Merge branch 'master' of https://github.com/explosion/spaCy

website/api/_top-level/_displacy.jade

@@ -25,7 +25,7 @@ p
 +table(["Name", "Type", "Description", "Default"])
     +row
         +cell #[code docs]
-        +cell list or #[code Doc]
+        +cell list, #[code Doc], #[code Span]
         +cell Document(s) to visualize.
         +cell
 
@@ -84,7 +84,7 @@ p Render a dependency parse tree or named entity visualization.
 +table(["Name", "Type", "Description", "Default"])
     +row
         +cell #[code docs]
-        +cell list or #[code Doc]
+        +cell list, #[code Doc], #[code Span]
         +cell Document(s) to visualize.
         +cell
 
@@ -157,6 +157,12 @@ p
             |  as it prevents long arcs to attach punctuation.
         +cell #[code True]
 
+    +row
+        +cell #[code collapse_phrases]
+        +cell bool
+        +cell Merge noun phrases into one token.
+        +cell #[code False]
+
     +row
         +cell #[code compact]
         +cell bool

website/api/cli.jade

@@ -136,6 +136,12 @@ p
         +cell flag
         +cell Print information as Markdown.
 
+    +row
+        +cell #[code --silent], #[code -s]
+            +tag-new("2.0.12")
+        +cell flag
+        +cell Don't print anything, just return the values.
+
     +row
         +cell #[code --help], #[code -h]
         +cell flag

website/api/doc.jade

@@ -202,8 +202,8 @@ p
 
 +aside-code("Example").
     from spacy.tokens import Doc
-    Doc.set_extension('is_city', default=False)
+    Doc.set_extension('has_city', default=False)
-    extension = Doc.get_extension('is_city')
+    extension = Doc.get_extension('has_city')
     assert extension == (False, None, None, None)
 
 +table(["Name", "Type", "Description"])
@@ -227,8 +227,8 @@ p Check whether an extension has been registered on the #[code Doc] class.
 
 +aside-code("Example").
     from spacy.tokens import Doc
-    Doc.set_extension('is_city', default=False)
+    Doc.set_extension('has_city', default=False)
-    assert Doc.has_extension('is_city')
+    assert Doc.has_extension('has_city')
 
 +table(["Name", "Type", "Description"])
     +row
@@ -241,6 +241,31 @@ p Check whether an extension has been registered on the #[code Doc] class.
         +cell bool
         +cell Whether the extension has been registered.
 
++h(2, "remove_extension") Doc.remove_extension
+    +tag classmethod
+    +tag-new("2.0.12")
+
+p Remove a previously registered extension.
+
++aside-code("Example").
+    from spacy.tokens import Doc
+    Doc.set_extension('has_city', default=False)
+    removed = Doc.remove_extension('has_city')
+    assert not Doc.has_extension('has_city')
+
++table(["Name", "Type", "Description"])
+    +row
+        +cell #[code name]
+        +cell unicode
+        +cell Name of the extension.
+
+    +row("foot")
+        +cell returns
+        +cell tuple
+        +cell
+            |  A #[code.u-break (default, method, getter, setter)] tuple of the
+            |  removed extension.
+
 +h(2, "char_span") Doc.char_span
     +tag method
     +tag-new(2)
@@ -761,6 +786,13 @@ p
         +cell bool
         +cell A flag indicating that the document has been syntactically parsed.
 
+    +row
+        +cell #[code is_sentenced]
+        +cell bool
+        +cell
+            |  A flag indicating that sentence boundaries have been applied to
+            |  the document.
+
     +row
         +cell #[code sentiment]
         +cell float

website/api/span.jade

@@ -219,6 +219,31 @@ p Check whether an extension has been registered on the #[code Span] class.
         +cell bool
         +cell Whether the extension has been registered.
 
++h(2, "remove_extension") Span.remove_extension
+    +tag classmethod
+    +tag-new("2.0.12")
+
+p Remove a previously registered extension.
+
++aside-code("Example").
+    from spacy.tokens import Span
+    Span.set_extension('is_city', default=False)
+    removed = Span.remove_extension('is_city')
+    assert not Span.has_extension('is_city')
+
++table(["Name", "Type", "Description"])
+    +row
+        +cell #[code name]
+        +cell unicode
+        +cell Name of the extension.
+
+    +row("foot")
+        +cell returns
+        +cell tuple
+        +cell
+            |  A #[code.u-break (default, method, getter, setter)] tuple of the
+            |  removed extension.
+
 +h(2, "similarity") Span.similarity
     +tag method
     +tag-model("vectors")

website/api/token.jade

@@ -154,6 +154,31 @@ p Check whether an extension has been registered on the #[code Token] class.
         +cell bool
         +cell Whether the extension has been registered.
 
++h(2, "remove_extension") Token.remove_extension
+    +tag classmethod
+    +tag-new("2.0.11")
+
+p Remove a previously registered extension.
+
++aside-code("Example").
+    from spacy.tokens import Token
+    Token.set_extension('is_fruit', default=False)
+    removed = Token.remove_extension('is_fruit')
+    assert not Token.has_extension('is_fruit')
+
++table(["Name", "Type", "Description"])
+    +row
+        +cell #[code name]
+        +cell unicode
+        +cell Name of the extension.
+
+    +row("foot")
+        +cell returns
+        +cell tuple
+        +cell
+            |  A #[code.u-break (default, method, getter, setter)] tuple of the
+            |  removed extension.
+
 +h(2, "check_flag") Token.check_flag
     +tag method
 
@@ -484,6 +509,17 @@ p The L2 norm of the token's vector representation.
 +h(2, "attributes") Attributes
 
 +table(["Name", "Type", "Description"])
+    +row
+        +cell #[code doc]
+        +cell #[code Doc]
+        +cell The parent document.
+
+    +row
+        +cell #[code sent]
+            +tag-new("2.0.12")
+        +cell #[code Span]
+        +cell The sentence span that this token is a part of.
+
     +row
         +cell #[code text]
         +cell unicode

website/models/_data.json

@@ -76,6 +76,7 @@
     },
 
     "MODEL_LICENSES": {
+        "MIT":             "https://opensource.org/licenses/MIT",
         "CC BY 4.0":       "https://creativecommons.org/licenses/by/4.0/",
         "CC BY-SA":        "https://creativecommons.org/licenses/by-sa/3.0/",
         "CC BY-SA 3.0":    "https://creativecommons.org/licenses/by-sa/3.0/",
@@ -115,8 +116,12 @@
         "ro": "Romanian",
         "hr": "Croatian",
         "tr": "Turkish",
+        "el": "Greek",
         "he": "Hebrew",
+        "ar": "Arabic",
         "fa": "Persian",
+        "ur": "Urdu",
+        "tt": "Tatar",
         "ga": "Irish",
         "bn": "Bengali",
         "hi": "Hindi",

website/usage/_models/_languages.jade

@@ -44,7 +44,7 @@ p
 
     +list.o-no-block
         +item #[strong Chinese]: #[+a("https://github.com/fxsjy/jieba") Jieba]
-        +item #[strong Japanese]: #[+a("https://github.com/mocobeta/janome") Janome]
+        +item #[strong Japanese]: #[+a("https://github.com/taku910/mecab") MeCab]
         +item #[strong Thai]: #[+a("https://github.com/wannaphongcom/pythainlp") pythainlp]
         +item #[strong Vietnamese]: #[+a("https://github.com/trungtv/pyvi") Pyvi]
         +item #[strong Russian]: #[+a("https://github.com/kmike/pymorphy2") pymorphy2]