(
+    reason="Can not be fixed without variable-width look-behind (which we don't want)"
+)
+@pytest.mark.issue(1235)
+def test_issue1235():
+    """Test that g is not split of if preceded by a number and a letter"""
+    nlp = English()
+    testwords = "e2g 2g 52g"
+    doc = nlp(testwords)
+    assert len(doc) == 5
+    assert doc[0].text == "e2g"
+    assert doc[1].text == "2"
+    assert doc[2].text == "g"
+    assert doc[3].text == "52"
+    assert doc[4].text == "g"
+
+
+@pytest.mark.issue(1242)
+def test_issue1242():
+    nlp = English()
+    doc = nlp("")
+    assert len(doc) == 0
+    docs = list(nlp.pipe(["", "hello"]))
+    assert len(docs[0]) == 0
+    assert len(docs[1]) == 1
+
+
+@pytest.mark.issue(1257)
+def test_issue1257():
+    """Test that tokens compare correctly."""
+    doc1 = Doc(Vocab(), words=["a", "b", "c"])
+    doc2 = Doc(Vocab(), words=["a", "c", "e"])
+    assert doc1[0] != doc2[0]
+    assert not doc1[0] == doc2[0]
+
+
+@pytest.mark.issue(1375)
+def test_issue1375():
+    """Test that token.nbor() raises IndexError for out-of-bounds access."""
+    doc = Doc(Vocab(), words=["0", "1", "2"])
+    with pytest.raises(IndexError):
+        assert doc[0].nbor(-1)
+    assert doc[1].nbor(-1).text == "0"
+    with pytest.raises(IndexError):
+        assert doc[2].nbor(1)
+    assert doc[1].nbor(1).text == "2"
+
+
+@pytest.mark.issue(1488)
+def test_issue1488():
+    """Test that tokenizer can parse DOT inside non-whitespace separators"""
+    prefix_re = re.compile(r"""[\[\("']""")
+    suffix_re = re.compile(r"""[\]\)"']""")
+    infix_re = re.compile(r"""[-~\.]""")
+    simple_url_re = re.compile(r"""^https?://""")
+
+    def my_tokenizer(nlp):
+        return Tokenizer(
+            nlp.vocab,
+            {},
+            prefix_search=prefix_re.search,
+            suffix_search=suffix_re.search,
+            infix_finditer=infix_re.finditer,
+            token_match=simple_url_re.match,
+        )
+
+    nlp = English()
+    nlp.tokenizer = my_tokenizer(nlp)
+    doc = nlp("This is a test.")
+    for token in doc:
+        assert token.text
+
+
+@pytest.mark.issue(1494)
+def test_issue1494():
+    """Test if infix_finditer works correctly"""
+    infix_re = re.compile(r"""[^a-z]""")
+    test_cases = [
+        ("token 123test", ["token", "1", "2", "3", "test"]),
+        ("token 1test", ["token", "1test"]),
+        ("hello...test", ["hello", ".", ".", ".", "test"]),
+    ]
+
+    def new_tokenizer(nlp):
+        return Tokenizer(nlp.vocab, {}, infix_finditer=infix_re.finditer)
+
+    nlp = English()
+    nlp.tokenizer = new_tokenizer(nlp)
+    for text, expected in test_cases:
+        assert [token.text for token in nlp(text)] == expected
+
+
+@pytest.mark.skip(
+    reason="Can not be fixed without iterative looping between prefix/suffix and infix"
+)
+@pytest.mark.issue(2070)
+def test_issue2070():
+    """Test that checks that a dot followed by a quote is handled
+    appropriately.
+    """
+    # Problem: The dot is now properly split off, but the prefix/suffix rules
+    # are not applied again afterwards. This means that the quote will still be
+    # attached to the remaining token.
+    nlp = English()
+    doc = nlp('First sentence."A quoted sentence" he said ...')
+    assert len(doc) == 11
+
+
+@pytest.mark.issue(2926)
+def test_issue2926(fr_tokenizer):
+    """Test that the tokenizer correctly splits tokens separated by a slash (/)
+    ending in a digit.
+    """
+    doc = fr_tokenizer("Learn html5/css3/javascript/jquery")
+    assert len(doc) == 8
+    assert doc[0].text == "Learn"
+    assert doc[1].text == "html5"
+    assert doc[2].text == "/"
+    assert doc[3].text == "css3"
+    assert doc[4].text == "/"
+    assert doc[5].text == "javascript"
+    assert doc[6].text == "/"
+    assert doc[7].text == "jquery"
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "ABLEItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume TABLE ItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume ItemColumn IAcceptance Limits of ErrorIn-Service Limits of ErrorColumn IIColumn IIIColumn IVColumn VComputed VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeUnder Registration of\xa0VolumeOver Registration of\xa0VolumeCubic FeetCubic FeetCubic FeetCubic FeetCubic Feet1Up to 10.0100.0050.0100.005220.0200.0100.0200.010350.0360.0180.0360.0184100.0500.0250.0500.0255Over 100.5% of computed volume0.25% of computed volume0.5% of computed volume0.25% of computed volume",
+        "oow.jspsearch.eventoracleopenworldsearch.technologyoraclesolarissearch.technologystoragesearch.technologylinuxsearch.technologyserverssearch.technologyvirtualizationsearch.technologyengineeredsystemspcodewwmkmppscem:",
+    ],
+)
+@pytest.mark.issue(2626)
+def test_issue2626_2835(en_tokenizer, text):
+    """Check that sentence doesn't cause an infinite loop in the tokenizer."""
+    doc = en_tokenizer(text)
+    assert doc
+
+
+@pytest.mark.issue(2656)
+def test_issue2656(en_tokenizer):
+    """Test that tokenizer correctly splits off punctuation after numbers with
+    decimal points.
+    """
+    doc = en_tokenizer("I went for 40.3, and got home by 10.0.")
+    assert len(doc) == 11
+    assert doc[0].text == "I"
+    assert doc[1].text == "went"
+    assert doc[2].text == "for"
+    assert doc[3].text == "40.3"
+    assert doc[4].text == ","
+    assert doc[5].text == "and"
+    assert doc[6].text == "got"
+    assert doc[7].text == "home"
+    assert doc[8].text == "by"
+    assert doc[9].text == "10.0"
+    assert doc[10].text == "."
+
+
+@pytest.mark.issue(2754)
+def test_issue2754(en_tokenizer):
+    """Test that words like 'a' and 'a.m.' don't get exceptional norm values."""
+    a = en_tokenizer("a")
+    assert a[0].norm_ == "a"
+    am = en_tokenizer("am")
+    assert am[0].norm_ == "am"
+
+
+@pytest.mark.issue(3002)
+def test_issue3002():
+    """Test that the tokenizer doesn't hang on a long list of dots"""
+    nlp = German()
+    doc = nlp(
+        "880.794.982.218.444.893.023.439.794.626.120.190.780.624.990.275.671 ist eine lange Zahl"
+    )
+    assert len(doc) == 5
+
+
+@pytest.mark.skip(reason="default suffix rules avoid one upper-case letter before dot")
+@pytest.mark.issue(3449)
+def test_issue3449():
+    nlp = English()
+    nlp.add_pipe("sentencizer")
+    text1 = "He gave the ball to I. Do you want to go to the movies with I?"
+    text2 = "He gave the ball to I.  Do you want to go to the movies with I?"
+    text3 = "He gave the ball to I.\nDo you want to go to the movies with I?"
+    t1 = nlp(text1)
+    t2 = nlp(text2)
+    t3 = nlp(text3)
+    assert t1[5].text == "I"
+    assert t2[5].text == "I"
+    assert t3[5].text == "I"
+
+
+@pytest.mark.parametrize(
+    "text,words", [("A'B C", ["A", "'", "B", "C"]), ("A-B", ["A-B"])]
+)
+def test_gold_misaligned(en_tokenizer, text, words):
+    doc = en_tokenizer(text)
+    Example.from_dict(doc, {"words": words})
 
 
 def test_tokenizer_handles_no_word(tokenizer):
diff --git a/spacy/tests/training/test_training.py b/spacy/tests/training/test_training.py
index 68f86190b..0d73300d8 100644
--- a/spacy/tests/training/test_training.py
+++ b/spacy/tests/training/test_training.py
@@ -1,15 +1,18 @@
+import random
+
 import numpy
-from spacy.training import offsets_to_biluo_tags, biluo_tags_to_offsets, Alignment
-from spacy.training import biluo_tags_to_spans, iob_to_biluo
-from spacy.training import Corpus, docs_to_json, Example
-from spacy.training.align import get_alignments
-from spacy.training.converters import json_to_docs
-from spacy.lang.en import English
-from spacy.tokens import Doc, DocBin
-from spacy.util import get_words_and_spaces, minibatch
-from thinc.api import compounding
 import pytest
 import srsly
+from spacy.lang.en import English
+from spacy.tokens import Doc, DocBin
+from spacy.training import Alignment, Corpus, Example, biluo_tags_to_offsets
+from spacy.training import biluo_tags_to_spans, docs_to_json, iob_to_biluo
+from spacy.training import offsets_to_biluo_tags
+from spacy.training.align import get_alignments
+from spacy.training.converters import json_to_docs
+from spacy.util import get_words_and_spaces, load_model_from_path, minibatch
+from spacy.util import load_config_from_str
+from thinc.api import compounding
 
 from ..util import make_tempdir
 
@@ -68,6 +71,207 @@ def vocab():
     return nlp.vocab
 
 
+@pytest.mark.issue(999)
+def test_issue999():
+    """Test that adding entities and resuming training works passably OK.
+    There are two issues here:
+    1) We have to re-add labels. This isn't very nice.
+    2) There's no way to set the learning rate for the weight update, so we
+        end up out-of-scale, causing it to learn too fast.
+    """
+    TRAIN_DATA = [
+        ["hey", []],
+        ["howdy", []],
+        ["hey there", []],
+        ["hello", []],
+        ["hi", []],
+        ["i'm looking for a place to eat", []],
+        ["i'm looking for a place in the north of town", [(31, 36, "LOCATION")]],
+        ["show me chinese restaurants", [(8, 15, "CUISINE")]],
+        ["show me chines restaurants", [(8, 14, "CUISINE")]],
+    ]
+    nlp = English()
+    ner = nlp.add_pipe("ner")
+    for _, offsets in TRAIN_DATA:
+        for start, end, label in offsets:
+            ner.add_label(label)
+    nlp.initialize()
+    for itn in range(20):
+        random.shuffle(TRAIN_DATA)
+        for raw_text, entity_offsets in TRAIN_DATA:
+            example = Example.from_dict(
+                nlp.make_doc(raw_text), {"entities": entity_offsets}
+            )
+            nlp.update([example])
+
+    with make_tempdir() as model_dir:
+        nlp.to_disk(model_dir)
+        nlp2 = load_model_from_path(model_dir)
+
+    for raw_text, entity_offsets in TRAIN_DATA:
+        doc = nlp2(raw_text)
+        ents = {(ent.start_char, ent.end_char): ent.label_ for ent in doc.ents}
+        for start, end, label in entity_offsets:
+            if (start, end) in ents:
+                assert ents[(start, end)] == label
+                break
+            else:
+                if entity_offsets:
+                    raise Exception(ents)
+
+
+@pytest.mark.issue(4402)
+def test_issue4402():
+    json_data = {
+        "id": 0,
+        "paragraphs": [
+            {
+                "raw": "How should I cook bacon in an oven?\nI've heard of people cooking bacon in an oven.",
+                "sentences": [
+                    {
+                        "tokens": [
+                            {"id": 0, "orth": "How", "ner": "O"},
+                            {"id": 1, "orth": "should", "ner": "O"},
+                            {"id": 2, "orth": "I", "ner": "O"},
+                            {"id": 3, "orth": "cook", "ner": "O"},
+                            {"id": 4, "orth": "bacon", "ner": "O"},
+                            {"id": 5, "orth": "in", "ner": "O"},
+                            {"id": 6, "orth": "an", "ner": "O"},
+                            {"id": 7, "orth": "oven", "ner": "O"},
+                            {"id": 8, "orth": "?", "ner": "O"},
+                        ],
+                        "brackets": [],
+                    },
+                    {
+                        "tokens": [
+                            {"id": 9, "orth": "\n", "ner": "O"},
+                            {"id": 10, "orth": "I", "ner": "O"},
+                            {"id": 11, "orth": "'ve", "ner": "O"},
+                            {"id": 12, "orth": "heard", "ner": "O"},
+                            {"id": 13, "orth": "of", "ner": "O"},
+                            {"id": 14, "orth": "people", "ner": "O"},
+                            {"id": 15, "orth": "cooking", "ner": "O"},
+                            {"id": 16, "orth": "bacon", "ner": "O"},
+                            {"id": 17, "orth": "in", "ner": "O"},
+                            {"id": 18, "orth": "an", "ner": "O"},
+                            {"id": 19, "orth": "oven", "ner": "O"},
+                            {"id": 20, "orth": ".", "ner": "O"},
+                        ],
+                        "brackets": [],
+                    },
+                ],
+                "cats": [
+                    {"label": "baking", "value": 1.0},
+                    {"label": "not_baking", "value": 0.0},
+                ],
+            },
+            {
+                "raw": "What is the difference between white and brown eggs?\n",
+                "sentences": [
+                    {
+                        "tokens": [
+                            {"id": 0, "orth": "What", "ner": "O"},
+                            {"id": 1, "orth": "is", "ner": "O"},
+                            {"id": 2, "orth": "the", "ner": "O"},
+                            {"id": 3, "orth": "difference", "ner": "O"},
+                            {"id": 4, "orth": "between", "ner": "O"},
+                            {"id": 5, "orth": "white", "ner": "O"},
+                            {"id": 6, "orth": "and", "ner": "O"},
+                            {"id": 7, "orth": "brown", "ner": "O"},
+                            {"id": 8, "orth": "eggs", "ner": "O"},
+                            {"id": 9, "orth": "?", "ner": "O"},
+                        ],
+                        "brackets": [],
+                    },
+                    {"tokens": [{"id": 10, "orth": "\n", "ner": "O"}], "brackets": []},
+                ],
+                "cats": [
+                    {"label": "baking", "value": 0.0},
+                    {"label": "not_baking", "value": 1.0},
+                ],
+            },
+        ],
+    }
+    nlp = English()
+    attrs = ["ORTH", "SENT_START", "ENT_IOB", "ENT_TYPE"]
+    with make_tempdir() as tmpdir:
+        output_file = tmpdir / "test4402.spacy"
+        docs = json_to_docs([json_data])
+        data = DocBin(docs=docs, attrs=attrs).to_bytes()
+        with output_file.open("wb") as file_:
+            file_.write(data)
+        reader = Corpus(output_file)
+        train_data = list(reader(nlp))
+        assert len(train_data) == 2
+
+        split_train_data = []
+        for eg in train_data:
+            split_train_data.extend(eg.split_sents())
+        assert len(split_train_data) == 4
+
+
+CONFIG_7029 = """
+[nlp]
+lang = "en"
+pipeline = ["tok2vec", "tagger"]
+
+[components]
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v1"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v1"
+width = ${components.tok2vec.model.encode:width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,2500,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v1"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[components.tagger]
+factory = "tagger"
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode:width}
+upstream = "*"
+"""
+
+
+@pytest.mark.issue(7029)
+def test_issue7029():
+    """Test that an empty document doesn't mess up an entire batch."""
+    TRAIN_DATA = [
+        ("I like green eggs", {"tags": ["N", "V", "J", "N"]}),
+        ("Eat blue ham", {"tags": ["V", "J", "N"]}),
+    ]
+    nlp = English.from_config(load_config_from_str(CONFIG_7029))
+    train_examples = []
+    for t in TRAIN_DATA:
+        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    for i in range(50):
+        losses = {}
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
+    texts = ["first", "second", "third", "fourth", "and", "then", "some", ""]
+    docs1 = list(nlp.pipe(texts, batch_size=1))
+    docs2 = list(nlp.pipe(texts, batch_size=4))
+    assert [doc[0].tag_ for doc in docs1[:-1]] == [doc[0].tag_ for doc in docs2[:-1]]
+
+
 def test_gold_biluo_U(en_vocab):
     words = ["I", "flew", "to", "London", "."]
     spaces = [True, True, True, False, True]
diff --git a/spacy/tests/vocab_vectors/test_lexeme.py b/spacy/tests/vocab_vectors/test_lexeme.py
index b6fee6628..d91f41db3 100644
--- a/spacy/tests/vocab_vectors/test_lexeme.py
+++ b/spacy/tests/vocab_vectors/test_lexeme.py
@@ -1,7 +1,25 @@
-import pytest
 import numpy
+import pytest
 from spacy.attrs import IS_ALPHA, IS_DIGIT
+from spacy.lookups import Lookups
+from spacy.tokens import Doc
 from spacy.util import OOV_RANK
+from spacy.vocab import Vocab
+
+
+@pytest.mark.issue(361)
+@pytest.mark.parametrize("text1,text2", [("cat", "dog")])
+def test_issue361(en_vocab, text1, text2):
+    """Test Issue #361: Equality of lexemes"""
+    assert en_vocab[text1] == en_vocab[text1]
+    assert en_vocab[text1] != en_vocab[text2]
+
+
+@pytest.mark.issue(600)
+def test_issue600():
+    vocab = Vocab(tag_map={"NN": {"pos": "NOUN"}})
+    doc = Doc(vocab, words=["hello"])
+    doc[0].tag_ = "NN"
 
 
 @pytest.mark.parametrize("text1,prob1,text2,prob2", [("NOUN", -1, "opera", -2)])
diff --git a/spacy/tests/vocab_vectors/test_similarity.py b/spacy/tests/vocab_vectors/test_similarity.py
index b5f7303b5..3b9308f4d 100644
--- a/spacy/tests/vocab_vectors/test_similarity.py
+++ b/spacy/tests/vocab_vectors/test_similarity.py
@@ -16,6 +16,16 @@ def vocab(en_vocab, vectors):
     return en_vocab
 
 
+@pytest.mark.issue(2219)
+def test_issue2219(en_vocab):
+    """Test if indexing issue still occurs during Token-Token similarity"""
+    vectors = [("a", [1, 2, 3]), ("letter", [4, 5, 6])]
+    add_vecs_to_vocab(en_vocab, vectors)
+    [(word1, vec1), (word2, vec2)] = vectors
+    doc = Doc(en_vocab, words=[word1, word2])
+    assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
+
+
 def test_vectors_similarity_LL(vocab, vectors):
     [(word1, vec1), (word2, vec2)] = vectors
     lex1 = vocab[word1]
diff --git a/spacy/tests/vocab_vectors/test_vectors.py b/spacy/tests/vocab_vectors/test_vectors.py
index f2e74c3c9..9dc40b499 100644
--- a/spacy/tests/vocab_vectors/test_vectors.py
+++ b/spacy/tests/vocab_vectors/test_vectors.py
@@ -1,14 +1,15 @@
-import pytest
 import numpy
-from numpy.testing import assert_allclose, assert_equal, assert_almost_equal
-from thinc.api import get_current_ops
+import pytest
+from numpy.testing import assert_allclose, assert_almost_equal, assert_equal
+from thinc.api import NumpyOps, get_current_ops
+
 from spacy.lang.en import English
-from spacy.vocab import Vocab
-from spacy.vectors import Vectors
-from spacy.tokenizer import Tokenizer
 from spacy.strings import hash_string  # type: ignore
+from spacy.tokenizer import Tokenizer
 from spacy.tokens import Doc
 from spacy.training.initialize import convert_vectors
+from spacy.vectors import Vectors
+from spacy.vocab import Vocab
 
 from ..util import add_vecs_to_vocab, get_cosine, make_tempdir
 
@@ -65,6 +66,79 @@ def tokenizer_v(vocab):
     return Tokenizer(vocab, {}, None, None, None)
 
 
+@pytest.mark.issue(1518)
+def test_issue1518():
+    """Test vectors.resize() works."""
+    vectors = Vectors(shape=(10, 10))
+    vectors.add("hello", row=2)
+    vectors.resize((5, 9))
+
+
+@pytest.mark.issue(1539)
+def test_issue1539():
+    """Ensure vectors.resize() doesn't try to modify dictionary during iteration."""
+    v = Vectors(shape=(10, 10), keys=[5, 3, 98, 100])
+    v.resize((100, 100))
+
+
+@pytest.mark.issue(1807)
+def test_issue1807():
+    """Test vocab.set_vector also adds the word to the vocab."""
+    vocab = Vocab(vectors_name="test_issue1807")
+    assert "hello" not in vocab
+    vocab.set_vector("hello", numpy.ones((50,), dtype="f"))
+    assert "hello" in vocab
+
+
+@pytest.mark.issue(2871)
+def test_issue2871():
+    """Test that vectors recover the correct key for spaCy reserved words."""
+    words = ["dog", "cat", "SUFFIX"]
+    vocab = Vocab(vectors_name="test_issue2871")
+    vocab.vectors.resize(shape=(3, 10))
+    vector_data = numpy.zeros((3, 10), dtype="f")
+    for word in words:
+        _ = vocab[word]  # noqa: F841
+        vocab.set_vector(word, vector_data[0])
+    vocab.vectors.name = "dummy_vectors"
+    assert vocab["dog"].rank == 0
+    assert vocab["cat"].rank == 1
+    assert vocab["SUFFIX"].rank == 2
+    assert vocab.vectors.find(key="dog") == 0
+    assert vocab.vectors.find(key="cat") == 1
+    assert vocab.vectors.find(key="SUFFIX") == 2
+
+
+@pytest.mark.issue(3412)
+def test_issue3412():
+    data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f")
+    vectors = Vectors(data=data, keys=["A", "B", "C"])
+    keys, best_rows, scores = vectors.most_similar(
+        numpy.asarray([[9, 8, 7], [0, 0, 0]], dtype="f")
+    )
+    assert best_rows[0] == 2
+
+
+@pytest.mark.issue(4725)
+def test_issue4725_2():
+    if isinstance(get_current_ops, NumpyOps):
+        # ensures that this runs correctly and doesn't hang or crash because of the global vectors
+        # if it does crash, it's usually because of calling 'spawn' for multiprocessing (e.g. on Windows),
+        # or because of issues with pickling the NER (cf test_issue4725_1)
+        vocab = Vocab(vectors_name="test_vocab_add_vector")
+        data = numpy.ndarray((5, 3), dtype="f")
+        data[0] = 1.0
+        data[1] = 2.0
+        vocab.set_vector("cat", data[0])
+        vocab.set_vector("dog", data[1])
+        nlp = English(vocab=vocab)
+        nlp.add_pipe("ner")
+        nlp.initialize()
+        docs = ["Kurt is in London."] * 10
+        for _ in nlp.pipe(docs, batch_size=2, n_process=2):
+            pass
+
+
 def test_init_vectors_with_resize_shape(strings, resize_data):
     v = Vectors(shape=(len(strings), 3))
     v.resize(shape=resize_data.shape)
diff --git a/spacy/tests/vocab_vectors/test_vocab_api.py b/spacy/tests/vocab_vectors/test_vocab_api.py
index 56ef1d108..16cf80a08 100644
--- a/spacy/tests/vocab_vectors/test_vocab_api.py
+++ b/spacy/tests/vocab_vectors/test_vocab_api.py
@@ -1,6 +1,19 @@
 import pytest
-from spacy.attrs import LEMMA, ORTH, IS_ALPHA
+from spacy.attrs import IS_ALPHA, LEMMA, ORTH
 from spacy.parts_of_speech import NOUN, VERB
+from spacy.vocab import Vocab
+
+
+@pytest.mark.issue(1868)
+def test_issue1868():
+    """Test Vocab.__contains__ works with int keys."""
+    vocab = Vocab()
+    lex = vocab["hello"]
+    assert lex.orth in vocab
+    assert lex.orth_ in vocab
+    assert "some string" not in vocab
+    int_id = vocab.strings.add("some string")
+    assert int_id not in vocab
 
 
 @pytest.mark.parametrize(

From 472740d613675be8d3055e6e0a7e59b76d76a551 Mon Sep 17 00:00:00 2001
From: Natalia Rodnova <4512370+nrodnova@users.noreply.github.com>
Date: Mon, 6 Dec 2021 01:58:01 -0700
Subject: [PATCH 32/37] Added sents property to Span for Spans spanning over
 several sentences (#9699)

* Added sents property to Span class that returns a generator of sentences the Span belongs to

* Added description to Span.sents property

* Update test_span to clarify the difference between span.sent and span.sents

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update spacy/tests/doc/test_span.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Fix documentation typos in spacy/tokens/span.pyx

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update Span.sents doc string in spacy/tokens/span.pyx

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Parametrized test_span_spans

* Corrected Span.sents to check for span-level hook first. Also, made Span.sent respect doc-level sents hook if no span-level hook is provided

* Corrected Span ocumentation copy/paste issue

* Put back accidentally deleted lines

* Fixed formatting in span.pyx

* Moved check for SENT_START annotation after user hooks in Span.sents

* add version where the property was introduced

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/tests/doc/test_span.py | 70 ++++++++++++++++++++++++++++++++++++
 spacy/tokens/span.pyx        | 45 +++++++++++++++++++++++
 website/docs/api/span.md     | 21 +++++++++++
 3 files changed, 136 insertions(+)

diff --git a/spacy/tests/doc/test_span.py b/spacy/tests/doc/test_span.py
index d18293d3f..10aba5b94 100644
--- a/spacy/tests/doc/test_span.py
+++ b/spacy/tests/doc/test_span.py
@@ -200,6 +200,12 @@ def test_spans_span_sent(doc, doc_not_parsed):
     assert doc[:2].sent.root.text == "is"
     assert doc[:2].sent.text == "This is a sentence."
     assert doc[6:7].sent.root.left_edge.text == "This"
+    assert doc[0 : len(doc)].sent == list(doc.sents)[0]
+    assert list(doc[0 : len(doc)].sents) == list(doc.sents)
+
+    with pytest.raises(ValueError):
+        doc_not_parsed[:2].sent
+
     # test on manual sbd
     doc_not_parsed[0].is_sent_start = True
     doc_not_parsed[5].is_sent_start = True
@@ -207,6 +213,35 @@ def test_spans_span_sent(doc, doc_not_parsed):
     assert doc_not_parsed[10:14].sent == doc_not_parsed[5:]
 
 
+@pytest.mark.parametrize(
+    "start,end,expected_sentence",
+    [
+        (0, 14, "This is"),  # Entire doc
+        (1, 4, "This is"),  # Overlapping with 2 sentences
+        (0, 2, "This is"),  # Beginning of the Doc. Full sentence
+        (0, 1, "This is"),  # Beginning of the Doc. Part of a sentence
+        (10, 14, "And a"),  # End of the Doc. Overlapping with 2 senteces
+        (12, 14, "third."),  # End of the Doc. Full sentence
+        (1, 1, "This is"),  # Empty Span
+    ],
+)
+def test_spans_span_sent_user_hooks(doc, start, end, expected_sentence):
+
+    # Doc-level sents hook
+    def user_hook(doc):
+        return [doc[ii : ii + 2] for ii in range(0, len(doc), 2)]
+
+    doc.user_hooks["sents"] = user_hook
+
+    # Make sure doc-level sents hook works
+    assert doc[start:end].sent.text == expected_sentence
+
+    # Span-level sent hook
+    doc.user_span_hooks["sent"] = lambda x: x
+    # Now, span=level sent hook overrides the doc-level sents hook
+    assert doc[start:end].sent == doc[start:end]
+
+
 def test_spans_lca_matrix(en_tokenizer):
     """Test span's lca matrix generation"""
     tokens = en_tokenizer("the lazy dog slept")
@@ -536,3 +571,38 @@ def test_span_with_vectors(doc):
     # single-token span with vector
     assert_array_equal(ops.to_numpy(doc[10:11].vector), [-1, -1, -1])
     doc.vocab.vectors = prev_vectors
+
+
+@pytest.mark.parametrize(
+    "start,end,expected_sentences,expected_sentences_with_hook",
+    [
+        (0, 14, 3, 7),  # Entire doc
+        (3, 6, 2, 2),  # Overlapping with 2 sentences
+        (0, 4, 1, 2),  # Beginning of the Doc. Full sentence
+        (0, 3, 1, 2),  # Beginning of the Doc. Part of a sentence
+        (9, 14, 2, 3),  # End of the Doc. Overlapping with 2 senteces
+        (10, 14, 1, 2),  # End of the Doc. Full sentence
+        (11, 14, 1, 2),  # End of the Doc. Partial sentence
+        (0, 0, 1, 1),  # Empty Span
+    ],
+)
+def test_span_sents(doc, start, end, expected_sentences, expected_sentences_with_hook):
+
+    assert len(list(doc[start:end].sents)) == expected_sentences
+
+    def user_hook(doc):
+        return [doc[ii : ii + 2] for ii in range(0, len(doc), 2)]
+
+    doc.user_hooks["sents"] = user_hook
+
+    assert len(list(doc[start:end].sents)) == expected_sentences_with_hook
+
+    doc.user_span_hooks["sents"] = lambda x: [x]
+
+    assert list(doc[start:end].sents)[0] == doc[start:end]
+    assert len(list(doc[start:end].sents)) == 1
+
+
+def test_span_sents_not_parsed(doc_not_parsed):
+    with pytest.raises(ValueError):
+        list(Span(doc_not_parsed, 0, 3).sents)
diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx
index 96f843a33..cd02cab36 100644
--- a/spacy/tokens/span.pyx
+++ b/spacy/tokens/span.pyx
@@ -404,6 +404,10 @@ cdef class Span:
         """
         if "sent" in self.doc.user_span_hooks:
             return self.doc.user_span_hooks["sent"](self)
+        elif "sents" in self.doc.user_hooks:
+            for sentence in self.doc.user_hooks["sents"](self.doc):
+                if sentence.start <= self.start < sentence.end:
+                    return sentence
         # Use `sent_start` token attribute to find sentence boundaries
         cdef int n = 0
         if self.doc.has_annotation("SENT_START"):
@@ -422,6 +426,47 @@ cdef class Span:
         else:
             raise ValueError(Errors.E030)
 
+    @property
+    def sents(self):
+        """Obtain the sentences that contain this span. If the given span
+        crosses sentence boundaries, return all sentences it is a part of.
+
+        RETURNS (Iterable[Span]): All sentences that the span is a part of.
+
+         DOCS: https://spacy.io/api/span#sents
+        """
+        cdef int start
+        cdef int i
+
+        if "sents" in self.doc.user_span_hooks:
+            yield from self.doc.user_span_hooks["sents"](self)
+        elif "sents" in self.doc.user_hooks:
+            for sentence in self.doc.user_hooks["sents"](self.doc):
+                if sentence.end > self.start:
+                    if sentence.start < self.end or sentence.start == self.start == self.end:
+                        yield sentence
+                    else:
+                        break
+        else:
+            if not self.doc.has_annotation("SENT_START"):
+                raise ValueError(Errors.E030)
+            # Use `sent_start` token attribute to find sentence boundaries
+            # Find start of the 1st sentence of the Span
+            start = self.start
+            while self.doc.c[start].sent_start != 1 and start > 0:
+                start -= 1
+
+            # Now, find all the sentences in the span
+            for i in range(start + 1, self.doc.length):
+                if self.doc.c[i].sent_start == 1:
+                    yield Span(self.doc, start, i)
+                    start = i
+                    if start >= self.end:
+                        break
+            if start < self.end:
+                yield Span(self.doc, start, self.end)
+
+
     @property
     def ents(self):
         """The named entities in the span. Returns a tuple of named entity
diff --git a/website/docs/api/span.md b/website/docs/api/span.md
index 2938b4253..7ecebf93e 100644
--- a/website/docs/api/span.md
+++ b/website/docs/api/span.md
@@ -518,6 +518,27 @@ sent = doc[sent.start : max(sent.end, span.end)]
 | ----------- | ------------------------------------------------------- |
 | **RETURNS** | The sentence span that this span is a part of. ~~Span~~ |
 
+## Span.sents {#sents tag="property" model="sentences" new="3.2.1"}
+
+Returns a generator over the sentences the span belongs to. This property is only available
+when [sentence boundaries](/usage/linguistic-features#sbd) have been set on the
+document by the `parser`, `senter`, `sentencizer` or some custom function. It
+will raise an error otherwise.
+
+If the span happens to cross sentence boundaries, all sentences the span overlaps with will be returned.
+
+> #### Example
+>
+> ```python
+> doc = nlp("Give it back! He pleaded.")
+> span = doc[2:4]
+> assert len(span.sents) == 2
+> ```
+
+| Name        | Description                                                                |
+| ----------- | -------------------------------------------------------------------------- |
+| **RETURNS** | A generator yielding sentences this `Span` is a part of ~~Iterable[Span]~~ |
+
 ## Attributes {#attributes}
 
 | Name                                    | Description                                                                                                                   |

From b56b9e7f31956edd59b5dbd676c7aa1b6e1048b0 Mon Sep 17 00:00:00 2001
From: Duygu Altinok <duygu.altinok12@gmail.com>
Date: Mon, 6 Dec 2021 15:32:49 +0100
Subject: [PATCH 33/37] Entity ruler remove pattern (#9685)

* added ruler coe

* added error for none existing pattern

* changed error to warning

* changed error to warning

* added basic tests

* fixed place

* added test files

* went back to error

* went back to pattern error

* minor change to docs

* changed style

* changed doc

* changed error slightly

* added remove to phrasem api

* error key already existed

* phrase matcher match code to api

* blacked tests

* moved comments before expr

* corrected error no

* Update website/docs/api/entityruler.md

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update website/docs/api/entityruler.md

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/errors.py                           |   2 +
 spacy/matcher/phrasematcher.pyi           |  16 +-
 spacy/pipeline/entityruler.py             |  40 +++++
 spacy/tests/pipeline/test_entity_ruler.py | 182 ++++++++++++++++++++++
 website/docs/api/entityruler.md           |  18 +++
 5 files changed, 252 insertions(+), 6 deletions(-)

diff --git a/spacy/errors.py b/spacy/errors.py
index c5e364013..ad7a0280f 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -889,6 +889,8 @@ class Errors(metaclass=ErrorsWithCodes):
              "Non-UD tags should use the `tag` property.")
     E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
     E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't exist.")
+    E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler patterns.")
+    
 
 
 # Deprecated model shortcuts, only used in errors and warnings
diff --git a/spacy/matcher/phrasematcher.pyi b/spacy/matcher/phrasematcher.pyi
index d73633ec0..741bf7bb6 100644
--- a/spacy/matcher/phrasematcher.pyi
+++ b/spacy/matcher/phrasematcher.pyi
@@ -8,12 +8,9 @@ class PhraseMatcher:
     def __init__(
         self, vocab: Vocab, attr: Optional[Union[int, str]], validate: bool = ...
     ) -> None: ...
-    def __call__(
-        self,
-        doclike: Union[Doc, Span],
-        *,
-        as_spans: bool = ...,
-    ) -> Union[List[Tuple[int, int, int]], List[Span]]: ...
+    def __reduce__(self) -> Any: ...
+    def __len__(self) -> int: ...
+    def __contains__(self, key: str) -> bool: ...
     def add(
         self,
         key: str,
@@ -23,3 +20,10 @@ class PhraseMatcher:
             Callable[[Matcher, Doc, int, List[Tuple[Any, ...]]], Any]
         ] = ...,
     ) -> None: ...
+    def remove(self, key: str) -> None: ...
+    def __call__(
+        self,
+        doclike: Union[Doc, Span],
+        *,
+        as_spans: bool = ...,
+    ) -> Union[List[Tuple[int, int, int]], List[Span]]: ...
diff --git a/spacy/pipeline/entityruler.py b/spacy/pipeline/entityruler.py
index 78d7a0be2..614d71f41 100644
--- a/spacy/pipeline/entityruler.py
+++ b/spacy/pipeline/entityruler.py
@@ -348,6 +348,46 @@ class EntityRuler(Pipe):
             self.nlp.vocab, attr=self.phrase_matcher_attr, validate=self._validate
         )
 
+    def remove(self, ent_id: str) -> None:
+        """Remove a pattern by its ent_id if a pattern with this ent_id was added before
+
+        ent_id (str): id of the pattern to be removed
+        RETURNS: None
+        DOCS: https://spacy.io/api/entityruler#remove
+        """
+        label_id_pairs = [
+            (label, eid) for (label, eid) in self._ent_ids.values() if eid == ent_id
+        ]
+        if not label_id_pairs:
+            raise ValueError(Errors.E1024.format(ent_id=ent_id))
+        created_labels = [
+            self._create_label(label, eid) for (label, eid) in label_id_pairs
+        ]
+        # remove the patterns from self.phrase_patterns
+        self.phrase_patterns = defaultdict(
+            list,
+            {
+                label: val
+                for (label, val) in self.phrase_patterns.items()
+                if label not in created_labels
+            },
+        )
+        # remove the patterns from self.token_pattern
+        self.token_patterns = defaultdict(
+            list,
+            {
+                label: val
+                for (label, val) in self.token_patterns.items()
+                if label not in created_labels
+            },
+        )
+        # remove the patterns from self.token_pattern
+        for label in created_labels:
+            if label in self.phrase_matcher:
+                self.phrase_matcher.remove(label)
+            else:
+                self.matcher.remove(label)
+
     def _require_patterns(self) -> None:
         """Raise a warning if this component has no patterns defined."""
         if len(self) == 0:
diff --git a/spacy/tests/pipeline/test_entity_ruler.py b/spacy/tests/pipeline/test_entity_ruler.py
index 0cecafff3..f2031d0a9 100644
--- a/spacy/tests/pipeline/test_entity_ruler.py
+++ b/spacy/tests/pipeline/test_entity_ruler.py
@@ -373,3 +373,185 @@ def test_entity_ruler_serialize_dir(nlp, patterns):
         ruler.from_disk(d / "test_ruler")  # read from an existing directory
         with pytest.raises(ValueError):
             ruler.from_disk(d / "non_existing_dir")  # read from a bad directory
+
+
+def test_entity_ruler_remove_basic(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+        {"label": "ORG", "pattern": "ACM"},
+    ]
+    ruler.add_patterns(patterns)
+    doc = ruler(nlp.make_doc("Duygu went to school"))
+    assert len(ruler.patterns) == 3
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "PERSON"
+    assert doc.ents[0].text == "Duygu"
+    assert "PERSON||duygu" in ruler.phrase_matcher
+    ruler.remove("duygu")
+    doc = ruler(nlp.make_doc("Duygu went to school"))
+    assert len(doc.ents) == 0
+    assert "PERSON||duygu" not in ruler.phrase_matcher
+    assert len(ruler.patterns) == 2
+
+
+def test_entity_ruler_remove_same_id_multiple_patterns(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "DuyguCorp", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+    ]
+    ruler.add_patterns(patterns)
+    doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
+    assert len(ruler.patterns) == 3
+    assert "PERSON||duygu" in ruler.phrase_matcher
+    assert "ORG||duygu" in ruler.phrase_matcher
+    assert len(doc.ents) == 3
+    ruler.remove("duygu")
+    doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
+    assert len(ruler.patterns) == 1
+    assert "PERSON||duygu" not in ruler.phrase_matcher
+    assert "ORG||duygu" not in ruler.phrase_matcher
+    assert len(doc.ents) == 1
+
+
+def test_entity_ruler_remove_nonexisting_pattern(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+        {"label": "ORG", "pattern": "ACM"},
+    ]
+    ruler.add_patterns(patterns)
+    assert len(ruler.patterns) == 3
+    with pytest.raises(ValueError):
+        ruler.remove("nepattern")
+        assert len(ruler.patterns) == 3
+
+
+def test_entity_ruler_remove_several_patterns(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+        {"label": "ORG", "pattern": "ACM"},
+    ]
+    ruler.add_patterns(patterns)
+    doc = ruler(nlp.make_doc("Duygu founded her company ACME."))
+    assert len(ruler.patterns) == 3
+    assert len(doc.ents) == 2
+    assert doc.ents[0].label_ == "PERSON"
+    assert doc.ents[0].text == "Duygu"
+    assert doc.ents[1].label_ == "ORG"
+    assert doc.ents[1].text == "ACME"
+    ruler.remove("duygu")
+    doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
+    assert len(ruler.patterns) == 2
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "ORG"
+    assert doc.ents[0].text == "ACME"
+    ruler.remove("acme")
+    doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
+    assert len(ruler.patterns) == 1
+    assert len(doc.ents) == 0
+
+
+def test_entity_ruler_remove_patterns_in_a_row(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+        {"label": "DATE", "pattern": "her birthday", "id": "bday"},
+        {"label": "ORG", "pattern": "ACM"},
+    ]
+    ruler.add_patterns(patterns)
+    doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
+    assert len(doc.ents) == 3
+    assert doc.ents[0].label_ == "PERSON"
+    assert doc.ents[0].text == "Duygu"
+    assert doc.ents[1].label_ == "ORG"
+    assert doc.ents[1].text == "ACME"
+    assert doc.ents[2].label_ == "DATE"
+    assert doc.ents[2].text == "her birthday"
+    ruler.remove("duygu")
+    ruler.remove("acme")
+    ruler.remove("bday")
+    doc = ruler(nlp.make_doc("Duygu went to school"))
+    assert len(doc.ents) == 0
+
+
+def test_entity_ruler_remove_all_patterns(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [
+        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "ORG", "pattern": "ACME", "id": "acme"},
+        {"label": "DATE", "pattern": "her birthday", "id": "bday"},
+    ]
+    ruler.add_patterns(patterns)
+    assert len(ruler.patterns) == 3
+    ruler.remove("duygu")
+    assert len(ruler.patterns) == 2
+    ruler.remove("acme")
+    assert len(ruler.patterns) == 1
+    ruler.remove("bday")
+    assert len(ruler.patterns) == 0
+    with pytest.warns(UserWarning):
+        doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
+        assert len(doc.ents) == 0
+
+
+def test_entity_ruler_remove_and_add(nlp):
+    ruler = EntityRuler(nlp)
+    patterns = [{"label": "DATE", "pattern": "last time"}]
+    ruler.add_patterns(patterns)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 1
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "DATE"
+    assert doc.ents[0].text == "last time"
+    patterns1 = [{"label": "DATE", "pattern": "this time", "id": "ttime"}]
+    ruler.add_patterns(patterns1)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 2
+    assert len(doc.ents) == 2
+    assert doc.ents[0].label_ == "DATE"
+    assert doc.ents[0].text == "last time"
+    assert doc.ents[1].label_ == "DATE"
+    assert doc.ents[1].text == "this time"
+    ruler.remove("ttime")
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 1
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "DATE"
+    assert doc.ents[0].text == "last time"
+    ruler.add_patterns(patterns1)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 2
+    assert len(doc.ents) == 2
+    patterns2 = [{"label": "DATE", "pattern": "another time", "id": "ttime"}]
+    ruler.add_patterns(patterns2)
+    doc = ruler(
+        nlp.make_doc(
+            "I saw him last time we met, this time he brought some flowers, another time some chocolate."
+        )
+    )
+    assert len(ruler.patterns) == 3
+    assert len(doc.ents) == 3
+    ruler.remove("ttime")
+    doc = ruler(
+        nlp.make_doc(
+            "I saw him last time we met, this time he brought some flowers, another time some chocolate."
+        )
+    )
+    assert len(ruler.patterns) == 1
+    assert len(doc.ents) == 1
diff --git a/website/docs/api/entityruler.md b/website/docs/api/entityruler.md
index fb33642f8..6d8f835bf 100644
--- a/website/docs/api/entityruler.md
+++ b/website/docs/api/entityruler.md
@@ -210,6 +210,24 @@ of dicts) or a phrase pattern (string). For more details, see the usage guide on
 | ---------- | ---------------------------------------------------------------- |
 | `patterns` | The patterns to add. ~~List[Dict[str, Union[str, List[dict]]]]~~ |
 
+
+## EntityRuler.remove {#remove tag="method" new="3.2.1"}
+
+Remove a pattern by its ID from the entity ruler. A `ValueError` is raised if the ID does not exist.
+
+> #### Example
+>
+> ```python
+> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
+> ruler = nlp.add_pipe("entity_ruler")
+> ruler.add_patterns(patterns)
+> ruler.remove("apple")
+> ```
+
+| Name       | Description                                                      |
+| ---------- | ---------------------------------------------------------------- |
+| `id`       | The ID of the pattern rule. ~~str~~ |
+
 ## EntityRuler.to_disk {#to_disk tag="method"}
 
 Save the entity ruler patterns to a directory. The patterns will be saved as

From 9964243eb2a0a2aa78e7f2377e57b97f8225bba3 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Mon, 6 Dec 2021 18:04:44 +0100
Subject: [PATCH 34/37] Make the Tagger neg_prefix configurable (#9802)

---
 spacy/pipeline/tagger.pyx | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/spacy/pipeline/tagger.pyx b/spacy/pipeline/tagger.pyx
index c0768dfec..a2bec888e 100644
--- a/spacy/pipeline/tagger.pyx
+++ b/spacy/pipeline/tagger.pyx
@@ -45,7 +45,7 @@ DEFAULT_TAGGER_MODEL = Config().from_str(default_model_config)["model"]
 @Language.factory(
     "tagger",
     assigns=["token.tag"],
-    default_config={"model": DEFAULT_TAGGER_MODEL, "overwrite": False, "scorer": {"@scorers": "spacy.tagger_scorer.v1"}},
+    default_config={"model": DEFAULT_TAGGER_MODEL, "overwrite": False, "scorer": {"@scorers": "spacy.tagger_scorer.v1"}, "neg_prefix": "!"},
     default_score_weights={"tag_acc": 1.0},
 )
 def make_tagger(
@@ -54,6 +54,7 @@ def make_tagger(
     model: Model,
     overwrite: bool,
     scorer: Optional[Callable],
+    neg_prefix: str,
 ):
     """Construct a part-of-speech tagger component.
 
@@ -62,7 +63,7 @@ def make_tagger(
         in size, and be normalized as probabilities (all scores between 0 and 1,
         with the rows summing to 1).
     """
-    return Tagger(nlp.vocab, model, name, overwrite=overwrite, scorer=scorer)
+    return Tagger(nlp.vocab, model, name, overwrite=overwrite, scorer=scorer, neg_prefix=neg_prefix)
 
 
 def tagger_score(examples, **kwargs):
@@ -87,6 +88,7 @@ class Tagger(TrainablePipe):
         *,
         overwrite=BACKWARD_OVERWRITE,
         scorer=tagger_score,
+        neg_prefix="!",
     ):
         """Initialize a part-of-speech tagger.
 
@@ -103,7 +105,7 @@ class Tagger(TrainablePipe):
         self.model = model
         self.name = name
         self._rehearsal_model = None
-        cfg = {"labels": [], "overwrite": overwrite}
+        cfg = {"labels": [], "overwrite": overwrite, "neg_prefix": neg_prefix}
         self.cfg = dict(sorted(cfg.items()))
         self.scorer = scorer
 
@@ -253,7 +255,7 @@ class Tagger(TrainablePipe):
         DOCS: https://spacy.io/api/tagger#get_loss
         """
         validate_examples(examples, "Tagger.get_loss")
-        loss_func = SequenceCategoricalCrossentropy(names=self.labels, normalize=False, neg_prefix="!")
+        loss_func = SequenceCategoricalCrossentropy(names=self.labels, normalize=False, neg_prefix=self.cfg["neg_prefix"])
         # Convert empty tag "" to missing value None so that both misaligned
         # tokens and tokens with missing annotation have the default missing
         # value None.

From a0cdc2b007799317e3d8691b31de045dd8a893d1 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Mon, 6 Dec 2021 20:39:15 +0100
Subject: [PATCH 35/37] Use Language.pipe in evaluate (#9800)

---
 spacy/language.py | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/spacy/language.py b/spacy/language.py
index 204b24ecb..638616316 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -1404,20 +1404,13 @@ class Language:
         for eg in examples:
             self.make_doc(eg.reference.text)
         # apply all pipeline components
-        for name, pipe in self.pipeline:
-            kwargs = component_cfg.get(name, {})
-            kwargs.setdefault("batch_size", batch_size)
-            for doc, eg in zip(
-                _pipe(
-                    (eg.predicted for eg in examples),
-                    proc=pipe,
-                    name=name,
-                    default_error_handler=self.default_error_handler,
-                    kwargs=kwargs,
-                ),
-                examples,
-            ):
-                eg.predicted = doc
+        docs = self.pipe(
+            (eg.predicted for eg in examples),
+            batch_size=batch_size,
+            component_cfg=component_cfg,
+        )
+        for eg, doc in zip(examples, docs):
+            eg.predicted = doc
         end_time = timer()
         results = scorer.score(examples)
         n_words = sum(len(eg.predicted) for eg in examples)

From 51a3b60027d3daa9da503b153845a823165a9f8d Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 7 Dec 2021 09:42:40 +0100
Subject: [PATCH 36/37] Document Tagger neg_prefix, fix typo (#9821)

---
 website/docs/api/entityrecognizer.md |  2 +-
 website/docs/api/tagger.md           | 11 ++++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/website/docs/api/entityrecognizer.md b/website/docs/api/entityrecognizer.md
index 2f7a88fbf..14b6fece4 100644
--- a/website/docs/api/entityrecognizer.md
+++ b/website/docs/api/entityrecognizer.md
@@ -65,7 +65,7 @@ architectures and their arguments and hyperparameters.
 | `moves`                       | A list of transition names. Inferred from the data if not provided. Defaults to `None`. ~~Optional[List[str]]~~                                                                                                                                     |
 | `update_with_oracle_cut_size` | During training, cut long sequences into shorter segments by creating intermediate states based on the gold-standard history. The model is not very sensitive to this parameter, so you usually won't need to change it. Defaults to `100`. ~~int~~ |
 | `model`                       | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. Defaults to [TransitionBasedParser](/api/architectures#TransitionBasedParser). ~~Model[List[Doc], List[Floats2d]]~~                                                 |
-| `incorrect_spans_key`         | This key refers to a `SpanGroup` in `doc.spans` that specifies incorrect spans. The NER wiill learn not to predict (exactly) those spans. Defaults to `None`. ~~Optional[str]~~                                                                     |
+| `incorrect_spans_key`         | This key refers to a `SpanGroup` in `doc.spans` that specifies incorrect spans. The NER will learn not to predict (exactly) those spans. Defaults to `None`. ~~Optional[str]~~                                                                      |
 | `scorer`                      | The scoring method. Defaults to [`spacy.scorer.get_ner_prf`](/api/scorer#get_ner_prf). ~~Optional[Callable]~~                                                                                                                                       |
 
 ```python
diff --git a/website/docs/api/tagger.md b/website/docs/api/tagger.md
index 93b6bc88b..b51864d3a 100644
--- a/website/docs/api/tagger.md
+++ b/website/docs/api/tagger.md
@@ -40,11 +40,12 @@ architectures and their arguments and hyperparameters.
 > nlp.add_pipe("tagger", config=config)
 > ```
 
-| Setting                                  | Description                                                                                                                                                                                                                                                                                            |
-| ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `model`                                  | A model instance that predicts the tag probabilities. The output vectors should match the number of tags in size, and be normalized as probabilities (all scores between 0 and 1, with the rows summing to `1`). Defaults to [Tagger](/api/architectures#Tagger). ~~Model[List[Doc], List[Floats2d]]~~ |
-| `overwrite` <Tag variant="new">3.2</Tag> | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                                                                                                                                                                                              |
-| `scorer` <Tag variant="new">3.2</Tag>    | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attribute `"tag"`. ~~Optional[Callable]~~                                                                                                                                                            |
+| Setting                                     | Description                                                                                                                                                                                                                                                                                            |
+| ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `model`                                     | A model instance that predicts the tag probabilities. The output vectors should match the number of tags in size, and be normalized as probabilities (all scores between 0 and 1, with the rows summing to `1`). Defaults to [Tagger](/api/architectures#Tagger). ~~Model[List[Doc], List[Floats2d]]~~ |
+| `overwrite` <Tag variant="new">3.2</Tag>    | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                                                                                                                                                                                              |
+| `scorer` <Tag variant="new">3.2</Tag>       | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attribute `"tag"`. ~~Optional[Callable]~~                                                                                                                                                            |
+| `neg_prefix` <Tag variant="new">3.2.1</Tag> | The prefix used to specify incorrect tags while training. The tagger will learn not to predict exactly this tag. Defaults to `!`. ~~str~~                                                                                                                                                              |
 
 ```python
 %%GITHUB_SPACY/spacy/pipeline/tagger.pyx

From 800737b41632c4b8dc24c992c8dd36f073549579 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Tue, 7 Dec 2021 10:51:45 +0100
Subject: [PATCH 37/37] Set version to v3.2.1 (#9823)

---
 spacy/about.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/about.py b/spacy/about.py
index 29f78805c..c253d5052 100644
--- a/spacy/about.py
+++ b/spacy/about.py
@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.2.0"
+__version__ = "3.2.1"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"