Merge branch 'master' into spacy.io

spacy/lang/ko/__init__.py

@@ -58,7 +58,8 @@ def check_spaces(text, tokens):
             yield prev_end != idx
         prev_end = idx + len(token)
         start = prev_end
-    yield False
+    if start > 0:
+        yield False
 
 
 class KoreanTokenizer(DummyTokenizer):

spacy/tests/lang/ko/test_tokenizer.py

@@ -45,3 +45,8 @@ def test_ko_tokenizer_full_tags(ko_tokenizer, text, expected_tags):
 def test_ko_tokenizer_pos(ko_tokenizer, text, expected_pos):
     pos = [token.pos_ for token in ko_tokenizer(text)]
     assert pos == expected_pos.split()
+
+
+def test_ko_empty_doc(ko_tokenizer):
+    tokens = ko_tokenizer("")
+    assert len(tokens) == 0

website/docs/usage/linguistic-features.md

@@ -26,6 +26,14 @@ import PosDeps101 from 'usage/101/\_pos-deps.md'
 
 <PosDeps101 />
 
+<Infobox title="📖 Part-of-speech tag scheme">
+
+For a list of the fine-grained and coarse-grained part-of-speech tags assigned
+by spaCy's models across different languages, see the
+[POS tag scheme documentation](/api/annotation#pos-tagging).
+
+</Infobox>
+
 ### Rule-based morphology {#rule-based-morphology}
 
 Inflectional morphology is the process by which a root form of a word is
@@ -62,13 +70,6 @@ of the two. The system works as follows:
    lemmatizer also accepts list-based exception files, acquired from
    [WordNet](https://wordnet.princeton.edu/).
    
-<Infobox title="📖 Part-of-speech tag scheme">
-
-For a list of the fine-grained and coarse-grained part-of-speech tags assigned
-by spaCy's models across different languages, see the
-[POS tag scheme documentation](/api/annotation#pos-tagging).
-
-</Infobox>
 
 ## Dependency Parsing {#dependency-parse model="parser"}
 
@@ -289,7 +290,7 @@ for token in doc:
 
 For a list of the syntactic dependency labels assigned by spaCy's models across
 different languages, see the
-[dependency label scheme documentation](/api/annotation#pos-tagging).
+[dependency label scheme documentation](/api/annotation#dependency-parsing).
 
 </Infobox>