Update v2.2.x for bugfix release (#6384)

* Fix on_match callback and remove empty patterns (#6312)

For the `DependencyMatcher`:

* Fix on_match callback so that it is called once per matched pattern
* Fix results so that patterns with empty match lists are not returned

* Add --prefer-binary for python 3.5

* Add version pins for pyrsistent

* Use backwards-compatible super()

* Try to fix tests on Travis (2.7)

* Fix naming conflict and formatting

* Update pkuseg version in Chinese tokenizer warnings

* Some changes for Armenian (#5616)

* Fixing numericals

* We need a Armenian question sign to make the sentence a question

* Update lex_attrs.py (#5608)

* Fix compat

* Update Armenian from v2.3.x

Co-authored-by: Ines Montani <ines@ines.io>
Co-authored-by: Karen Hambardzumyan <mahnerak@gmail.com>
Co-authored-by: Marat M. Yavrumyan <myavrum@ysu.am>

azure-pipelines.yml

@@ -80,8 +80,8 @@ jobs:
       architecture: 'x64'
 
   - script: |
-      python -m pip install -U setuptools
-      pip install -r requirements.txt
+      python -m pip install -U pip setuptools
+      pip install -r requirements.txt --prefer-binary
     displayName: 'Install dependencies'
 
   - script: |
@@ -96,7 +96,7 @@ jobs:
 
   - bash: |
       SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
-      pip install dist/$SDIST
+      pip install dist/$SDIST --prefer-binary
     displayName: 'Install from sdist'
 
   - script: python -m pytest --pyargs spacy

requirements.txt

@@ -14,6 +14,7 @@ plac>=0.9.6,<1.2.0
 pathlib==1.0.1; python_version < "3.4"
 tqdm>=4.38.0,<5.0.0
 # Optional dependencies
+pyrsistent<0.17.0
 jsonschema>=2.6.0,<3.1.0
 # Development dependencies
 cython>=0.25

spacy/errors.py

@@ -7,8 +7,8 @@ def add_codes(err_cls):
 
     class ErrorsWithCodes(err_cls):
         def __getattribute__(self, code):
-            msg = super().__getattribute__(code)
-            if code.startswith('__'):  # python system attributes like __class__
+            msg = super(ErrorsWithCodes, self).__getattribute__(code)
+            if code.startswith("__"):  # python system attributes like __class__
                 return msg
             else:
                 return "[{code}] {msg}".format(code=code, msg=msg)

spacy/lang/hy/__init__.py

@@ -1,11 +1,12 @@
+# coding: utf8
+from __future__ import unicode_literals
+
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
 from .tag_map import TAG_MAP
 
-
 from ...attrs import LANG
 from ...language import Language
-from ...tokens import Doc
 
 
 class ArmenianDefaults(Language.Defaults):

spacy/lang/hy/examples.py

@@ -1,6 +1,6 @@
+# coding: utf8
 from __future__ import unicode_literals
 
-
 """
 Example sentences to test spaCy and its language models.
 >>> from spacy.lang.hy.examples import sentences
@@ -11,6 +11,6 @@
 sentences = [
     "Լոնդոնը Միացյալ Թագավորության մեծ քաղաք է։",
     "Ո՞վ է Ֆրանսիայի նախագահը։",
-    "Որն է Միացյալ Նահանգների մայրաքաղաքը։",
+    "Ո՞րն է Միացյալ Նահանգների մայրաքաղաքը։",
     "Ե՞րբ է ծնվել Բարաք Օբաման։",
 ]

spacy/lang/hy/lex_attrs.py

@@ -1,11 +1,12 @@
+# coding: utf8
 from __future__ import unicode_literals
 
 from ...attrs import LIKE_NUM
 
 
 _num_words = [
-    "զրօ",
-    "մէկ",
+    "զրո",
+    "մեկ",
     "երկու",
     "երեք",
     "չորս",
@@ -17,20 +18,21 @@
     "տասը",
     "տասնմեկ",
     "տասներկու",
-    "տասն­երեք",
-    "տասն­չորս",
-    "տասն­հինգ",
-    "տասն­վեց",
-    "տասն­յոթ",
-    "տասն­ութ",
-    "տասն­ինը",
-    "քսան" "երեսուն",
+    "տասներեք",
+    "տասնչորս",
+    "տասնհինգ",
+    "տասնվեց",
+    "տասնյոթ",
+    "տասնութ",
+    "տասնինը",
+    "քսան",
+    "երեսուն",
     "քառասուն",
     "հիսուն",
-    "վաթցսուն",
+    "վաթսուն",
     "յոթանասուն",
     "ութսուն",
-    "ինիսուն",
+    "իննսուն",
     "հարյուր",
     "հազար",
     "միլիոն",

spacy/lang/hy/stop_words.py

@@ -1,6 +1,6 @@
+# coding: utf8
 from __future__ import unicode_literals
 
-
 STOP_WORDS = set(
     """
 նա
@@ -105,6 +105,6 @@
 յուրաքանչյուր
 այս
 մեջ
-թ	
+թ
 """.split()
 )