From c21efea9bb1d3e92ba16695190eae27e53e1d5e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ole=20Henrik=20Skogstr=C3=B8m?= <oleskogstrom@gmail.com>
Date: Fri, 6 Jul 2018 15:54:15 +0200
Subject: [PATCH] Add sent property to token (#2521)

* Add sent property to token

* Refactored and cleaned up copy paste errors.
---
 spacy/tests/doc/test_token_api.py | 16 ++++++++++++++++
 spacy/tokens/token.pyx            |  7 +++++++
 2 files changed, 23 insertions(+)

diff --git a/spacy/tests/doc/test_token_api.py b/spacy/tests/doc/test_token_api.py
index e81d5b7be..7ed27f989 100644
--- a/spacy/tests/doc/test_token_api.py
+++ b/spacy/tests/doc/test_token_api.py
@@ -56,6 +56,14 @@ def test_doc_token_api_str_builtin(en_tokenizer, text):
     assert str(tokens[0]) == text.split(' ')[0]
     assert str(tokens[1]) == text.split(' ')[1]
 
+@pytest.fixture
+def doc(en_tokenizer):
+    text = "This is a sentence. This is another sentence. And a third."
+    heads = [1, 0, 1, -2, -3, 1, 0, 1, -2, -3, 0, 1, -2, -1]
+    deps = ['nsubj', 'ROOT', 'det', 'attr', 'punct', 'nsubj', 'ROOT', 'det',
+            'attr', 'punct', 'ROOT', 'det', 'npadvmod', 'punct']
+    tokens = en_tokenizer(text)
+    return get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)
 
 def test_doc_token_api_is_properties(en_vocab):
     text = ["Hi", ",", "my", "email", "is", "test@me.com"]
@@ -162,3 +170,11 @@ def test_is_sent_start(en_tokenizer):
     assert doc[5].is_sent_start is True
     doc.is_parsed = True
     assert len(list(doc.sents)) == 2
+
+def test_tokens_sent(doc):
+    """Test token.sent property"""
+    assert len(list(doc.sents)) == 3
+    assert doc[1].sent.text == 'This is a sentence .'
+    assert doc[7].sent.text == 'This is another sentence .'
+    assert doc[1].sent.root.left_edge.text == 'This'
+    assert doc[7].sent.root.left_edge.text == 'This'
diff --git a/spacy/tokens/token.pyx b/spacy/tokens/token.pyx
index a0f1bf9d3..bd8f29859 100644
--- a/spacy/tokens/token.pyx
+++ b/spacy/tokens/token.pyx
@@ -356,6 +356,13 @@ cdef class Token:
         def __get__(self):
             return self.c.r_kids
 
+    property sent:
+        """RETURNS (Span): The sentence span that the token is a part of."""
+        def __get__(self):
+            if 'sent' in self.doc.user_token_hooks:
+                return self.doc.user_token_hooks['sent'](self)
+            return self.doc[self.i : self.i+1].sent
+
     property sent_start:
         def __get__(self):
             # Raising a deprecation warning here causes errors for autocomplete