From 4bb6bc3f9e0c2eff374f4690c8674a0eb23287b0 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Fri, 25 Aug 2017 20:03:14 -0500
Subject: [PATCH] Add support for sent_start to GoldParse

---
 spacy/gold.pxd | 1 +
 spacy/gold.pyx | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/spacy/gold.pxd b/spacy/gold.pxd
index 5873b23ac..a1550b1ef 100644
--- a/spacy/gold.pxd
+++ b/spacy/gold.pxd
@@ -9,6 +9,7 @@ cdef struct GoldParseC:
     int* tags
     int* heads
     int* has_dep
+    int* sent_start
     attr_t* labels
     int** brackets
     Transition* ner
diff --git a/spacy/gold.pyx b/spacy/gold.pyx
index 096f265a9..f00d04109 100644
--- a/spacy/gold.pyx
+++ b/spacy/gold.pyx
@@ -426,6 +426,7 @@ cdef class GoldParse:
         self.c.heads = <int*>self.mem.alloc(len(doc), sizeof(int))
         self.c.labels = <attr_t*>self.mem.alloc(len(doc), sizeof(attr_t))
         self.c.has_dep = <int*>self.mem.alloc(len(doc), sizeof(int))
+        self.c.sent_start = <int*>self.mem.alloc(len(doc), sizeof(int))
         self.c.ner = <Transition*>self.mem.alloc(len(doc), sizeof(Transition))
 
         self.cats = list(cats)
@@ -482,6 +483,10 @@ cdef class GoldParse:
         """
         return not nonproj.is_nonproj_tree(self.heads)
 
+    @property
+    def sent_starts(self):
+        return [self.c.sent_start[i] for i in range(self.length)]
+
 
 def biluo_tags_from_offsets(doc, entities, missing='O'):
     """Encode labelled spans into per-token tags, using the Begin/In/Last/Unit/Out