From 275c9ad872a87c4ba131987656be4861617d3d90 Mon Sep 17 00:00:00 2001
From: adrianeboyd <adrianeboyd@gmail.com>
Date: Wed, 16 Oct 2019 13:40:18 +0200
Subject: [PATCH] Allow int values in token patterns (#4444)

* Add missing int value option to top-level pattern validation in Matcher

* Adjust existing tests accordingly

* Add new test for valid pattern `{"LENGTH": int}`
---
 spacy/matcher/matcher.pyx                      | 2 +-
 spacy/tests/matcher/test_pattern_validation.py | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/spacy/matcher/matcher.pyx b/spacy/matcher/matcher.pyx
index 4a5f69ff4..5dd6eab77 100644
--- a/spacy/matcher/matcher.pyx
+++ b/spacy/matcher/matcher.pyx
@@ -658,7 +658,7 @@ def _get_attr_values(spec, string_store):
             value = string_store.add(value)
         elif isinstance(value, bool):
             value = int(value)
-        elif isinstance(value, dict):
+        elif isinstance(value, (dict, int)):
             continue
         else:
             raise ValueError(Errors.E153.format(vtype=type(value).__name__))
diff --git a/spacy/tests/matcher/test_pattern_validation.py b/spacy/tests/matcher/test_pattern_validation.py
index 665bcf935..80f08e40c 100644
--- a/spacy/tests/matcher/test_pattern_validation.py
+++ b/spacy/tests/matcher/test_pattern_validation.py
@@ -12,24 +12,25 @@ from spacy.util import get_json_validator, validate_json
 TEST_PATTERNS = [
     # Bad patterns flagged in all cases
     ([{"XX": "foo"}], 1, 1),
-    ([{"LENGTH": "2", "TEXT": 2}, {"LOWER": "test"}], 2, 1),
     ([{"IS_ALPHA": {"==": True}}, {"LIKE_NUM": None}], 2, 1),
     ([{"IS_PUNCT": True, "OP": "$"}], 1, 1),
-    ([{"IS_DIGIT": -1}], 1, 1),
-    ([{"ORTH": -1}], 1, 1),
     ([{"_": "foo"}], 1, 1),
     ('[{"TEXT": "foo"}, {"LOWER": "bar"}]', 1, 1),
     ([1, 2, 3], 3, 1),
     # Bad patterns flagged outside of Matcher
     ([{"_": {"foo": "bar", "baz": {"IN": "foo"}}}], 1, 0),
     # Bad patterns not flagged with minimal checks
+    ([{"LENGTH": "2", "TEXT": 2}, {"LOWER": "test"}], 2, 0),
     ([{"LENGTH": {"IN": [1, 2, "3"]}}, {"POS": {"IN": "VERB"}}], 2, 0),
     ([{"LENGTH": {"VALUE": 5}}], 1, 0),
     ([{"TEXT": {"VALUE": "foo"}}], 1, 0),
+    ([{"IS_DIGIT": -1}], 1, 0),
+    ([{"ORTH": -1}], 1, 0),
     # Good patterns
     ([{"TEXT": "foo"}, {"LOWER": "bar"}], 0, 0),
     ([{"LEMMA": {"IN": ["love", "like"]}}, {"POS": "DET", "OP": "?"}], 0, 0),
     ([{"LIKE_NUM": True, "LENGTH": {">=": 5}}], 0, 0),
+    ([{"LENGTH": 2}], 0, 0),
     ([{"LOWER": {"REGEX": "^X", "NOT_IN": ["XXX", "XY"]}}], 0, 0),
     ([{"NORM": "a"}, {"POS": {"IN": ["NOUN"]}}], 0, 0),
     ([{"_": {"foo": {"NOT_IN": ["bar", "baz"]}, "a": 5, "b": {">": 10}}}], 0, 0),