Merge branch 'master' into spacy.io

spacy/tests/regression/test_issue1001-1500.py

@@ -13,6 +13,28 @@ from spacy.lemmatizer import Lemmatizer
 from spacy.symbols import ORTH, LEMMA, POS, VERB, VerbForm_part
 
 
+@pytest.mark.xfail
+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.Defaults.create_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.Defaults.create_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.xfail(
     reason="g is split of as a unit, as the suffix regular expression can not look back further (variable-width)"
 )

website/src/components/link.js

@@ -8,6 +8,8 @@ import Icon from './icon'
 import classes from '../styles/link.module.sass'
 import { isString } from './util'
 
+const internalRegex = /(http(s?)):\/\/(prodi.gy|spacy.io|irl.spacy.io)/gi
+
 const Whitespace = ({ children }) => (
     // Ensure that links are always wrapped in spaces
     <> {children} </>
@@ -68,13 +70,15 @@ const Link = ({
             </Wrapper>
         )
     }
+    const isInternal = internalRegex.test(dest)
+    const rel = isInternal ? null : 'noopener nofollow noreferrer'
     return (
         <Wrapper>
             <OutboundLink
                 href={dest}
                 className={linkClassNames}
                 target="_blank"
-                rel="noopener nofollow noreferrer"
+                rel={rel}
                 {...other}
             >
                 {content}