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

spacy/symbols.pxd

@@ -13,12 +13,12 @@ cdef enum symbol_t:
     LIKE_EMAIL
     IS_STOP
     IS_OOV
+    IS_BRACKET
+    IS_QUOTE
+    IS_LEFT_PUNCT
+    IS_RIGHT_PUNCT
 
-    FLAG14 = 14
+    FLAG18 = 18
-    FLAG15
-    FLAG16
-    FLAG17
-    FLAG18
     FLAG19
     FLAG20
     FLAG21
@@ -455,15 +455,5 @@ cdef enum symbol_t:
     root
     xcomp
 
-# Move these up to FLAG14--FLAG18 once we finish the functionality
+    acl
-# and are ready to regenerate the model.
+    LAW
-#IS_BRACKET
-#IS_QUOTE
-#IS_LEFT_PUNCT
-#IS_RIGHT_PUNCT
-
-# These symbols are currently missing. However, if we add them currently,
-# we'll throw off the integer index and the model will have to be retrained.
-# We therefore wait until the next data version to add them.
-# acl
-

spacy/symbols.pyx

@@ -18,10 +18,11 @@ IDS = {
     "LIKE_EMAIL": LIKE_EMAIL,
     "IS_STOP": IS_STOP,
     "IS_OOV": IS_OOV,
-    "FLAG14": FLAG14,
+    "IS_BRACKET": IS_BRACKET,
-    "FLAG15": FLAG15,
+    "IS_QUOTE": IS_QUOTE,
-    "FLAG16": FLAG16,
+    "IS_LEFT_PUNCT": IS_LEFT_PUNCT,
-    "FLAG17": FLAG17,
+    "IS_RIGHT_PUNCT": IS_RIGHT_PUNCT,
+
     "FLAG18": FLAG18,
     "FLAG19": FLAG19,
     "FLAG20": FLAG20,
@@ -457,7 +458,10 @@ IDS = {
     "quantmod": quantmod,
     "rcmod": rcmod,
     "root": root,
-    "xcomp": xcomp
+    "xcomp": xcomp,
+
+    "acl": acl,
+    "LAW": LAW
 }
 
 def sort_nums(x):

website/api/_annotation/_named-entities.jade

@@ -37,6 +37,10 @@
         +cell #[code WORK_OF_ART]
         +cell Titles of books, songs, etc.
 
+    +row
+        +cell #[code LAW]
+        +cell Named documents made into laws.
+
     +row
         +cell #[code LANGUAGE]
         +cell Any named language.

website/api/token.jade

@@ -586,6 +586,16 @@ p The L2 norm of the token's vector representation.
         +cell bool
         +cell Is the token punctuation?
 
+    +row
+        +cell #[code is_left_punct]
+        +cell bool
+        +cell Is the token a left punctuation mark, e.g. #[code (]?
+
+    +row
+        +cell #[code is_right_punct]
+        +cell bool
+        +cell Is the token a right punctuation mark, e.g. #[code )]?
+
     +row
         +cell #[code is_space]
         +cell bool
@@ -593,6 +603,16 @@ p The L2 norm of the token's vector representation.
             |  Does the token consist of whitespace characters? Equivalent to
             |  #[code token.text.isspace()].
 
+    +row
+        +cell #[code is_bracket]
+        +cell bool
+        +cell Is the token a bracket?
+
+    +row
+        +cell #[code is_quote]
+        +cell bool
+        +cell Is the token a quotation mark?
+
     +row
         +cell #[code like_url]
         +cell bool