Add doc.is_sentenced attribute, re #1959

spacy/tokens/doc.pyx

@@ -186,6 +186,20 @@ cdef class Doc:
     def _(self):
         return Underscore(Underscore.doc_extensions, self)
 
+    @property
+    def is_sentenced(self):
+        # Check if the document has sentence boundaries,
+        # i.e at least one tok has the sent_start in (-1, 1)
+        if 'sents' in self.user_hooks:
+            return True
+        if self.is_parsed:
+            return True
+        for i in range(self.length):
+            if self.c[i].sent_start == -1 or self.c[i].sent_start == 1:
+                return True
+        else:
+            return False
+
     def __getitem__(self, object i):
         """Get a `Token` or `Span` object.
 
@@ -515,29 +529,23 @@ cdef class Doc:
             >>> assert [s.root.text for s in doc.sents] == ["is", "'s"]
         """
         def __get__(self):
+            if not self.is_sentenced:
+                raise ValueError(
+                    "Sentence boundaries unset. You can add the 'sentencizer' "
+                    "component to the pipeline with: "
+                    "nlp.add_pipe(nlp.create_pipe('sentencizer')) "
+                    "Alternatively, add the dependency parser, or set "
+                    "sentence boundaries by setting doc[i].sent_start")
             if 'sents' in self.user_hooks:
                 yield from self.user_hooks['sents'](self)
-                return
+            else:
-
+                start = 0
-            cdef int i
-            if not self.is_parsed:
                 for i in range(1, self.length):
-                    if self.c[i].sent_start != 0:
+                    if self.c[i].sent_start == 1:
-                        break
+                        yield Span(self, start, i)
-                else:
+                        start = i
-                    raise ValueError(
+                if start != self.length:
-                        "Sentence boundaries unset. You can add the 'sentencizer' "
+                    yield Span(self, start, self.length)
-                        "component to the pipeline with: "
-                        "nlp.add_pipe(nlp.create_pipe('sentencizer')) "
-                        "Alternatively, add the dependency parser, or set "
-                        "sentence boundaries by setting doc[i].sent_start")
-            start = 0
-            for i in range(1, self.length):
-                if self.c[i].sent_start == 1:
-                    yield Span(self, start, i)
-                    start = i
-            if start != self.length:
-                yield Span(self, start, self.length)
 
     cdef int push_back(self, LexemeOrToken lex_or_tok, bint has_space) except -1:
         if self.length == 0:

spacy/tokens/span.pyx

@@ -300,17 +300,7 @@ cdef class Span:
                     if n >= self.doc.length:
                         raise RuntimeError
                 return self.doc[root.l_edge:root.r_edge + 1]
-            else:
+            elif self.doc.is_sentenced:
-                # Check if the document has sentence boundaries,
-                # i.e at least one tok has the sent_start == 1
-                for i in range(self.doc.length):
-                    if self.doc.c[i].sent_start == 1:
-                        break
-                else:
-                    raise ValueError(
-                        "Access to sentence requires either the dependency parse "
-                        "or sentence boundaries to be set by setting " +
-                        "doc[i].is_sent_start = True")
                 # find start of the sentence
                 start = self.start
                 while self.doc.c[start].sent_start != 1 and start > 0:
@@ -323,7 +313,11 @@ cdef class Span:
                         break
                 #
                 return self.doc[start:end]
-
+            else:
+                raise ValueError(
+                    "Access to sentence requires either the dependency parse "
+                    "or sentence boundaries to be set by setting " +
+                    "doc[i].is_sent_start = True")
 
     property has_vector:
         """RETURNS (bool): Whether a word vector is associated with the object.