diff --git a/requirements.txt b/requirements.txt
index e61a029c9..bf95839b5 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,7 +4,7 @@ preshed>=2.0.1,<2.1.0
thinc>=7.0.2,<7.1.0
blis>=0.2.2,<0.3.0
murmurhash>=0.28.0,<1.1.0
-wasabi>=0.1.3,<1.1.0
+wasabi>=0.2.0,<1.1.0
srsly>=0.0.5,<1.1.0
# Third party dependencies
numpy>=1.15.0
diff --git a/setup.py b/setup.py
index 6f29e1efa..ed030eaf0 100755
--- a/setup.py
+++ b/setup.py
@@ -232,7 +232,7 @@ def setup_package():
"plac<1.0.0,>=0.9.6",
"requests>=2.13.0,<3.0.0",
"jsonschema>=2.6.0,<3.0.0",
- "wasabi>=0.0.12,<1.1.0",
+ "wasabi>=0.2.0,<1.1.0",
"srsly>=0.0.5,<1.1.0",
'pathlib==1.0.1; python_version < "3.4"',
],
diff --git a/spacy/about.py b/spacy/about.py
index 7b1f36c40..1592620ae 100644
--- a/spacy/about.py
+++ b/spacy/about.py
@@ -4,7 +4,7 @@
# fmt: off
__title__ = "spacy"
-__version__ = "2.1.1"
+__version__ = "2.1.2"
__summary__ = "Industrial-strength Natural Language Processing (NLP) with Python and Cython"
__uri__ = "https://spacy.io"
__author__ = "Explosion AI"
diff --git a/spacy/compat.py b/spacy/compat.py
index 8af49f254..997e8787b 100644
--- a/spacy/compat.py
+++ b/spacy/compat.py
@@ -11,6 +11,7 @@ from __future__ import unicode_literals
import os
import sys
import itertools
+import ast
from thinc.neural.util import copy_array
@@ -150,3 +151,26 @@ def import_file(name, loc):
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
+
+
+def unescape_unicode(string):
+ """Python2.7's re module chokes when compiling patterns that have ranges
+ between escaped unicode codepoints if the two codepoints are unrecognised
+ in the unicode database. For instance:
+
+ re.compile('[\\uAA77-\\uAA79]').findall("hello")
+
+ Ends up matching every character (on Python 2). This problem doesn't occur
+ if we're dealing with unicode literals.
+ """
+ if string is None:
+ return string
+ # We only want to unescape the unicode, so we first must protect the other
+ # backslashes.
+ string = string.replace("\\", "\\\\")
+ # Now we remove that protection for the unicode.
+ string = string.replace("\\\\u", "\\u")
+ string = string.replace("\\\\U", "\\U")
+ # Now we unescape by evaling the string with the AST. This can't execute
+ # code -- it only does the representational level.
+ return ast.literal_eval("u'''" + string + "'''")
diff --git a/spacy/lang/en/morph_rules.py b/spacy/lang/en/morph_rules.py
index d073e27a5..54a108d53 100644
--- a/spacy/lang/en/morph_rules.py
+++ b/spacy/lang/en/morph_rules.py
@@ -1,13 +1,97 @@
# coding: utf8
from __future__ import unicode_literals
-from ...symbols import LEMMA, PRON_LEMMA
+from ...symbols import LEMMA, PRON_LEMMA, AUX
+_subordinating_conjunctions = [
+ "that",
+ "if",
+ "as",
+ "because",
+ "of",
+ "for",
+ "before",
+ "in",
+ "while",
+ "after",
+ "since",
+ "like",
+ "with",
+ "so",
+ "to",
+ "by",
+ "on",
+ "about",
+ "than",
+ "whether",
+ "although",
+ "from",
+ "though",
+ "until",
+ "unless",
+ "once",
+ "without",
+ "at",
+ "into",
+ "cause",
+ "over",
+ "upon",
+ "till",
+ "whereas",
+ "beyond",
+ "whilst",
+ "except",
+ "despite",
+ "wether",
+ "then",
+ "but",
+ "becuse",
+ "whie",
+ "below",
+ "against",
+ "it",
+ "w/out",
+ "toward",
+ "albeit",
+ "save",
+ "besides",
+ "becouse",
+ "coz",
+ "til",
+ "ask",
+ "i'd",
+ "out",
+ "near",
+ "seince",
+ "towards",
+ "tho",
+ "sice",
+ "will",
+]
+
+_relative_pronouns = ["this", "that", "those", "these"]
MORPH_RULES = {
+ "DT": {word: {"POS": "PRON"} for word in _relative_pronouns},
+ "IN": {word: {"POS": "SCONJ"} for word in _subordinating_conjunctions},
+ "NN": {
+ "something": {"POS": "PRON"},
+ "anyone": {"POS": "PRON"},
+ "anything": {"POS": "PRON"},
+ "nothing": {"POS": "PRON"},
+ "someone": {"POS": "PRON"},
+ "everything": {"POS": "PRON"},
+ "everyone": {"POS": "PRON"},
+ "everybody": {"POS": "PRON"},
+ "nobody": {"POS": "PRON"},
+ "somebody": {"POS": "PRON"},
+ "anybody": {"POS": "PRON"},
+ "any1": {"POS": "PRON"},
+ },
"PRP": {
"I": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
@@ -15,14 +99,16 @@ MORPH_RULES = {
},
"me": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
"Case": "Acc",
},
- "you": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two"},
+ "you": {LEMMA: PRON_LEMMA, "POS": "PRON", "PronType": "Prs", "Person": "Two"},
"he": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -31,6 +117,7 @@ MORPH_RULES = {
},
"him": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -39,6 +126,7 @@ MORPH_RULES = {
},
"she": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -47,6 +135,7 @@ MORPH_RULES = {
},
"her": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -55,6 +144,7 @@ MORPH_RULES = {
},
"it": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -62,6 +152,7 @@ MORPH_RULES = {
},
"we": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
@@ -69,6 +160,7 @@ MORPH_RULES = {
},
"us": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
@@ -76,6 +168,7 @@ MORPH_RULES = {
},
"they": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
@@ -83,6 +176,7 @@ MORPH_RULES = {
},
"them": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
@@ -90,6 +184,7 @@ MORPH_RULES = {
},
"mine": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
@@ -98,6 +193,7 @@ MORPH_RULES = {
},
"his": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -107,6 +203,7 @@ MORPH_RULES = {
},
"hers": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -116,6 +213,7 @@ MORPH_RULES = {
},
"its": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -125,6 +223,7 @@ MORPH_RULES = {
},
"ours": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
@@ -133,6 +232,7 @@ MORPH_RULES = {
},
"yours": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Two",
"Number": "Plur",
@@ -141,6 +241,7 @@ MORPH_RULES = {
},
"theirs": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
@@ -149,6 +250,7 @@ MORPH_RULES = {
},
"myself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Sing",
@@ -157,6 +259,7 @@ MORPH_RULES = {
},
"yourself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Two",
"Case": "Acc",
@@ -164,6 +267,7 @@ MORPH_RULES = {
},
"himself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -173,6 +277,7 @@ MORPH_RULES = {
},
"herself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -182,6 +287,7 @@ MORPH_RULES = {
},
"itself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -191,6 +297,7 @@ MORPH_RULES = {
},
"themself": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Sing",
@@ -199,6 +306,7 @@ MORPH_RULES = {
},
"ourselves": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "One",
"Number": "Plur",
@@ -207,6 +315,7 @@ MORPH_RULES = {
},
"yourselves": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Two",
"Case": "Acc",
@@ -214,6 +323,7 @@ MORPH_RULES = {
},
"themselves": {
LEMMA: PRON_LEMMA,
+ "POS": "PRON",
"PronType": "Prs",
"Person": "Three",
"Number": "Plur",
@@ -269,9 +379,17 @@ MORPH_RULES = {
"Poss": "Yes",
},
},
+ "RB": {word: {"POS": "PART"} for word in ["not", "n't", "nt", "n’t"]},
+ "VB": {
+ word: {"POS": "AUX"}
+ for word in ["be", "have", "do", "get", "of", "am", "are", "'ve"]
+ },
+ "VBN": {"been": {LEMMA: "be", "POS": "AUX"}},
+ "VBG": {"being": {LEMMA: "be", "POS": "AUX"}},
"VBZ": {
"am": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "One",
"Tense": "Pres",
@@ -279,6 +397,7 @@ MORPH_RULES = {
},
"are": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "Two",
"Tense": "Pres",
@@ -286,6 +405,7 @@ MORPH_RULES = {
},
"is": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "Three",
"Tense": "Pres",
@@ -293,6 +413,7 @@ MORPH_RULES = {
},
"'re": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "Two",
"Tense": "Pres",
@@ -300,26 +421,65 @@ MORPH_RULES = {
},
"'s": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "Three",
"Tense": "Pres",
"Mood": "Ind",
},
+ "has": {LEMMA: "have", "POS": "AUX"},
+ "does": {LEMMA: "do", "POS": "AUX"},
},
"VBP": {
- "are": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"},
- "'re": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"},
+ "are": {
+ LEMMA: "be",
+ "POS": "AUX",
+ "VerbForm": "Fin",
+ "Tense": "Pres",
+ "Mood": "Ind",
+ },
+ "'re": {
+ LEMMA: "be",
+ "POS": "AUX",
+ "VerbForm": "Fin",
+ "Tense": "Pres",
+ "Mood": "Ind",
+ },
"am": {
LEMMA: "be",
+ "POS": "AUX",
"VerbForm": "Fin",
"Person": "One",
"Tense": "Pres",
"Mood": "Ind",
},
+ "do": {"POS": "AUX"},
+ "have": {"POS": "AUX"},
+ "'m": {"POS": "AUX", LEMMA: "be"},
+ "'ve": {"POS": "AUX"},
+ "'re": {"POS": "AUX", LEMMA: "be"},
+ "'s": {"POS": "AUX"},
+ "is": {"POS": "AUX"},
+ "'d": {"POS": "AUX"},
},
"VBD": {
- "was": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Past", "Number": "Sing"},
- "were": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Past", "Number": "Plur"},
+ "was": {
+ LEMMA: "be",
+ "POS": "AUX",
+ "VerbForm": "Fin",
+ "Tense": "Past",
+ "Number": "Sing",
+ },
+ "were": {
+ LEMMA: "be",
+ "POS": "AUX",
+ "VerbForm": "Fin",
+ "Tense": "Past",
+ "Number": "Plur",
+ },
+ "did": {LEMMA: "do", "POS": "AUX"},
+ "had": {LEMMA: "have", "POS": "AUX"},
+ "'d": {LEMMA: "have", "POS": "AUX"},
},
}
diff --git a/spacy/lang/en/tag_map.py b/spacy/lang/en/tag_map.py
index 67f43c53c..246258f57 100644
--- a/spacy/lang/en/tag_map.py
+++ b/spacy/lang/en/tag_map.py
@@ -2,7 +2,7 @@
from __future__ import unicode_literals
from ...symbols import POS, PUNCT, SYM, ADJ, CCONJ, NUM, DET, ADV, ADP, X, VERB
-from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON
+from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON, AUX
TAG_MAP = {
@@ -20,15 +20,15 @@ TAG_MAP = {
"CC": {POS: CCONJ, "ConjType": "coor"},
"CD": {POS: NUM, "NumType": "card"},
"DT": {POS: DET},
- "EX": {POS: ADV, "AdvType": "ex"},
+ "EX": {POS: PRON, "AdvType": "ex"},
"FW": {POS: X, "Foreign": "yes"},
"HYPH": {POS: PUNCT, "PunctType": "dash"},
"IN": {POS: ADP},
"JJ": {POS: ADJ, "Degree": "pos"},
"JJR": {POS: ADJ, "Degree": "comp"},
"JJS": {POS: ADJ, "Degree": "sup"},
- "LS": {POS: PUNCT, "NumType": "ord"},
- "MD": {POS: VERB, "VerbType": "mod"},
+ "LS": {POS: X, "NumType": "ord"},
+ "MD": {POS: AUX, "VerbType": "mod"},
"NIL": {POS: ""},
"NN": {POS: NOUN, "Number": "sing"},
"NNP": {POS: PROPN, "NounType": "prop", "Number": "sing"},
@@ -37,11 +37,11 @@ TAG_MAP = {
"PDT": {POS: DET, "AdjType": "pdt", "PronType": "prn"},
"POS": {POS: PART, "Poss": "yes"},
"PRP": {POS: PRON, "PronType": "prs"},
- "PRP$": {POS: DET, "PronType": "prs", "Poss": "yes"},
+ "PRP$": {POS: PRON, "PronType": "prs", "Poss": "yes"},
"RB": {POS: ADV, "Degree": "pos"},
"RBR": {POS: ADV, "Degree": "comp"},
"RBS": {POS: ADV, "Degree": "sup"},
- "RP": {POS: PART},
+ "RP": {POS: ADP},
"SP": {POS: SPACE},
"SYM": {POS: SYM},
"TO": {POS: PART, "PartType": "inf", "VerbForm": "inf"},
@@ -58,9 +58,9 @@ TAG_MAP = {
"Number": "sing",
"Person": 3,
},
- "WDT": {POS: DET, "PronType": "int|rel"},
+ "WDT": {POS: PRON, "PronType": "int|rel"},
"WP": {POS: PRON, "PronType": "int|rel"},
- "WP$": {POS: DET, "Poss": "yes", "PronType": "int|rel"},
+ "WP$": {POS: PRON, "Poss": "yes", "PronType": "int|rel"},
"WRB": {POS: ADV, "PronType": "int|rel"},
"ADD": {POS: X},
"NFP": {POS: PUNCT},
diff --git a/spacy/tests/regression/test_issue3356.py b/spacy/tests/regression/test_issue3356.py
new file mode 100644
index 000000000..4e27055c7
--- /dev/null
+++ b/spacy/tests/regression/test_issue3356.py
@@ -0,0 +1,70 @@
+import pytest
+import re
+from ... import compat
+
+prefix_search = (
+ b"^\xc2\xa7|^%|^=|^\xe2\x80\x94|^\xe2\x80\x93|^\\+(?![0-9])"
+ b"|^\xe2\x80\xa6|^\xe2\x80\xa6\xe2\x80\xa6|^,|^:|^;|^\\!|^\\?"
+ b"|^\xc2\xbf|^\xd8\x9f|^\xc2\xa1|^\\(|^\\)|^\\[|^\\]|^\\{|^\\}"
+ b"|^<|^>|^_|^#|^\\*|^&|^\xe3\x80\x82|^\xef\xbc\x9f|^\xef\xbc\x81|"
+ b"^\xef\xbc\x8c|^\xe3\x80\x81|^\xef\xbc\x9b|^\xef\xbc\x9a|"
+ b"^\xef\xbd\x9e|^\xc2\xb7|^\xe0\xa5\xa4|^\xd8\x8c|^\xd8\x9b|"
+ b"^\xd9\xaa|^\\.\\.+|^\xe2\x80\xa6|^\\'|^\"|^\xe2\x80\x9d|"
+ b"^\xe2\x80\x9c|^`|^\xe2\x80\x98|^\xc2\xb4|^\xe2\x80\x99|"
+ b"^\xe2\x80\x9a|^,|^\xe2\x80\x9e|^\xc2\xbb|^\xc2\xab|^\xe3\x80\x8c|"
+ b"^\xe3\x80\x8d|^\xe3\x80\x8e|^\xe3\x80\x8f|^\xef\xbc\x88|"
+ b"^\xef\xbc\x89|^\xe3\x80\x94|^\xe3\x80\x95|^\xe3\x80\x90|"
+ b"^\xe3\x80\x91|^\xe3\x80\x8a|^\xe3\x80\x8b|^\xe3\x80\x88|"
+ b"^\xe3\x80\x89|^\\$|^\xc2\xa3|^\xe2\x82\xac|^\xc2\xa5|^\xe0\xb8\xbf|"
+ b"^US\\$|^C\\$|^A\\$|^\xe2\x82\xbd|^\xef\xb7\xbc|^\xe2\x82\xb4|"
+ b"^[\\u00A6\\u00A9\\u00AE\\u00B0\\u0482\\u058D\\u058E\\u060E\\u060F"
+ b"\\u06DE\\u06E9\\u06FD\\u06FE\\u07F6\\u09FA\\u0B70\\u0BF3-\\u0BF8"
+ b"\\u0BFA\\u0C7F\\u0D4F\\u0D79\\u0F01-\\u0F03\\u0F13\\u0F15-\\u0F17"
+ b"\\u0F1A-\\u0F1F\\u0F34\\u0F36\\u0F38\\u0FBE-\\u0FC5\\u0FC7-\\u0FCC"
+ b"\\u0FCE\\u0FCF\\u0FD5-\\u0FD8\\u109E\\u109F\\u1390-\\u1399\\u1940"
+ b"\\u19DE-\\u19FF\\u1B61-\\u1B6A\\u1B74-\\u1B7C\\u2100\\u2101\\u2103"
+ b"-\\u2106\\u2108\\u2109\\u2114\\u2116\\u2117\\u211E-\\u2123\\u2125"
+ b"\\u2127\\u2129\\u212E\\u213A\\u213B\\u214A\\u214C\\u214D\\u214F"
+ b"\\u218A\\u218B\\u2195-\\u2199\\u219C-\\u219F\\u21A1\\u21A2\\u21A4"
+ b"\\u21A5\\u21A7-\\u21AD\\u21AF-\\u21CD\\u21D0\\u21D1\\u21D3\\u21D5"
+ b"-\\u21F3\\u2300-\\u2307\\u230C-\\u231F\\u2322-\\u2328\\u232B"
+ b"-\\u237B\\u237D-\\u239A\\u23B4-\\u23DB\\u23E2-\\u2426\\u2440"
+ b"-\\u244A\\u249C-\\u24E9\\u2500-\\u25B6\\u25B8-\\u25C0\\u25C2"
+ b"-\\u25F7\\u2600-\\u266E\\u2670-\\u2767\\u2794-\\u27BF\\u2800"
+ b"-\\u28FF\\u2B00-\\u2B2F\\u2B45\\u2B46\\u2B4D-\\u2B73\\u2B76"
+ b"-\\u2B95\\u2B98-\\u2BC8\\u2BCA-\\u2BFE\\u2CE5-\\u2CEA\\u2E80"
+ b"-\\u2E99\\u2E9B-\\u2EF3\\u2F00-\\u2FD5\\u2FF0-\\u2FFB\\u3004"
+ b"\\u3012\\u3013\\u3020\\u3036\\u3037\\u303E\\u303F\\u3190\\u3191"
+ b"\\u3196-\\u319F\\u31C0-\\u31E3\\u3200-\\u321E\\u322A-\\u3247\\u3250"
+ b"\\u3260-\\u327F\\u328A-\\u32B0\\u32C0-\\u32FE\\u3300-\\u33FF\\u4DC0"
+ b"-\\u4DFF\\uA490-\\uA4C6\\uA828-\\uA82B\\uA836\\uA837\\uA839\\uAA77"
+ b"-\\uAA79\\uFDFD\\uFFE4\\uFFE8\\uFFED\\uFFEE\\uFFFC\\uFFFD\\U00010137"
+ b"-\\U0001013F\\U00010179-\\U00010189\\U0001018C-\\U0001018E"
+ b"\\U00010190-\\U0001019B\\U000101A0\\U000101D0-\\U000101FC\\U00010877"
+ b"\\U00010878\\U00010AC8\\U0001173F\\U00016B3C-\\U00016B3F\\U00016B45"
+ b"\\U0001BC9C\\U0001D000-\\U0001D0F5\\U0001D100-\\U0001D126\\U0001D129"
+ b"-\\U0001D164\\U0001D16A-\\U0001D16C\\U0001D183\\U0001D184\\U0001D18C"
+ b"-\\U0001D1A9\\U0001D1AE-\\U0001D1E8\\U0001D200-\\U0001D241\\U0001D245"
+ b"\\U0001D300-\\U0001D356\\U0001D800-\\U0001D9FF\\U0001DA37-\\U0001DA3A"
+ b"\\U0001DA6D-\\U0001DA74\\U0001DA76-\\U0001DA83\\U0001DA85\\U0001DA86"
+ b"\\U0001ECAC\\U0001F000-\\U0001F02B\\U0001F030-\\U0001F093\\U0001F0A0"
+ b"-\\U0001F0AE\\U0001F0B1-\\U0001F0BF\\U0001F0C1-\\U0001F0CF\\U0001F0D1"
+ b"-\\U0001F0F5\\U0001F110-\\U0001F16B\\U0001F170-\\U0001F1AC\\U0001F1E6"
+ b"-\\U0001F202\\U0001F210-\\U0001F23B\\U0001F240-\\U0001F248\\U0001F250"
+ b"\\U0001F251\\U0001F260-\\U0001F265\\U0001F300-\\U0001F3FA\\U0001F400"
+ b"-\\U0001F6D4\\U0001F6E0-\\U0001F6EC\\U0001F6F0-\\U0001F6F9\\U0001F700"
+ b"-\\U0001F773\\U0001F780-\\U0001F7D8\\U0001F800-\\U0001F80B\\U0001F810"
+ b"-\\U0001F847\\U0001F850-\\U0001F859\\U0001F860-\\U0001F887\\U0001F890"
+ b"-\\U0001F8AD\\U0001F900-\\U0001F90B\\U0001F910-\\U0001F93E\\U0001F940"
+ b"-\\U0001F970\\U0001F973-\\U0001F976\\U0001F97A\\U0001F97C-\\U0001F9A2"
+ b"\\U0001F9B0-\\U0001F9B9\\U0001F9C0-\\U0001F9C2\\U0001F9D0-\\U0001F9FF"
+ b"\\U0001FA60-\\U0001FA6D]"
+)
+
+
+if compat.is_python2:
+ # If we have this test in Python 3, pytest chokes, as it can't print the
+ # string above in the xpass message.
+ def test_issue3356():
+ pattern = re.compile(compat.unescape_unicode(prefix_search.decode("utf8")))
+ assert not pattern.search(u"hello")
diff --git a/spacy/tokenizer.pyx b/spacy/tokenizer.pyx
index 86c2d6ad3..e390a72b9 100644
--- a/spacy/tokenizer.pyx
+++ b/spacy/tokenizer.pyx
@@ -14,6 +14,7 @@ import re
from .tokens.doc cimport Doc
from .strings cimport hash_string
+from .compat import unescape_unicode
from .errors import Errors, Warnings, deprecation_warning
from . import util
@@ -428,6 +429,9 @@ cdef class Tokenizer:
))
exclude = util.get_serialization_exclude(deserializers, exclude, kwargs)
msg = util.from_bytes(bytes_data, deserializers, exclude)
+ for key in ["prefix_search", "suffix_search", "infix_finditer"]:
+ if key in data:
+ data[key] = unescape_unicode(data[key])
if data.get("prefix_search"):
self.prefix_search = re.compile(data["prefix_search"]).search
if data.get("suffix_search"):
diff --git a/website/src/widgets/landing.js b/website/src/widgets/landing.js
index 062307642..f7e9ce790 100644
--- a/website/src/widgets/landing.js
+++ b/website/src/widgets/landing.js
@@ -218,7 +218,7 @@ const Landing = ({ data }) => {
Benchmarks
In 2015, independent researchers from Emory University and Yahoo! Labs
- showed that spaCy offered the
+ showed that spaCy offered the{' '}
fastest syntactic parser in the world and that its accuracy
was within 1% of the best available (